diff --git a/.mailmap b/.mailmap index 08b80428f583..52489f564069 100644 --- a/.mailmap +++ b/.mailmap @@ -21,6 +21,7 @@ Andrey Ryabinin Andrew Morton Andrew Vasquez Andy Adamson +Antoine Tenart Antonio Ospite Archit Taneja Arnaud Patard @@ -30,6 +31,9 @@ Axel Lin Ben Gardner Ben M Cahill Björn Steinbrink +Boris Brezillon +Boris Brezillon +Boris Brezillon Brian Avery Brian King Christoph Hellwig @@ -89,6 +93,7 @@ Leonid I Ananiev Linas Vepstas Mark Brown Matthieu CASTET +Mauro Carvalho Chehab Mayuresh Janorkar Michael Buesch Michel Dänzer @@ -122,6 +127,7 @@ Santosh Shilimkar Sascha Hauer S.Çağlar Onur Shiraz Hashim +Shuah Khan Simon Kelley Stéphane Witzmann Stephen Hemminger diff --git a/CREDITS b/CREDITS index 0f0bf22afe0c..2a3fbcd229e6 100644 --- a/CREDITS +++ b/CREDITS @@ -649,6 +649,7 @@ D: Configure, Menuconfig, xconfig N: Mauro Carvalho Chehab E: m.chehab@samsung.org +E: mchehab@osg.samsung.com E: mchehab@infradead.org D: Media subsystem (V4L/DVB) drivers and core D: EDAC drivers and EDAC 3.0 core rework diff --git a/Documentation/ABI/testing/configfs-usb-gadget-uvc b/Documentation/ABI/testing/configfs-usb-gadget-uvc index 2f4a0051b32d..1ba0d0fda9c0 100644 --- a/Documentation/ABI/testing/configfs-usb-gadget-uvc +++ b/Documentation/ABI/testing/configfs-usb-gadget-uvc @@ -1,6 +1,6 @@ What: /config/usb-gadget/gadget/functions/uvc.name Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: UVC function directory streaming_maxburst - 0..15 (ss only) @@ -9,37 +9,37 @@ Description: UVC function directory What: /config/usb-gadget/gadget/functions/uvc.name/control Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Control descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/class Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Class descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/class/ss Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Super speed control class descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/class/fs Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Full speed control class descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Terminal descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal/output Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Output terminal descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal/output/default Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Default output terminal descriptors All attributes read only: @@ -53,12 +53,12 @@ Description: Default output terminal descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal/camera Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Camera terminal descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/terminal/camera/default Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Default camera terminal descriptors All attributes read only: @@ -75,12 +75,12 @@ Description: Default camera terminal descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/processing Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Processing unit descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/processing/default Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Default processing unit descriptors All attributes read only: @@ -94,49 +94,49 @@ Description: Default processing unit descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/header Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Control header descriptors What: /config/usb-gadget/gadget/functions/uvc.name/control/header/name Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Specific control header descriptors dwClockFrequency bcdUVC What: /config/usb-gadget/gadget/functions/uvc.name/streaming Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Streaming descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/class Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Streaming class descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/class/ss Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Super speed streaming class descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/class/hs Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: High speed streaming class descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/class/fs Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Full speed streaming class descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/color_matching Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Color matching descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/color_matching/default Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Default color matching descriptors All attributes read only: @@ -150,12 +150,12 @@ Description: Default color matching descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: MJPEG format descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg/name Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Specific MJPEG format descriptors All attributes read only, @@ -174,7 +174,7 @@ Description: Specific MJPEG format descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/mjpeg/name/name Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Specific MJPEG frame descriptors dwFrameInterval - indicates how frame interval can be @@ -196,12 +196,12 @@ Description: Specific MJPEG frame descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Uncompressed format descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed/name Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Specific uncompressed format descriptors bmaControls - this format's data for bmaControls in @@ -221,7 +221,7 @@ Description: Specific uncompressed format descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/uncompressed/name/name Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Specific uncompressed frame descriptors dwFrameInterval - indicates how frame interval can be @@ -243,12 +243,12 @@ Description: Specific uncompressed frame descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/header Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Streaming header descriptors What: /config/usb-gadget/gadget/functions/uvc.name/streaming/header/name Date: Dec 2014 -KernelVersion: 3.20 +KernelVersion: 4.0 Description: Specific streaming header descriptors All attributes read only: diff --git a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 index 6708c5e264aa..33e96f740639 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 +++ b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 @@ -1,4 +1,4 @@ -What /sys/bus/iio/devices/iio:deviceX/in_proximity_raw +What /sys/bus/iio/devices/iio:deviceX/in_proximity_input Date: March 2014 KernelVersion: 3.15 Contact: Matt Ranostay diff --git a/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt b/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt index 96c25ee01501..6532a59c9b43 100644 --- a/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt +++ b/Documentation/devicetree/bindings/display/bridge/adi,adv7511.txt @@ -1,13 +1,19 @@ -Analog Device ADV7511(W)/13 HDMI Encoders +Analog Device ADV7511(W)/13/33 HDMI Encoders ----------------------------------------- -The ADV7511, ADV7511W and ADV7513 are HDMI audio and video transmitters +The ADV7511, ADV7511W, ADV7513 and ADV7533 are HDMI audio and video transmitters compatible with HDMI 1.4 and DVI 1.0. They support color space conversion, -S/PDIF, CEC and HDCP. +S/PDIF, CEC and HDCP. ADV7533 supports the DSI interface for input pixels, while +the others support RGB interface. Required properties: -- compatible: Should be one of "adi,adv7511", "adi,adv7511w" or "adi,adv7513" +- compatible: Should be one of: + "adi,adv7511" + "adi,adv7511w" + "adi,adv7513" + "adi,adv7533" + - reg: I2C slave address The ADV7511 supports a large number of input data formats that differ by their @@ -32,6 +38,11 @@ The following input format properties are required except in "rgb 1x" and - adi,input-justification: The input bit justification ("left", "evenly", "right"). +The following properties are required for ADV7533: + +- adi,dsi-lanes: Number of DSI data lanes connected to the DSI host. It should + be one of 1, 2, 3 or 4. + Optional properties: - interrupts: Specifier for the ADV7511 interrupt @@ -42,13 +53,18 @@ Optional properties: - adi,embedded-sync: The input uses synchronization signals embedded in the data stream (similar to BT.656). Defaults to separate H/V synchronization signals. +- adi,disable-timing-generator: Only for ADV7533. Disables the internal timing + generator. The chip will rely on the sync signals in the DSI data lanes, + rather than generate its own timings for HDMI output. Required nodes: The ADV7511 has two video ports. Their connections are modelled using the OF graph bindings specified in Documentation/devicetree/bindings/graph.txt. -- Video port 0 for the RGB or YUV input +- Video port 0 for the RGB, YUV or DSI input. In the case of ADV7533, the + remote endpoint phandle should be a reference to a valid mipi_dsi_host device + node. - Video port 1 for the HDMI output diff --git a/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt b/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt index 4f2ba8c13d92..4a0f4f7682ad 100644 --- a/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt +++ b/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt @@ -5,6 +5,7 @@ Required properties for dp-controller: platform specific such as: * "samsung,exynos5-dp" * "rockchip,rk3288-dp" + * "rockchip,rk3399-edp" -reg: physical base address of the controller and length of memory mapped region. diff --git a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.txt b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.txt new file mode 100644 index 000000000000..e3f6aa6a214d --- /dev/null +++ b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.txt @@ -0,0 +1,53 @@ +Toshiba TC358767 eDP bridge bindings + +Required properties: + - compatible: "toshiba,tc358767" + - reg: i2c address of the bridge, 0x68 or 0x0f, depending on bootstrap pins + - clock-names: should be "ref" + - clocks: OF device-tree clock specification for refclk input. The reference + clock rate must be 13 MHz, 19.2 MHz, 26 MHz, or 38.4 MHz. + +Optional properties: + - shutdown-gpios: OF device-tree gpio specification for SD pin + (active high shutdown input) + - reset-gpios: OF device-tree gpio specification for RSTX pin + (active low system reset) + - ports: the ports node can contain video interface port nodes to connect + to a DPI/DSI source and to an eDP/DP sink according to [1][2]: + - port@0: DSI input port + - port@1: DPI input port + - port@2: eDP/DP output port + +[1]: Documentation/devicetree/bindings/graph.txt +[2]: Documentation/devicetree/bindings/media/video-interfaces.txt + +Example: + edp-bridge@68 { + compatible = "toshiba,tc358767"; + reg = <0x68>; + shutdown-gpios = <&gpio3 23 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>; + clock-names = "ref"; + clocks = <&edp_refclk>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@1 { + reg = <1>; + + bridge_in: endpoint { + remote-endpoint = <&dpi_out>; + }; + }; + + port@2 { + reg = <2>; + + bridge_out: endpoint { + remote-endpoint = <&panel_in>; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/display/fsl,dcu.txt b/Documentation/devicetree/bindings/display/fsl,dcu.txt index ae55cde1b69e..63ec2a624aa9 100644 --- a/Documentation/devicetree/bindings/display/fsl,dcu.txt +++ b/Documentation/devicetree/bindings/display/fsl,dcu.txt @@ -12,7 +12,7 @@ Required properties: - clock-names: Should be "dcu" and "pix" See ../clocks/clock-bindings.txt for details. - big-endian Boolean property, LS1021A DCU registers are big-endian. -- fsl,panel: The phandle to panel node. +- port Video port for the panel output Optional properties: - fsl,tcon: The phandle to the timing controller node. @@ -24,6 +24,11 @@ dcu: dcu@2ce0000 { clocks = <&platform_clk 0>, <&platform_clk 0>; clock-names = "dcu", "pix"; big-endian; - fsl,panel = <&panel>; fsl,tcon = <&tcon>; + + port { + dcu_out: endpoint { + remote-endpoint = <&panel_out>; + }; + }; }; diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt index f5948c48b9a2..6b1cab17f52d 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi.txt +++ b/Documentation/devicetree/bindings/display/msm/dsi.txt @@ -11,8 +11,7 @@ Required properties: be 0 or 1, since we have 2 DSI controllers at most for now. - interrupts: The interrupt signal from the DSI block. - power-domains: Should be <&mmcc MDSS_GDSC>. -- clocks: device clocks - See Documentation/devicetree/bindings/clocks/clock-bindings.txt for details. +- clocks: Phandles to device clocks. - clock-names: the following clocks are required: * "mdp_core_clk" * "iface_clk" @@ -23,16 +22,21 @@ Required properties: * "core_clk" For DSIv2, we need an additional clock: * "src_clk" +- assigned-clocks: Parents of "byte_clk" and "pixel_clk" for the given platform. +- assigned-clock-parents: The Byte clock and Pixel clock PLL outputs provided + by a DSI PHY block. See [1] for details on clock bindings. - vdd-supply: phandle to vdd regulator device node - vddio-supply: phandle to vdd-io regulator device node - vdda-supply: phandle to vdda regulator device node -- qcom,dsi-phy: phandle to DSI PHY device node +- phys: phandle to DSI PHY device node +- phy-names: the name of the corresponding PHY device - syscon-sfpb: A phandle to mmss_sfpb syscon node (only for DSIv2) +- ports: Contains 2 DSI controller ports as child nodes. Each port contains + an endpoint subnode as defined in [2] and [3]. Optional properties: - panel@0: Node of panel connected to this DSI controller. - See files in Documentation/devicetree/bindings/display/panel/ for each supported - panel. + See files in [4] for each supported panel. - qcom,dual-dsi-mode: Boolean value indicating if the DSI controller is driving a panel which needs 2 DSI links. - qcom,master-dsi: Boolean value indicating if the DSI controller is driving @@ -44,34 +48,38 @@ Optional properties: - pinctrl-names: the pin control state names; should contain "default" - pinctrl-0: the default pinctrl state (active) - pinctrl-n: the "sleep" pinctrl state -- port: DSI controller output port, containing one endpoint subnode. +- ports: contains DSI controller input and output ports as children, each + containing one endpoint subnode. DSI Endpoint properties: - - remote-endpoint: set to phandle of the connected panel's endpoint. - See Documentation/devicetree/bindings/graph.txt for device graph info. - - qcom,data-lane-map: this describes how the logical DSI lanes are mapped - to the physical lanes on the given platform. The value contained in - index n describes what logical data lane is mapped to the physical data - lane n (DATAn, where n lies between 0 and 3). + - remote-endpoint: For port@0, set to phandle of the connected panel/bridge's + input endpoint. For port@1, set to the MDP interface output. See [2] for + device graph info. + + - data-lanes: this describes how the physical DSI data lanes are mapped + to the logical lanes on the given platform. The value contained in + index n describes what physical lane is mapped to the logical lane n + (DATAn, where n lies between 0 and 3). The clock lane position is fixed + and can't be changed. Hence, they aren't a part of the DT bindings. See + [3] for more info on the data-lanes property. For example: - qcom,data-lane-map = <3 0 1 2>; + data-lanes = <3 0 1 2>; - The above mapping describes that the logical data lane DATA3 is mapped to - the physical data lane DATA0, logical DATA0 to physical DATA1, logic DATA1 - to phys DATA2 and logic DATA2 to phys DATA3. + The above mapping describes that the logical data lane DATA0 is mapped to + the physical data lane DATA3, logical DATA1 to physical DATA0, logic DATA2 + to phys DATA1 and logic DATA3 to phys DATA2. There are only a limited number of physical to logical mappings possible: - - "0123": Logic 0->Phys 0; Logic 1->Phys 1; Logic 2->Phys 2; Logic 3->Phys 3; - "3012": Logic 3->Phys 0; Logic 0->Phys 1; Logic 1->Phys 2; Logic 2->Phys 3; - "2301": Logic 2->Phys 0; Logic 3->Phys 1; Logic 0->Phys 2; Logic 1->Phys 3; - "1230": Logic 1->Phys 0; Logic 2->Phys 1; Logic 3->Phys 2; Logic 0->Phys 3; - "0321": Logic 0->Phys 0; Logic 3->Phys 1; Logic 2->Phys 2; Logic 1->Phys 3; - "1032": Logic 1->Phys 0; Logic 0->Phys 1; Logic 3->Phys 2; Logic 2->Phys 3; - "2103": Logic 2->Phys 0; Logic 1->Phys 1; Logic 0->Phys 2; Logic 3->Phys 3; - "3210": Logic 3->Phys 0; Logic 2->Phys 1; Logic 1->Phys 2; Logic 0->Phys 3; + <0 1 2 3> + <1 2 3 0> + <2 3 0 1> + <3 0 1 2> + <0 3 2 1> + <1 0 3 2> + <2 1 0 3> + <3 2 1 0> DSI PHY: Required properties: @@ -86,11 +94,12 @@ Required properties: * "dsi_pll" * "dsi_phy" * "dsi_phy_regulator" +- clock-cells: Must be 1. The DSI PHY block acts as a clock provider, creating + 2 clocks: A byte clock (index 0), and a pixel clock (index 1). - qcom,dsi-phy-index: The ID of DSI PHY hardware instance. This should be 0 or 1, since we have 2 DSI PHYs at most for now. - power-domains: Should be <&mmcc MDSS_GDSC>. -- clocks: device clocks - See Documentation/devicetree/bindings/clocks/clock-bindings.txt for details. +- clocks: Phandles to device clocks. See [1] for details on clock bindings. - clock-names: the following clocks are required: * "iface_clk" - vddio-supply: phandle to vdd-io regulator device node @@ -99,11 +108,16 @@ Optional properties: - qcom,dsi-phy-regulator-ldo-mode: Boolean value indicating if the LDO mode PHY regulator is wanted. +[1] Documentation/devicetree/bindings/clocks/clock-bindings.txt +[2] Documentation/devicetree/bindings/graph.txt +[3] Documentation/devicetree/bindings/media/video-interfaces.txt +[4] Documentation/devicetree/bindings/display/panel/ + Example: - mdss_dsi0: qcom,mdss_dsi@fd922800 { + dsi0: dsi@fd922800 { compatible = "qcom,mdss-dsi-ctrl"; qcom,dsi-host-index = <0>; - interrupt-parent = <&mdss_mdp>; + interrupt-parent = <&mdp>; interrupts = <4 0>; reg-names = "dsi_ctrl"; reg = <0xfd922800 0x200>; @@ -124,19 +138,48 @@ Example: <&mmcc MDSS_AHB_CLK>, <&mmcc MDSS_MDP_CLK>, <&mmcc MDSS_PCLK0_CLK>; + + assigned-clocks = + <&mmcc BYTE0_CLK_SRC>, + <&mmcc PCLK0_CLK_SRC>; + assigned-clock-parents = + <&dsi_phy0 0>, + <&dsi_phy0 1>; + vdda-supply = <&pma8084_l2>; vdd-supply = <&pma8084_l22>; vddio-supply = <&pma8084_l12>; - qcom,dsi-phy = <&mdss_dsi_phy0>; + phys = <&dsi_phy0>; + phy-names ="dsi-phy"; qcom,dual-dsi-mode; qcom,master-dsi; qcom,sync-dual-dsi; pinctrl-names = "default", "sleep"; - pinctrl-0 = <&mdss_dsi_active>; - pinctrl-1 = <&mdss_dsi_suspend>; + pinctrl-0 = <&dsi_active>; + pinctrl-1 = <&dsi_suspend>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + dsi0_in: endpoint { + remote-endpoint = <&mdp_intf1_out>; + }; + }; + + port@1 { + reg = <1>; + dsi0_out: endpoint { + remote-endpoint = <&panel_in>; + data-lanes = <0 1 2 3>; + }; + }; + }; panel: panel@0 { compatible = "sharp,lq101r1sx01"; @@ -152,16 +195,9 @@ Example: }; }; }; - - port { - dsi0_out: endpoint { - remote-endpoint = <&panel_in>; - lanes = <0 1 2 3>; - }; - }; }; - mdss_dsi_phy0: qcom,mdss_dsi_phy@fd922a00 { + dsi_phy0: dsi-phy@fd922a00 { compatible = "qcom,dsi-phy-28nm-hpm"; qcom,dsi-phy-index = <0>; reg-names = @@ -173,6 +209,7 @@ Example: <0xfd922d80 0x7b>; clock-names = "iface_clk"; clocks = <&mmcc MDSS_AHB_CLK>; + #clock-cells = <1>; vddio-supply = <&pma8084_l12>; qcom,dsi-phy-regulator-ldo-mode; diff --git a/Documentation/devicetree/bindings/display/msm/mdp.txt b/Documentation/devicetree/bindings/display/msm/mdp.txt deleted file mode 100644 index a214f6cd0363..000000000000 --- a/Documentation/devicetree/bindings/display/msm/mdp.txt +++ /dev/null @@ -1,59 +0,0 @@ -Qualcomm adreno/snapdragon display controller - -Required properties: -- compatible: - * "qcom,mdp4" - mdp4 - * "qcom,mdp5" - mdp5 -- reg: Physical base address and length of the controller's registers. -- interrupts: The interrupt signal from the display controller. -- connectors: array of phandles for output device(s) -- clocks: device clocks - See ../clocks/clock-bindings.txt for details. -- clock-names: the following clocks are required. - For MDP4: - * "core_clk" - * "iface_clk" - * "lut_clk" - * "src_clk" - * "hdmi_clk" - * "mdp_clk" - For MDP5: - * "bus_clk" - * "iface_clk" - * "core_clk_src" - * "core_clk" - * "lut_clk" (some MDP5 versions may not need this) - * "vsync_clk" - -Optional properties: -- gpus: phandle for gpu device -- clock-names: the following clocks are optional: - * "lut_clk" - -Example: - -/ { - ... - - mdp: qcom,mdp@5100000 { - compatible = "qcom,mdp4"; - reg = <0x05100000 0xf0000>; - interrupts = ; - connectors = <&hdmi>; - gpus = <&gpu>; - clock-names = - "core_clk", - "iface_clk", - "lut_clk", - "src_clk", - "hdmi_clk", - "mdp_clk"; - clocks = - <&mmcc MDP_SRC>, - <&mmcc MDP_AHB_CLK>, - <&mmcc MDP_LUT_CLK>, - <&mmcc TV_SRC>, - <&mmcc HDMI_TV_CLK>, - <&mmcc MDP_TV_CLK>; - }; -}; diff --git a/Documentation/devicetree/bindings/display/msm/mdp4.txt b/Documentation/devicetree/bindings/display/msm/mdp4.txt new file mode 100644 index 000000000000..3c341a15ccdc --- /dev/null +++ b/Documentation/devicetree/bindings/display/msm/mdp4.txt @@ -0,0 +1,112 @@ +Qualcomm adreno/snapdragon MDP4 display controller + +Description: + +This is the bindings documentation for the MDP4 display controller found in +SoCs like MSM8960, APQ8064 and MSM8660. + +Required properties: +- compatible: + * "qcom,mdp4" - mdp4 +- reg: Physical base address and length of the controller's registers. +- interrupts: The interrupt signal from the display controller. +- clocks: device clocks + See ../clocks/clock-bindings.txt for details. +- clock-names: the following clocks are required. + * "core_clk" + * "iface_clk" + * "bus_clk" + * "lut_clk" + * "hdmi_clk" + * "tv_clk" +- ports: contains the list of output ports from MDP. These connect to interfaces + that are external to the MDP hardware, such as HDMI, DSI, EDP etc (LVDS is a + special case since it is a part of the MDP block itself). + + 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 + + The output port mappings are: + Port 0 -> LCDC/LVDS + Port 1 -> DSI1 Cmd/Video + Port 2 -> DSI2 Cmd/Video + Port 3 -> DTV + +Optional properties: +- clock-names: the following clocks are optional: + * "lut_clk" + +Example: + +/ { + ... + + hdmi: hdmi@4a00000 { + ... + ports { + ... + port@0 { + reg = <0>; + hdmi_in: endpoint { + remote-endpoint = <&mdp_dtv_out>; + }; + }; + ... + }; + ... + }; + + ... + + mdp: mdp@5100000 { + compatible = "qcom,mdp4"; + reg = <0x05100000 0xf0000>; + interrupts = ; + clock-names = + "core_clk", + "iface_clk", + "lut_clk", + "hdmi_clk", + "tv_clk"; + clocks = + <&mmcc MDP_CLK>, + <&mmcc MDP_AHB_CLK>, + <&mmcc MDP_AXI_CLK>, + <&mmcc MDP_LUT_CLK>, + <&mmcc HDMI_TV_CLK>, + <&mmcc MDP_TV_CLK>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + mdp_lvds_out: endpoint { + }; + }; + + port@1 { + reg = <1>; + mdp_dsi1_out: endpoint { + }; + }; + + port@2 { + reg = <2>; + mdp_dsi2_out: endpoint { + }; + }; + + port@3 { + reg = <3>; + mdp_dtv_out: endpoint { + remote-endpoint = <&hdmi_in>; + }; + }; + }; + }; +}; diff --git a/Documentation/devicetree/bindings/display/msm/mdp5.txt b/Documentation/devicetree/bindings/display/msm/mdp5.txt new file mode 100644 index 000000000000..30c11ea83754 --- /dev/null +++ b/Documentation/devicetree/bindings/display/msm/mdp5.txt @@ -0,0 +1,160 @@ +Qualcomm adreno/snapdragon MDP5 display controller + +Description: + +This is the bindings documentation for the Mobile Display Subsytem(MDSS) that +encapsulates sub-blocks like MDP5, DSI, HDMI, eDP etc, and the MDP5 display +controller found in SoCs like MSM8974, APQ8084, MSM8916, MSM8994 and MSM8996. + +MDSS: +Required properties: +- compatible: + * "qcom,mdss" - MDSS +- reg: Physical base address and length of the controller's registers. +- reg-names: The names of register regions. The following regions are required: + * "mdss_phys" + * "vbif_phys" +- interrupts: The 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. +- power-domains: a power domain consumer specifier according to + Documentation/devicetree/bindings/power/power_domain.txt +- clocks: device clocks. See ../clocks/clock-bindings.txt for details. +- clock-names: the following clocks are required. + * "iface_clk" + * "bus_clk" + * "vsync_clk" +- #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: +- clock-names: the following clocks are optional: + * "lut_clk" + +MDP5: +Required properties: +- compatible: + * "qcom,mdp5" - MDP5 +- reg: Physical base address and length of the controller's registers. +- reg-names: The names of register regions. The following regions are required: + * "mdp_phys" +- interrupts: Interrupt line from MDP5 to MDSS interrupt controller. +- interrupt-parent: phandle to the MDSS block + through MDP block +- clocks: device clocks. See ../clocks/clock-bindings.txt for details. +- clock-names: the following clocks are required. +- * "bus_clk" +- * "iface_clk" +- * "core_clk" +- * "vsync_clk" +- ports: contains the list of output ports from MDP. These connect to interfaces + that are external to the MDP hardware, such as HDMI, DSI, EDP etc (LVDS is a + special case since it is a part of the MDP block itself). + + 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 + + The availability of output ports can vary across SoC revisions: + + For MSM8974 and APQ8084: + Port 0 -> MDP_INTF0 (eDP) + Port 1 -> MDP_INTF1 (DSI1) + Port 2 -> MDP_INTF2 (DSI2) + Port 3 -> MDP_INTF3 (HDMI) + + For MSM8916: + Port 0 -> MDP_INTF1 (DSI1) + + For MSM8994 and MSM8996: + Port 0 -> MDP_INTF1 (DSI1) + Port 1 -> MDP_INTF2 (DSI2) + Port 2 -> MDP_INTF3 (HDMI) + +Optional properties: +- clock-names: the following clocks are optional: + * "lut_clk" + +Example: + +/ { + ... + + mdss: mdss@1a00000 { + compatible = "qcom,mdss"; + reg = <0x1a00000 0x1000>, + <0x1ac8000 0x3000>; + reg-names = "mdss_phys", "vbif_phys"; + + power-domains = <&gcc MDSS_GDSC>; + + clocks = <&gcc GCC_MDSS_AHB_CLK>, + <&gcc GCC_MDSS_AXI_CLK>, + <&gcc GCC_MDSS_VSYNC_CLK>; + clock-names = "iface_clk", + "bus_clk", + "vsync_clk" + + interrupts = <0 72 0>; + + interrupt-controller; + #interrupt-cells = <1>; + + #address-cells = <1>; + #size-cells = <1>; + ranges; + + mdp: mdp@1a01000 { + compatible = "qcom,mdp5"; + reg = <0x1a01000 0x90000>; + reg-names = "mdp_phys"; + + interrupt-parent = <&mdss>; + interrupts = <0 0>; + + clocks = <&gcc GCC_MDSS_AHB_CLK>, + <&gcc GCC_MDSS_AXI_CLK>, + <&gcc GCC_MDSS_MDP_CLK>, + <&gcc GCC_MDSS_VSYNC_CLK>; + clock-names = "iface_clk", + "bus_clk", + "core_clk", + "vsync_clk"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + mdp5_intf1_out: endpoint { + remote-endpoint = <&dsi0_in>; + }; + }; + }; + }; + + dsi0: dsi@1a98000 { + ... + ports { + ... + port@0 { + reg = <0>; + dsi0_in: endpoint { + remote-endpoint = <&mdp5_intf1_out>; + }; + }; + ... + }; + ... + }; + + dsi_phy0: dsi-phy@1a98300 { + ... + }; + }; +}; diff --git a/Documentation/devicetree/bindings/display/panel/lg,lp079qx1-sp0v.txt b/Documentation/devicetree/bindings/display/panel/lg,lp079qx1-sp0v.txt new file mode 100644 index 000000000000..b9877acad012 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/lg,lp079qx1-sp0v.txt @@ -0,0 +1,7 @@ +LG LP079QX1-SP0V 7.9" (1536x2048 pixels) TFT LCD panel + +Required properties: +- compatible: should be "lg,lp079qx1-sp0v" + +This binding is compatible with the simple-panel binding, which is specified +in simple-panel.txt in this directory. diff --git a/Documentation/devicetree/bindings/display/panel/lg,lp097qx1-spa1.txt b/Documentation/devicetree/bindings/display/panel/lg,lp097qx1-spa1.txt new file mode 100644 index 000000000000..42141516f078 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/lg,lp097qx1-spa1.txt @@ -0,0 +1,7 @@ +LG 9.7" (2048x1536 pixels) TFT LCD panel + +Required properties: +- compatible: should be "lg,lp097qx1-spa1" + +This binding is compatible with the simple-panel binding, which is specified +in simple-panel.txt in this directory. diff --git a/Documentation/devicetree/bindings/display/panel/samsung,lsn122dl01-c01.txt b/Documentation/devicetree/bindings/display/panel/samsung,lsn122dl01-c01.txt new file mode 100644 index 000000000000..dba298b43b24 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/samsung,lsn122dl01-c01.txt @@ -0,0 +1,7 @@ +Samsung 12.2" (2560x1600 pixels) TFT LCD panel + +Required properties: +- compatible: should be "samsung,lsn122dl01-c01" + +This binding is compatible with the simple-panel binding, which is specified +in simple-panel.txt in this directory. diff --git a/Documentation/devicetree/bindings/display/panel/sharp,lq101k1ly04.txt b/Documentation/devicetree/bindings/display/panel/sharp,lq101k1ly04.txt new file mode 100644 index 000000000000..4aff25b8dfe6 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/sharp,lq101k1ly04.txt @@ -0,0 +1,7 @@ +Sharp Display Corp. LQ101K1LY04 10.07" WXGA TFT LCD panel + +Required properties: +- compatible: should be "sharp,lq101k1ly04" + +This binding is compatible with the simple-panel binding, which is specified +in simple-panel.txt in this directory. diff --git a/Documentation/devicetree/bindings/display/panel/sharp,lq123p1jx31.txt b/Documentation/devicetree/bindings/display/panel/sharp,lq123p1jx31.txt new file mode 100644 index 000000000000..bcb0e8a29f71 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/sharp,lq123p1jx31.txt @@ -0,0 +1,7 @@ +Sharp 12.3" (2400x1600 pixels) TFT LCD panel + +Required properties: +- compatible: should be "sharp,lq123p1jx31" + +This binding is compatible with the simple-panel binding, which is specified +in simple-panel.txt in this directory. diff --git a/Documentation/devicetree/bindings/display/panel/starry,kr122ea0sra.txt b/Documentation/devicetree/bindings/display/panel/starry,kr122ea0sra.txt new file mode 100644 index 000000000000..1e87fe6078af --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/starry,kr122ea0sra.txt @@ -0,0 +1,7 @@ +Starry 12.2" (1920x1200 pixels) TFT LCD panel + +Required properties: +- compatible: should be "starry,kr122ea0sra" + +This binding is compatible with the simple-panel binding, which is specified +in simple-panel.txt in this directory. diff --git a/Documentation/devicetree/bindings/display/rockchip/analogix_dp-rockchip.txt b/Documentation/devicetree/bindings/display/rockchip/analogix_dp-rockchip.txt index e832ff98fd61..01cced1c2a18 100644 --- a/Documentation/devicetree/bindings/display/rockchip/analogix_dp-rockchip.txt +++ b/Documentation/devicetree/bindings/display/rockchip/analogix_dp-rockchip.txt @@ -2,7 +2,8 @@ Rockchip RK3288 specific extensions to the Analogix Display Port ================================ Required properties: -- compatible: "rockchip,rk3288-edp"; +- compatible: "rockchip,rk3288-dp", + "rockchip,rk3399-edp"; - reg: physical base address of the controller and length @@ -27,6 +28,12 @@ Required properties: Port 0: contained 2 endpoints, connecting to the output of vop. Port 1: contained 1 endpoint, connecting to the input of panel. +Optional property for different chips: +- clocks: from common clock binding: handle to grf_vio clock. + +- clock-names: from common clock binding: + Required elements: "grf" + For the below properties, please refer to Analogix DP binding document: * Documentation/devicetree/bindings/drm/bridge/analogix_dp.txt - phys (required) diff --git a/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.txt b/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.txt index a3bd8c050c4e..0fad7ed2ea19 100644 --- a/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.txt +++ b/Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.txt @@ -208,6 +208,7 @@ of the following host1x client modules: See ../clocks/clock-bindings.txt for details. - clock-names: Must include the following entries: - sor: clock input for the SOR hardware + - source: source clock for the SOR clock - parent: input for the pixel clock - dp: reference clock for the SOR clock - safe: safe reference for the SOR clock during power up @@ -226,9 +227,9 @@ of the following host1x client modules: - nvidia,dpaux: phandle to a DispayPort AUX interface - dpaux: DisplayPort AUX interface - - compatible: For Tegra124, must contain "nvidia,tegra124-dpaux". Otherwise, - must contain '"nvidia,-dpaux", "nvidia,tegra124-dpaux"', where - is tegra132. + - compatible : Should contain one of the following: + - "nvidia,tegra124-dpaux": for Tegra124 and Tegra132 + - "nvidia,tegra210-dpaux": for Tegra210 - reg: Physical base address and length of the controller's registers. - interrupts: The interrupt outputs from the controller. - clocks: Must contain an entry for each entry in clock-names. @@ -241,6 +242,12 @@ of the following host1x client modules: - reset-names: Must include the following entries: - dpaux - vdd-supply: phandle of a supply that powers the DisplayPort link + - i2c-bus: Subnode where I2C slave devices are listed. This subnode + must be always present. If there are no I2C slave devices, an empty + node should be added. See ../../i2c/i2c.txt for more information. + + See ../pinctrl/nvidia,tegra124-dpaux-padctl.txt for information + regarding the DPAUX pad controller bindings. Example: diff --git a/Documentation/devicetree/bindings/hwmon/ina2xx.txt b/Documentation/devicetree/bindings/hwmon/ina2xx.txt index 9bcd5e87830d..02af0d94e921 100644 --- a/Documentation/devicetree/bindings/hwmon/ina2xx.txt +++ b/Documentation/devicetree/bindings/hwmon/ina2xx.txt @@ -7,6 +7,7 @@ Required properties: - "ti,ina220" for ina220 - "ti,ina226" for ina226 - "ti,ina230" for ina230 + - "ti,ina231" for ina231 - reg: I2C address Optional properties: diff --git a/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt b/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt index bfeabb843941..71191ff0e781 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-arb-gpio-challenge.txt @@ -44,8 +44,8 @@ Required properties: - our-claim-gpio: The GPIO that we use to claim the bus. - their-claim-gpios: The GPIOs that the other sides use to claim the bus. Note that some implementations may only support a single other master. -- Standard I2C mux properties. See mux.txt in this directory. -- Single I2C child bus node at reg 0. See mux.txt in this directory. +- Standard I2C mux properties. See i2c-mux.txt in this directory. +- Single I2C child bus node at reg 0. See i2c-mux.txt in this directory. Optional properties: - slew-delay-us: microseconds to wait for a GPIO to go high. Default is 10 us. diff --git a/Documentation/devicetree/bindings/i2c/i2c-demux-pinctrl.txt b/Documentation/devicetree/bindings/i2c/i2c-demux-pinctrl.txt index 6078aefe7ed4..7ce23ac61308 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-demux-pinctrl.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-demux-pinctrl.txt @@ -27,7 +27,8 @@ Required properties: - i2c-bus-name: The name of this bus. Also needed as pinctrl-name for the I2C parents. -Furthermore, I2C mux properties and child nodes. See mux.txt in this directory. +Furthermore, I2C mux properties and child nodes. See i2c-mux.txt in this +directory. Example: diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-gpio.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-gpio.txt index 66709a825541..21da3ecbb370 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-mux-gpio.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-mux-gpio.txt @@ -22,8 +22,8 @@ Required properties: - i2c-parent: The phandle of the I2C bus that this multiplexer's master-side port is connected to. - mux-gpios: list of gpios used to control the muxer -* Standard I2C mux properties. See mux.txt in this directory. -* I2C child bus nodes. See mux.txt in this directory. +* Standard I2C mux properties. See i2c-mux.txt in this directory. +* I2C child bus nodes. See i2c-mux.txt in this directory. Optional properties: - idle-state: value to set the muxer to when idle. When no value is @@ -33,7 +33,7 @@ For each i2c child node, an I2C child bus will be created. They will be numbered based on their order in the device tree. Whenever an access is made to a device on a child bus, the value set -in the revelant node's reg property will be output using the list of +in the relevant node's reg property will be output using the list of GPIOs, the first in the list holding the least-significant value. If an idle state is defined, using the idle-state (optional) property, diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt index ae8af1694e95..33119a98e144 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-mux-pinctrl.txt @@ -28,9 +28,9 @@ Also required are: * Standard pinctrl properties that specify the pin mux state for each child bus. See ../pinctrl/pinctrl-bindings.txt. -* Standard I2C mux properties. See mux.txt in this directory. +* Standard I2C mux properties. See i2c-mux.txt in this directory. -* I2C child bus nodes. See mux.txt in this directory. +* I2C child bus nodes. See i2c-mux.txt in this directory. For each named state defined in the pinctrl-names property, an I2C child bus will be created. I2C child bus numbers are assigned based on the index into diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt index 688783fbe696..de00d7fc450b 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-mux-reg.txt @@ -7,8 +7,8 @@ Required properties: - compatible: i2c-mux-reg - i2c-parent: The phandle of the I2C bus that this multiplexer's master-side port is connected to. -* Standard I2C mux properties. See mux.txt in this directory. -* I2C child bus nodes. See mux.txt in this directory. +* Standard I2C mux properties. See i2c-mux.txt in this directory. +* I2C child bus nodes. See i2c-mux.txt in this directory. Optional properties: - reg: this pair of specifies the register to control the mux. @@ -24,7 +24,7 @@ Optional properties: given, it defaults to the last value used. Whenever an access is made to a device on a child bus, the value set -in the revelant node's reg property will be output to the register. +in the relevant node's reg property will be output to the register. If an idle state is defined, using the idle-state (optional) property, whenever an access is not being made to a device on a child bus, the diff --git a/Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt b/Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt index 14aa6cf58201..6a9a63cb0543 100644 --- a/Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt +++ b/Documentation/devicetree/bindings/net/marvell-bt-sd8xxx.txt @@ -13,10 +13,10 @@ Optional properties: initialization. This is an array of 28 values(u8). - marvell,wakeup-pin: It represents wakeup pin number of the bluetooth chip. - firmware will use the pin to wakeup host system. + firmware will use the pin to wakeup host system (u16). - marvell,wakeup-gap-ms: wakeup gap represents wakeup latency of the host platform. The value will be configured to firmware. This - is needed to work chip's sleep feature as expected. + is needed to work chip's sleep feature as expected (u16). - interrupt-parent: phandle of the parent interrupt controller - interrupts : interrupt pin number to the cpu. Driver will request an irq based on this interrupt number. During system suspend, the irq will be @@ -50,7 +50,7 @@ calibration data is also available in below example. 0x37 0x01 0x1c 0x00 0xff 0xff 0xff 0xff 0x01 0x7f 0x04 0x02 0x00 0x00 0xba 0xce 0xc0 0xc6 0x2d 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0xf0 0x00>; - marvell,wakeup-pin = <0x0d>; - marvell,wakeup-gap-ms = <0x64>; + marvell,wakeup-pin = /bits/ 16 <0x0d>; + marvell,wakeup-gap-ms = /bits/ 16 <0x64>; }; }; diff --git a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-dpaux-padctl.txt b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-dpaux-padctl.txt new file mode 100644 index 000000000000..f2abdaee9022 --- /dev/null +++ b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-dpaux-padctl.txt @@ -0,0 +1,60 @@ +Device tree binding for NVIDIA Tegra DPAUX pad controller +======================================================== + +The Tegra Display Port Auxiliary (DPAUX) pad controller manages two pins +which can be assigned to either the DPAUX channel or to an I2C +controller. + +This document defines the device-specific binding for the DPAUX pad +controller. Refer to pinctrl-bindings.txt in this directory for generic +information about pin controller device tree bindings. Please refer to +the binding document ../display/tegra/nvidia,tegra20-host1x.txt for more +details on the DPAUX binding. + +Pin muxing: +----------- + +Child nodes contain the pinmux configurations following the conventions +from the pinctrl-bindings.txt document. + +Since only three configurations are possible, only three child nodes are +needed to describe the pin mux'ing options for the DPAUX pads. +Furthermore, given that the pad functions are only applicable to a +single set of pads, the child nodes only need to describe the pad group +the functions are being applied to rather than the individual pads. + +Required properties: +- groups: Must be "dpaux-io" +- function: Must be either "aux", "i2c" or "off". + +Example: +-------- + + dpaux@545c0000 { + ... + + state_dpaux_aux: pinmux-aux { + groups = "dpaux-io"; + function = "aux"; + }; + + state_dpaux_i2c: pinmux-i2c { + groups = "dpaux-io"; + function = "i2c"; + }; + + state_dpaux_off: pinmux-off { + groups = "dpaux-io"; + function = "off"; + }; + }; + + ... + + i2c@7000d100 { + ... + pinctrl-0 = <&state_dpaux_i2c>; + pinctrl-1 = <&state_dpaux_off>; + pinctrl-names = "default", "idle"; + status = "disabled"; + }; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index a7440bcd67ff..44722769209f 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -247,6 +247,7 @@ sony Sony Corporation spansion Spansion Inc. sprd Spreadtrum Communications Inc. st STMicroelectronics +starry Starry Electronic Technology (ShenZhen) Co., LTD startek Startek ste ST-Ericsson stericsson ST-Ericsson @@ -255,6 +256,7 @@ synology Synology, Inc. SUNW Sun Microsystems, Inc tbs TBS Technologies tcl Toby Churchill Ltd. +technexion TechNexion technologic Technologic Systems thine THine Electronics, Inc. ti Texas Instruments @@ -269,6 +271,7 @@ tronsmart Tronsmart truly Truly Semiconductors Limited tyan Tyan Computer Corporation upisemi uPI Semiconductor Corp. +uniwest United Western Technologies Corp (UniWest) urt United Radiant Technology Corporation usi Universal Scientific Industrial Co., Ltd. v3 V3 Semiconductor diff --git a/Documentation/gdb-kernel-debugging.txt b/Documentation/gdb-kernel-debugging.txt index 4ab7d43d0754..7050ce8794b9 100644 --- a/Documentation/gdb-kernel-debugging.txt +++ b/Documentation/gdb-kernel-debugging.txt @@ -139,27 +139,6 @@ Examples of using the Linux-provided gdb helpers start_comm = "swapper/2\000\000\000\000\000\000" } - o Dig into a radix tree data structure, such as the IRQ descriptors: - (gdb) print (struct irq_desc)$lx_radix_tree_lookup(irq_desc_tree, 18) - $6 = { - irq_common_data = { - state_use_accessors = 67584, - handler_data = 0x0 <__vectors_start>, - msi_desc = 0x0 <__vectors_start>, - affinity = {{ - bits = {65535} - }} - }, - irq_data = { - mask = 0, - irq = 18, - hwirq = 27, - common = 0xee803d80, - chip = 0xc0eb0854 , - domain = 0xee808000, - parent_data = 0x0 <__vectors_start>, - chip_data = 0xc0eb0854 - } <... trimmed ...> List of commands and functions ------------------------------ diff --git a/Documentation/gpu/drm-internals.rst b/Documentation/gpu/drm-internals.rst index 4f7176576feb..3bb26135971f 100644 --- a/Documentation/gpu/drm-internals.rst +++ b/Documentation/gpu/drm-internals.rst @@ -188,7 +188,8 @@ Manual IRQ Registration Drivers that require multiple interrupt handlers can't use the managed IRQ registration functions. In that case IRQs must be registered and unregistered manually (usually with the :c:func:`request_irq()` and -:c:func:`free_irq()` functions, or their devm_\* equivalent). +:c:func:`free_irq()` functions, or their :c:func:`devm_request_irq()` and +:c:func:`devm_free_irq()` equivalents). When manually registering IRQs, drivers must not set the DRIVER_HAVE_IRQ driver feature flag, and must not provide the @@ -242,11 +243,13 @@ Open/Close, File Operations and IOCTLs Open and Close -------------- -int (\*firstopen) (struct drm_device \*); void (\*lastclose) (struct -drm_device \*); int (\*open) (struct drm_device \*, struct drm_file -\*); void (\*preclose) (struct drm_device \*, struct drm_file \*); -void (\*postclose) (struct drm_device \*, struct drm_file \*); - Open and close handlers. None of those methods are mandatory. +Open and close handlers. None of those methods are mandatory:: + + int (*firstopen) (struct drm_device *); + void (*lastclose) (struct drm_device *); + int (*open) (struct drm_device *, struct drm_file *); + void (*preclose) (struct drm_device *, struct drm_file *); + void (*postclose) (struct drm_device *, struct drm_file *); The firstopen method is called by the DRM core for legacy UMS (User Mode Setting) drivers only when an application opens a device that has no @@ -280,8 +283,8 @@ private data in the open method should free it here. The lastclose method should restore CRTC and plane properties to default value, so that a subsequent open of the device will not inherit state from the previous user. It can also be used to execute delayed power -switching state changes, e.g. in conjunction with the vga_switcheroo -infrastructure (see ?). Beyond that KMS drivers should not do any +switching state changes, e.g. in conjunction with the :ref:`vga_switcheroo` +infrastructure. Beyond that KMS drivers should not do any further cleanup. Only legacy UMS drivers might need to clean up device state so that the vga console or an independent fbdev driver could take over. diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst index 0e1c80436c1d..8dfa4b214b96 100644 --- a/Documentation/gpu/drm-kms.rst +++ b/Documentation/gpu/drm-kms.rst @@ -67,9 +67,6 @@ drivers can manually clean up a framebuffer at module unload time with DRM Format Handling ------------------- -.. kernel-doc:: include/drm/drm_fourcc.h - :internal: - .. kernel-doc:: drivers/gpu/drm/drm_fourcc.c :export: @@ -652,5 +649,5 @@ Vertical Blanking and Interrupt Handling Functions Reference .. kernel-doc:: drivers/gpu/drm/drm_irq.c :export: -.. kernel-doc:: include/drm/drmP.h - :functions: drm_crtc_vblank_waitqueue +.. kernel-doc:: include/drm/drm_irq.h + :internal: diff --git a/Documentation/gpu/vga-switcheroo.rst b/Documentation/gpu/vga-switcheroo.rst index 327d930a2229..cbbdb994f1dd 100644 --- a/Documentation/gpu/vga-switcheroo.rst +++ b/Documentation/gpu/vga-switcheroo.rst @@ -1,3 +1,5 @@ +.. _vga_switcheroo: + ============== VGA Switcheroo ============== @@ -94,9 +96,3 @@ Public functions .. kernel-doc:: include/linux/apple-gmux.h :internal: - -.. WARNING: DOCPROC directive not supported: !Cdrivers/gpu/vga/vga_switcheroo.c - -.. WARNING: DOCPROC directive not supported: !Cinclude/linux/vga_switcheroo.h - -.. WARNING: DOCPROC directive not supported: !Cdrivers/platform/x86/apple-gmux.c diff --git a/Documentation/leds/leds-class.txt b/Documentation/leds/leds-class.txt index d406d98339b2..44f5e6bccd97 100644 --- a/Documentation/leds/leds-class.txt +++ b/Documentation/leds/leds-class.txt @@ -74,8 +74,8 @@ blink_set() function (see ). To set an LED to blinking, however, it is better to use the API function led_blink_set(), as it will check and implement software fallback if necessary. -To turn off blinking again, use the API function led_brightness_set() -as that will not just set the LED brightness but also stop any software +To turn off blinking, use the API function led_brightness_set() +with brightness value LED_OFF, which should stop any software timers that may have been required for blinking. The blink_set() function should choose a user friendly blinking value diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt index 8638f61c8c9d..37eca00796ee 100644 --- a/Documentation/scsi/scsi_eh.txt +++ b/Documentation/scsi/scsi_eh.txt @@ -263,19 +263,23 @@ scmd->allowed. 3. scmd recovered ACTION: scsi_eh_finish_cmd() is invoked to EH-finish scmd - - shost->host_failed-- - clear scmd->eh_eflags - scsi_setup_cmd_retry() - move from local eh_work_q to local eh_done_q LOCKING: none + CONCURRENCY: at most one thread per separate eh_work_q to + keep queue manipulation lockless 4. EH completes ACTION: scsi_eh_flush_done_q() retries scmds or notifies upper - layer of failure. + layer of failure. May be called concurrently but must have + a no more than one thread per separate eh_work_q to + manipulate the queue locklessly - scmd is removed from eh_done_q and scmd->eh_entry is cleared - if retry is necessary, scmd is requeued using scsi_queue_insert() - otherwise, scsi_finish_command() is invoked for scmd + - zero shost->host_failed LOCKING: queue or finish function performs appropriate locking diff --git a/Documentation/x86/intel_mpx.txt b/Documentation/x86/intel_mpx.txt index 1a5a12184a35..85d0549ad846 100644 --- a/Documentation/x86/intel_mpx.txt +++ b/Documentation/x86/intel_mpx.txt @@ -45,7 +45,7 @@ is how we expect the compiler, application and kernel to work together. MPX-instrumented. 3) The kernel detects that the CPU has MPX, allows the new prctl() to succeed, and notes the location of the bounds directory. Userspace is - expected to keep the bounds directory at that locationWe note it + expected to keep the bounds directory at that location. We note it instead of reading it each time because the 'xsave' operation needed to access the bounds directory register is an expensive operation. 4) If the application needs to spill bounds out of the 4 registers, it @@ -167,7 +167,7 @@ If a #BR is generated due to a bounds violation caused by MPX. We need to decode MPX instructions to get violation address and set this address into extended struct siginfo. -The _sigfault feild of struct siginfo is extended as follow: +The _sigfault field of struct siginfo is extended as follow: 87 /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ 88 struct { @@ -240,5 +240,5 @@ them at the same bounds table. This is allowed architecturally. See more information "Intel(R) Architecture Instruction Set Extensions Programming Reference" (9.3.4). -However, if users did this, the kernel might be fooled in to unmaping an +However, if users did this, the kernel might be fooled in to unmapping an in-use bounds table since it does not recognize sharing. diff --git a/Documentation/x86/tlb.txt b/Documentation/x86/tlb.txt index 39d172326703..6a0607b99ed8 100644 --- a/Documentation/x86/tlb.txt +++ b/Documentation/x86/tlb.txt @@ -5,7 +5,7 @@ memory, it has two choices: from areas other than the one we are trying to flush will be destroyed and must be refilled later, at some cost. 2. Use the invlpg instruction to invalidate a single page at a - time. This could potentialy cost many more instructions, but + time. This could potentially cost many more instructions, but it is a much more precise operation, causing no collateral damage to other TLB entries. @@ -19,7 +19,7 @@ Which method to do depends on a few things: work. 3. The size of the TLB. The larger the TLB, the more collateral damage we do with a full flush. So, the larger the TLB, the - more attrative an individual flush looks. Data and + more attractive an individual flush looks. Data and instructions have separate TLBs, as do different page sizes. 4. The microarchitecture. The TLB has become a multi-level cache on modern CPUs, and the global flushes have become more diff --git a/Documentation/x86/x86_64/machinecheck b/Documentation/x86/x86_64/machinecheck index b1fb30273286..d0648a74fceb 100644 --- a/Documentation/x86/x86_64/machinecheck +++ b/Documentation/x86/x86_64/machinecheck @@ -36,7 +36,7 @@ between all CPUs. check_interval How often to poll for corrected machine check errors, in seconds - (Note output is hexademical). Default 5 minutes. When the poller + (Note output is hexadecimal). Default 5 minutes. When the poller finds MCEs it triggers an exponential speedup (poll more often) on the polling interval. When the poller stops finding MCEs, it triggers an exponential backoff (poll less often) on the polling diff --git a/MAINTAINERS b/MAINTAINERS index 512185c9b768..ea8c7ab56cf5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -595,6 +595,10 @@ S: Odd Fixes L: linux-alpha@vger.kernel.org F: arch/alpha/ +ALPS PS/2 TOUCHPAD DRIVER +R: Pali Rohár +F: drivers/input/mouse/alps.* + ALTERA MAILBOX DRIVER M: Ley Foon Tan L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers) @@ -1167,6 +1171,7 @@ F: arch/arm/mach-footbridge/ ARM/FREESCALE IMX / MXC ARM ARCHITECTURE M: Shawn Guo M: Sascha Hauer +R: Fabio Estevam L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git @@ -1697,8 +1702,6 @@ S: Maintained F: drivers/edac/altera_edac. ARM/STI ARCHITECTURE -M: Srinivas Kandagatla -M: Maxime Coquelin M: Patrice Chotard L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: kernel@stlinux.com @@ -1731,6 +1734,7 @@ F: drivers/ata/ahci_st.c ARM/STM32 ARCHITECTURE M: Maxime Coquelin +M: Alexandre Torgue L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/mcoquelin/stm32.git @@ -2250,7 +2254,8 @@ F: include/net/ax25.h F: net/ax25/ AZ6007 DVB DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -2717,7 +2722,8 @@ F: Documentation/filesystems/btrfs.txt F: fs/btrfs/ BTTV VIDEO4LINUX DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -2781,9 +2787,9 @@ F: include/net/caif/ F: net/caif/ CALGARY x86-64 IOMMU -M: Muli Ben-Yehuda -M: "Jon D. Mason" -L: discuss@x86-64.org +M: Muli Ben-Yehuda +M: Jon Mason +L: iommu@lists.linux-foundation.org S: Maintained F: arch/x86/kernel/pci-calgary_64.c F: arch/x86/kernel/tce_64.c @@ -3094,6 +3100,7 @@ M: Stephen Boyd L: linux-clk@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux.git S: Maintained +F: Documentation/devicetree/bindings/clock/ F: drivers/clk/ X: drivers/clk/clkdev.c F: include/linux/clk-pr* @@ -3351,7 +3358,8 @@ S: Maintained F: drivers/media/dvb-frontends/cx24120* CX88 VIDEO4LINUX DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -3774,6 +3782,17 @@ F: include/linux/*fence.h F: Documentation/dma-buf-sharing.txt T: git git://git.linaro.org/people/sumitsemwal/linux-dma-buf.git +SYNC FILE FRAMEWORK +M: Sumit Semwal +R: Gustavo Padovan +S: Maintained +L: linux-media@vger.kernel.org +L: dri-devel@lists.freedesktop.org +F: drivers/dma-buf/sync_file.c +F: include/linux/sync_file.h +F: Documentation/sync_file.txt +T: git git://git.linaro.org/people/sumitsemwal/linux-dma-buf.git + DMA GENERIC OFFLOAD ENGINE SUBSYSTEM M: Vinod Koul L: dmaengine@vger.kernel.org @@ -3781,6 +3800,7 @@ Q: https://patchwork.kernel.org/project/linux-dmaengine/list/ S: Maintained F: drivers/dma/ F: include/linux/dmaengine.h +F: Documentation/devicetree/bindings/dma/ F: Documentation/dmaengine/ T: git git://git.infradead.org/users/vkoul/slave-dma.git @@ -4317,7 +4337,8 @@ F: fs/ecryptfs/ EDAC-CORE M: Doug Thompson M: Borislav Petkov -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-edac@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/bp/bp.git for-next T: git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-edac.git linux_next @@ -4362,7 +4383,8 @@ S: Maintained F: drivers/edac/e7xxx_edac.c EDAC-GHES -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/ghes_edac.c @@ -4386,19 +4408,22 @@ S: Maintained F: drivers/edac/i5000_edac.c EDAC-I5400 -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/i5400_edac.c EDAC-I7300 -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/i7300_edac.c EDAC-I7CORE -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/i7core_edac.c @@ -4435,7 +4460,8 @@ S: Maintained F: drivers/edac/r82600_edac.c EDAC-SBRIDGE -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/sb_edac.c @@ -4488,13 +4514,14 @@ S: Orphan F: fs/efs/ EHEA (IBM pSeries eHEA 10Gb ethernet adapter) DRIVER -M: Thadeu Lima de Souza Cascardo +M: Douglas Miller L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/ibm/ehea/ EM28XX VIDEO4LINUX DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -6513,6 +6540,7 @@ F: include/uapi/linux/sunrpc/ KERNEL SELFTEST FRAMEWORK M: Shuah Khan +M: Shuah Khan L: linux-kselftest@vger.kernel.org T: git git://git.kernel.org/pub/scm/shuah/linux-kselftest S: Maintained @@ -7384,7 +7412,8 @@ S: Supported F: drivers/media/pci/netup_unidvb/* MEDIA INPUT INFRASTRUCTURE (V4L/DVB) -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab P: LinuxTV.org Project L: linux-media@vger.kernel.org W: https://linuxtv.org @@ -7432,7 +7461,7 @@ F: drivers/scsi/megaraid.* F: drivers/scsi/megaraid/ MELLANOX ETHERNET DRIVER (mlx4_en) -M: Eugenia Emantayev +M: Tariq Toukan L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -7484,6 +7513,7 @@ Q: http://patchwork.ozlabs.org/project/linux-mtd/list/ T: git git://git.infradead.org/linux-mtd.git T: git git://git.infradead.org/l2-mtd.git S: Maintained +F: Documentation/devicetree/bindings/mtd/ F: drivers/mtd/ F: include/linux/mtd/ F: include/uapi/mtd/ @@ -8035,6 +8065,7 @@ Q: http://patchwork.kernel.org/project/linux-wireless/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/wireless-drivers-next.git S: Maintained +F: Documentation/devicetree/bindings/net/wireless/ F: drivers/net/wireless/ NETXEN (1/10) GbE SUPPORT @@ -8432,10 +8463,9 @@ F: drivers/i2c/busses/i2c-ocores.c OPEN FIRMWARE AND FLATTENED DEVICE TREE M: Rob Herring M: Frank Rowand -M: Grant Likely L: devicetree@vger.kernel.org W: http://www.devicetree.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/glikely/linux.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git S: Maintained F: drivers/of/ F: include/linux/of*.h @@ -8443,12 +8473,10 @@ F: scripts/dtc/ OPEN FIRMWARE AND FLATTENED DEVICE TREE BINDINGS M: Rob Herring -M: Pawel Moll M: Mark Rutland -M: Ian Campbell -M: Kumar Gala L: devicetree@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git +Q: http://patchwork.ozlabs.org/project/devicetree-bindings/list/ S: Maintained F: Documentation/devicetree/ F: arch/*/boot/dts/ @@ -8973,6 +9001,7 @@ L: linux-gpio@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl.git S: Maintained F: Documentation/devicetree/bindings/pinctrl/ +F: Documentation/pinctrl.txt F: drivers/pinctrl/ F: include/linux/pinctrl/ @@ -9880,7 +9909,8 @@ S: Odd Fixes F: drivers/media/i2c/saa6588* SAA7134 VIDEO4LINUX DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -10399,7 +10429,8 @@ S: Maintained F: drivers/media/radio/si4713/radio-usb-si4713.c SIANO DVB DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -11165,7 +11196,8 @@ S: Maintained F: drivers/media/i2c/tda9840* TEA5761 TUNER DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -11173,7 +11205,8 @@ S: Odd fixes F: drivers/media/tuners/tea5761.* TEA5767 TUNER DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -11560,7 +11593,8 @@ F: include/linux/shmem_fs.h F: mm/shmem.c TM6000 VIDEO4LINUX DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git @@ -11914,7 +11948,8 @@ F: drivers/usb/common/usb-otg-fsm.c USB OVER IP DRIVER M: Valentina Manea -M: Shuah Khan +M: Shuah Khan +M: Shuah Khan L: linux-usb@vger.kernel.org S: Maintained F: Documentation/usb/usbip_protocol.txt @@ -11985,6 +12020,7 @@ L: linux-usb@vger.kernel.org W: http://www.linux-usb.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb.git S: Supported +F: Documentation/devicetree/bindings/usb/ F: Documentation/usb/ F: drivers/usb/ F: include/linux/usb.h @@ -12158,6 +12194,7 @@ VIRTIO CORE, NET AND BLOCK DRIVERS M: "Michael S. Tsirkin" L: virtualization@lists.linux-foundation.org S: Maintained +F: Documentation/devicetree/bindings/virtio/ F: drivers/virtio/ F: tools/virtio/ F: drivers/net/virtio_net.c @@ -12546,7 +12583,8 @@ S: Maintained F: arch/x86/entry/vdso/ XC2028/3028 TUNER DRIVER -M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab +M: Mauro Carvalho Chehab L: linux-media@vger.kernel.org W: https://linuxtv.org T: git git://linuxtv.org/media_tree.git diff --git a/Makefile b/Makefile index 801457b847a4..d30c59f9ce92 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 7 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = NAME = Psychotic Stoned Sheep # *DOCUMENTATION* @@ -363,11 +363,13 @@ CHECK = sparse CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \ -Wbitwise -Wno-return-void $(CF) +NOSTDINC_FLAGS = CFLAGS_MODULE = AFLAGS_MODULE = LDFLAGS_MODULE = CFLAGS_KERNEL = AFLAGS_KERNEL = +LDFLAGS_vmlinux = CFLAGS_GCOV = -fprofile-arcs -ftest-coverage -fno-tree-loop-im -Wno-maybe-uninitialized CFLAGS_KCOV = -fsanitize-coverage=trace-pc diff --git a/arch/Kconfig b/arch/Kconfig index d794384a0404..15996290fed4 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -226,8 +226,8 @@ config ARCH_INIT_TASK config ARCH_TASK_STRUCT_ALLOCATOR bool -# Select if arch has its private alloc_thread_info() function -config ARCH_THREAD_INFO_ALLOCATOR +# Select if arch has its private alloc_thread_stack() function +config ARCH_THREAD_STACK_ALLOCATOR bool # Select if arch wants to size task_struct dynamically via arch_task_struct_size: @@ -606,6 +606,9 @@ config HAVE_ARCH_HASH file which provides platform-specific implementations of some functions in or fs/namei.c. +config ISA_BUS_API + def_bool ISA + # # ABI hall of shame # diff --git a/arch/alpha/include/asm/pgalloc.h b/arch/alpha/include/asm/pgalloc.h index aab14a019c20..c2ebb6f36c9d 100644 --- a/arch/alpha/include/asm/pgalloc.h +++ b/arch/alpha/include/asm/pgalloc.h @@ -40,7 +40,7 @@ pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pmd_t * pmd_alloc_one(struct mm_struct *mm, unsigned long address) { - pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pmd_t *ret = (pmd_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); return ret; } @@ -53,7 +53,7 @@ pmd_free(struct mm_struct *mm, pmd_t *pmd) static inline pte_t * pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); return pte; } diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 0dcbacfdea4b..0d3e59f56974 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -61,7 +61,7 @@ config RWSEM_GENERIC_SPINLOCK def_bool y config ARCH_DISCONTIGMEM_ENABLE - def_bool y + def_bool n config ARCH_FLATMEM_ENABLE def_bool y @@ -186,9 +186,6 @@ if SMP config ARC_HAS_COH_CACHES def_bool n -config ARC_HAS_REENTRANT_IRQ_LV2 - def_bool n - config ARC_MCIP bool "ARConnect Multicore IP (MCIP) Support " depends on ISA_ARCV2 @@ -366,25 +363,10 @@ config NODES_SHIFT if ISA_ARCOMPACT config ARC_COMPACT_IRQ_LEVELS - bool "ARCompact IRQ Priorities: High(2)/Low(1)" + bool "Setup Timer IRQ as high Priority" default n - # Timer HAS to be high priority, for any other high priority config - select ARC_IRQ3_LV2 # if SMP, LV2 enabled ONLY if ARC implementation has LV2 re-entrancy - depends on !SMP || ARC_HAS_REENTRANT_IRQ_LV2 - -if ARC_COMPACT_IRQ_LEVELS - -config ARC_IRQ3_LV2 - bool - -config ARC_IRQ5_LV2 - bool - -config ARC_IRQ6_LV2 - bool - -endif #ARC_COMPACT_IRQ_LEVELS + depends on !SMP config ARC_FPU_SAVE_RESTORE bool "Enable FPU state persistence across context switch" @@ -407,11 +389,6 @@ config ARC_HAS_LLSC default y depends on !ARC_CANT_LLSC -config ARC_STAR_9000923308 - bool "Workaround for llock/scond livelock" - default n - depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC - config ARC_HAS_SWAPE bool "Insn: SWAPE (endian-swap)" default y @@ -471,7 +448,7 @@ config LINUX_LINK_BASE config HIGHMEM bool "High Memory Support" - select DISCONTIGMEM + select ARCH_DISCONTIGMEM_ENABLE help With ARC 2G:2G address split, only upper 2G is directly addressable by kernel. Enable this to potentially allow access to rest of 2G and PAE diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 02fabef2891c..85814e74677d 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -66,8 +66,6 @@ endif endif -cflags-$(CONFIG_ARC_DW2_UNWIND) += -fasynchronous-unwind-tables - # By default gcc 4.8 generates dwarf4 which kernel unwinder can't grok ifeq ($(atleast_gcc48),y) cflags-$(CONFIG_ARC_DW2_UNWIND) += -gdwarf-2 @@ -127,7 +125,7 @@ libs-y += arch/arc/lib/ $(LIBGCC) boot := arch/arc/boot -#default target for make without any arguements. +#default target for make without any arguments. KBUILD_IMAGE := bootpImage all: $(KBUILD_IMAGE) diff --git a/arch/arc/boot/dts/abilis_tb100.dtsi b/arch/arc/boot/dts/abilis_tb100.dtsi index 3942634f805a..02410b211433 100644 --- a/arch/arc/boot/dts/abilis_tb100.dtsi +++ b/arch/arc/boot/dts/abilis_tb100.dtsi @@ -23,8 +23,6 @@ / { - clock-frequency = <500000000>; /* 500 MHZ */ - soc100 { bus-frequency = <166666666>; diff --git a/arch/arc/boot/dts/abilis_tb101.dtsi b/arch/arc/boot/dts/abilis_tb101.dtsi index b0467229a5c4..f9e7686044eb 100644 --- a/arch/arc/boot/dts/abilis_tb101.dtsi +++ b/arch/arc/boot/dts/abilis_tb101.dtsi @@ -23,8 +23,6 @@ / { - clock-frequency = <500000000>; /* 500 MHZ */ - soc100 { bus-frequency = <166666666>; diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi index 3e02f152edcb..6ae2c476ad82 100644 --- a/arch/arc/boot/dts/axc001.dtsi +++ b/arch/arc/boot/dts/axc001.dtsi @@ -15,7 +15,6 @@ / { compatible = "snps,arc"; - clock-frequency = <750000000>; /* 750 MHZ */ #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi index 378e455a94c4..14df46f141bf 100644 --- a/arch/arc/boot/dts/axc003.dtsi +++ b/arch/arc/boot/dts/axc003.dtsi @@ -14,7 +14,6 @@ / { compatible = "snps,arc"; - clock-frequency = <90000000>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi index 64c94b2860ab..3d6cfa32bf51 100644 --- a/arch/arc/boot/dts/axc003_idu.dtsi +++ b/arch/arc/boot/dts/axc003_idu.dtsi @@ -14,7 +14,6 @@ / { compatible = "snps,arc"; - clock-frequency = <90000000>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/boot/dts/eznps.dts b/arch/arc/boot/dts/eznps.dts index b89f6c3eb352..1e0d225791c1 100644 --- a/arch/arc/boot/dts/eznps.dts +++ b/arch/arc/boot/dts/eznps.dts @@ -18,7 +18,6 @@ / { compatible = "ezchip,arc-nps"; - clock-frequency = <83333333>; /* 83.333333 MHZ */ #address-cells = <1>; #size-cells = <1>; interrupt-parent = <&intc>; diff --git a/arch/arc/boot/dts/nsim_700.dts b/arch/arc/boot/dts/nsim_700.dts index 5d5e373e0ebc..63970513e4ae 100644 --- a/arch/arc/boot/dts/nsim_700.dts +++ b/arch/arc/boot/dts/nsim_700.dts @@ -11,7 +11,6 @@ / { compatible = "snps,nsim"; - clock-frequency = <80000000>; /* 80 MHZ */ #address-cells = <1>; #size-cells = <1>; interrupt-parent = <&core_intc>; diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts index 37c416defe90..e659a340ca8a 100644 --- a/arch/arc/boot/dts/nsimosci.dts +++ b/arch/arc/boot/dts/nsimosci.dts @@ -11,7 +11,6 @@ / { compatible = "snps,nsimosci"; - clock-frequency = <20000000>; /* 20 MHZ */ #address-cells = <1>; #size-cells = <1>; interrupt-parent = <&core_intc>; diff --git a/arch/arc/boot/dts/nsimosci_hs.dts b/arch/arc/boot/dts/nsimosci_hs.dts index f2a22c49541d..16ce5d65cfde 100644 --- a/arch/arc/boot/dts/nsimosci_hs.dts +++ b/arch/arc/boot/dts/nsimosci_hs.dts @@ -11,7 +11,6 @@ / { compatible = "snps,nsimosci_hs"; - clock-frequency = <20000000>; /* 20 MHZ */ #address-cells = <1>; #size-cells = <1>; interrupt-parent = <&core_intc>; diff --git a/arch/arc/boot/dts/nsimosci_hs_idu.dts b/arch/arc/boot/dts/nsimosci_hs_idu.dts index 34457a5e7706..ce8dfbc30c4d 100644 --- a/arch/arc/boot/dts/nsimosci_hs_idu.dts +++ b/arch/arc/boot/dts/nsimosci_hs_idu.dts @@ -11,7 +11,6 @@ / { compatible = "snps,nsimosci_hs"; - clock-frequency = <5000000>; /* 5 MHZ */ #address-cells = <1>; #size-cells = <1>; interrupt-parent = <&core_intc>; diff --git a/arch/arc/boot/dts/skeleton.dtsi b/arch/arc/boot/dts/skeleton.dtsi index 3a10cc633e2b..65808fe0a290 100644 --- a/arch/arc/boot/dts/skeleton.dtsi +++ b/arch/arc/boot/dts/skeleton.dtsi @@ -13,7 +13,6 @@ / { compatible = "snps,arc"; - clock-frequency = <80000000>; /* 80 MHZ */ #address-cells = <1>; #size-cells = <1>; chosen { }; diff --git a/arch/arc/boot/dts/skeleton_hs.dtsi b/arch/arc/boot/dts/skeleton_hs.dtsi index 71fd308a9298..2dfe8037dfbb 100644 --- a/arch/arc/boot/dts/skeleton_hs.dtsi +++ b/arch/arc/boot/dts/skeleton_hs.dtsi @@ -8,7 +8,6 @@ / { compatible = "snps,arc"; - clock-frequency = <80000000>; /* 80 MHZ */ #address-cells = <1>; #size-cells = <1>; chosen { }; diff --git a/arch/arc/boot/dts/skeleton_hs_idu.dtsi b/arch/arc/boot/dts/skeleton_hs_idu.dtsi index d1cb25a66989..4c11079f3565 100644 --- a/arch/arc/boot/dts/skeleton_hs_idu.dtsi +++ b/arch/arc/boot/dts/skeleton_hs_idu.dtsi @@ -8,7 +8,6 @@ / { compatible = "snps,arc"; - clock-frequency = <80000000>; /* 80 MHZ */ #address-cells = <1>; #size-cells = <1>; chosen { }; diff --git a/arch/arc/boot/dts/vdk_axc003.dtsi b/arch/arc/boot/dts/vdk_axc003.dtsi index ad4ee43bd2ac..0fd6ba985b16 100644 --- a/arch/arc/boot/dts/vdk_axc003.dtsi +++ b/arch/arc/boot/dts/vdk_axc003.dtsi @@ -14,7 +14,6 @@ / { compatible = "snps,arc"; - clock-frequency = <50000000>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/boot/dts/vdk_axc003_idu.dtsi b/arch/arc/boot/dts/vdk_axc003_idu.dtsi index a3cb6263c581..82214cd7ba0c 100644 --- a/arch/arc/boot/dts/vdk_axc003_idu.dtsi +++ b/arch/arc/boot/dts/vdk_axc003_idu.dtsi @@ -15,7 +15,6 @@ / { compatible = "snps,arc"; - clock-frequency = <50000000>; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 5f3dcbbc0cc9..dd683995bc9d 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -25,50 +25,17 @@ #define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i)) -#ifdef CONFIG_ARC_STAR_9000923308 - -#define SCOND_FAIL_RETRY_VAR_DEF \ - unsigned int delay = 1, tmp; \ - -#define SCOND_FAIL_RETRY_ASM \ - " bz 4f \n" \ - " ; --- scond fail delay --- \n" \ - " mov %[tmp], %[delay] \n" /* tmp = delay */ \ - "2: brne.d %[tmp], 0, 2b \n" /* while (tmp != 0) */ \ - " sub %[tmp], %[tmp], 1 \n" /* tmp-- */ \ - " rol %[delay], %[delay] \n" /* delay *= 2 */ \ - " b 1b \n" /* start over */ \ - "4: ; --- success --- \n" \ - -#define SCOND_FAIL_RETRY_VARS \ - ,[delay] "+&r" (delay),[tmp] "=&r" (tmp) \ - -#else /* !CONFIG_ARC_STAR_9000923308 */ - -#define SCOND_FAIL_RETRY_VAR_DEF - -#define SCOND_FAIL_RETRY_ASM \ - " bnz 1b \n" \ - -#define SCOND_FAIL_RETRY_VARS - -#endif - #define ATOMIC_OP(op, c_op, asm_op) \ static inline void atomic_##op(int i, atomic_t *v) \ { \ - unsigned int val; \ - SCOND_FAIL_RETRY_VAR_DEF \ + unsigned int val; \ \ __asm__ __volatile__( \ "1: llock %[val], [%[ctr]] \n" \ " " #asm_op " %[val], %[val], %[i] \n" \ " scond %[val], [%[ctr]] \n" \ - " \n" \ - SCOND_FAIL_RETRY_ASM \ - \ + " bnz 1b \n" \ : [val] "=&r" (val) /* Early clobber to prevent reg reuse */ \ - SCOND_FAIL_RETRY_VARS \ : [ctr] "r" (&v->counter), /* Not "m": llock only supports reg direct addr mode */ \ [i] "ir" (i) \ : "cc"); \ @@ -77,8 +44,7 @@ static inline void atomic_##op(int i, atomic_t *v) \ #define ATOMIC_OP_RETURN(op, c_op, asm_op) \ static inline int atomic_##op##_return(int i, atomic_t *v) \ { \ - unsigned int val; \ - SCOND_FAIL_RETRY_VAR_DEF \ + unsigned int val; \ \ /* \ * Explicit full memory barrier needed before/after as \ @@ -90,11 +56,8 @@ static inline int atomic_##op##_return(int i, atomic_t *v) \ "1: llock %[val], [%[ctr]] \n" \ " " #asm_op " %[val], %[val], %[i] \n" \ " scond %[val], [%[ctr]] \n" \ - " \n" \ - SCOND_FAIL_RETRY_ASM \ - \ + " bnz 1b \n" \ : [val] "=&r" (val) \ - SCOND_FAIL_RETRY_VARS \ : [ctr] "r" (&v->counter), \ [i] "ir" (i) \ : "cc"); \ diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h index e0e1faf03c50..14c310f2e0b1 100644 --- a/arch/arc/include/asm/entry-compact.h +++ b/arch/arc/include/asm/entry-compact.h @@ -76,8 +76,8 @@ * We need to be a bit more cautious here. What if a kernel bug in * L1 ISR, caused SP to go whaco (some small value which looks like * USER stk) and then we take L2 ISR. - * Above brlo alone would treat it as a valid L1-L2 sceanrio - * instead of shouting alound + * Above brlo alone would treat it as a valid L1-L2 scenario + * instead of shouting around * The only feasible way is to make sure this L2 happened in * L1 prelogue ONLY i.e. ilink2 is less than a pre-set marker in * L1 ISR before it switches stack diff --git a/arch/arc/include/asm/mmu_context.h b/arch/arc/include/asm/mmu_context.h index 1fd467ef658f..b0b87f2447f5 100644 --- a/arch/arc/include/asm/mmu_context.h +++ b/arch/arc/include/asm/mmu_context.h @@ -83,7 +83,7 @@ static inline void get_new_mmu_context(struct mm_struct *mm) local_flush_tlb_all(); /* - * Above checke for rollover of 8 bit ASID in 32 bit container. + * Above check for rollover of 8 bit ASID in 32 bit container. * If the container itself wrapped around, set it to a non zero * "generation" to distinguish from no context */ diff --git a/arch/arc/include/asm/pgalloc.h b/arch/arc/include/asm/pgalloc.h index 86ed671286df..3749234b7419 100644 --- a/arch/arc/include/asm/pgalloc.h +++ b/arch/arc/include/asm/pgalloc.h @@ -95,7 +95,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, { pte_t *pte; - pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, + pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_ZERO, __get_order_pte()); return pte; @@ -107,7 +107,7 @@ pte_alloc_one(struct mm_struct *mm, unsigned long address) pgtable_t pte_pg; struct page *page; - pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL | __GFP_REPEAT, __get_order_pte()); + pte_pg = (pgtable_t)__get_free_pages(GFP_KERNEL, __get_order_pte()); if (!pte_pg) return 0; memzero((void *)pte_pg, PTRS_PER_PTE * sizeof(pte_t)); diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 034bbdc0ff61..858f98ef7f1b 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -47,7 +47,7 @@ * Page Tables are purely for Linux VM's consumption and the bits below are * suited to that (uniqueness). Hence some are not implemented in the TLB and * some have different value in TLB. - * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible becoz they live in + * e.g. MMU v2: K_READ bit is 8 and so is GLOBAL (possible because they live in * seperate PD0 and PD1, which combined forms a translation entry) * while for PTE perspective, they are 8 and 9 respectively * with MMU v3: Most bits (except SHARED) represent the exact hardware pos diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h index f9048994b22f..16b630fbeb6a 100644 --- a/arch/arc/include/asm/processor.h +++ b/arch/arc/include/asm/processor.h @@ -78,7 +78,7 @@ struct task_struct; #define KSTK_ESP(tsk) (task_pt_regs(tsk)->sp) /* - * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode. + * Where about of Task's sp, fp, blink when it was last seen in kernel mode. * Look in process.c for details of kernel stack layout */ #define TSK_K_ESP(tsk) (tsk->thread.ksp) diff --git a/arch/arc/include/asm/smp.h b/arch/arc/include/asm/smp.h index 991380438d6b..89fdd1b0a76e 100644 --- a/arch/arc/include/asm/smp.h +++ b/arch/arc/include/asm/smp.h @@ -86,7 +86,7 @@ static inline const char *arc_platform_smp_cpuinfo(void) * (1) These insn were introduced only in 4.10 release. So for older released * support needed. * - * (2) In a SMP setup, the LLOCK/SCOND atomiticity across CPUs needs to be + * (2) In a SMP setup, the LLOCK/SCOND atomicity across CPUs needs to be * gaurantted by the platform (not something which core handles). * Assuming a platform won't, SMP Linux needs to use spinlocks + local IRQ * disabling for atomicity. diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h index 800e7c430ca5..cded4a9b5438 100644 --- a/arch/arc/include/asm/spinlock.h +++ b/arch/arc/include/asm/spinlock.h @@ -20,11 +20,6 @@ #ifdef CONFIG_ARC_HAS_LLSC -/* - * A normal LLOCK/SCOND based system, w/o need for livelock workaround - */ -#ifndef CONFIG_ARC_STAR_9000923308 - static inline void arch_spin_lock(arch_spinlock_t *lock) { unsigned int val; @@ -238,293 +233,6 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) smp_mb(); } -#else /* CONFIG_ARC_STAR_9000923308 */ - -/* - * HS38x4 could get into a LLOCK/SCOND livelock in case of multiple overlapping - * coherency transactions in the SCU. The exclusive line state keeps rotating - * among contenting cores leading to a never ending cycle. So break the cycle - * by deferring the retry of failed exclusive access (SCOND). The actual delay - * needed is function of number of contending cores as well as the unrelated - * coherency traffic from other cores. To keep the code simple, start off with - * small delay of 1 which would suffice most cases and in case of contention - * double the delay. Eventually the delay is sufficient such that the coherency - * pipeline is drained, thus a subsequent exclusive access would succeed. - */ - -#define SCOND_FAIL_RETRY_VAR_DEF \ - unsigned int delay, tmp; \ - -#define SCOND_FAIL_RETRY_ASM \ - " ; --- scond fail delay --- \n" \ - " mov %[tmp], %[delay] \n" /* tmp = delay */ \ - "2: brne.d %[tmp], 0, 2b \n" /* while (tmp != 0) */ \ - " sub %[tmp], %[tmp], 1 \n" /* tmp-- */ \ - " rol %[delay], %[delay] \n" /* delay *= 2 */ \ - " b 1b \n" /* start over */ \ - " \n" \ - "4: ; --- done --- \n" \ - -#define SCOND_FAIL_RETRY_VARS \ - ,[delay] "=&r" (delay), [tmp] "=&r" (tmp) \ - -static inline void arch_spin_lock(arch_spinlock_t *lock) -{ - unsigned int val; - SCOND_FAIL_RETRY_VAR_DEF; - - smp_mb(); - - __asm__ __volatile__( - "0: mov %[delay], 1 \n" - "1: llock %[val], [%[slock]] \n" - " breq %[val], %[LOCKED], 0b \n" /* spin while LOCKED */ - " scond %[LOCKED], [%[slock]] \n" /* acquire */ - " bz 4f \n" /* done */ - " \n" - SCOND_FAIL_RETRY_ASM - - : [val] "=&r" (val) - SCOND_FAIL_RETRY_VARS - : [slock] "r" (&(lock->slock)), - [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__) - : "memory", "cc"); - - smp_mb(); -} - -/* 1 - lock taken successfully */ -static inline int arch_spin_trylock(arch_spinlock_t *lock) -{ - unsigned int val, got_it = 0; - SCOND_FAIL_RETRY_VAR_DEF; - - smp_mb(); - - __asm__ __volatile__( - "0: mov %[delay], 1 \n" - "1: llock %[val], [%[slock]] \n" - " breq %[val], %[LOCKED], 4f \n" /* already LOCKED, just bail */ - " scond %[LOCKED], [%[slock]] \n" /* acquire */ - " bz.d 4f \n" - " mov.z %[got_it], 1 \n" /* got it */ - " \n" - SCOND_FAIL_RETRY_ASM - - : [val] "=&r" (val), - [got_it] "+&r" (got_it) - SCOND_FAIL_RETRY_VARS - : [slock] "r" (&(lock->slock)), - [LOCKED] "r" (__ARCH_SPIN_LOCK_LOCKED__) - : "memory", "cc"); - - smp_mb(); - - return got_it; -} - -static inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - smp_mb(); - - lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__; - - smp_mb(); -} - -/* - * Read-write spinlocks, allowing multiple readers but only one writer. - * Unfair locking as Writers could be starved indefinitely by Reader(s) - */ - -static inline void arch_read_lock(arch_rwlock_t *rw) -{ - unsigned int val; - SCOND_FAIL_RETRY_VAR_DEF; - - smp_mb(); - - /* - * zero means writer holds the lock exclusively, deny Reader. - * Otherwise grant lock to first/subseq reader - * - * if (rw->counter > 0) { - * rw->counter--; - * ret = 1; - * } - */ - - __asm__ __volatile__( - "0: mov %[delay], 1 \n" - "1: llock %[val], [%[rwlock]] \n" - " brls %[val], %[WR_LOCKED], 0b\n" /* <= 0: spin while write locked */ - " sub %[val], %[val], 1 \n" /* reader lock */ - " scond %[val], [%[rwlock]] \n" - " bz 4f \n" /* done */ - " \n" - SCOND_FAIL_RETRY_ASM - - : [val] "=&r" (val) - SCOND_FAIL_RETRY_VARS - : [rwlock] "r" (&(rw->counter)), - [WR_LOCKED] "ir" (0) - : "memory", "cc"); - - smp_mb(); -} - -/* 1 - lock taken successfully */ -static inline int arch_read_trylock(arch_rwlock_t *rw) -{ - unsigned int val, got_it = 0; - SCOND_FAIL_RETRY_VAR_DEF; - - smp_mb(); - - __asm__ __volatile__( - "0: mov %[delay], 1 \n" - "1: llock %[val], [%[rwlock]] \n" - " brls %[val], %[WR_LOCKED], 4f\n" /* <= 0: already write locked, bail */ - " sub %[val], %[val], 1 \n" /* counter-- */ - " scond %[val], [%[rwlock]] \n" - " bz.d 4f \n" - " mov.z %[got_it], 1 \n" /* got it */ - " \n" - SCOND_FAIL_RETRY_ASM - - : [val] "=&r" (val), - [got_it] "+&r" (got_it) - SCOND_FAIL_RETRY_VARS - : [rwlock] "r" (&(rw->counter)), - [WR_LOCKED] "ir" (0) - : "memory", "cc"); - - smp_mb(); - - return got_it; -} - -static inline void arch_write_lock(arch_rwlock_t *rw) -{ - unsigned int val; - SCOND_FAIL_RETRY_VAR_DEF; - - smp_mb(); - - /* - * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__), - * deny writer. Otherwise if unlocked grant to writer - * Hence the claim that Linux rwlocks are unfair to writers. - * (can be starved for an indefinite time by readers). - * - * if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) { - * rw->counter = 0; - * ret = 1; - * } - */ - - __asm__ __volatile__( - "0: mov %[delay], 1 \n" - "1: llock %[val], [%[rwlock]] \n" - " brne %[val], %[UNLOCKED], 0b \n" /* while !UNLOCKED spin */ - " mov %[val], %[WR_LOCKED] \n" - " scond %[val], [%[rwlock]] \n" - " bz 4f \n" - " \n" - SCOND_FAIL_RETRY_ASM - - : [val] "=&r" (val) - SCOND_FAIL_RETRY_VARS - : [rwlock] "r" (&(rw->counter)), - [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__), - [WR_LOCKED] "ir" (0) - : "memory", "cc"); - - smp_mb(); -} - -/* 1 - lock taken successfully */ -static inline int arch_write_trylock(arch_rwlock_t *rw) -{ - unsigned int val, got_it = 0; - SCOND_FAIL_RETRY_VAR_DEF; - - smp_mb(); - - __asm__ __volatile__( - "0: mov %[delay], 1 \n" - "1: llock %[val], [%[rwlock]] \n" - " brne %[val], %[UNLOCKED], 4f \n" /* !UNLOCKED, bail */ - " mov %[val], %[WR_LOCKED] \n" - " scond %[val], [%[rwlock]] \n" - " bz.d 4f \n" - " mov.z %[got_it], 1 \n" /* got it */ - " \n" - SCOND_FAIL_RETRY_ASM - - : [val] "=&r" (val), - [got_it] "+&r" (got_it) - SCOND_FAIL_RETRY_VARS - : [rwlock] "r" (&(rw->counter)), - [UNLOCKED] "ir" (__ARCH_RW_LOCK_UNLOCKED__), - [WR_LOCKED] "ir" (0) - : "memory", "cc"); - - smp_mb(); - - return got_it; -} - -static inline void arch_read_unlock(arch_rwlock_t *rw) -{ - unsigned int val; - - smp_mb(); - - /* - * rw->counter++; - */ - __asm__ __volatile__( - "1: llock %[val], [%[rwlock]] \n" - " add %[val], %[val], 1 \n" - " scond %[val], [%[rwlock]] \n" - " bnz 1b \n" - " \n" - : [val] "=&r" (val) - : [rwlock] "r" (&(rw->counter)) - : "memory", "cc"); - - smp_mb(); -} - -static inline void arch_write_unlock(arch_rwlock_t *rw) -{ - unsigned int val; - - smp_mb(); - - /* - * rw->counter = __ARCH_RW_LOCK_UNLOCKED__; - */ - __asm__ __volatile__( - "1: llock %[val], [%[rwlock]] \n" - " scond %[UNLOCKED], [%[rwlock]]\n" - " bnz 1b \n" - " \n" - : [val] "=&r" (val) - : [rwlock] "r" (&(rw->counter)), - [UNLOCKED] "r" (__ARCH_RW_LOCK_UNLOCKED__) - : "memory", "cc"); - - smp_mb(); -} - -#undef SCOND_FAIL_RETRY_VAR_DEF -#undef SCOND_FAIL_RETRY_ASM -#undef SCOND_FAIL_RETRY_VARS - -#endif /* CONFIG_ARC_STAR_9000923308 */ - #else /* !CONFIG_ARC_HAS_LLSC */ static inline void arch_spin_lock(arch_spinlock_t *lock) diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h index 3af67455659a..2d79e527fa50 100644 --- a/arch/arc/include/asm/thread_info.h +++ b/arch/arc/include/asm/thread_info.h @@ -103,7 +103,7 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void) /* * _TIF_ALLWORK_MASK includes SYSCALL_TRACE, but we don't need it. - * SYSCALL_TRACE is anways seperately/unconditionally tested right after a + * SYSCALL_TRACE is anyway seperately/unconditionally tested right after a * syscall, so all that reamins to be tested is _TIF_WORK_MASK */ diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h index d1da6032b715..a78d5670884f 100644 --- a/arch/arc/include/asm/uaccess.h +++ b/arch/arc/include/asm/uaccess.h @@ -32,7 +32,7 @@ #define __kernel_ok (segment_eq(get_fs(), KERNEL_DS)) /* - * Algorthmically, for __user_ok() we want do: + * Algorithmically, for __user_ok() we want do: * (start < TASK_SIZE) && (start+len < TASK_SIZE) * where TASK_SIZE could either be retrieved from thread_info->addr_limit or * emitted directly in code. diff --git a/arch/arc/include/uapi/asm/swab.h b/arch/arc/include/uapi/asm/swab.h index 095599a73195..71f3918b0fc3 100644 --- a/arch/arc/include/uapi/asm/swab.h +++ b/arch/arc/include/uapi/asm/swab.h @@ -74,7 +74,7 @@ __tmp ^ __in; \ }) -#elif (ARC_BSWAP_TYPE == 2) /* Custom single cycle bwap instruction */ +#elif (ARC_BSWAP_TYPE == 2) /* Custom single cycle bswap instruction */ #define __arch_swab32(x) \ ({ \ diff --git a/arch/arc/kernel/entry-compact.S b/arch/arc/kernel/entry-compact.S index 0cb0abaa0479..98812c1248df 100644 --- a/arch/arc/kernel/entry-compact.S +++ b/arch/arc/kernel/entry-compact.S @@ -91,27 +91,13 @@ VECTOR mem_service ; 0x8, Mem exception (0x1) VECTOR instr_service ; 0x10, Instrn Error (0x2) ; ******************** Device ISRs ********************** -#ifdef CONFIG_ARC_IRQ3_LV2 +#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS VECTOR handle_interrupt_level2 #else VECTOR handle_interrupt_level1 #endif -VECTOR handle_interrupt_level1 - -#ifdef CONFIG_ARC_IRQ5_LV2 -VECTOR handle_interrupt_level2 -#else -VECTOR handle_interrupt_level1 -#endif - -#ifdef CONFIG_ARC_IRQ6_LV2 -VECTOR handle_interrupt_level2 -#else -VECTOR handle_interrupt_level1 -#endif - -.rept 25 +.rept 28 VECTOR handle_interrupt_level1 ; Other devices .endr diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c index c5cceca36118..ce9deb953ca9 100644 --- a/arch/arc/kernel/intc-compact.c +++ b/arch/arc/kernel/intc-compact.c @@ -28,10 +28,8 @@ void arc_init_IRQ(void) { int level_mask = 0; - /* setup any high priority Interrupts (Level2 in ARCompact jargon) */ - level_mask |= IS_ENABLED(CONFIG_ARC_IRQ3_LV2) << 3; - level_mask |= IS_ENABLED(CONFIG_ARC_IRQ5_LV2) << 5; - level_mask |= IS_ENABLED(CONFIG_ARC_IRQ6_LV2) << 6; + /* Is timer high priority Interrupt (Level2 in ARCompact jargon) */ + level_mask |= IS_ENABLED(CONFIG_ARC_COMPACT_IRQ_LEVELS) << TIMER0_IRQ; /* * Write to register, even if no LV2 IRQs configured to reset it diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 6fd48021324b..08f03d9b5b3e 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -108,7 +108,7 @@ static void arc_perf_event_update(struct perf_event *event, int64_t delta = new_raw_count - prev_raw_count; /* - * We don't afaraid of hwc->prev_count changing beneath our feet + * We aren't afraid of hwc->prev_count changing beneath our feet * because there's no way for us to re-enter this function anytime. */ local64_set(&hwc->prev_count, new_raw_count); diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index f63b8bfefb0c..2ee7a4d758a8 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -392,7 +392,7 @@ void __init setup_arch(char **cmdline_p) /* * If we are here, it is established that @uboot_arg didn't * point to DT blob. Instead if u-boot says it is cmdline, - * Appent to embedded DT cmdline. + * append to embedded DT cmdline. * setup_machine_fdt() would have populated @boot_command_line */ if (uboot_tag == 1) { diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index 004b7f0bc76c..6cb3736b6b83 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -34,7 +34,7 @@ * -ViXS were still seeing crashes when using insmod to load drivers. * It turned out that the code to change Execute permssions for TLB entries * of user was not guarded for interrupts (mod_tlb_permission) - * This was cauing TLB entries to be overwritten on unrelated indexes + * This was causing TLB entries to be overwritten on unrelated indexes * * Vineetg: July 15th 2008: Bug #94183 * -Exception happens in Delay slot of a JMP, and before user space resumes, diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index e0efff15a5ae..b9192a653b7e 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -142,7 +142,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, * prelogue is setup (callee regs saved and then fp set and not other * way around */ - pr_warn("CONFIG_ARC_DW2_UNWIND needs to be enabled\n"); + pr_warn_once("CONFIG_ARC_DW2_UNWIND needs to be enabled\n"); return 0; #endif diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index a6f91e88ce36..934150e7ac48 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -276,7 +276,7 @@ static int tlb_stats_open(struct inode *inode, struct file *file) return 0; } -/* called on user read(): display the couters */ +/* called on user read(): display the counters */ static ssize_t tlb_stats_output(struct file *file, /* file descriptor */ char __user *user_buf, /* user buffer */ size_t len, /* length of buffer */ diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 9e5eddbb856f..5a294b2c3cb3 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -215,7 +215,7 @@ void read_decode_cache_bcr(void) * ------------------ * This ver of MMU supports variable page sizes (1k-16k): although Linux will * only support 8k (default), 16k and 4k. - * However from hardware perspective, smaller page sizes aggrevate aliasing + * However from hardware perspective, smaller page sizes aggravate aliasing * meaning more vaddr bits needed to disambiguate the cache-line-op ; * the existing scheme of piggybacking won't work for certain configurations. * Two new registers IC_PTAG and DC_PTAG inttoduced. @@ -302,7 +302,7 @@ void __cache_line_loop_v3(phys_addr_t paddr, unsigned long vaddr, /* * This is technically for MMU v4, using the MMU v3 programming model - * Special work for HS38 aliasing I-cache configuratino with PAE40 + * Special work for HS38 aliasing I-cache configuration with PAE40 * - upper 8 bits of paddr need to be written into PTAG_HI * - (and needs to be written before the lower 32 bits) * Note that PTAG_HI is hoisted outside the line loop @@ -936,7 +936,7 @@ void arc_cache_init(void) ic->ver, CONFIG_ARC_MMU_VER); /* - * In MMU v4 (HS38x) the alising icache config uses IVIL/PTAG + * In MMU v4 (HS38x) the aliasing icache config uses IVIL/PTAG * pair to provide vaddr/paddr respectively, just as in MMU v3 */ if (is_isa_arcv2() && ic->alias) diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 8c8e36fa5659..73d7e4c75b7d 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -10,7 +10,7 @@ * DMA Coherent API Notes * * I/O is inherently non-coherent on ARC. So a coherent DMA buffer is - * implemented by accessintg it using a kernel virtual address, with + * implemented by accessing it using a kernel virtual address, with * Cache bit off in the TLB entry. * * The default DMA address == Phy address which is 0x8000_0000 based. diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index 06b6c2d695bf..414b42710a36 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -741,6 +741,7 @@ dtb-$(CONFIG_MACH_SUN7I) += \ sun7i-a20-olimex-som-evb.dtb \ sun7i-a20-olinuxino-lime.dtb \ sun7i-a20-olinuxino-lime2.dtb \ + sun7i-a20-olinuxino-lime2-emmc.dtb \ sun7i-a20-olinuxino-micro.dtb \ sun7i-a20-orangepi.dtb \ sun7i-a20-orangepi-mini.dtb \ diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts index d82dd6e3f9b1..5687d6b4da60 100644 --- a/arch/arm/boot/dts/am437x-sk-evm.dts +++ b/arch/arm/boot/dts/am437x-sk-evm.dts @@ -418,7 +418,7 @@ &i2c0 { status = "okay"; pinctrl-names = "default"; pinctrl-0 = <&i2c0_pins>; - clock-frequency = <400000>; + clock-frequency = <100000>; tps@24 { compatible = "ti,tps65218"; diff --git a/arch/arm/boot/dts/am57xx-idk-common.dtsi b/arch/arm/boot/dts/am57xx-idk-common.dtsi index b01a5948cdd0..0e63b9dff6e7 100644 --- a/arch/arm/boot/dts/am57xx-idk-common.dtsi +++ b/arch/arm/boot/dts/am57xx-idk-common.dtsi @@ -60,10 +60,26 @@ tps659038: tps659038@58 { tps659038_pmic { compatible = "ti,tps659038-pmic"; + + smps12-in-supply = <&vmain>; + smps3-in-supply = <&vmain>; + smps45-in-supply = <&vmain>; + smps6-in-supply = <&vmain>; + smps7-in-supply = <&vmain>; + smps8-in-supply = <&vmain>; + smps9-in-supply = <&vmain>; + ldo1-in-supply = <&vmain>; + ldo2-in-supply = <&vmain>; + ldo3-in-supply = <&vmain>; + ldo4-in-supply = <&vmain>; + ldo9-in-supply = <&vmain>; + ldoln-in-supply = <&vmain>; + ldousb-in-supply = <&vmain>; + ldortc-in-supply = <&vmain>; + regulators { smps12_reg: smps12 { /* VDD_MPU */ - vin-supply = <&vmain>; regulator-name = "smps12"; regulator-min-microvolt = <850000>; regulator-max-microvolt = <1250000>; @@ -73,7 +89,6 @@ smps12_reg: smps12 { smps3_reg: smps3 { /* VDD_DDR EMIF1 EMIF2 */ - vin-supply = <&vmain>; regulator-name = "smps3"; regulator-min-microvolt = <1350000>; regulator-max-microvolt = <1350000>; @@ -84,7 +99,6 @@ smps3_reg: smps3 { smps45_reg: smps45 { /* VDD_DSPEVE on AM572 */ /* VDD_IVA + VDD_DSP on AM571 */ - vin-supply = <&vmain>; regulator-name = "smps45"; regulator-min-microvolt = <850000>; regulator-max-microvolt = <1250000>; @@ -94,7 +108,6 @@ smps45_reg: smps45 { smps6_reg: smps6 { /* VDD_GPU */ - vin-supply = <&vmain>; regulator-name = "smps6"; regulator-min-microvolt = <850000>; regulator-max-microvolt = <1250000>; @@ -104,7 +117,6 @@ smps6_reg: smps6 { smps7_reg: smps7 { /* VDD_CORE */ - vin-supply = <&vmain>; regulator-name = "smps7"; regulator-min-microvolt = <850000>; regulator-max-microvolt = <1150000>; @@ -115,13 +127,11 @@ smps7_reg: smps7 { smps8_reg: smps8 { /* 5728 - VDD_IVAHD */ /* 5718 - N.C. test point */ - vin-supply = <&vmain>; regulator-name = "smps8"; }; smps9_reg: smps9 { /* VDD_3_3D */ - vin-supply = <&vmain>; regulator-name = "smps9"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; @@ -132,7 +142,6 @@ smps9_reg: smps9 { ldo1_reg: ldo1 { /* VDDSHV8 - VSDMMC */ /* NOTE: on rev 1.3a, data supply */ - vin-supply = <&vmain>; regulator-name = "ldo1"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; @@ -142,7 +151,6 @@ ldo1_reg: ldo1 { ldo2_reg: ldo2 { /* VDDSH18V */ - vin-supply = <&vmain>; regulator-name = "ldo2"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -152,7 +160,6 @@ ldo2_reg: ldo2 { ldo3_reg: ldo3 { /* R1.3a 572x V1_8PHY_LDO3: USB, SATA */ - vin-supply = <&vmain>; regulator-name = "ldo3"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -162,7 +169,6 @@ ldo3_reg: ldo3 { ldo4_reg: ldo4 { /* R1.3a 572x V1_8PHY_LDO4: PCIE, HDMI*/ - vin-supply = <&vmain>; regulator-name = "ldo4"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -174,7 +180,6 @@ ldo4_reg: ldo4 { ldo9_reg: ldo9 { /* VDD_RTC */ - vin-supply = <&vmain>; regulator-name = "ldo9"; regulator-min-microvolt = <840000>; regulator-max-microvolt = <1160000>; @@ -184,7 +189,6 @@ ldo9_reg: ldo9 { ldoln_reg: ldoln { /* VDDA_1V8_PLL */ - vin-supply = <&vmain>; regulator-name = "ldoln"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -194,7 +198,6 @@ ldoln_reg: ldoln { ldousb_reg: ldousb { /* VDDA_3V_USB: VDDA_USBHS33 */ - vin-supply = <&vmain>; regulator-name = "ldousb"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; @@ -204,7 +207,6 @@ ldousb_reg: ldousb { ldortc_reg: ldortc { /* VDDA_RTC */ - vin-supply = <&vmain>; regulator-name = "ldortc"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; diff --git a/arch/arm/boot/dts/armada-385-linksys.dtsi b/arch/arm/boot/dts/armada-385-linksys.dtsi index 8450944b28e6..22f7a13e20b4 100644 --- a/arch/arm/boot/dts/armada-385-linksys.dtsi +++ b/arch/arm/boot/dts/armada-385-linksys.dtsi @@ -58,8 +58,8 @@ memory { soc { ranges = ; + MBUS_ID(0x09, 0x19) 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000>; internal-regs { diff --git a/arch/arm/boot/dts/dm8148-evm.dts b/arch/arm/boot/dts/dm8148-evm.dts index cbc17b0794b1..4128fa91823c 100644 --- a/arch/arm/boot/dts/dm8148-evm.dts +++ b/arch/arm/boot/dts/dm8148-evm.dts @@ -93,6 +93,10 @@ partition@0x780000 { }; }; +&mmc1 { + status = "disabled"; +}; + &mmc2 { pinctrl-names = "default"; pinctrl-0 = <&sd1_pins>; @@ -101,6 +105,10 @@ &mmc2 { cd-gpios = <&gpio2 6 GPIO_ACTIVE_LOW>; }; +&mmc3 { + status = "disabled"; +}; + &pincntl { sd1_pins: pinmux_sd1_pins { pinctrl-single,pins = < diff --git a/arch/arm/boot/dts/dm8148-t410.dts b/arch/arm/boot/dts/dm8148-t410.dts index 5d4313fd5a46..3f184863e0c5 100644 --- a/arch/arm/boot/dts/dm8148-t410.dts +++ b/arch/arm/boot/dts/dm8148-t410.dts @@ -45,6 +45,14 @@ &cpsw_emac1 { phy-mode = "rgmii"; }; +&mmc1 { + status = "disabled"; +}; + +&mmc2 { + status = "disabled"; +}; + &mmc3 { pinctrl-names = "default"; pinctrl-0 = <&sd2_pins>; @@ -53,6 +61,7 @@ &mmc3 { dmas = <&edma_xbar 8 0 1 /* use SDTXEVT1 instead of MCASP0TX */ &edma_xbar 9 0 2>; /* use SDRXEVT1 instead of MCASP0RX */ dma-names = "tx", "rx"; + non-removable; }; &pincntl { diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index e0074014385a..3a8f3976f6f9 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -1451,6 +1451,8 @@ gpmc: gpmc@50000000 { ti,hwmods = "gpmc"; reg = <0x50000000 0x37c>; /* device IO registers */ interrupts = ; + dmas = <&edma_xbar 4 0>; + dma-names = "rxtx"; gpmc,num-cs = <8>; gpmc,num-waitpins = <2>; #address-cells = <2>; diff --git a/arch/arm/boot/dts/dra74x.dtsi b/arch/arm/boot/dts/dra74x.dtsi index 4220eeffc65a..5e06020f450b 100644 --- a/arch/arm/boot/dts/dra74x.dtsi +++ b/arch/arm/boot/dts/dra74x.dtsi @@ -107,8 +107,8 @@ &dss { reg = <0x58000000 0x80>, <0x58004054 0x4>, <0x58004300 0x20>, - <0x58005054 0x4>, - <0x58005300 0x20>; + <0x58009054 0x4>, + <0x58009300 0x20>; reg-names = "dss", "pll1_clkctrl", "pll1", "pll2_clkctrl", "pll2"; diff --git a/arch/arm/boot/dts/exynos5250-snow-common.dtsi b/arch/arm/boot/dts/exynos5250-snow-common.dtsi index ddfe1f558c10..fa14f77df563 100644 --- a/arch/arm/boot/dts/exynos5250-snow-common.dtsi +++ b/arch/arm/boot/dts/exynos5250-snow-common.dtsi @@ -242,7 +242,7 @@ &dp { hpd-gpios = <&gpx0 7 GPIO_ACTIVE_HIGH>; ports { - port0 { + port { dp_out: endpoint { remote-endpoint = <&bridge_in>; }; @@ -485,13 +485,20 @@ ptn3460: lvds-bridge@20 { edid-emulation = <5>; ports { - port0 { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + bridge_out: endpoint { remote-endpoint = <&panel_in>; }; }; - port1 { + port@1 { + reg = <1>; + bridge_in: endpoint { remote-endpoint = <&dp_out>; }; diff --git a/arch/arm/boot/dts/exynos5420-peach-pit.dts b/arch/arm/boot/dts/exynos5420-peach-pit.dts index f9d2e4f1a0e0..1de972d46a87 100644 --- a/arch/arm/boot/dts/exynos5420-peach-pit.dts +++ b/arch/arm/boot/dts/exynos5420-peach-pit.dts @@ -163,7 +163,7 @@ &dp { hpd-gpios = <&gpx2 6 GPIO_ACTIVE_HIGH>; ports { - port0 { + port { dp_out: endpoint { remote-endpoint = <&bridge_in>; }; @@ -631,13 +631,20 @@ ps8625: lvds-bridge@48 { use-external-pwm; ports { - port0 { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + bridge_out: endpoint { remote-endpoint = <&panel_in>; }; }; - port1 { + port@1 { + reg = <1>; + bridge_in: endpoint { remote-endpoint = <&dp_out>; }; diff --git a/arch/arm/boot/dts/omap3-evm-37xx.dts b/arch/arm/boot/dts/omap3-evm-37xx.dts index 76056ba92ced..ed449827c3d3 100644 --- a/arch/arm/boot/dts/omap3-evm-37xx.dts +++ b/arch/arm/boot/dts/omap3-evm-37xx.dts @@ -85,7 +85,7 @@ mmc2_pins: pinmux_mmc2_pins { OMAP3_CORE1_IOPAD(0x2158, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_clk.sdmmc2_clk */ OMAP3_CORE1_IOPAD(0x215a, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_cmd.sdmmc2_cmd */ OMAP3_CORE1_IOPAD(0x215c, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat0.sdmmc2_dat0 */ - OMAP3_CORE1_IOPAD(0x215e, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat1.sdmmc2_dat1 */ + OMAP3_CORE1_IOPAD(0x215e, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat1.sdmmc2_dat1 */ OMAP3_CORE1_IOPAD(0x2160, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat2.sdmmc2_dat2 */ OMAP3_CORE1_IOPAD(0x2162, PIN_INPUT_PULLUP | MUX_MODE0) /* sdmmc2_dat3.sdmmc2_dat3 */ >; diff --git a/arch/arm/boot/dts/omap3-igep.dtsi b/arch/arm/boot/dts/omap3-igep.dtsi index 41f5d386f21f..f4f2ce46d681 100644 --- a/arch/arm/boot/dts/omap3-igep.dtsi +++ b/arch/arm/boot/dts/omap3-igep.dtsi @@ -188,6 +188,7 @@ &mmc1 { vmmc-supply = <&vmmc1>; vmmc_aux-supply = <&vsim>; bus-width = <4>; + cd-gpios = <&twl_gpio 0 GPIO_ACTIVE_LOW>; }; &mmc3 { diff --git a/arch/arm/boot/dts/omap3-igep0020-common.dtsi b/arch/arm/boot/dts/omap3-igep0020-common.dtsi index d6f839cab649..b6971060648a 100644 --- a/arch/arm/boot/dts/omap3-igep0020-common.dtsi +++ b/arch/arm/boot/dts/omap3-igep0020-common.dtsi @@ -194,6 +194,12 @@ OMAP3630_CORE2_IOPAD(0x25f6, PIN_OUTPUT | MUX_MODE4) /* etk_d13.gpio_27 */ OMAP3630_CORE2_IOPAD(0x25f8, PIN_OUTPUT | MUX_MODE4) /* etk_d14.gpio_28 */ >; }; + + mmc1_wp_pins: pinmux_mmc1_cd_pins { + pinctrl-single,pins = < + OMAP3630_CORE2_IOPAD(0x25fa, PIN_INPUT | MUX_MODE4) /* etk_d15.gpio_29 */ + >; + }; }; &i2c3 { @@ -250,3 +256,8 @@ dpi_out: endpoint { }; }; }; + +&mmc1 { + pinctrl-0 = <&mmc1_pins &mmc1_wp_pins>; + wp-gpios = <&gpio1 29 GPIO_ACTIVE_LOW>; /* gpio_29 */ +}; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index d9e2d9c6e999..2b74a81d1de2 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -288,7 +288,7 @@ ssi_pins: pinmux_ssi { pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLUP | MUX_MODE1) /* ssi1_rdy_tx */ OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE1) /* ssi1_flag_tx */ - OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */ + OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4) /* ssi1_wake_tx (cawake) */ OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE1) /* ssi1_dat_tx */ OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE1) /* ssi1_dat_rx */ OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE1) /* ssi1_flag_rx */ @@ -300,7 +300,7 @@ OMAP3_CORE1_IOPAD(0x218a, PIN_OUTPUT | MUX_MODE1) /* ssi1_wake */ modem_pins: pinmux_modem { pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x20dc, PIN_OUTPUT | MUX_MODE4) /* gpio 70 => cmt_apeslpx */ - OMAP3_CORE1_IOPAD(0x20e0, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* gpio 72 => ape_rst_rq */ + OMAP3_CORE1_IOPAD(0x20e0, PIN_INPUT | MUX_MODE4) /* gpio 72 => ape_rst_rq */ OMAP3_CORE1_IOPAD(0x20e2, PIN_OUTPUT | MUX_MODE4) /* gpio 73 => cmt_rst_rq */ OMAP3_CORE1_IOPAD(0x20e4, PIN_OUTPUT | MUX_MODE4) /* gpio 74 => cmt_en */ OMAP3_CORE1_IOPAD(0x20e6, PIN_OUTPUT | MUX_MODE4) /* gpio 75 => cmt_rst */ diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi index a00ca761675d..927b17fc4ed8 100644 --- a/arch/arm/boot/dts/omap3-n950-n9.dtsi +++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi @@ -97,7 +97,7 @@ ssi_pins: pinmux_ssi_pins { OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE1) /* ssi1_dat_tx */ OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE1) /* ssi1_flag_tx */ OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLUP | MUX_MODE1) /* ssi1_rdy_tx */ - OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */ + OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4) /* ssi1_wake_tx (cawake) */ OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE1) /* ssi1_dat_rx */ OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE1) /* ssi1_flag_rx */ OMAP3_CORE1_IOPAD(0x2188, PIN_OUTPUT | MUX_MODE1) /* ssi1_rdy_rx */ @@ -110,7 +110,7 @@ ssi_pins_idle: pinmux_ssi_pins_idle { OMAP3_CORE1_IOPAD(0x217c, PIN_OUTPUT | MUX_MODE7) /* ssi1_dat_tx */ OMAP3_CORE1_IOPAD(0x217e, PIN_OUTPUT | MUX_MODE7) /* ssi1_flag_tx */ OMAP3_CORE1_IOPAD(0x2180, PIN_INPUT_PULLDOWN | MUX_MODE7) /* ssi1_rdy_tx */ - OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* ssi1_wake_tx (cawake) */ + OMAP3_CORE1_IOPAD(0x2182, PIN_INPUT | MUX_MODE4) /* ssi1_wake_tx (cawake) */ OMAP3_CORE1_IOPAD(0x2184, PIN_INPUT | MUX_MODE7) /* ssi1_dat_rx */ OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE7) /* ssi1_flag_rx */ OMAP3_CORE1_IOPAD(0x2188, PIN_OUTPUT | MUX_MODE4) /* ssi1_rdy_rx */ @@ -120,7 +120,7 @@ OMAP3_CORE1_IOPAD(0x218a, PIN_OUTPUT | MUX_MODE7) /* ssi1_wake */ modem_pins1: pinmux_modem_core1_pins { pinctrl-single,pins = < - OMAP3_CORE1_IOPAD(0x207a, PIN_INPUT | WAKEUP_EN | MUX_MODE4) /* gpio_34 (ape_rst_rq) */ + OMAP3_CORE1_IOPAD(0x207a, PIN_INPUT | MUX_MODE4) /* gpio_34 (ape_rst_rq) */ OMAP3_CORE1_IOPAD(0x2100, PIN_OUTPUT | MUX_MODE4) /* gpio_88 (cmt_rst_rq) */ OMAP3_CORE1_IOPAD(0x210a, PIN_OUTPUT | MUX_MODE4) /* gpio_93 (cmt_apeslpx) */ >; diff --git a/arch/arm/boot/dts/omap3-zoom3.dts b/arch/arm/boot/dts/omap3-zoom3.dts index f19170bdcc1f..c29b41dc7b95 100644 --- a/arch/arm/boot/dts/omap3-zoom3.dts +++ b/arch/arm/boot/dts/omap3-zoom3.dts @@ -98,7 +98,7 @@ uart2_pins: pinmux_uart2_pins { pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x2174, PIN_INPUT_PULLUP | MUX_MODE0) /* uart2_cts.uart2_cts */ OMAP3_CORE1_IOPAD(0x2176, PIN_OUTPUT | MUX_MODE0) /* uart2_rts.uart2_rts */ - OMAP3_CORE1_IOPAD(0x217a, WAKEUP_EN | PIN_INPUT | MUX_MODE0) /* uart2_rx.uart2_rx */ + OMAP3_CORE1_IOPAD(0x217a, PIN_INPUT | MUX_MODE0) /* uart2_rx.uart2_rx */ OMAP3_CORE1_IOPAD(0x2178, PIN_OUTPUT | MUX_MODE0) /* uart2_tx.uart2_tx */ >; }; @@ -107,7 +107,7 @@ uart3_pins: pinmux_uart3_pins { pinctrl-single,pins = < OMAP3_CORE1_IOPAD(0x219a, PIN_INPUT_PULLDOWN | MUX_MODE0) /* uart3_cts_rctx.uart3_cts_rctx */ OMAP3_CORE1_IOPAD(0x219c, PIN_OUTPUT | MUX_MODE0) /* uart3_rts_sd.uart3_rts_sd */ - OMAP3_CORE1_IOPAD(0x219e, WAKEUP_EN | PIN_INPUT | MUX_MODE0) /* uart3_rx_irrx.uart3_rx_irrx */ + OMAP3_CORE1_IOPAD(0x219e, PIN_INPUT | MUX_MODE0) /* uart3_rx_irrx.uart3_rx_irrx */ OMAP3_CORE1_IOPAD(0x21a0, PIN_OUTPUT | MUX_MODE0) /* uart3_tx_irtx.uart3_tx_irtx */ >; }; @@ -125,7 +125,7 @@ mmc3_2_pins: pinmux_mmc3_2_pins { pinctrl-single,pins = < OMAP3630_CORE2_IOPAD(0x25d8, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_clk.sdmmc3_clk */ OMAP3630_CORE2_IOPAD(0x25e4, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d4.sdmmc3_dat0 */ - OMAP3630_CORE2_IOPAD(0x25e6, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d5.sdmmc3_dat1 */ + OMAP3630_CORE2_IOPAD(0x25e6, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d5.sdmmc3_dat1 */ OMAP3630_CORE2_IOPAD(0x25e8, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d6.sdmmc3_dat2 */ OMAP3630_CORE2_IOPAD(0x25e2, PIN_INPUT_PULLUP | MUX_MODE2) /* etk_d3.sdmmc3_dat3 */ >; diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index dc759a3028b7..5d5b620b7d9b 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -14,6 +14,29 @@ aliases { display0 = &hdmi0; }; + vmain: fixedregulator-vmain { + compatible = "regulator-fixed"; + regulator-name = "vmain"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + vsys_cobra: fixedregulator-vsys_cobra { + compatible = "regulator-fixed"; + regulator-name = "vsys_cobra"; + vin-supply = <&vmain>; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + vdds_1v8_main: fixedregulator-vdds_1v8_main { + compatible = "regulator-fixed"; + regulator-name = "vdds_1v8_main"; + vin-supply = <&smps7_reg>; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + vmmcsd_fixed: fixedregulator-mmcsd { compatible = "regulator-fixed"; regulator-name = "vmmcsd_fixed"; @@ -309,7 +332,7 @@ OMAP5_IOPAD(0x05a, PIN_OUTPUT | MUX_MODE0) /* fref_clk1_out, USB hub clk */ wlcore_irq_pin: pinmux_wlcore_irq_pin { pinctrl-single,pins = < - OMAP5_IOPAD(0x40, WAKEUP_EN | PIN_INPUT_PULLUP | MUX_MODE6) /* llia_wakereqin.gpio1_wk14 */ + OMAP5_IOPAD(0x40, PIN_INPUT_PULLUP | MUX_MODE6) /* llia_wakereqin.gpio1_wk14 */ >; }; }; @@ -409,6 +432,26 @@ palmas_pmic { ti,ldo6-vibrator; + smps123-in-supply = <&vsys_cobra>; + smps45-in-supply = <&vsys_cobra>; + smps6-in-supply = <&vsys_cobra>; + smps7-in-supply = <&vsys_cobra>; + smps8-in-supply = <&vsys_cobra>; + smps9-in-supply = <&vsys_cobra>; + smps10_out2-in-supply = <&vsys_cobra>; + smps10_out1-in-supply = <&vsys_cobra>; + ldo1-in-supply = <&vsys_cobra>; + ldo2-in-supply = <&vsys_cobra>; + ldo3-in-supply = <&vdds_1v8_main>; + ldo4-in-supply = <&vdds_1v8_main>; + ldo5-in-supply = <&vsys_cobra>; + ldo6-in-supply = <&vdds_1v8_main>; + ldo7-in-supply = <&vsys_cobra>; + ldo8-in-supply = <&vsys_cobra>; + ldo9-in-supply = <&vmmcsd_fixed>; + ldoln-in-supply = <&vsys_cobra>; + ldousb-in-supply = <&vsys_cobra>; + regulators { smps123_reg: smps123 { /* VDD_OPP_MPU */ @@ -600,7 +643,8 @@ twl6040: twl@4b { pinctrl-0 = <&twl6040_pins>; interrupts = ; /* IRQ_SYS_2N cascaded to gic */ - ti,audpwron-gpio = <&gpio5 13 GPIO_ACTIVE_HIGH>; /* gpio line 141 */ + + /* audpwron gpio defined in the board specific dts */ vio-supply = <&smps7_reg>; v2v1-supply = <&smps9_reg>; diff --git a/arch/arm/boot/dts/omap5-igep0050.dts b/arch/arm/boot/dts/omap5-igep0050.dts index 46ecb1dd3b5c..f75ce02fb398 100644 --- a/arch/arm/boot/dts/omap5-igep0050.dts +++ b/arch/arm/boot/dts/omap5-igep0050.dts @@ -35,6 +35,22 @@ tca6416: tca6416@21 { }; }; +/* LDO4 is VPP1 - ball AD9 */ +&ldo4_reg { + regulator-min-microvolt = <2000000>; + regulator-max-microvolt = <2000000>; +}; + +/* + * LDO7 is used for HDMI: VDDA_DSIPORTA - ball AA33, VDDA_DSIPORTC - ball AE33, + * VDDA_HDMI - ball AN25 + */ +&ldo7_reg { + status = "okay"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; +}; + &omap5_pmx_core { i2c4_pins: pinmux_i2c4_pins { pinctrl-single,pins = < @@ -52,3 +68,13 @@ &tpd12s015 { <&gpio7 3 0>; /* 195, SDA */ }; +&twl6040 { + ti,audpwron-gpio = <&gpio5 16 GPIO_ACTIVE_HIGH>; /* gpio line 144 */ +}; + +&twl6040_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x1c4, PIN_OUTPUT | MUX_MODE6) /* mcspi1_somi.gpio5_144 */ + OMAP5_IOPAD(0x1ca, PIN_OUTPUT | MUX_MODE6) /* perslimbus2_clock.gpio5_145 */ + >; +}; diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts index 60b3fbb3bf07..a51e60518eb6 100644 --- a/arch/arm/boot/dts/omap5-uevm.dts +++ b/arch/arm/boot/dts/omap5-uevm.dts @@ -51,3 +51,13 @@ &tpd12s015 { <&gpio9 1 GPIO_ACTIVE_HIGH>, /* TCA6424A P00, LS OE */ <&gpio7 1 GPIO_ACTIVE_HIGH>; /* GPIO 193, HPD */ }; + +&twl6040 { + ti,audpwron-gpio = <&gpio5 13 GPIO_ACTIVE_HIGH>; /* gpio line 141 */ +}; + +&twl6040_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x1be, PIN_OUTPUT | MUX_MODE6) /* mcspi1_somi.gpio5_141 */ + >; +}; diff --git a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts index a3601e4c0a2e..b844473601d2 100644 --- a/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts +++ b/arch/arm/boot/dts/socfpga_cyclone5_vining_fpga.dts @@ -136,6 +136,7 @@ regulator-usb-nrst { &gmac1 { status = "okay"; phy-mode = "rgmii"; + phy-handle = <&phy1>; snps,reset-gpio = <&porta 0 GPIO_ACTIVE_LOW>; snps,reset-active-low; diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi index ad8ba10764a3..d294e82447a2 100644 --- a/arch/arm/boot/dts/stih407-family.dtsi +++ b/arch/arm/boot/dts/stih407-family.dtsi @@ -24,18 +24,21 @@ gp0_reserved: rproc@40000000 { compatible = "shared-dma-pool"; reg = <0x40000000 0x01000000>; no-map; + status = "disabled"; }; gp1_reserved: rproc@41000000 { compatible = "shared-dma-pool"; reg = <0x41000000 0x01000000>; no-map; + status = "disabled"; }; audio_reserved: rproc@42000000 { compatible = "shared-dma-pool"; reg = <0x42000000 0x01000000>; no-map; + status = "disabled"; }; dmu_reserved: rproc@43000000 { diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index a03e56fb5dbc..ca58eb279d55 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -65,8 +65,9 @@ framebuffer@0 { compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-hdmi"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>, - <&ahb_gates 44>, <&dram_gates 26>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 43>, <&ahb_gates 44>, + <&dram_gates 26>; status = "disabled"; }; @@ -74,8 +75,9 @@ framebuffer@1 { compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_fe0-de_be0-lcd0-hdmi"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>, - <&ahb_gates 44>, <&ahb_gates 46>, + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 43>, <&ahb_gates 44>, + <&ahb_gates 46>, <&dram_gates 25>, <&dram_gates 26>; status = "disabled"; }; @@ -84,9 +86,9 @@ framebuffer@2 { compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_fe0-de_be0-lcd0"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 44>, - <&ahb_gates 46>, <&dram_gates 25>, - <&dram_gates 26>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 44>, <&ahb_gates 46>, + <&dram_gates 25>, <&dram_gates 26>; status = "disabled"; }; @@ -94,8 +96,9 @@ framebuffer@3 { compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_fe0-de_be0-lcd0-tve0"; - clocks = <&pll5 1>, <&ahb_gates 34>, <&ahb_gates 36>, - <&ahb_gates 44>, <&ahb_gates 46>, + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 34>, + <&ahb_gates 36>, <&ahb_gates 44>, + <&ahb_gates 46>, <&dram_gates 5>, <&dram_gates 25>, <&dram_gates 26>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi index bddd0de88af6..367f33012493 100644 --- a/arch/arm/boot/dts/sun5i-a10s.dtsi +++ b/arch/arm/boot/dts/sun5i-a10s.dtsi @@ -65,8 +65,8 @@ framebuffer@0 { compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-hdmi"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>, - <&ahb_gates 44>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 43>, <&ahb_gates 44>; status = "disabled"; }; @@ -74,7 +74,8 @@ framebuffer@1 { compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 44>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 44>; status = "disabled"; }; @@ -82,8 +83,8 @@ framebuffer@2 { compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-tve0"; - clocks = <&pll5 1>, <&ahb_gates 34>, <&ahb_gates 36>, - <&ahb_gates 44>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 34>, + <&ahb_gates 36>, <&ahb_gates 44>; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/sun5i-r8-chip.dts b/arch/arm/boot/dts/sun5i-r8-chip.dts index a8d8b4582397..f694482bdeb6 100644 --- a/arch/arm/boot/dts/sun5i-r8-chip.dts +++ b/arch/arm/boot/dts/sun5i-r8-chip.dts @@ -52,7 +52,7 @@ / { model = "NextThing C.H.I.P."; - compatible = "nextthing,chip", "allwinner,sun5i-r8"; + compatible = "nextthing,chip", "allwinner,sun5i-r8", "allwinner,sun5i-a13"; aliases { i2c0 = &i2c0; diff --git a/arch/arm/boot/dts/sun6i-a31s-primo81.dts b/arch/arm/boot/dts/sun6i-a31s-primo81.dts index 68b479b8772c..73c133f5e79c 100644 --- a/arch/arm/boot/dts/sun6i-a31s-primo81.dts +++ b/arch/arm/boot/dts/sun6i-a31s-primo81.dts @@ -176,8 +176,6 @@ ®_aldo3 { }; ®_dc1sw { - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; regulator-name = "vcc-lcd"; }; diff --git a/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts b/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts index 360adfb1e9ca..d6ad6196a768 100644 --- a/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts +++ b/arch/arm/boot/dts/sun6i-a31s-yones-toptech-bs1078-v2.dts @@ -135,8 +135,6 @@ ®_aldo3 { ®_dc1sw { regulator-name = "vcc-lcd-usb2"; - regulator-min-microvolt = <3000000>; - regulator-max-microvolt = <3000000>; }; ®_dc5ldo { diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi index febdf4c72fb0..2c34bbbb9570 100644 --- a/arch/arm/boot/dts/sun7i-a20.dtsi +++ b/arch/arm/boot/dts/sun7i-a20.dtsi @@ -67,8 +67,9 @@ framebuffer@0 { compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-hdmi"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 43>, - <&ahb_gates 44>, <&dram_gates 26>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 43>, <&ahb_gates 44>, + <&dram_gates 26>; status = "disabled"; }; @@ -76,8 +77,8 @@ framebuffer@1 { compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0"; - clocks = <&pll5 1>, <&ahb_gates 36>, <&ahb_gates 44>, - <&dram_gates 26>; + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 36>, + <&ahb_gates 44>, <&dram_gates 26>; status = "disabled"; }; @@ -85,7 +86,7 @@ framebuffer@2 { compatible = "allwinner,simple-framebuffer", "simple-framebuffer"; allwinner,pipeline = "de_be0-lcd0-tve0"; - clocks = <&pll5 1>, + clocks = <&pll3>, <&pll5 1>, <&ahb_gates 34>, <&ahb_gates 36>, <&ahb_gates 44>, <&dram_gates 5>, <&dram_gates 26>; status = "disabled"; @@ -231,6 +232,7 @@ pll3: clk@01c20010 { pll3x2: pll3x2_clk { #clock-cells = <0>; compatible = "fixed-factor-clock"; + clocks = <&pll3>; clock-div = <1>; clock-mult = <2>; clock-output-names = "pll3-2x"; @@ -272,6 +274,7 @@ pll7: clk@01c20030 { pll7x2: pll7x2_clk { #clock-cells = <0>; compatible = "fixed-factor-clock"; + clocks = <&pll7>; clock-div = <1>; clock-mult = <2>; clock-output-names = "pll7-2x"; diff --git a/arch/arm/boot/dts/tegra30-beaver.dts b/arch/arm/boot/dts/tegra30-beaver.dts index 1eca3b28ac64..b6da15d823a6 100644 --- a/arch/arm/boot/dts/tegra30-beaver.dts +++ b/arch/arm/boot/dts/tegra30-beaver.dts @@ -1843,7 +1843,7 @@ ldo4_reg: ldo4 { ldo5_reg: ldo5 { regulator-name = "vddio_sdmmc,avdd_vdac"; - regulator-min-microvolt = <3300000>; + regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; regulator-always-on; }; @@ -1914,6 +1914,7 @@ i2s@70080400 { sdhci@78000000 { status = "okay"; + vqmmc-supply = <&ldo5_reg>; cd-gpios = <&gpio TEGRA_GPIO(I, 5) GPIO_ACTIVE_LOW>; wp-gpios = <&gpio TEGRA_GPIO(T, 3) GPIO_ACTIVE_HIGH>; power-gpios = <&gpio TEGRA_GPIO(D, 7) GPIO_ACTIVE_HIGH>; diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig index 10f49ab5328e..47195e8690b4 100644 --- a/arch/arm/configs/exynos_defconfig +++ b/arch/arm/configs/exynos_defconfig @@ -82,6 +82,7 @@ CONFIG_TOUCHSCREEN_MMS114=y CONFIG_INPUT_MISC=y CONFIG_INPUT_MAX77693_HAPTIC=y CONFIG_INPUT_MAX8997_HAPTIC=y +CONFIG_KEYBOARD_SAMSUNG=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_SAMSUNG=y CONFIG_SERIAL_SAMSUNG_CONSOLE=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 8f857564657f..8a5fff1b7f6f 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -264,6 +264,7 @@ CONFIG_KEYBOARD_TEGRA=y CONFIG_KEYBOARD_SPEAR=y CONFIG_KEYBOARD_ST_KEYSCAN=y CONFIG_KEYBOARD_CROS_EC=m +CONFIG_KEYBOARD_SAMSUNG=m CONFIG_MOUSE_PS2_ELANTECH=y CONFIG_MOUSE_CYAPA=m CONFIG_MOUSE_ELAN_I2C=y diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index 19cfab526d13..20febb368844 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -29,7 +29,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pmd_t *)get_zeroed_page(GFP_KERNEL | __GFP_REPEAT); + return (pmd_t *)get_zeroed_page(GFP_KERNEL); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index aeddd28b3595..92fd2c8a9af0 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -193,6 +193,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) #define pmd_large(pmd) (pmd_val(pmd) & 2) #define pmd_bad(pmd) (pmd_val(pmd) & 2) +#define pmd_present(pmd) (pmd_val(pmd)) #define copy_pmd(pmdpd,pmdps) \ do { \ diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index fa70db7c714b..2a029bceaf2f 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -211,6 +211,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) : !!(pmd_val(pmd) & (val))) #define pmd_isclear(pmd, val) (!(pmd_val(pmd) & (val))) +#define pmd_present(pmd) (pmd_isset((pmd), L_PMD_SECT_VALID)) #define pmd_young(pmd) (pmd_isset((pmd), PMD_SECT_AF)) #define pte_special(pte) (pte_isset((pte), L_PTE_SPECIAL)) static inline pte_t pte_mkspecial(pte_t pte) @@ -249,10 +250,10 @@ PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF); #define pfn_pmd(pfn,prot) (__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) #define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) -/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */ +/* represent a notpresent pmd by faulting entry, this is used by pmdp_invalidate */ static inline pmd_t pmd_mknotpresent(pmd_t pmd) { - return __pmd(0); + return __pmd(pmd_val(pmd) & ~L_PMD_SECT_VALID); } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 348caabb7625..d62204060cbe 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -182,7 +182,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; #define pgd_offset_k(addr) pgd_offset(&init_mm, addr) #define pmd_none(pmd) (!pmd_val(pmd)) -#define pmd_present(pmd) (pmd_val(pmd)) static inline pte_t *pmd_page_vaddr(pmd_t pmd) { diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index df90bc59bfce..861521606c6d 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -486,7 +486,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = { static void smp_cross_call(const struct cpumask *target, unsigned int ipinr) { - trace_ipi_raise(target, ipi_types[ipinr]); + trace_ipi_raise_rcuidle(target, ipi_types[ipinr]); __smp_cross_call(target, ipinr); } diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 893941ec98dc..f1bde7c4e736 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -263,6 +263,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) kvm_timer_vcpu_terminate(vcpu); kvm_vgic_vcpu_destroy(vcpu); kvm_pmu_vcpu_destroy(vcpu); + kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, vcpu); } diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index e65aa7d11b20..20dcf6e904b2 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -61,7 +61,6 @@ config ARCH_EXYNOS4 select CLKSRC_SAMSUNG_PWM if CPU_EXYNOS4210 select CPU_EXYNOS4210 select GIC_NON_BANKED - select KEYBOARD_SAMSUNG if INPUT_KEYBOARD select MIGHT_HAVE_CACHE_L2X0 help Samsung EXYNOS4 (Cortex-A9) SoC based systems diff --git a/arch/arm/mach-imx/mach-imx6ul.c b/arch/arm/mach-imx/mach-imx6ul.c index a38b16b69923..b56de4b8cdf2 100644 --- a/arch/arm/mach-imx/mach-imx6ul.c +++ b/arch/arm/mach-imx/mach-imx6ul.c @@ -46,7 +46,7 @@ static int ksz8081_phy_fixup(struct phy_device *dev) static void __init imx6ul_enet_phy_init(void) { if (IS_BUILTIN(CONFIG_PHYLIB)) - phy_register_fixup_for_uid(PHY_ID_KSZ8081, 0xffffffff, + phy_register_fixup_for_uid(PHY_ID_KSZ8081, MICREL_PHY_ID_MASK, ksz8081_phy_fixup); } diff --git a/arch/arm/mach-mvebu/Makefile b/arch/arm/mach-mvebu/Makefile index ecf9e0c3b107..e53c6cfcab51 100644 --- a/arch/arm/mach-mvebu/Makefile +++ b/arch/arm/mach-mvebu/Makefile @@ -7,9 +7,15 @@ CFLAGS_pmsu.o := -march=armv7-a obj-$(CONFIG_MACH_MVEBU_ANY) += system-controller.o mvebu-soc-id.o ifeq ($(CONFIG_MACH_MVEBU_V7),y) -obj-y += cpu-reset.o board-v7.o coherency.o coherency_ll.o pmsu.o pmsu_ll.o pm.o pm-board.o +obj-y += cpu-reset.o board-v7.o coherency.o coherency_ll.o pmsu.o pmsu_ll.o + +obj-$(CONFIG_PM) += pm.o pm-board.o obj-$(CONFIG_SMP) += platsmp.o headsmp.o platsmp-a9.o headsmp-a9.o endif obj-$(CONFIG_MACH_DOVE) += dove.o -obj-$(CONFIG_MACH_KIRKWOOD) += kirkwood.o kirkwood-pm.o + +ifeq ($(CONFIG_MACH_KIRKWOOD),y) +obj-y += kirkwood.o +obj-$(CONFIG_PM) += kirkwood-pm.o +endif diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c index 7e989d61159c..e80f0dde2189 100644 --- a/arch/arm/mach-mvebu/coherency.c +++ b/arch/arm/mach-mvebu/coherency.c @@ -162,22 +162,16 @@ static void __init armada_370_coherency_init(struct device_node *np) } /* - * This ioremap hook is used on Armada 375/38x to ensure that PCIe - * memory areas are mapped as MT_UNCACHED instead of MT_DEVICE. This - * is needed as a workaround for a deadlock issue between the PCIe - * interface and the cache controller. + * This ioremap hook is used on Armada 375/38x to ensure that all MMIO + * areas are mapped as MT_UNCACHED instead of MT_DEVICE. This is + * needed for the HW I/O coherency mechanism to work properly without + * deadlock. */ static void __iomem * -armada_pcie_wa_ioremap_caller(phys_addr_t phys_addr, size_t size, - unsigned int mtype, void *caller) +armada_wa_ioremap_caller(phys_addr_t phys_addr, size_t size, + unsigned int mtype, void *caller) { - struct resource pcie_mem; - - mvebu_mbus_get_pcie_mem_aperture(&pcie_mem); - - if (pcie_mem.start <= phys_addr && (phys_addr + size) <= pcie_mem.end) - mtype = MT_UNCACHED; - + mtype = MT_UNCACHED; return __arm_ioremap_caller(phys_addr, size, mtype, caller); } @@ -186,7 +180,8 @@ static void __init armada_375_380_coherency_init(struct device_node *np) struct device_node *cache_dn; coherency_cpu_base = of_iomap(np, 0); - arch_ioremap_caller = armada_pcie_wa_ioremap_caller; + arch_ioremap_caller = armada_wa_ioremap_caller; + pci_ioremap_set_mem_type(MT_UNCACHED); /* * We should switch the PL310 to I/O coherency mode only if diff --git a/arch/arm/mach-omap1/ams-delta-fiq-handler.S b/arch/arm/mach-omap1/ams-delta-fiq-handler.S index 5d7fb596bf4a..bf608441b357 100644 --- a/arch/arm/mach-omap1/ams-delta-fiq-handler.S +++ b/arch/arm/mach-omap1/ams-delta-fiq-handler.S @@ -43,8 +43,8 @@ #define OTHERS_MASK (MODEM_IRQ_MASK | HOOK_SWITCH_MASK) /* IRQ handler register bitmasks */ -#define DEFERRED_FIQ_MASK (0x1 << (INT_DEFERRED_FIQ % IH2_BASE)) -#define GPIO_BANK1_MASK (0x1 << INT_GPIO_BANK1) +#define DEFERRED_FIQ_MASK OMAP_IRQ_BIT(INT_DEFERRED_FIQ) +#define GPIO_BANK1_MASK OMAP_IRQ_BIT(INT_GPIO_BANK1) /* Driver buffer byte offsets */ #define BUF_MASK (FIQ_MASK * 4) @@ -110,7 +110,7 @@ ENTRY(qwerty_fiqin_start) mov r8, #2 @ reset FIQ agreement str r8, [r12, #IRQ_CONTROL_REG_OFFSET] - cmp r10, #INT_GPIO_BANK1 @ is it GPIO bank interrupt? + cmp r10, #(INT_GPIO_BANK1 - NR_IRQS_LEGACY) @ is it GPIO interrupt? beq gpio @ yes - process it mov r8, #1 diff --git a/arch/arm/mach-omap1/ams-delta-fiq.c b/arch/arm/mach-omap1/ams-delta-fiq.c index d1f12095f315..ec760ae2f917 100644 --- a/arch/arm/mach-omap1/ams-delta-fiq.c +++ b/arch/arm/mach-omap1/ams-delta-fiq.c @@ -109,7 +109,8 @@ void __init ams_delta_init_fiq(void) * Since no set_type() method is provided by OMAP irq chip, * switch to edge triggered interrupt type manually. */ - offset = IRQ_ILR0_REG_OFFSET + INT_DEFERRED_FIQ * 0x4; + offset = IRQ_ILR0_REG_OFFSET + + ((INT_DEFERRED_FIQ - NR_IRQS_LEGACY) & 0x1f) * 0x4; val = omap_readl(DEFERRED_FIQ_IH_BASE + offset) & ~(1 << 1); omap_writel(val, DEFERRED_FIQ_IH_BASE + offset); @@ -149,7 +150,7 @@ void __init ams_delta_init_fiq(void) /* * Redirect GPIO interrupts to FIQ */ - offset = IRQ_ILR0_REG_OFFSET + INT_GPIO_BANK1 * 0x4; + offset = IRQ_ILR0_REG_OFFSET + (INT_GPIO_BANK1 - NR_IRQS_LEGACY) * 0x4; val = omap_readl(OMAP_IH1_BASE + offset) | 1; omap_writel(val, OMAP_IH1_BASE + offset); } diff --git a/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h b/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h index adb5e7649659..6dfc3e1210a3 100644 --- a/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h +++ b/arch/arm/mach-omap1/include/mach/ams-delta-fiq.h @@ -14,6 +14,8 @@ #ifndef __AMS_DELTA_FIQ_H #define __AMS_DELTA_FIQ_H +#include + /* * Interrupt number used for passing control from FIQ to IRQ. * IRQ12, described as reserved, has been selected. diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 0517f0c1581a..1a648e9dfaa0 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -17,6 +17,7 @@ config ARCH_OMAP3 select PM_OPP if PM select PM if CPU_IDLE select SOC_HAS_OMAP2_SDRC + select ARM_ERRATA_430973 config ARCH_OMAP4 bool "TI OMAP4" @@ -36,6 +37,7 @@ config ARCH_OMAP4 select PM if CPU_IDLE select ARM_ERRATA_754322 select ARM_ERRATA_775420 + select OMAP_INTERCONNECT config SOC_OMAP5 bool "TI OMAP5" @@ -67,6 +69,8 @@ config SOC_AM43XX select HAVE_ARM_SCU select GENERIC_CLOCKEVENTS_BROADCAST select HAVE_ARM_TWD + select ARM_ERRATA_754322 + select ARM_ERRATA_775420 config SOC_DRA7XX bool "TI DRA7XX" @@ -240,4 +244,12 @@ endmenu endif +config OMAP5_ERRATA_801819 + bool "Errata 801819: An eviction from L1 data cache might stall indefinitely" + depends on SOC_OMAP5 || SOC_DRA7XX + help + A livelock can occur in the L2 cache arbitration that might prevent + a snoop from completing. Under certain conditions this can cause the + system to deadlock. + endmenu diff --git a/arch/arm/mach-omap2/omap-secure.h b/arch/arm/mach-omap2/omap-secure.h index af2851fbcdf0..bae263fba640 100644 --- a/arch/arm/mach-omap2/omap-secure.h +++ b/arch/arm/mach-omap2/omap-secure.h @@ -46,6 +46,7 @@ #define OMAP5_DRA7_MON_SET_CNTFRQ_INDEX 0x109 #define OMAP5_MON_AMBA_IF_INDEX 0x108 +#define OMAP5_DRA7_MON_SET_ACR_INDEX 0x107 /* Secure PPA(Primary Protected Application) APIs */ #define OMAP4_PPA_L2_POR_INDEX 0x23 diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c index c625cc10d9f9..8cd1de914ee4 100644 --- a/arch/arm/mach-omap2/omap-smp.c +++ b/arch/arm/mach-omap2/omap-smp.c @@ -50,6 +50,39 @@ void __iomem *omap4_get_scu_base(void) return scu_base; } +#ifdef CONFIG_OMAP5_ERRATA_801819 +void omap5_erratum_workaround_801819(void) +{ + u32 acr, revidr; + u32 acr_mask; + + /* REVIDR[3] indicates erratum fix available on silicon */ + asm volatile ("mrc p15, 0, %0, c0, c0, 6" : "=r" (revidr)); + if (revidr & (0x1 << 3)) + return; + + asm volatile ("mrc p15, 0, %0, c1, c0, 1" : "=r" (acr)); + /* + * BIT(27) - Disables streaming. All write-allocate lines allocate in + * the L1 or L2 cache. + * BIT(25) - Disables streaming. All write-allocate lines allocate in + * the L1 cache. + */ + acr_mask = (0x3 << 25) | (0x3 << 27); + /* 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 erratum workaround 801819 applied on CPU%d\n", + __func__, smp_processor_id()); +} +#else +static inline void omap5_erratum_workaround_801819(void) { } +#endif + static void omap4_secondary_init(unsigned int cpu) { /* @@ -64,12 +97,15 @@ static void omap4_secondary_init(unsigned int cpu) omap_secure_dispatcher(OMAP4_PPA_CPU_ACTRL_SMP_INDEX, 4, 0, 0, 0, 0, 0); - /* - * Configure the CNTFRQ register for the secondary cpu's which - * indicates the frequency of the cpu local timers. - */ - if (soc_is_omap54xx() || soc_is_dra7xx()) + if (soc_is_omap54xx() || soc_is_dra7xx()) { + /* + * Configure the CNTFRQ register for the secondary cpu's which + * indicates the frequency of the cpu local timers. + */ set_cntfreq(); + /* Configure ACR to disable streaming WA for 801819 */ + omap5_erratum_workaround_801819(); + } /* * Synchronise with the boot thread. @@ -218,6 +254,8 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus) if (cpu_is_omap446x()) startup_addr = omap4460_secondary_startup; + if (soc_is_dra74x() || soc_is_omap54xx()) + omap5_erratum_workaround_801819(); /* * Write the address of secondary startup routine into the diff --git a/arch/arm/mach-omap2/powerdomain.c b/arch/arm/mach-omap2/powerdomain.c index 78af6d8cf2e2..daf2753de7aa 100644 --- a/arch/arm/mach-omap2/powerdomain.c +++ b/arch/arm/mach-omap2/powerdomain.c @@ -186,8 +186,9 @@ static int _pwrdm_state_switch(struct powerdomain *pwrdm, int flag) trace_state = (PWRDM_TRACE_STATES_FLAG | ((next & OMAP_POWERSTATE_MASK) << 8) | ((prev & OMAP_POWERSTATE_MASK) << 0)); - trace_power_domain_target(pwrdm->name, trace_state, - smp_processor_id()); + trace_power_domain_target_rcuidle(pwrdm->name, + trace_state, + smp_processor_id()); } break; default: @@ -523,8 +524,8 @@ int pwrdm_set_next_pwrst(struct powerdomain *pwrdm, u8 pwrst) if (arch_pwrdm && arch_pwrdm->pwrdm_set_next_pwrst) { /* Trace the pwrdm desired target state */ - trace_power_domain_target(pwrdm->name, pwrst, - smp_processor_id()); + trace_power_domain_target_rcuidle(pwrdm->name, pwrst, + smp_processor_id()); /* Program the pwrdm desired target state */ ret = arch_pwrdm->pwrdm_set_next_pwrst(pwrdm, pwrst); } diff --git a/arch/arm/mach-omap2/powerdomains7xx_data.c b/arch/arm/mach-omap2/powerdomains7xx_data.c index 0ec2d00f4237..eb350a673133 100644 --- a/arch/arm/mach-omap2/powerdomains7xx_data.c +++ b/arch/arm/mach-omap2/powerdomains7xx_data.c @@ -36,14 +36,7 @@ static struct powerdomain iva_7xx_pwrdm = { .prcm_offs = DRA7XX_PRM_IVA_INST, .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, - .pwrsts_logic_ret = PWRSTS_OFF, .banks = 4, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* hwa_mem */ - [1] = PWRSTS_OFF_RET, /* sl2_mem */ - [2] = PWRSTS_OFF_RET, /* tcm1_mem */ - [3] = PWRSTS_OFF_RET, /* tcm2_mem */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* hwa_mem */ [1] = PWRSTS_ON, /* sl2_mem */ @@ -76,12 +69,7 @@ static struct powerdomain ipu_7xx_pwrdm = { .prcm_offs = DRA7XX_PRM_IPU_INST, .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, - .pwrsts_logic_ret = PWRSTS_OFF, .banks = 2, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* aessmem */ - [1] = PWRSTS_OFF_RET, /* periphmem */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* aessmem */ [1] = PWRSTS_ON, /* periphmem */ @@ -95,11 +83,7 @@ static struct powerdomain dss_7xx_pwrdm = { .prcm_offs = DRA7XX_PRM_DSS_INST, .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, - .pwrsts_logic_ret = PWRSTS_OFF, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* dss_mem */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* dss_mem */ }, @@ -111,13 +95,8 @@ static struct powerdomain l4per_7xx_pwrdm = { .name = "l4per_pwrdm", .prcm_offs = DRA7XX_PRM_L4PER_INST, .prcm_partition = DRA7XX_PRM_PARTITION, - .pwrsts = PWRSTS_RET_ON, - .pwrsts_logic_ret = PWRSTS_RET, + .pwrsts = PWRSTS_ON, .banks = 2, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* nonretained_bank */ - [1] = PWRSTS_OFF_RET, /* retained_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* nonretained_bank */ [1] = PWRSTS_ON, /* retained_bank */ @@ -132,9 +111,6 @@ static struct powerdomain gpu_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* gpu_mem */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* gpu_mem */ }, @@ -148,8 +124,6 @@ static struct powerdomain wkupaon_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_ON, .banks = 1, - .pwrsts_mem_ret = { - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* wkup_bank */ }, @@ -161,15 +135,7 @@ static struct powerdomain core_7xx_pwrdm = { .prcm_offs = DRA7XX_PRM_CORE_INST, .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_ON, - .pwrsts_logic_ret = PWRSTS_RET, .banks = 5, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* core_nret_bank */ - [1] = PWRSTS_OFF_RET, /* core_ocmram */ - [2] = PWRSTS_OFF_RET, /* core_other_bank */ - [3] = PWRSTS_OFF_RET, /* ipu_l2ram */ - [4] = PWRSTS_OFF_RET, /* ipu_unicache */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* core_nret_bank */ [1] = PWRSTS_ON, /* core_ocmram */ @@ -226,11 +192,7 @@ static struct powerdomain vpe_7xx_pwrdm = { .prcm_offs = DRA7XX_PRM_VPE_INST, .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, - .pwrsts_logic_ret = PWRSTS_OFF, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* vpe_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* vpe_bank */ }, @@ -260,14 +222,8 @@ static struct powerdomain l3init_7xx_pwrdm = { .name = "l3init_pwrdm", .prcm_offs = DRA7XX_PRM_L3INIT_INST, .prcm_partition = DRA7XX_PRM_PARTITION, - .pwrsts = PWRSTS_RET_ON, - .pwrsts_logic_ret = PWRSTS_RET, + .pwrsts = PWRSTS_ON, .banks = 3, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* gmac_bank */ - [1] = PWRSTS_OFF_RET, /* l3init_bank1 */ - [2] = PWRSTS_OFF_RET, /* l3init_bank2 */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* gmac_bank */ [1] = PWRSTS_ON, /* l3init_bank1 */ @@ -283,9 +239,6 @@ static struct powerdomain eve3_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* eve3_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* eve3_bank */ }, @@ -299,9 +252,6 @@ static struct powerdomain emu_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* emu_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* emu_bank */ }, @@ -314,11 +264,6 @@ static struct powerdomain dsp2_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 3, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* dsp2_edma */ - [1] = PWRSTS_OFF_RET, /* dsp2_l1 */ - [2] = PWRSTS_OFF_RET, /* dsp2_l2 */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* dsp2_edma */ [1] = PWRSTS_ON, /* dsp2_l1 */ @@ -334,11 +279,6 @@ static struct powerdomain dsp1_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 3, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* dsp1_edma */ - [1] = PWRSTS_OFF_RET, /* dsp1_l1 */ - [2] = PWRSTS_OFF_RET, /* dsp1_l2 */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* dsp1_edma */ [1] = PWRSTS_ON, /* dsp1_l1 */ @@ -354,9 +294,6 @@ static struct powerdomain cam_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* vip_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* vip_bank */ }, @@ -370,9 +307,6 @@ static struct powerdomain eve4_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* eve4_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* eve4_bank */ }, @@ -386,9 +320,6 @@ static struct powerdomain eve2_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* eve2_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* eve2_bank */ }, @@ -402,9 +333,6 @@ static struct powerdomain eve1_7xx_pwrdm = { .prcm_partition = DRA7XX_PRM_PARTITION, .pwrsts = PWRSTS_OFF_ON, .banks = 1, - .pwrsts_mem_ret = { - [0] = PWRSTS_OFF_RET, /* eve1_bank */ - }, .pwrsts_mem_on = { [0] = PWRSTS_ON, /* eve1_bank */ }, diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index 5b385bb8aff9..cb9497a20fb3 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -496,8 +496,7 @@ void __init omap_init_time(void) __omap_sync32k_timer_init(1, "timer_32k_ck", "ti,timer-alwon", 2, "timer_sys_ck", NULL, false); - if (of_have_populated_dt()) - clocksource_probe(); + clocksource_probe(); } #if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_SOC_AM43XX) @@ -505,6 +504,8 @@ void __init omap3_secure_sync32k_timer_init(void) { __omap_sync32k_timer_init(12, "secure_32k_fck", "ti,timer-secure", 2, "timer_sys_ck", NULL, false); + + clocksource_probe(); } #endif /* CONFIG_ARCH_OMAP3 */ @@ -513,6 +514,8 @@ void __init omap3_gptimer_timer_init(void) { __omap_sync32k_timer_init(2, "timer_sys_ck", NULL, 1, "timer_sys_ck", "ti,timer-alwon", true); + + clocksource_probe(); } #endif diff --git a/arch/arm/mach-vexpress/spc.c b/arch/arm/mach-vexpress/spc.c index 5766ce2be32b..8409cab3f760 100644 --- a/arch/arm/mach-vexpress/spc.c +++ b/arch/arm/mach-vexpress/spc.c @@ -547,7 +547,7 @@ static struct clk *ve_spc_clk_register(struct device *cpu_dev) init.name = dev_name(cpu_dev); init.ops = &clk_spc_ops; - init.flags = CLK_IS_ROOT | CLK_GET_RATE_NOCACHE; + init.flags = CLK_GET_RATE_NOCACHE; init.num_parents = 0; return devm_clk_register(cpu_dev, &spc->hw); diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c index 84baa16f4c0b..e93aa6734147 100644 --- a/arch/arm/plat-samsung/devs.c +++ b/arch/arm/plat-samsung/devs.c @@ -68,7 +68,7 @@ #include #include -static u64 samsung_device_dma_mask = DMA_BIT_MASK(32); +#define samsung_device_dma_mask (*((u64[]) { DMA_BIT_MASK(32) })) /* AC97 */ #ifdef CONFIG_CPU_S3C2440 diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 7085e322dc42..648a32c89541 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -95,7 +95,7 @@ boot := arch/arm64/boot Image: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ -Image.%: vmlinux +Image.%: Image $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ zinstall install: diff --git a/arch/arm64/boot/dts/lg/lg1312.dtsi b/arch/arm64/boot/dts/lg/lg1312.dtsi index 3a4e9a2ab313..fbafa24cd533 100644 --- a/arch/arm64/boot/dts/lg/lg1312.dtsi +++ b/arch/arm64/boot/dts/lg/lg1312.dtsi @@ -125,7 +125,7 @@ amba { #size-cells = <1>; #interrupts-cells = <3>; - compatible = "arm,amba-bus"; + compatible = "simple-bus"; interrupt-parent = <&gic>; ranges; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 46f325a143b0..d7f8e06910bc 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -163,7 +163,7 @@ xin24m: xin24m { }; amba { - compatible = "arm,amba-bus"; + compatible = "simple-bus"; #address-cells = <2>; #size-cells = <2>; ranges; diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 87e1985f3be8..9d9fd4b9a72e 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -80,12 +80,14 @@ #define APM_CPU_PART_POTENZA 0x000 #define CAVIUM_CPU_PART_THUNDERX 0x0A1 +#define CAVIUM_CPU_PART_THUNDERX_81XX 0x0A2 #define BRCM_CPU_PART_VULCAN 0x516 #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) +#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h index f69f69c8120c..da84645525b9 100644 --- a/arch/arm64/include/asm/kgdb.h +++ b/arch/arm64/include/asm/kgdb.h @@ -38,25 +38,54 @@ extern int kgdb_fault_expected; #endif /* !__ASSEMBLY__ */ /* - * gdb is expecting the following registers layout. + * gdb remote procotol (well most versions of it) expects the following + * register layout. * * General purpose regs: * r0-r30: 64 bit * sp,pc : 64 bit - * pstate : 64 bit - * Total: 34 + * pstate : 32 bit + * Total: 33 + 1 * FPU regs: * f0-f31: 128 bit - * Total: 32 - * Extra regs * fpsr & fpcr: 32 bit - * Total: 2 + * Total: 32 + 2 * + * To expand a little on the "most versions of it"... when the gdb remote + * protocol for AArch64 was developed it depended on a statement in the + * Architecture Reference Manual that claimed "SPSR_ELx is a 32-bit register". + * and, as a result, allocated only 32-bits for the PSTATE in the remote + * protocol. In fact this statement is still present in ARM DDI 0487A.i. + * + * Unfortunately "is a 32-bit register" has a very special meaning for + * system registers. It means that "the upper bits, bits[63:32], are + * RES0.". RES0 is heavily used in the ARM architecture documents as a + * way to leave space for future architecture changes. So to translate a + * little for people who don't spend their spare time reading ARM architecture + * manuals, what "is a 32-bit register" actually means in this context is + * "is a 64-bit register but one with no meaning allocated to any of the + * upper 32-bits... *yet*". + * + * Perhaps then we should not be surprised that this has led to some + * confusion. Specifically a patch, influenced by the above translation, + * that extended PSTATE to 64-bit was accepted into gdb-7.7 but the patch + * was reverted in gdb-7.8.1 and all later releases, when this was + * discovered to be an undocumented protocol change. + * + * So... it is *not* wrong for us to only allocate 32-bits to PSTATE + * here even though the kernel itself allocates 64-bits for the same + * state. That is because this bit of code tells the kernel how the gdb + * remote protocol (well most versions of it) describes the register state. + * + * Note that if you are using one of the versions of gdb that supports + * the gdb-7.7 version of the protocol you cannot use kgdb directly + * without providing a custom register description (gdb can load new + * protocol descriptions at runtime). */ -#define _GP_REGS 34 +#define _GP_REGS 33 #define _FP_REGS 32 -#define _EXTRA_REGS 2 +#define _EXTRA_REGS 3 /* * general purpose registers size in bytes. * pstate is only 4 bytes. subtract 4 bytes diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index ff98585d085a..d25f4f137c2a 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -26,7 +26,7 @@ #define check_pgt_cache() do { } while (0) -#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) #define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) #if CONFIG_PGTABLE_LEVELS > 2 diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index a307eb6e7fa8..7f94755089e2 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -117,6 +117,8 @@ struct pt_regs { }; u64 orig_x0; u64 syscallno; + u64 orig_addr_limit; + u64 unused; // maintain 16 byte alignment }; #define arch_has_single_step() (1) diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index 433e50405274..022644704a93 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -124,6 +124,18 @@ static inline void cpu_panic_kernel(void) cpu_park_loop(); } +/* + * If a secondary CPU enters the kernel but fails to come online, + * (e.g. due to mismatched features), and cannot exit the kernel, + * we increment cpus_stuck_in_kernel and leave the CPU in a + * quiesecent loop within the kernel text. The memory containing + * this loop must not be re-used for anything else as the 'stuck' + * core is executing it. + * + * This function is used to inhibit features like kexec and hibernate. + */ +bool cpus_are_stuck_in_kernel(void); + #endif /* ifndef __ASSEMBLY__ */ #endif /* ifndef __ASM_SMP_H */ diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index fc9682bfe002..e875a5a551d7 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -30,22 +30,53 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) { unsigned int tmp; arch_spinlock_t lockval; + u32 owner; + + /* + * Ensure prior spin_lock operations to other locks have completed + * on this CPU before we test whether "lock" is locked. + */ + smp_mb(); + owner = READ_ONCE(lock->owner) << 16; asm volatile( " sevl\n" "1: wfe\n" "2: ldaxr %w0, %2\n" + /* Is the lock free? */ " eor %w1, %w0, %w0, ror #16\n" -" cbnz %w1, 1b\n" +" cbz %w1, 3f\n" + /* Lock taken -- has there been a subsequent unlock->lock transition? */ +" eor %w1, %w3, %w0, lsl #16\n" +" cbz %w1, 1b\n" + /* + * The owner has been updated, so there was an unlock->lock + * transition that we missed. That means we can rely on the + * store-release of the unlock operation paired with the + * load-acquire of the lock operation to publish any of our + * previous stores to the new lock owner and therefore don't + * need to bother with the writeback below. + */ +" b 4f\n" +"3:\n" + /* + * Serialise against any concurrent lockers by writing back the + * unlocked lock value + */ ARM64_LSE_ATOMIC_INSN( /* LL/SC */ " stxr %w1, %w0, %2\n" -" cbnz %w1, 2b\n", /* Serialise against any concurrent lockers */ - /* LSE atomics */ " nop\n" -" nop\n") +" nop\n", + /* LSE atomics */ +" mov %w1, %w0\n" +" cas %w0, %w0, %2\n" +" eor %w1, %w1, %w0\n") + /* Somebody else wrote to the lock, GOTO 10 and reload the value */ +" cbnz %w1, 2b\n" +"4:" : "=&r" (lockval), "=&r" (tmp), "+Q" (*lock) - : + : "r" (owner) : "memory"); } @@ -148,6 +179,7 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock) static inline int arch_spin_is_locked(arch_spinlock_t *lock) { + smp_mb(); /* See arch_spin_unlock_wait */ return !arch_spin_value_unlocked(READ_ONCE(*lock)); } diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index f8e5d47f0880..2f4ba774488a 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -60,6 +60,7 @@ int main(void) DEFINE(S_PC, offsetof(struct pt_regs, pc)); DEFINE(S_ORIG_X0, offsetof(struct pt_regs, orig_x0)); DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno)); + DEFINE(S_ORIG_ADDR_LIMIT, offsetof(struct pt_regs, orig_addr_limit)); DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); BLANK(); DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter)); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index d42789499f17..af716b65110d 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -98,6 +98,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = { MIDR_RANGE(MIDR_THUNDERX, 0x00, (1 << MIDR_VARIANT_SHIFT) | 1), }, + { + /* Cavium ThunderX, T81 pass 1.0 */ + .desc = "Cavium erratum 27456", + .capability = ARM64_WORKAROUND_CAVIUM_27456, + MIDR_RANGE(MIDR_THUNDERX_81XX, 0x00, 0x00), + }, #endif { } diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 12e8d2bcb3f9..6c3b7345a6c4 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -97,7 +98,14 @@ mov x29, xzr // fp pointed to user-space .else add x21, sp, #S_FRAME_SIZE - .endif + get_thread_info tsk + /* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */ + ldr x20, [tsk, #TI_ADDR_LIMIT] + str x20, [sp, #S_ORIG_ADDR_LIMIT] + mov x20, #TASK_SIZE_64 + str x20, [tsk, #TI_ADDR_LIMIT] + ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO) + .endif /* \el == 0 */ mrs x22, elr_el1 mrs x23, spsr_el1 stp lr, x21, [sp, #S_LR] @@ -128,6 +136,14 @@ .endm .macro kernel_exit, el + .if \el != 0 + /* Restore the task's original addr_limit. */ + ldr x20, [sp, #S_ORIG_ADDR_LIMIT] + str x20, [tsk, #TI_ADDR_LIMIT] + + /* No need to restore UAO, it will be restored from SPSR_EL1 */ + .endif + ldp x21, x22, [sp, #S_PC] // load ELR, SPSR .if \el == 0 ct_user_enter @@ -406,7 +422,6 @@ el1_irq: bl trace_hardirqs_off #endif - get_thread_info tsk irq_handler #ifdef CONFIG_PREEMPT diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index f8df75d740f4..21ab5df9fa76 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include @@ -236,6 +237,11 @@ int swsusp_arch_suspend(void) unsigned long flags; struct sleep_stack_data state; + if (cpus_are_stuck_in_kernel()) { + pr_err("Can't hibernate: no mechanism to offline secondary CPUs.\n"); + return -EBUSY; + } + local_dbg_save(flags); if (__cpu_suspend_enter(&state)) { diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c index b67531a13136..b5f063e5eff7 100644 --- a/arch/arm64/kernel/kgdb.c +++ b/arch/arm64/kernel/kgdb.c @@ -58,7 +58,17 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { { "x30", 8, offsetof(struct pt_regs, regs[30])}, { "sp", 8, offsetof(struct pt_regs, sp)}, { "pc", 8, offsetof(struct pt_regs, pc)}, - { "pstate", 8, offsetof(struct pt_regs, pstate)}, + /* + * struct pt_regs thinks PSTATE is 64-bits wide but gdb remote + * protocol disagrees. Therefore we must extract only the lower + * 32-bits. Look for the big comment in asm/kgdb.h for more + * detail. + */ + { "pstate", 4, offsetof(struct pt_regs, pstate) +#ifdef CONFIG_CPU_BIG_ENDIAN + + 4 +#endif + }, { "v0", 16, -1 }, { "v1", 16, -1 }, { "v2", 16, -1 }, @@ -128,6 +138,8 @@ sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task) memset((char *)gdb_regs, 0, NUMREGBYTES); thread_regs = task_pt_regs(task); memcpy((void *)gdb_regs, (void *)thread_regs->regs, GP_REG_BYTES); + /* Special case for PSTATE (check comments in asm/kgdb.h for details) */ + dbg_get_reg(33, gdb_regs + GP_REG_BYTES, thread_regs); } void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 678e0842cb3b..62ff3c0622e2 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -909,3 +909,21 @@ int setup_profiling_timer(unsigned int multiplier) { return -EINVAL; } + +static bool have_cpu_die(void) +{ +#ifdef CONFIG_HOTPLUG_CPU + int any_cpu = raw_smp_processor_id(); + + if (cpu_ops[any_cpu]->cpu_die) + return true; +#endif + return false; +} + +bool cpus_are_stuck_in_kernel(void) +{ + bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die()); + + return !!cpus_stuck_in_kernel || smp_spin_tables; +} diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index f7cf463107df..2a43012616b7 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -64,8 +64,7 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom, /* * We need to switch to kernel mode so that we can use __get_user - * to safely read from kernel space. Note that we now dump the - * code first, just in case the backtrace kills us. + * to safely read from kernel space. */ fs = get_fs(); set_fs(KERNEL_DS); @@ -111,21 +110,12 @@ static void dump_backtrace_entry(unsigned long where) print_ip_sym(where); } -static void dump_instr(const char *lvl, struct pt_regs *regs) +static void __dump_instr(const char *lvl, struct pt_regs *regs) { unsigned long addr = instruction_pointer(regs); - mm_segment_t fs; char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str; int i; - /* - * We need to switch to kernel mode so that we can use __get_user - * to safely read from kernel space. Note that we now dump the - * code first, just in case the backtrace kills us. - */ - fs = get_fs(); - set_fs(KERNEL_DS); - for (i = -4; i < 1; i++) { unsigned int val, bad; @@ -139,8 +129,18 @@ static void dump_instr(const char *lvl, struct pt_regs *regs) } } printk("%sCode: %s\n", lvl, str); +} - set_fs(fs); +static void dump_instr(const char *lvl, struct pt_regs *regs) +{ + if (!user_mode(regs)) { + mm_segment_t fs = get_fs(); + set_fs(KERNEL_DS); + __dump_instr(lvl, regs); + set_fs(fs); + } else { + __dump_instr(lvl, regs); + } } static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c index b7b397802088..efcf1f7ef1e4 100644 --- a/arch/arm64/mm/context.c +++ b/arch/arm64/mm/context.c @@ -179,7 +179,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu) &asid_generation); flush_context(cpu); - /* We have at least 1 ASID per CPU, so this will always succeed */ + /* We have more ASIDs than CPUs, so this will always succeed */ asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1); set_asid: @@ -227,8 +227,11 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu) static int asids_init(void) { asid_bits = get_cpu_asid_bits(); - /* If we end up with more CPUs than ASIDs, expect things to crash */ - WARN_ON(NUM_USER_ASIDS < num_possible_cpus()); + /* + * Expect allocation after rollover to fail if we don't have at least + * one more ASID than CPUs. ASID #0 is reserved for init_mm. + */ + WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus()); atomic64_set(&asid_generation, ASID_FIRST_VERSION); asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map), GFP_KERNEL); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 5954881a35ac..b1166d1e5955 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -109,7 +109,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, * PTE_RDONLY is cleared by default in the asm below, so set it in * back if necessary (read-only or clean PTE). */ - if (!pte_write(entry) || !dirty) + if (!pte_write(entry) || !pte_sw_dirty(entry)) pte_val(entry) |= PTE_RDONLY; /* @@ -280,7 +280,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, } if (permission_fault(esr) && (addr < USER_DS)) { - if (get_fs() == KERNEL_DS) + /* regs->orig_addr_limit may be 0 if we entered from EL0 */ + if (regs->orig_addr_limit == KERNEL_DS) die("Accessing user space memory with fs=KERNEL_DS", regs, esr); if (!search_exception_tables(regs->pc)) @@ -441,7 +442,7 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs) return 1; } -static struct fault_info { +static const struct fault_info { int (*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs); int sig; int code; diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index dbd12ea8ce68..43a76b07eb32 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -71,10 +71,6 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr) { struct page *page = pte_page(pte); - /* no flushing needed for anonymous pages */ - if (!page_mapping(page)) - return; - if (!test_and_set_bit(PG_dcache_clean, &page->flags)) sync_icache_aliases(page_address(page), PAGE_SIZE << compound_order(page)); diff --git a/arch/avr32/include/asm/pgalloc.h b/arch/avr32/include/asm/pgalloc.h index 1aba19d68c5e..db039cb368be 100644 --- a/arch/avr32/include/asm/pgalloc.h +++ b/arch/avr32/include/asm/pgalloc.h @@ -43,7 +43,7 @@ static inline void pgd_ctor(void *x) */ static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - return quicklist_alloc(QUICK_PGD, GFP_KERNEL | __GFP_REPEAT, pgd_ctor); + return quicklist_alloc(QUICK_PGD, GFP_KERNEL, pgd_ctor); } static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) @@ -54,7 +54,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL); + return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL); } static inline pgtable_t pte_alloc_one(struct mm_struct *mm, @@ -63,7 +63,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, struct page *page; void *pg; - pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL); + pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL); if (!pg) return NULL; diff --git a/arch/cris/include/asm/pgalloc.h b/arch/cris/include/asm/pgalloc.h index 235ece437ddd..42f1affb9c2d 100644 --- a/arch/cris/include/asm/pgalloc.h +++ b/arch/cris/include/asm/pgalloc.h @@ -24,14 +24,14 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); return pte; } static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *pte; - pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); + pte = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0); if (!pte) return NULL; if (!pgtable_page_ctor(pte)) { diff --git a/arch/frv/mm/pgalloc.c b/arch/frv/mm/pgalloc.c index 41907d25ed38..c9ed14f6c67d 100644 --- a/arch/frv/mm/pgalloc.c +++ b/arch/frv/mm/pgalloc.c @@ -22,7 +22,7 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((aligned(PAGE_SIZE))); pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT); + pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL); if (pte) clear_page(pte); return pte; @@ -33,9 +33,9 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) struct page *page; #ifdef CONFIG_HIGHPTE - page = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT, 0); + page = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM, 0); #else - page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0); + page = alloc_pages(GFP_KERNEL, 0); #endif if (!page) return NULL; diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h index 77da3b0ae3c2..eeebf862c46c 100644 --- a/arch/hexagon/include/asm/pgalloc.h +++ b/arch/hexagon/include/asm/pgalloc.h @@ -64,7 +64,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, { struct page *pte; - pte = alloc_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO); + pte = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!pte) return NULL; if (!pgtable_page_ctor(pte)) { @@ -78,7 +78,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - gfp_t flags = GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO; + gfp_t flags = GFP_KERNEL | __GFP_ZERO; return (pte_t *) __get_free_page(flags); } diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index f80758cb7157..e109ee95e919 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -45,7 +45,7 @@ config IA64 select GENERIC_SMP_IDLE_THREAD select ARCH_INIT_TASK select ARCH_TASK_STRUCT_ALLOCATOR - select ARCH_THREAD_INFO_ALLOCATOR + select ARCH_THREAD_STACK_ALLOCATOR select ARCH_CLOCKSOURCE_DATA select GENERIC_TIME_VSYSCALL_OLD select SYSCTL_ARCH_UNALIGN_NO_WARN diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h index aa995b67c3f5..d1212b84fb83 100644 --- a/arch/ia64/include/asm/thread_info.h +++ b/arch/ia64/include/asm/thread_info.h @@ -48,15 +48,15 @@ struct thread_info { #ifndef ASM_OFFSETS_C /* how to get the thread information struct from C */ #define current_thread_info() ((struct thread_info *) ((char *) current + IA64_TASK_SIZE)) -#define alloc_thread_info_node(tsk, node) \ - ((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE)) +#define alloc_thread_stack_node(tsk, node) \ + ((unsigned long *) ((char *) (tsk) + IA64_TASK_SIZE)) #define task_thread_info(tsk) ((struct thread_info *) ((char *) (tsk) + IA64_TASK_SIZE)) #else #define current_thread_info() ((struct thread_info *) 0) -#define alloc_thread_info_node(tsk, node) ((struct thread_info *) 0) +#define alloc_thread_stack_node(tsk, node) ((unsigned long *) 0) #define task_thread_info(tsk) ((struct thread_info *) 0) #endif -#define free_thread_info(ti) /* nothing */ +#define free_thread_stack(ti) /* nothing */ #define task_stack_page(tsk) ((void *)(tsk)) #define __HAVE_THREAD_FUNCTIONS diff --git a/arch/ia64/kernel/init_task.c b/arch/ia64/kernel/init_task.c index f9efe9739d3f..0eaa89f3defd 100644 --- a/arch/ia64/kernel/init_task.c +++ b/arch/ia64/kernel/init_task.c @@ -26,6 +26,7 @@ static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); * handled. This is done by having a special ".data..init_task" section... */ #define init_thread_info init_task_mem.s.thread_info +#define init_stack init_task_mem.stack union { struct { diff --git a/arch/m32r/boot/compressed/m32r_sio.c b/arch/m32r/boot/compressed/m32r_sio.c index 01d877c6868f..cf3023dced49 100644 --- a/arch/m32r/boot/compressed/m32r_sio.c +++ b/arch/m32r/boot/compressed/m32r_sio.c @@ -8,12 +8,13 @@ #include -static void putc(char c); +static void m32r_putc(char c); static int puts(const char *s) { char c; - while ((c = *s++)) putc(c); + while ((c = *s++)) + m32r_putc(c); return 0; } @@ -41,7 +42,7 @@ static int puts(const char *s) #define BOOT_SIO0TXB PLD_ESIO0TXB #endif -static void putc(char c) +static void m32r_putc(char c) { while ((*BOOT_SIO0STS & 0x3) != 0x3) cpu_relax(); @@ -61,7 +62,7 @@ static void putc(char c) #define SIO0TXB (volatile unsigned short *)(0x00efd000 + 30) #endif -static void putc(char c) +static void m32r_putc(char c) { while ((*SIO0STS & 0x1) == 0) cpu_relax(); diff --git a/arch/m68k/coldfire/head.S b/arch/m68k/coldfire/head.S index fa31be297b85..73d92ea0ce65 100644 --- a/arch/m68k/coldfire/head.S +++ b/arch/m68k/coldfire/head.S @@ -288,7 +288,7 @@ _clear_bss: #endif /* - * Assember start up done, start code proper. + * Assembler start up done, start code proper. */ jsr start_kernel /* start Linux kernel */ diff --git a/arch/m68k/coldfire/m5272.c b/arch/m68k/coldfire/m5272.c index c525e4c08f84..9abb1a441da0 100644 --- a/arch/m68k/coldfire/m5272.c +++ b/arch/m68k/coldfire/m5272.c @@ -111,7 +111,7 @@ void __init config_BSP(char *commandp, int size) /***************************************************************************/ /* - * Some 5272 based boards have the FEC ethernet diectly connected to + * Some 5272 based boards have the FEC ethernet directly connected to * an ethernet switch. In this case we need to use the fixed phy type, * and we need to declare it early in boot. */ diff --git a/arch/m68k/coldfire/pci.c b/arch/m68k/coldfire/pci.c index 821de928dc3f..6a640be48568 100644 --- a/arch/m68k/coldfire/pci.c +++ b/arch/m68k/coldfire/pci.c @@ -42,7 +42,7 @@ static unsigned long iospace; /* * We need to be carefull probing on bus 0 (directly connected to host - * bridge). We should only acccess the well defined possible devices in + * bridge). We should only access the well defined possible devices in * use, ignore aliases and the like. */ static unsigned char mcf_host_slot2sid[32] = { diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 3ee6976f6088..8f5b6f7dd136 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -359,6 +360,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -553,7 +555,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index e96787ffcbce..31bded9c83d4 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -341,6 +342,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -512,7 +514,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 083fe6beac14..0d7739e04ae2 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -350,6 +351,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -533,7 +535,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 475130c06dcb..2cbb5c465fec 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -340,6 +341,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -504,7 +506,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index 4339658c200f..96102a42c156 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -341,6 +342,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -514,7 +516,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 831cc8c3a2e2..97d88f7dc5a7 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -357,6 +358,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -536,7 +538,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 6377afeb522b..be25ef208f0f 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -390,6 +391,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -616,7 +618,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 4304b3d56262..a008344360c9 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -339,6 +340,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -504,7 +506,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 074bda4094ff..6735a25f36d4 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -340,6 +341,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -504,7 +506,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 07b9fa8d7f2e..780c6e9f6cf9 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -346,6 +347,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -527,7 +529,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 36e6fae02d45..44693cf361e5 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -337,6 +338,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -506,7 +508,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 903acf929511..ef0071d61158 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -9,6 +9,7 @@ CONFIG_LOG_BUF_SHIFT=16 # CONFIG_PID_NS is not set # CONFIG_NET_NS is not set CONFIG_BLK_DEV_INITRD=y +CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_USERFAULTFD=y CONFIG_SLAB=y CONFIG_MODULES=y @@ -337,6 +338,7 @@ CONFIG_MACVTAP=m CONFIG_IPVLAN=m CONFIG_VXLAN=m CONFIG_GENEVE=m +CONFIG_GTP=m CONFIG_MACSEC=m CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y @@ -506,7 +508,9 @@ CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m CONFIG_TEST_PRINTF=m CONFIG_TEST_BITMAP=m +CONFIG_TEST_UUID=m CONFIG_TEST_RHASHTABLE=m +CONFIG_TEST_HASH=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m CONFIG_TEST_BPF=m diff --git a/arch/m68k/ifpsp060/src/fpsp.S b/arch/m68k/ifpsp060/src/fpsp.S index 78cb60f5bb4d..9bbffebe3eb5 100644 --- a/arch/m68k/ifpsp060/src/fpsp.S +++ b/arch/m68k/ifpsp060/src/fpsp.S @@ -10191,7 +10191,7 @@ xdnrm_con: xdnrm_sd: mov.l %a1,-(%sp) tst.b LOCAL_EX(%a0) # is denorm pos or neg? - smi.b %d1 # set d0 accodingly + smi.b %d1 # set d0 accordingly bsr.l unf_sub mov.l (%sp)+,%a1 xdnrm_exit: @@ -10990,7 +10990,7 @@ src_qnan_m: # routines where an instruction is selected by an index into # a large jump table corresponding to a given instruction which # has been decoded. Flow continues here where we now decode -# further accoding to the source operand type. +# further according to the source operand type. # global fsinh @@ -23196,14 +23196,14 @@ m_sign: # # 1. Branch on the sign of the adjusted exponent. # 2p.(positive exp) -# 2. Check M16 and the digits in lwords 2 and 3 in decending order. +# 2. Check M16 and the digits in lwords 2 and 3 in descending order. # 3. Add one for each zero encountered until a non-zero digit. # 4. Subtract the count from the exp. # 5. Check if the exp has crossed zero in #3 above; make the exp abs # and set SE. # 6. Multiply the mantissa by 10**count. # 2n.(negative exp) -# 2. Check the digits in lwords 3 and 2 in decending order. +# 2. Check the digits in lwords 3 and 2 in descending order. # 3. Add one for each zero encountered until a non-zero digit. # 4. Add the count to the exp. # 5. Check if the exp has crossed zero in #3 above; clear SE. diff --git a/arch/m68k/ifpsp060/src/pfpsp.S b/arch/m68k/ifpsp060/src/pfpsp.S index 4aedef973cf6..3535e6c87eec 100644 --- a/arch/m68k/ifpsp060/src/pfpsp.S +++ b/arch/m68k/ifpsp060/src/pfpsp.S @@ -13156,14 +13156,14 @@ m_sign: # # 1. Branch on the sign of the adjusted exponent. # 2p.(positive exp) -# 2. Check M16 and the digits in lwords 2 and 3 in decending order. +# 2. Check M16 and the digits in lwords 2 and 3 in descending order. # 3. Add one for each zero encountered until a non-zero digit. # 4. Subtract the count from the exp. # 5. Check if the exp has crossed zero in #3 above; make the exp abs # and set SE. # 6. Multiply the mantissa by 10**count. # 2n.(negative exp) -# 2. Check the digits in lwords 3 and 2 in decending order. +# 2. Check the digits in lwords 3 and 2 in descending order. # 3. Add one for each zero encountered until a non-zero digit. # 4. Add the count to the exp. # 5. Check if the exp has crossed zero in #3 above; clear SE. diff --git a/arch/m68k/include/asm/dma.h b/arch/m68k/include/asm/dma.h index 429fe26e320c..208b4daa14b3 100644 --- a/arch/m68k/include/asm/dma.h +++ b/arch/m68k/include/asm/dma.h @@ -18,7 +18,7 @@ * AUG/22/2000 : added support for 32-bit Dual-Address-Mode (K) 2000 * Oliver Kamphenkel (O.Kamphenkel@tu-bs.de) * - * AUG/25/2000 : addad support for 8, 16 and 32-bit Single-Address-Mode (K)2000 + * AUG/25/2000 : added support for 8, 16 and 32-bit Single-Address-Mode (K)2000 * Oliver Kamphenkel (O.Kamphenkel@tu-bs.de) * * APR/18/2002 : added proper support for MCF5272 DMA controller. diff --git a/arch/m68k/include/asm/m525xsim.h b/arch/m68k/include/asm/m525xsim.h index f186459072e9..699f20c8a0fe 100644 --- a/arch/m68k/include/asm/m525xsim.h +++ b/arch/m68k/include/asm/m525xsim.h @@ -123,10 +123,10 @@ /* * I2C module. */ -#define MCFI2C_BASE0 (MCF_MBAR + 0x280) /* Base addreess I2C0 */ +#define MCFI2C_BASE0 (MCF_MBAR + 0x280) /* Base address I2C0 */ #define MCFI2C_SIZE0 0x20 /* Register set size */ -#define MCFI2C_BASE1 (MCF_MBAR2 + 0x440) /* Base addreess I2C1 */ +#define MCFI2C_BASE1 (MCF_MBAR2 + 0x440) /* Base address I2C1 */ #define MCFI2C_SIZE1 0x20 /* Register set size */ /* diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h index f9924fbcfe42..fb95aed5f428 100644 --- a/arch/m68k/include/asm/mcf_pgalloc.h +++ b/arch/m68k/include/asm/mcf_pgalloc.h @@ -14,7 +14,7 @@ extern const char bad_pmd_string[]; extern inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - unsigned long page = __get_free_page(GFP_DMA|__GFP_REPEAT); + unsigned long page = __get_free_page(GFP_DMA); if (!page) return NULL; @@ -51,7 +51,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page, static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) { - struct page *page = alloc_pages(GFP_DMA|__GFP_REPEAT, 0); + struct page *page = alloc_pages(GFP_DMA, 0); pte_t *pte; if (!page) diff --git a/arch/m68k/include/asm/mcfmmu.h b/arch/m68k/include/asm/mcfmmu.h index 26cc3d5a63f8..8824236e303f 100644 --- a/arch/m68k/include/asm/mcfmmu.h +++ b/arch/m68k/include/asm/mcfmmu.h @@ -38,7 +38,7 @@ /* * MMU Operation register. */ -#define MMUOR_UAA 0x00000001 /* Update allocatiom address */ +#define MMUOR_UAA 0x00000001 /* Update allocation address */ #define MMUOR_ACC 0x00000002 /* TLB access */ #define MMUOR_RD 0x00000004 /* TLB access read */ #define MMUOR_WR 0x00000000 /* TLB access write */ diff --git a/arch/m68k/include/asm/motorola_pgalloc.h b/arch/m68k/include/asm/motorola_pgalloc.h index 24bcba496c75..c895b987202c 100644 --- a/arch/m68k/include/asm/motorola_pgalloc.h +++ b/arch/m68k/include/asm/motorola_pgalloc.h @@ -11,7 +11,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long ad { pte_t *pte; - pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); if (pte) { __flush_page_to_ram(pte); flush_tlb_kernel_page(pte); @@ -32,7 +32,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addres struct page *page; pte_t *pte; - page = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); + page = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0); if(!page) return NULL; if (!pgtable_page_ctor(page)) { diff --git a/arch/m68k/include/asm/q40_master.h b/arch/m68k/include/asm/q40_master.h index fc5b36278d04..c48d21b68f04 100644 --- a/arch/m68k/include/asm/q40_master.h +++ b/arch/m68k/include/asm/q40_master.h @@ -1,6 +1,6 @@ /* * Q40 master Chip Control - * RTC stuff merged for compactnes.. + * RTC stuff merged for compactness. */ #ifndef _Q40_MASTER_H diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h index 0931388de47f..1901f61f926f 100644 --- a/arch/m68k/include/asm/sun3_pgalloc.h +++ b/arch/m68k/include/asm/sun3_pgalloc.h @@ -37,7 +37,7 @@ do { \ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - unsigned long page = __get_free_page(GFP_KERNEL|__GFP_REPEAT); + unsigned long page = __get_free_page(GFP_KERNEL); if (!page) return NULL; @@ -49,7 +49,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { - struct page *page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0); + struct page *page = alloc_pages(GFP_KERNEL, 0); if (page == NULL) return NULL; diff --git a/arch/m68k/mac/iop.c b/arch/m68k/mac/iop.c index 4d2adfb32a2a..7990b6f50105 100644 --- a/arch/m68k/mac/iop.c +++ b/arch/m68k/mac/iop.c @@ -60,7 +60,7 @@ * * The host talks to the IOPs using a rather simple message-passing scheme via * a shared memory area in the IOP RAM. Each IOP has seven "channels"; each - * channel is conneced to a specific software driver on the IOP. For example + * channel is connected to a specific software driver on the IOP. For example * on the SCC IOP there is one channel for each serial port. Each channel has * an incoming and and outgoing message queue with a depth of one. * diff --git a/arch/m68k/math-emu/fp_decode.h b/arch/m68k/math-emu/fp_decode.h index 759679d9ab96..6d1e760e2a0e 100644 --- a/arch/m68k/math-emu/fp_decode.h +++ b/arch/m68k/math-emu/fp_decode.h @@ -130,7 +130,7 @@ do_fscc=0 bfextu %d2{#13,#3},%d0 .endm -| decode the 8bit diplacement from the brief extension word +| decode the 8bit displacement from the brief extension word .macro fp_decode_disp8 move.b %d2,%d0 ext.w %d0 diff --git a/arch/metag/include/asm/pgalloc.h b/arch/metag/include/asm/pgalloc.h index 3104df0a4822..c2caa1ee4360 100644 --- a/arch/metag/include/asm/pgalloc.h +++ b/arch/metag/include/asm/pgalloc.h @@ -42,8 +42,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | - __GFP_ZERO); + pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); return pte; } @@ -51,7 +50,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *pte; - pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0); + pte = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0); if (!pte) return NULL; if (!pgtable_page_ctor(pte)) { diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h index 61436d69775c..7c89390c0c13 100644 --- a/arch/microblaze/include/asm/pgalloc.h +++ b/arch/microblaze/include/asm/pgalloc.h @@ -116,9 +116,9 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, struct page *ptepage; #ifdef CONFIG_HIGHPTE - int flags = GFP_KERNEL | __GFP_HIGHMEM | __GFP_REPEAT; + int flags = GFP_KERNEL | __GFP_HIGHMEM; #else - int flags = GFP_KERNEL | __GFP_REPEAT; + int flags = GFP_KERNEL; #endif ptepage = alloc_pages(flags, 0); diff --git a/arch/microblaze/mm/pgtable.c b/arch/microblaze/mm/pgtable.c index 4f4520e779a5..eb99fcc76088 100644 --- a/arch/microblaze/mm/pgtable.c +++ b/arch/microblaze/mm/pgtable.c @@ -239,8 +239,7 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, { pte_t *pte; if (mem_init_done) { - pte = (pte_t *)__get_free_page(GFP_KERNEL | - __GFP_REPEAT | __GFP_ZERO); + pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); } else { pte = (pte_t *)early_get_page(); if (pte) diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 6733ac575da4..36a391d289aa 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -74,7 +74,7 @@ #define KVM_GUEST_KUSEG 0x00000000UL #define KVM_GUEST_KSEG0 0x40000000UL #define KVM_GUEST_KSEG23 0x60000000UL -#define KVM_GUEST_KSEGX(a) ((_ACAST32_(a)) & 0x60000000) +#define KVM_GUEST_KSEGX(a) ((_ACAST32_(a)) & 0xe0000000) #define KVM_GUEST_CPHYSADDR(a) ((_ACAST32_(a)) & 0x1fffffff) #define KVM_GUEST_CKSEG0ADDR(a) (KVM_GUEST_CPHYSADDR(a) | KVM_GUEST_KSEG0) @@ -338,6 +338,7 @@ struct kvm_mips_tlb { #define KVM_MIPS_GUEST_TLB_SIZE 64 struct kvm_vcpu_arch { void *host_ebase, *guest_ebase; + int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu); unsigned long host_stack; unsigned long host_gp; diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index b336037e8768..93c079a1cfc8 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -69,7 +69,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, { pte_t *pte; - pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, PTE_ORDER); + pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER); return pte; } @@ -79,7 +79,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, { struct page *pte; - pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER); + pte = alloc_pages(GFP_KERNEL, PTE_ORDER); if (!pte) return NULL; clear_highpage(pte); @@ -113,7 +113,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) { pmd_t *pmd; - pmd = (pmd_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT, PMD_ORDER); + pmd = (pmd_t *) __get_free_pages(GFP_KERNEL, PMD_ORDER); if (pmd) pmd_init((unsigned long)pmd, (unsigned long)invalid_pte_table); return pmd; diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index a6b611f1da43..7d44e888134f 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -24,7 +24,7 @@ struct mm_struct; struct vm_area_struct; #define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_NO_READ | \ - _CACHE_CACHABLE_NONCOHERENT) + _page_cachable_default) #define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_WRITE | \ _page_cachable_default) #define PAGE_COPY __pgprot(_PAGE_PRESENT | _PAGE_NO_EXEC | \ @@ -476,7 +476,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) pte.pte_low &= (_PAGE_MODIFIED | _PAGE_ACCESSED | _PFNX_MASK); pte.pte_high &= (_PFN_MASK | _CACHE_MASK); pte.pte_low |= pgprot_val(newprot) & ~_PFNX_MASK; - pte.pte_high |= pgprot_val(newprot) & ~_PFN_MASK; + pte.pte_high |= pgprot_val(newprot) & ~(_PFN_MASK | _CACHE_MASK); return pte; } #elif defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) @@ -491,7 +491,8 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) #else static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { - return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)); + return __pte((pte_val(pte) & _PAGE_CHG_MASK) | + (pgprot_val(newprot) & ~_PAGE_CHG_MASK)); } #endif @@ -632,7 +633,8 @@ static inline struct page *pmd_page(pmd_t pmd) static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - pmd_val(pmd) = (pmd_val(pmd) & _PAGE_CHG_MASK) | pgprot_val(newprot); + pmd_val(pmd) = (pmd_val(pmd) & (_PAGE_CHG_MASK | _PAGE_HUGE)) | + (pgprot_val(newprot) & ~_PAGE_CHG_MASK); return pmd; } diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 396df6eb0a12..645c8a1982a7 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1636,6 +1636,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, if (index < 0) { vcpu->arch.host_cp0_entryhi = (va & VPN2_MASK); vcpu->arch.host_cp0_badvaddr = va; + vcpu->arch.pc = curr_pc; er = kvm_mips_emulate_tlbmiss_ld(cause, NULL, run, vcpu); preempt_enable(); @@ -1647,6 +1648,8 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, * invalid exception to the guest */ if (!TLB_IS_VALID(*tlb, va)) { + vcpu->arch.host_cp0_badvaddr = va; + vcpu->arch.pc = curr_pc; er = kvm_mips_emulate_tlbinv_ld(cause, NULL, run, vcpu); preempt_enable(); @@ -1666,7 +1669,7 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, cache, op, base, arch->gprs[base], offset); er = EMULATE_FAIL; preempt_enable(); - goto dont_update_pc; + goto done; } @@ -1694,16 +1697,20 @@ enum emulation_result kvm_mips_emulate_cache(uint32_t inst, uint32_t *opc, kvm_err("NO-OP CACHE (cache: %#x, op: %#x, base[%d]: %#lx, offset: %#x\n", cache, op, base, arch->gprs[base], offset); er = EMULATE_FAIL; - preempt_enable(); - goto dont_update_pc; } preempt_enable(); +done: + /* Rollback PC only if emulation was unsuccessful */ + if (er == EMULATE_FAIL) + vcpu->arch.pc = curr_pc; dont_update_pc: - /* Rollback PC */ - vcpu->arch.pc = curr_pc; -done: + /* + * This is for exceptions whose emulation updates the PC, so do not + * overwrite the PC under any circumstances + */ + return er; } diff --git a/arch/mips/kvm/interrupt.h b/arch/mips/kvm/interrupt.h index 4ab4bdfad703..2143884709e4 100644 --- a/arch/mips/kvm/interrupt.h +++ b/arch/mips/kvm/interrupt.h @@ -28,6 +28,7 @@ #define MIPS_EXC_MAX 12 /* XXXSL More to follow */ +extern char __kvm_mips_vcpu_run_end[]; extern char mips32_exception[], mips32_exceptionEnd[]; extern char mips32_GuestException[], mips32_GuestExceptionEnd[]; diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S index 3ef03009de5f..828fcfc1cd7f 100644 --- a/arch/mips/kvm/locore.S +++ b/arch/mips/kvm/locore.S @@ -202,6 +202,7 @@ FEXPORT(__kvm_mips_load_k0k1) /* Jump to guest */ eret +EXPORT(__kvm_mips_vcpu_run_end) VECTOR(MIPSX(exception), unknown) /* Find out what mode we came from and jump to the proper handler. */ diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index dc052fb5c7a2..44da5259f390 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -315,6 +315,15 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) memcpy(gebase + offset, mips32_GuestException, mips32_GuestExceptionEnd - mips32_GuestException); +#ifdef MODULE + offset += mips32_GuestExceptionEnd - mips32_GuestException; + memcpy(gebase + offset, (char *)__kvm_mips_vcpu_run, + __kvm_mips_vcpu_run_end - (char *)__kvm_mips_vcpu_run); + vcpu->arch.vcpu_run = gebase + offset; +#else + vcpu->arch.vcpu_run = __kvm_mips_vcpu_run; +#endif + /* Invalidate the icache for these ranges */ local_flush_icache_range((unsigned long)gebase, (unsigned long)gebase + ALIGN(size, PAGE_SIZE)); @@ -404,7 +413,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) /* Disable hardware page table walking while in guest */ htw_stop(); - r = __kvm_mips_vcpu_run(run, vcpu); + r = vcpu->arch.vcpu_run(run, vcpu); /* Re-enable HTW before enabling interrupts */ htw_start(); diff --git a/arch/mn10300/include/asm/thread_info.h b/arch/mn10300/include/asm/thread_info.h index 4861a78c7160..f5f90bbf019d 100644 --- a/arch/mn10300/include/asm/thread_info.h +++ b/arch/mn10300/include/asm/thread_info.h @@ -115,7 +115,7 @@ static inline unsigned long current_stack_pointer(void) } #ifndef CONFIG_KGDB -void arch_release_thread_info(struct thread_info *ti); +void arch_release_thread_stack(unsigned long *stack); #endif #define get_thread_info(ti) get_task_struct((ti)->task) #define put_thread_info(ti) put_task_struct((ti)->task) diff --git a/arch/mn10300/kernel/kgdb.c b/arch/mn10300/kernel/kgdb.c index 99770823451a..2d7986c386fe 100644 --- a/arch/mn10300/kernel/kgdb.c +++ b/arch/mn10300/kernel/kgdb.c @@ -397,8 +397,9 @@ static bool kgdb_arch_undo_singlestep(struct pt_regs *regs) * single-step state is cleared. At this point the breakpoints should have * been removed by __switch_to(). */ -void arch_release_thread_info(struct thread_info *ti) +void arch_release_thread_stack(unsigned long *stack) { + struct thread_info *ti = (void *)stack; if (kgdb_sstep_thread == ti) { kgdb_sstep_thread = NULL; diff --git a/arch/mn10300/mm/pgtable.c b/arch/mn10300/mm/pgtable.c index e77a7c728081..9577cf768875 100644 --- a/arch/mn10300/mm/pgtable.c +++ b/arch/mn10300/mm/pgtable.c @@ -63,7 +63,7 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT); + pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL); if (pte) clear_page(pte); return pte; @@ -74,9 +74,9 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) struct page *pte; #ifdef CONFIG_HIGHPTE - pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT, 0); + pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM, 0); #else - pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0); + pte = alloc_pages(GFP_KERNEL, 0); #endif if (!pte) return NULL; diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h index 6e2985e0a7b9..bb47d08c8ef7 100644 --- a/arch/nios2/include/asm/pgalloc.h +++ b/arch/nios2/include/asm/pgalloc.h @@ -42,8 +42,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, { pte_t *pte; - pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, - PTE_ORDER); + pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER); return pte; } @@ -53,7 +52,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, { struct page *pte; - pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER); + pte = alloc_pages(GFP_KERNEL, PTE_ORDER); if (pte) { if (!pgtable_page_ctor(pte)) { __free_page(pte); diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h index 21484e5b9e9a..87eebd185089 100644 --- a/arch/openrisc/include/asm/pgalloc.h +++ b/arch/openrisc/include/asm/pgalloc.h @@ -77,7 +77,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *pte; - pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0); + pte = alloc_pages(GFP_KERNEL, 0); if (!pte) return NULL; clear_page(page_address(pte)); diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c index 62b08ef392be..5b2a95116e8f 100644 --- a/arch/openrisc/mm/ioremap.c +++ b/arch/openrisc/mm/ioremap.c @@ -122,7 +122,7 @@ pte_t __init_refok *pte_alloc_one_kernel(struct mm_struct *mm, pte_t *pte; if (likely(mem_init_done)) { - pte = (pte_t *) __get_free_page(GFP_KERNEL | __GFP_REPEAT); + pte = (pte_t *) __get_free_page(GFP_KERNEL); } else { pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE); #if 0 diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index f2fd327dce2e..f08dda3f0995 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -63,8 +63,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd) static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) { - pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL|__GFP_REPEAT, - PMD_ORDER); + pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL, PMD_ORDER); if (pmd) memset(pmd, 0, PAGE_SIZE< diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 937d4e247ac3..df294224e280 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -228,5 +228,20 @@ extern void radix__vmemmap_remove_mapping(unsigned long start, extern int radix__map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t flags, unsigned int psz); + +static inline unsigned long radix__get_tree_size(void) +{ + unsigned long rts_field; + /* + * we support 52 bits, hence 52-31 = 21, 0b10101 + * RTS encoding details + * bits 0 - 3 of rts -> bits 6 - 8 unsigned long + * bits 4 - 5 of rts -> bits 62 - 63 of unsigned long + */ + rts_field = (0x5UL << 5); /* 6 - 8 bits */ + rts_field |= (0x2UL << 61); + + return rts_field; +} #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index 13ef38828dfe..3fa94fcac628 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -18,16 +18,19 @@ extern void radix__local_flush_tlb_mm(struct mm_struct *mm); extern void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); extern void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, unsigned long ap, int nid); +extern void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); extern void radix__tlb_flush(struct mmu_gather *tlb); #ifdef CONFIG_SMP extern void radix__flush_tlb_mm(struct mm_struct *mm); extern void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr); extern void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, unsigned long ap, int nid); +extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr); #else #define radix__flush_tlb_mm(mm) radix__local_flush_tlb_mm(mm) #define radix__flush_tlb_page(vma,addr) radix__local_flush_tlb_page(vma,addr) #define radix___flush_tlb_page(mm,addr,p,i) radix___local_flush_tlb_page(mm,addr,p,i) +#define radix__flush_tlb_pwc(tlb, addr) radix__local_flush_tlb_pwc(tlb, addr) #endif #endif diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index d98424ae356c..96e5769b18b0 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -72,5 +72,19 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, #define flush_tlb_mm(mm) local_flush_tlb_mm(mm) #define flush_tlb_page(vma, addr) local_flush_tlb_page(vma, addr) #endif /* CONFIG_SMP */ +/* + * flush the page walk cache for the address + */ +static inline void flush_tlb_pgtable(struct mmu_gather *tlb, unsigned long address) +{ + /* + * Flush the page table walk cache on freeing a page table. We already + * have marked the upper/higher level page table entry none by now. + * So it is safe to flush PWC here. + */ + if (!radix_enabled()) + return; + radix__flush_tlb_pwc(tlb, address); +} #endif /* _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H */ diff --git a/arch/powerpc/include/asm/book3s/pgalloc.h b/arch/powerpc/include/asm/book3s/pgalloc.h index 54f591e9572e..c0a69ae92256 100644 --- a/arch/powerpc/include/asm/book3s/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/pgalloc.h @@ -4,11 +4,6 @@ #include extern void tlb_remove_table(struct mmu_gather *tlb, void *table); -static inline void tlb_flush_pgtable(struct mmu_gather *tlb, - unsigned long address) -{ - -} #ifdef CONFIG_PPC64 #include diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h index 0c12a3bfe2ab..897d2e1c8a9b 100644 --- a/arch/powerpc/include/asm/nohash/64/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h @@ -57,8 +57,7 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), - GFP_KERNEL|__GFP_REPEAT); + return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE), GFP_KERNEL); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) @@ -88,7 +87,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO); + return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); } static inline pgtable_t pte_alloc_one(struct mm_struct *mm, @@ -172,7 +171,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { - pte_fragment_fre((unsigned long *)pte, 1); + pte_fragment_free((unsigned long *)pte, 1); } static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) @@ -190,8 +189,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), - GFP_KERNEL|__GFP_REPEAT); + return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX), GFP_KERNEL); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 2714a3b81d24..d70101e1e25c 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -642,13 +642,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, if (pe->type & EEH_PE_VF) { eeh_pe_dev_traverse(pe, eeh_rmv_device, NULL); } else { - eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_lock_rescan_remove(); pci_hp_remove_devices(bus); pci_unlock_rescan_remove(); } } else if (frozen_bus) { - eeh_pe_dev_traverse(pe, eeh_rmv_device, &rmv_data); + eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data); } /* @@ -692,10 +691,12 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, */ edev = list_first_entry(&pe->edevs, struct eeh_dev, list); eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL); - if (pe->type & EEH_PE_VF) + if (pe->type & EEH_PE_VF) { eeh_add_virt_device(edev, NULL); - else + } else { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_hp_add_devices(bus); + } } else if (frozen_bus && rmv_data->removed) { pr_info("EEH: Sleep 5s ahead of partial hotplug\n"); ssleep(5); diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 4c9440629128..8bcc1b457115 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1399,11 +1399,12 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_RADIX) lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ mtlr r10 -BEGIN_MMU_FTR_SECTION - b 2f -END_MMU_FTR_SECTION_IFSET(MMU_FTR_RADIX) andi. r10,r12,MSR_RI /* check for unrecoverable exception */ +BEGIN_MMU_FTR_SECTION beq- 2f +FTR_SECTION_ELSE + b 2f +ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_RADIX) .machine push .machine "power4" diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 3759df52bd67..a5ae49a2dcc4 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -47,7 +47,6 @@ static int __init pcibios_init(void) printk(KERN_INFO "PCI: Probing PCI hardware\n"); - pci_io_base = ISA_IO_BASE; /* For now, override phys_mem_access_prot. If we need it,g * later, we may move that initialization to each ppc_md */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index e2f12cbcade9..0b93893424f5 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1505,6 +1505,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.regs = regs - 1; } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * Clear any transactional state, we're exec()ing. The cause is + * not important as there will never be a recheckpoint so it's not + * user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); +#endif + memset(regs->gpr, 0, sizeof(regs->gpr)); regs->ctr = 0; regs->link = 0; diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index ccd2037c797f..6ee4b72cda42 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -719,7 +719,7 @@ unsigned char ibm_architecture_vec[] = { * must match by the macro below. Update the definition if * the structure layout changes. */ -#define IBM_ARCH_VEC_NRCORES_OFFSET 125 +#define IBM_ARCH_VEC_NRCORES_OFFSET 133 W(NR_CPUS), /* number of cores supported */ 0, 0, diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 30a03c03fe73..060b140f03c6 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -377,7 +377,7 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, #else BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != - offsetof(struct thread_fp_state, fpr[32][0])); + offsetof(struct thread_fp_state, fpr[32])); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.fp_state, 0, -1); @@ -405,7 +405,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, return 0; #else BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != - offsetof(struct thread_fp_state, fpr[32][0])); + offsetof(struct thread_fp_state, fpr[32])); return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.fp_state, 0, -1); diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index bf8f34a58670..b7019b559ddb 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -110,17 +110,11 @@ _GLOBAL(tm_reclaim) std r3, STK_PARAM(R3)(r1) SAVE_NVGPRS(r1) - /* We need to setup MSR for VSX register save instructions. Here we - * also clear the MSR RI since when we do the treclaim, we won't have a - * valid kernel pointer for a while. We clear RI here as it avoids - * adding another mtmsr closer to the treclaim. This makes the region - * maked as non-recoverable wider than it needs to be but it saves on - * inserting another mtmsrd later. - */ + /* We need to setup MSR for VSX register save instructions. */ mfmsr r14 mr r15, r14 ori r15, r15, MSR_FP - li r16, MSR_RI + li r16, 0 ori r16, r16, MSR_EE /* IRQs hard off */ andc r15, r15, r16 oris r15, r15, MSR_VEC@h @@ -176,7 +170,17 @@ dont_backup_fp: 1: tdeqi r6, 0 EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,0 - /* The moment we treclaim, ALL of our GPRs will switch + /* Clear MSR RI since we are about to change r1, EE is already off. */ + li r4, 0 + mtmsrd r4, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + * + * The moment we treclaim, ALL of our GPRs will switch * to user register state. (FPRs, CCR etc. also!) * Use an sprg and a tm_scratch in the PACA to shuffle. */ @@ -197,6 +201,11 @@ dont_backup_fp: /* Store the PPR in r11 and reset to decent value */ std r11, GPR11(r1) /* Temporary stash */ + + /* Reset MSR RI so we can take SLB faults again */ + li r11, MSR_RI + mtmsrd r11, 1 + mfspr r11, SPRN_PPR HMT_MEDIUM @@ -397,11 +406,6 @@ restore_gprs: ld r5, THREAD_TM_DSCR(r3) ld r6, THREAD_TM_PPR(r3) - /* Clear the MSR RI since we are about to change R1. EE is already off - */ - li r4, 0 - mtmsrd r4, 1 - REST_GPR(0, r7) /* GPR0 */ REST_2GPRS(2, r7) /* GPR2-3 */ REST_GPR(4, r7) /* GPR4 */ @@ -439,10 +443,33 @@ restore_gprs: ld r6, _CCR(r7) mtcr r6 - REST_GPR(1, r7) /* GPR1 */ - REST_GPR(5, r7) /* GPR5-7 */ REST_GPR(6, r7) - ld r7, GPR7(r7) + + /* + * Store r1 and r5 on the stack so that we can access them + * after we clear MSR RI. + */ + + REST_GPR(5, r7) + std r5, -8(r1) + ld r5, GPR1(r7) + std r5, -16(r1) + + REST_GPR(7, r7) + + /* Clear MSR RI since we are about to change r1. EE is already off */ + li r5, 0 + mtmsrd r5, 1 + + /* + * BE CAREFUL HERE: + * At this point we can't take an SLB miss since we have MSR_RI + * off. Load only to/from the stack/paca which are in SLB bolted regions + * until we turn MSR RI back on. + */ + + ld r5, -8(r1) + ld r1, -16(r1) /* Commit register state as checkpointed state: */ TRECHKPT diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index d873f6507f72..f8a871a72985 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -316,8 +316,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp, DBG_LOW(" -> hit\n"); /* Update the HPTE */ hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) & - ~(HPTE_R_PP | HPTE_R_N)) | - (newpp & (HPTE_R_PP | HPTE_R_N | + ~(HPTE_R_PPP | HPTE_R_N)) | + (newpp & (HPTE_R_PPP | HPTE_R_N | HPTE_R_C))); } native_unlock_hpte(hptep); @@ -385,8 +385,8 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, /* Update the HPTE */ hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) & - ~(HPTE_R_PP | HPTE_R_N)) | - (newpp & (HPTE_R_PP | HPTE_R_N))); + ~(HPTE_R_PPP | HPTE_R_N)) | + (newpp & (HPTE_R_PPP | HPTE_R_N))); /* * Ensure it is out of the tlb too. Bolted entries base and * actual page size will be same. @@ -550,7 +550,11 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot, } } /* This works for all page sizes, and for 256M and 1T segments */ - *ssize = hpte_v >> HPTE_V_SSIZE_SHIFT; + if (cpu_has_feature(CPU_FTR_ARCH_300)) + *ssize = hpte_r >> HPTE_R_3_0_SSIZE_SHIFT; + else + *ssize = hpte_v >> HPTE_V_SSIZE_SHIFT; + shift = mmu_psize_defs[size].shift; avpn = (HPTE_V_AVPN_VAL(hpte_v) & ~mmu_psize_defs[size].avpnm); diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index b2740c67e172..2971ea18c768 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -201,9 +201,8 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags) /* * We can't allow hardware to update hpte bits. Hence always * set 'R' bit and set 'C' if it is a write fault - * Memory coherence is always enabled */ - rflags |= HPTE_R_R | HPTE_R_M; + rflags |= HPTE_R_R; if (pteflags & _PAGE_DIRTY) rflags |= HPTE_R_C; @@ -213,10 +212,15 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags) if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_TOLERANT) rflags |= HPTE_R_I; - if ((pteflags & _PAGE_CACHE_CTL ) == _PAGE_NON_IDEMPOTENT) + else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT) rflags |= (HPTE_R_I | HPTE_R_G); - if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO) - rflags |= (HPTE_R_I | HPTE_R_W); + else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO) + rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M); + else + /* + * Add memory coherence if cache inhibited is not set + */ + rflags |= HPTE_R_M; return rflags; } @@ -918,6 +922,10 @@ void __init hash__early_init_mmu(void) vmemmap = (struct page *)H_VMEMMAP_BASE; ioremap_bot = IOREMAP_BASE; +#ifdef CONFIG_PCI + pci_io_base = ISA_IO_BASE; +#endif + /* Initialize the MMU Hash table and create the linear mapping * of memory. Has to be done before SLB initialization as this is * currently where the page size encoding is obtained. diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 5aac1a3f86cd..119d18611500 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -73,7 +73,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, cachep = PGT_CACHE(pdshift - pshift); #endif - new = kmem_cache_zalloc(cachep, GFP_KERNEL|__GFP_REPEAT); + new = kmem_cache_zalloc(cachep, GFP_KERNEL); BUG_ON(pshift > HUGEPD_SHIFT_MASK); BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK); diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index 227b2a6c4544..196222227e82 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -65,7 +65,7 @@ static int radix__init_new_context(struct mm_struct *mm, int index) /* * set the process table entry, */ - rts_field = 3ull << PPC_BITLSHIFT(2); + rts_field = radix__get_tree_size(); process_tb[index].prtb0 = cpu_to_be64(rts_field | __pa(mm->pgd) | RADIX_PGD_INDEX_SIZE); return 0; } diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index c939e6e57a9e..7931e1496f0d 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -160,9 +160,8 @@ static void __init radix_init_pgtable(void) process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT); /* * Fill in the process table. - * we support 52 bits, hence 52-28 = 24, 11000 */ - rts_field = 3ull << PPC_BITLSHIFT(2); + rts_field = radix__get_tree_size(); process_tb->prtb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE); /* * Fill in the partition table. We are suppose to use effective address @@ -176,10 +175,8 @@ static void __init radix_init_pgtable(void) static void __init radix_init_partition_table(void) { unsigned long rts_field; - /* - * we support 52 bits, hence 52-28 = 24, 11000 - */ - rts_field = 3ull << PPC_BITLSHIFT(2); + + rts_field = radix__get_tree_size(); BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large."); partition_tb = early_alloc_pgtable(1UL << PATB_SIZE_SHIFT); @@ -331,6 +328,11 @@ void __init radix__early_init_mmu(void) __vmalloc_end = RADIX_VMALLOC_END; vmemmap = (struct page *)RADIX_VMEMMAP_BASE; ioremap_bot = IOREMAP_BASE; + +#ifdef CONFIG_PCI + pci_io_base = ISA_IO_BASE; +#endif + /* * For now radix also use the same frag size */ diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index bf7bf32b54f8..7f922f557936 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -84,7 +84,7 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long add pte_t *pte; if (slab_is_available()) { - pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); } else { pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); if (pte) @@ -97,7 +97,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *ptepage; - gfp_t flags = GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO; + gfp_t flags = GFP_KERNEL | __GFP_ZERO; ptepage = alloc_pages(flags, 0); if (!ptepage) diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index e009e0604a8a..f5e8d4edb808 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -350,8 +350,7 @@ static pte_t *get_from_cache(struct mm_struct *mm) static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel) { void *ret = NULL; - struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | - __GFP_REPEAT | __GFP_ZERO); + struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); if (!page) return NULL; if (!kernel && !pgtable_page_ctor(page)) { diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 0fdaf93a3e09..ab2f60e812e2 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -18,16 +18,20 @@ static DEFINE_RAW_SPINLOCK(native_tlbie_lock); -static inline void __tlbiel_pid(unsigned long pid, int set) +#define RIC_FLUSH_TLB 0 +#define RIC_FLUSH_PWC 1 +#define RIC_FLUSH_ALL 2 + +static inline void __tlbiel_pid(unsigned long pid, int set, + unsigned long ric) { - unsigned long rb,rs,ric,prs,r; + unsigned long rb,rs,prs,r; rb = PPC_BIT(53); /* IS = 1 */ rb |= set << PPC_BITLSHIFT(51); rs = ((unsigned long)pid) << PPC_BITLSHIFT(31); prs = 1; /* process scoped */ r = 1; /* raidx format */ - ric = 2; /* invalidate all the caches */ asm volatile("ptesync": : :"memory"); asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |" @@ -39,25 +43,24 @@ static inline void __tlbiel_pid(unsigned long pid, int set) /* * We use 128 set in radix mode and 256 set in hpt mode. */ -static inline void _tlbiel_pid(unsigned long pid) +static inline void _tlbiel_pid(unsigned long pid, unsigned long ric) { int set; for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) { - __tlbiel_pid(pid, set); + __tlbiel_pid(pid, set, ric); } return; } -static inline void _tlbie_pid(unsigned long pid) +static inline void _tlbie_pid(unsigned long pid, unsigned long ric) { - unsigned long rb,rs,ric,prs,r; + unsigned long rb,rs,prs,r; rb = PPC_BIT(53); /* IS = 1 */ rs = pid << PPC_BITLSHIFT(31); prs = 1; /* process scoped */ r = 1; /* raidx format */ - ric = 2; /* invalidate all the caches */ asm volatile("ptesync": : :"memory"); asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |" @@ -67,16 +70,15 @@ static inline void _tlbie_pid(unsigned long pid) } static inline void _tlbiel_va(unsigned long va, unsigned long pid, - unsigned long ap) + unsigned long ap, unsigned long ric) { - unsigned long rb,rs,ric,prs,r; + unsigned long rb,rs,prs,r; rb = va & ~(PPC_BITMASK(52, 63)); rb |= ap << PPC_BITLSHIFT(58); rs = pid << PPC_BITLSHIFT(31); prs = 1; /* process scoped */ r = 1; /* raidx format */ - ric = 0; /* no cluster flush yet */ asm volatile("ptesync": : :"memory"); asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |" @@ -86,16 +88,15 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid, } static inline void _tlbie_va(unsigned long va, unsigned long pid, - unsigned long ap) + unsigned long ap, unsigned long ric) { - unsigned long rb,rs,ric,prs,r; + unsigned long rb,rs,prs,r; rb = va & ~(PPC_BITMASK(52, 63)); rb |= ap << PPC_BITLSHIFT(58); rs = pid << PPC_BITLSHIFT(31); prs = 1; /* process scoped */ r = 1; /* raidx format */ - ric = 0; /* no cluster flush yet */ asm volatile("ptesync": : :"memory"); asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |" @@ -117,25 +118,40 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid, */ void radix__local_flush_tlb_mm(struct mm_struct *mm) { - unsigned int pid; + unsigned long pid; preempt_disable(); pid = mm->context.id; if (pid != MMU_NO_CONTEXT) - _tlbiel_pid(pid); + _tlbiel_pid(pid, RIC_FLUSH_ALL); preempt_enable(); } EXPORT_SYMBOL(radix__local_flush_tlb_mm); +void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr) +{ + unsigned long pid; + struct mm_struct *mm = tlb->mm; + + preempt_disable(); + + pid = mm->context.id; + if (pid != MMU_NO_CONTEXT) + _tlbiel_pid(pid, RIC_FLUSH_PWC); + + preempt_enable(); +} +EXPORT_SYMBOL(radix__local_flush_tlb_pwc); + void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, unsigned long ap, int nid) { - unsigned int pid; + unsigned long pid; preempt_disable(); pid = mm ? mm->context.id : 0; if (pid != MMU_NO_CONTEXT) - _tlbiel_va(vmaddr, pid, ap); + _tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB); preempt_enable(); } @@ -160,7 +176,7 @@ static int mm_is_core_local(struct mm_struct *mm) void radix__flush_tlb_mm(struct mm_struct *mm) { - unsigned int pid; + unsigned long pid; preempt_disable(); pid = mm->context.id; @@ -172,20 +188,46 @@ void radix__flush_tlb_mm(struct mm_struct *mm) if (lock_tlbie) raw_spin_lock(&native_tlbie_lock); - _tlbie_pid(pid); + _tlbie_pid(pid, RIC_FLUSH_ALL); if (lock_tlbie) raw_spin_unlock(&native_tlbie_lock); } else - _tlbiel_pid(pid); + _tlbiel_pid(pid, RIC_FLUSH_ALL); no_context: preempt_enable(); } EXPORT_SYMBOL(radix__flush_tlb_mm); +void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr) +{ + unsigned long pid; + struct mm_struct *mm = tlb->mm; + + preempt_disable(); + + pid = mm->context.id; + if (unlikely(pid == MMU_NO_CONTEXT)) + goto no_context; + + if (!mm_is_core_local(mm)) { + int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); + + if (lock_tlbie) + raw_spin_lock(&native_tlbie_lock); + _tlbie_pid(pid, RIC_FLUSH_PWC); + if (lock_tlbie) + raw_spin_unlock(&native_tlbie_lock); + } else + _tlbiel_pid(pid, RIC_FLUSH_PWC); +no_context: + preempt_enable(); +} +EXPORT_SYMBOL(radix__flush_tlb_pwc); + void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, unsigned long ap, int nid) { - unsigned int pid; + unsigned long pid; preempt_disable(); pid = mm ? mm->context.id : 0; @@ -196,11 +238,11 @@ void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr, if (lock_tlbie) raw_spin_lock(&native_tlbie_lock); - _tlbie_va(vmaddr, pid, ap); + _tlbie_va(vmaddr, pid, ap, RIC_FLUSH_TLB); if (lock_tlbie) raw_spin_unlock(&native_tlbie_lock); } else - _tlbiel_va(vmaddr, pid, ap); + _tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB); bail: preempt_enable(); } @@ -224,7 +266,7 @@ void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end) if (lock_tlbie) raw_spin_lock(&native_tlbie_lock); - _tlbie_pid(0); + _tlbie_pid(0, RIC_FLUSH_ALL); if (lock_tlbie) raw_spin_unlock(&native_tlbie_lock); } diff --git a/arch/powerpc/platforms/512x/clock-commonclk.c b/arch/powerpc/platforms/512x/clock-commonclk.c index c50ea76ba66c..6081fbd75330 100644 --- a/arch/powerpc/platforms/512x/clock-commonclk.c +++ b/arch/powerpc/platforms/512x/clock-commonclk.c @@ -221,7 +221,7 @@ static bool soc_has_mclk_mux0_canin(void) /* convenience wrappers around the common clk API */ static inline struct clk *mpc512x_clk_fixed(const char *name, int rate) { - return clk_register_fixed_rate(NULL, name, NULL, CLK_IS_ROOT, rate); + return clk_register_fixed_rate(NULL, name, NULL, 0, rate); } static inline struct clk *mpc512x_clk_factor( diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index 84fb984f29c1..85c85eb3e245 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -172,7 +172,7 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i, if (rc < 0) goto out; - skip = roundup(cprm->file->f_pos - total + sz, 4) - cprm->file->f_pos; + skip = roundup(cprm->pos - total + sz, 4) - cprm->pos; if (!dump_skip(cprm, skip)) goto Eio; out: diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index b7dfc1359d01..3e8865b187de 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -927,7 +927,7 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, dn = pci_device_to_OF_node(dev); pdn = PCI_DN(dn); buid = pdn->phb->buid; - cfg_addr = (pdn->busno << 8) | pdn->devfn; + cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8)); ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query, cfg_addr, BUID_HI(buid), BUID_LO(buid)); @@ -956,7 +956,7 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, dn = pci_device_to_OF_node(dev); pdn = PCI_DN(dn); buid = pdn->phb->buid; - cfg_addr = (pdn->busno << 8) | pdn->devfn; + cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8)); do { /* extra outputs are LIOBN and dma-addr (hi, lo) */ diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h index 5e04f3cbd320..8ae236b0f80b 100644 --- a/arch/s390/include/asm/fpu/api.h +++ b/arch/s390/include/asm/fpu/api.h @@ -22,7 +22,7 @@ static inline int test_fp_ctl(u32 fpc) " la %0,0\n" "1:\n" EX_TABLE(0b,1b) - : "=d" (rc), "=d" (orig_fpc) + : "=d" (rc), "=&d" (orig_fpc) : "d" (fpc), "0" (-EINVAL)); return rc; } diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 37b9017c6a96..ac82e8eb936d 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -245,6 +245,7 @@ struct kvm_vcpu_stat { u32 exit_stop_request; u32 exit_validity; u32 exit_instruction; + u32 exit_pei; u32 halt_successful_poll; u32 halt_attempted_poll; u32 halt_poll_invalid; diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index f20abdb5630a..d14069d4b88d 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -2064,12 +2064,5 @@ void s390_reset_system(void) S390_lowcore.program_new_psw.addr = (unsigned long) s390_base_pgm_handler; - /* - * Clear subchannel ID and number to signal new kernel that no CCW or - * SCSI IPL has been done (for kexec and kdump) - */ - S390_lowcore.subchannel_id = 0; - S390_lowcore.subchannel_nr = 0; - do_reset_calls(); } diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 59215c518f37..7ec63b1d920d 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -649,6 +649,8 @@ static int cpumf_pmu_commit_txn(struct pmu *pmu) /* Performance monitoring unit for s390x */ static struct pmu cpumf_pmu = { + .task_ctx_nr = perf_sw_context, + .capabilities = PERF_PMU_CAP_NO_INTERRUPT, .pmu_enable = cpumf_pmu_enable, .pmu_disable = cpumf_pmu_disable, .event_init = cpumf_pmu_event_init, @@ -708,12 +710,6 @@ static int __init cpumf_pmu_init(void) goto out; } - /* The CPU measurement counter facility does not have overflow - * interrupts to do sampling. Sampling must be provided by - * external means, for example, by timers. - */ - cpumf_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; - cpumf_pmu.attr_groups = cpumf_cf_event_group(); rc = perf_pmu_register(&cpumf_pmu, "cpum_cf", PERF_TYPE_RAW); if (rc) { diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 2e6b54e4d3f9..252157181302 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -341,6 +341,8 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) static int handle_partial_execution(struct kvm_vcpu *vcpu) { + vcpu->stat.exit_pei++; + if (vcpu->arch.sie_block->ipa == 0xb254) /* MVPG */ return handle_mvpg_pei(vcpu); if (vcpu->arch.sie_block->ipa >> 8 == 0xae) /* SIGP */ diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 6d8ec3ac9dd8..43f2a2b80490 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -61,6 +61,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "exit_external_request", VCPU_STAT(exit_external_request) }, { "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) }, { "exit_instruction", VCPU_STAT(exit_instruction) }, + { "exit_pei", VCPU_STAT(exit_pei) }, { "exit_program_interruption", VCPU_STAT(exit_program_interruption) }, { "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) }, { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, @@ -657,7 +658,7 @@ static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr) kvm->arch.model.cpuid = proc->cpuid; lowest_ibc = sclp.ibc >> 16 & 0xfff; unblocked_ibc = sclp.ibc & 0xfff; - if (lowest_ibc) { + if (lowest_ibc && proc->ibc) { if (proc->ibc > unblocked_ibc) kvm->arch.model.ibc = unblocked_ibc; else if (proc->ibc < lowest_ibc) diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index e8b5962ac12a..e2565d2d0c32 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -169,7 +169,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm) return table; } /* Allocate a fresh page */ - page = alloc_page(GFP_KERNEL|__GFP_REPEAT); + page = alloc_page(GFP_KERNEL); if (!page) return NULL; if (!pgtable_page_ctor(page)) { diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 4324b87f9398..9f0ce0e6eeb4 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -437,7 +437,7 @@ void ptep_zap_unused(struct mm_struct *mm, unsigned long addr, pgste = pgste_get_lock(ptep); pgstev = pgste_val(pgste); pte = *ptep; - if (pte_swap(pte) && + if (!reset && pte_swap(pte) && ((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED || (pgstev & _PGSTE_GPS_ZERO))) { ptep_zap_swap_entry(mm, pte_to_swp_entry(pte)); diff --git a/arch/score/include/asm/pgalloc.h b/arch/score/include/asm/pgalloc.h index 2e067657db98..49b012d78c1a 100644 --- a/arch/score/include/asm/pgalloc.h +++ b/arch/score/include/asm/pgalloc.h @@ -42,8 +42,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, { pte_t *pte; - pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, - PTE_ORDER); + pte = (pte_t *) __get_free_pages(GFP_KERNEL|__GFP_ZERO, PTE_ORDER); return pte; } @@ -53,7 +52,7 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm, { struct page *pte; - pte = alloc_pages(GFP_KERNEL | __GFP_REPEAT, PTE_ORDER); + pte = alloc_pages(GFP_KERNEL, PTE_ORDER); if (!pte) return NULL; clear_highpage(pte); diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h index a33673b3687d..f3f42c84c40f 100644 --- a/arch/sh/include/asm/pgalloc.h +++ b/arch/sh/include/asm/pgalloc.h @@ -34,7 +34,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - return quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL); + return quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL); } static inline pgtable_t pte_alloc_one(struct mm_struct *mm, @@ -43,7 +43,7 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm, struct page *page; void *pg; - pg = quicklist_alloc(QUICK_PT, GFP_KERNEL | __GFP_REPEAT, NULL); + pg = quicklist_alloc(QUICK_PT, GFP_KERNEL, NULL); if (!pg) return NULL; page = virt_to_page(pg); diff --git a/arch/sh/mm/pgtable.c b/arch/sh/mm/pgtable.c index 26e03a1f7ca4..a62bd8696779 100644 --- a/arch/sh/mm/pgtable.c +++ b/arch/sh/mm/pgtable.c @@ -1,7 +1,7 @@ #include #include -#define PGALLOC_GFP GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO +#define PGALLOC_GFP GFP_KERNEL | __GFP_ZERO static struct kmem_cache *pgd_cachep; #if PAGETABLE_LEVELS > 2 diff --git a/arch/sparc/include/asm/pgalloc_64.h b/arch/sparc/include/asm/pgalloc_64.h index 5e3187185b4a..3529f1378cd8 100644 --- a/arch/sparc/include/asm/pgalloc_64.h +++ b/arch/sparc/include/asm/pgalloc_64.h @@ -41,8 +41,7 @@ static inline void __pud_populate(pud_t *pud, pmd_t *pmd) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(pgtable_cache, - GFP_KERNEL|__GFP_REPEAT); + return kmem_cache_alloc(pgtable_cache, GFP_KERNEL); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) @@ -52,8 +51,7 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { - return kmem_cache_alloc(pgtable_cache, - GFP_KERNEL|__GFP_REPEAT); + return kmem_cache_alloc(pgtable_cache, GFP_KERNEL); } static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 14bb0d5ed3c6..aec508e37490 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2704,8 +2704,7 @@ void __flush_tlb_all(void) pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | - __GFP_REPEAT | __GFP_ZERO); + struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); pte_t *pte = NULL; if (page) @@ -2717,8 +2716,7 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm, pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { - struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | - __GFP_REPEAT | __GFP_ZERO); + struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); if (!page) return NULL; if (!pgtable_page_ctor(page)) { diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h index 4b7cef9e94e0..c1467ac59ce6 100644 --- a/arch/tile/include/asm/thread_info.h +++ b/arch/tile/include/asm/thread_info.h @@ -78,7 +78,7 @@ struct thread_info { #ifndef __ASSEMBLY__ -void arch_release_thread_info(struct thread_info *info); +void arch_release_thread_stack(unsigned long *stack); /* How to get the thread information struct from C. */ register unsigned long stack_pointer __asm__("sp"); diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 6b705ccc9cc1..a465d8372edd 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -73,8 +73,9 @@ void arch_cpu_idle(void) /* * Release a thread_info structure */ -void arch_release_thread_info(struct thread_info *info) +void arch_release_thread_stack(unsigned long *stack) { + struct thread_info *info = (void *)stack; struct single_step_state *step_state = info->step_state; if (step_state) { diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c index 7bf2491a9c1f..c4d5bf841a7f 100644 --- a/arch/tile/mm/pgtable.c +++ b/arch/tile/mm/pgtable.c @@ -231,7 +231,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) struct page *pgtable_alloc_one(struct mm_struct *mm, unsigned long address, int order) { - gfp_t flags = GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO; + gfp_t flags = GFP_KERNEL|__GFP_ZERO; struct page *p; int i; diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index b2a2dff50b4e..e7437ec62710 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -204,7 +204,7 @@ pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { pte_t *pte; - pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); return pte; } @@ -212,7 +212,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { struct page *pte; - pte = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + pte = alloc_page(GFP_KERNEL|__GFP_ZERO); if (!pte) return NULL; if (!pgtable_page_ctor(pte)) { diff --git a/arch/unicore32/include/asm/pgalloc.h b/arch/unicore32/include/asm/pgalloc.h index 2e02d1356fdf..26775793c204 100644 --- a/arch/unicore32/include/asm/pgalloc.h +++ b/arch/unicore32/include/asm/pgalloc.h @@ -28,7 +28,7 @@ extern void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd); #define pgd_alloc(mm) get_pgd_slow(mm) #define pgd_free(mm, pgd) free_pgd_slow(mm, pgd) -#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) /* * Allocate one PTE table. diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0a7b885964ba..d9a94da0c29f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2439,6 +2439,15 @@ config PCI_CNB20LE_QUIRK source "drivers/pci/Kconfig" +config ISA_BUS + bool "ISA-style bus support on modern systems" if EXPERT + select ISA_BUS_API + help + Enables ISA-style drivers on modern systems. This is necessary to + support PC/104 devices on X86_64 platforms. + + If unsure, say N. + # x86_64 have no ISA slots, but can have ISA-style DMA. config ISA_DMA_API bool "ISA-style DMA support" if (X86_64 && EXPERT) diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 700a9c6e6159..be8e688fa0d4 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -162,6 +162,9 @@ isoimage: $(obj)/bzImage for i in lib lib64 share end ; do \ if [ -f /usr/$$i/syslinux/isolinux.bin ] ; then \ cp /usr/$$i/syslinux/isolinux.bin $(obj)/isoimage ; \ + if [ -f /usr/$$i/syslinux/ldlinux.c32 ]; then \ + cp /usr/$$i/syslinux/ldlinux.c32 $(obj)/isoimage ; \ + fi ; \ break ; \ fi ; \ if [ $$i = end ] ; then exit 1 ; fi ; \ diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 33787ee817f0..91eac39625be 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -263,7 +263,7 @@ static bool check_hw_exists(void) msr_fail: pr_cont("Broken PMU hardware detected, using software events only.\n"); - pr_info("%sFailed to access perfctr msr (MSR %x is %Lx)\n", + printk("%sFailed to access perfctr msr (MSR %x is %Lx)\n", boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR, reg, val_new); @@ -2319,7 +2319,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { struct stack_frame frame; - const void __user *fp; + const unsigned long __user *fp; if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { /* TODO: We don't support guest os callchain now */ @@ -2332,7 +2332,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM)) return; - fp = (void __user *)regs->bp; + fp = (unsigned long __user *)regs->bp; perf_callchain_store(entry, regs->ip); @@ -2345,16 +2345,17 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs pagefault_disable(); while (entry->nr < entry->max_stack) { unsigned long bytes; + frame.next_frame = NULL; frame.return_address = 0; - if (!access_ok(VERIFY_READ, fp, 16)) + if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2)) break; - bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8); + bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp)); if (bytes != 0) break; - bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8); + bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp)); if (bytes != 0) break; diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile index 3660b2cf245a..06c2baa51814 100644 --- a/arch/x86/events/intel/Makefile +++ b/arch/x86/events/intel/Makefile @@ -1,8 +1,8 @@ obj-$(CONFIG_CPU_SUP_INTEL) += core.o bts.o cqm.o obj-$(CONFIG_CPU_SUP_INTEL) += ds.o knc.o obj-$(CONFIG_CPU_SUP_INTEL) += lbr.o p4.o p6.o pt.o -obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl.o -intel-rapl-objs := rapl.o +obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += intel-rapl-perf.o +intel-rapl-perf-objs := rapl.o obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += intel-uncore.o intel-uncore-objs := uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE) += intel-cstate.o diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7c666958a625..9b4f9d3ce465 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -115,6 +115,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */ INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -139,6 +143,10 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -182,6 +190,16 @@ struct event_constraint intel_skl_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ + + /* + * when HT is off, these can only run on the bottom 4 counters + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0xf), /* MEM_TRANS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xc6, 0xf), /* FRONTEND_RETIRED.* */ + EVENT_CONSTRAINT_END }; @@ -250,6 +268,10 @@ static struct event_constraint intel_hsw_event_constraints[] = { /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), + /* + * When HT is off these events can only run on the bottom 4 counters + * When HT is on, they are impacted by the HT bug and require EXCL access + */ INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -264,6 +286,13 @@ struct event_constraint intel_bdw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ + /* + * when HT is off, these can only run on the bottom 4 counters + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xcd, 0xf), /* MEM_TRANS_RETIRED.* */ EVENT_CONSTRAINT_END }; diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 99c4bab123cd..e30eef4f29a6 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -714,7 +714,7 @@ static void cleanup_rapl_pmus(void) int i; for (i = 0; i < rapl_pmus->maxpkg; i++) - kfree(rapl_pmus->pmus + i); + kfree(rapl_pmus->pmus[i]); kfree(rapl_pmus); } diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index b2625867ebd1..874e8bd64d1d 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -2868,27 +2868,10 @@ static struct intel_uncore_type bdx_uncore_cbox = { .format_group = &hswep_uncore_cbox_format_group, }; -static struct intel_uncore_type bdx_uncore_sbox = { - .name = "sbox", - .num_counters = 4, - .num_boxes = 4, - .perf_ctr_bits = 48, - .event_ctl = HSWEP_S0_MSR_PMON_CTL0, - .perf_ctr = HSWEP_S0_MSR_PMON_CTR0, - .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK, - .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL, - .msr_offset = HSWEP_SBOX_MSR_OFFSET, - .ops = &hswep_uncore_sbox_msr_ops, - .format_group = &hswep_uncore_sbox_format_group, -}; - -#define BDX_MSR_UNCORE_SBOX 3 - static struct intel_uncore_type *bdx_msr_uncores[] = { &bdx_uncore_ubox, &bdx_uncore_cbox, &hswep_uncore_pcu, - &bdx_uncore_sbox, NULL, }; @@ -2897,10 +2880,6 @@ void bdx_uncore_cpu_init(void) if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; uncore_msr_uncores = bdx_msr_uncores; - - /* BDX-DE doesn't have SBOX */ - if (boot_cpu_data.x86_model == 86) - uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL; } static struct intel_uncore_type bdx_uncore_ha = { diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 4a413485f9eb..c64b1e9c5d1a 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -301,10 +301,6 @@ #define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ #define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ #define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ -#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */ - - #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional @@ -312,5 +308,7 @@ */ #define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif +#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h new file mode 100644 index 000000000000..6999f7d01a0d --- /dev/null +++ b/arch/x86/include/asm/intel-family.h @@ -0,0 +1,68 @@ +#ifndef _ASM_X86_INTEL_FAMILY_H +#define _ASM_X86_INTEL_FAMILY_H + +/* + * "Big Core" Processors (Branded as Core, Xeon, etc...) + * + * The "_X" parts are generally the EP and EX Xeons, or the + * "Extreme" ones, like Broadwell-E. + * + * Things ending in "2" are usually because we have no better + * name for them. There's no processor called "WESTMERE2". + */ + +#define INTEL_FAM6_CORE_YONAH 0x0E +#define INTEL_FAM6_CORE2_MEROM 0x0F +#define INTEL_FAM6_CORE2_MEROM_L 0x16 +#define INTEL_FAM6_CORE2_PENRYN 0x17 +#define INTEL_FAM6_CORE2_DUNNINGTON 0x1D + +#define INTEL_FAM6_NEHALEM 0x1E +#define INTEL_FAM6_NEHALEM_EP 0x1A +#define INTEL_FAM6_NEHALEM_EX 0x2E +#define INTEL_FAM6_WESTMERE 0x25 +#define INTEL_FAM6_WESTMERE2 0x1F +#define INTEL_FAM6_WESTMERE_EP 0x2C +#define INTEL_FAM6_WESTMERE_EX 0x2F + +#define INTEL_FAM6_SANDYBRIDGE 0x2A +#define INTEL_FAM6_SANDYBRIDGE_X 0x2D +#define INTEL_FAM6_IVYBRIDGE 0x3A +#define INTEL_FAM6_IVYBRIDGE_X 0x3E + +#define INTEL_FAM6_HASWELL_CORE 0x3C +#define INTEL_FAM6_HASWELL_X 0x3F +#define INTEL_FAM6_HASWELL_ULT 0x45 +#define INTEL_FAM6_HASWELL_GT3E 0x46 + +#define INTEL_FAM6_BROADWELL_CORE 0x3D +#define INTEL_FAM6_BROADWELL_XEON_D 0x56 +#define INTEL_FAM6_BROADWELL_GT3E 0x47 +#define INTEL_FAM6_BROADWELL_X 0x4F + +#define INTEL_FAM6_SKYLAKE_MOBILE 0x4E +#define INTEL_FAM6_SKYLAKE_DESKTOP 0x5E +#define INTEL_FAM6_SKYLAKE_X 0x55 +#define INTEL_FAM6_KABYLAKE_MOBILE 0x8E +#define INTEL_FAM6_KABYLAKE_DESKTOP 0x9E + +/* "Small Core" Processors (Atom) */ + +#define INTEL_FAM6_ATOM_PINEVIEW 0x1C +#define INTEL_FAM6_ATOM_LINCROFT 0x26 +#define INTEL_FAM6_ATOM_PENWELL 0x27 +#define INTEL_FAM6_ATOM_CLOVERVIEW 0x35 +#define INTEL_FAM6_ATOM_CEDARVIEW 0x36 +#define INTEL_FAM6_ATOM_SILVERMONT1 0x37 /* BayTrail/BYT / Valleyview */ +#define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */ +#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */ +#define INTEL_FAM6_ATOM_MERRIFIELD1 0x4A /* Tangier */ +#define INTEL_FAM6_ATOM_MERRIFIELD2 0x5A /* Annidale */ +#define INTEL_FAM6_ATOM_GOLDMONT 0x5C +#define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */ + +/* Xeon Phi */ + +#define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */ + +#endif /* _ASM_X86_INTEL_FAMILY_H */ diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 4421b5da409d..d1d1e5094c28 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -38,12 +38,11 @@ typedef u8 kprobe_opcode_t; #define RELATIVECALL_OPCODE 0xe8 #define RELATIVE_ADDR_SIZE 4 #define MAX_STACK_SIZE 64 -#define MIN_STACK_SIZE(ADDR) \ - (((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \ - THREAD_SIZE - (unsigned long)(ADDR))) \ - ? (MAX_STACK_SIZE) \ - : (((unsigned long)current_thread_info()) + \ - THREAD_SIZE - (unsigned long)(ADDR))) +#define CUR_STACK_SIZE(ADDR) \ + (current_top_of_stack() - (unsigned long)(ADDR)) +#define MIN_STACK_SIZE(ADDR) \ + (MAX_STACK_SIZE < CUR_STACK_SIZE(ADDR) ? \ + MAX_STACK_SIZE : CUR_STACK_SIZE(ADDR)) #define flush_insn_slot(p) do { } while (0) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e0fbe7e70dc1..69e62862b622 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -27,6 +27,7 @@ #include #include +#include #include #include #include @@ -1368,4 +1369,14 @@ static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} +static inline int kvm_cpu_get_apicid(int mps_cpu) +{ +#ifdef CONFIG_X86_LOCAL_APIC + return __default_cpu_present_to_apicid(mps_cpu); +#else + WARN_ON_ONCE(1); + return BAD_APICID; +#endif +} + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 7dc1d8fef7fd..b5fee97813cd 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -122,7 +122,7 @@ notrace static inline void native_write_msr(unsigned int msr, "2:\n" _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe) : : "c" (msr), "a"(low), "d" (high) : "memory"); - if (msr_tracepoint_active(__tracepoint_read_msr)) + if (msr_tracepoint_active(__tracepoint_write_msr)) do_trace_write_msr(msr, ((u64)high << 32 | low), 0); } @@ -141,7 +141,7 @@ notrace static inline int native_write_msr_safe(unsigned int msr, : "c" (msr), "0" (low), "d" (high), [fault] "i" (-EIO) : "memory"); - if (msr_tracepoint_active(__tracepoint_read_msr)) + if (msr_tracepoint_active(__tracepoint_write_msr)) do_trace_write_msr(msr, ((u64)high << 32 | low), err); return err; } diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index bf7f8b55b0f9..574c23cf761a 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -81,7 +81,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { struct page *page; - page = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0); + page = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0); if (!page) return NULL; if (!pgtable_pmd_page_ctor(page)) { @@ -125,7 +125,7 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); + return (pud_t *)get_zeroed_page(GFP_KERNEL); } static inline void pud_free(struct mm_struct *mm, pud_t *pud) diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index fdcc04020636..7c1c89598688 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -68,30 +68,23 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) return product; } -static __always_inline -u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src) -{ - u64 delta = rdtsc_ordered() - src->tsc_timestamp; - return pvclock_scale_delta(delta, src->tsc_to_system_mul, - src->tsc_shift); -} - static __always_inline unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, cycle_t *cycles, u8 *flags) { unsigned version; - cycle_t ret, offset; - u8 ret_flags; + cycle_t offset; + u64 delta; version = src->version; + /* Make the latest version visible */ + smp_rmb(); - offset = pvclock_get_nsec_offset(src); - ret = src->system_time + offset; - ret_flags = src->flags; - - *cycles = ret; - *flags = ret_flags; + delta = rdtsc_ordered() - src->tsc_timestamp; + offset = pvclock_scale_delta(delta, src->tsc_to_system_mul, + src->tsc_shift); + *cycles = src->system_time + offset; + *flags = src->flags; return version; } diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 7c247e7404be..0944218af9e2 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -14,7 +14,7 @@ extern int kstack_depth_to_print; struct thread_info; struct stacktrace_ops; -typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo, +typedef unsigned long (*walk_stack_t)(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, @@ -23,13 +23,13 @@ typedef unsigned long (*walk_stack_t)(struct thread_info *tinfo, int *graph); extern unsigned long -print_context_stack(struct thread_info *tinfo, +print_context_stack(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data, unsigned long *end, int *graph); extern unsigned long -print_context_stack_bp(struct thread_info *tinfo, +print_context_stack_bp(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data, unsigned long *end, int *graph); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index a147e676fc7b..e991d5c8bb3a 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -71,8 +71,8 @@ int amd_cache_northbridges(void) while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL) i++; - if (i == 0) - return 0; + if (!i) + return -ENODEV; nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL); if (!nb) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 84e33ff5a6d5..446702ed99dc 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2588,8 +2588,8 @@ static struct resource * __init ioapic_setup_resources(void) res[num].flags = IORESOURCE_MEM | IORESOURCE_BUSY; snprintf(mem, IOAPIC_RESOURCE_NAME_SIZE, "IOAPIC %u", i); mem += IOAPIC_RESOURCE_NAME_SIZE; + ioapics[i].iomem_res = &res[num]; num++; - ioapics[i].iomem_res = res; } ioapic_resources = res; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index c343a54bed39..f5c69d8974e1 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -674,14 +674,14 @@ static void init_amd_bd(struct cpuinfo_x86 *c) u64 value; /* re-enable TopologyExtensions if switched off by BIOS */ - if ((c->x86_model >= 0x10) && (c->x86_model <= 0x1f) && + if ((c->x86_model >= 0x10) && (c->x86_model <= 0x6f) && !cpu_has(c, X86_FEATURE_TOPOEXT)) { if (msr_set_bit(0xc0011005, 54) > 0) { rdmsrl(0xc0011005, value); if (value & BIT_64(54)) { set_cpu_cap(c, X86_FEATURE_TOPOEXT); - pr_info(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); + pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); } } } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 2bb25c3fe2e8..ef8017ca5ba9 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -42,16 +42,14 @@ void printk_address(unsigned long address) static void print_ftrace_graph_addr(unsigned long addr, void *data, const struct stacktrace_ops *ops, - struct thread_info *tinfo, int *graph) + struct task_struct *task, int *graph) { - struct task_struct *task; unsigned long ret_addr; int index; if (addr != (unsigned long)return_to_handler) return; - task = tinfo->task; index = task->curr_ret_stack; if (!task->ret_stack || index < *graph) @@ -68,7 +66,7 @@ print_ftrace_graph_addr(unsigned long addr, void *data, static inline void print_ftrace_graph_addr(unsigned long addr, void *data, const struct stacktrace_ops *ops, - struct thread_info *tinfo, int *graph) + struct task_struct *task, int *graph) { } #endif @@ -79,10 +77,10 @@ print_ftrace_graph_addr(unsigned long addr, void *data, * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack */ -static inline int valid_stack_ptr(struct thread_info *tinfo, +static inline int valid_stack_ptr(struct task_struct *task, void *p, unsigned int size, void *end) { - void *t = tinfo; + void *t = task_stack_page(task); if (end) { if (p < end && p >= (end-THREAD_SIZE)) return 1; @@ -93,14 +91,14 @@ static inline int valid_stack_ptr(struct thread_info *tinfo, } unsigned long -print_context_stack(struct thread_info *tinfo, +print_context_stack(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data, unsigned long *end, int *graph) { struct stack_frame *frame = (struct stack_frame *)bp; - while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) { + while (valid_stack_ptr(task, stack, sizeof(*stack), end)) { unsigned long addr; addr = *stack; @@ -112,7 +110,7 @@ print_context_stack(struct thread_info *tinfo, } else { ops->address(data, addr, 0); } - print_ftrace_graph_addr(addr, data, ops, tinfo, graph); + print_ftrace_graph_addr(addr, data, ops, task, graph); } stack++; } @@ -121,7 +119,7 @@ print_context_stack(struct thread_info *tinfo, EXPORT_SYMBOL_GPL(print_context_stack); unsigned long -print_context_stack_bp(struct thread_info *tinfo, +print_context_stack_bp(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data, unsigned long *end, int *graph) @@ -129,7 +127,7 @@ print_context_stack_bp(struct thread_info *tinfo, struct stack_frame *frame = (struct stack_frame *)bp; unsigned long *ret_addr = &frame->return_address; - while (valid_stack_ptr(tinfo, ret_addr, sizeof(*ret_addr), end)) { + while (valid_stack_ptr(task, ret_addr, sizeof(*ret_addr), end)) { unsigned long addr = *ret_addr; if (!__kernel_text_address(addr)) @@ -139,7 +137,7 @@ print_context_stack_bp(struct thread_info *tinfo, break; frame = frame->next_frame; ret_addr = &frame->return_address; - print_ftrace_graph_addr(addr, data, ops, tinfo, graph); + print_ftrace_graph_addr(addr, data, ops, task, graph); } return (unsigned long)frame; diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 464ffd69b92e..fef917e79b9d 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -61,15 +61,13 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, bp = stack_frame(task, regs); for (;;) { - struct thread_info *context; void *end_stack; end_stack = is_hardirq_stack(stack, cpu); if (!end_stack) end_stack = is_softirq_stack(stack, cpu); - context = task_thread_info(task); - bp = ops->walk_stack(context, stack, bp, ops, data, + bp = ops->walk_stack(task, stack, bp, ops, data, end_stack, &graph); /* Stop if not on irq stack */ diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 5f1c6266eb30..d558a8a49016 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -153,7 +153,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, const struct stacktrace_ops *ops, void *data) { const unsigned cpu = get_cpu(); - struct thread_info *tinfo; unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu); unsigned long dummy; unsigned used = 0; @@ -179,7 +178,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, * current stack address. If the stacks consist of nested * exceptions */ - tinfo = task_thread_info(task); while (!done) { unsigned long *stack_end; enum stack_type stype; @@ -202,7 +200,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (ops->stack(data, id) < 0) break; - bp = ops->walk_stack(tinfo, stack, bp, ops, + bp = ops->walk_stack(task, stack, bp, ops, data, stack_end, &graph); ops->stack(data, ""); /* @@ -218,7 +216,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, if (ops->stack(data, "IRQ") < 0) break; - bp = ops->walk_stack(tinfo, stack, bp, + bp = ops->walk_stack(task, stack, bp, ops, data, stack_end, &graph); /* * We link to the next stack (which would be @@ -240,7 +238,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs, /* * This handles the process stack: */ - bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph); + bp = ops->walk_stack(task, stack, bp, ops, data, NULL, &graph); put_cpu(); } EXPORT_SYMBOL(dump_trace); diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 757390eb562b..de7501edb21c 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -11,7 +11,11 @@ #include #include +#include +#include #include +#include +#include #include #include #include @@ -21,6 +25,9 @@ #include #include #include +#include + +#define dev_err(msg) pr_err("pci 0000:%02x:%02x.%d: %s", bus, slot, func, msg) static void __init fix_hypertransport_config(int num, int slot, int func) { @@ -75,6 +82,13 @@ static void __init nvidia_bugs(int num, int slot, int func) { #ifdef CONFIG_ACPI #ifdef CONFIG_X86_IO_APIC + /* + * Only applies to Nvidia root ports (bus 0) and not to + * Nvidia graphics cards with PCI ports on secondary buses. + */ + if (num) + return; + /* * All timer overrides on Nvidia are * wrong unless HPET is enabled. @@ -574,6 +588,61 @@ static void __init force_disable_hpet(int num, int slot, int func) #endif } +#define BCM4331_MMIO_SIZE 16384 +#define BCM4331_PM_CAP 0x40 +#define bcma_aread32(reg) ioread32(mmio + 1 * BCMA_CORE_SIZE + reg) +#define bcma_awrite32(reg, val) iowrite32(val, mmio + 1 * BCMA_CORE_SIZE + reg) + +static void __init apple_airport_reset(int bus, int slot, int func) +{ + void __iomem *mmio; + u16 pmcsr; + u64 addr; + int i; + + if (!dmi_match(DMI_SYS_VENDOR, "Apple Inc.")) + return; + + /* Card may have been put into PCI_D3hot by grub quirk */ + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + pmcsr &= ~PCI_PM_CTRL_STATE_MASK; + write_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL, pmcsr); + mdelay(10); + + pmcsr = read_pci_config_16(bus, slot, func, BCM4331_PM_CAP + PCI_PM_CTRL); + if ((pmcsr & PCI_PM_CTRL_STATE_MASK) != PCI_D0) { + dev_err("Cannot power up Apple AirPort card\n"); + return; + } + } + + addr = read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_0); + addr |= (u64)read_pci_config(bus, slot, func, PCI_BASE_ADDRESS_1) << 32; + addr &= PCI_BASE_ADDRESS_MEM_MASK; + + mmio = early_ioremap(addr, BCM4331_MMIO_SIZE); + if (!mmio) { + dev_err("Cannot iomap Apple AirPort card\n"); + return; + } + + pr_info("Resetting Apple AirPort card (left enabled by EFI)\n"); + + for (i = 0; bcma_aread32(BCMA_RESET_ST) && i < 30; i++) + udelay(10); + + bcma_awrite32(BCMA_RESET_CTL, BCMA_RESET_CTL_RESET); + bcma_aread32(BCMA_RESET_CTL); + udelay(1); + + bcma_awrite32(BCMA_RESET_CTL, 0); + bcma_aread32(BCMA_RESET_CTL); + udelay(10); + + early_iounmap(mmio, BCM4331_MMIO_SIZE); +} #define QFLAG_APPLY_ONCE 0x1 #define QFLAG_APPLIED 0x2 @@ -587,12 +656,6 @@ struct chipset { void (*f)(int num, int slot, int func); }; -/* - * Only works for devices on the root bus. If you add any devices - * not on bus 0 readd another loop level in early_quirks(). But - * be careful because at least the Nvidia quirk here relies on - * only matching on bus 0. - */ static struct chipset early_qrk[] __initdata = { { PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_CLASS_BRIDGE_PCI, PCI_ANY_ID, QFLAG_APPLY_ONCE, nvidia_bugs }, @@ -622,9 +685,13 @@ static struct chipset early_qrk[] __initdata = { */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, + { PCI_VENDOR_ID_BROADCOM, 0x4331, + PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset}, {} }; +static void __init early_pci_scan_bus(int bus); + /** * check_dev_quirk - apply early quirks to a given PCI device * @num: bus number @@ -633,7 +700,7 @@ static struct chipset early_qrk[] __initdata = { * * Check the vendor & device ID against the early quirks table. * - * If the device is single function, let early_quirks() know so we don't + * If the device is single function, let early_pci_scan_bus() know so we don't * poke at this device again. */ static int __init check_dev_quirk(int num, int slot, int func) @@ -642,6 +709,7 @@ static int __init check_dev_quirk(int num, int slot, int func) u16 vendor; u16 device; u8 type; + u8 sec; int i; class = read_pci_config_16(num, slot, func, PCI_CLASS_DEVICE); @@ -669,25 +737,36 @@ static int __init check_dev_quirk(int num, int slot, int func) type = read_pci_config_byte(num, slot, func, PCI_HEADER_TYPE); + + if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) { + sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS); + if (sec > num) + early_pci_scan_bus(sec); + } + if (!(type & 0x80)) return -1; return 0; } -void __init early_quirks(void) +static void __init early_pci_scan_bus(int bus) { int slot, func; - if (!early_pci_allowed()) - return; - /* Poor man's PCI discovery */ - /* Only scan the root bus */ for (slot = 0; slot < 32; slot++) for (func = 0; func < 8; func++) { /* Only probe function 0 on single fn devices */ - if (check_dev_quirk(0, slot, func)) + if (check_dev_quirk(bus, slot, func)) break; } } + +void __init early_quirks(void) +{ + if (!early_pci_allowed()) + return; + + early_pci_scan_bus(0); +} diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 4d38416e2a7f..04f89caef9c4 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -57,7 +57,7 @@ # error "Need more than one PGD for the ESPFIX hack" #endif -#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO) /* This contains the *bottom* address of the espfix stack */ DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 38da8f29a9c8..c627bf8d98ad 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -130,11 +130,9 @@ void irq_ctx_init(int cpu) void do_softirq_own_stack(void) { - struct thread_info *curstk; struct irq_stack *irqstk; u32 *isp, *prev_esp; - curstk = current_stack(); irqstk = __this_cpu_read(softirq_stack); /* build the stack frame on the softirq stack */ diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 38cf7a741250..7847e5c0e0b5 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -961,7 +961,19 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) * normal page fault. */ regs->ip = (unsigned long)cur->addr; + /* + * Trap flag (TF) has been set here because this fault + * happened where the single stepping will be done. + * So clear it by resetting the current kprobe: + */ + regs->flags &= ~X86_EFLAGS_TF; + + /* + * If the TF flag was set before the kprobe hit, + * don't touch it: + */ regs->flags |= kcb->kprobe_old_flags; + if (kcb->kprobe_status == KPROBE_REENTER) restore_previous_kprobe(kcb); else diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 99bfc025111d..06c58ce46762 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -61,11 +61,16 @@ void pvclock_resume(void) u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src) { unsigned version; - cycle_t ret; u8 flags; do { - version = __pvclock_read_cycles(src, &ret, &flags); + version = src->version; + /* Make the latest version visible */ + smp_rmb(); + + flags = src->flags; + /* Make sure that the version double-check is last. */ + smp_rmb(); } while ((src->version & 1) || version != src->version); return flags & valid_flags; @@ -80,6 +85,8 @@ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) do { version = __pvclock_read_cycles(src, &ret, &flags); + /* Make sure that the version double-check is last. */ + smp_rmb(); } while ((src->version & 1) || version != src->version); if (unlikely((flags & PVCLOCK_GUEST_STOPPED) != 0)) { diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index d1590486204a..00f03d82e69a 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -96,6 +96,12 @@ static inline void cond_local_irq_disable(struct pt_regs *regs) local_irq_disable(); } +/* + * In IST context, we explicitly disable preemption. This serves two + * purposes: it makes it much less likely that we would accidentally + * schedule in IST context and it will force a warning if we somehow + * manage to schedule by accident. + */ void ist_enter(struct pt_regs *regs) { if (user_mode(regs)) { @@ -110,13 +116,7 @@ void ist_enter(struct pt_regs *regs) rcu_nmi_enter(); } - /* - * We are atomic because we're on the IST stack; or we're on - * x86_32, in which case we still shouldn't schedule; or we're - * on x86_64 and entered from user mode, in which case we're - * still atomic unless ist_begin_non_atomic is called. - */ - preempt_count_add(HARDIRQ_OFFSET); + preempt_disable(); /* This code is a bit fragile. Test it. */ RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work"); @@ -124,7 +124,7 @@ void ist_enter(struct pt_regs *regs) void ist_exit(struct pt_regs *regs) { - preempt_count_sub(HARDIRQ_OFFSET); + preempt_enable_no_resched(); if (!user_mode(regs)) rcu_nmi_exit(); @@ -155,7 +155,7 @@ void ist_begin_non_atomic(struct pt_regs *regs) BUG_ON((unsigned long)(current_top_of_stack() - current_stack_pointer()) >= THREAD_SIZE); - preempt_count_sub(HARDIRQ_OFFSET); + preempt_enable_no_resched(); } /** @@ -165,7 +165,7 @@ void ist_begin_non_atomic(struct pt_regs *regs) */ void ist_end_non_atomic(void) { - preempt_count_add(HARDIRQ_OFFSET); + preempt_disable(); } static nokprobe_inline int diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index bbb5b283ff63..a397200281c1 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1310,7 +1310,8 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ if (guest_tsc < tsc_deadline) - __delay(tsc_deadline - guest_tsc); + __delay(min(tsc_deadline - guest_tsc, + nsec_to_cycles(vcpu, lapic_timer_advance_ns))); } static void start_apic_timer(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 1163e8173e5a..16ef31b87452 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -238,7 +238,9 @@ module_param(nested, int, S_IRUGO); /* enable / disable AVIC */ static int avic; +#ifdef CONFIG_X86_LOCAL_APIC module_param(avic, int, S_IRUGO); +#endif static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu); @@ -981,11 +983,14 @@ static __init int svm_hardware_setup(void) } else kvm_disable_tdp(); - if (avic && (!npt_enabled || !boot_cpu_has(X86_FEATURE_AVIC))) - avic = false; - - if (avic) - pr_info("AVIC enabled\n"); + if (avic) { + if (!npt_enabled || + !boot_cpu_has(X86_FEATURE_AVIC) || + !IS_ENABLED(CONFIG_X86_LOCAL_APIC)) + avic = false; + else + pr_info("AVIC enabled\n"); + } return 0; @@ -1324,7 +1329,7 @@ static int avic_vm_init(struct kvm *kvm) static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run) { u64 entry; - int h_physical_id = __default_cpu_present_to_apicid(vcpu->cpu); + int h_physical_id = kvm_cpu_get_apicid(vcpu->cpu); struct vcpu_svm *svm = to_svm(vcpu); if (!kvm_vcpu_apicv_active(vcpu)) @@ -1349,7 +1354,7 @@ static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { u64 entry; /* ID = 0xff (broadcast), ID > 0xff (reserved) */ - int h_physical_id = __default_cpu_present_to_apicid(cpu); + int h_physical_id = kvm_cpu_get_apicid(cpu); struct vcpu_svm *svm = to_svm(vcpu); if (!kvm_vcpu_apicv_active(vcpu)) @@ -4236,7 +4241,7 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) if (avic_vcpu_is_running(vcpu)) wrmsrl(SVM_AVIC_DOORBELL, - __default_cpu_present_to_apicid(vcpu->cpu)); + kvm_cpu_get_apicid(vcpu->cpu)); else kvm_vcpu_wake_up(vcpu); } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index fb93010beaa4..64a79f271276 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2072,7 +2072,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) unsigned int dest; if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(vcpu)) return; do { @@ -2180,7 +2181,8 @@ static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(vcpu)) return; /* Set SN when the vCPU is preempted */ @@ -6669,7 +6671,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, /* Checks for #GP/#SS exceptions. */ exn = false; - if (is_protmode(vcpu)) { + if (is_long_mode(vcpu)) { + /* Long mode: #GP(0)/#SS(0) if the memory address is in a + * non-canonical form. This is the only check on the memory + * destination for long mode! + */ + exn = is_noncanonical_address(*ret); + } else if (is_protmode(vcpu)) { /* Protected mode: apply checks for segment validity in the * following order: * - segment type check (#GP(0) may be thrown) @@ -6686,17 +6694,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, * execute-only code segment */ exn = ((s.type & 0xa) == 8); - } - if (exn) { - kvm_queue_exception_e(vcpu, GP_VECTOR, 0); - return 1; - } - if (is_long_mode(vcpu)) { - /* Long mode: #GP(0)/#SS(0) if the memory address is in a - * non-canonical form. This is an only check for long mode. - */ - exn = is_noncanonical_address(*ret); - } else if (is_protmode(vcpu)) { + if (exn) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. */ exn = (s.unusable != 0); @@ -10714,7 +10715,8 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu) struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(vcpu)) return 0; vcpu->pre_pcpu = vcpu->cpu; @@ -10780,7 +10782,8 @@ static void vmx_post_block(struct kvm_vcpu *vcpu) unsigned long flags; if (!kvm_arch_has_assigned_device(vcpu->kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(vcpu)) return; do { @@ -10833,7 +10836,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, int idx, ret = -EINVAL; if (!kvm_arch_has_assigned_device(kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + !irq_remapping_cap(IRQ_POSTING_CAP) || + !kvm_vcpu_apicv_active(kvm->vcpus[0])) return 0; idx = srcu_read_lock(&kvm->irq_srcu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 902d9da12392..7da5dd2057a9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1244,12 +1244,6 @@ static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0); static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz); static unsigned long max_tsc_khz; -static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) -{ - return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, - vcpu->arch.virtual_tsc_shift); -} - static u32 adjust_tsc_khz(u32 khz, s32 ppm) { u64 v = (u64)khz * (1000000 + ppm); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 7ce3634ab5fe..a82ca466b62e 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -2,6 +2,7 @@ #define ARCH_X86_KVM_X86_H #include +#include #include "kvm_cache_regs.h" #define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL @@ -195,6 +196,12 @@ extern unsigned int lapic_timer_advance_ns; extern struct static_key kvm_no_apic_vcpu; +static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) +{ + return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, + vcpu->arch.virtual_tsc_shift); +} + /* Same "calling convention" as do_div: * - divide (n << 32) by base * - put result in n diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 1b1110fa0057..0493c17b8a51 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -54,8 +54,8 @@ static int kasan_die_handler(struct notifier_block *self, void *data) { if (val == DIE_GPF) { - pr_emerg("CONFIG_KASAN_INLINE enabled"); - pr_emerg("GPF could be caused by NULL-ptr deref or user memory access"); + pr_emerg("CONFIG_KASAN_INLINE enabled\n"); + pr_emerg("GPF could be caused by NULL-ptr deref or user memory access\n"); } return NOTIFY_OK; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 4eb287e25043..aa0ff4b02a96 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -6,7 +6,7 @@ #include #include -#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO +#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO #ifdef CONFIG_HIGHPTE #define PGALLOC_USER_GFP __GFP_HIGHMEM diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index b2a4e2a61f6b..3cd69832d7f4 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -396,6 +396,7 @@ int __init pci_acpi_init(void) return -ENODEV; printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n"); + acpi_irq_penalty_init(); pcibios_enable_irq = acpi_pci_irq_enable; pcibios_disable_irq = acpi_pci_irq_disable; x86_init.pci.init_irq = x86_init_noop; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 6e7242be1c87..b226b3f497f1 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -139,7 +139,7 @@ int __init efi_alloc_page_tables(void) if (efi_enabled(EFI_OLD_MEMMAP)) return 0; - gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO; + gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO; efi_pgd = (pgd_t *)__get_free_page(gfp_mask); if (!efi_pgd) return -ENOMEM; diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 009947d419a6..f2b5e6a5cf95 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -19,6 +19,7 @@ #include #include #include +#include /* Defined in hibernate_asm_64.S */ extern asmlinkage __visible int restore_image(void); @@ -28,6 +29,7 @@ extern asmlinkage __visible int restore_image(void); * kernel's text (this value is passed in the image header). */ unsigned long restore_jump_address __visible; +unsigned long jump_address_phys; /* * Value of the cr3 register from before the hibernation (this value is passed @@ -37,7 +39,43 @@ unsigned long restore_cr3 __visible; pgd_t *temp_level4_pgt __visible; -void *relocated_restore_code __visible; +unsigned long relocated_restore_code __visible; + +static int set_up_temporary_text_mapping(void) +{ + pmd_t *pmd; + pud_t *pud; + + /* + * The new mapping only has to cover the page containing the image + * kernel's entry point (jump_address_phys), because the switch over to + * it is carried out by relocated code running from a page allocated + * specifically for this purpose and covered by the identity mapping, so + * the temporary kernel text mapping is only needed for the final jump. + * Moreover, in that mapping the virtual address of the image kernel's + * entry point must be the same as its virtual address in the image + * kernel (restore_jump_address), so the image kernel's + * restore_registers() code doesn't find itself in a different area of + * the virtual address space after switching over to the original page + * tables used by the image kernel. + */ + pud = (pud_t *)get_safe_page(GFP_ATOMIC); + if (!pud) + return -ENOMEM; + + pmd = (pmd_t *)get_safe_page(GFP_ATOMIC); + if (!pmd) + return -ENOMEM; + + set_pmd(pmd + pmd_index(restore_jump_address), + __pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC)); + set_pud(pud + pud_index(restore_jump_address), + __pud(__pa(pmd) | _KERNPG_TABLE)); + set_pgd(temp_level4_pgt + pgd_index(restore_jump_address), + __pgd(__pa(pud) | _KERNPG_TABLE)); + + return 0; +} static void *alloc_pgt_page(void *context) { @@ -59,9 +97,10 @@ static int set_up_temporary_mappings(void) if (!temp_level4_pgt) return -ENOMEM; - /* It is safe to reuse the original kernel mapping */ - set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map), - init_level4_pgt[pgd_index(__START_KERNEL_map)]); + /* Prepare a temporary mapping for the kernel text */ + result = set_up_temporary_text_mapping(); + if (result) + return result; /* Set up the direct mapping from scratch */ for (i = 0; i < nr_pfn_mapped; i++) { @@ -78,19 +117,50 @@ static int set_up_temporary_mappings(void) return 0; } +static int relocate_restore_code(void) +{ + pgd_t *pgd; + pud_t *pud; + + relocated_restore_code = get_safe_page(GFP_ATOMIC); + if (!relocated_restore_code) + return -ENOMEM; + + memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE); + + /* Make the page containing the relocated code executable */ + pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code); + pud = pud_offset(pgd, relocated_restore_code); + if (pud_large(*pud)) { + set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX)); + } else { + pmd_t *pmd = pmd_offset(pud, relocated_restore_code); + + if (pmd_large(*pmd)) { + set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX)); + } else { + pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code); + + set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX)); + } + } + __flush_tlb_all(); + + return 0; +} + int swsusp_arch_resume(void) { int error; /* We have got enough memory and from now on we cannot recover */ - if ((error = set_up_temporary_mappings())) + error = set_up_temporary_mappings(); + if (error) return error; - relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC); - if (!relocated_restore_code) - return -ENOMEM; - memcpy(relocated_restore_code, &core_restore_code, - &restore_registers - &core_restore_code); + error = relocate_restore_code(); + if (error) + return error; restore_image(); return 0; @@ -109,11 +179,12 @@ int pfn_is_nosave(unsigned long pfn) struct restore_data_record { unsigned long jump_address; + unsigned long jump_address_phys; unsigned long cr3; unsigned long magic; }; -#define RESTORE_MAGIC 0x0123456789ABCDEFUL +#define RESTORE_MAGIC 0x123456789ABCDEF0UL /** * arch_hibernation_header_save - populate the architecture specific part @@ -126,7 +197,8 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size) if (max_size < sizeof(struct restore_data_record)) return -EOVERFLOW; - rdr->jump_address = restore_jump_address; + rdr->jump_address = (unsigned long)&restore_registers; + rdr->jump_address_phys = __pa_symbol(&restore_registers); rdr->cr3 = restore_cr3; rdr->magic = RESTORE_MAGIC; return 0; @@ -142,6 +214,7 @@ int arch_hibernation_header_restore(void *addr) struct restore_data_record *rdr = addr; restore_jump_address = rdr->jump_address; + jump_address_phys = rdr->jump_address_phys; restore_cr3 = rdr->cr3; return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL; } diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index 4400a43b9e28..3177c2bc26f6 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -44,9 +44,6 @@ ENTRY(swsusp_arch_suspend) pushfq popq pt_regs_flags(%rax) - /* save the address of restore_registers */ - movq $restore_registers, %rax - movq %rax, restore_jump_address(%rip) /* save cr3 */ movq %cr3, %rax movq %rax, restore_cr3(%rip) @@ -57,31 +54,34 @@ ENTRY(swsusp_arch_suspend) ENDPROC(swsusp_arch_suspend) ENTRY(restore_image) - /* switch to temporary page tables */ - movq $__PAGE_OFFSET, %rdx - movq temp_level4_pgt(%rip), %rax - subq %rdx, %rax - movq %rax, %cr3 - /* Flush TLB */ - movq mmu_cr4_features(%rip), %rax - movq %rax, %rdx - andq $~(X86_CR4_PGE), %rdx - movq %rdx, %cr4; # turn off PGE - movq %cr3, %rcx; # flush TLB - movq %rcx, %cr3; - movq %rax, %cr4; # turn PGE back on - /* prepare to jump to the image kernel */ - movq restore_jump_address(%rip), %rax - movq restore_cr3(%rip), %rbx + movq restore_jump_address(%rip), %r8 + movq restore_cr3(%rip), %r9 + + /* prepare to switch to temporary page tables */ + movq temp_level4_pgt(%rip), %rax + movq mmu_cr4_features(%rip), %rbx /* prepare to copy image data to their original locations */ movq restore_pblist(%rip), %rdx + + /* jump to relocated restore code */ movq relocated_restore_code(%rip), %rcx jmpq *%rcx /* code below has been relocated to a safe page */ ENTRY(core_restore_code) + /* switch to temporary page tables */ + movq $__PAGE_OFFSET, %rcx + subq %rcx, %rax + movq %rax, %cr3 + /* flush TLB */ + movq %rbx, %rcx + andq $~(X86_CR4_PGE), %rcx + movq %rcx, %cr4; # turn off PGE + movq %cr3, %rcx; # flush TLB + movq %rcx, %cr3; + movq %rbx, %cr4; # turn PGE back on .Lloop: testq %rdx, %rdx jz .Ldone @@ -96,24 +96,17 @@ ENTRY(core_restore_code) /* progress to the next pbe */ movq pbe_next(%rdx), %rdx jmp .Lloop + .Ldone: /* jump to the restore_registers address from the image header */ - jmpq *%rax - /* - * NOTE: This assumes that the boot kernel's text mapping covers the - * image kernel's page containing restore_registers and the address of - * this page is the same as in the image kernel's text mapping (it - * should always be true, because the text mapping is linear, starting - * from 0, and is supposed to cover the entire kernel text for every - * kernel). - * - * code below belongs to the image kernel - */ + jmpq *%r8 + /* code below belongs to the image kernel */ + .align PAGE_SIZE ENTRY(restore_registers) FRAME_BEGIN /* go back to the original page tables */ - movq %rbx, %cr3 + movq %r9, %cr3 /* Flush TLB, including "global" things (vmalloc) */ movq mmu_cr4_features(%rip), %rax diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 478a2de543a5..67433714b791 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1113,7 +1113,7 @@ static void __init xen_cleanhighmap(unsigned long vaddr, /* NOTE: The loop is more greedy than the cleanup_highmap variant. * We include the PMD passed in on _both_ boundaries. */ - for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE)); + for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PTRS_PER_PMD)); pmd++, vaddr += PMD_SIZE) { if (pmd_none(*pmd)) continue; @@ -1551,41 +1551,6 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) #endif } -#ifdef CONFIG_X86_32 -static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) -{ - /* If there's an existing pte, then don't allow _PAGE_RW to be set */ - if (pte_val_ma(*ptep) & _PAGE_PRESENT) - pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & - pte_val_ma(pte)); - - return pte; -} -#else /* CONFIG_X86_64 */ -static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) -{ - unsigned long pfn; - - if (xen_feature(XENFEAT_writable_page_tables) || - xen_feature(XENFEAT_auto_translated_physmap) || - xen_start_info->mfn_list >= __START_KERNEL_map) - return pte; - - /* - * Pages belonging to the initial p2m list mapped outside the default - * address range must be mapped read-only. This region contains the - * page tables for mapping the p2m list, too, and page tables MUST be - * mapped read-only. - */ - pfn = pte_pfn(pte); - if (pfn >= xen_start_info->first_p2m_pfn && - pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames) - pte = __pte_ma(pte_val_ma(pte) & ~_PAGE_RW); - - return pte; -} -#endif /* CONFIG_X86_64 */ - /* * Init-time set_pte while constructing initial pagetables, which * doesn't allow RO page table pages to be remapped RW. @@ -1600,13 +1565,37 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) * so always write the PTE directly and rely on Xen trapping and * emulating any updates as necessary. */ +__visible pte_t xen_make_pte_init(pteval_t pte) +{ +#ifdef CONFIG_X86_64 + unsigned long pfn; + + /* + * Pages belonging to the initial p2m list mapped outside the default + * address range must be mapped read-only. This region contains the + * page tables for mapping the p2m list, too, and page tables MUST be + * mapped read-only. + */ + pfn = (pte & PTE_PFN_MASK) >> PAGE_SHIFT; + if (xen_start_info->mfn_list < __START_KERNEL_map && + pfn >= xen_start_info->first_p2m_pfn && + pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames) + pte &= ~_PAGE_RW; +#endif + pte = pte_pfn_to_mfn(pte); + return native_make_pte(pte); +} +PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init); + static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) { - if (pte_mfn(pte) != INVALID_P2M_ENTRY) - pte = mask_rw_pte(ptep, pte); - else - pte = __pte_ma(0); - +#ifdef CONFIG_X86_32 + /* If there's an existing pte, then don't allow _PAGE_RW to be set */ + if (pte_mfn(pte) != INVALID_P2M_ENTRY + && pte_val_ma(*ptep) & _PAGE_PRESENT) + pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & + pte_val_ma(pte)); +#endif native_set_pte(ptep, pte); } @@ -2407,6 +2396,7 @@ static void __init xen_post_allocator_init(void) pv_mmu_ops.alloc_pud = xen_alloc_pud; pv_mmu_ops.release_pud = xen_release_pud; #endif + pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte); #ifdef CONFIG_X86_64 pv_mmu_ops.write_cr3 = &xen_write_cr3; @@ -2455,7 +2445,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .pte_val = PV_CALLEE_SAVE(xen_pte_val), .pgd_val = PV_CALLEE_SAVE(xen_pgd_val), - .make_pte = PV_CALLEE_SAVE(xen_make_pte), + .make_pte = PV_CALLEE_SAVE(xen_make_pte_init), .make_pgd = PV_CALLEE_SAVE(xen_make_pgd), #ifdef CONFIG_X86_PAE diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index cab9f766bb06..dd2a49a8aacc 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -182,7 +182,7 @@ static void * __ref alloc_p2m_page(void) if (unlikely(!slab_is_available())) return alloc_bootmem_align(PAGE_SIZE, PAGE_SIZE); - return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT); + return (void *)__get_free_page(GFP_KERNEL); } static void __ref free_p2m_page(void *p) diff --git a/arch/xtensa/include/asm/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h index d38eb9237e64..1065bc8bcae5 100644 --- a/arch/xtensa/include/asm/pgalloc.h +++ b/arch/xtensa/include/asm/pgalloc.h @@ -44,7 +44,7 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, pte_t *ptep; int i; - ptep = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT); + ptep = (pte_t *)__get_free_page(GFP_KERNEL); if (!ptep) return NULL; for (i = 0; i < 1024; i++) diff --git a/block/blk-lib.c b/block/blk-lib.c index 23d7f301a196..9e29dc351695 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -113,6 +113,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, ret = submit_bio_wait(type, bio); if (ret == -EOPNOTSUPP) ret = 0; + bio_put(bio); } blk_finish_plug(&plug); @@ -165,8 +166,10 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, } } - if (bio) + if (bio) { ret = submit_bio_wait(REQ_WRITE | REQ_WRITE_SAME, bio); + bio_put(bio); + } return ret != -EOPNOTSUPP ? ret : 0; } EXPORT_SYMBOL(blkdev_issue_write_same); @@ -206,8 +209,11 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, } } - if (bio) - return submit_bio_wait(WRITE, bio); + if (bio) { + ret = submit_bio_wait(WRITE, bio); + bio_put(bio); + return ret; + } return 0; } diff --git a/block/blk-mq.c b/block/blk-mq.c index 29cbc1b5fbdb..f9b9049b1284 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1262,12 +1262,9 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_queue_split(q, &bio, q->bio_split); - if (!is_flush_fua && !blk_queue_nomerges(q)) { - if (blk_attempt_plug_merge(q, bio, &request_count, - &same_queue_rq)) - return BLK_QC_T_NONE; - } else - request_count = blk_plug_queued_count(q); + if (!is_flush_fua && !blk_queue_nomerges(q) && + blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq)) + return BLK_QC_T_NONE; rq = blk_mq_map_request(q, bio, &data); if (unlikely(!rq)) @@ -1358,9 +1355,11 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) blk_queue_split(q, &bio, q->bio_split); - if (!is_flush_fua && !blk_queue_nomerges(q) && - blk_attempt_plug_merge(q, bio, &request_count, NULL)) - return BLK_QC_T_NONE; + if (!is_flush_fua && !blk_queue_nomerges(q)) { + if (blk_attempt_plug_merge(q, bio, &request_count, NULL)) + return BLK_QC_T_NONE; + } else + request_count = blk_plug_queued_count(q); rq = blk_mq_map_request(q, bio, &data); if (unlikely(!rq)) diff --git a/block/ioprio.c b/block/ioprio.c index cc7800e9eb44..01b8116298a1 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -150,8 +150,10 @@ static int get_task_ioprio(struct task_struct *p) if (ret) goto out; ret = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, IOPRIO_NORM); + task_lock(p); if (p->io_context) ret = p->io_context->ioprio; + task_unlock(p); out: return ret; } diff --git a/crypto/asymmetric_keys/mscode_parser.c b/crypto/asymmetric_keys/mscode_parser.c index 6a76d5c70ef6..9492e1c22d38 100644 --- a/crypto/asymmetric_keys/mscode_parser.c +++ b/crypto/asymmetric_keys/mscode_parser.c @@ -124,5 +124,10 @@ int mscode_note_digest(void *context, size_t hdrlen, struct pefile_context *ctx = context; ctx->digest = kmemdup(value, vlen, GFP_KERNEL); - return ctx->digest ? 0 : -ENOMEM; + if (!ctx->digest) + return -ENOMEM; + + ctx->digest_len = vlen; + + return 0; } diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c index 44b746e9df1b..2ffd69769466 100644 --- a/crypto/asymmetric_keys/pkcs7_verify.c +++ b/crypto/asymmetric_keys/pkcs7_verify.c @@ -227,7 +227,7 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7, if (asymmetric_key_id_same(p->id, auth)) goto found_issuer_check_skid; } - } else { + } else if (sig->auth_ids[1]) { auth = sig->auth_ids[1]; pr_debug("- want %*phN\n", auth->len, auth->data); for (p = pkcs7->certs; p; p = p->next) { diff --git a/crypto/asymmetric_keys/restrict.c b/crypto/asymmetric_keys/restrict.c index ac4bddf669de..19d1afb9890f 100644 --- a/crypto/asymmetric_keys/restrict.c +++ b/crypto/asymmetric_keys/restrict.c @@ -87,7 +87,7 @@ int restrict_link_by_signature(struct key *trust_keyring, sig = payload->data[asym_auth]; if (!sig->auth_ids[0] && !sig->auth_ids[1]) - return 0; + return -ENOKEY; if (ca_keyid && !asymmetric_key_id_partial(sig->auth_ids[1], ca_keyid)) return -EPERM; diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c index 43fe85f20d57..7097a3395b25 100644 --- a/crypto/crypto_user.c +++ b/crypto/crypto_user.c @@ -455,6 +455,7 @@ static const int crypto_msg_min[CRYPTO_NR_MSGTYPES] = { [CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), [CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), [CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), + [CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), [CRYPTO_MSG_DELRNG - CRYPTO_MSG_BASE] = 0, }; diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c index ead8dc0d084e..8ba426635b1b 100644 --- a/crypto/rsa-pkcs1pad.c +++ b/crypto/rsa-pkcs1pad.c @@ -102,10 +102,10 @@ struct pkcs1pad_inst_ctx { }; struct pkcs1pad_request { - struct akcipher_request child_req; - struct scatterlist in_sg[3], out_sg[2]; uint8_t *in_buf, *out_buf; + + struct akcipher_request child_req; }; static int pkcs1pad_set_pub_key(struct crypto_akcipher *tfm, const void *key, diff --git a/drivers/acpi/acpi_dbg.c b/drivers/acpi/acpi_dbg.c index 1f4128487dd4..dee86925a9a1 100644 --- a/drivers/acpi/acpi_dbg.c +++ b/drivers/acpi/acpi_dbg.c @@ -602,7 +602,7 @@ static int acpi_aml_read_user(char __user *buf, int len) crc->tail = (crc->tail + n) & (ACPI_AML_BUF_SIZE - 1); ret = n; out: - acpi_aml_unlock_fifo(ACPI_AML_OUT_USER, !ret); + acpi_aml_unlock_fifo(ACPI_AML_OUT_USER, ret >= 0); return ret; } @@ -672,7 +672,7 @@ static int acpi_aml_write_user(const char __user *buf, int len) crc->head = (crc->head + n) & (ACPI_AML_BUF_SIZE - 1); ret = n; out: - acpi_aml_unlock_fifo(ACPI_AML_IN_USER, !ret); + acpi_aml_unlock_fifo(ACPI_AML_IN_USER, ret >= 0); return n; } diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c index daceb80022b0..3b7fb99362b6 100644 --- a/drivers/acpi/acpica/hwregs.c +++ b/drivers/acpi/acpica/hwregs.c @@ -306,12 +306,6 @@ acpi_status acpi_hw_read(u32 *value, struct acpi_generic_address *reg) acpi_status acpi_hw_write(u32 value, struct acpi_generic_address *reg) { u64 address; - u8 access_width; - u32 bit_width; - u8 bit_offset; - u64 value64; - u32 new_value32, old_value32; - u8 index; acpi_status status; ACPI_FUNCTION_NAME(hw_write); @@ -323,145 +317,23 @@ acpi_status acpi_hw_write(u32 value, struct acpi_generic_address *reg) return (status); } - /* Convert access_width into number of bits based */ - - access_width = acpi_hw_get_access_bit_width(reg, 32); - bit_width = reg->bit_offset + reg->bit_width; - bit_offset = reg->bit_offset; - /* * Two address spaces supported: Memory or IO. PCI_Config is * not supported here because the GAS structure is insufficient */ - index = 0; - while (bit_width) { - /* - * Use offset style bit reads because "Index * AccessWidth" is - * ensured to be less than 32-bits by acpi_hw_validate_register(). - */ - new_value32 = ACPI_GET_BITS(&value, index * access_width, - ACPI_MASK_BITS_ABOVE_32 - (access_width)); + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { + status = acpi_os_write_memory((acpi_physical_address) + address, (u64)value, + reg->bit_width); + } else { /* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */ - if (bit_offset >= access_width) { - bit_offset -= access_width; - } else { - /* - * Use offset style bit masks because access_width is ensured - * to be less than 32-bits by acpi_hw_validate_register() and - * bit_offset/bit_width is less than access_width here. - */ - if (bit_offset) { - new_value32 &= ACPI_MASK_BITS_BELOW(bit_offset); - } - if (bit_width < access_width) { - new_value32 &= ACPI_MASK_BITS_ABOVE(bit_width); - } - - if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { - if (bit_offset || bit_width < access_width) { - /* - * Read old values in order not to modify the bits that - * are beyond the register bit_width/bit_offset setting. - */ - status = - acpi_os_read_memory((acpi_physical_address) - address + - index * - ACPI_DIV_8 - (access_width), - &value64, - access_width); - old_value32 = (u32)value64; - - /* - * Use offset style bit masks because access_width is - * ensured to be less than 32-bits by - * acpi_hw_validate_register() and bit_offset/bit_width is - * less than access_width here. - */ - if (bit_offset) { - old_value32 &= - ACPI_MASK_BITS_ABOVE - (bit_offset); - bit_offset = 0; - } - if (bit_width < access_width) { - old_value32 &= - ACPI_MASK_BITS_BELOW - (bit_width); - } - - new_value32 |= old_value32; - } - - value64 = (u64)new_value32; - status = - acpi_os_write_memory((acpi_physical_address) - address + - index * - ACPI_DIV_8 - (access_width), - value64, access_width); - } else { /* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */ - - if (bit_offset || bit_width < access_width) { - /* - * Read old values in order not to modify the bits that - * are beyond the register bit_width/bit_offset setting. - */ - status = - acpi_hw_read_port((acpi_io_address) - address + - index * - ACPI_DIV_8 - (access_width), - &old_value32, - access_width); - - /* - * Use offset style bit masks because access_width is - * ensured to be less than 32-bits by - * acpi_hw_validate_register() and bit_offset/bit_width is - * less than access_width here. - */ - if (bit_offset) { - old_value32 &= - ACPI_MASK_BITS_ABOVE - (bit_offset); - bit_offset = 0; - } - if (bit_width < access_width) { - old_value32 &= - ACPI_MASK_BITS_BELOW - (bit_width); - } - - new_value32 |= old_value32; - } - - status = acpi_hw_write_port((acpi_io_address) - address + - index * - ACPI_DIV_8 - (access_width), - new_value32, - access_width); - } - } - - /* - * Index * access_width is ensured to be less than 32-bits by - * acpi_hw_validate_register(). - */ - bit_width -= - bit_width > access_width ? access_width : bit_width; - index++; + status = acpi_hw_write_port((acpi_io_address) + address, value, reg->bit_width); } ACPI_DEBUG_PRINT((ACPI_DB_IO, "Wrote: %8.8X width %2d to %8.8X%8.8X (%s)\n", - value, access_width, ACPI_FORMAT_UINT64(address), + value, reg->bit_width, ACPI_FORMAT_UINT64(address), acpi_ut_get_region_name(reg->space_id))); return (status); diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 31e8da648fff..262ca31b86d9 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1051,7 +1051,7 @@ static int __init acpi_bus_init(void) * Maybe EC region is required at bus_scan/acpi_get_devices. So it * is necessary to enable it as early as possible. */ - acpi_boot_ec_enable(); + acpi_ec_dsdt_probe(); printk(KERN_INFO PREFIX "Interpreter enabled\n"); diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 0e70181f150c..290d6f5be44b 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1331,8 +1331,6 @@ static int ec_install_handlers(struct acpi_ec *ec) static void ec_remove_handlers(struct acpi_ec *ec) { - acpi_ec_stop(ec, false); - if (test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) { if (ACPI_FAILURE(acpi_remove_address_space_handler(ec->handle, ACPI_ADR_SPACE_EC, &acpi_ec_space_handler))) @@ -1340,6 +1338,19 @@ static void ec_remove_handlers(struct acpi_ec *ec) clear_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags); } + /* + * Stops handling the EC transactions after removing the operation + * region handler. This is required because _REG(DISCONNECT) + * invoked during the removal can result in new EC transactions. + * + * Flushes the EC requests and thus disables the GPE before + * removing the GPE handler. This is required by the current ACPICA + * GPE core. ACPICA GPE core will automatically disable a GPE when + * it is indicated but there is no way to handle it. So the drivers + * must disable the GPEs prior to removing the GPE handlers. + */ + acpi_ec_stop(ec, false); + if (test_bit(EC_FLAGS_GPE_HANDLER_INSTALLED, &ec->flags)) { if (ACPI_FAILURE(acpi_remove_gpe_handler(NULL, ec->gpe, &acpi_ec_gpe_handler))) @@ -1446,10 +1457,30 @@ ec_parse_io_ports(struct acpi_resource *resource, void *context) return AE_OK; } -int __init acpi_boot_ec_enable(void) +static const struct acpi_device_id ec_device_ids[] = { + {"PNP0C09", 0}, + {"", 0}, +}; + +int __init acpi_ec_dsdt_probe(void) { - if (!boot_ec) + acpi_status status; + + if (boot_ec) return 0; + + /* + * Finding EC from DSDT if there is no ECDT EC available. When this + * function is invoked, ACPI tables have been fully loaded, we can + * walk namespace now. + */ + boot_ec = make_acpi_ec(); + if (!boot_ec) + return -ENOMEM; + status = acpi_get_devices(ec_device_ids[0].id, + ec_parse_device, boot_ec, NULL); + if (ACPI_FAILURE(status) || !boot_ec->handle) + return -ENODEV; if (!ec_install_handlers(boot_ec)) { first_ec = boot_ec; return 0; @@ -1457,11 +1488,6 @@ int __init acpi_boot_ec_enable(void) return -EFAULT; } -static const struct acpi_device_id ec_device_ids[] = { - {"PNP0C09", 0}, - {"", 0}, -}; - #if 0 /* * Some EC firmware variations refuses to respond QR_EC when SCI_EVT is not diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 9bb0773d39bf..27cc7feabfe4 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -181,7 +181,7 @@ typedef int (*acpi_ec_query_func) (void *data); int acpi_ec_init(void); int acpi_ec_ecdt_probe(void); -int acpi_boot_ec_enable(void); +int acpi_ec_dsdt_probe(void); void acpi_ec_block_transactions(void); void acpi_ec_unblock_transactions(void); void acpi_ec_unblock_transactions_early(void); diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index 2215fc847fa9..1f0e06065ae6 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -928,7 +928,7 @@ static ssize_t format_show(struct device *dev, { struct acpi_nfit_control_region *dcr = to_nfit_dcr(dev); - return sprintf(buf, "0x%04x\n", be16_to_cpu(dcr->code)); + return sprintf(buf, "0x%04x\n", le16_to_cpu(dcr->code)); } static DEVICE_ATTR_RO(format); @@ -961,8 +961,8 @@ static ssize_t format1_show(struct device *dev, continue; if (nfit_dcr->dcr->code == dcr->code) continue; - rc = sprintf(buf, "%#x\n", - be16_to_cpu(nfit_dcr->dcr->code)); + rc = sprintf(buf, "0x%04x\n", + le16_to_cpu(nfit_dcr->dcr->code)); break; } if (rc != ENXIO) @@ -1151,9 +1151,10 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, if (disable_vendor_specific) dsm_mask &= ~(1 << 8); } else { - dev_err(dev, "unknown dimm command family\n"); + dev_dbg(dev, "unknown dimm command family\n"); nfit_mem->family = -1; - return force_enable_dimms ? 0 : -ENODEV; + /* DSMs are optional, continue loading the driver... */ + return 0; } uuid = to_nfit_uuid(nfit_mem->family); diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h index 11cb38348aef..02b9ea1e8d2e 100644 --- a/drivers/acpi/nfit.h +++ b/drivers/acpi/nfit.h @@ -53,12 +53,12 @@ enum nfit_uuids { }; /* - * Region format interface codes are stored as an array of bytes in the - * NFIT DIMM Control Region structure + * Region format interface codes are stored with the interface as the + * LSB and the function as the MSB. */ -#define NFIT_FIC_BYTE cpu_to_be16(0x101) /* byte-addressable energy backed */ -#define NFIT_FIC_BLK cpu_to_be16(0x201) /* block-addressable non-energy backed */ -#define NFIT_FIC_BYTEN cpu_to_be16(0x301) /* byte-addressable non-energy backed */ +#define NFIT_FIC_BYTE cpu_to_le16(0x101) /* byte-addressable energy backed */ +#define NFIT_FIC_BLK cpu_to_le16(0x201) /* block-addressable non-energy backed */ +#define NFIT_FIC_BYTEN cpu_to_le16(0x301) /* byte-addressable non-energy backed */ enum { NFIT_BLK_READ_FLUSH = 1, diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index 8fc7323ed3e8..c983bf733ad3 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -470,6 +470,7 @@ static int acpi_irq_pci_sharing_penalty(int irq) { struct acpi_pci_link *link; int penalty = 0; + int i; list_for_each_entry(link, &acpi_link_list, list) { /* @@ -478,18 +479,14 @@ static int acpi_irq_pci_sharing_penalty(int irq) */ if (link->irq.active && link->irq.active == irq) penalty += PIRQ_PENALTY_PCI_USING; - else { - int i; - /* - * If a link is inactive, penalize the IRQs it - * might use, but not as severely. - */ - for (i = 0; i < link->irq.possible_count; i++) - if (link->irq.possible[i] == irq) - penalty += PIRQ_PENALTY_PCI_POSSIBLE / - link->irq.possible_count; - } + /* + * penalize the IRQs PCI might use, but not as severely. + */ + for (i = 0; i < link->irq.possible_count; i++) + if (link->irq.possible[i] == irq) + penalty += PIRQ_PENALTY_PCI_POSSIBLE / + link->irq.possible_count; } return penalty; @@ -499,9 +496,6 @@ static int acpi_irq_get_penalty(int irq) { int penalty = 0; - if (irq < ACPI_MAX_ISA_IRQS) - penalty += acpi_isa_irq_penalty[irq]; - /* * Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict * with PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be @@ -516,10 +510,49 @@ static int acpi_irq_get_penalty(int irq) penalty += PIRQ_PENALTY_PCI_USING; } + if (irq < ACPI_MAX_ISA_IRQS) + return penalty + acpi_isa_irq_penalty[irq]; + penalty += acpi_irq_pci_sharing_penalty(irq); return penalty; } +int __init acpi_irq_penalty_init(void) +{ + struct acpi_pci_link *link; + int i; + + /* + * Update penalties to facilitate IRQ balancing. + */ + list_for_each_entry(link, &acpi_link_list, list) { + + /* + * reflect the possible and active irqs in the penalty table -- + * useful for breaking ties. + */ + if (link->irq.possible_count) { + int penalty = + PIRQ_PENALTY_PCI_POSSIBLE / + link->irq.possible_count; + + for (i = 0; i < link->irq.possible_count; i++) { + if (link->irq.possible[i] < ACPI_MAX_ISA_IRQS) + acpi_isa_irq_penalty[link->irq. + possible[i]] += + penalty; + } + + } else if (link->irq.active && + (link->irq.active < ACPI_MAX_ISA_IRQS)) { + acpi_isa_irq_penalty[link->irq.active] += + PIRQ_PENALTY_PCI_POSSIBLE; + } + } + + return 0; +} + static int acpi_irq_balance = -1; /* 0: static, 1: balance */ static int acpi_pci_link_allocate(struct acpi_pci_link *link) @@ -839,7 +872,7 @@ void acpi_penalize_isa_irq(int irq, int active) { if ((irq >= 0) && (irq < ARRAY_SIZE(acpi_isa_irq_penalty))) acpi_isa_irq_penalty[irq] = acpi_irq_get_penalty(irq) + - active ? PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING; + (active ? PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING); } bool acpi_isa_irq_available(int irq) diff --git a/drivers/ata/ahci_seattle.c b/drivers/ata/ahci_seattle.c index 6e702ab57220..1d31c0c0fc20 100644 --- a/drivers/ata/ahci_seattle.c +++ b/drivers/ata/ahci_seattle.c @@ -137,7 +137,7 @@ static const struct ata_port_info *ahci_seattle_get_port_info( u32 val; plat_data = devm_kzalloc(dev, sizeof(*plat_data), GFP_KERNEL); - if (IS_ERR(plat_data)) + if (!plat_data) return &ahci_port_info; plat_data->sgpio_ctrl = devm_ioremap_resource(dev, diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 6be7770f68e9..31c183aed368 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4314,6 +4314,12 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { */ { "ST380013AS", "3.20", ATA_HORKAGE_MAX_SEC_1024 }, + /* + * Device times out with higher max sects. + * https://bugzilla.kernel.org/show_bug.cgi?id=121671 + */ + { "LITEON CX1-JB256-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 }, + /* Devices we expect to fail diagnostics */ /* Devices where NCQ should be avoided */ diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 61dc7a99e89a..c6f017458958 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -606,7 +606,7 @@ void ata_scsi_error(struct Scsi_Host *host) ata_scsi_port_error_handler(host, ap); /* finish or retry handled scmd's and clean up */ - WARN_ON(host->host_failed || !list_empty(&eh_work_q)); + WARN_ON(!list_empty(&eh_work_q)); DPRINTK("EXIT\n"); } diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index bd74ee555278..745489a1c86a 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -986,7 +986,7 @@ static inline void mv_write_cached_reg(void __iomem *addr, u32 *old, u32 new) * Looks like a lot of fuss, but it avoids an unnecessary * +1 usec read-after-write delay for unaffected registers. */ - laddr = (long)addr & 0xffff; + laddr = (unsigned long)addr & 0xffff; if (laddr >= 0x300 && laddr <= 0x33c) { laddr &= 0x000f; if (laddr == 0x4 || laddr == 0xc) { diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 6b2a84e7f2be..2609ba20b396 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -10,7 +10,7 @@ obj-$(CONFIG_DMA_CMA) += dma-contiguous.o obj-y += power/ obj-$(CONFIG_HAS_DMA) += dma-mapping.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o -obj-$(CONFIG_ISA) += isa.o +obj-$(CONFIG_ISA_BUS_API) += isa.o obj-$(CONFIG_FW_LOADER) += firmware_class.o obj-$(CONFIG_NUMA) += node.o obj-$(CONFIG_MEMORY_HOTPLUG_SPARSE) += memory.o diff --git a/drivers/base/isa.c b/drivers/base/isa.c index 91dba65d7264..cd6ccdcf9df0 100644 --- a/drivers/base/isa.c +++ b/drivers/base/isa.c @@ -180,4 +180,4 @@ static int __init isa_bus_init(void) return error; } -device_initcall(isa_bus_init); +postcore_initcall(isa_bus_init); diff --git a/drivers/base/module.c b/drivers/base/module.c index db930d3ee312..2a215780eda2 100644 --- a/drivers/base/module.c +++ b/drivers/base/module.c @@ -24,10 +24,12 @@ static char *make_driver_name(struct device_driver *drv) static void module_create_drivers_dir(struct module_kobject *mk) { - if (!mk || mk->drivers_dir) - return; + static DEFINE_MUTEX(drivers_dir_mutex); - mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj); + mutex_lock(&drivers_dir_mutex); + if (mk && !mk->drivers_dir) + mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj); + mutex_unlock(&drivers_dir_mutex); } void module_add_driver(struct module *mod, struct device_driver *drv) diff --git a/drivers/base/power/opp/cpu.c b/drivers/base/power/opp/cpu.c index 83d6e7ba1a34..8c3434bdb26d 100644 --- a/drivers/base/power/opp/cpu.c +++ b/drivers/base/power/opp/cpu.c @@ -211,7 +211,7 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, } /* Mark opp-table as multiple CPUs are sharing it now */ - opp_table->shared_opp = true; + opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED; } unlock: mutex_unlock(&opp_table_lock); @@ -227,7 +227,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_sharing_cpus); * * This updates the @cpumask with CPUs that are sharing OPPs with @cpu_dev. * - * Returns -ENODEV if OPP table isn't already present. + * Returns -ENODEV if OPP table isn't already present and -EINVAL if the OPP + * table's status is access-unknown. * * Locking: The internal opp_table and opp structures are RCU protected. * Hence this function internally uses RCU updater strategy with mutex locks @@ -249,9 +250,14 @@ int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask) goto unlock; } + if (opp_table->shared_opp == OPP_TABLE_ACCESS_UNKNOWN) { + ret = -EINVAL; + goto unlock; + } + cpumask_clear(cpumask); - if (opp_table->shared_opp) { + if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED) { list_for_each_entry(opp_dev, &opp_table->dev_list, node) cpumask_set_cpu(opp_dev->dev->id, cpumask); } else { diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c index 94d2010558e3..1dfd3dd92624 100644 --- a/drivers/base/power/opp/of.c +++ b/drivers/base/power/opp/of.c @@ -34,7 +34,10 @@ static struct opp_table *_managed_opp(const struct device_node *np) * But the OPPs will be considered as shared only if the * OPP table contains a "opp-shared" property. */ - return opp_table->shared_opp ? opp_table : NULL; + if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED) + return opp_table; + + return NULL; } } @@ -353,7 +356,10 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np) } opp_table->np = opp_np; - opp_table->shared_opp = of_property_read_bool(opp_np, "opp-shared"); + if (of_property_read_bool(opp_np, "opp-shared")) + opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED; + else + opp_table->shared_opp = OPP_TABLE_ACCESS_EXCLUSIVE; mutex_unlock(&opp_table_lock); diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h index 20f3be22e060..fabd5ca1a083 100644 --- a/drivers/base/power/opp/opp.h +++ b/drivers/base/power/opp/opp.h @@ -119,6 +119,12 @@ struct opp_device { #endif }; +enum opp_table_access { + OPP_TABLE_ACCESS_UNKNOWN = 0, + OPP_TABLE_ACCESS_EXCLUSIVE = 1, + OPP_TABLE_ACCESS_SHARED = 2, +}; + /** * struct opp_table - Device opp structure * @node: table node - contains the devices with OPPs that @@ -166,7 +172,7 @@ struct opp_table { /* For backward compatibility with v1 bindings */ unsigned int voltage_tolerance_v1; - bool shared_opp; + enum opp_table_access shared_opp; struct dev_pm_opp *suspend_opp; unsigned int *supported_hw; diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h index eda09090cb52..f642c4264c27 100644 --- a/drivers/bcma/bcma_private.h +++ b/drivers/bcma/bcma_private.h @@ -8,8 +8,6 @@ #include #include -#define BCMA_CORE_SIZE 0x1000 - #define bcma_err(bus, fmt, ...) \ pr_err("bus%d: " fmt, (bus)->num, ##__VA_ARGS__) #define bcma_warn(bus, fmt, ...) \ diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index d597e432e195..ab19adb07a12 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -1750,7 +1750,7 @@ aoecmd_init(void) int ret; /* get_zeroed_page returns page with ref count 1 */ - p = (void *) get_zeroed_page(GFP_KERNEL | __GFP_REPEAT); + p = (void *) get_zeroed_page(GFP_KERNEL); if (!p) return -ENOMEM; empty_page = virt_to_page(p); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 31e73a7a40f2..6a48ed41963f 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -941,7 +941,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd) debugfs_create_u64("size_bytes", 0444, dir, &nbd->bytesize); debugfs_create_u32("timeout", 0444, dir, &nbd->xmit_timeout); debugfs_create_u32("blocksize", 0444, dir, &nbd->blksize); - debugfs_create_file("flags", 0444, dir, &nbd, &nbd_dbg_flags_ops); + debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_ops); return 0; } diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index ca13df854639..fcc5b4e0aef2 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -207,6 +207,9 @@ struct blkfront_info struct blk_mq_tag_set tag_set; struct blkfront_ring_info *rinfo; unsigned int nr_rings; + /* Save uncomplete reqs and bios for migration. */ + struct list_head requests; + struct bio_list bio_list; }; static unsigned int nr_minors; @@ -874,8 +877,12 @@ static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *qd) { unsigned long flags; - struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)hctx->driver_data; + int qid = hctx->queue_num; + struct blkfront_info *info = hctx->queue->queuedata; + struct blkfront_ring_info *rinfo = NULL; + BUG_ON(info->nr_rings <= qid); + rinfo = &info->rinfo[qid]; blk_mq_start_request(qd->rq); spin_lock_irqsave(&rinfo->ring_lock, flags); if (RING_FULL(&rinfo->ring)) @@ -901,20 +908,9 @@ static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_MQ_RQ_QUEUE_BUSY; } -static int blk_mq_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, - unsigned int index) -{ - struct blkfront_info *info = (struct blkfront_info *)data; - - BUG_ON(info->nr_rings <= index); - hctx->driver_data = &info->rinfo[index]; - return 0; -} - static struct blk_mq_ops blkfront_mq_ops = { .queue_rq = blkif_queue_rq, .map_queue = blk_mq_map_queue, - .init_hctx = blk_mq_init_hctx, }; static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size, @@ -950,6 +946,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size, return PTR_ERR(rq); } + rq->queuedata = info; queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq); if (info->feature_discard) { @@ -2008,69 +2005,22 @@ static int blkif_recover(struct blkfront_info *info) { unsigned int i, r_index; struct request *req, *n; - struct blk_shadow *copy; int rc; struct bio *bio, *cloned_bio; - struct bio_list bio_list, merge_bio; unsigned int segs, offset; int pending, size; struct split_bio *split_bio; - struct list_head requests; blkfront_gather_backend_features(info); segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST; blk_queue_max_segments(info->rq, segs); - bio_list_init(&bio_list); - INIT_LIST_HEAD(&requests); for (r_index = 0; r_index < info->nr_rings; r_index++) { - struct blkfront_ring_info *rinfo; - - rinfo = &info->rinfo[r_index]; - /* Stage 1: Make a safe copy of the shadow state. */ - copy = kmemdup(rinfo->shadow, sizeof(rinfo->shadow), - GFP_NOIO | __GFP_REPEAT | __GFP_HIGH); - if (!copy) - return -ENOMEM; - - /* Stage 2: Set up free list. */ - memset(&rinfo->shadow, 0, sizeof(rinfo->shadow)); - for (i = 0; i < BLK_RING_SIZE(info); i++) - rinfo->shadow[i].req.u.rw.id = i+1; - rinfo->shadow_free = rinfo->ring.req_prod_pvt; - rinfo->shadow[BLK_RING_SIZE(info)-1].req.u.rw.id = 0x0fffffff; + struct blkfront_ring_info *rinfo = &info->rinfo[r_index]; rc = blkfront_setup_indirect(rinfo); - if (rc) { - kfree(copy); + if (rc) return rc; - } - - for (i = 0; i < BLK_RING_SIZE(info); i++) { - /* Not in use? */ - if (!copy[i].request) - continue; - - /* - * Get the bios in the request so we can re-queue them. - */ - if (copy[i].request->cmd_flags & - (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) { - /* - * Flush operations don't contain bios, so - * we need to requeue the whole request - */ - list_add(©[i].request->queuelist, &requests); - continue; - } - merge_bio.head = copy[i].request->bio; - merge_bio.tail = copy[i].request->biotail; - bio_list_merge(&bio_list, &merge_bio); - copy[i].request->bio = NULL; - blk_end_request_all(copy[i].request, 0); - } - - kfree(copy); } xenbus_switch_state(info->xbdev, XenbusStateConnected); @@ -2085,7 +2035,7 @@ static int blkif_recover(struct blkfront_info *info) kick_pending_request_queues(rinfo); } - list_for_each_entry_safe(req, n, &requests, queuelist) { + list_for_each_entry_safe(req, n, &info->requests, queuelist) { /* Requeue pending requests (flush or discard) */ list_del_init(&req->queuelist); BUG_ON(req->nr_phys_segments > segs); @@ -2093,7 +2043,7 @@ static int blkif_recover(struct blkfront_info *info) } blk_mq_kick_requeue_list(info->rq); - while ((bio = bio_list_pop(&bio_list)) != NULL) { + while ((bio = bio_list_pop(&info->bio_list)) != NULL) { /* Traverse the list of pending bios and re-queue them */ if (bio_segments(bio) > segs) { /* @@ -2139,9 +2089,42 @@ static int blkfront_resume(struct xenbus_device *dev) { struct blkfront_info *info = dev_get_drvdata(&dev->dev); int err = 0; + unsigned int i, j; dev_dbg(&dev->dev, "blkfront_resume: %s\n", dev->nodename); + bio_list_init(&info->bio_list); + INIT_LIST_HEAD(&info->requests); + for (i = 0; i < info->nr_rings; i++) { + struct blkfront_ring_info *rinfo = &info->rinfo[i]; + struct bio_list merge_bio; + struct blk_shadow *shadow = rinfo->shadow; + + for (j = 0; j < BLK_RING_SIZE(info); j++) { + /* Not in use? */ + if (!shadow[j].request) + continue; + + /* + * Get the bios in the request so we can re-queue them. + */ + if (shadow[j].request->cmd_flags & + (REQ_FLUSH | REQ_FUA | REQ_DISCARD | REQ_SECURE)) { + /* + * Flush operations don't contain bios, so + * we need to requeue the whole request + */ + list_add(&shadow[j].request->queuelist, &info->requests); + continue; + } + merge_bio.head = shadow[j].request->bio; + merge_bio.tail = shadow[j].request->biotail; + bio_list_merge(&info->bio_list, &merge_bio); + shadow[j].request->bio = NULL; + blk_mq_end_request(shadow[j].request, 0); + } + } + blkif_free(info, info->connected == BLKIF_STATE_CONNECTED); err = negotiate_mq(info); @@ -2149,6 +2132,8 @@ static int blkfront_resume(struct xenbus_device *dev) return err; err = talk_to_blkback(dev, info); + if (!err) + blk_mq_update_nr_hw_queues(&info->tag_set, info->nr_rings); /* * We have to wait for the backend to switch to @@ -2485,10 +2470,23 @@ static void blkback_changed(struct xenbus_device *dev, break; case XenbusStateConnected: - if (dev->state != XenbusStateInitialised) { + /* + * talk_to_blkback sets state to XenbusStateInitialised + * and blkfront_connect sets it to XenbusStateConnected + * (if connection went OK). + * + * If the backend (or toolstack) decides to poke at backend + * state (and re-trigger the watch by setting the state repeatedly + * to XenbusStateConnected (4)) we need to deal with this. + * This is allowed as this is used to communicate to the guest + * that the size of disk has changed! + */ + if ((dev->state != XenbusStateInitialised) && + (dev->state != XenbusStateConnected)) { if (talk_to_blkback(dev, info)) break; } + blkfront_connect(info); break; diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 94fb407d8561..44b1bd6baa38 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -3820,6 +3820,7 @@ static void handle_new_recv_msgs(ipmi_smi_t intf) while (!list_empty(&intf->waiting_rcv_msgs)) { smi_msg = list_entry(intf->waiting_rcv_msgs.next, struct ipmi_smi_msg, link); + list_del(&smi_msg->link); if (!run_to_completion) spin_unlock_irqrestore(&intf->waiting_rcv_msgs_lock, flags); @@ -3829,11 +3830,14 @@ static void handle_new_recv_msgs(ipmi_smi_t intf) if (rv > 0) { /* * To preserve message order, quit if we - * can't handle a message. + * can't handle a message. Add the message + * back at the head, this is safe because this + * tasklet is the only thing that pulls the + * messages. */ + list_add(&smi_msg->link, &intf->waiting_rcv_msgs); break; } else { - list_del(&smi_msg->link); if (rv == 0) /* Message handled */ ipmi_free_smi_msg(smi_msg); diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index 53ddba26578c..98efbfcdb503 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -175,6 +175,7 @@ config COMMON_CLK_KEYSTONE config COMMON_CLK_NXP def_bool COMMON_CLK && (ARCH_LPC18XX || ARCH_LPC32XX) select REGMAP_MMIO if ARCH_LPC32XX + select MFD_SYSCON if ARCH_LPC18XX ---help--- Support for clock providers on NXP platforms. diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c index 10f846cc8db1..25d5906640c3 100644 --- a/drivers/clk/at91/clk-programmable.c +++ b/drivers/clk/at91/clk-programmable.c @@ -99,7 +99,7 @@ static int clk_programmable_set_parent(struct clk_hw *hw, u8 index) struct clk_programmable *prog = to_clk_programmable(hw); const struct clk_programmable_layout *layout = prog->layout; unsigned int mask = layout->css_mask; - unsigned int pckr = 0; + unsigned int pckr = index; if (layout->have_slck_mck) mask |= AT91_PMC_CSSMCK_MCK; diff --git a/drivers/clk/clk-oxnas.c b/drivers/clk/clk-oxnas.c index efba7d4dbcfc..79bcb2e42060 100644 --- a/drivers/clk/clk-oxnas.c +++ b/drivers/clk/clk-oxnas.c @@ -144,9 +144,9 @@ static int oxnas_stdclk_probe(struct platform_device *pdev) return -ENOMEM; regmap = syscon_node_to_regmap(of_get_parent(np)); - if (!regmap) { + if (IS_ERR(regmap)) { dev_err(&pdev->dev, "failed to have parent regmap\n"); - return -EINVAL; + return PTR_ERR(regmap); } for (i = 0; i < ARRAY_SIZE(clk_oxnas_init); i++) { diff --git a/drivers/clk/microchip/clk-pic32mzda.c b/drivers/clk/microchip/clk-pic32mzda.c index 020a29acc5b0..51f54380474b 100644 --- a/drivers/clk/microchip/clk-pic32mzda.c +++ b/drivers/clk/microchip/clk-pic32mzda.c @@ -180,15 +180,15 @@ static int pic32mzda_clk_probe(struct platform_device *pdev) /* register fixed rate clocks */ clks[POSCCLK] = clk_register_fixed_rate(&pdev->dev, "posc_clk", NULL, - CLK_IS_ROOT, 24000000); + 0, 24000000); clks[FRCCLK] = clk_register_fixed_rate(&pdev->dev, "frc_clk", NULL, - CLK_IS_ROOT, 8000000); + 0, 8000000); clks[BFRCCLK] = clk_register_fixed_rate(&pdev->dev, "bfrc_clk", NULL, - CLK_IS_ROOT, 8000000); + 0, 8000000); clks[LPRCCLK] = clk_register_fixed_rate(&pdev->dev, "lprc_clk", NULL, - CLK_IS_ROOT, 32000); + 0, 32000); clks[UPLLCLK] = clk_register_fixed_rate(&pdev->dev, "usbphy_clk", NULL, - CLK_IS_ROOT, 24000000); + 0, 24000000); /* fixed rate (optional) clock */ if (of_find_property(np, "microchip,pic32mzda-sosc", NULL)) { pr_info("pic32-clk: dt requests SOSC.\n"); diff --git a/drivers/clk/rockchip/clk-cpu.c b/drivers/clk/rockchip/clk-cpu.c index 4bb130cd0062..05b3d73bfefa 100644 --- a/drivers/clk/rockchip/clk-cpu.c +++ b/drivers/clk/rockchip/clk-cpu.c @@ -321,9 +321,9 @@ struct clk *rockchip_clk_register_cpuclk(const char *name, } cclk = clk_register(NULL, &cpuclk->hw); - if (IS_ERR(clk)) { + if (IS_ERR(cclk)) { pr_err("%s: could not register cpuclk %s\n", __func__, name); - ret = PTR_ERR(clk); + ret = PTR_ERR(cclk); goto free_rate_table; } diff --git a/drivers/clk/rockchip/clk-mmc-phase.c b/drivers/clk/rockchip/clk-mmc-phase.c index bc856f21f6b2..077fcdc7908b 100644 --- a/drivers/clk/rockchip/clk-mmc-phase.c +++ b/drivers/clk/rockchip/clk-mmc-phase.c @@ -41,8 +41,6 @@ static unsigned long rockchip_mmc_recalc(struct clk_hw *hw, #define ROCKCHIP_MMC_DEGREE_MASK 0x3 #define ROCKCHIP_MMC_DELAYNUM_OFFSET 2 #define ROCKCHIP_MMC_DELAYNUM_MASK (0xff << ROCKCHIP_MMC_DELAYNUM_OFFSET) -#define ROCKCHIP_MMC_INIT_STATE_RESET 0x1 -#define ROCKCHIP_MMC_INIT_STATE_SHIFT 1 #define PSECS_PER_SEC 1000000000000LL @@ -154,6 +152,7 @@ struct clk *rockchip_clk_register_mmc(const char *name, return ERR_PTR(-ENOMEM); init.name = name; + init.flags = 0; init.num_parents = num_parents; init.parent_names = parent_names; init.ops = &rockchip_mmc_clk_ops; @@ -162,15 +161,6 @@ struct clk *rockchip_clk_register_mmc(const char *name, mmc_clock->reg = reg; mmc_clock->shift = shift; - /* - * Assert init_state to soft reset the CLKGEN - * for mmc tuning phase and degree - */ - if (mmc_clock->shift == ROCKCHIP_MMC_INIT_STATE_SHIFT) - writel(HIWORD_UPDATE(ROCKCHIP_MMC_INIT_STATE_RESET, - ROCKCHIP_MMC_INIT_STATE_RESET, - mmc_clock->shift), mmc_clock->reg); - clk = clk_register(NULL, &mmc_clock->hw); if (IS_ERR(clk)) kfree(mmc_clock); diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c index 291543f52caa..8059a8d3ea36 100644 --- a/drivers/clk/rockchip/clk-rk3399.c +++ b/drivers/clk/rockchip/clk-rk3399.c @@ -832,9 +832,9 @@ static struct rockchip_clk_branch rk3399_clk_branches[] __initdata = { RK3399_CLKGATE_CON(13), 1, GFLAGS), /* perihp */ - GATE(0, "cpll_aclk_perihp_src", "gpll", CLK_IGNORE_UNUSED, + GATE(0, "cpll_aclk_perihp_src", "cpll", CLK_IGNORE_UNUSED, RK3399_CLKGATE_CON(5), 0, GFLAGS), - GATE(0, "gpll_aclk_perihp_src", "cpll", CLK_IGNORE_UNUSED, + GATE(0, "gpll_aclk_perihp_src", "gpll", CLK_IGNORE_UNUSED, RK3399_CLKGATE_CON(5), 1, GFLAGS), COMPOSITE(ACLK_PERIHP, "aclk_perihp", mux_aclk_perihp_p, CLK_IGNORE_UNUSED, RK3399_CLKSEL_CON(14), 7, 1, MFLAGS, 0, 5, DFLAGS, @@ -1466,6 +1466,8 @@ static struct rockchip_clk_branch rk3399_clk_pmu_branches[] __initdata = { static const char *const rk3399_cru_critical_clocks[] __initconst = { "aclk_cci_pre", + "aclk_gic", + "aclk_gic_noc", "pclk_perilp0", "pclk_perilp0", "hclk_perilp0", @@ -1508,6 +1510,7 @@ static void __init rk3399_clk_init(struct device_node *np) ctx = rockchip_clk_init(np, reg_base, CLK_NR_CLKS); if (IS_ERR(ctx)) { pr_err("%s: rockchip clk init failed\n", __func__); + iounmap(reg_base); return; } @@ -1553,6 +1556,7 @@ static void __init rk3399_pmu_clk_init(struct device_node *np) ctx = rockchip_clk_init(np, reg_base, CLKPMU_NR_CLKS); if (IS_ERR(ctx)) { pr_err("%s: rockchip pmu clk init failed\n", __func__); + iounmap(reg_base); return; } diff --git a/drivers/clk/sunxi/clk-sun4i-display.c b/drivers/clk/sunxi/clk-sun4i-display.c index 445a7498d6df..9780fac6d029 100644 --- a/drivers/clk/sunxi/clk-sun4i-display.c +++ b/drivers/clk/sunxi/clk-sun4i-display.c @@ -33,6 +33,8 @@ struct sun4i_a10_display_clk_data { u8 width_div; u8 width_mux; + + u32 flags; }; struct reset_data { @@ -166,7 +168,7 @@ static void __init sun4i_a10_display_init(struct device_node *node, data->has_div ? &div->hw : NULL, data->has_div ? &clk_divider_ops : NULL, &gate->hw, &clk_gate_ops, - 0); + data->flags); if (IS_ERR(clk)) { pr_err("%s: Couldn't register the clock\n", clk_name); goto free_div; @@ -232,6 +234,7 @@ static const struct sun4i_a10_display_clk_data sun4i_a10_tcon_ch0_data __initcon .offset_rst = 29, .offset_mux = 24, .width_mux = 2, + .flags = CLK_SET_RATE_PARENT, }; static void __init sun4i_a10_tcon_ch0_setup(struct device_node *node) diff --git a/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c b/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c index 98a4582de56a..b6d29d1bedca 100644 --- a/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c +++ b/drivers/clk/sunxi/clk-sun4i-tcon-ch1.c @@ -79,15 +79,11 @@ static int tcon_ch1_is_enabled(struct clk_hw *hw) static u8 tcon_ch1_get_parent(struct clk_hw *hw) { struct tcon_ch1_clk *tclk = hw_to_tclk(hw); - int num_parents = clk_hw_get_num_parents(hw); u32 reg; reg = readl(tclk->reg) >> TCON_CH1_SCLK2_MUX_SHIFT; reg &= reg >> TCON_CH1_SCLK2_MUX_MASK; - if (reg >= num_parents) - return -EINVAL; - return reg; } diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index 15d06fcf0b50..b02f9c606e0b 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -56,11 +56,21 @@ static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC }; /* proc_event_counts is used as the sequence number of the netlink message */ static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 }; -static inline void get_seq(__u32 *ts, int *cpu) +static inline void send_msg(struct cn_msg *msg) { preempt_disable(); - *ts = __this_cpu_inc_return(proc_event_counts) - 1; - *cpu = smp_processor_id(); + + msg->seq = __this_cpu_inc_return(proc_event_counts) - 1; + ((struct proc_event *)msg->data)->cpu = smp_processor_id(); + + /* + * Preemption remains disabled during send to ensure the messages are + * ordered according to their sequence numbers. + * + * If cn_netlink_send() fails, the data is not sent. + */ + cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT); + preempt_enable(); } @@ -77,7 +87,6 @@ void proc_fork_connector(struct task_struct *task) msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_FORK; rcu_read_lock(); @@ -92,8 +101,7 @@ void proc_fork_connector(struct task_struct *task) msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - /* If cn_netlink_send() failed, the data is not sent */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } void proc_exec_connector(struct task_struct *task) @@ -108,7 +116,6 @@ void proc_exec_connector(struct task_struct *task) msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_EXEC; ev->event_data.exec.process_pid = task->pid; @@ -118,7 +125,7 @@ void proc_exec_connector(struct task_struct *task) msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } void proc_id_connector(struct task_struct *task, int which_id) @@ -150,14 +157,13 @@ void proc_id_connector(struct task_struct *task, int which_id) return; } rcu_read_unlock(); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } void proc_sid_connector(struct task_struct *task) @@ -172,7 +178,6 @@ void proc_sid_connector(struct task_struct *task) msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_SID; ev->event_data.sid.process_pid = task->pid; @@ -182,7 +187,7 @@ void proc_sid_connector(struct task_struct *task) msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } void proc_ptrace_connector(struct task_struct *task, int ptrace_id) @@ -197,7 +202,6 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id) msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_PTRACE; ev->event_data.ptrace.process_pid = task->pid; @@ -215,7 +219,7 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id) msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } void proc_comm_connector(struct task_struct *task) @@ -230,7 +234,6 @@ void proc_comm_connector(struct task_struct *task) msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_COMM; ev->event_data.comm.process_pid = task->pid; @@ -241,7 +244,7 @@ void proc_comm_connector(struct task_struct *task) msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } void proc_coredump_connector(struct task_struct *task) @@ -256,7 +259,6 @@ void proc_coredump_connector(struct task_struct *task) msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_COREDUMP; ev->event_data.coredump.process_pid = task->pid; @@ -266,7 +268,7 @@ void proc_coredump_connector(struct task_struct *task) msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } void proc_exit_connector(struct task_struct *task) @@ -281,7 +283,6 @@ void proc_exit_connector(struct task_struct *task) msg = buffer_to_cn_msg(buffer); ev = (struct proc_event *)msg->data; memset(&ev->event_data, 0, sizeof(ev->event_data)); - get_seq(&msg->seq, &ev->cpu); ev->timestamp_ns = ktime_get_ns(); ev->what = PROC_EVENT_EXIT; ev->event_data.exit.process_pid = task->pid; @@ -293,7 +294,7 @@ void proc_exit_connector(struct task_struct *task) msg->ack = 0; /* not used */ msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } /* @@ -325,7 +326,7 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack) msg->ack = rcvd_ack + 1; msg->len = sizeof(*ev); msg->flags = 0; /* not used */ - cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL); + send_msg(msg); } /** diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 3646b143bbf5..0bb44d5b5df4 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -79,15 +79,16 @@ static const struct of_device_id machines[] __initconst = { static int __init cpufreq_dt_platdev_init(void) { struct device_node *np = of_find_node_by_path("/"); + const struct of_device_id *match; if (!np) return -ENODEV; - if (!of_match_node(machines, np)) + match = of_match_node(machines, np); + of_node_put(np); + if (!match) return -ENODEV; - of_node_put(of_root); - return PTR_ERR_OR_ZERO(platform_device_register_simple("cpufreq-dt", -1, NULL, 0)); } diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 9009295f5134..5617c7087d77 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2261,6 +2261,10 @@ int cpufreq_update_policy(unsigned int cpu) * -> ask driver for current freq and notify governors about a change */ if (cpufreq_driver->get && !cpufreq_driver->setpolicy) { + if (cpufreq_suspended) { + ret = -EAGAIN; + goto unlock; + } new_policy.cur = cpufreq_update_current_freq(policy); if (WARN_ON(!new_policy.cur)) { ret = -EIO; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 0d159b513469..1fa1a32928d7 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -372,26 +372,9 @@ static bool intel_pstate_get_ppc_enable_status(void) return acpi_ppc; } -/* - * The max target pstate ratio is a 8 bit value in both PLATFORM_INFO MSR and - * in TURBO_RATIO_LIMIT MSR, which pstate driver stores in max_pstate and - * max_turbo_pstate fields. The PERF_CTL MSR contains 16 bit value for P state - * ratio, out of it only high 8 bits are used. For example 0x1700 is setting - * target ratio 0x17. The _PSS control value stores in a format which can be - * directly written to PERF_CTL MSR. But in intel_pstate driver this shift - * occurs during write to PERF_CTL (E.g. for cores core_set_pstate()). - * This function converts the _PSS control value to intel pstate driver format - * for comparison and assignment. - */ -static int convert_to_native_pstate_format(struct cpudata *cpu, int index) -{ - return cpu->acpi_perf_data.states[index].control >> 8; -} - static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) { struct cpudata *cpu; - int turbo_pss_ctl; int ret; int i; @@ -441,11 +424,10 @@ static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy) * max frequency, which will cause a reduced performance as * this driver uses real max turbo frequency as the max * frequency. So correct this frequency in _PSS table to - * correct max turbo frequency based on the turbo ratio. + * correct max turbo frequency based on the turbo state. * Also need to convert to MHz as _PSS freq is in MHz. */ - turbo_pss_ctl = convert_to_native_pstate_format(cpu, 0); - if (turbo_pss_ctl > cpu->pstate.max_pstate) + if (!limits->turbo_disabled) cpu->acpi_perf_data.states[0].core_frequency = policy->cpuinfo.max_freq / 1000; cpu->valid_pss_table = true; @@ -1418,6 +1400,9 @@ static void intel_pstate_set_update_util_hook(unsigned int cpu_num) { struct cpudata *cpu = all_cpu_data[cpu_num]; + if (cpu->update_util_set) + return; + /* Prevent intel_pstate_update_util() from using stale data. */ cpu->sample.time = 0; cpufreq_add_update_util_hook(cpu_num, &cpu->update_util, @@ -1458,7 +1443,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) if (!policy->cpuinfo.max_freq) return -ENODEV; - intel_pstate_clear_update_util_hook(policy->cpu); + pr_debug("set_policy cpuinfo.max %u policy->max %u\n", + policy->cpuinfo.max_freq, policy->max); cpu = all_cpu_data[0]; if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate && @@ -1495,13 +1481,13 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) limits->max_sysfs_pct); limits->max_perf_pct = max(limits->min_policy_pct, limits->max_perf_pct); - limits->max_perf = round_up(limits->max_perf, FRAC_BITS); /* Make sure min_perf_pct <= max_perf_pct */ limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct); limits->min_perf = div_fp(limits->min_perf_pct, 100); limits->max_perf = div_fp(limits->max_perf_pct, 100); + limits->max_perf = round_up(limits->max_perf, FRAC_BITS); out: intel_pstate_set_update_util_hook(policy->cpu); @@ -1558,8 +1544,11 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy) /* cpuinfo and default policy values */ policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling; - policy->cpuinfo.max_freq = - cpu->pstate.turbo_pstate * cpu->pstate.scaling; + update_turbo_state(); + policy->cpuinfo.max_freq = limits->turbo_disabled ? + cpu->pstate.max_pstate : cpu->pstate.turbo_pstate; + policy->cpuinfo.max_freq *= cpu->pstate.scaling; + intel_pstate_init_acpi_perf_limits(policy); policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL; cpumask_set_cpu(policy->cpu, policy->cpus); diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c index 808a320e9d5d..a7ecb9a84c15 100644 --- a/drivers/cpufreq/pcc-cpufreq.c +++ b/drivers/cpufreq/pcc-cpufreq.c @@ -487,7 +487,7 @@ static int __init pcc_cpufreq_probe(void) doorbell.space_id = reg_resource->space_id; doorbell.bit_width = reg_resource->bit_width; doorbell.bit_offset = reg_resource->bit_offset; - doorbell.access_width = 64; + doorbell.access_width = 4; doorbell.address = reg_resource->address; pr_debug("probe: doorbell: space_id is %d, bit_width is %d, " diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index a4d0059e232c..c73207abb5a4 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -173,7 +173,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, struct cpuidle_state *target_state = &drv->states[index]; bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP); - u64 time_start, time_end; + ktime_t time_start, time_end; s64 diff; /* @@ -195,13 +195,13 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, sched_idle_set_state(target_state); trace_cpu_idle_rcuidle(index, dev->cpu); - time_start = local_clock(); + time_start = ns_to_ktime(local_clock()); stop_critical_timings(); entered_state = target_state->enter(dev, drv, index); start_critical_timings(); - time_end = local_clock(); + time_end = ns_to_ktime(local_clock()); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); /* The cpu is no longer idle or about to enter idle. */ @@ -217,11 +217,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, if (!cpuidle_state_is_coupled(drv, index)) local_irq_enable(); - /* - * local_clock() returns the time in nanosecond, let's shift - * by 10 (divide by 1024) to have microsecond based time. - */ - diff = (time_end - time_start) >> 10; + diff = ktime_us_delta(time_end, time_start); if (diff > INT_MAX) diff = INT_MAX; diff --git a/drivers/crypto/qat/qat_common/Makefile b/drivers/crypto/qat/qat_common/Makefile index 6d74b91f2152..5fc3dbb9ada0 100644 --- a/drivers/crypto/qat/qat_common/Makefile +++ b/drivers/crypto/qat/qat_common/Makefile @@ -2,6 +2,7 @@ $(obj)/qat_rsapubkey-asn1.o: $(obj)/qat_rsapubkey-asn1.c \ $(obj)/qat_rsapubkey-asn1.h $(obj)/qat_rsaprivkey-asn1.o: $(obj)/qat_rsaprivkey-asn1.c \ $(obj)/qat_rsaprivkey-asn1.h +$(obj)/qat_asym_algs.o: $(obj)/qat_rsapubkey-asn1.h $(obj)/qat_rsaprivkey-asn1.h clean-files += qat_rsapubkey-asn1.c qat_rsapubkey-asn1.h clean-files += qat_rsaprivkey-asn1.c qat_rsaprivkey-asn1.h diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c index 574e87c7f2b8..9acccad26928 100644 --- a/drivers/crypto/ux500/hash/hash_core.c +++ b/drivers/crypto/ux500/hash/hash_core.c @@ -781,7 +781,7 @@ static int hash_process_data(struct hash_device_data *device_data, &device_data->state); memmove(req_ctx->state.buffer, device_data->state.buffer, - HASH_BLOCK_SIZE / sizeof(u32)); + HASH_BLOCK_SIZE); if (ret) { dev_err(device_data->dev, "%s: hash_resume_state() failed!\n", @@ -832,7 +832,7 @@ static int hash_process_data(struct hash_device_data *device_data, memmove(device_data->state.buffer, req_ctx->state.buffer, - HASH_BLOCK_SIZE / sizeof(u32)); + HASH_BLOCK_SIZE); if (ret) { dev_err(device_data->dev, "%s: hash_save_state() failed!\n", __func__); diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c index 495577b6d31b..94ad5c0adbcb 100644 --- a/drivers/crypto/vmx/aes_cbc.c +++ b/drivers/crypto/vmx/aes_cbc.c @@ -182,7 +182,7 @@ struct crypto_alg p8_aes_cbc_alg = { .cra_name = "cbc(aes)", .cra_driver_name = "p8_aes_cbc", .cra_module = THIS_MODULE, - .cra_priority = 1000, + .cra_priority = 2000, .cra_type = &crypto_blkcipher_type, .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK, .cra_alignmask = 0, diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c index 0a3c1b04cf3c..38ed10d761d0 100644 --- a/drivers/crypto/vmx/aes_ctr.c +++ b/drivers/crypto/vmx/aes_ctr.c @@ -166,7 +166,7 @@ struct crypto_alg p8_aes_ctr_alg = { .cra_name = "ctr(aes)", .cra_driver_name = "p8_aes_ctr", .cra_module = THIS_MODULE, - .cra_priority = 1000, + .cra_priority = 2000, .cra_type = &crypto_blkcipher_type, .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK, .cra_alignmask = 0, diff --git a/drivers/crypto/vmx/ppc-xlate.pl b/drivers/crypto/vmx/ppc-xlate.pl index 9f4994cabcc7..b18e67d0e065 100644 --- a/drivers/crypto/vmx/ppc-xlate.pl +++ b/drivers/crypto/vmx/ppc-xlate.pl @@ -141,7 +141,7 @@ my $vmr = sub { # Some ABIs specify vrsave, special-purpose register #256, as reserved # for system use. -my $no_vrsave = ($flavour =~ /aix|linux64le/); +my $no_vrsave = ($flavour =~ /linux-ppc64le/); my $mtspr = sub { my ($f,$idx,$ra) = @_; if ($idx == 256 && $no_vrsave) { diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 1d6c803804d5..e92418facc92 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -268,8 +268,11 @@ int update_devfreq(struct devfreq *devfreq) devfreq_notify_transition(devfreq, &freqs, DEVFREQ_PRECHANGE); err = devfreq->profile->target(devfreq->dev.parent, &freq, flags); - if (err) + if (err) { + freqs.new = cur_freq; + devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE); return err; + } freqs.new = freq; devfreq_notify_transition(devfreq, &freqs, DEVFREQ_POSTCHANGE); @@ -552,6 +555,7 @@ struct devfreq *devfreq_add_device(struct device *dev, devfreq->profile = profile; strncpy(devfreq->governor_name, governor_name, DEVFREQ_NAME_LEN); devfreq->previous_freq = profile->initial_freq; + devfreq->last_status.current_frequency = profile->initial_freq; devfreq->data = data; devfreq->nb.notifier_call = devfreq_notifier_call; @@ -561,23 +565,22 @@ struct devfreq *devfreq_add_device(struct device *dev, mutex_lock(&devfreq->lock); } - devfreq->trans_table = devm_kzalloc(dev, sizeof(unsigned int) * - devfreq->profile->max_state * - devfreq->profile->max_state, - GFP_KERNEL); - devfreq->time_in_state = devm_kzalloc(dev, sizeof(unsigned long) * - devfreq->profile->max_state, - GFP_KERNEL); - devfreq->last_stat_updated = jiffies; - dev_set_name(&devfreq->dev, "%s", dev_name(dev)); err = device_register(&devfreq->dev); if (err) { - put_device(&devfreq->dev); mutex_unlock(&devfreq->lock); goto err_out; } + devfreq->trans_table = devm_kzalloc(&devfreq->dev, sizeof(unsigned int) * + devfreq->profile->max_state * + devfreq->profile->max_state, + GFP_KERNEL); + devfreq->time_in_state = devm_kzalloc(&devfreq->dev, sizeof(unsigned long) * + devfreq->profile->max_state, + GFP_KERNEL); + devfreq->last_stat_updated = jiffies; + srcu_init_notifier_head(&devfreq->transition_notifier_list); mutex_unlock(&devfreq->lock); @@ -603,7 +606,6 @@ struct devfreq *devfreq_add_device(struct device *dev, err_init: list_del(&devfreq->node); device_unregister(&devfreq->dev); - kfree(devfreq); err_out: return ERR_PTR(err); } @@ -621,7 +623,6 @@ int devfreq_remove_device(struct devfreq *devfreq) return -EINVAL; device_unregister(&devfreq->dev); - put_device(&devfreq->dev); return 0; } diff --git a/drivers/devfreq/event/exynos-nocp.c b/drivers/devfreq/event/exynos-nocp.c index 6b6a5f310486..a5841403bde8 100644 --- a/drivers/devfreq/event/exynos-nocp.c +++ b/drivers/devfreq/event/exynos-nocp.c @@ -220,9 +220,6 @@ static int exynos_nocp_parse_dt(struct platform_device *pdev, /* Maps the memory mapped IO to control nocp register */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (IS_ERR(res)) - return PTR_ERR(res); - base = devm_ioremap_resource(dev, res); if (IS_ERR(base)) return PTR_ERR(base); diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig index 9824bc4addf8..25bcfa0b474f 100644 --- a/drivers/dma-buf/Kconfig +++ b/drivers/dma-buf/Kconfig @@ -1,11 +1,20 @@ menu "DMABUF options" config SYNC_FILE - bool "sync_file support for fences" + bool "Explicit Synchronization Framework" default n select ANON_INODES select DMA_SHARED_BUFFER ---help--- - This option enables the fence framework synchronization to export - sync_files to userspace that can represent one or more fences. + The Sync File Framework adds explicit syncronization via + userspace. It enables send/receive 'struct fence' objects to/from + userspace via Sync File fds for synchronization between drivers via + userspace components. It has been ported from Android. + + The first and main user for this is graphics in which a fence is + associated with a buffer. When a job is submitted to the GPU a fence + is attached to the buffer and is transferred via userspace, using Sync + Files fds, to the DRM driver for example. More details at + Documentation/sync_file.txt. + endmenu diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 20ce0687b111..ddaee60ae52a 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -334,6 +334,7 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) struct reservation_object *resv = exp_info->resv; struct file *file; size_t alloc_size = sizeof(struct dma_buf); + int ret; if (!exp_info->resv) alloc_size += sizeof(struct reservation_object); @@ -357,8 +358,8 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) dmabuf = kzalloc(alloc_size, GFP_KERNEL); if (!dmabuf) { - module_put(exp_info->owner); - return ERR_PTR(-ENOMEM); + ret = -ENOMEM; + goto err_module; } dmabuf->priv = exp_info->priv; @@ -379,8 +380,8 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) file = anon_inode_getfile("dmabuf", &dma_buf_fops, dmabuf, exp_info->flags); if (IS_ERR(file)) { - kfree(dmabuf); - return ERR_CAST(file); + ret = PTR_ERR(file); + goto err_dmabuf; } file->f_mode |= FMODE_LSEEK; @@ -394,6 +395,12 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) mutex_unlock(&db_list.lock); return dmabuf; + +err_dmabuf: + kfree(dmabuf); +err_module: + module_put(exp_info->owner); + return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(dma_buf_export); diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 8e304b1befc5..75bd6621dc5d 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -242,7 +242,7 @@ struct at_xdmac_lld { u32 mbr_dus; /* Destination Microblock Stride Register */ }; - +/* 64-bit alignment needed to update CNDA and CUBC registers in an atomic way. */ struct at_xdmac_desc { struct at_xdmac_lld lld; enum dma_transfer_direction direction; @@ -253,7 +253,7 @@ struct at_xdmac_desc { unsigned int xfer_size; struct list_head descs_list; struct list_head xfer_node; -}; +} __aligned(sizeof(u64)); static inline void __iomem *at_xdmac_chan_reg_base(struct at_xdmac *atxdmac, unsigned int chan_nb) { @@ -1400,6 +1400,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, u32 cur_nda, check_nda, cur_ubc, mask, value; u8 dwidth = 0; unsigned long flags; + bool initd; ret = dma_cookie_status(chan, cookie, txstate); if (ret == DMA_COMPLETE) @@ -1424,7 +1425,16 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, residue = desc->xfer_size; /* * Flush FIFO: only relevant when the transfer is source peripheral - * synchronized. + * synchronized. Flush is needed before reading CUBC because data in + * the FIFO are not reported by CUBC. Reporting a residue of the + * transfer length while we have data in FIFO can cause issue. + * Usecase: atmel USART has a timeout which means I have received + * characters but there is no more character received for a while. On + * timeout, it requests the residue. If the data are in the DMA FIFO, + * we will return a residue of the transfer length. It means no data + * received. If an application is waiting for these data, it will hang + * since we won't have another USART timeout without receiving new + * data. */ mask = AT_XDMAC_CC_TYPE | AT_XDMAC_CC_DSYNC; value = AT_XDMAC_CC_TYPE_PER_TRAN | AT_XDMAC_CC_DSYNC_PER2MEM; @@ -1435,34 +1445,43 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, } /* - * When processing the residue, we need to read two registers but we - * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where - * we stand in the descriptor list and AT_XDMAC_CUBC is used - * to know how many data are remaining for the current descriptor. - * Since the dma channel is not paused to not loose data, between the - * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of - * descriptor. - * For that reason, after reading AT_XDMAC_CUBC, we check if we are - * still using the same descriptor by reading a second time - * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to - * read again AT_XDMAC_CUBC. + * The easiest way to compute the residue should be to pause the DMA + * but doing this can lead to miss some data as some devices don't + * have FIFO. + * We need to read several registers because: + * - DMA is running therefore a descriptor change is possible while + * reading these registers + * - When the block transfer is done, the value of the CUBC register + * is set to its initial value until the fetch of the next descriptor. + * This value will corrupt the residue calculation so we have to skip + * it. + * + * INITD -------- ------------ + * |____________________| + * _______________________ _______________ + * NDA @desc2 \/ @desc3 + * _______________________/\_______________ + * __________ ___________ _______________ + * CUBC 0 \/ MAX desc1 \/ MAX desc2 + * __________/\___________/\_______________ + * + * Since descriptors are aligned on 64 bits, we can assume that + * the update of NDA and CUBC is atomic. * Memory barriers are used to ensure the read order of the registers. - * A max number of retries is set because unlikely it can never ends if - * we are transferring a lot of data with small buffers. + * A max number of retries is set because unlikely it could never ends. */ - cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; - rmb(); - cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC); for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) { - rmb(); check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; - - if (likely(cur_nda == check_nda)) - break; - - cur_nda = check_nda; + rmb(); + initd = !!(at_xdmac_chan_read(atchan, AT_XDMAC_CC) & AT_XDMAC_CC_INITD); rmb(); cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC); + rmb(); + cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; + rmb(); + + if ((check_nda == cur_nda) && initd) + break; } if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) { @@ -1470,6 +1489,19 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, goto spin_unlock; } + /* + * Flush FIFO: only relevant when the transfer is source peripheral + * synchronized. Another flush is needed here because CUBC is updated + * when the controller sends the data write command. It can lead to + * report data that are not written in the memory or the device. The + * FIFO flush ensures that data are really written. + */ + if ((desc->lld.mbr_cfg & mask) == value) { + at_xdmac_write(atxdmac, AT_XDMAC_GSWF, atchan->mask); + while (!(at_xdmac_chan_read(atchan, AT_XDMAC_CIS) & AT_XDMAC_CIS_FIS)) + cpu_relax(); + } + /* * Remove size of all microblocks already transferred and the current * one. Then add the remaining size to transfer of the current diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index 25d1dadcddd1..d0446a75990a 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -703,8 +703,9 @@ static int mv_chan_memcpy_self_test(struct mv_xor_chan *mv_chan) goto free_resources; } - src_dma = dma_map_page(dma_chan->device->dev, virt_to_page(src), 0, - PAGE_SIZE, DMA_TO_DEVICE); + src_dma = dma_map_page(dma_chan->device->dev, virt_to_page(src), + (size_t)src & ~PAGE_MASK, PAGE_SIZE, + DMA_TO_DEVICE); unmap->addr[0] = src_dma; ret = dma_mapping_error(dma_chan->device->dev, src_dma); @@ -714,8 +715,9 @@ static int mv_chan_memcpy_self_test(struct mv_xor_chan *mv_chan) } unmap->to_cnt = 1; - dest_dma = dma_map_page(dma_chan->device->dev, virt_to_page(dest), 0, - PAGE_SIZE, DMA_FROM_DEVICE); + dest_dma = dma_map_page(dma_chan->device->dev, virt_to_page(dest), + (size_t)dest & ~PAGE_MASK, PAGE_SIZE, + DMA_FROM_DEVICE); unmap->addr[1] = dest_dma; ret = dma_mapping_error(dma_chan->device->dev, dest_dma); diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 6aa256b0a1ed..c3ee3ad98a63 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -565,7 +565,8 @@ void edac_mc_reset_delay_period(unsigned long value) list_for_each(item, &mc_devices) { mci = list_entry(item, struct mem_ctl_info, link); - edac_mod_work(&mci->work, value); + if (mci->op_state == OP_RUNNING_POLL) + edac_mod_work(&mci->work, value); } mutex_unlock(&mem_ctls_mutex); } diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index b4d0bf6534cf..4fb2eb7c800d 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -239,8 +239,11 @@ static const u32 rir_offset[MAX_RIR_RANGES][MAX_RIR_WAY] = { { 0x1a0, 0x1a4, 0x1a8, 0x1ac, 0x1b0, 0x1b4, 0x1b8, 0x1bc }, }; -#define RIR_RNK_TGT(reg) GET_BITFIELD(reg, 16, 19) -#define RIR_OFFSET(reg) GET_BITFIELD(reg, 2, 14) +#define RIR_RNK_TGT(type, reg) (((type) == BROADWELL) ? \ + GET_BITFIELD(reg, 20, 23) : GET_BITFIELD(reg, 16, 19)) + +#define RIR_OFFSET(type, reg) (((type) == HASWELL || (type) == BROADWELL) ? \ + GET_BITFIELD(reg, 2, 15) : GET_BITFIELD(reg, 2, 14)) /* Device 16, functions 2-7 */ @@ -326,6 +329,7 @@ struct pci_id_descr { struct pci_id_table { const struct pci_id_descr *descr; int n_devs; + enum type type; }; struct sbridge_dev { @@ -394,9 +398,14 @@ static const struct pci_id_descr pci_dev_descr_sbridge[] = { { PCI_DESCR(PCI_DEVICE_ID_INTEL_SBRIDGE_BR, 0) }, }; -#define PCI_ID_TABLE_ENTRY(A) { .descr=A, .n_devs = ARRAY_SIZE(A) } +#define PCI_ID_TABLE_ENTRY(A, T) { \ + .descr = A, \ + .n_devs = ARRAY_SIZE(A), \ + .type = T \ +} + static const struct pci_id_table pci_dev_descr_sbridge_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge), + PCI_ID_TABLE_ENTRY(pci_dev_descr_sbridge, SANDY_BRIDGE), {0,} /* 0 terminated list. */ }; @@ -463,7 +472,7 @@ static const struct pci_id_descr pci_dev_descr_ibridge[] = { }; static const struct pci_id_table pci_dev_descr_ibridge_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge), + PCI_ID_TABLE_ENTRY(pci_dev_descr_ibridge, IVY_BRIDGE), {0,} /* 0 terminated list. */ }; @@ -536,7 +545,7 @@ static const struct pci_id_descr pci_dev_descr_haswell[] = { }; static const struct pci_id_table pci_dev_descr_haswell_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell), + PCI_ID_TABLE_ENTRY(pci_dev_descr_haswell, HASWELL), {0,} /* 0 terminated list. */ }; @@ -580,7 +589,7 @@ static const struct pci_id_descr pci_dev_descr_knl[] = { }; static const struct pci_id_table pci_dev_descr_knl_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_knl), + PCI_ID_TABLE_ENTRY(pci_dev_descr_knl, KNIGHTS_LANDING), {0,} }; @@ -648,7 +657,7 @@ static const struct pci_id_descr pci_dev_descr_broadwell[] = { }; static const struct pci_id_table pci_dev_descr_broadwell_table[] = { - PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell), + PCI_ID_TABLE_ENTRY(pci_dev_descr_broadwell, BROADWELL), {0,} /* 0 terminated list. */ }; @@ -1894,14 +1903,14 @@ static void get_memory_layout(const struct mem_ctl_info *mci) pci_read_config_dword(pvt->pci_tad[i], rir_offset[j][k], ®); - tmp_mb = RIR_OFFSET(reg) << 6; + tmp_mb = RIR_OFFSET(pvt->info.type, reg) << 6; gb = div_u64_rem(tmp_mb, 1024, &mb); edac_dbg(0, "CH#%d RIR#%d INTL#%d, offset %u.%03u GB (0x%016Lx), tgt: %d, reg=0x%08x\n", i, j, k, gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, - (u32)RIR_RNK_TGT(reg), + (u32)RIR_RNK_TGT(pvt->info.type, reg), reg); } } @@ -2234,7 +2243,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, pci_read_config_dword(pvt->pci_tad[ch_add + base_ch], rir_offset[n_rir][idx], ®); - *rank = RIR_RNK_TGT(reg); + *rank = RIR_RNK_TGT(pvt->info.type, reg); edac_dbg(0, "RIR#%d: channel address 0x%08Lx < 0x%08Lx, RIR interleave %d, index %d\n", n_rir, @@ -2369,22 +2378,19 @@ static int sbridge_get_onedevice(struct pci_dev **prev, * @num_mc: pointer to the memory controllers count, to be incremented in case * of success. * @table: model specific table - * @allow_dups: allow for multiple devices to exist with the same device id - * (as implemented, this isn't expected to work correctly in the - * multi-socket case). - * @multi_bus: don't assume devices on different buses belong to different - * memory controllers. * * returns 0 in case of success or error code */ -static int sbridge_get_all_devices_full(u8 *num_mc, - const struct pci_id_table *table, - int allow_dups, - int multi_bus) +static int sbridge_get_all_devices(u8 *num_mc, + const struct pci_id_table *table) { int i, rc; struct pci_dev *pdev = NULL; + int allow_dups = 0; + int multi_bus = 0; + if (table->type == KNIGHTS_LANDING) + allow_dups = multi_bus = 1; while (table && table->descr) { for (i = 0; i < table->n_devs; i++) { if (!allow_dups || i == 0 || @@ -2411,11 +2417,6 @@ static int sbridge_get_all_devices_full(u8 *num_mc, return 0; } -#define sbridge_get_all_devices(num_mc, table) \ - sbridge_get_all_devices_full(num_mc, table, 0, 0) -#define sbridge_get_all_devices_knl(num_mc, table) \ - sbridge_get_all_devices_full(num_mc, table, 1, 1) - static int sbridge_mci_bind_devs(struct mem_ctl_info *mci, struct sbridge_dev *sbridge_dev) { @@ -3357,12 +3358,12 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type) #define ICPU(model, table) \ { X86_VENDOR_INTEL, 6, model, 0, (unsigned long)&table } -/* Order here must match "enum type" */ static const struct x86_cpu_id sbridge_cpuids[] = { ICPU(0x2d, pci_dev_descr_sbridge_table), /* SANDY_BRIDGE */ ICPU(0x3e, pci_dev_descr_ibridge_table), /* IVY_BRIDGE */ ICPU(0x3f, pci_dev_descr_haswell_table), /* HASWELL */ ICPU(0x4f, pci_dev_descr_broadwell_table), /* BROADWELL */ + ICPU(0x56, pci_dev_descr_broadwell_table), /* BROADWELL-DE */ ICPU(0x57, pci_dev_descr_knl_table), /* KNIGHTS_LANDING */ { } }; @@ -3398,7 +3399,7 @@ static int sbridge_probe(const struct x86_cpu_id *id) mc, mc + 1, num_mc); sbridge_dev->mc = mc++; - rc = sbridge_register_mci(sbridge_dev, id - sbridge_cpuids); + rc = sbridge_register_mci(sbridge_dev, ptable->type); if (unlikely(rc < 0)) goto fail1; } diff --git a/drivers/extcon/extcon-palmas.c b/drivers/extcon/extcon-palmas.c index 8b3226dca1d9..caff46c0e214 100644 --- a/drivers/extcon/extcon-palmas.c +++ b/drivers/extcon/extcon-palmas.c @@ -360,6 +360,8 @@ static int palmas_usb_probe(struct platform_device *pdev) palmas_enable_irq(palmas_usb); /* perform initial detection */ + if (palmas_usb->enable_gpio_vbus_detection) + palmas_vbus_irq_handler(palmas_usb->gpio_vbus_irq, palmas_usb); palmas_gpio_id_detect(&palmas_usb->wq_detectid.work); device_set_wakeup_capable(&pdev->dev, true); return 0; diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c index a850cbc48d8d..c49d50e68aee 100644 --- a/drivers/firmware/efi/arm-init.c +++ b/drivers/firmware/efi/arm-init.c @@ -174,6 +174,7 @@ static __init void reserve_regions(void) { efi_memory_desc_t *md; u64 paddr, npages, size; + int resv; if (efi_enabled(EFI_DBG)) pr_info("Processing EFI memory map:\n"); @@ -190,12 +191,14 @@ static __init void reserve_regions(void) paddr = md->phys_addr; npages = md->num_pages; + resv = is_reserve_region(md); if (efi_enabled(EFI_DBG)) { char buf[64]; - pr_info(" 0x%012llx-0x%012llx %s", + pr_info(" 0x%012llx-0x%012llx %s%s\n", paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1, - efi_md_typeattr_format(buf, sizeof(buf), md)); + efi_md_typeattr_format(buf, sizeof(buf), md), + resv ? "*" : ""); } memrange_efi_to_native(&paddr, &npages); @@ -204,14 +207,9 @@ static __init void reserve_regions(void) if (is_normal_ram(md)) early_init_dt_add_memory_arch(paddr, size); - if (is_reserve_region(md)) { + if (resv) memblock_mark_nomap(paddr, size); - if (efi_enabled(EFI_DBG)) - pr_cont("*"); - } - if (efi_enabled(EFI_DBG)) - pr_cont("\n"); } set_bit(EFI_MEMMAP, &efi.flags); diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 48da857f4774..d7860614f87f 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -33,6 +33,7 @@ config ARCH_REQUIRE_GPIOLIB menuconfig GPIOLIB bool "GPIO Support" + select ANON_INODES help This enables GPIO support through the generic GPIO library. You only need to enable this, if you also want to enable @@ -48,7 +49,7 @@ config GPIO_DEVRES config OF_GPIO def_bool y - depends on OF || COMPILE_TEST + depends on OF config GPIO_ACPI def_bool y @@ -401,9 +402,12 @@ config GPIO_TB10X select OF_GPIO config GPIO_TEGRA - bool - default y + bool "NVIDIA Tegra GPIO support" + default ARCH_TEGRA depends on ARCH_TEGRA || COMPILE_TEST + depends on OF + help + Say yes here to support GPIO pins on NVIDIA Tegra SoCs. config GPIO_TS4800 tristate "TS-4800 DIO blocks and compatibles" @@ -530,7 +534,7 @@ menu "Port-mapped I/O GPIO drivers" config GPIO_104_DIO_48E tristate "ACCES 104-DIO-48E GPIO support" - depends on ISA + depends on ISA_BUS_API select GPIOLIB_IRQCHIP help Enables GPIO support for the ACCES 104-DIO-48E series (104-DIO-48E, @@ -540,7 +544,7 @@ config GPIO_104_DIO_48E config GPIO_104_IDIO_16 tristate "ACCES 104-IDIO-16 GPIO support" - depends on ISA + depends on ISA_BUS_API select GPIOLIB_IRQCHIP help Enables GPIO support for the ACCES 104-IDIO-16 family (104-IDIO-16, @@ -551,7 +555,7 @@ config GPIO_104_IDIO_16 config GPIO_104_IDI_48 tristate "ACCES 104-IDI-48 GPIO support" - depends on ISA + depends on ISA_BUS_API select GPIOLIB_IRQCHIP help Enables GPIO support for the ACCES 104-IDI-48 family (104-IDI-48A, @@ -627,7 +631,7 @@ config GPIO_TS5500 config GPIO_WS16C48 tristate "WinSystems WS16C48 GPIO support" - depends on ISA + depends on ISA_BUS_API select GPIOLIB_IRQCHIP help Enables GPIO support for the WinSystems WS16C48. The base port diff --git a/drivers/gpio/gpio-104-dio-48e.c b/drivers/gpio/gpio-104-dio-48e.c index 1a647c07be67..fcf776971ca9 100644 --- a/drivers/gpio/gpio-104-dio-48e.c +++ b/drivers/gpio/gpio-104-dio-48e.c @@ -75,7 +75,7 @@ static int dio48e_gpio_direction_input(struct gpio_chip *chip, unsigned offset) { struct dio48e_gpio *const dio48egpio = gpiochip_get_data(chip); const unsigned io_port = offset / 8; - const unsigned control_port = io_port / 2; + const unsigned int control_port = io_port / 3; const unsigned control_addr = dio48egpio->base + 3 + control_port*4; unsigned long flags; unsigned control; @@ -115,7 +115,7 @@ static int dio48e_gpio_direction_output(struct gpio_chip *chip, unsigned offset, { struct dio48e_gpio *const dio48egpio = gpiochip_get_data(chip); const unsigned io_port = offset / 8; - const unsigned control_port = io_port / 2; + const unsigned int control_port = io_port / 3; const unsigned mask = BIT(offset % 8); const unsigned control_addr = dio48egpio->base + 3 + control_port*4; const unsigned out_port = (io_port > 2) ? io_port + 1 : io_port; diff --git a/drivers/gpio/gpio-104-idi-48.c b/drivers/gpio/gpio-104-idi-48.c index 6c75c83baf5a..2d2763ea1a68 100644 --- a/drivers/gpio/gpio-104-idi-48.c +++ b/drivers/gpio/gpio-104-idi-48.c @@ -247,6 +247,7 @@ static int idi_48_probe(struct device *dev, unsigned int id) idi48gpio->irq = irq[id]; spin_lock_init(&idi48gpio->lock); + spin_lock_init(&idi48gpio->ack_lock); dev_set_drvdata(dev, idi48gpio); diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c index 9aabc48ff5de..953e4b829e32 100644 --- a/drivers/gpio/gpio-bcm-kona.c +++ b/drivers/gpio/gpio-bcm-kona.c @@ -547,11 +547,11 @@ static void bcm_kona_gpio_reset(struct bcm_kona_gpio *kona_gpio) /* disable interrupts and clear status */ for (i = 0; i < kona_gpio->num_bank; i++) { /* Unlock the entire bank first */ - bcm_kona_gpio_write_lock_regs(kona_gpio, i, UNLOCK_CODE); + bcm_kona_gpio_write_lock_regs(reg_base, i, UNLOCK_CODE); writel(0xffffffff, reg_base + GPIO_INT_MASK(i)); writel(0xffffffff, reg_base + GPIO_INT_STATUS(i)); /* Now re-lock the bank */ - bcm_kona_gpio_write_lock_regs(kona_gpio, i, LOCK_CODE); + bcm_kona_gpio_write_lock_regs(reg_base, i, LOCK_CODE); } } diff --git a/drivers/gpio/gpio-sch.c b/drivers/gpio/gpio-sch.c index e85e7539cf5d..eb43ae4835c1 100644 --- a/drivers/gpio/gpio-sch.c +++ b/drivers/gpio/gpio-sch.c @@ -61,9 +61,8 @@ static unsigned sch_gpio_bit(struct sch_gpio *sch, unsigned gpio) return gpio % 8; } -static int sch_gpio_reg_get(struct gpio_chip *gc, unsigned gpio, unsigned reg) +static int sch_gpio_reg_get(struct sch_gpio *sch, unsigned gpio, unsigned reg) { - struct sch_gpio *sch = gpiochip_get_data(gc); unsigned short offset, bit; u8 reg_val; @@ -75,10 +74,9 @@ static int sch_gpio_reg_get(struct gpio_chip *gc, unsigned gpio, unsigned reg) return reg_val; } -static void sch_gpio_reg_set(struct gpio_chip *gc, unsigned gpio, unsigned reg, +static void sch_gpio_reg_set(struct sch_gpio *sch, unsigned gpio, unsigned reg, int val) { - struct sch_gpio *sch = gpiochip_get_data(gc); unsigned short offset, bit; u8 reg_val; @@ -98,14 +96,15 @@ static int sch_gpio_direction_in(struct gpio_chip *gc, unsigned gpio_num) struct sch_gpio *sch = gpiochip_get_data(gc); spin_lock(&sch->lock); - sch_gpio_reg_set(gc, gpio_num, GIO, 1); + sch_gpio_reg_set(sch, gpio_num, GIO, 1); spin_unlock(&sch->lock); return 0; } static int sch_gpio_get(struct gpio_chip *gc, unsigned gpio_num) { - return sch_gpio_reg_get(gc, gpio_num, GLV); + struct sch_gpio *sch = gpiochip_get_data(gc); + return sch_gpio_reg_get(sch, gpio_num, GLV); } static void sch_gpio_set(struct gpio_chip *gc, unsigned gpio_num, int val) @@ -113,7 +112,7 @@ static void sch_gpio_set(struct gpio_chip *gc, unsigned gpio_num, int val) struct sch_gpio *sch = gpiochip_get_data(gc); spin_lock(&sch->lock); - sch_gpio_reg_set(gc, gpio_num, GLV, val); + sch_gpio_reg_set(sch, gpio_num, GLV, val); spin_unlock(&sch->lock); } @@ -123,7 +122,7 @@ static int sch_gpio_direction_out(struct gpio_chip *gc, unsigned gpio_num, struct sch_gpio *sch = gpiochip_get_data(gc); spin_lock(&sch->lock); - sch_gpio_reg_set(gc, gpio_num, GIO, 0); + sch_gpio_reg_set(sch, gpio_num, GIO, 0); spin_unlock(&sch->lock); /* @@ -182,13 +181,13 @@ static int sch_gpio_probe(struct platform_device *pdev) * GPIO7 is configured by the CMC as SLPIOVR * Enable GPIO[9:8] core powered gpios explicitly */ - sch_gpio_reg_set(&sch->chip, 8, GEN, 1); - sch_gpio_reg_set(&sch->chip, 9, GEN, 1); + sch_gpio_reg_set(sch, 8, GEN, 1); + sch_gpio_reg_set(sch, 9, GEN, 1); /* * SUS_GPIO[2:0] enabled by default * Enable SUS_GPIO3 resume powered gpio explicitly */ - sch_gpio_reg_set(&sch->chip, 13, GEN, 1); + sch_gpio_reg_set(sch, 13, GEN, 1); break; case PCI_DEVICE_ID_INTEL_ITC_LPC: diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c index ec891a27952f..661b0e34e067 100644 --- a/drivers/gpio/gpio-tegra.c +++ b/drivers/gpio/gpio-tegra.c @@ -98,7 +98,6 @@ struct tegra_gpio_info { const struct tegra_gpio_soc_config *soc; struct gpio_chip gc; struct irq_chip ic; - struct lock_class_key lock_class; u32 bank_count; }; @@ -547,6 +546,12 @@ static const struct dev_pm_ops tegra_gpio_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(tegra_gpio_suspend, tegra_gpio_resume) }; +/* + * This lock class tells lockdep that GPIO irqs are in a different category + * than their parents, so it won't report false recursion. + */ +static struct lock_class_key gpio_lock_class; + static int tegra_gpio_probe(struct platform_device *pdev) { const struct tegra_gpio_soc_config *config; @@ -660,7 +665,7 @@ static int tegra_gpio_probe(struct platform_device *pdev) bank = &tgi->bank_info[GPIO_BANK(gpio)]; - irq_set_lockdep_class(irq, &tgi->lock_class); + irq_set_lockdep_class(irq, &gpio_lock_class); irq_set_chip_data(irq, bank); irq_set_chip_and_handler(irq, &tgi->ic, handle_simple_irq); } diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c index 75c6355b018d..e72794e463aa 100644 --- a/drivers/gpio/gpio-zynq.c +++ b/drivers/gpio/gpio-zynq.c @@ -709,7 +709,13 @@ static int zynq_gpio_probe(struct platform_device *pdev) dev_err(&pdev->dev, "input clock not found.\n"); return PTR_ERR(gpio->clk); } + ret = clk_prepare_enable(gpio->clk); + if (ret) { + dev_err(&pdev->dev, "Unable to enable clock.\n"); + return ret; + } + pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); ret = pm_runtime_get_sync(&pdev->dev); if (ret < 0) @@ -747,6 +753,7 @@ static int zynq_gpio_probe(struct platform_device *pdev) pm_runtime_put(&pdev->dev); err_pm_dis: pm_runtime_disable(&pdev->dev); + clk_disable_unprepare(gpio->clk); return ret; } diff --git a/drivers/gpio/gpiolib-legacy.c b/drivers/gpio/gpiolib-legacy.c index 3a5c7011ad3b..8b830996fe02 100644 --- a/drivers/gpio/gpiolib-legacy.c +++ b/drivers/gpio/gpiolib-legacy.c @@ -28,6 +28,10 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) if (!desc && gpio_is_valid(gpio)) return -EPROBE_DEFER; + err = gpiod_request(desc, label); + if (err) + return err; + if (flags & GPIOF_OPEN_DRAIN) set_bit(FLAG_OPEN_DRAIN, &desc->flags); @@ -37,10 +41,6 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) if (flags & GPIOF_ACTIVE_LOW) set_bit(FLAG_ACTIVE_LOW, &desc->flags); - err = gpiod_request(desc, label); - if (err) - return err; - if (flags & GPIOF_DIR_IN) err = gpiod_direction_input(desc); else diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index d22dcc38179d..4aabddb38b59 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 24f60d28f0c0..be74bd370f1f 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -449,7 +449,6 @@ static void gpiodevice_release(struct device *dev) { struct gpio_device *gdev = dev_get_drvdata(dev); - cdev_del(&gdev->chrdev); list_del(&gdev->list); ida_simple_remove(&gpio_ida, gdev->id); kfree(gdev->label); @@ -482,7 +481,6 @@ static int gpiochip_setup_dev(struct gpio_device *gdev) /* From this point, the .release() function cleans up gpio_device */ gdev->dev.release = gpiodevice_release; - get_device(&gdev->dev); pr_debug("%s: registered GPIOs %d to %d on device: %s (%s)\n", __func__, gdev->base, gdev->base + gdev->ngpio - 1, dev_name(&gdev->dev), gdev->chip->label ? : "generic"); @@ -770,6 +768,8 @@ void gpiochip_remove(struct gpio_chip *chip) * be removed, else it will be dangling until the last user is * gone. */ + cdev_del(&gdev->chrdev); + device_del(&gdev->dev); put_device(&gdev->dev); } EXPORT_SYMBOL_GPL(gpiochip_remove); @@ -869,7 +869,7 @@ struct gpio_chip *gpiochip_find(void *data, spin_lock_irqsave(&gpio_lock, flags); list_for_each_entry(gdev, &gpio_devices, list) - if (match(gdev->chip, data)) + if (gdev->chip && match(gdev->chip, data)) break; /* No match? */ @@ -1352,14 +1352,6 @@ static int __gpiod_request(struct gpio_desc *desc, const char *label) spin_lock_irqsave(&gpio_lock, flags); } done: - if (status < 0) { - /* Clear flags that might have been set by the caller before - * requesting the GPIO. - */ - clear_bit(FLAG_ACTIVE_LOW, &desc->flags); - clear_bit(FLAG_OPEN_DRAIN, &desc->flags); - clear_bit(FLAG_OPEN_SOURCE, &desc->flags); - } spin_unlock_irqrestore(&gpio_lock, flags); return status; } @@ -1373,8 +1365,12 @@ static int __gpiod_request(struct gpio_desc *desc, const char *label) #define VALIDATE_DESC(desc) do { \ if (!desc) \ return 0; \ + if (IS_ERR(desc)) { \ + pr_warn("%s: invalid GPIO (errorpointer)\n", __func__); \ + return PTR_ERR(desc); \ + } \ if (!desc->gdev) { \ - pr_warn("%s: invalid GPIO\n", __func__); \ + pr_warn("%s: invalid GPIO (no device)\n", __func__); \ return -EINVAL; \ } \ if ( !desc->gdev->chip ) { \ @@ -1386,8 +1382,12 @@ static int __gpiod_request(struct gpio_desc *desc, const char *label) #define VALIDATE_DESC_VOID(desc) do { \ if (!desc) \ return; \ + if (IS_ERR(desc)) { \ + pr_warn("%s: invalid GPIO (errorpointer)\n", __func__); \ + return; \ + } \ if (!desc->gdev) { \ - pr_warn("%s: invalid GPIO\n", __func__); \ + pr_warn("%s: invalid GPIO (no device)\n", __func__); \ return; \ } \ if (!desc->gdev->chip) { \ @@ -2056,7 +2056,14 @@ int gpiod_to_irq(const struct gpio_desc *desc) struct gpio_chip *chip; int offset; - VALIDATE_DESC(desc); + /* + * Cannot VALIDATE_DESC() here as gpiod_to_irq() consumer semantics + * requires this function to not return zero on an invalid descriptor + * but rather a negative error number. + */ + if (!desc || IS_ERR(desc) || !desc->gdev || !desc->gdev->chip) + return -EINVAL; + chip = desc->gdev->chip; offset = gpio_chip_hwgpio(desc); if (chip->to_irq) { @@ -2572,28 +2579,13 @@ struct gpio_desc *__must_check gpiod_get_optional(struct device *dev, } EXPORT_SYMBOL_GPL(gpiod_get_optional); -/** - * gpiod_parse_flags - helper function to parse GPIO lookup flags - * @desc: gpio to be setup - * @lflags: gpio_lookup_flags - returned from of_find_gpio() or - * of_get_gpio_hog() - * - * Set the GPIO descriptor flags based on the given GPIO lookup flags. - */ -static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags) -{ - if (lflags & GPIO_ACTIVE_LOW) - set_bit(FLAG_ACTIVE_LOW, &desc->flags); - if (lflags & GPIO_OPEN_DRAIN) - set_bit(FLAG_OPEN_DRAIN, &desc->flags); - if (lflags & GPIO_OPEN_SOURCE) - set_bit(FLAG_OPEN_SOURCE, &desc->flags); -} /** * gpiod_configure_flags - helper function to configure a given GPIO * @desc: gpio whose value will be assigned * @con_id: function within the GPIO consumer + * @lflags: gpio_lookup_flags - returned from of_find_gpio() or + * of_get_gpio_hog() * @dflags: gpiod_flags - optional GPIO initialization flags * * Return 0 on success, -ENOENT if no GPIO has been assigned to the @@ -2601,10 +2593,17 @@ static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags) * occurred while trying to acquire the GPIO. */ static int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id, - enum gpiod_flags dflags) + unsigned long lflags, enum gpiod_flags dflags) { int status; + if (lflags & GPIO_ACTIVE_LOW) + set_bit(FLAG_ACTIVE_LOW, &desc->flags); + if (lflags & GPIO_OPEN_DRAIN) + set_bit(FLAG_OPEN_DRAIN, &desc->flags); + if (lflags & GPIO_OPEN_SOURCE) + set_bit(FLAG_OPEN_SOURCE, &desc->flags); + /* No particular flag request, return here... */ if (!(dflags & GPIOD_FLAGS_BIT_DIR_SET)) { pr_debug("no flags found for %s\n", con_id); @@ -2671,13 +2670,11 @@ struct gpio_desc *__must_check gpiod_get_index(struct device *dev, return desc; } - gpiod_parse_flags(desc, lookupflags); - status = gpiod_request(desc, con_id); if (status < 0) return ERR_PTR(status); - status = gpiod_configure_flags(desc, con_id, flags); + status = gpiod_configure_flags(desc, con_id, lookupflags, flags); if (status < 0) { dev_dbg(dev, "setup of GPIO %s failed\n", con_id); gpiod_put(desc); @@ -2733,6 +2730,10 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, if (IS_ERR(desc)) return desc; + ret = gpiod_request(desc, NULL); + if (ret) + return ERR_PTR(ret); + if (active_low) set_bit(FLAG_ACTIVE_LOW, &desc->flags); @@ -2743,10 +2744,6 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, set_bit(FLAG_OPEN_SOURCE, &desc->flags); } - ret = gpiod_request(desc, NULL); - if (ret) - return ERR_PTR(ret); - return desc; } EXPORT_SYMBOL_GPL(fwnode_get_named_gpiod); @@ -2799,8 +2796,6 @@ int gpiod_hog(struct gpio_desc *desc, const char *name, chip = gpiod_to_chip(desc); hwnum = gpio_chip_hwgpio(desc); - gpiod_parse_flags(desc, lflags); - local_desc = gpiochip_request_own_desc(chip, hwnum, name); if (IS_ERR(local_desc)) { status = PTR_ERR(local_desc); @@ -2809,7 +2804,7 @@ int gpiod_hog(struct gpio_desc *desc, const char *name, return status; } - status = gpiod_configure_flags(desc, name, dflags); + status = gpiod_configure_flags(desc, name, lflags, dflags); if (status < 0) { pr_err("setup of hog GPIO %s (chip %s, offset %d) failed, %d\n", name, chip->label, hwnum, status); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index da3d02154fa6..8ebc5f1eb4c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -85,8 +85,12 @@ extern int amdgpu_vm_debug; extern int amdgpu_sched_jobs; extern int amdgpu_sched_hw_submission; extern int amdgpu_powerplay; +extern int amdgpu_powercontainment; extern unsigned amdgpu_pcie_gen_cap; extern unsigned amdgpu_pcie_lane_cap; +extern unsigned amdgpu_cg_mask; +extern unsigned amdgpu_pg_mask; +extern char *amdgpu_disable_cu; #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS 3000 #define AMDGPU_MAX_USEC_TIMEOUT 100000 /* 100 ms */ @@ -183,6 +187,10 @@ int amdgpu_set_clockgating_state(struct amdgpu_device *adev, int amdgpu_set_powergating_state(struct amdgpu_device *adev, enum amd_ip_block_type block_type, enum amd_powergating_state state); +int amdgpu_wait_for_idle(struct amdgpu_device *adev, + enum amd_ip_block_type block_type); +bool amdgpu_is_idle(struct amdgpu_device *adev, + enum amd_ip_block_type block_type); struct amdgpu_ip_block_version { enum amd_ip_block_type type; @@ -298,13 +306,16 @@ struct amdgpu_ring_funcs { uint32_t oa_base, uint32_t oa_size); /* testing functions */ int (*test_ring)(struct amdgpu_ring *ring); - int (*test_ib)(struct amdgpu_ring *ring); + int (*test_ib)(struct amdgpu_ring *ring, long timeout); /* insert NOP packets */ void (*insert_nop)(struct amdgpu_ring *ring, uint32_t count); /* pad the indirect buffer to the necessary number of dw */ void (*pad_ib)(struct amdgpu_ring *ring, struct amdgpu_ib *ib); unsigned (*init_cond_exec)(struct amdgpu_ring *ring); void (*patch_cond_exec)(struct amdgpu_ring *ring, unsigned offset); + /* note usage for clock and power gating */ + void (*begin_use)(struct amdgpu_ring *ring); + void (*end_use)(struct amdgpu_ring *ring); }; /* @@ -594,11 +605,9 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync, struct reservation_object *resv, void *owner); -bool amdgpu_sync_is_idle(struct amdgpu_sync *sync); -int amdgpu_sync_cycle_fences(struct amdgpu_sync *dst, struct amdgpu_sync *src, - struct fence *fence); +struct fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync, + struct amdgpu_ring *ring); struct fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync); -int amdgpu_sync_wait(struct amdgpu_sync *sync); void amdgpu_sync_free(struct amdgpu_sync *sync); int amdgpu_sync_init(void); void amdgpu_sync_fini(void); @@ -754,12 +763,11 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs, int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size, struct amdgpu_job **job); +void amdgpu_job_free_resources(struct amdgpu_job *job); void amdgpu_job_free(struct amdgpu_job *job); -void amdgpu_job_free_func(struct kref *refcount); int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring, struct amd_sched_entity *entity, void *owner, struct fence **f); -void amdgpu_job_timeout_func(struct work_struct *work); struct amdgpu_ring { struct amdgpu_device *adev; @@ -767,12 +775,9 @@ struct amdgpu_ring { struct amdgpu_fence_driver fence_drv; struct amd_gpu_scheduler sched; - spinlock_t fence_lock; struct amdgpu_bo *ring_obj; volatile uint32_t *ring; unsigned rptr_offs; - u64 next_rptr_gpu_addr; - volatile u32 *next_rptr_cpu_addr; unsigned wptr; unsigned wptr_old; unsigned ring_size; @@ -791,14 +796,16 @@ struct amdgpu_ring { u32 doorbell_index; bool use_doorbell; unsigned wptr_offs; - unsigned next_rptr_offs; unsigned fence_offs; uint64_t current_ctx; enum amdgpu_ring_type type; char name[16]; unsigned cond_exe_offs; - u64 cond_exe_gpu_addr; - volatile u32 *cond_exe_cpu_addr; + u64 cond_exe_gpu_addr; + volatile u32 *cond_exe_cpu_addr; +#if defined(CONFIG_DEBUG_FS) + struct dentry *ent; +#endif }; /* @@ -861,6 +868,7 @@ struct amdgpu_vm { struct amdgpu_bo *page_directory; unsigned max_pde_used; struct fence *page_directory_fence; + uint64_t last_eviction_counter; /* array of page tables, one for each page directory entry */ struct amdgpu_vm_pt *page_tables; @@ -883,13 +891,14 @@ struct amdgpu_vm_id { struct fence *first; struct amdgpu_sync active; struct fence *last_flush; - struct amdgpu_ring *last_user; atomic64_t owner; uint64_t pd_gpu_addr; /* last flushed PD/PT update */ struct fence *flushed_updates; + uint32_t current_gpu_reset_count; + uint32_t gds_base; uint32_t gds_size; uint32_t gws_base; @@ -905,6 +914,10 @@ struct amdgpu_vm_manager { struct list_head ids_lru; struct amdgpu_vm_id ids[AMDGPU_NUM_VM]; + /* Handling of VM fences */ + u64 fence_context; + unsigned seqno[AMDGPU_MAX_RINGS]; + uint32_t max_pfn; /* vram base address for page table entry */ u64 vram_base_offset; @@ -926,17 +939,14 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm); void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm, struct list_head *validated, struct amdgpu_bo_list_entry *entry); -void amdgpu_vm_get_pt_bos(struct amdgpu_vm *vm, struct list_head *duplicates); +void amdgpu_vm_get_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm, + struct list_head *duplicates); void amdgpu_vm_move_pt_bos_in_lru(struct amdgpu_device *adev, struct amdgpu_vm *vm); int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, struct amdgpu_sync *sync, struct fence *fence, - unsigned *vm_id, uint64_t *vm_pd_addr); -int amdgpu_vm_flush(struct amdgpu_ring *ring, - unsigned vm_id, uint64_t pd_addr, - uint32_t gds_base, uint32_t gds_size, - uint32_t gws_base, uint32_t gws_size, - uint32_t oa_base, uint32_t oa_size); + struct amdgpu_job *job); +int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job); void amdgpu_vm_reset_id(struct amdgpu_device *adev, unsigned vm_id); uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr); int amdgpu_vm_update_page_directory(struct amdgpu_device *adev, @@ -1142,6 +1152,12 @@ struct amdgpu_cu_info { uint32_t bitmap[4][4]; }; +struct amdgpu_gfx_funcs { + /* get the gpu clock counter */ + uint64_t (*get_gpu_clock_counter)(struct amdgpu_device *adev); + void (*select_se_sh)(struct amdgpu_device *adev, u32 se_num, u32 sh_num, u32 instance); +}; + struct amdgpu_gfx { struct mutex gpu_clock_mutex; struct amdgpu_gca_config config; @@ -1178,6 +1194,7 @@ struct amdgpu_gfx { /* ce ram size*/ unsigned ce_ram_size; struct amdgpu_cu_info cu_info; + const struct amdgpu_gfx_funcs *funcs; }; int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm, @@ -1195,10 +1212,6 @@ void amdgpu_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count); void amdgpu_ring_generic_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib); void amdgpu_ring_commit(struct amdgpu_ring *ring); void amdgpu_ring_undo(struct amdgpu_ring *ring); -unsigned amdgpu_ring_backup(struct amdgpu_ring *ring, - uint32_t **data); -int amdgpu_ring_restore(struct amdgpu_ring *ring, - unsigned size, uint32_t *data); int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, unsigned ring_size, u32 nop, u32 align_mask, struct amdgpu_irq_src *irq_src, unsigned irq_type, @@ -1250,6 +1263,7 @@ struct amdgpu_job { uint32_t num_ibs; void *owner; uint64_t ctx; + bool vm_needs_flush; unsigned vm_id; uint64_t vm_pd_addr; uint32_t gds_base, gds_size; @@ -1257,8 +1271,7 @@ struct amdgpu_job { uint32_t oa_base, oa_size; /* user fence handling */ - struct amdgpu_bo *uf_bo; - uint32_t uf_offset; + uint64_t uf_addr; uint64_t uf_sequence; }; @@ -1560,6 +1573,12 @@ struct amdgpu_dpm_funcs { u32 (*get_fan_control_mode)(struct amdgpu_device *adev); int (*set_fan_speed_percent)(struct amdgpu_device *adev, u32 speed); int (*get_fan_speed_percent)(struct amdgpu_device *adev, u32 *speed); + int (*force_clock_level)(struct amdgpu_device *adev, enum pp_clock_type type, uint32_t mask); + int (*print_clock_levels)(struct amdgpu_device *adev, enum pp_clock_type type, char *buf); + int (*get_sclk_od)(struct amdgpu_device *adev); + int (*set_sclk_od)(struct amdgpu_device *adev, uint32_t value); + int (*get_mclk_od)(struct amdgpu_device *adev); + int (*set_mclk_od)(struct amdgpu_device *adev, uint32_t value); }; struct amdgpu_dpm { @@ -1662,6 +1681,7 @@ struct amdgpu_uvd { struct amdgpu_ring ring; struct amdgpu_irq_src irq; bool address_64_bit; + bool use_ctx_buf; struct amd_sched_entity entity; }; @@ -1683,6 +1703,7 @@ struct amdgpu_vce { struct drm_file *filp[AMDGPU_MAX_VCE_HANDLES]; uint32_t img_size[AMDGPU_MAX_VCE_HANDLES]; struct delayed_work idle_work; + struct mutex idle_mutex; const struct firmware *fw; /* VCE firmware */ struct amdgpu_ring ring[AMDGPU_MAX_VCE_RINGS]; struct amdgpu_irq_src irq; @@ -1767,6 +1788,8 @@ int amdgpu_debugfs_init(struct drm_minor *minor); void amdgpu_debugfs_cleanup(struct drm_minor *minor); #endif +int amdgpu_debugfs_firmware_init(struct amdgpu_device *adev); + /* * amdgpu smumgr functions */ @@ -1811,15 +1834,13 @@ struct amdgpu_asic_funcs { u32 sh_num, u32 reg_offset, u32 *value); void (*set_vga_state)(struct amdgpu_device *adev, bool state); int (*reset)(struct amdgpu_device *adev); - /* wait for mc_idle */ - int (*wait_for_mc_idle)(struct amdgpu_device *adev); /* get the reference clock */ u32 (*get_xclk)(struct amdgpu_device *adev); - /* get the gpu clock counter */ - uint64_t (*get_gpu_clock_counter)(struct amdgpu_device *adev); /* MM block clocks */ int (*set_uvd_clocks)(struct amdgpu_device *adev, u32 vclk, u32 dclk); int (*set_vce_clocks)(struct amdgpu_device *adev, u32 evclk, u32 ecclk); + /* query virtual capabilities */ + u32 (*get_virtual_caps)(struct amdgpu_device *adev); }; /* @@ -1914,8 +1935,12 @@ void amdgpu_cgs_destroy_device(struct cgs_device *cgs_device); /* GPU virtualization */ +#define AMDGPU_VIRT_CAPS_SRIOV_EN (1 << 0) +#define AMDGPU_VIRT_CAPS_IS_VF (1 << 1) struct amdgpu_virtualization { bool supports_sr_iov; + bool is_virtual; + u32 caps; }; /* @@ -1997,6 +2022,10 @@ struct amdgpu_device { spinlock_t didt_idx_lock; amdgpu_rreg_t didt_rreg; amdgpu_wreg_t didt_wreg; + /* protects concurrent gc_cac register access */ + spinlock_t gc_cac_idx_lock; + amdgpu_rreg_t gc_cac_rreg; + amdgpu_wreg_t gc_cac_wreg; /* protects concurrent ENDPOINT (audio) register access */ spinlock_t audio_endpt_idx_lock; amdgpu_block_rreg_t audio_endpt_rreg; @@ -2022,6 +2051,7 @@ struct amdgpu_device { atomic64_t vram_vis_usage; atomic64_t gtt_usage; atomic64_t num_bytes_moved; + atomic64_t num_evictions; atomic_t gpu_reset_counter; /* display */ @@ -2125,6 +2155,8 @@ void amdgpu_mm_wdoorbell(struct amdgpu_device *adev, u32 index, u32 v); #define WREG32_UVD_CTX(reg, v) adev->uvd_ctx_wreg(adev, (reg), (v)) #define RREG32_DIDT(reg) adev->didt_rreg(adev, (reg)) #define WREG32_DIDT(reg, v) adev->didt_wreg(adev, (reg), (v)) +#define RREG32_GC_CAC(reg) adev->gc_cac_rreg(adev, (reg)) +#define WREG32_GC_CAC(reg, v) adev->gc_cac_wreg(adev, (reg), (v)) #define RREG32_AUDIO_ENDPT(block, reg) adev->audio_endpt_rreg(adev, (block), (reg)) #define WREG32_AUDIO_ENDPT(block, reg, v) adev->audio_endpt_wreg(adev, (block), (reg), (v)) #define WREG32_P(reg, val, mask) \ @@ -2200,11 +2232,10 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring) */ #define amdgpu_asic_set_vga_state(adev, state) (adev)->asic_funcs->set_vga_state((adev), (state)) #define amdgpu_asic_reset(adev) (adev)->asic_funcs->reset((adev)) -#define amdgpu_asic_wait_for_mc_idle(adev) (adev)->asic_funcs->wait_for_mc_idle((adev)) #define amdgpu_asic_get_xclk(adev) (adev)->asic_funcs->get_xclk((adev)) #define amdgpu_asic_set_uvd_clocks(adev, v, d) (adev)->asic_funcs->set_uvd_clocks((adev), (v), (d)) #define amdgpu_asic_set_vce_clocks(adev, ev, ec) (adev)->asic_funcs->set_vce_clocks((adev), (ev), (ec)) -#define amdgpu_asic_get_gpu_clock_counter(adev) (adev)->asic_funcs->get_gpu_clock_counter((adev)) +#define amdgpu_asic_get_virtual_caps(adev) ((adev)->asic_funcs->get_virtual_caps((adev))) #define amdgpu_asic_read_disabled_bios(adev) (adev)->asic_funcs->read_disabled_bios((adev)) #define amdgpu_asic_read_bios_from_rom(adev, b, l) (adev)->asic_funcs->read_bios_from_rom((adev), (b), (l)) #define amdgpu_asic_read_register(adev, se, sh, offset, v)((adev)->asic_funcs->read_register((adev), (se), (sh), (offset), (v))) @@ -2215,7 +2246,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring) #define amdgpu_vm_set_pte_pde(adev, ib, pe, addr, count, incr, flags) ((adev)->vm_manager.vm_pte_funcs->set_pte_pde((ib), (pe), (addr), (count), (incr), (flags))) #define amdgpu_ring_parse_cs(r, p, ib) ((r)->funcs->parse_cs((p), (ib))) #define amdgpu_ring_test_ring(r) (r)->funcs->test_ring((r)) -#define amdgpu_ring_test_ib(r) (r)->funcs->test_ib((r)) +#define amdgpu_ring_test_ib(r, t) (r)->funcs->test_ib((r), (t)) #define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r)) #define amdgpu_ring_get_wptr(r) (r)->funcs->get_wptr((r)) #define amdgpu_ring_set_wptr(r) (r)->funcs->set_wptr((r)) @@ -2257,6 +2288,8 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring) #define amdgpu_dpm_print_power_state(adev, ps) (adev)->pm.funcs->print_power_state((adev), (ps)) #define amdgpu_dpm_vblank_too_short(adev) (adev)->pm.funcs->vblank_too_short((adev)) #define amdgpu_dpm_enable_bapm(adev, e) (adev)->pm.funcs->enable_bapm((adev), (e)) +#define amdgpu_gfx_get_gpu_clock_counter(adev) (adev)->gfx.funcs->get_gpu_clock_counter((adev)) +#define amdgpu_gfx_select_se_sh(adev, se, sh, instance) (adev)->gfx.funcs->select_se_sh((adev), (se), (sh), (instance)) #define amdgpu_dpm_get_temperature(adev) \ ((adev)->pp_enabled ? \ @@ -2335,6 +2368,18 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring) #define amdgpu_dpm_force_clock_level(adev, type, level) \ (adev)->powerplay.pp_funcs->force_clock_level((adev)->powerplay.pp_handle, type, level) +#define amdgpu_dpm_get_sclk_od(adev) \ + (adev)->powerplay.pp_funcs->get_sclk_od((adev)->powerplay.pp_handle) + +#define amdgpu_dpm_set_sclk_od(adev, value) \ + (adev)->powerplay.pp_funcs->set_sclk_od((adev)->powerplay.pp_handle, value) + +#define amdgpu_dpm_get_mclk_od(adev) \ + ((adev)->powerplay.pp_funcs->get_mclk_od((adev)->powerplay.pp_handle)) + +#define amdgpu_dpm_set_mclk_od(adev, value) \ + ((adev)->powerplay.pp_funcs->set_mclk_od((adev)->powerplay.pp_handle, value)) + #define amdgpu_dpm_dispatch_task(adev, event_id, input, output) \ (adev)->powerplay.pp_funcs->dispatch_tasks((adev)->powerplay.pp_handle, (event_id), (input), (output)) @@ -2376,9 +2421,13 @@ bool amdgpu_device_is_px(struct drm_device *dev); #if defined(CONFIG_VGA_SWITCHEROO) void amdgpu_register_atpx_handler(void); void amdgpu_unregister_atpx_handler(void); +bool amdgpu_has_atpx_dgpu_power_cntl(void); +bool amdgpu_is_atpx_hybrid(void); #else static inline void amdgpu_register_atpx_handler(void) {} static inline void amdgpu_unregister_atpx_handler(void) {} +static inline bool amdgpu_has_atpx_dgpu_power_cntl(void) { return false; } +static inline bool amdgpu_is_atpx_hybrid(void) { return false; } #endif /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 32809f749903..d080d0807a5b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -240,8 +240,8 @@ uint64_t get_gpu_clock_counter(struct kgd_dev *kgd) { struct amdgpu_device *rdev = (struct amdgpu_device *)kgd; - if (rdev->asic_funcs->get_gpu_clock_counter) - return rdev->asic_funcs->get_gpu_clock_counter(rdev); + if (rdev->gfx.funcs->get_gpu_clock_counter) + return rdev->gfx.funcs->get_gpu_clock_counter(rdev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index 9df1bcb35bf0..983175363b06 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -551,28 +551,19 @@ int amdgpu_atombios_get_clock_info(struct amdgpu_device *adev) le16_to_cpu(firmware_info->info.usReferenceClock); ppll->reference_div = 0; - if (crev < 2) - ppll->pll_out_min = - le16_to_cpu(firmware_info->info.usMinPixelClockPLL_Output); - else - ppll->pll_out_min = - le32_to_cpu(firmware_info->info_12.ulMinPixelClockPLL_Output); + ppll->pll_out_min = + le32_to_cpu(firmware_info->info_12.ulMinPixelClockPLL_Output); ppll->pll_out_max = le32_to_cpu(firmware_info->info.ulMaxPixelClockPLL_Output); - if (crev >= 4) { - ppll->lcd_pll_out_min = - le16_to_cpu(firmware_info->info_14.usLcdMinPixelClockPLL_Output) * 100; - if (ppll->lcd_pll_out_min == 0) - ppll->lcd_pll_out_min = ppll->pll_out_min; - ppll->lcd_pll_out_max = - le16_to_cpu(firmware_info->info_14.usLcdMaxPixelClockPLL_Output) * 100; - if (ppll->lcd_pll_out_max == 0) - ppll->lcd_pll_out_max = ppll->pll_out_max; - } else { + ppll->lcd_pll_out_min = + le16_to_cpu(firmware_info->info_14.usLcdMinPixelClockPLL_Output) * 100; + if (ppll->lcd_pll_out_min == 0) ppll->lcd_pll_out_min = ppll->pll_out_min; + ppll->lcd_pll_out_max = + le16_to_cpu(firmware_info->info_14.usLcdMaxPixelClockPLL_Output) * 100; + if (ppll->lcd_pll_out_max == 0) ppll->lcd_pll_out_max = ppll->pll_out_max; - } if (ppll->pll_out_min == 0) ppll->pll_out_min = 64800; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index 35a1248aaa77..49de92600074 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "amd_acpi.h" @@ -27,6 +28,7 @@ struct amdgpu_atpx_functions { struct amdgpu_atpx { acpi_handle handle; struct amdgpu_atpx_functions functions; + bool is_hybrid; }; static struct amdgpu_atpx_priv { @@ -63,6 +65,14 @@ bool amdgpu_has_atpx(void) { return amdgpu_atpx_priv.atpx_detected; } +bool amdgpu_has_atpx_dgpu_power_cntl(void) { + return amdgpu_atpx_priv.atpx.functions.power_cntl; +} + +bool amdgpu_is_atpx_hybrid(void) { + return amdgpu_atpx_priv.atpx.is_hybrid; +} + /** * amdgpu_atpx_call - call an ATPX method * @@ -142,18 +152,12 @@ static void amdgpu_atpx_parse_functions(struct amdgpu_atpx_functions *f, u32 mas */ static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx) { - /* make sure required functions are enabled */ - /* dGPU power control is required */ - if (atpx->functions.power_cntl == false) { - printk("ATPX dGPU power cntl not present, forcing\n"); - atpx->functions.power_cntl = true; - } + u32 valid_bits = 0; if (atpx->functions.px_params) { union acpi_object *info; struct atpx_px_params output; size_t size; - u32 valid_bits; info = amdgpu_atpx_call(atpx->handle, ATPX_FUNCTION_GET_PX_PARAMETERS, NULL); if (!info) @@ -172,19 +176,43 @@ static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx) memcpy(&output, info->buffer.pointer, size); valid_bits = output.flags & output.valid_flags; - /* if separate mux flag is set, mux controls are required */ - if (valid_bits & ATPX_SEPARATE_MUX_FOR_I2C) { - atpx->functions.i2c_mux_cntl = true; - atpx->functions.disp_mux_cntl = true; - } - /* if any outputs are muxed, mux controls are required */ - if (valid_bits & (ATPX_CRT1_RGB_SIGNAL_MUXED | - ATPX_TV_SIGNAL_MUXED | - ATPX_DFP_SIGNAL_MUXED)) - atpx->functions.disp_mux_cntl = true; kfree(info); } + + /* if separate mux flag is set, mux controls are required */ + if (valid_bits & ATPX_SEPARATE_MUX_FOR_I2C) { + atpx->functions.i2c_mux_cntl = true; + atpx->functions.disp_mux_cntl = true; + } + /* if any outputs are muxed, mux controls are required */ + if (valid_bits & (ATPX_CRT1_RGB_SIGNAL_MUXED | + ATPX_TV_SIGNAL_MUXED | + ATPX_DFP_SIGNAL_MUXED)) + atpx->functions.disp_mux_cntl = true; + + + /* some bioses set these bits rather than flagging power_cntl as supported */ + if (valid_bits & (ATPX_DYNAMIC_PX_SUPPORTED | + ATPX_DYNAMIC_DGPU_POWER_OFF_SUPPORTED)) + atpx->functions.power_cntl = true; + + atpx->is_hybrid = false; + if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) { + printk("ATPX Hybrid Graphics\n"); +#if 1 + /* This is a temporary hack until the D3 cold support + * makes it upstream. The ATPX power_control method seems + * to still work on even if the system should be using + * the new standardized hybrid D3 cold ACPI interface. + */ + atpx->functions.power_cntl = true; +#else + atpx->functions.power_cntl = false; +#endif + atpx->is_hybrid = true; + } + return 0; } @@ -259,6 +287,10 @@ static int amdgpu_atpx_set_discrete_state(struct amdgpu_atpx *atpx, u8 state) if (!info) return -EIO; kfree(info); + + /* 200ms delay is required after off */ + if (state == 0) + msleep(200); } return 0; } @@ -507,7 +539,6 @@ static int amdgpu_atpx_get_client_id(struct pci_dev *pdev) static const struct vga_switcheroo_handler amdgpu_atpx_handler = { .switchto = amdgpu_atpx_switchto, .power_state = amdgpu_atpx_power_state, - .init = amdgpu_atpx_init, .get_client_id = amdgpu_atpx_get_client_id, }; @@ -542,6 +573,7 @@ static bool amdgpu_atpx_detect(void) printk(KERN_INFO "vga_switcheroo: detected switching method %s handle\n", acpi_method_name); amdgpu_atpx_priv.atpx_detected = true; + amdgpu_atpx_init(); return true; } return false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index 99ca75baa47d..2b6afe123f3d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -352,22 +352,22 @@ bool amdgpu_get_bios(struct amdgpu_device *adev) uint16_t tmp, bios_header_start; r = amdgpu_atrm_get_bios(adev); - if (r == false) + if (!r) r = amdgpu_acpi_vfct_bios(adev); - if (r == false) + if (!r) r = igp_read_bios_from_vram(adev); - if (r == false) + if (!r) r = amdgpu_read_bios(adev); - if (r == false) { + if (!r) { r = amdgpu_read_bios_from_rom(adev); } - if (r == false) { + if (!r) { r = amdgpu_read_disabled_bios(adev); } - if (r == false) { + if (!r) { r = amdgpu_read_platform_bios(adev); } - if (r == false || adev->bios == NULL) { + if (!r || adev->bios == NULL) { DRM_ERROR("Unable to locate a BIOS ROM\n"); adev->bios = NULL; return false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index 823bf5e0b0c8..651115dcce12 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -94,6 +94,7 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev, unsigned last_entry = 0, first_userptr = num_entries; unsigned i; int r; + unsigned long total_size = 0; array = drm_malloc_ab(num_entries, sizeof(struct amdgpu_bo_list_entry)); if (!array) @@ -140,6 +141,7 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev, if (entry->robj->prefered_domains == AMDGPU_GEM_DOMAIN_OA) oa_obj = entry->robj; + total_size += amdgpu_bo_size(entry->robj); trace_amdgpu_bo_list_set(list, entry->robj); } @@ -155,6 +157,7 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev, list->array = array; list->num_entries = num_entries; + trace_amdgpu_cs_bo_status(list->num_entries, total_size); return 0; error_free: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c index 199f76baf22c..bc0440f7a31d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c @@ -312,6 +312,8 @@ static uint32_t amdgpu_cgs_read_ind_register(struct cgs_device *cgs_device, return RREG32_UVD_CTX(index); case CGS_IND_REG__DIDT: return RREG32_DIDT(index); + case CGS_IND_REG_GC_CAC: + return RREG32_GC_CAC(index); case CGS_IND_REG__AUDIO_ENDPT: DRM_ERROR("audio endpt register access not implemented.\n"); return 0; @@ -336,6 +338,8 @@ static void amdgpu_cgs_write_ind_register(struct cgs_device *cgs_device, return WREG32_UVD_CTX(index, value); case CGS_IND_REG__DIDT: return WREG32_DIDT(index, value); + case CGS_IND_REG_GC_CAC: + return WREG32_GC_CAC(index, value); case CGS_IND_REG__AUDIO_ENDPT: DRM_ERROR("audio endpt register access not implemented.\n"); return; @@ -696,6 +700,17 @@ static uint32_t fw_type_convert(struct cgs_device *cgs_device, uint32_t fw_type) return result; } +static int amdgpu_cgs_rel_firmware(struct cgs_device *cgs_device, enum cgs_ucode_id type) +{ + CGS_FUNC_ADEV; + if ((CGS_UCODE_ID_SMU == type) || (CGS_UCODE_ID_SMU_SK == type)) { + release_firmware(adev->pm.fw); + return 0; + } + /* cannot release other firmware because they are not created by cgs */ + return -EINVAL; +} + static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, enum cgs_ucode_id type, struct cgs_firmware_info *info) @@ -737,6 +752,9 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, if (!adev->pm.fw) { switch (adev->asic_type) { + case CHIP_TOPAZ: + strcpy(fw_name, "amdgpu/topaz_smc.bin"); + break; case CHIP_TONGA: strcpy(fw_name, "amdgpu/tonga_smc.bin"); break; @@ -776,6 +794,7 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, } hdr = (const struct smc_firmware_header_v1_0 *) adev->pm.fw->data; + amdgpu_ucode_print_smc_hdr(&hdr->header); adev->pm.fw_version = le32_to_cpu(hdr->header.ucode_version); ucode_size = le32_to_cpu(hdr->header.ucode_size_bytes); ucode_start_address = le32_to_cpu(hdr->ucode_start_addr); @@ -784,13 +803,14 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, info->version = adev->pm.fw_version; info->image_size = ucode_size; + info->ucode_start_address = ucode_start_address; info->kptr = (void *)src; } return 0; } static int amdgpu_cgs_query_system_info(struct cgs_device *cgs_device, - struct cgs_system_info *sys_info) + struct cgs_system_info *sys_info) { CGS_FUNC_ADEV; @@ -810,6 +830,12 @@ static int amdgpu_cgs_query_system_info(struct cgs_device *cgs_device, case CGS_SYSTEM_INFO_PCIE_MLW: sys_info->value = adev->pm.pcie_mlw_mask; break; + case CGS_SYSTEM_INFO_PCIE_DEV: + sys_info->value = adev->pdev->device; + break; + case CGS_SYSTEM_INFO_PCIE_REV: + sys_info->value = adev->pdev->revision; + break; case CGS_SYSTEM_INFO_CG_FLAGS: sys_info->value = adev->cg_flags; break; @@ -819,6 +845,9 @@ static int amdgpu_cgs_query_system_info(struct cgs_device *cgs_device, case CGS_SYSTEM_INFO_GFX_CU_INFO: sys_info->value = adev->gfx.cu_info.number; break; + case CGS_SYSTEM_INFO_GFX_SE_INFO: + sys_info->value = adev->gfx.config.max_shader_engines; + break; default: return -ENODEV; } @@ -892,14 +921,12 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device, acpi_handle handle; struct acpi_object_list input; struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; - union acpi_object *params = NULL; - union acpi_object *obj = NULL; + union acpi_object *params, *obj; uint8_t name[5] = {'\0'}; - struct cgs_acpi_method_argument *argument = NULL; + struct cgs_acpi_method_argument *argument; uint32_t i, count; acpi_status status; int result; - uint32_t func_no = 0xFFFFFFFF; handle = ACPI_HANDLE(&adev->pdev->dev); if (!handle) @@ -916,7 +943,6 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device, if (info->pinput_argument == NULL) return -EINVAL; argument = info->pinput_argument; - func_no = argument->value; for (i = 0; i < info->input_count; i++) { if (((argument->type == ACPI_TYPE_STRING) || (argument->type == ACPI_TYPE_BUFFER)) && @@ -961,11 +987,11 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device, params->integer.value = argument->value; break; case ACPI_TYPE_STRING: - params->string.length = argument->method_length; + params->string.length = argument->data_length; params->string.pointer = argument->pointer; break; case ACPI_TYPE_BUFFER: - params->buffer.length = argument->method_length; + params->buffer.length = argument->data_length; params->buffer.pointer = argument->pointer; break; default: @@ -985,7 +1011,7 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device, if (ACPI_FAILURE(status)) { result = -EIO; - goto error; + goto free_input; } /* return the output info */ @@ -995,7 +1021,7 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device, if ((obj->type != ACPI_TYPE_PACKAGE) || (obj->package.count != count)) { result = -EIO; - goto error; + goto free_obj; } params = obj->package.elements; } else @@ -1003,13 +1029,13 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device, if (params == NULL) { result = -EIO; - goto error; + goto free_obj; } for (i = 0; i < count; i++) { if (argument->type != params->type) { result = -EIO; - goto error; + goto free_obj; } switch (params->type) { case ACPI_TYPE_INTEGER: @@ -1019,7 +1045,7 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device, if ((params->string.length != argument->data_length) || (params->string.pointer == NULL)) { result = -EIO; - goto error; + goto free_obj; } strncpy(argument->pointer, params->string.pointer, @@ -1028,7 +1054,7 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device, case ACPI_TYPE_BUFFER: if (params->buffer.pointer == NULL) { result = -EIO; - goto error; + goto free_obj; } memcpy(argument->pointer, params->buffer.pointer, @@ -1041,9 +1067,10 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device, params++; } -error: - if (obj != NULL) - kfree(obj); + result = 0; +free_obj: + kfree(obj); +free_input: kfree((void *)input.pointer); return result; } @@ -1055,7 +1082,7 @@ static int amdgpu_cgs_acpi_eval_object(struct cgs_device *cgs_device, } #endif -int amdgpu_cgs_call_acpi_method(struct cgs_device *cgs_device, +static int amdgpu_cgs_call_acpi_method(struct cgs_device *cgs_device, uint32_t acpi_method, uint32_t acpi_function, void *pinput, void *poutput, @@ -1068,17 +1095,14 @@ int amdgpu_cgs_call_acpi_method(struct cgs_device *cgs_device, struct cgs_acpi_method_info info = {0}; acpi_input[0].type = CGS_ACPI_TYPE_INTEGER; - acpi_input[0].method_length = sizeof(uint32_t); acpi_input[0].data_length = sizeof(uint32_t); acpi_input[0].value = acpi_function; acpi_input[1].type = CGS_ACPI_TYPE_BUFFER; - acpi_input[1].method_length = CGS_ACPI_MAX_BUFFER_SIZE; acpi_input[1].data_length = input_size; acpi_input[1].pointer = pinput; acpi_output.type = CGS_ACPI_TYPE_BUFFER; - acpi_output.method_length = CGS_ACPI_MAX_BUFFER_SIZE; acpi_output.data_length = output_size; acpi_output.pointer = poutput; @@ -1125,6 +1149,7 @@ static const struct cgs_ops amdgpu_cgs_ops = { amdgpu_cgs_pm_query_clock_limits, amdgpu_cgs_set_camera_voltages, amdgpu_cgs_get_firmware_info, + amdgpu_cgs_rel_firmware, amdgpu_cgs_set_powergating_state, amdgpu_cgs_set_clockgating_state, amdgpu_cgs_get_active_displays_info, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index cb07da41152b..ff0b55a65ca3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -1690,7 +1690,6 @@ amdgpu_connector_add(struct amdgpu_device *adev, DRM_MODE_SCALE_NONE); /* no HPD on analog connectors */ amdgpu_connector->hpd.hpd = AMDGPU_HPD_NONE; - connector->polled = DRM_CONNECTOR_POLL_CONNECT; connector->interlace_allowed = true; connector->doublescan_allowed = true; break; @@ -1893,8 +1892,10 @@ amdgpu_connector_add(struct amdgpu_device *adev, } if (amdgpu_connector->hpd.hpd == AMDGPU_HPD_NONE) { - if (i2c_bus->valid) - connector->polled = DRM_CONNECTOR_POLL_CONNECT; + if (i2c_bus->valid) { + connector->polled = DRM_CONNECTOR_POLL_CONNECT | + DRM_CONNECTOR_POLL_DISCONNECT; + } } else connector->polled = DRM_CONNECTOR_POLL_HPD; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 9bc8f1d99733..0307ff5887c5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -216,11 +216,8 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data) if (ret) goto free_all_kdata; - if (p->uf_entry.robj) { - p->job->uf_bo = amdgpu_bo_ref(p->uf_entry.robj); - p->job->uf_offset = uf_offset; - } - + if (p->uf_entry.robj) + p->job->uf_addr = uf_offset; kfree(chunk_array); return 0; @@ -459,7 +456,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, list_splice(&need_pages, &p->validated); } - amdgpu_vm_get_pt_bos(&fpriv->vm, &duplicates); + amdgpu_vm_get_pt_bos(p->adev, &fpriv->vm, &duplicates); p->bytes_moved_threshold = amdgpu_cs_get_threshold_for_moves(p->adev); p->bytes_moved = 0; @@ -472,6 +469,9 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, if (r) goto error_validate; + fpriv->vm.last_eviction_counter = + atomic64_read(&p->adev->num_evictions); + if (p->bo_list) { struct amdgpu_bo *gds = p->bo_list->gds_obj; struct amdgpu_bo *gws = p->bo_list->gws_obj; @@ -499,6 +499,9 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, } } + if (p->uf_entry.robj) + p->job->uf_addr += amdgpu_bo_gpu_offset(p->uf_entry.robj); + error_validate: if (r) { amdgpu_vm_move_pt_bos_in_lru(p->adev, &fpriv->vm); @@ -653,18 +656,21 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev, /* Only for UVD/VCE VM emulation */ if (ring->funcs->parse_cs) { + p->job->vm = NULL; for (i = 0; i < p->job->num_ibs; i++) { r = amdgpu_ring_parse_cs(ring, p, i); if (r) return r; } + } else { + p->job->vm_pd_addr = amdgpu_bo_gpu_offset(vm->page_directory); + + r = amdgpu_bo_vm_update_pte(p, vm); + if (r) + return r; } - r = amdgpu_bo_vm_update_pte(p, vm); - if (!r) - amdgpu_cs_sync_rings(p); - - return r; + return amdgpu_cs_sync_rings(p); } static int amdgpu_cs_handle_lockup(struct amdgpu_device *adev, int r) @@ -761,7 +767,7 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev, } /* UVD & VCE fw doesn't support user fences */ - if (parser->job->uf_bo && ( + if (parser->job->uf_addr && ( parser->job->ring->type == AMDGPU_RING_TYPE_UVD || parser->job->ring->type == AMDGPU_RING_TYPE_VCE)) return -EINVAL; @@ -830,17 +836,13 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, { struct amdgpu_ring *ring = p->job->ring; struct amd_sched_entity *entity = &p->ctx->rings[ring->idx].entity; - struct fence *fence; struct amdgpu_job *job; int r; job = p->job; p->job = NULL; - r = amd_sched_job_init(&job->base, &ring->sched, - entity, amdgpu_job_timeout_func, - amdgpu_job_free_func, - p->filp, &fence); + r = amd_sched_job_init(&job->base, &ring->sched, entity, p->filp); if (r) { amdgpu_job_free(job); return r; @@ -848,9 +850,10 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, job->owner = p->filp; job->ctx = entity->fence_context; - p->fence = fence_get(fence); - cs->out.handle = amdgpu_ctx_add_fence(p->ctx, ring, fence); + p->fence = fence_get(&job->base.s_fence->finished); + cs->out.handle = amdgpu_ctx_add_fence(p->ctx, ring, p->fence); job->uf_sequence = cs->out.handle; + amdgpu_job_free_resources(job); trace_amdgpu_cs_ioctl(job); amd_sched_entity_push_job(&job->base); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index bb8b149786d7..df7ab2458e50 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -25,6 +25,7 @@ * Alex Deucher * Jerome Glisse */ +#include #include #include #include @@ -35,6 +36,7 @@ #include #include #include "amdgpu.h" +#include "amdgpu_trace.h" #include "amdgpu_i2c.h" #include "atom.h" #include "amdgpu_atombios.h" @@ -79,24 +81,27 @@ bool amdgpu_device_is_px(struct drm_device *dev) uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg, bool always_indirect) { + uint32_t ret; + if ((reg * 4) < adev->rmmio_size && !always_indirect) - return readl(((void __iomem *)adev->rmmio) + (reg * 4)); + ret = readl(((void __iomem *)adev->rmmio) + (reg * 4)); else { unsigned long flags; - uint32_t ret; spin_lock_irqsave(&adev->mmio_idx_lock, flags); writel((reg * 4), ((void __iomem *)adev->rmmio) + (mmMM_INDEX * 4)); ret = readl(((void __iomem *)adev->rmmio) + (mmMM_DATA * 4)); spin_unlock_irqrestore(&adev->mmio_idx_lock, flags); - - return ret; } + trace_amdgpu_mm_rreg(adev->pdev->device, reg, ret); + return ret; } void amdgpu_mm_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v, bool always_indirect) { + trace_amdgpu_mm_wreg(adev->pdev->device, reg, v); + if ((reg * 4) < adev->rmmio_size && !always_indirect) writel(v, ((void __iomem *)adev->rmmio) + (reg * 4)); else { @@ -827,8 +832,10 @@ static uint32_t cail_ioreg_read(struct card_info *info, uint32_t reg) */ static void amdgpu_atombios_fini(struct amdgpu_device *adev) { - if (adev->mode_info.atom_context) + if (adev->mode_info.atom_context) { kfree(adev->mode_info.atom_context->scratch); + kfree(adev->mode_info.atom_context->iio); + } kfree(adev->mode_info.atom_context); adev->mode_info.atom_context = NULL; kfree(adev->mode_info.atom_card_info); @@ -1068,11 +1075,14 @@ int amdgpu_set_clockgating_state(struct amdgpu_device *adev, int i, r = 0; for (i = 0; i < adev->num_ip_blocks; i++) { + if (!adev->ip_block_status[i].valid) + continue; if (adev->ip_blocks[i].type == block_type) { r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev, state); if (r) return r; + break; } } return r; @@ -1085,16 +1095,53 @@ int amdgpu_set_powergating_state(struct amdgpu_device *adev, int i, r = 0; for (i = 0; i < adev->num_ip_blocks; i++) { + if (!adev->ip_block_status[i].valid) + continue; if (adev->ip_blocks[i].type == block_type) { r = adev->ip_blocks[i].funcs->set_powergating_state((void *)adev, state); if (r) return r; + break; } } return r; } +int amdgpu_wait_for_idle(struct amdgpu_device *adev, + enum amd_ip_block_type block_type) +{ + int i, r; + + for (i = 0; i < adev->num_ip_blocks; i++) { + if (!adev->ip_block_status[i].valid) + continue; + if (adev->ip_blocks[i].type == block_type) { + r = adev->ip_blocks[i].funcs->wait_for_idle((void *)adev); + if (r) + return r; + break; + } + } + return 0; + +} + +bool amdgpu_is_idle(struct amdgpu_device *adev, + enum amd_ip_block_type block_type) +{ + int i; + + for (i = 0; i < adev->num_ip_blocks; i++) { + if (!adev->ip_block_status[i].valid) + continue; + if (adev->ip_blocks[i].type == block_type) + return adev->ip_blocks[i].funcs->is_idle((void *)adev); + } + return true; + +} + const struct amdgpu_ip_block_version * amdgpu_get_ip_block( struct amdgpu_device *adev, enum amd_ip_block_type type) @@ -1207,6 +1254,9 @@ static int amdgpu_early_init(struct amdgpu_device *adev) } } + adev->cg_flags &= amdgpu_cg_mask; + adev->pg_flags &= amdgpu_pg_mask; + return 0; } @@ -1325,6 +1375,11 @@ static int amdgpu_fini(struct amdgpu_device *adev) adev->ip_block_status[i].valid = false; } + for (i = adev->num_ip_blocks - 1; i >= 0; i--) { + if (adev->ip_blocks[i].funcs->late_fini) + adev->ip_blocks[i].funcs->late_fini((void *)adev); + } + return 0; } @@ -1378,6 +1433,15 @@ static int amdgpu_resume(struct amdgpu_device *adev) return 0; } +static bool amdgpu_device_is_virtual(void) +{ +#ifdef CONFIG_X86 + return boot_cpu_has(X86_FEATURE_HYPERVISOR); +#else + return false; +#endif +} + /** * amdgpu_device_init - initialize the driver * @@ -1424,9 +1488,12 @@ int amdgpu_device_init(struct amdgpu_device *adev, adev->uvd_ctx_wreg = &amdgpu_invalid_wreg; adev->didt_rreg = &amdgpu_invalid_rreg; adev->didt_wreg = &amdgpu_invalid_wreg; + adev->gc_cac_rreg = &amdgpu_invalid_rreg; + adev->gc_cac_wreg = &amdgpu_invalid_wreg; adev->audio_endpt_rreg = &amdgpu_block_invalid_rreg; adev->audio_endpt_wreg = &amdgpu_block_invalid_wreg; + DRM_INFO("initializing kernel modesetting (%s 0x%04X:0x%04X 0x%04X:0x%04X 0x%02X).\n", amdgpu_asic_name[adev->asic_type], pdev->vendor, pdev->device, pdev->subsystem_vendor, pdev->subsystem_device, pdev->revision); @@ -1451,6 +1518,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, spin_lock_init(&adev->pcie_idx_lock); spin_lock_init(&adev->uvd_ctx_idx_lock); spin_lock_init(&adev->didt_idx_lock); + spin_lock_init(&adev->gc_cac_idx_lock); spin_lock_init(&adev->audio_endpt_idx_lock); adev->rmmio_base = pci_resource_start(adev->pdev, 5); @@ -1495,29 +1563,38 @@ int amdgpu_device_init(struct amdgpu_device *adev, vga_switcheroo_init_domain_pm_ops(adev->dev, &adev->vga_pm_domain); /* Read BIOS */ - if (!amdgpu_get_bios(adev)) - return -EINVAL; + if (!amdgpu_get_bios(adev)) { + r = -EINVAL; + goto failed; + } /* Must be an ATOMBIOS */ if (!adev->is_atom_bios) { dev_err(adev->dev, "Expecting atombios for GPU\n"); - return -EINVAL; + r = -EINVAL; + goto failed; } r = amdgpu_atombios_init(adev); if (r) { dev_err(adev->dev, "amdgpu_atombios_init failed\n"); - return r; + goto failed; } /* See if the asic supports SR-IOV */ adev->virtualization.supports_sr_iov = amdgpu_atombios_has_gpu_virtualization_table(adev); + /* Check if we are executing in a virtualized environment */ + adev->virtualization.is_virtual = amdgpu_device_is_virtual(); + adev->virtualization.caps = amdgpu_asic_get_virtual_caps(adev); + /* Post card if necessary */ if (!amdgpu_card_posted(adev) || - adev->virtualization.supports_sr_iov) { + (adev->virtualization.is_virtual && + !(adev->virtualization.caps & AMDGPU_VIRT_CAPS_SRIOV_EN))) { if (!adev->bios) { dev_err(adev->dev, "Card not posted and no BIOS - ignoring\n"); - return -EINVAL; + r = -EINVAL; + goto failed; } DRM_INFO("GPU not posted. posting now...\n"); amdgpu_atom_asic_init(adev->mode_info.atom_context); @@ -1527,7 +1604,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, r = amdgpu_atombios_get_clock_info(adev); if (r) { dev_err(adev->dev, "amdgpu_atombios_get_clock_info failed\n"); - return r; + goto failed; } /* init i2c buses */ amdgpu_atombios_i2c_init(adev); @@ -1536,7 +1613,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, r = amdgpu_fence_driver_init(adev); if (r) { dev_err(adev->dev, "amdgpu_fence_driver_init failed\n"); - return r; + goto failed; } /* init the mode config */ @@ -1546,7 +1623,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, if (r) { dev_err(adev->dev, "amdgpu_init failed\n"); amdgpu_fini(adev); - return r; + goto failed; } adev->accel_working = true; @@ -1556,7 +1633,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, r = amdgpu_ib_pool_init(adev); if (r) { dev_err(adev->dev, "IB initialization failed (%d).\n", r); - return r; + goto failed; } r = amdgpu_ib_ring_tests(adev); @@ -1573,6 +1650,12 @@ int amdgpu_device_init(struct amdgpu_device *adev, DRM_ERROR("registering register debugfs failed (%d).\n", r); } + r = amdgpu_debugfs_firmware_init(adev); + if (r) { + DRM_ERROR("registering firmware debugfs failed (%d).\n", r); + return r; + } + if ((amdgpu_testing & 1)) { if (adev->accel_working) amdgpu_test_moves(adev); @@ -1598,10 +1681,15 @@ int amdgpu_device_init(struct amdgpu_device *adev, r = amdgpu_late_init(adev); if (r) { dev_err(adev->dev, "amdgpu_late_init failed\n"); - return r; + goto failed; } return 0; + +failed: + if (runtime) + vga_switcheroo_fini_domain_pm_ops(adev->dev); + return r; } static void amdgpu_debugfs_remove_files(struct amdgpu_device *adev); @@ -1624,6 +1712,7 @@ void amdgpu_device_fini(struct amdgpu_device *adev) amdgpu_bo_evict_vram(adev); amdgpu_ib_pool_fini(adev); amdgpu_fence_driver_fini(adev); + drm_crtc_force_disable_all(adev->ddev); amdgpu_fbdev_fini(adev); r = amdgpu_fini(adev); kfree(adev->ip_block_status); @@ -1635,6 +1724,8 @@ void amdgpu_device_fini(struct amdgpu_device *adev) kfree(adev->bios); adev->bios = NULL; vga_switcheroo_unregister_client(adev->pdev); + if (adev->flags & AMD_IS_PX) + vga_switcheroo_fini_domain_pm_ops(adev->dev); vga_client_register(adev->pdev, NULL, NULL, NULL); if (adev->rio_mem) pci_iounmap(adev->pdev, adev->rio_mem); @@ -1820,7 +1911,23 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon) } drm_kms_helper_poll_enable(dev); + + /* + * Most of the connector probing functions try to acquire runtime pm + * refs to ensure that the GPU is powered on when connector polling is + * performed. Since we're calling this from a runtime PM callback, + * trying to acquire rpm refs will cause us to deadlock. + * + * Since we're guaranteed to be holding the rpm lock, it's safe to + * temporarily disable the rpm helpers so this doesn't deadlock us. + */ +#ifdef CONFIG_PM + dev->dev->power.disable_depth++; +#endif drm_helper_hpd_irq_event(dev); +#ifdef CONFIG_PM + dev->dev->power.disable_depth--; +#endif if (fbcon) { amdgpu_fbdev_set_suspend(adev, 0); @@ -1840,11 +1947,6 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon) */ int amdgpu_gpu_reset(struct amdgpu_device *adev) { - unsigned ring_sizes[AMDGPU_MAX_RINGS]; - uint32_t *ring_data[AMDGPU_MAX_RINGS]; - - bool saved = false; - int i, r; int resched; @@ -1853,22 +1955,30 @@ int amdgpu_gpu_reset(struct amdgpu_device *adev) /* block TTM */ resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev); - r = amdgpu_suspend(adev); - + /* block scheduler */ for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { struct amdgpu_ring *ring = adev->rings[i]; + if (!ring) continue; - - ring_sizes[i] = amdgpu_ring_backup(ring, &ring_data[i]); - if (ring_sizes[i]) { - saved = true; - dev_info(adev->dev, "Saved %d dwords of commands " - "on ring %d.\n", ring_sizes[i], i); - } + kthread_park(ring->sched.thread); + amd_sched_hw_job_reset(&ring->sched); } + /* after all hw jobs are reset, hw fence is meaningless, so force_completion */ + amdgpu_fence_driver_force_completion(adev); + + /* save scratch */ + amdgpu_atombios_scratch_regs_save(adev); + r = amdgpu_suspend(adev); retry: + /* Disable fb access */ + if (adev->mode_info.num_crtc) { + struct amdgpu_mode_mc_save save; + amdgpu_display_stop_mc_access(adev, &save); + amdgpu_wait_for_idle(adev, AMD_IP_BLOCK_TYPE_GMC); + } + r = amdgpu_asic_reset(adev); /* post card */ amdgpu_atom_asic_init(adev->mode_info.atom_context); @@ -1877,32 +1987,29 @@ int amdgpu_gpu_reset(struct amdgpu_device *adev) dev_info(adev->dev, "GPU reset succeeded, trying to resume\n"); r = amdgpu_resume(adev); } - + /* restore scratch */ + amdgpu_atombios_scratch_regs_restore(adev); if (!r) { + r = amdgpu_ib_ring_tests(adev); + if (r) { + dev_err(adev->dev, "ib ring test failed (%d).\n", r); + r = amdgpu_suspend(adev); + goto retry; + } + for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { struct amdgpu_ring *ring = adev->rings[i]; if (!ring) continue; - - amdgpu_ring_restore(ring, ring_sizes[i], ring_data[i]); - ring_sizes[i] = 0; - ring_data[i] = NULL; - } - - r = amdgpu_ib_ring_tests(adev); - if (r) { - dev_err(adev->dev, "ib ring test failed (%d).\n", r); - if (saved) { - saved = false; - r = amdgpu_suspend(adev); - goto retry; - } + amd_sched_job_recovery(&ring->sched); + kthread_unpark(ring->sched.thread); } } else { - amdgpu_fence_driver_force_completion(adev); + dev_err(adev->dev, "asic resume failed (%d).\n", r); for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { - if (adev->rings[i]) - kfree(ring_data[i]); + if (adev->rings[i]) { + kthread_unpark(adev->rings[i]->sched.thread); + } } } @@ -1913,13 +2020,11 @@ int amdgpu_gpu_reset(struct amdgpu_device *adev) /* bad news, how to tell it to userspace ? */ dev_info(adev->dev, "GPU reset failed\n"); } + amdgpu_irq_gpu_reset_resume_helper(adev); return r; } -#define AMDGPU_DEFAULT_PCIE_GEN_MASK 0x30007 /* gen: chipset 1/2, asic 1/2/3 */ -#define AMDGPU_DEFAULT_PCIE_MLW_MASK 0x2f0000 /* 1/2/4/8/16 lanes */ - void amdgpu_get_pcie_info(struct amdgpu_device *adev) { u32 mask; @@ -2073,20 +2178,43 @@ static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf, struct amdgpu_device *adev = f->f_inode->i_private; ssize_t result = 0; int r; + bool use_bank; + unsigned instance_bank, sh_bank, se_bank; if (size & 0x3 || *pos & 0x3) return -EINVAL; + if (*pos & (1ULL << 62)) { + se_bank = (*pos >> 24) & 0x3FF; + sh_bank = (*pos >> 34) & 0x3FF; + instance_bank = (*pos >> 44) & 0x3FF; + use_bank = 1; + *pos &= 0xFFFFFF; + } else { + use_bank = 0; + } + + if (use_bank) { + if (sh_bank >= adev->gfx.config.max_sh_per_se || + se_bank >= adev->gfx.config.max_shader_engines) + return -EINVAL; + mutex_lock(&adev->grbm_idx_mutex); + amdgpu_gfx_select_se_sh(adev, se_bank, + sh_bank, instance_bank); + } + while (size) { uint32_t value; if (*pos > adev->rmmio_size) - return result; + goto end; value = RREG32(*pos >> 2); r = put_user(value, (uint32_t *)buf); - if (r) - return r; + if (r) { + result = r; + goto end; + } result += 4; buf += 4; @@ -2094,6 +2222,12 @@ static ssize_t amdgpu_debugfs_regs_read(struct file *f, char __user *buf, size -= 4; } +end: + if (use_bank) { + amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); + mutex_unlock(&adev->grbm_idx_mutex); + } + return result; } @@ -2293,6 +2427,68 @@ static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user * return result; } +static ssize_t amdgpu_debugfs_gca_config_read(struct file *f, char __user *buf, + size_t size, loff_t *pos) +{ + struct amdgpu_device *adev = f->f_inode->i_private; + ssize_t result = 0; + int r; + uint32_t *config, no_regs = 0; + + if (size & 0x3 || *pos & 0x3) + return -EINVAL; + + config = kmalloc(256 * sizeof(*config), GFP_KERNEL); + if (!config) + return -ENOMEM; + + /* version, increment each time something is added */ + config[no_regs++] = 0; + config[no_regs++] = adev->gfx.config.max_shader_engines; + config[no_regs++] = adev->gfx.config.max_tile_pipes; + config[no_regs++] = adev->gfx.config.max_cu_per_sh; + config[no_regs++] = adev->gfx.config.max_sh_per_se; + config[no_regs++] = adev->gfx.config.max_backends_per_se; + config[no_regs++] = adev->gfx.config.max_texture_channel_caches; + config[no_regs++] = adev->gfx.config.max_gprs; + config[no_regs++] = adev->gfx.config.max_gs_threads; + config[no_regs++] = adev->gfx.config.max_hw_contexts; + config[no_regs++] = adev->gfx.config.sc_prim_fifo_size_frontend; + config[no_regs++] = adev->gfx.config.sc_prim_fifo_size_backend; + config[no_regs++] = adev->gfx.config.sc_hiz_tile_fifo_size; + config[no_regs++] = adev->gfx.config.sc_earlyz_tile_fifo_size; + config[no_regs++] = adev->gfx.config.num_tile_pipes; + config[no_regs++] = adev->gfx.config.backend_enable_mask; + config[no_regs++] = adev->gfx.config.mem_max_burst_length_bytes; + config[no_regs++] = adev->gfx.config.mem_row_size_in_kb; + config[no_regs++] = adev->gfx.config.shader_engine_tile_size; + config[no_regs++] = adev->gfx.config.num_gpus; + config[no_regs++] = adev->gfx.config.multi_gpu_tile_size; + config[no_regs++] = adev->gfx.config.mc_arb_ramcfg; + config[no_regs++] = adev->gfx.config.gb_addr_config; + config[no_regs++] = adev->gfx.config.num_rbs; + + while (size && (*pos < no_regs * 4)) { + uint32_t value; + + value = config[*pos >> 2]; + r = put_user(value, (uint32_t *)buf); + if (r) { + kfree(config); + return r; + } + + result += 4; + buf += 4; + *pos += 4; + size -= 4; + } + + kfree(config); + return result; +} + + static const struct file_operations amdgpu_debugfs_regs_fops = { .owner = THIS_MODULE, .read = amdgpu_debugfs_regs_read, @@ -2318,11 +2514,18 @@ static const struct file_operations amdgpu_debugfs_regs_smc_fops = { .llseek = default_llseek }; +static const struct file_operations amdgpu_debugfs_gca_config_fops = { + .owner = THIS_MODULE, + .read = amdgpu_debugfs_gca_config_read, + .llseek = default_llseek +}; + static const struct file_operations *debugfs_regs[] = { &amdgpu_debugfs_regs_fops, &amdgpu_debugfs_regs_didt_fops, &amdgpu_debugfs_regs_pcie_fops, &amdgpu_debugfs_regs_smc_fops, + &amdgpu_debugfs_gca_config_fops, }; static const char *debugfs_regs_names[] = { @@ -2330,6 +2533,7 @@ static const char *debugfs_regs_names[] = { "amdgpu_regs_didt", "amdgpu_regs_pcie", "amdgpu_regs_smc", + "amdgpu_gca_config", }; static int amdgpu_debugfs_regs_init(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index a6eecf6f9065..76f96028313d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -122,7 +122,7 @@ static void amdgpu_flip_work_func(struct work_struct *__work) spin_unlock_irqrestore(&crtc->dev->event_lock, flags); usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); - }; + } if (!repcnt) DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, " @@ -220,19 +220,17 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc, r = amdgpu_bo_pin_restricted(new_rbo, AMDGPU_GEM_DOMAIN_VRAM, 0, 0, &base); if (unlikely(r != 0)) { - amdgpu_bo_unreserve(new_rbo); r = -EINVAL; DRM_ERROR("failed to pin new rbo buffer before flip\n"); - goto cleanup; + goto unreserve; } r = reservation_object_get_fences_rcu(new_rbo->tbo.resv, &work->excl, &work->shared_count, &work->shared); if (unlikely(r != 0)) { - amdgpu_bo_unreserve(new_rbo); DRM_ERROR("failed to get fences for buffer\n"); - goto cleanup; + goto unpin; } amdgpu_bo_get_tiling_flags(new_rbo, &tiling_flags); @@ -275,9 +273,11 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc, DRM_ERROR("failed to reserve new rbo in error path\n"); goto cleanup; } +unpin: if (unlikely(amdgpu_bo_unpin(new_rbo) != 0)) { DRM_ERROR("failed to unpin new rbo in error path\n"); } +unreserve: amdgpu_bo_unreserve(new_rbo); cleanup: @@ -516,9 +516,7 @@ static void amdgpu_user_framebuffer_destroy(struct drm_framebuffer *fb) { struct amdgpu_framebuffer *amdgpu_fb = to_amdgpu_framebuffer(fb); - if (amdgpu_fb->obj) { - drm_gem_object_unreference_unlocked(amdgpu_fb->obj); - } + drm_gem_object_unreference_unlocked(amdgpu_fb->obj); drm_framebuffer_cleanup(fb); kfree(amdgpu_fb); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index f888c015f76c..9aa533cf4ad1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -52,9 +52,10 @@ * - 3.1.0 - allow reading more status registers (GRBM, SRBM, SDMA, CP) * - 3.2.0 - GFX8: Uses EOP_TC_WB_ACTION_EN, so UMDs don't have to do the same * at the end of IBs. + * - 3.3.0 - Add VM support for UVD on supported hardware. */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 2 +#define KMS_DRIVER_MINOR 3 #define KMS_DRIVER_PATCHLEVEL 0 int amdgpu_vram_limit = 0; @@ -82,8 +83,12 @@ int amdgpu_exp_hw_support = 0; int amdgpu_sched_jobs = 32; int amdgpu_sched_hw_submission = 2; int amdgpu_powerplay = -1; +int amdgpu_powercontainment = 1; unsigned amdgpu_pcie_gen_cap = 0; unsigned amdgpu_pcie_lane_cap = 0; +unsigned amdgpu_cg_mask = 0xffffffff; +unsigned amdgpu_pg_mask = 0xffffffff; +char *amdgpu_disable_cu = NULL; MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes"); module_param_named(vramlimit, amdgpu_vram_limit, int, 0600); @@ -160,6 +165,9 @@ module_param_named(sched_hw_submission, amdgpu_sched_hw_submission, int, 0444); #ifdef CONFIG_DRM_AMD_POWERPLAY MODULE_PARM_DESC(powerplay, "Powerplay component (1 = enable, 0 = disable, -1 = auto (default))"); module_param_named(powerplay, amdgpu_powerplay, int, 0444); + +MODULE_PARM_DESC(powercontainment, "Power Containment (1 = enable (default), 0 = disable)"); +module_param_named(powercontainment, amdgpu_powercontainment, int, 0444); #endif MODULE_PARM_DESC(pcie_gen_cap, "PCIE Gen Caps (0: autodetect (default))"); @@ -168,6 +176,15 @@ module_param_named(pcie_gen_cap, amdgpu_pcie_gen_cap, uint, 0444); MODULE_PARM_DESC(pcie_lane_cap, "PCIE Lane Caps (0: autodetect (default))"); module_param_named(pcie_lane_cap, amdgpu_pcie_lane_cap, uint, 0444); +MODULE_PARM_DESC(cg_mask, "Clockgating flags mask (0 = disable clock gating)"); +module_param_named(cg_mask, amdgpu_cg_mask, uint, 0444); + +MODULE_PARM_DESC(pg_mask, "Powergating flags mask (0 = disable power gating)"); +module_param_named(pg_mask, amdgpu_pg_mask, uint, 0444); + +MODULE_PARM_DESC(disable_cu, "Disable CUs (se.sh.cu,...)"); +module_param_named(disable_cu, amdgpu_disable_cu, charp, 0444); + static const struct pci_device_id pciidlist[] = { #ifdef CONFIG_DRM_AMDGPU_CIK /* Kaveri */ @@ -413,7 +430,10 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev) pci_save_state(pdev); pci_disable_device(pdev); pci_ignore_hotplug(pdev); - pci_set_power_state(pdev, PCI_D3cold); + if (amdgpu_is_atpx_hybrid()) + pci_set_power_state(pdev, PCI_D3cold); + else if (!amdgpu_has_atpx_dgpu_power_cntl()) + pci_set_power_state(pdev, PCI_D3hot); drm_dev->switch_power_state = DRM_SWITCH_POWER_DYNAMIC_OFF; return 0; @@ -430,7 +450,9 @@ static int amdgpu_pmops_runtime_resume(struct device *dev) drm_dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; - pci_set_power_state(pdev, PCI_D0); + if (amdgpu_is_atpx_hybrid() || + !amdgpu_has_atpx_dgpu_power_cntl()) + pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); ret = pci_enable_device(pdev); if (ret) @@ -515,7 +537,7 @@ static struct drm_driver kms_driver = { .driver_features = DRIVER_USE_AGP | DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM | - DRIVER_PRIME | DRIVER_RENDER, + DRIVER_PRIME | DRIVER_RENDER | DRIVER_MODESET, .dev_priv_size = 0, .load = amdgpu_driver_load_kms, .open = amdgpu_driver_open_kms, @@ -590,7 +612,6 @@ static int __init amdgpu_init(void) DRM_INFO("amdgpu kernel modesetting enabled.\n"); driver = &kms_driver; pdriver = &amdgpu_kms_pci_driver; - driver->driver_features |= DRIVER_MODESET; driver->num_ioctls = amdgpu_max_kms_ioctl; amdgpu_register_atpx_handler(); /* let modprobe override vga console setting */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index d1558768cfb7..0b109aebfec6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -204,16 +204,25 @@ void amdgpu_fence_process(struct amdgpu_ring *ring) if (seq != ring->fence_drv.sync_seq) amdgpu_fence_schedule_fallback(ring); - while (last_seq != seq) { + if (unlikely(seq == last_seq)) + return; + + last_seq &= drv->num_fences_mask; + seq &= drv->num_fences_mask; + + do { struct fence *fence, **ptr; - ptr = &drv->fences[++last_seq & drv->num_fences_mask]; + ++last_seq; + last_seq &= drv->num_fences_mask; + ptr = &drv->fences[last_seq]; /* There is always exactly one thread signaling this fence slot */ fence = rcu_dereference_protected(*ptr, 1); RCU_INIT_POINTER(*ptr, NULL); - BUG_ON(!fence); + if (!fence) + continue; r = fence_signal(fence); if (!r) @@ -222,7 +231,7 @@ void amdgpu_fence_process(struct amdgpu_ring *ring) BUG(); fence_put(fence); - } + } while (last_seq != seq); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 8fab6486064f..88fbed2389c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -503,7 +503,7 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev, if (r) goto error_print; - amdgpu_vm_get_pt_bos(bo_va->vm, &duplicates); + amdgpu_vm_get_pt_bos(adev, bo_va->vm, &duplicates); list_for_each_entry(entry, &list, head) { domain = amdgpu_mem_type_to_domain(entry->bo->mem.mem_type); /* if anything is swapped out don't swap it in here, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 9f95da4f0536..a074edd95c70 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -70,3 +70,47 @@ void amdgpu_gfx_scratch_free(struct amdgpu_device *adev, uint32_t reg) } } } + +/** + * amdgpu_gfx_parse_disable_cu - Parse the disable_cu module parameter + * + * @mask: array in which the per-shader array disable masks will be stored + * @max_se: number of SEs + * @max_sh: number of SHs + * + * The bitmask of CUs to be disabled in the shader array determined by se and + * sh is stored in mask[se * max_sh + sh]. + */ +void amdgpu_gfx_parse_disable_cu(unsigned *mask, unsigned max_se, unsigned max_sh) +{ + unsigned se, sh, cu; + const char *p; + + memset(mask, 0, sizeof(*mask) * max_se * max_sh); + + if (!amdgpu_disable_cu || !*amdgpu_disable_cu) + return; + + p = amdgpu_disable_cu; + for (;;) { + char *next; + int ret = sscanf(p, "%u.%u.%u", &se, &sh, &cu); + if (ret < 3) { + DRM_ERROR("amdgpu: could not parse disable_cu\n"); + return; + } + + if (se < max_se && sh < max_sh && cu < 16) { + DRM_INFO("amdgpu: disabling CU %u.%u.%u\n", se, sh, cu); + mask[se * max_sh + sh] |= 1u << cu; + } else { + DRM_ERROR("amdgpu: disable_cu %u.%u.%u is out of range\n", + se, sh, cu); + } + + next = strchr(p, ','); + if (!next) + break; + p = next + 1; + } +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h index dc06cbda7be6..51321e154c09 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h @@ -27,4 +27,6 @@ int amdgpu_gfx_scratch_get(struct amdgpu_device *adev, uint32_t *reg); void amdgpu_gfx_scratch_free(struct amdgpu_device *adev, uint32_t reg); +unsigned amdgpu_gfx_parse_disable_cu(unsigned *mask, unsigned max_se, unsigned max_sh); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index 34e35423b78e..a31d7ef3032c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -33,6 +33,8 @@ #include "amdgpu.h" #include "atom.h" +#define AMDGPU_IB_TEST_TIMEOUT msecs_to_jiffies(1000) + /* * IB * IBs (Indirect Buffers) and areas of GPU accessible memory where @@ -122,7 +124,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, bool skip_preamble, need_ctx_switch; unsigned patch_offset = ~0; struct amdgpu_vm *vm; - struct fence *hwf; uint64_t ctx; unsigned i; @@ -160,10 +161,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, patch_offset = amdgpu_ring_init_cond_exec(ring); if (vm) { - r = amdgpu_vm_flush(ring, job->vm_id, job->vm_pd_addr, - job->gds_base, job->gds_size, - job->gws_base, job->gws_size, - job->oa_base, job->oa_size); + r = amdgpu_vm_flush(ring, job); if (r) { amdgpu_ring_undo(ring); return r; @@ -193,7 +191,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, if (ring->funcs->emit_hdp_invalidate) amdgpu_ring_emit_hdp_invalidate(ring); - r = amdgpu_fence_emit(ring, &hwf); + r = amdgpu_fence_emit(ring, f); if (r) { dev_err(adev->dev, "failed to emit fence (%d)\n", r); if (job && job->vm_id) @@ -203,17 +201,11 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, } /* wrap the last IB with fence */ - if (job && job->uf_bo) { - uint64_t addr = amdgpu_bo_gpu_offset(job->uf_bo); - - addr += job->uf_offset; - amdgpu_ring_emit_fence(ring, addr, job->uf_sequence, + if (job && job->uf_addr) { + amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence, AMDGPU_FENCE_FLAG_64BIT); } - if (f) - *f = fence_get(hwf); - if (patch_offset != ~0 && ring->funcs->patch_cond_exec) amdgpu_ring_patch_cond_exec(ring, patch_offset); @@ -296,7 +288,7 @@ int amdgpu_ib_ring_tests(struct amdgpu_device *adev) if (!ring || !ring->ready) continue; - r = amdgpu_ring_test_ib(ring); + r = amdgpu_ring_test_ib(ring, AMDGPU_IB_TEST_TIMEOUT); if (r) { ring->ready = false; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index 835a3fa8d8df..278708f5a744 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -383,6 +383,18 @@ int amdgpu_irq_update(struct amdgpu_device *adev, return r; } +void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev) +{ + int i, j; + for (i = 0; i < AMDGPU_MAX_IRQ_SRC_ID; i++) { + struct amdgpu_irq_src *src = adev->irq.sources[i]; + if (!src) + continue; + for (j = 0; j < src->num_types; j++) + amdgpu_irq_update(adev, src, j); + } +} + /** * amdgpu_irq_get - enable interrupt * diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h index e124b59f39c1..7ef09352e534 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.h @@ -94,6 +94,7 @@ int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src, unsigned type); bool amdgpu_irq_enabled(struct amdgpu_device *adev, struct amdgpu_irq_src *src, unsigned type); +void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev); int amdgpu_irq_add_domain(struct amdgpu_device *adev); void amdgpu_irq_remove_domain(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index f0dafa514fe4..6674d40eb3ab 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -28,21 +28,15 @@ #include "amdgpu.h" #include "amdgpu_trace.h" -static void amdgpu_job_free_handler(struct work_struct *ws) +static void amdgpu_job_timedout(struct amd_sched_job *s_job) { - struct amdgpu_job *job = container_of(ws, struct amdgpu_job, base.work_free_job); - amd_sched_job_put(&job->base); -} + struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base); -void amdgpu_job_timeout_func(struct work_struct *work) -{ - struct amdgpu_job *job = container_of(work, struct amdgpu_job, base.work_tdr.work); DRM_ERROR("ring %s timeout, last signaled seq=%u, last emitted seq=%u\n", - job->base.sched->name, - (uint32_t)atomic_read(&job->ring->fence_drv.last_seq), - job->ring->fence_drv.sync_seq); - - amd_sched_job_put(&job->base); + job->base.sched->name, + atomic_read(&job->ring->fence_drv.last_seq), + job->ring->fence_drv.sync_seq); + amdgpu_gpu_reset(job->adev); } int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs, @@ -63,7 +57,6 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs, (*job)->vm = vm; (*job)->ibs = (void *)&(*job)[1]; (*job)->num_ibs = num_ibs; - INIT_WORK(&(*job)->base.work_free_job, amdgpu_job_free_handler); amdgpu_sync_create(&(*job)->sync); @@ -86,27 +79,33 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size, return r; } -void amdgpu_job_free(struct amdgpu_job *job) +void amdgpu_job_free_resources(struct amdgpu_job *job) { - unsigned i; struct fence *f; + unsigned i; + /* use sched fence if available */ - f = (job->base.s_fence)? &job->base.s_fence->base : job->fence; + f = job->base.s_fence ? &job->base.s_fence->finished : job->fence; for (i = 0; i < job->num_ibs; ++i) - amdgpu_sa_bo_free(job->adev, &job->ibs[i].sa_bo, f); - fence_put(job->fence); - - amdgpu_bo_unref(&job->uf_bo); - amdgpu_sync_free(&job->sync); - - if (!job->base.use_sched) - kfree(job); + amdgpu_ib_free(job->adev, &job->ibs[i], f); } -void amdgpu_job_free_func(struct kref *refcount) +void amdgpu_job_free_cb(struct amd_sched_job *s_job) { - struct amdgpu_job *job = container_of(refcount, struct amdgpu_job, base.refcount); + struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base); + + fence_put(job->fence); + amdgpu_sync_free(&job->sync); + kfree(job); +} + +void amdgpu_job_free(struct amdgpu_job *job) +{ + amdgpu_job_free_resources(job); + + fence_put(job->fence); + amdgpu_sync_free(&job->sync); kfree(job); } @@ -114,22 +113,20 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring, struct amd_sched_entity *entity, void *owner, struct fence **f) { - struct fence *fence; int r; job->ring = ring; if (!f) return -EINVAL; - r = amd_sched_job_init(&job->base, &ring->sched, - entity, amdgpu_job_timeout_func, - amdgpu_job_free_func, owner, &fence); + r = amd_sched_job_init(&job->base, &ring->sched, entity, owner); if (r) return r; job->owner = owner; job->ctx = entity->fence_context; - *f = fence_get(fence); + *f = fence_get(&job->base.s_fence->finished); + amdgpu_job_free_resources(job); amd_sched_entity_push_job(&job->base); return 0; @@ -147,8 +144,8 @@ static struct fence *amdgpu_job_dependency(struct amd_sched_job *sched_job) int r; r = amdgpu_vm_grab_id(vm, ring, &job->sync, - &job->base.s_fence->base, - &job->vm_id, &job->vm_pd_addr); + &job->base.s_fence->finished, + job); if (r) DRM_ERROR("Error getting VM ID (%d)\n", r); @@ -170,29 +167,24 @@ static struct fence *amdgpu_job_run(struct amd_sched_job *sched_job) } job = to_amdgpu_job(sched_job); - r = amdgpu_sync_wait(&job->sync); - if (r) { - DRM_ERROR("failed to sync wait (%d)\n", r); - return NULL; - } + BUG_ON(amdgpu_sync_peek_fence(&job->sync, NULL)); trace_amdgpu_sched_run_job(job); r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs, job->sync.last_vm_update, job, &fence); - if (r) { + if (r) DRM_ERROR("Error scheduling IBs (%d)\n", r); - goto err; - } -err: - job->fence = fence; - amdgpu_job_free(job); + /* if gpu reset, hw fence will be replaced here */ + fence_put(job->fence); + job->fence = fence_get(fence); + amdgpu_job_free_resources(job); return fence; } const struct amd_sched_backend_ops amdgpu_sched_ops = { .dependency = amdgpu_job_dependency, .run_job = amdgpu_job_run, - .begin_job = amd_sched_job_begin, - .finish_job = amd_sched_job_finish, + .timedout_job = amdgpu_job_timedout, + .free_job = amdgpu_job_free_cb }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 40a23704a981..d942654a1de0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -60,7 +60,10 @@ int amdgpu_driver_unload_kms(struct drm_device *dev) if (adev->rmmio == NULL) goto done_free; - pm_runtime_get_sync(dev->dev); + if (amdgpu_device_is_px(dev)) { + pm_runtime_get_sync(dev->dev); + pm_runtime_forbid(dev->dev); + } amdgpu_amdkfd_device_fini(adev); @@ -135,13 +138,75 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) } out: - if (r) + if (r) { + /* balance pm_runtime_get_sync in amdgpu_driver_unload_kms */ + if (adev->rmmio && amdgpu_device_is_px(dev)) + pm_runtime_put_noidle(dev->dev); amdgpu_driver_unload_kms(dev); - + } return r; } +static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info, + struct drm_amdgpu_query_fw *query_fw, + struct amdgpu_device *adev) +{ + switch (query_fw->fw_type) { + case AMDGPU_INFO_FW_VCE: + fw_info->ver = adev->vce.fw_version; + fw_info->feature = adev->vce.fb_version; + break; + case AMDGPU_INFO_FW_UVD: + fw_info->ver = adev->uvd.fw_version; + fw_info->feature = 0; + break; + case AMDGPU_INFO_FW_GMC: + fw_info->ver = adev->mc.fw_version; + fw_info->feature = 0; + break; + case AMDGPU_INFO_FW_GFX_ME: + fw_info->ver = adev->gfx.me_fw_version; + fw_info->feature = adev->gfx.me_feature_version; + break; + case AMDGPU_INFO_FW_GFX_PFP: + fw_info->ver = adev->gfx.pfp_fw_version; + fw_info->feature = adev->gfx.pfp_feature_version; + break; + case AMDGPU_INFO_FW_GFX_CE: + fw_info->ver = adev->gfx.ce_fw_version; + fw_info->feature = adev->gfx.ce_feature_version; + break; + case AMDGPU_INFO_FW_GFX_RLC: + fw_info->ver = adev->gfx.rlc_fw_version; + fw_info->feature = adev->gfx.rlc_feature_version; + break; + case AMDGPU_INFO_FW_GFX_MEC: + if (query_fw->index == 0) { + fw_info->ver = adev->gfx.mec_fw_version; + fw_info->feature = adev->gfx.mec_feature_version; + } else if (query_fw->index == 1) { + fw_info->ver = adev->gfx.mec2_fw_version; + fw_info->feature = adev->gfx.mec2_feature_version; + } else + return -EINVAL; + break; + case AMDGPU_INFO_FW_SMC: + fw_info->ver = adev->pm.fw_version; + fw_info->feature = 0; + break; + case AMDGPU_INFO_FW_SDMA: + if (query_fw->index >= adev->sdma.num_instances) + return -EINVAL; + fw_info->ver = adev->sdma.instance[query_fw->index].fw_version; + fw_info->feature = adev->sdma.instance[query_fw->index].feature_version; + break; + default: + return -EINVAL; + } + return 0; +} + /* * Userspace get information ioctl */ @@ -288,67 +353,20 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file return copy_to_user(out, &count, min(size, 4u)) ? -EFAULT : 0; } case AMDGPU_INFO_TIMESTAMP: - ui64 = amdgpu_asic_get_gpu_clock_counter(adev); + ui64 = amdgpu_gfx_get_gpu_clock_counter(adev); return copy_to_user(out, &ui64, min(size, 8u)) ? -EFAULT : 0; case AMDGPU_INFO_FW_VERSION: { struct drm_amdgpu_info_firmware fw_info; + int ret; /* We only support one instance of each IP block right now. */ if (info->query_fw.ip_instance != 0) return -EINVAL; - switch (info->query_fw.fw_type) { - case AMDGPU_INFO_FW_VCE: - fw_info.ver = adev->vce.fw_version; - fw_info.feature = adev->vce.fb_version; - break; - case AMDGPU_INFO_FW_UVD: - fw_info.ver = adev->uvd.fw_version; - fw_info.feature = 0; - break; - case AMDGPU_INFO_FW_GMC: - fw_info.ver = adev->mc.fw_version; - fw_info.feature = 0; - break; - case AMDGPU_INFO_FW_GFX_ME: - fw_info.ver = adev->gfx.me_fw_version; - fw_info.feature = adev->gfx.me_feature_version; - break; - case AMDGPU_INFO_FW_GFX_PFP: - fw_info.ver = adev->gfx.pfp_fw_version; - fw_info.feature = adev->gfx.pfp_feature_version; - break; - case AMDGPU_INFO_FW_GFX_CE: - fw_info.ver = adev->gfx.ce_fw_version; - fw_info.feature = adev->gfx.ce_feature_version; - break; - case AMDGPU_INFO_FW_GFX_RLC: - fw_info.ver = adev->gfx.rlc_fw_version; - fw_info.feature = adev->gfx.rlc_feature_version; - break; - case AMDGPU_INFO_FW_GFX_MEC: - if (info->query_fw.index == 0) { - fw_info.ver = adev->gfx.mec_fw_version; - fw_info.feature = adev->gfx.mec_feature_version; - } else if (info->query_fw.index == 1) { - fw_info.ver = adev->gfx.mec2_fw_version; - fw_info.feature = adev->gfx.mec2_feature_version; - } else - return -EINVAL; - break; - case AMDGPU_INFO_FW_SMC: - fw_info.ver = adev->pm.fw_version; - fw_info.feature = 0; - break; - case AMDGPU_INFO_FW_SDMA: - if (info->query_fw.index >= adev->sdma.num_instances) - return -EINVAL; - fw_info.ver = adev->sdma.instance[info->query_fw.index].fw_version; - fw_info.feature = adev->sdma.instance[info->query_fw.index].feature_version; - break; - default: - return -EINVAL; - } + ret = amdgpu_firmware_info(&fw_info, &info->query_fw, adev); + if (ret) + return ret; + return copy_to_user(out, &fw_info, min((size_t)size, sizeof(fw_info))) ? -EFAULT : 0; } @@ -447,7 +465,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file dev_info.max_memory_clock = adev->pm.default_mclk * 10; } dev_info.enabled_rb_pipes_mask = adev->gfx.config.backend_enable_mask; - dev_info.num_rb_pipes = adev->gfx.config.num_rbs; + dev_info.num_rb_pipes = adev->gfx.config.max_backends_per_se * + adev->gfx.config.max_shader_engines; dev_info.num_hw_gfx_contexts = adev->gfx.config.max_hw_contexts; dev_info._pad = 0; dev_info.ids_flags = 0; @@ -565,6 +584,9 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev, amdgpu_ctx_mgr_fini(&fpriv->ctx_mgr); + amdgpu_uvd_free_handles(adev, file_priv); + amdgpu_vce_free_handles(adev, file_priv); + amdgpu_vm_fini(adev, &fpriv->vm); idr_for_each_entry(&fpriv->bo_list_handles, list, handle) @@ -589,10 +611,6 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev, void amdgpu_driver_preclose_kms(struct drm_device *dev, struct drm_file *file_priv) { - struct amdgpu_device *adev = dev->dev_private; - - amdgpu_uvd_free_handles(adev, file_priv); - amdgpu_vce_free_handles(adev, file_priv); } /* @@ -755,3 +773,130 @@ const struct drm_ioctl_desc amdgpu_ioctls_kms[] = { DRM_IOCTL_DEF_DRV(AMDGPU_GEM_USERPTR, amdgpu_gem_userptr_ioctl, DRM_AUTH|DRM_RENDER_ALLOW), }; const int amdgpu_max_kms_ioctl = ARRAY_SIZE(amdgpu_ioctls_kms); + +/* + * Debugfs info + */ +#if defined(CONFIG_DEBUG_FS) + +static int amdgpu_debugfs_firmware_info(struct seq_file *m, void *data) +{ + struct drm_info_node *node = (struct drm_info_node *) m->private; + struct drm_device *dev = node->minor->dev; + struct amdgpu_device *adev = dev->dev_private; + struct drm_amdgpu_info_firmware fw_info; + struct drm_amdgpu_query_fw query_fw; + int ret, i; + + /* VCE */ + query_fw.fw_type = AMDGPU_INFO_FW_VCE; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "VCE feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + + /* UVD */ + query_fw.fw_type = AMDGPU_INFO_FW_UVD; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "UVD feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + + /* GMC */ + query_fw.fw_type = AMDGPU_INFO_FW_GMC; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "MC feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + + /* ME */ + query_fw.fw_type = AMDGPU_INFO_FW_GFX_ME; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "ME feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + + /* PFP */ + query_fw.fw_type = AMDGPU_INFO_FW_GFX_PFP; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "PFP feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + + /* CE */ + query_fw.fw_type = AMDGPU_INFO_FW_GFX_CE; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "CE feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + + /* RLC */ + query_fw.fw_type = AMDGPU_INFO_FW_GFX_RLC; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "RLC feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + + /* MEC */ + query_fw.fw_type = AMDGPU_INFO_FW_GFX_MEC; + query_fw.index = 0; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "MEC feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + + /* MEC2 */ + if (adev->asic_type == CHIP_KAVERI || + (adev->asic_type > CHIP_TOPAZ && adev->asic_type != CHIP_STONEY)) { + query_fw.index = 1; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "MEC2 feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + } + + /* SMC */ + query_fw.fw_type = AMDGPU_INFO_FW_SMC; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "SMC feature version: %u, firmware version: 0x%08x\n", + fw_info.feature, fw_info.ver); + + /* SDMA */ + query_fw.fw_type = AMDGPU_INFO_FW_SDMA; + for (i = 0; i < adev->sdma.num_instances; i++) { + query_fw.index = i; + ret = amdgpu_firmware_info(&fw_info, &query_fw, adev); + if (ret) + return ret; + seq_printf(m, "SDMA%d feature version: %u, firmware version: 0x%08x\n", + i, fw_info.feature, fw_info.ver); + } + + return 0; +} + +static const struct drm_info_list amdgpu_firmware_info_list[] = { + {"amdgpu_firmware_info", amdgpu_debugfs_firmware_info, 0, NULL}, +}; +#endif + +int amdgpu_debugfs_firmware_init(struct amdgpu_device *adev) +{ +#if defined(CONFIG_DEBUG_FS) + return amdgpu_debugfs_add_files(adev, amdgpu_firmware_info_list, + ARRAY_SIZE(amdgpu_firmware_info_list)); +#else + return 0; +#endif +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 7ecea83ce453..6f0873c75a25 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -589,6 +589,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, struct ttm_mem_reg *new_mem) { struct amdgpu_bo *rbo; + struct ttm_mem_reg *old_mem = &bo->mem; if (!amdgpu_ttm_bo_is_amdgpu_bo(bo)) return; @@ -602,6 +603,8 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, /* move_notify is called before move happens */ amdgpu_update_memory_usage(rbo->adev, &bo->mem, new_mem); + + trace_amdgpu_ttm_bo_move(rbo, new_mem->mem_type, old_mem->mem_type); } int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 589b36e8c5cf..ff63b88b0ffa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -270,30 +270,28 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = ddev->dev_private; enum amd_pm_state_type state = 0; - long idx; + unsigned long idx; int ret; if (strlen(buf) == 1) adev->pp_force_state_enabled = false; - else { - ret = kstrtol(buf, 0, &idx); + else if (adev->pp_enabled) { + struct pp_states_info data; - if (ret) { + ret = kstrtoul(buf, 0, &idx); + if (ret || idx >= ARRAY_SIZE(data.states)) { count = -EINVAL; goto fail; } - if (adev->pp_enabled) { - struct pp_states_info data; - amdgpu_dpm_get_pp_num_states(adev, &data); - state = data.states[idx]; - /* only set user selected power states */ - if (state != POWER_STATE_TYPE_INTERNAL_BOOT && - state != POWER_STATE_TYPE_DEFAULT) { - amdgpu_dpm_dispatch_task(adev, - AMD_PP_EVENT_ENABLE_USER_STATE, &state, NULL); - adev->pp_force_state_enabled = true; - } + amdgpu_dpm_get_pp_num_states(adev, &data); + state = data.states[idx]; + /* only set user selected power states */ + if (state != POWER_STATE_TYPE_INTERNAL_BOOT && + state != POWER_STATE_TYPE_DEFAULT) { + amdgpu_dpm_dispatch_task(adev, + AMD_PP_EVENT_ENABLE_USER_STATE, &state, NULL); + adev->pp_force_state_enabled = true; } } fail: @@ -349,6 +347,8 @@ static ssize_t amdgpu_get_pp_dpm_sclk(struct device *dev, if (adev->pp_enabled) size = amdgpu_dpm_print_clock_levels(adev, PP_SCLK, buf); + else if (adev->pm.funcs->print_clock_levels) + size = adev->pm.funcs->print_clock_levels(adev, PP_SCLK, buf); return size; } @@ -365,7 +365,9 @@ static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev, uint32_t i, mask = 0; char sub_str[2]; - for (i = 0; i < strlen(buf) - 1; i++) { + for (i = 0; i < strlen(buf); i++) { + if (*(buf + i) == '\n') + continue; sub_str[0] = *(buf + i); sub_str[1] = '\0'; ret = kstrtol(sub_str, 0, &level); @@ -379,6 +381,8 @@ static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev, if (adev->pp_enabled) amdgpu_dpm_force_clock_level(adev, PP_SCLK, mask); + else if (adev->pm.funcs->force_clock_level) + adev->pm.funcs->force_clock_level(adev, PP_SCLK, mask); fail: return count; } @@ -393,6 +397,8 @@ static ssize_t amdgpu_get_pp_dpm_mclk(struct device *dev, if (adev->pp_enabled) size = amdgpu_dpm_print_clock_levels(adev, PP_MCLK, buf); + else if (adev->pm.funcs->print_clock_levels) + size = adev->pm.funcs->print_clock_levels(adev, PP_MCLK, buf); return size; } @@ -409,7 +415,9 @@ static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev, uint32_t i, mask = 0; char sub_str[2]; - for (i = 0; i < strlen(buf) - 1; i++) { + for (i = 0; i < strlen(buf); i++) { + if (*(buf + i) == '\n') + continue; sub_str[0] = *(buf + i); sub_str[1] = '\0'; ret = kstrtol(sub_str, 0, &level); @@ -423,6 +431,8 @@ static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev, if (adev->pp_enabled) amdgpu_dpm_force_clock_level(adev, PP_MCLK, mask); + else if (adev->pm.funcs->force_clock_level) + adev->pm.funcs->force_clock_level(adev, PP_MCLK, mask); fail: return count; } @@ -437,6 +447,8 @@ static ssize_t amdgpu_get_pp_dpm_pcie(struct device *dev, if (adev->pp_enabled) size = amdgpu_dpm_print_clock_levels(adev, PP_PCIE, buf); + else if (adev->pm.funcs->print_clock_levels) + size = adev->pm.funcs->print_clock_levels(adev, PP_PCIE, buf); return size; } @@ -453,7 +465,9 @@ static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev, uint32_t i, mask = 0; char sub_str[2]; - for (i = 0; i < strlen(buf) - 1; i++) { + for (i = 0; i < strlen(buf); i++) { + if (*(buf + i) == '\n') + continue; sub_str[0] = *(buf + i); sub_str[1] = '\0'; ret = kstrtol(sub_str, 0, &level); @@ -467,6 +481,100 @@ static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev, if (adev->pp_enabled) amdgpu_dpm_force_clock_level(adev, PP_PCIE, mask); + else if (adev->pm.funcs->force_clock_level) + adev->pm.funcs->force_clock_level(adev, PP_PCIE, mask); +fail: + return count; +} + +static ssize_t amdgpu_get_pp_sclk_od(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct drm_device *ddev = dev_get_drvdata(dev); + struct amdgpu_device *adev = ddev->dev_private; + uint32_t value = 0; + + if (adev->pp_enabled) + value = amdgpu_dpm_get_sclk_od(adev); + else if (adev->pm.funcs->get_sclk_od) + value = adev->pm.funcs->get_sclk_od(adev); + + return snprintf(buf, PAGE_SIZE, "%d\n", value); +} + +static ssize_t amdgpu_set_pp_sclk_od(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t count) +{ + struct drm_device *ddev = dev_get_drvdata(dev); + struct amdgpu_device *adev = ddev->dev_private; + int ret; + long int value; + + ret = kstrtol(buf, 0, &value); + + if (ret) { + count = -EINVAL; + goto fail; + } + + if (adev->pp_enabled) { + amdgpu_dpm_set_sclk_od(adev, (uint32_t)value); + amdgpu_dpm_dispatch_task(adev, AMD_PP_EVENT_READJUST_POWER_STATE, NULL, NULL); + } else if (adev->pm.funcs->set_sclk_od) { + adev->pm.funcs->set_sclk_od(adev, (uint32_t)value); + adev->pm.dpm.current_ps = adev->pm.dpm.boot_ps; + amdgpu_pm_compute_clocks(adev); + } + +fail: + return count; +} + +static ssize_t amdgpu_get_pp_mclk_od(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct drm_device *ddev = dev_get_drvdata(dev); + struct amdgpu_device *adev = ddev->dev_private; + uint32_t value = 0; + + if (adev->pp_enabled) + value = amdgpu_dpm_get_mclk_od(adev); + else if (adev->pm.funcs->get_mclk_od) + value = adev->pm.funcs->get_mclk_od(adev); + + return snprintf(buf, PAGE_SIZE, "%d\n", value); +} + +static ssize_t amdgpu_set_pp_mclk_od(struct device *dev, + struct device_attribute *attr, + const char *buf, + size_t count) +{ + struct drm_device *ddev = dev_get_drvdata(dev); + struct amdgpu_device *adev = ddev->dev_private; + int ret; + long int value; + + ret = kstrtol(buf, 0, &value); + + if (ret) { + count = -EINVAL; + goto fail; + } + + if (adev->pp_enabled) { + amdgpu_dpm_set_mclk_od(adev, (uint32_t)value); + amdgpu_dpm_dispatch_task(adev, AMD_PP_EVENT_READJUST_POWER_STATE, NULL, NULL); + } else if (adev->pm.funcs->set_mclk_od) { + adev->pm.funcs->set_mclk_od(adev, (uint32_t)value); + adev->pm.dpm.current_ps = adev->pm.dpm.boot_ps; + amdgpu_pm_compute_clocks(adev); + } + fail: return count; } @@ -492,6 +600,12 @@ static DEVICE_ATTR(pp_dpm_mclk, S_IRUGO | S_IWUSR, static DEVICE_ATTR(pp_dpm_pcie, S_IRUGO | S_IWUSR, amdgpu_get_pp_dpm_pcie, amdgpu_set_pp_dpm_pcie); +static DEVICE_ATTR(pp_sclk_od, S_IRUGO | S_IWUSR, + amdgpu_get_pp_sclk_od, + amdgpu_set_pp_sclk_od); +static DEVICE_ATTR(pp_mclk_od, S_IRUGO | S_IWUSR, + amdgpu_get_pp_mclk_od, + amdgpu_set_pp_mclk_od); static ssize_t amdgpu_hwmon_show_temp(struct device *dev, struct device_attribute *attr, @@ -1110,22 +1224,34 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev) DRM_ERROR("failed to create device file pp_table\n"); return ret; } - ret = device_create_file(adev->dev, &dev_attr_pp_dpm_sclk); - if (ret) { - DRM_ERROR("failed to create device file pp_dpm_sclk\n"); - return ret; - } - ret = device_create_file(adev->dev, &dev_attr_pp_dpm_mclk); - if (ret) { - DRM_ERROR("failed to create device file pp_dpm_mclk\n"); - return ret; - } - ret = device_create_file(adev->dev, &dev_attr_pp_dpm_pcie); - if (ret) { - DRM_ERROR("failed to create device file pp_dpm_pcie\n"); - return ret; - } } + + ret = device_create_file(adev->dev, &dev_attr_pp_dpm_sclk); + if (ret) { + DRM_ERROR("failed to create device file pp_dpm_sclk\n"); + return ret; + } + ret = device_create_file(adev->dev, &dev_attr_pp_dpm_mclk); + if (ret) { + DRM_ERROR("failed to create device file pp_dpm_mclk\n"); + return ret; + } + ret = device_create_file(adev->dev, &dev_attr_pp_dpm_pcie); + if (ret) { + DRM_ERROR("failed to create device file pp_dpm_pcie\n"); + return ret; + } + ret = device_create_file(adev->dev, &dev_attr_pp_sclk_od); + if (ret) { + DRM_ERROR("failed to create device file pp_sclk_od\n"); + return ret; + } + ret = device_create_file(adev->dev, &dev_attr_pp_mclk_od); + if (ret) { + DRM_ERROR("failed to create device file pp_mclk_od\n"); + return ret; + } + ret = amdgpu_debugfs_pm_init(adev); if (ret) { DRM_ERROR("Failed to register debugfs file for dpm!\n"); @@ -1148,10 +1274,12 @@ void amdgpu_pm_sysfs_fini(struct amdgpu_device *adev) device_remove_file(adev->dev, &dev_attr_pp_cur_state); device_remove_file(adev->dev, &dev_attr_pp_force_state); device_remove_file(adev->dev, &dev_attr_pp_table); - device_remove_file(adev->dev, &dev_attr_pp_dpm_sclk); - device_remove_file(adev->dev, &dev_attr_pp_dpm_mclk); - device_remove_file(adev->dev, &dev_attr_pp_dpm_pcie); } + device_remove_file(adev->dev, &dev_attr_pp_dpm_sclk); + device_remove_file(adev->dev, &dev_attr_pp_dpm_mclk); + device_remove_file(adev->dev, &dev_attr_pp_dpm_pcie); + device_remove_file(adev->dev, &dev_attr_pp_sclk_od); + device_remove_file(adev->dev, &dev_attr_pp_mclk_od); } void amdgpu_pm_compute_clocks(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c index 6bd961fb43dc..c5738a22b690 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_powerplay.c @@ -52,6 +52,7 @@ static int amdgpu_powerplay_init(struct amdgpu_device *adev) pp_init->chip_family = adev->family; pp_init->chip_id = adev->asic_type; pp_init->device = amdgpu_cgs_create_device(adev); + pp_init->powercontainment_enabled = amdgpu_powercontainment; ret = amd_powerplay_init(pp_init, amd_pp); kfree(pp_init); @@ -183,13 +184,6 @@ static int amdgpu_pp_sw_fini(void *handle) if (ret) return ret; -#ifdef CONFIG_DRM_AMD_POWERPLAY - if (adev->pp_enabled) { - amdgpu_pm_sysfs_fini(adev); - amd_powerplay_fini(adev->powerplay.pp_handle); - } -#endif - return ret; } @@ -223,6 +217,22 @@ static int amdgpu_pp_hw_fini(void *handle) return ret; } +static void amdgpu_pp_late_fini(void *handle) +{ +#ifdef CONFIG_DRM_AMD_POWERPLAY + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + if (adev->pp_enabled) { + amdgpu_pm_sysfs_fini(adev); + amd_powerplay_fini(adev->powerplay.pp_handle); + } + + if (adev->powerplay.ip_funcs->late_fini) + adev->powerplay.ip_funcs->late_fini( + adev->powerplay.pp_handle); +#endif +} + static int amdgpu_pp_suspend(void *handle) { int ret = 0; @@ -311,6 +321,7 @@ const struct amd_ip_funcs amdgpu_pp_ip_funcs = { .sw_fini = amdgpu_pp_sw_fini, .hw_init = amdgpu_pp_hw_init, .hw_fini = amdgpu_pp_hw_fini, + .late_fini = amdgpu_pp_late_fini, .suspend = amdgpu_pp_suspend, .resume = amdgpu_pp_resume, .is_idle = amdgpu_pp_is_idle, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 3b02272db678..85aeb0a804bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -28,6 +28,7 @@ */ #include #include +#include #include #include #include "amdgpu.h" @@ -48,6 +49,7 @@ */ static int amdgpu_debugfs_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring); +static void amdgpu_debugfs_ring_fini(struct amdgpu_ring *ring); /** * amdgpu_ring_alloc - allocate space on the ring buffer @@ -73,6 +75,10 @@ int amdgpu_ring_alloc(struct amdgpu_ring *ring, unsigned ndw) ring->count_dw = ndw; ring->wptr_old = ring->wptr; + + if (ring->funcs->begin_use) + ring->funcs->begin_use(ring); + return 0; } @@ -125,6 +131,9 @@ void amdgpu_ring_commit(struct amdgpu_ring *ring) mb(); amdgpu_ring_set_wptr(ring); + + if (ring->funcs->end_use) + ring->funcs->end_use(ring); } /** @@ -137,78 +146,9 @@ void amdgpu_ring_commit(struct amdgpu_ring *ring) void amdgpu_ring_undo(struct amdgpu_ring *ring) { ring->wptr = ring->wptr_old; -} -/** - * amdgpu_ring_backup - Back up the content of a ring - * - * @ring: the ring we want to back up - * - * Saves all unprocessed commits from a ring, returns the number of dwords saved. - */ -unsigned amdgpu_ring_backup(struct amdgpu_ring *ring, - uint32_t **data) -{ - unsigned size, ptr, i; - - *data = NULL; - - if (ring->ring_obj == NULL) - return 0; - - /* it doesn't make sense to save anything if all fences are signaled */ - if (!amdgpu_fence_count_emitted(ring)) - return 0; - - ptr = le32_to_cpu(*ring->next_rptr_cpu_addr); - - size = ring->wptr + (ring->ring_size / 4); - size -= ptr; - size &= ring->ptr_mask; - if (size == 0) - return 0; - - /* and then save the content of the ring */ - *data = kmalloc_array(size, sizeof(uint32_t), GFP_KERNEL); - if (!*data) - return 0; - for (i = 0; i < size; ++i) { - (*data)[i] = ring->ring[ptr++]; - ptr &= ring->ptr_mask; - } - - return size; -} - -/** - * amdgpu_ring_restore - append saved commands to the ring again - * - * @ring: ring to append commands to - * @size: number of dwords we want to write - * @data: saved commands - * - * Allocates space on the ring and restore the previously saved commands. - */ -int amdgpu_ring_restore(struct amdgpu_ring *ring, - unsigned size, uint32_t *data) -{ - int i, r; - - if (!size || !data) - return 0; - - /* restore the saved ring content */ - r = amdgpu_ring_alloc(ring, size); - if (r) - return r; - - for (i = 0; i < size; ++i) { - amdgpu_ring_write(ring, data[i]); - } - - amdgpu_ring_commit(ring); - kfree(data); - return 0; + if (ring->funcs->end_use) + ring->funcs->end_use(ring); } /** @@ -260,14 +200,6 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, return r; } - r = amdgpu_wb_get(adev, &ring->next_rptr_offs); - if (r) { - dev_err(adev->dev, "(%d) ring next_rptr wb alloc failed\n", r); - return r; - } - ring->next_rptr_gpu_addr = adev->wb.gpu_addr + ring->next_rptr_offs * 4; - ring->next_rptr_cpu_addr = &adev->wb.wb[ring->next_rptr_offs]; - r = amdgpu_wb_get(adev, &ring->cond_exe_offs); if (r) { dev_err(adev->dev, "(%d) ring cond_exec_polling wb alloc failed\n", r); @@ -276,7 +208,6 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, ring->cond_exe_gpu_addr = adev->wb.gpu_addr + (ring->cond_exe_offs * 4); ring->cond_exe_cpu_addr = &adev->wb.wb[ring->cond_exe_offs]; - spin_lock_init(&ring->fence_lock); r = amdgpu_fence_driver_start_ring(ring, irq_src, irq_type); if (r) { dev_err(adev->dev, "failed initializing fences (%d).\n", r); @@ -310,6 +241,9 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, } r = amdgpu_bo_kmap(ring->ring_obj, (void **)&ring->ring); + + memset((void *)ring->ring, 0, ring->ring_size); + amdgpu_bo_unreserve(ring->ring_obj); if (r) { dev_err(adev->dev, "(%d) ring map failed\n", r); @@ -343,10 +277,10 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring) ring->ring = NULL; ring->ring_obj = NULL; + amdgpu_wb_free(ring->adev, ring->cond_exe_offs); amdgpu_wb_free(ring->adev, ring->fence_offs); amdgpu_wb_free(ring->adev, ring->rptr_offs); amdgpu_wb_free(ring->adev, ring->wptr_offs); - amdgpu_wb_free(ring->adev, ring->next_rptr_offs); if (ring_obj) { r = amdgpu_bo_reserve(ring_obj, false); @@ -357,6 +291,7 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring) } amdgpu_bo_unref(&ring_obj); } + amdgpu_debugfs_ring_fini(ring); } /* @@ -364,57 +299,62 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring) */ #if defined(CONFIG_DEBUG_FS) -static int amdgpu_debugfs_ring_info(struct seq_file *m, void *data) +/* Layout of file is 12 bytes consisting of + * - rptr + * - wptr + * - driver's copy of wptr + * + * followed by n-words of ring data + */ +static ssize_t amdgpu_debugfs_ring_read(struct file *f, char __user *buf, + size_t size, loff_t *pos) { - struct drm_info_node *node = (struct drm_info_node *) m->private; - struct drm_device *dev = node->minor->dev; - struct amdgpu_device *adev = dev->dev_private; - int roffset = (unsigned long)node->info_ent->data; - struct amdgpu_ring *ring = (void *)(((uint8_t*)adev) + roffset); - uint32_t rptr, wptr, rptr_next; - unsigned i; + struct amdgpu_ring *ring = (struct amdgpu_ring*)f->f_inode->i_private; + int r, i; + uint32_t value, result, early[3]; - wptr = amdgpu_ring_get_wptr(ring); - seq_printf(m, "wptr: 0x%08x [%5d]\n", wptr, wptr); + if (*pos & 3 || size & 3) + return -EINVAL; - rptr = amdgpu_ring_get_rptr(ring); - rptr_next = le32_to_cpu(*ring->next_rptr_cpu_addr); + result = 0; - seq_printf(m, "rptr: 0x%08x [%5d]\n", rptr, rptr); - - seq_printf(m, "driver's copy of the wptr: 0x%08x [%5d]\n", - ring->wptr, ring->wptr); - - if (!ring->ready) - return 0; - - /* print 8 dw before current rptr as often it's the last executed - * packet that is the root issue - */ - i = (rptr + ring->ptr_mask + 1 - 32) & ring->ptr_mask; - while (i != rptr) { - seq_printf(m, "r[%5d]=0x%08x", i, ring->ring[i]); - if (i == rptr) - seq_puts(m, " *"); - if (i == rptr_next) - seq_puts(m, " #"); - seq_puts(m, "\n"); - i = (i + 1) & ring->ptr_mask; + if (*pos < 12) { + early[0] = amdgpu_ring_get_rptr(ring); + early[1] = amdgpu_ring_get_wptr(ring); + early[2] = ring->wptr; + for (i = *pos / 4; i < 3 && size; i++) { + r = put_user(early[i], (uint32_t *)buf); + if (r) + return r; + buf += 4; + result += 4; + size -= 4; + *pos += 4; + } } - while (i != wptr) { - seq_printf(m, "r[%5d]=0x%08x", i, ring->ring[i]); - if (i == rptr) - seq_puts(m, " *"); - if (i == rptr_next) - seq_puts(m, " #"); - seq_puts(m, "\n"); - i = (i + 1) & ring->ptr_mask; + + while (size) { + if (*pos >= (ring->ring_size + 12)) + return result; + + value = ring->ring[(*pos - 12)/4]; + r = put_user(value, (uint32_t*)buf); + if (r) + return r; + buf += 4; + result += 4; + size -= 4; + *pos += 4; } - return 0; + + return result; } -static struct drm_info_list amdgpu_debugfs_ring_info_list[AMDGPU_MAX_RINGS]; -static char amdgpu_debugfs_ring_names[AMDGPU_MAX_RINGS][32]; +static const struct file_operations amdgpu_debugfs_ring_fops = { + .owner = THIS_MODULE, + .read = amdgpu_debugfs_ring_read, + .llseek = default_llseek +}; #endif @@ -422,28 +362,27 @@ static int amdgpu_debugfs_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #if defined(CONFIG_DEBUG_FS) - unsigned offset = (uint8_t*)ring - (uint8_t*)adev; - unsigned i; - struct drm_info_list *info; - char *name; + struct drm_minor *minor = adev->ddev->primary; + struct dentry *ent, *root = minor->debugfs_root; + char name[32]; - for (i = 0; i < ARRAY_SIZE(amdgpu_debugfs_ring_info_list); ++i) { - info = &amdgpu_debugfs_ring_info_list[i]; - if (!info->data) - break; - } - - if (i == ARRAY_SIZE(amdgpu_debugfs_ring_info_list)) - return -ENOSPC; - - name = &amdgpu_debugfs_ring_names[i][0]; sprintf(name, "amdgpu_ring_%s", ring->name); - info->name = name; - info->show = amdgpu_debugfs_ring_info; - info->driver_features = 0; - info->data = (void*)(uintptr_t)offset; - return amdgpu_debugfs_add_files(adev, info, 1); + ent = debugfs_create_file(name, + S_IFREG | S_IRUGO, root, + ring, &amdgpu_debugfs_ring_fops); + if (IS_ERR(ent)) + return PTR_ERR(ent); + + i_size_write(ent->d_inode, ring->ring_size + 12); + ring->ent = ent; #endif return 0; } + +static void amdgpu_debugfs_ring_fini(struct amdgpu_ring *ring) +{ +#if defined(CONFIG_DEBUG_FS) + debugfs_remove(ring->ent); +#endif +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c index b16366c2b4a0..d8af37a845f4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c @@ -115,6 +115,7 @@ int amdgpu_sa_bo_manager_start(struct amdgpu_device *adev, return r; } r = amdgpu_bo_kmap(sa_manager->bo, &sa_manager->cpu_ptr); + memset(sa_manager->cpu_ptr, 0, sa_manager->size); amdgpu_bo_unreserve(sa_manager->bo); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index 34a92808bbd4..5c8d3022fb87 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -223,13 +223,16 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, } /** - * amdgpu_sync_is_idle - test if all fences are signaled + * amdgpu_sync_peek_fence - get the next fence not signaled yet * * @sync: the sync object + * @ring: optional ring to use for test * - * Returns true if all fences in the sync object are signaled. + * Returns the next fence not signaled yet without removing it from the sync + * object. */ -bool amdgpu_sync_is_idle(struct amdgpu_sync *sync) +struct fence *amdgpu_sync_peek_fence(struct amdgpu_sync *sync, + struct amdgpu_ring *ring) { struct amdgpu_sync_entry *e; struct hlist_node *tmp; @@ -237,6 +240,19 @@ bool amdgpu_sync_is_idle(struct amdgpu_sync *sync) hash_for_each_safe(sync->fences, i, tmp, e, node) { struct fence *f = e->fence; + struct amd_sched_fence *s_fence = to_amd_sched_fence(f); + + if (ring && s_fence) { + /* For fences from the same ring it is sufficient + * when they are scheduled. + */ + if (s_fence->sched == &ring->sched) { + if (fence_is_signaled(&s_fence->scheduled)) + continue; + + return &s_fence->scheduled; + } + } if (fence_is_signaled(f)) { hash_del(&e->node); @@ -245,58 +261,19 @@ bool amdgpu_sync_is_idle(struct amdgpu_sync *sync) continue; } - return false; + return f; } - return true; + return NULL; } /** - * amdgpu_sync_cycle_fences - move fences from one sync object into another + * amdgpu_sync_get_fence - get the next fence from the sync object * - * @dst: the destination sync object - * @src: the source sync object - * @fence: fence to add to source + * @sync: sync object to use * - * Remove all fences from source and put them into destination and add - * fence as new one into source. + * Get and removes the next fence from the sync object not signaled yet. */ -int amdgpu_sync_cycle_fences(struct amdgpu_sync *dst, struct amdgpu_sync *src, - struct fence *fence) -{ - struct amdgpu_sync_entry *e, *newone; - struct hlist_node *tmp; - int i; - - /* Allocate the new entry before moving the old ones */ - newone = kmem_cache_alloc(amdgpu_sync_slab, GFP_KERNEL); - if (!newone) - return -ENOMEM; - - hash_for_each_safe(src->fences, i, tmp, e, node) { - struct fence *f = e->fence; - - hash_del(&e->node); - if (fence_is_signaled(f)) { - fence_put(f); - kmem_cache_free(amdgpu_sync_slab, e); - continue; - } - - if (amdgpu_sync_add_later(dst, f)) { - kmem_cache_free(amdgpu_sync_slab, e); - continue; - } - - hash_add(dst->fences, &e->node, f->context); - } - - hash_add(src->fences, &newone->node, fence->context); - newone->fence = fence_get(fence); - - return 0; -} - struct fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync) { struct amdgpu_sync_entry *e; @@ -319,25 +296,6 @@ struct fence *amdgpu_sync_get_fence(struct amdgpu_sync *sync) return NULL; } -int amdgpu_sync_wait(struct amdgpu_sync *sync) -{ - struct amdgpu_sync_entry *e; - struct hlist_node *tmp; - int i, r; - - hash_for_each_safe(sync->fences, i, tmp, e, node) { - r = fence_wait(e->fence, false); - if (r) - return r; - - hash_del(&e->node); - fence_put(e->fence); - kmem_cache_free(amdgpu_sync_slab, e); - } - - return 0; -} - /** * amdgpu_sync_free - free the sync object * diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h index 26a5f4acf584..0d8d65eb46cd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h @@ -11,19 +11,68 @@ #define TRACE_SYSTEM amdgpu #define TRACE_INCLUDE_FILE amdgpu_trace +TRACE_EVENT(amdgpu_mm_rreg, + TP_PROTO(unsigned did, uint32_t reg, uint32_t value), + TP_ARGS(did, reg, value), + TP_STRUCT__entry( + __field(unsigned, did) + __field(uint32_t, reg) + __field(uint32_t, value) + ), + TP_fast_assign( + __entry->did = did; + __entry->reg = reg; + __entry->value = value; + ), + TP_printk("0x%04lx, 0x%04lx, 0x%08lx", + (unsigned long)__entry->did, + (unsigned long)__entry->reg, + (unsigned long)__entry->value) +); + +TRACE_EVENT(amdgpu_mm_wreg, + TP_PROTO(unsigned did, uint32_t reg, uint32_t value), + TP_ARGS(did, reg, value), + TP_STRUCT__entry( + __field(unsigned, did) + __field(uint32_t, reg) + __field(uint32_t, value) + ), + TP_fast_assign( + __entry->did = did; + __entry->reg = reg; + __entry->value = value; + ), + TP_printk("0x%04lx, 0x%04lx, 0x%08lx", + (unsigned long)__entry->did, + (unsigned long)__entry->reg, + (unsigned long)__entry->value) +); + TRACE_EVENT(amdgpu_bo_create, TP_PROTO(struct amdgpu_bo *bo), TP_ARGS(bo), TP_STRUCT__entry( __field(struct amdgpu_bo *, bo) __field(u32, pages) + __field(u32, type) + __field(u32, prefer) + __field(u32, allow) + __field(u32, visible) ), TP_fast_assign( __entry->bo = bo; __entry->pages = bo->tbo.num_pages; + __entry->type = bo->tbo.mem.mem_type; + __entry->prefer = bo->prefered_domains; + __entry->allow = bo->allowed_domains; + __entry->visible = bo->flags; ), - TP_printk("bo=%p, pages=%u", __entry->bo, __entry->pages) + + TP_printk("bo=%p,pages=%u,type=%d,prefered=%d,allowed=%d,visible=%d", + __entry->bo, __entry->pages, __entry->type, + __entry->prefer, __entry->allow, __entry->visible) ); TRACE_EVENT(amdgpu_cs, @@ -64,7 +113,7 @@ TRACE_EVENT(amdgpu_cs_ioctl, __entry->adev = job->adev; __entry->sched_job = &job->base; __entry->ib = job->ibs; - __entry->fence = &job->base.s_fence->base; + __entry->fence = &job->base.s_fence->finished; __entry->ring_name = job->ring->name; __entry->num_ibs = job->num_ibs; ), @@ -89,7 +138,7 @@ TRACE_EVENT(amdgpu_sched_run_job, __entry->adev = job->adev; __entry->sched_job = &job->base; __entry->ib = job->ibs; - __entry->fence = &job->base.s_fence->base; + __entry->fence = &job->base.s_fence->finished; __entry->ring_name = job->ring->name; __entry->num_ibs = job->num_ibs; ), @@ -100,24 +149,26 @@ TRACE_EVENT(amdgpu_sched_run_job, TRACE_EVENT(amdgpu_vm_grab_id, - TP_PROTO(struct amdgpu_vm *vm, int ring, unsigned vmid, - uint64_t pd_addr), - TP_ARGS(vm, ring, vmid, pd_addr), + TP_PROTO(struct amdgpu_vm *vm, int ring, struct amdgpu_job *job), + TP_ARGS(vm, ring, job), TP_STRUCT__entry( __field(struct amdgpu_vm *, vm) __field(u32, ring) __field(u32, vmid) __field(u64, pd_addr) + __field(u32, needs_flush) ), TP_fast_assign( __entry->vm = vm; __entry->ring = ring; - __entry->vmid = vmid; - __entry->pd_addr = pd_addr; + __entry->vmid = job->vm_id; + __entry->pd_addr = job->vm_pd_addr; + __entry->needs_flush = job->vm_needs_flush; ), - TP_printk("vm=%p, ring=%u, id=%u, pd_addr=%010Lx", __entry->vm, - __entry->ring, __entry->vmid, __entry->pd_addr) + TP_printk("vm=%p, ring=%u, id=%u, pd_addr=%010Lx needs_flush=%u", + __entry->vm, __entry->ring, __entry->vmid, + __entry->pd_addr, __entry->needs_flush) ); TRACE_EVENT(amdgpu_vm_bo_map, @@ -244,13 +295,55 @@ TRACE_EVENT(amdgpu_bo_list_set, TP_STRUCT__entry( __field(struct amdgpu_bo_list *, list) __field(struct amdgpu_bo *, bo) + __field(u64, bo_size) ), TP_fast_assign( __entry->list = list; __entry->bo = bo; + __entry->bo_size = amdgpu_bo_size(bo); ), - TP_printk("list=%p, bo=%p", __entry->list, __entry->bo) + TP_printk("list=%p, bo=%p, bo_size = %Ld", + __entry->list, + __entry->bo, + __entry->bo_size) +); + +TRACE_EVENT(amdgpu_cs_bo_status, + TP_PROTO(uint64_t total_bo, uint64_t total_size), + TP_ARGS(total_bo, total_size), + TP_STRUCT__entry( + __field(u64, total_bo) + __field(u64, total_size) + ), + + TP_fast_assign( + __entry->total_bo = total_bo; + __entry->total_size = total_size; + ), + TP_printk("total bo size = %Ld, total bo count = %Ld", + __entry->total_bo, __entry->total_size) +); + +TRACE_EVENT(amdgpu_ttm_bo_move, + TP_PROTO(struct amdgpu_bo* bo, uint32_t new_placement, uint32_t old_placement), + TP_ARGS(bo, new_placement, old_placement), + TP_STRUCT__entry( + __field(struct amdgpu_bo *, bo) + __field(u64, bo_size) + __field(u32, new_placement) + __field(u32, old_placement) + ), + + TP_fast_assign( + __entry->bo = bo; + __entry->bo_size = amdgpu_bo_size(bo); + __entry->new_placement = new_placement; + __entry->old_placement = old_placement; + ), + TP_printk("bo=%p from:%d to %d with size = %Ld", + __entry->bo, __entry->old_placement, + __entry->new_placement, __entry->bo_size) ); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 3b9053af4762..b7742e62972a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -286,9 +286,10 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo, r = amdgpu_copy_buffer(ring, old_start, new_start, new_mem->num_pages * PAGE_SIZE, /* bytes */ bo->resv, &fence); - /* FIXME: handle copy error */ - r = ttm_bo_move_accel_cleanup(bo, fence, - evict, no_wait_gpu, new_mem); + if (r) + return r; + + r = ttm_bo_pipeline_move(bo, fence, evict, new_mem); fence_put(fence); return r; } @@ -396,6 +397,11 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, return -EINVAL; adev = amdgpu_get_adev(bo->bdev); + + /* remember the eviction */ + if (evict) + atomic64_inc(&adev->num_evictions); + if (old_mem->mem_type == TTM_PL_SYSTEM && bo->ttm == NULL) { amdgpu_move_null(bo, new_mem); return 0; @@ -429,7 +435,8 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, if (r) { memcpy: - r = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem); + r = ttm_bo_move_memcpy(bo, evict, interruptible, + no_wait_gpu, new_mem); if (r) { return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 01abfc21b4a2..b11f4e8868d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -40,9 +40,16 @@ #include "uvd/uvd_4_2_d.h" /* 1 second timeout */ -#define UVD_IDLE_TIMEOUT_MS 1000 +#define UVD_IDLE_TIMEOUT msecs_to_jiffies(1000) + +/* Firmware versions for VI */ +#define FW_1_65_10 ((1 << 24) | (65 << 16) | (10 << 8)) +#define FW_1_87_11 ((1 << 24) | (87 << 16) | (11 << 8)) +#define FW_1_87_12 ((1 << 24) | (87 << 16) | (12 << 8)) +#define FW_1_37_15 ((1 << 24) | (37 << 16) | (15 << 8)) + /* Polaris10/11 firmware version */ -#define FW_1_66_16 ((1 << 24) | (66 << 16) | (16 << 8)) +#define FW_1_66_16 ((1 << 24) | (66 << 16) | (16 << 8)) /* Firmware Names */ #ifdef CONFIG_DRM_AMDGPU_CIK @@ -92,7 +99,6 @@ MODULE_FIRMWARE(FIRMWARE_STONEY); MODULE_FIRMWARE(FIRMWARE_POLARIS10); MODULE_FIRMWARE(FIRMWARE_POLARIS11); -static void amdgpu_uvd_note_usage(struct amdgpu_device *adev); static void amdgpu_uvd_idle_work_handler(struct work_struct *work); int amdgpu_uvd_sw_init(struct amdgpu_device *adev) @@ -246,6 +252,23 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev) if (!amdgpu_ip_block_version_cmp(adev, AMD_IP_BLOCK_TYPE_UVD, 5, 0)) adev->uvd.address_64_bit = true; + switch (adev->asic_type) { + case CHIP_TONGA: + adev->uvd.use_ctx_buf = adev->uvd.fw_version >= FW_1_65_10; + break; + case CHIP_CARRIZO: + adev->uvd.use_ctx_buf = adev->uvd.fw_version >= FW_1_87_11; + break; + case CHIP_FIJI: + adev->uvd.use_ctx_buf = adev->uvd.fw_version >= FW_1_87_12; + break; + case CHIP_STONEY: + adev->uvd.use_ctx_buf = adev->uvd.fw_version >= FW_1_37_15; + break; + default: + adev->uvd.use_ctx_buf = adev->asic_type >= CHIP_POLARIS10; + } + return 0; } @@ -253,19 +276,20 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev) { int r; - if (adev->uvd.vcpu_bo == NULL) - return 0; + kfree(adev->uvd.saved_bo); amd_sched_entity_fini(&adev->uvd.ring.sched, &adev->uvd.entity); - r = amdgpu_bo_reserve(adev->uvd.vcpu_bo, false); - if (!r) { - amdgpu_bo_kunmap(adev->uvd.vcpu_bo); - amdgpu_bo_unpin(adev->uvd.vcpu_bo); - amdgpu_bo_unreserve(adev->uvd.vcpu_bo); - } + if (adev->uvd.vcpu_bo) { + r = amdgpu_bo_reserve(adev->uvd.vcpu_bo, false); + if (!r) { + amdgpu_bo_kunmap(adev->uvd.vcpu_bo); + amdgpu_bo_unpin(adev->uvd.vcpu_bo); + amdgpu_bo_unreserve(adev->uvd.vcpu_bo); + } - amdgpu_bo_unref(&adev->uvd.vcpu_bo); + amdgpu_bo_unref(&adev->uvd.vcpu_bo); + } amdgpu_ring_fini(&adev->uvd.ring); @@ -345,8 +369,6 @@ void amdgpu_uvd_free_handles(struct amdgpu_device *adev, struct drm_file *filp) if (handle != 0 && adev->uvd.filp[i] == filp) { struct fence *fence; - amdgpu_uvd_note_usage(adev); - r = amdgpu_uvd_get_destroy_msg(ring, handle, false, &fence); if (r) { @@ -437,7 +459,7 @@ static int amdgpu_uvd_cs_msg_decode(struct amdgpu_device *adev, uint32_t *msg, unsigned fs_in_mb = width_in_mb * height_in_mb; unsigned image_size, tmp, min_dpb_size, num_dpb_buffer; - unsigned min_ctx_size = 0; + unsigned min_ctx_size = ~0; image_size = width * height; image_size += image_size / 2; @@ -556,7 +578,7 @@ static int amdgpu_uvd_cs_msg_decode(struct amdgpu_device *adev, uint32_t *msg, /* reference picture buffer */ min_dpb_size = image_size * num_dpb_buffer; - if (adev->asic_type < CHIP_POLARIS10){ + if (!adev->uvd.use_ctx_buf){ /* macroblock context buffer */ min_dpb_size += width_in_mb * height_in_mb * num_dpb_buffer * 192; @@ -661,7 +683,7 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx, } DRM_ERROR("No more free UVD handles!\n"); - return -EINVAL; + return -ENOSPC; case 1: /* it's a decode msg, calc buffer sizes */ @@ -912,8 +934,6 @@ int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, uint32_t ib_idx) return -EINVAL; } - amdgpu_uvd_note_usage(ctx.parser->adev); - return 0; } @@ -967,7 +987,7 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo, if (direct) { r = amdgpu_ib_schedule(ring, 1, ib, NULL, NULL, &f); - job->fence = f; + job->fence = fence_get(f); if (r) goto err_free; @@ -1109,16 +1129,14 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work) amdgpu_asic_set_uvd_clocks(adev, 0, 0); } } else { - schedule_delayed_work(&adev->uvd.idle_work, - msecs_to_jiffies(UVD_IDLE_TIMEOUT_MS)); + schedule_delayed_work(&adev->uvd.idle_work, UVD_IDLE_TIMEOUT); } } -static void amdgpu_uvd_note_usage(struct amdgpu_device *adev) +void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring) { + struct amdgpu_device *adev = ring->adev; bool set_clocks = !cancel_delayed_work_sync(&adev->uvd.idle_work); - set_clocks &= schedule_delayed_work(&adev->uvd.idle_work, - msecs_to_jiffies(UVD_IDLE_TIMEOUT_MS)); if (set_clocks) { if (adev->pm.dpm_enabled) { @@ -1128,3 +1146,48 @@ static void amdgpu_uvd_note_usage(struct amdgpu_device *adev) } } } + +void amdgpu_uvd_ring_end_use(struct amdgpu_ring *ring) +{ + schedule_delayed_work(&ring->adev->uvd.idle_work, UVD_IDLE_TIMEOUT); +} + +/** + * amdgpu_uvd_ring_test_ib - test ib execution + * + * @ring: amdgpu_ring pointer + * + * Test if we can successfully execute an IB + */ +int amdgpu_uvd_ring_test_ib(struct amdgpu_ring *ring, long timeout) +{ + struct fence *fence; + long r; + + r = amdgpu_uvd_get_create_msg(ring, 1, NULL); + if (r) { + DRM_ERROR("amdgpu: failed to get create msg (%ld).\n", r); + goto error; + } + + r = amdgpu_uvd_get_destroy_msg(ring, 1, true, &fence); + if (r) { + DRM_ERROR("amdgpu: failed to get destroy ib (%ld).\n", r); + goto error; + } + + r = fence_wait_timeout(fence, false, timeout); + if (r == 0) { + DRM_ERROR("amdgpu: IB test timed out.\n"); + r = -ETIMEDOUT; + } else if (r < 0) { + DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r); + } else { + DRM_INFO("ib test on ring %d succeeded\n", ring->idx); + r = 0; + } + +error: + fence_put(fence); + return r; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h index 9a3b449081a7..c850009602d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h @@ -35,5 +35,8 @@ int amdgpu_uvd_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, void amdgpu_uvd_free_handles(struct amdgpu_device *adev, struct drm_file *filp); int amdgpu_uvd_ring_parse_cs(struct amdgpu_cs_parser *parser, uint32_t ib_idx); +void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring); +void amdgpu_uvd_ring_end_use(struct amdgpu_ring *ring); +int amdgpu_uvd_ring_test_ib(struct amdgpu_ring *ring, long timeout); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 875626a2eccb..05865ce35351 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -36,7 +36,7 @@ #include "cikd.h" /* 1 second timeout */ -#define VCE_IDLE_TIMEOUT_MS 1000 +#define VCE_IDLE_TIMEOUT msecs_to_jiffies(1000) /* Firmware Names */ #ifdef CONFIG_DRM_AMDGPU_CIK @@ -85,8 +85,6 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size) unsigned ucode_version, version_major, version_minor, binary_id; int i, r; - INIT_DELAYED_WORK(&adev->vce.idle_work, amdgpu_vce_idle_work_handler); - switch (adev->asic_type) { #ifdef CONFIG_DRM_AMDGPU_CIK case CHIP_BONAIRE: @@ -197,6 +195,9 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size) adev->vce.filp[i] = NULL; } + INIT_DELAYED_WORK(&adev->vce.idle_work, amdgpu_vce_idle_work_handler); + mutex_init(&adev->vce.idle_mutex); + return 0; } @@ -220,6 +221,7 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev) amdgpu_ring_fini(&adev->vce.ring[1]); release_firmware(adev->vce.fw); + mutex_destroy(&adev->vce.idle_mutex); return 0; } @@ -310,37 +312,44 @@ static void amdgpu_vce_idle_work_handler(struct work_struct *work) amdgpu_asic_set_vce_clocks(adev, 0, 0); } } else { - schedule_delayed_work(&adev->vce.idle_work, - msecs_to_jiffies(VCE_IDLE_TIMEOUT_MS)); + schedule_delayed_work(&adev->vce.idle_work, VCE_IDLE_TIMEOUT); } } /** - * amdgpu_vce_note_usage - power up VCE + * amdgpu_vce_ring_begin_use - power up VCE * - * @adev: amdgpu_device pointer + * @ring: amdgpu ring * * Make sure VCE is powerd up when we want to use it */ -static void amdgpu_vce_note_usage(struct amdgpu_device *adev) +void amdgpu_vce_ring_begin_use(struct amdgpu_ring *ring) { - bool streams_changed = false; - bool set_clocks = !cancel_delayed_work_sync(&adev->vce.idle_work); - set_clocks &= schedule_delayed_work(&adev->vce.idle_work, - msecs_to_jiffies(VCE_IDLE_TIMEOUT_MS)); + struct amdgpu_device *adev = ring->adev; + bool set_clocks; - if (adev->pm.dpm_enabled) { - /* XXX figure out if the streams changed */ - streams_changed = false; - } - - if (set_clocks || streams_changed) { + mutex_lock(&adev->vce.idle_mutex); + set_clocks = !cancel_delayed_work_sync(&adev->vce.idle_work); + if (set_clocks) { if (adev->pm.dpm_enabled) { amdgpu_dpm_enable_vce(adev, true); } else { amdgpu_asic_set_vce_clocks(adev, 53300, 40000); } } + mutex_unlock(&adev->vce.idle_mutex); +} + +/** + * amdgpu_vce_ring_end_use - power VCE down + * + * @ring: amdgpu ring + * + * Schedule work to power VCE down again + */ +void amdgpu_vce_ring_end_use(struct amdgpu_ring *ring) +{ + schedule_delayed_work(&ring->adev->vce.idle_work, VCE_IDLE_TIMEOUT); } /** @@ -357,11 +366,10 @@ void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp) int i, r; for (i = 0; i < AMDGPU_MAX_VCE_HANDLES; ++i) { uint32_t handle = atomic_read(&adev->vce.handles[i]); + if (!handle || adev->vce.filp[i] != filp) continue; - amdgpu_vce_note_usage(adev); - r = amdgpu_vce_get_destroy_msg(ring, handle, false, NULL); if (r) DRM_ERROR("Error destroying VCE handle (%d)!\n", r); @@ -437,7 +445,7 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle, ib->ptr[i] = 0x0; r = amdgpu_ib_schedule(ring, 1, ib, NULL, NULL, &f); - job->fence = f; + job->fence = fence_get(f); if (r) goto err; @@ -469,7 +477,6 @@ int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, struct amdgpu_job *job; struct amdgpu_ib *ib; struct fence *f = NULL; - uint64_t dummy; int i, r; r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job); @@ -477,7 +484,6 @@ int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, return r; ib = &job->ibs[0]; - dummy = ib->gpu_addr + 1024; /* stitch together an VCE destroy msg */ ib->length_dw = 0; @@ -485,11 +491,14 @@ int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, ib->ptr[ib->length_dw++] = 0x00000001; /* session cmd */ ib->ptr[ib->length_dw++] = handle; - ib->ptr[ib->length_dw++] = 0x00000014; /* len */ - ib->ptr[ib->length_dw++] = 0x05000005; /* feedback buffer */ - ib->ptr[ib->length_dw++] = upper_32_bits(dummy); - ib->ptr[ib->length_dw++] = dummy; - ib->ptr[ib->length_dw++] = 0x00000001; + ib->ptr[ib->length_dw++] = 0x00000020; /* len */ + ib->ptr[ib->length_dw++] = 0x00000002; /* task info */ + ib->ptr[ib->length_dw++] = 0xffffffff; /* next task info, set to 0xffffffff if no */ + ib->ptr[ib->length_dw++] = 0x00000001; /* destroy session */ + ib->ptr[ib->length_dw++] = 0x00000000; + ib->ptr[ib->length_dw++] = 0x00000000; + ib->ptr[ib->length_dw++] = 0xffffffff; /* feedback is not needed, set to 0xffffffff and firmware will not output feedback */ + ib->ptr[ib->length_dw++] = 0x00000000; ib->ptr[ib->length_dw++] = 0x00000008; /* len */ ib->ptr[ib->length_dw++] = 0x02000001; /* destroy cmd */ @@ -499,7 +508,7 @@ int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle, if (direct) { r = amdgpu_ib_schedule(ring, 1, ib, NULL, NULL, &f); - job->fence = f; + job->fence = fence_get(f); if (r) goto err; @@ -580,12 +589,10 @@ static int amdgpu_vce_cs_reloc(struct amdgpu_cs_parser *p, uint32_t ib_idx, * we we don't have another free session index. */ static int amdgpu_vce_validate_handle(struct amdgpu_cs_parser *p, - uint32_t handle, bool *allocated) + uint32_t handle, uint32_t *allocated) { unsigned i; - *allocated = false; - /* validate the handle */ for (i = 0; i < AMDGPU_MAX_VCE_HANDLES; ++i) { if (atomic_read(&p->adev->vce.handles[i]) == handle) { @@ -602,7 +609,7 @@ static int amdgpu_vce_validate_handle(struct amdgpu_cs_parser *p, if (!atomic_cmpxchg(&p->adev->vce.handles[i], 0, handle)) { p->adev->vce.filp[i] = p->filp; p->adev->vce.img_size[i] = 0; - *allocated = true; + *allocated |= 1 << i; return i; } } @@ -622,15 +629,13 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx) struct amdgpu_ib *ib = &p->job->ibs[ib_idx]; unsigned fb_idx = 0, bs_idx = 0; int session_idx = -1; - bool destroyed = false; - bool created = false; - bool allocated = false; + uint32_t destroyed = 0; + uint32_t created = 0; + uint32_t allocated = 0; uint32_t tmp, handle = 0; uint32_t *size = &tmp; int i, r = 0, idx = 0; - amdgpu_vce_note_usage(p->adev); - while (idx < ib->length_dw) { uint32_t len = amdgpu_get_ib_value(p, ib_idx, idx); uint32_t cmd = amdgpu_get_ib_value(p, ib_idx, idx + 1); @@ -641,30 +646,30 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx) goto out; } - if (destroyed) { - DRM_ERROR("No other command allowed after destroy!\n"); - r = -EINVAL; - goto out; - } - switch (cmd) { - case 0x00000001: // session + case 0x00000001: /* session */ handle = amdgpu_get_ib_value(p, ib_idx, idx + 2); session_idx = amdgpu_vce_validate_handle(p, handle, &allocated); - if (session_idx < 0) - return session_idx; + if (session_idx < 0) { + r = session_idx; + goto out; + } size = &p->adev->vce.img_size[session_idx]; break; - case 0x00000002: // task info + case 0x00000002: /* task info */ fb_idx = amdgpu_get_ib_value(p, ib_idx, idx + 6); bs_idx = amdgpu_get_ib_value(p, ib_idx, idx + 7); break; - case 0x01000001: // create - created = true; - if (!allocated) { + case 0x01000001: /* create */ + created |= 1 << session_idx; + if (destroyed & (1 << session_idx)) { + destroyed &= ~(1 << session_idx); + allocated |= 1 << session_idx; + + } else if (!(allocated & (1 << session_idx))) { DRM_ERROR("Handle already in use!\n"); r = -EINVAL; goto out; @@ -675,16 +680,16 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx) 8 * 3 / 2; break; - case 0x04000001: // config extension - case 0x04000002: // pic control - case 0x04000005: // rate control - case 0x04000007: // motion estimation - case 0x04000008: // rdo - case 0x04000009: // vui - case 0x05000002: // auxiliary buffer + case 0x04000001: /* config extension */ + case 0x04000002: /* pic control */ + case 0x04000005: /* rate control */ + case 0x04000007: /* motion estimation */ + case 0x04000008: /* rdo */ + case 0x04000009: /* vui */ + case 0x05000002: /* auxiliary buffer */ break; - case 0x03000001: // encode + case 0x03000001: /* encode */ r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 10, idx + 9, *size, 0); if (r) @@ -696,18 +701,18 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx) goto out; break; - case 0x02000001: // destroy - destroyed = true; + case 0x02000001: /* destroy */ + destroyed |= 1 << session_idx; break; - case 0x05000001: // context buffer + case 0x05000001: /* context buffer */ r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3, idx + 2, *size * 2, 0); if (r) goto out; break; - case 0x05000004: // video bitstream buffer + case 0x05000004: /* video bitstream buffer */ tmp = amdgpu_get_ib_value(p, ib_idx, idx + 4); r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3, idx + 2, tmp, bs_idx); @@ -715,7 +720,7 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx) goto out; break; - case 0x05000005: // feedback buffer + case 0x05000005: /* feedback buffer */ r = amdgpu_vce_cs_reloc(p, ib_idx, idx + 3, idx + 2, 4096, fb_idx); if (r) @@ -737,21 +742,24 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx) idx += len / 4; } - if (allocated && !created) { + if (allocated & ~created) { DRM_ERROR("New session without create command!\n"); r = -ENOENT; } out: - if ((!r && destroyed) || (r && allocated)) { - /* - * IB contains a destroy msg or we have allocated an - * handle and got an error, anyway free the handle - */ - for (i = 0; i < AMDGPU_MAX_VCE_HANDLES; ++i) - atomic_cmpxchg(&p->adev->vce.handles[i], handle, 0); + if (!r) { + /* No error, free all destroyed handle slots */ + tmp = destroyed; + } else { + /* Error during parsing, free all allocated handle slots */ + tmp = allocated; } + for (i = 0; i < AMDGPU_MAX_VCE_HANDLES; ++i) + if (tmp & (1 << i)) + atomic_set(&p->adev->vce.handles[i], 0); + return r; } @@ -837,10 +845,10 @@ int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring) * @ring: the engine to test on * */ -int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring) +int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout) { struct fence *fence = NULL; - int r; + long r; /* skip vce ring1 ib test for now, since it's not reliable */ if (ring == &ring->adev->vce.ring[1]) @@ -848,21 +856,25 @@ int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring) r = amdgpu_vce_get_create_msg(ring, 1, NULL); if (r) { - DRM_ERROR("amdgpu: failed to get create msg (%d).\n", r); + DRM_ERROR("amdgpu: failed to get create msg (%ld).\n", r); goto error; } r = amdgpu_vce_get_destroy_msg(ring, 1, true, &fence); if (r) { - DRM_ERROR("amdgpu: failed to get destroy ib (%d).\n", r); + DRM_ERROR("amdgpu: failed to get destroy ib (%ld).\n", r); goto error; } - r = fence_wait(fence, false); - if (r) { - DRM_ERROR("amdgpu: fence wait failed (%d).\n", r); + r = fence_wait_timeout(fence, false, timeout); + if (r == 0) { + DRM_ERROR("amdgpu: IB test timed out.\n"); + r = -ETIMEDOUT; + } else if (r < 0) { + DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r); } else { DRM_INFO("ib test on ring %d succeeded\n", ring->idx); + r = 0; } error: fence_put(fence); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h index f40cf761c66f..63f83d0d985c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h @@ -39,6 +39,8 @@ void amdgpu_vce_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib, void amdgpu_vce_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq, unsigned flags); int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring); -int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring); +int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout); +void amdgpu_vce_ring_begin_use(struct amdgpu_ring *ring); +void amdgpu_vce_ring_end_use(struct amdgpu_ring *ring); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 9f36ed30ba11..8e642fc48df4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -25,6 +25,7 @@ * Alex Deucher * Jerome Glisse */ +#include #include #include #include "amdgpu.h" @@ -114,16 +115,26 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm, /** * amdgpu_vm_get_bos - add the vm BOs to a duplicates list * + * @adev: amdgpu device pointer * @vm: vm providing the BOs * @duplicates: head of duplicates list * * Add the page directory to the BO duplicates list * for command submission. */ -void amdgpu_vm_get_pt_bos(struct amdgpu_vm *vm, struct list_head *duplicates) +void amdgpu_vm_get_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm, + struct list_head *duplicates) { + uint64_t num_evictions; unsigned i; + /* We only need to validate the page tables + * if they aren't already valid. + */ + num_evictions = atomic64_read(&adev->num_evictions); + if (num_evictions == vm->last_eviction_counter) + return; + /* add the vm page table to the list */ for (i = 0; i <= vm->max_pde_used; ++i) { struct amdgpu_bo_list_entry *entry = &vm->page_tables[i].entry; @@ -162,6 +173,13 @@ void amdgpu_vm_move_pt_bos_in_lru(struct amdgpu_device *adev, spin_unlock(&glob->lru_lock); } +static bool amdgpu_vm_is_gpu_reset(struct amdgpu_device *adev, + struct amdgpu_vm_id *id) +{ + return id->current_gpu_reset_count != + atomic_read(&adev->gpu_reset_counter) ? true : false; +} + /** * amdgpu_vm_grab_id - allocate the next free VMID * @@ -174,18 +192,67 @@ void amdgpu_vm_move_pt_bos_in_lru(struct amdgpu_device *adev, */ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, struct amdgpu_sync *sync, struct fence *fence, - unsigned *vm_id, uint64_t *vm_pd_addr) + struct amdgpu_job *job) { - uint64_t pd_addr = amdgpu_bo_gpu_offset(vm->page_directory); struct amdgpu_device *adev = ring->adev; + uint64_t fence_context = adev->fence_context + ring->idx; struct fence *updates = sync->last_vm_update; - struct amdgpu_vm_id *id; - unsigned i = ring->idx; - int r; + struct amdgpu_vm_id *id, *idle; + struct fence **fences; + unsigned i; + int r = 0; + + fences = kmalloc_array(sizeof(void *), adev->vm_manager.num_ids, + GFP_KERNEL); + if (!fences) + return -ENOMEM; mutex_lock(&adev->vm_manager.lock); + /* Check if we have an idle VMID */ + i = 0; + list_for_each_entry(idle, &adev->vm_manager.ids_lru, list) { + fences[i] = amdgpu_sync_peek_fence(&idle->active, ring); + if (!fences[i]) + break; + ++i; + } + + /* If we can't find a idle VMID to use, wait till one becomes available */ + if (&idle->list == &adev->vm_manager.ids_lru) { + u64 fence_context = adev->vm_manager.fence_context + ring->idx; + unsigned seqno = ++adev->vm_manager.seqno[ring->idx]; + struct fence_array *array; + unsigned j; + + for (j = 0; j < i; ++j) + fence_get(fences[j]); + + array = fence_array_create(i, fences, fence_context, + seqno, true); + if (!array) { + for (j = 0; j < i; ++j) + fence_put(fences[j]); + kfree(fences); + r = -ENOMEM; + goto error; + } + + + r = amdgpu_sync_fence(ring->adev, sync, &array->base); + fence_put(&array->base); + if (r) + goto error; + + mutex_unlock(&adev->vm_manager.lock); + return 0; + + } + kfree(fences); + + job->vm_needs_flush = true; /* Check if we can use a VMID already assigned to this VM */ + i = ring->idx; do { struct fence *flushed; @@ -196,67 +263,52 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, /* Check all the prerequisites to using this VMID */ if (!id) continue; + if (amdgpu_vm_is_gpu_reset(adev, id)) + continue; if (atomic64_read(&id->owner) != vm->client_id) continue; - if (pd_addr != id->pd_gpu_addr) + if (job->vm_pd_addr != id->pd_gpu_addr) continue; - if (id->last_user != ring && - (!id->last_flush || !fence_is_signaled(id->last_flush))) + if (!id->last_flush) + continue; + + if (id->last_flush->context != fence_context && + !fence_is_signaled(id->last_flush)) continue; flushed = id->flushed_updates; - if (updates && (!flushed || fence_is_later(updates, flushed))) + if (updates && + (!flushed || fence_is_later(updates, flushed))) continue; - /* Good we can use this VMID */ - if (id->last_user == ring) { - r = amdgpu_sync_fence(ring->adev, sync, - id->first); - if (r) - goto error; - } - - /* And remember this submission as user of the VMID */ + /* Good we can use this VMID. Remember this submission as + * user of the VMID. + */ r = amdgpu_sync_fence(ring->adev, &id->active, fence); if (r) goto error; + id->current_gpu_reset_count = atomic_read(&adev->gpu_reset_counter); list_move_tail(&id->list, &adev->vm_manager.ids_lru); vm->ids[ring->idx] = id; - *vm_id = id - adev->vm_manager.ids; - *vm_pd_addr = AMDGPU_VM_NO_FLUSH; - trace_amdgpu_vm_grab_id(vm, ring->idx, *vm_id, *vm_pd_addr); + job->vm_id = id - adev->vm_manager.ids; + job->vm_needs_flush = false; + trace_amdgpu_vm_grab_id(vm, ring->idx, job); mutex_unlock(&adev->vm_manager.lock); return 0; } while (i != ring->idx); - id = list_first_entry(&adev->vm_manager.ids_lru, - struct amdgpu_vm_id, - list); + /* Still no ID to use? Then use the idle one found earlier */ + id = idle; - if (!amdgpu_sync_is_idle(&id->active)) { - struct list_head *head = &adev->vm_manager.ids_lru; - struct amdgpu_vm_id *tmp; - - list_for_each_entry_safe(id, tmp, &adev->vm_manager.ids_lru, - list) { - if (amdgpu_sync_is_idle(&id->active)) { - list_move(&id->list, head); - head = &id->list; - } - } - id = list_first_entry(&adev->vm_manager.ids_lru, - struct amdgpu_vm_id, - list); - } - - r = amdgpu_sync_cycle_fences(sync, &id->active, fence); + /* Remember this submission as user of the VMID */ + r = amdgpu_sync_fence(ring->adev, &id->active, fence); if (r) goto error; @@ -269,22 +321,46 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, fence_put(id->flushed_updates); id->flushed_updates = fence_get(updates); - id->pd_gpu_addr = pd_addr; - + id->pd_gpu_addr = job->vm_pd_addr; + id->current_gpu_reset_count = atomic_read(&adev->gpu_reset_counter); list_move_tail(&id->list, &adev->vm_manager.ids_lru); - id->last_user = ring; atomic64_set(&id->owner, vm->client_id); vm->ids[ring->idx] = id; - *vm_id = id - adev->vm_manager.ids; - *vm_pd_addr = pd_addr; - trace_amdgpu_vm_grab_id(vm, ring->idx, *vm_id, *vm_pd_addr); + job->vm_id = id - adev->vm_manager.ids; + trace_amdgpu_vm_grab_id(vm, ring->idx, job); error: mutex_unlock(&adev->vm_manager.lock); return r; } +static bool amdgpu_vm_ring_has_compute_vm_bug(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + const struct amdgpu_ip_block_version *ip_block; + + if (ring->type != AMDGPU_RING_TYPE_COMPUTE) + /* only compute rings */ + return false; + + ip_block = amdgpu_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX); + if (!ip_block) + return false; + + if (ip_block->major <= 7) { + /* gfx7 has no workaround */ + return true; + } else if (ip_block->major == 8) { + if (adev->gfx.mec_fw_version >= 673) + /* gfx8 is fixed in MEC firmware 673 */ + return false; + else + return true; + } + return false; +} + /** * amdgpu_vm_flush - hardware flush the vm * @@ -294,59 +370,52 @@ int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring, * * Emit a VM flush when it is necessary. */ -int amdgpu_vm_flush(struct amdgpu_ring *ring, - unsigned vm_id, uint64_t pd_addr, - uint32_t gds_base, uint32_t gds_size, - uint32_t gws_base, uint32_t gws_size, - uint32_t oa_base, uint32_t oa_size) +int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job) { struct amdgpu_device *adev = ring->adev; - struct amdgpu_vm_id *id = &adev->vm_manager.ids[vm_id]; + struct amdgpu_vm_id *id = &adev->vm_manager.ids[job->vm_id]; bool gds_switch_needed = ring->funcs->emit_gds_switch && ( - id->gds_base != gds_base || - id->gds_size != gds_size || - id->gws_base != gws_base || - id->gws_size != gws_size || - id->oa_base != oa_base || - id->oa_size != oa_size); + id->gds_base != job->gds_base || + id->gds_size != job->gds_size || + id->gws_base != job->gws_base || + id->gws_size != job->gws_size || + id->oa_base != job->oa_base || + id->oa_size != job->oa_size); int r; if (ring->funcs->emit_pipeline_sync && ( - pd_addr != AMDGPU_VM_NO_FLUSH || gds_switch_needed || - ring->type == AMDGPU_RING_TYPE_COMPUTE)) + job->vm_needs_flush || gds_switch_needed || + amdgpu_vm_ring_has_compute_vm_bug(ring))) amdgpu_ring_emit_pipeline_sync(ring); - if (ring->funcs->emit_vm_flush && - pd_addr != AMDGPU_VM_NO_FLUSH) { + if (ring->funcs->emit_vm_flush && (job->vm_needs_flush || + amdgpu_vm_is_gpu_reset(adev, id))) { struct fence *fence; - trace_amdgpu_vm_flush(pd_addr, ring->idx, vm_id); - amdgpu_ring_emit_vm_flush(ring, vm_id, pd_addr); + trace_amdgpu_vm_flush(job->vm_pd_addr, ring->idx, job->vm_id); + amdgpu_ring_emit_vm_flush(ring, job->vm_id, job->vm_pd_addr); + + r = amdgpu_fence_emit(ring, &fence); + if (r) + return r; mutex_lock(&adev->vm_manager.lock); - if ((id->pd_gpu_addr == pd_addr) && (id->last_user == ring)) { - r = amdgpu_fence_emit(ring, &fence); - if (r) { - mutex_unlock(&adev->vm_manager.lock); - return r; - } - fence_put(id->last_flush); - id->last_flush = fence; - } + fence_put(id->last_flush); + id->last_flush = fence; mutex_unlock(&adev->vm_manager.lock); } if (gds_switch_needed) { - id->gds_base = gds_base; - id->gds_size = gds_size; - id->gws_base = gws_base; - id->gws_size = gws_size; - id->oa_base = oa_base; - id->oa_size = oa_size; - amdgpu_ring_emit_gds_switch(ring, vm_id, - gds_base, gds_size, - gws_base, gws_size, - oa_base, oa_size); + id->gds_base = job->gds_base; + id->gds_size = job->gds_size; + id->gws_base = job->gws_base; + id->gws_size = job->gws_size; + id->oa_base = job->oa_base; + id->oa_size = job->oa_size; + amdgpu_ring_emit_gds_switch(ring, job->vm_id, + job->gds_base, job->gds_size, + job->gws_base, job->gws_size, + job->oa_base, job->oa_size); } return 0; @@ -723,7 +792,7 @@ static void amdgpu_vm_frag_ptes(struct amdgpu_device *adev, * @vm: requested vm * @start: start of GPU address range * @end: end of GPU address range - * @dst: destination address to map to + * @dst: destination address to map to, the next dst inside the function * @flags: mapping flags * * Update the page tables in the range @start - @end. @@ -737,49 +806,75 @@ static void amdgpu_vm_update_ptes(struct amdgpu_device *adev, { const uint64_t mask = AMDGPU_VM_PTE_COUNT - 1; - uint64_t last_pe_start = ~0, last_pe_end = ~0, last_dst = ~0; - uint64_t addr; + uint64_t cur_pe_start, cur_pe_end, cur_dst; + uint64_t addr; /* next GPU address to be updated */ + uint64_t pt_idx; + struct amdgpu_bo *pt; + unsigned nptes; /* next number of ptes to be updated */ + uint64_t next_pe_start; + + /* initialize the variables */ + addr = start; + pt_idx = addr >> amdgpu_vm_block_size; + pt = vm->page_tables[pt_idx].entry.robj; + + if ((addr & ~mask) == (end & ~mask)) + nptes = end - addr; + else + nptes = AMDGPU_VM_PTE_COUNT - (addr & mask); + + cur_pe_start = amdgpu_bo_gpu_offset(pt); + cur_pe_start += (addr & mask) * 8; + cur_pe_end = cur_pe_start + 8 * nptes; + cur_dst = dst; + + /* for next ptb*/ + addr += nptes; + dst += nptes * AMDGPU_GPU_PAGE_SIZE; /* walk over the address space and update the page tables */ - for (addr = start; addr < end; ) { - uint64_t pt_idx = addr >> amdgpu_vm_block_size; - struct amdgpu_bo *pt = vm->page_tables[pt_idx].entry.robj; - unsigned nptes; - uint64_t pe_start; + while (addr < end) { + pt_idx = addr >> amdgpu_vm_block_size; + pt = vm->page_tables[pt_idx].entry.robj; if ((addr & ~mask) == (end & ~mask)) nptes = end - addr; else nptes = AMDGPU_VM_PTE_COUNT - (addr & mask); - pe_start = amdgpu_bo_gpu_offset(pt); - pe_start += (addr & mask) * 8; + next_pe_start = amdgpu_bo_gpu_offset(pt); + next_pe_start += (addr & mask) * 8; - if (last_pe_end != pe_start) { - - amdgpu_vm_frag_ptes(adev, vm_update_params, - last_pe_start, last_pe_end, - last_dst, flags); - - last_pe_start = pe_start; - last_pe_end = pe_start + 8 * nptes; - last_dst = dst; + if (cur_pe_end == next_pe_start) { + /* The next ptb is consecutive to current ptb. + * Don't call amdgpu_vm_frag_ptes now. + * Will update two ptbs together in future. + */ + cur_pe_end += 8 * nptes; } else { - last_pe_end += 8 * nptes; + amdgpu_vm_frag_ptes(adev, vm_update_params, + cur_pe_start, cur_pe_end, + cur_dst, flags); + + cur_pe_start = next_pe_start; + cur_pe_end = next_pe_start + 8 * nptes; + cur_dst = dst; } + /* for next ptb*/ addr += nptes; dst += nptes * AMDGPU_GPU_PAGE_SIZE; } - amdgpu_vm_frag_ptes(adev, vm_update_params, last_pe_start, - last_pe_end, last_dst, flags); + amdgpu_vm_frag_ptes(adev, vm_update_params, cur_pe_start, + cur_pe_end, cur_dst, flags); } /** * amdgpu_vm_bo_update_mapping - update a mapping in the vm page table * * @adev: amdgpu_device pointer + * @exclusive: fence we need to sync to * @src: address where to copy page table entries from * @pages_addr: DMA addresses to use for mapping * @vm: requested vm @@ -793,6 +888,7 @@ static void amdgpu_vm_update_ptes(struct amdgpu_device *adev, * Returns 0 for success, -EINVAL for failure. */ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, + struct fence *exclusive, uint64_t src, dma_addr_t *pages_addr, struct amdgpu_vm *vm, @@ -853,6 +949,10 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, vm_update_params.ib = &job->ibs[0]; + r = amdgpu_sync_fence(adev, &job->sync, exclusive); + if (r) + goto error_free; + r = amdgpu_sync_resv(adev, &job->sync, vm->page_directory->tbo.resv, owner); if (r) @@ -889,6 +989,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, * amdgpu_vm_bo_split_mapping - split a mapping into smaller chunks * * @adev: amdgpu_device pointer + * @exclusive: fence we need to sync to * @gtt_flags: flags as they are used for GTT * @pages_addr: DMA addresses to use for mapping * @vm: requested vm @@ -902,6 +1003,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, * Returns 0 for success, -EINVAL for failure. */ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev, + struct fence *exclusive, uint32_t gtt_flags, dma_addr_t *pages_addr, struct amdgpu_vm *vm, @@ -932,7 +1034,8 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev, addr += mapping->offset; if (!pages_addr || src) - return amdgpu_vm_bo_update_mapping(adev, src, pages_addr, vm, + return amdgpu_vm_bo_update_mapping(adev, exclusive, + src, pages_addr, vm, start, mapping->it.last, flags, addr, fence); @@ -940,7 +1043,8 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev, uint64_t last; last = min((uint64_t)mapping->it.last, start + max_size - 1); - r = amdgpu_vm_bo_update_mapping(adev, src, pages_addr, vm, + r = amdgpu_vm_bo_update_mapping(adev, exclusive, + src, pages_addr, vm, start, last, flags, addr, fence); if (r) @@ -973,6 +1077,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va_mapping *mapping; dma_addr_t *pages_addr = NULL; uint32_t gtt_flags, flags; + struct fence *exclusive; uint64_t addr; int r; @@ -994,8 +1099,11 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, default: break; } + + exclusive = reservation_object_get_excl(bo_va->bo->tbo.resv); } else { addr = 0; + exclusive = NULL; } flags = amdgpu_ttm_tt_pte_flags(adev, bo_va->bo->tbo.ttm, mem); @@ -1007,7 +1115,8 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, spin_unlock(&vm->status_lock); list_for_each_entry(mapping, &bo_va->invalids, list) { - r = amdgpu_vm_bo_split_mapping(adev, gtt_flags, pages_addr, vm, + r = amdgpu_vm_bo_split_mapping(adev, exclusive, + gtt_flags, pages_addr, vm, mapping, flags, addr, &bo_va->last_pt_update); if (r) @@ -1054,7 +1163,7 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev, struct amdgpu_bo_va_mapping, list); list_del(&mapping->list); - r = amdgpu_vm_bo_split_mapping(adev, 0, NULL, vm, mapping, + r = amdgpu_vm_bo_split_mapping(adev, NULL, 0, NULL, vm, mapping, 0, 0, NULL); kfree(mapping); if (r) @@ -1445,6 +1554,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) amdgpu_bo_unreserve(vm->page_directory); if (r) goto error_free_page_directory; + vm->last_eviction_counter = atomic64_read(&adev->num_evictions); return 0; @@ -1516,6 +1626,10 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev) &adev->vm_manager.ids_lru); } + adev->vm_manager.fence_context = fence_context_alloc(AMDGPU_MAX_RINGS); + for (i = 0; i < AMDGPU_MAX_RINGS; ++i) + adev->vm_manager.seqno[i] = 0; + atomic_set(&adev->vm_manager.vm_pte_next_ring, 0); atomic64_set(&adev->vm_manager.client_counter, 0); } diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c index 48b6bd671cda..c32eca26155c 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c @@ -98,6 +98,7 @@ amdgpu_atombios_encoder_set_backlight_level(struct amdgpu_encoder *amdgpu_encode case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA: case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1: case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2: + case ENCODER_OBJECT_ID_INTERNAL_UNIPHY3: if (dig->backlight_level == 0) amdgpu_atombios_encoder_setup_dig_transmitter(encoder, ATOM_TRANSMITTER_ACTION_LCD_BLOFF, 0, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c index 13cdb01e9b45..bc56c8a181e6 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.c @@ -156,3 +156,18 @@ u32 amdgpu_atombios_i2c_func(struct i2c_adapter *adap) return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; } +void amdgpu_atombios_i2c_channel_trans(struct amdgpu_device* adev, u8 slave_addr, u8 line_number, u8 offset, u8 data) +{ + PROCESS_I2C_CHANNEL_TRANSACTION_PS_ALLOCATION args; + int index = GetIndexIntoMasterTable(COMMAND, ProcessI2cChannelTransaction); + + args.ucRegIndex = offset; + args.lpI2CDataOut = data; + args.ucFlag = 1; + args.ucI2CSpeed = TARGET_HW_I2C_CLOCK; + args.ucTransBytes = 1; + args.ucSlaveAddr = slave_addr; + args.ucLineNumber = line_number; + + amdgpu_atom_execute_table(adev->mode_info.atom_context, index, (uint32_t *)&args); +} diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h index d6128d9de56e..251aaf41f65d 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h +++ b/drivers/gpu/drm/amd/amdgpu/atombios_i2c.h @@ -27,5 +27,7 @@ int amdgpu_atombios_i2c_xfer(struct i2c_adapter *i2c_adap, struct i2c_msg *msgs, int num); u32 amdgpu_atombios_i2c_func(struct i2c_adapter *adap); +void amdgpu_atombios_i2c_channel_trans(struct amdgpu_device* adev, + u8 slave_addr, u8 line_number, u8 offset, u8 data); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c index ea407db1fbcf..e2f0e5d58d5c 100644 --- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c @@ -50,7 +50,9 @@ #include "gmc/gmc_7_1_sh_mask.h" MODULE_FIRMWARE("radeon/bonaire_smc.bin"); +MODULE_FIRMWARE("radeon/bonaire_k_smc.bin"); MODULE_FIRMWARE("radeon/hawaii_smc.bin"); +MODULE_FIRMWARE("radeon/hawaii_k_smc.bin"); #define MC_CG_ARB_FREQ_F0 0x0a #define MC_CG_ARB_FREQ_F1 0x0b @@ -84,12 +86,14 @@ static const struct ci_pt_defaults defaults_bonaire_xt = { 0x17C, 0x172, 0x180, 0x1BC, 0x1B3, 0x1BD, 0x206, 0x200, 0x203, 0x25D, 0x25A, 0x255, 0x2C3, 0x2C5, 0x2B4 } }; +#if 0 static const struct ci_pt_defaults defaults_bonaire_pro = { 1, 0xF, 0xFD, 0x19, 5, 45, 0, 0x65062, { 0x8C, 0x23F, 0x244, 0xA6, 0x83, 0x85, 0x86, 0x86, 0x83, 0xDB, 0xDB, 0xDA, 0x67, 0x60, 0x5F }, { 0x187, 0x193, 0x193, 0x1C7, 0x1D1, 0x1D1, 0x210, 0x219, 0x219, 0x266, 0x26C, 0x26C, 0x2C9, 0x2CB, 0x2CB } }; +#endif static const struct ci_pt_defaults defaults_saturn_xt = { @@ -98,12 +102,14 @@ static const struct ci_pt_defaults defaults_saturn_xt = { 0x187, 0x187, 0x187, 0x1C7, 0x1C7, 0x1C7, 0x210, 0x210, 0x210, 0x266, 0x266, 0x266, 0x2C9, 0x2C9, 0x2C9 } }; +#if 0 static const struct ci_pt_defaults defaults_saturn_pro = { 1, 0xF, 0xFD, 0x19, 5, 55, 0, 0x30000, { 0x96, 0x21D, 0x23B, 0xA1, 0x85, 0x87, 0x83, 0x84, 0x81, 0xE6, 0xE6, 0xE6, 0x71, 0x6A, 0x6A }, { 0x193, 0x19E, 0x19E, 0x1D2, 0x1DC, 0x1DC, 0x21A, 0x223, 0x223, 0x26E, 0x27E, 0x274, 0x2CF, 0x2D2, 0x2D2 } }; +#endif static const struct ci_pt_config_reg didt_config_ci[] = { @@ -736,19 +742,19 @@ static int ci_enable_didt(struct amdgpu_device *adev, bool enable) if (pi->caps_sq_ramping || pi->caps_db_ramping || pi->caps_td_ramping || pi->caps_tcp_ramping) { - gfx_v7_0_enter_rlc_safe_mode(adev); + adev->gfx.rlc.funcs->enter_safe_mode(adev); if (enable) { ret = ci_program_pt_config_registers(adev, didt_config_ci); if (ret) { - gfx_v7_0_exit_rlc_safe_mode(adev); + adev->gfx.rlc.funcs->exit_safe_mode(adev); return ret; } } ci_do_enable_didt(adev, enable); - gfx_v7_0_exit_rlc_safe_mode(adev); + adev->gfx.rlc.funcs->exit_safe_mode(adev); } return 0; @@ -3030,7 +3036,7 @@ static int ci_populate_single_memory_level(struct amdgpu_device *adev, if (pi->mclk_stutter_mode_threshold && (memory_clock <= pi->mclk_stutter_mode_threshold) && - (pi->uvd_enabled == false) && + (!pi->uvd_enabled) && (RREG32(mmDPG_PIPE_STUTTER_CONTROL) & DPG_PIPE_STUTTER_CONTROL__STUTTER_ENABLE_MASK) && (adev->pm.dpm.new_active_crtc_count <= 2)) memory_level->StutterEnable = true; @@ -3636,6 +3642,10 @@ static int ci_setup_default_dpm_tables(struct amdgpu_device *adev) ci_setup_default_pcie_tables(adev); + /* save a copy of the default DPM table */ + memcpy(&(pi->golden_dpm_table), &(pi->dpm_table), + sizeof(struct ci_dpm_table)); + return 0; } @@ -5754,10 +5764,18 @@ static int ci_dpm_init_microcode(struct amdgpu_device *adev) switch (adev->asic_type) { case CHIP_BONAIRE: - chip_name = "bonaire"; + if ((adev->pdev->revision == 0x80) || + (adev->pdev->revision == 0x81) || + (adev->pdev->device == 0x665f)) + chip_name = "bonaire_k"; + else + chip_name = "bonaire"; break; case CHIP_HAWAII: - chip_name = "hawaii"; + if (adev->pdev->revision == 0x80) + chip_name = "hawaii_k"; + else + chip_name = "hawaii"; break; case CHIP_KAVERI: case CHIP_KABINI: @@ -6221,6 +6239,9 @@ static int ci_dpm_sw_fini(void *handle) ci_dpm_fini(adev); mutex_unlock(&adev->pm.mutex); + release_firmware(adev->pm.fw); + adev->pm.fw = NULL; + return 0; } @@ -6401,6 +6422,186 @@ static int ci_dpm_set_powergating_state(void *handle, return 0; } +static int ci_dpm_print_clock_levels(struct amdgpu_device *adev, + enum pp_clock_type type, char *buf) +{ + struct ci_power_info *pi = ci_get_pi(adev); + struct ci_single_dpm_table *sclk_table = &pi->dpm_table.sclk_table; + struct ci_single_dpm_table *mclk_table = &pi->dpm_table.mclk_table; + struct ci_single_dpm_table *pcie_table = &pi->dpm_table.pcie_speed_table; + + int i, now, size = 0; + uint32_t clock, pcie_speed; + + switch (type) { + case PP_SCLK: + amdgpu_ci_send_msg_to_smc(adev, PPSMC_MSG_API_GetSclkFrequency); + clock = RREG32(mmSMC_MSG_ARG_0); + + for (i = 0; i < sclk_table->count; i++) { + if (clock > sclk_table->dpm_levels[i].value) + continue; + break; + } + now = i; + + for (i = 0; i < sclk_table->count; i++) + size += sprintf(buf + size, "%d: %uMhz %s\n", + i, sclk_table->dpm_levels[i].value / 100, + (i == now) ? "*" : ""); + break; + case PP_MCLK: + amdgpu_ci_send_msg_to_smc(adev, PPSMC_MSG_API_GetMclkFrequency); + clock = RREG32(mmSMC_MSG_ARG_0); + + for (i = 0; i < mclk_table->count; i++) { + if (clock > mclk_table->dpm_levels[i].value) + continue; + break; + } + now = i; + + for (i = 0; i < mclk_table->count; i++) + size += sprintf(buf + size, "%d: %uMhz %s\n", + i, mclk_table->dpm_levels[i].value / 100, + (i == now) ? "*" : ""); + break; + case PP_PCIE: + pcie_speed = ci_get_current_pcie_speed(adev); + for (i = 0; i < pcie_table->count; i++) { + if (pcie_speed != pcie_table->dpm_levels[i].value) + continue; + break; + } + now = i; + + for (i = 0; i < pcie_table->count; i++) + size += sprintf(buf + size, "%d: %s %s\n", i, + (pcie_table->dpm_levels[i].value == 0) ? "2.5GB, x1" : + (pcie_table->dpm_levels[i].value == 1) ? "5.0GB, x16" : + (pcie_table->dpm_levels[i].value == 2) ? "8.0GB, x16" : "", + (i == now) ? "*" : ""); + break; + default: + break; + } + + return size; +} + +static int ci_dpm_force_clock_level(struct amdgpu_device *adev, + enum pp_clock_type type, uint32_t mask) +{ + struct ci_power_info *pi = ci_get_pi(adev); + + if (adev->pm.dpm.forced_level + != AMDGPU_DPM_FORCED_LEVEL_MANUAL) + return -EINVAL; + + switch (type) { + case PP_SCLK: + if (!pi->sclk_dpm_key_disabled) + amdgpu_ci_send_msg_to_smc_with_parameter(adev, + PPSMC_MSG_SCLKDPM_SetEnabledMask, + pi->dpm_level_enable_mask.sclk_dpm_enable_mask & mask); + break; + + case PP_MCLK: + if (!pi->mclk_dpm_key_disabled) + amdgpu_ci_send_msg_to_smc_with_parameter(adev, + PPSMC_MSG_MCLKDPM_SetEnabledMask, + pi->dpm_level_enable_mask.mclk_dpm_enable_mask & mask); + break; + + case PP_PCIE: + { + uint32_t tmp = mask & pi->dpm_level_enable_mask.pcie_dpm_enable_mask; + uint32_t level = 0; + + while (tmp >>= 1) + level++; + + if (!pi->pcie_dpm_key_disabled) + amdgpu_ci_send_msg_to_smc_with_parameter(adev, + PPSMC_MSG_PCIeDPM_ForceLevel, + level); + break; + } + default: + break; + } + + return 0; +} + +static int ci_dpm_get_sclk_od(struct amdgpu_device *adev) +{ + struct ci_power_info *pi = ci_get_pi(adev); + struct ci_single_dpm_table *sclk_table = &(pi->dpm_table.sclk_table); + struct ci_single_dpm_table *golden_sclk_table = + &(pi->golden_dpm_table.sclk_table); + int value; + + value = (sclk_table->dpm_levels[sclk_table->count - 1].value - + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value) * + 100 / + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value; + + return value; +} + +static int ci_dpm_set_sclk_od(struct amdgpu_device *adev, uint32_t value) +{ + struct ci_power_info *pi = ci_get_pi(adev); + struct ci_ps *ps = ci_get_ps(adev->pm.dpm.requested_ps); + struct ci_single_dpm_table *golden_sclk_table = + &(pi->golden_dpm_table.sclk_table); + + if (value > 20) + value = 20; + + ps->performance_levels[ps->performance_level_count - 1].sclk = + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value * + value / 100 + + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value; + + return 0; +} + +static int ci_dpm_get_mclk_od(struct amdgpu_device *adev) +{ + struct ci_power_info *pi = ci_get_pi(adev); + struct ci_single_dpm_table *mclk_table = &(pi->dpm_table.mclk_table); + struct ci_single_dpm_table *golden_mclk_table = + &(pi->golden_dpm_table.mclk_table); + int value; + + value = (mclk_table->dpm_levels[mclk_table->count - 1].value - + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value) * + 100 / + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value; + + return value; +} + +static int ci_dpm_set_mclk_od(struct amdgpu_device *adev, uint32_t value) +{ + struct ci_power_info *pi = ci_get_pi(adev); + struct ci_ps *ps = ci_get_ps(adev->pm.dpm.requested_ps); + struct ci_single_dpm_table *golden_mclk_table = + &(pi->golden_dpm_table.mclk_table); + + if (value > 20) + value = 20; + + ps->performance_levels[ps->performance_level_count - 1].mclk = + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value * + value / 100 + + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value; + + return 0; +} + const struct amd_ip_funcs ci_dpm_ip_funcs = { .name = "ci_dpm", .early_init = ci_dpm_early_init, @@ -6435,6 +6636,12 @@ static const struct amdgpu_dpm_funcs ci_dpm_funcs = { .get_fan_control_mode = &ci_dpm_get_fan_control_mode, .set_fan_speed_percent = &ci_dpm_set_fan_speed_percent, .get_fan_speed_percent = &ci_dpm_get_fan_speed_percent, + .print_clock_levels = ci_dpm_print_clock_levels, + .force_clock_level = ci_dpm_force_clock_level, + .get_sclk_od = ci_dpm_get_sclk_od, + .set_sclk_od = ci_dpm_set_sclk_od, + .get_mclk_od = ci_dpm_get_mclk_od, + .set_mclk_od = ci_dpm_set_mclk_od, }; static void ci_dpm_set_dpm_funcs(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.h b/drivers/gpu/drm/amd/amdgpu/ci_dpm.h index faccc30c93bf..91be2996ae7c 100644 --- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.h +++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.h @@ -193,6 +193,7 @@ struct ci_pt_defaults { struct ci_power_info { struct ci_dpm_table dpm_table; + struct ci_dpm_table golden_dpm_table; u32 voltage_control; u32 mvdd_control; u32 vddci_control; diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c index 07bc795a4ca9..4efc901f658c 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik.c +++ b/drivers/gpu/drm/amd/amdgpu/cik.c @@ -879,7 +879,7 @@ static void cik_vga_set_state(struct amdgpu_device *adev, bool state) uint32_t tmp; tmp = RREG32(mmCONFIG_CNTL); - if (state == false) + if (!state) tmp |= CONFIG_CNTL__VGA_DIS_MASK; else tmp &= ~CONFIG_CNTL__VGA_DIS_MASK; @@ -962,6 +962,12 @@ static bool cik_read_bios_from_rom(struct amdgpu_device *adev, return true; } +static u32 cik_get_virtual_caps(struct amdgpu_device *adev) +{ + /* CIK does not support SR-IOV */ + return 0; +} + static const struct amdgpu_allowed_register_entry cik_allowed_read_registers[] = { {mmGRBM_STATUS, false}, {mmGB_ADDR_CONFIG, false}, @@ -1029,12 +1035,12 @@ static uint32_t cik_read_indexed_register(struct amdgpu_device *adev, mutex_lock(&adev->grbm_idx_mutex); if (se_num != 0xffffffff || sh_num != 0xffffffff) - gfx_v7_0_select_se_sh(adev, se_num, sh_num); + amdgpu_gfx_select_se_sh(adev, se_num, sh_num, 0xffffffff); val = RREG32(reg_offset); if (se_num != 0xffffffff || sh_num != 0xffffffff) - gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); mutex_unlock(&adev->grbm_idx_mutex); return val; } @@ -1152,10 +1158,11 @@ static void kv_restore_regs_for_reset(struct amdgpu_device *adev, WREG32(mmGMCON_RENG_EXECUTE, save->gmcon_reng_execute); } -static void cik_gpu_pci_config_reset(struct amdgpu_device *adev) +static int cik_gpu_pci_config_reset(struct amdgpu_device *adev) { struct kv_reset_save_regs kv_save = { 0 }; u32 i; + int r = -EINVAL; dev_info(adev->dev, "GPU pci config reset\n"); @@ -1171,14 +1178,20 @@ static void cik_gpu_pci_config_reset(struct amdgpu_device *adev) /* wait for asic to come out of reset */ for (i = 0; i < adev->usec_timeout; i++) { - if (RREG32(mmCONFIG_MEMSIZE) != 0xffffffff) + if (RREG32(mmCONFIG_MEMSIZE) != 0xffffffff) { + /* enable BM */ + pci_set_master(adev->pdev); + r = 0; break; + } udelay(1); } /* does asic init need to be run first??? */ if (adev->flags & AMD_IS_APU) kv_restore_regs_for_reset(adev, &kv_save); + + return r; } static void cik_set_bios_scratch_engine_hung(struct amdgpu_device *adev, bool hung) @@ -1204,13 +1217,14 @@ static void cik_set_bios_scratch_engine_hung(struct amdgpu_device *adev, bool hu */ static int cik_asic_reset(struct amdgpu_device *adev) { + int r; cik_set_bios_scratch_engine_hung(adev, true); - cik_gpu_pci_config_reset(adev); + r = cik_gpu_pci_config_reset(adev); cik_set_bios_scratch_engine_hung(adev, false); - return 0; + return r; } static int cik_set_uvd_clock(struct amdgpu_device *adev, u32 clock, @@ -2007,9 +2021,7 @@ static const struct amdgpu_asic_funcs cik_asic_funcs = .get_xclk = &cik_get_xclk, .set_uvd_clocks = &cik_set_uvd_clocks, .set_vce_clocks = &cik_set_vce_clocks, - /* these should be moved to their own ip modules */ - .get_gpu_clock_counter = &gfx_v7_0_get_gpu_clock_counter, - .wait_for_mc_idle = &gmc_v7_0_mc_wait_for_idle, + .get_virtual_caps = &cik_get_virtual_caps, }; static int cik_common_early_init(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c index 518dca43b133..ee6466912497 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c @@ -66,6 +66,16 @@ MODULE_FIRMWARE("radeon/mullins_sdma1.bin"); u32 amdgpu_cik_gpu_check_soft_reset(struct amdgpu_device *adev); + +static void cik_sdma_free_microcode(struct amdgpu_device *adev) +{ + int i; + for (i = 0; i < adev->sdma.num_instances; i++) { + release_firmware(adev->sdma.instance[i].fw); + adev->sdma.instance[i].fw = NULL; + } +} + /* * sDMA - System DMA * Starting with CIK, the GPU has new asynchronous @@ -214,17 +224,6 @@ static void cik_sdma_ring_emit_ib(struct amdgpu_ring *ring, unsigned vm_id, bool ctx_switch) { u32 extra_bits = vm_id & 0xf; - u32 next_rptr = ring->wptr + 5; - - while ((next_rptr & 7) != 4) - next_rptr++; - - next_rptr += 4; - amdgpu_ring_write(ring, SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0)); - amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc); - amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff); - amdgpu_ring_write(ring, 1); /* number of DWs to follow */ - amdgpu_ring_write(ring, next_rptr); /* IB packet must end on a 8 DW boundary */ cik_sdma_ring_insert_nop(ring, (12 - (ring->wptr & 7)) % 8); @@ -355,7 +354,7 @@ static void cik_sdma_enable(struct amdgpu_device *adev, bool enable) u32 me_cntl; int i; - if (enable == false) { + if (!enable) { cik_sdma_gfx_stop(adev); cik_sdma_rlc_stop(adev); } @@ -419,6 +418,8 @@ static int cik_sdma_gfx_resume(struct amdgpu_device *adev) /* Initialize the ring buffer's read and write pointers */ WREG32(mmSDMA0_GFX_RB_RPTR + sdma_offsets[i], 0); WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], 0); + WREG32(mmSDMA0_GFX_IB_RPTR + sdma_offsets[i], 0); + WREG32(mmSDMA0_GFX_IB_OFFSET + sdma_offsets[i], 0); /* set the wb address whether it's enabled or not */ WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i], @@ -446,7 +447,12 @@ static int cik_sdma_gfx_resume(struct amdgpu_device *adev) WREG32(mmSDMA0_GFX_IB_CNTL + sdma_offsets[i], ib_cntl); ring->ready = true; + } + cik_sdma_enable(adev, true); + + for (i = 0; i < adev->sdma.num_instances; i++) { + ring = &adev->sdma.instance[i].ring; r = amdgpu_ring_test_ring(ring); if (r) { ring->ready = false; @@ -529,8 +535,8 @@ static int cik_sdma_start(struct amdgpu_device *adev) if (r) return r; - /* unhalt the MEs */ - cik_sdma_enable(adev, true); + /* halt the engine before programing */ + cik_sdma_enable(adev, false); /* start the gfx rings and rlc compute queues */ r = cik_sdma_gfx_resume(adev); @@ -611,20 +617,19 @@ static int cik_sdma_ring_test_ring(struct amdgpu_ring *ring) * Test a simple IB in the DMA ring (CIK). * Returns 0 on success, error on failure. */ -static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring) +static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring, long timeout) { struct amdgpu_device *adev = ring->adev; struct amdgpu_ib ib; struct fence *f = NULL; - unsigned i; unsigned index; - int r; u32 tmp = 0; u64 gpu_addr; + long r; r = amdgpu_wb_get(adev, &index); if (r) { - dev_err(adev->dev, "(%d) failed to allocate wb slot\n", r); + dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r); return r; } @@ -634,11 +639,12 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring) memset(&ib, 0, sizeof(ib)); r = amdgpu_ib_get(adev, NULL, 256, &ib); if (r) { - DRM_ERROR("amdgpu: failed to get ib (%d).\n", r); + DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r); goto err0; } - ib.ptr[0] = SDMA_PACKET(SDMA_OPCODE_WRITE, SDMA_WRITE_SUB_OPCODE_LINEAR, 0); + ib.ptr[0] = SDMA_PACKET(SDMA_OPCODE_WRITE, + SDMA_WRITE_SUB_OPCODE_LINEAR, 0); ib.ptr[1] = lower_32_bits(gpu_addr); ib.ptr[2] = upper_32_bits(gpu_addr); ib.ptr[3] = 1; @@ -648,28 +654,25 @@ static int cik_sdma_ring_test_ib(struct amdgpu_ring *ring) if (r) goto err1; - r = fence_wait(f, false); - if (r) { - DRM_ERROR("amdgpu: fence wait failed (%d).\n", r); + r = fence_wait_timeout(f, false, timeout); + if (r == 0) { + DRM_ERROR("amdgpu: IB test timed out\n"); + r = -ETIMEDOUT; + goto err1; + } else if (r < 0) { + DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r); goto err1; } - for (i = 0; i < adev->usec_timeout; i++) { - tmp = le32_to_cpu(adev->wb.wb[index]); - if (tmp == 0xDEADBEEF) - break; - DRM_UDELAY(1); - } - if (i < adev->usec_timeout) { - DRM_INFO("ib test on ring %d succeeded in %u usecs\n", - ring->idx, i); - goto err1; + tmp = le32_to_cpu(adev->wb.wb[index]); + if (tmp == 0xDEADBEEF) { + DRM_INFO("ib test on ring %d succeeded\n", ring->idx); + r = 0; } else { DRM_ERROR("amdgpu: ib test failed (0x%08X)\n", tmp); r = -EINVAL; } err1: - fence_put(f); amdgpu_ib_free(adev, &ib, NULL); fence_put(f); err0: @@ -998,6 +1001,7 @@ static int cik_sdma_sw_fini(void *handle) for (i = 0; i < adev->sdma.num_instances; i++) amdgpu_ring_fini(&adev->sdma.instance[i].ring); + cik_sdma_free_microcode(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c index 933e425a8154..2a11413ed54a 100644 --- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c @@ -425,7 +425,7 @@ static int cz_dpm_init(struct amdgpu_device *adev) pi->mgcg_cgtt_local1 = 0x0; pi->clock_slow_down_step = 25000; pi->skip_clock_slow_down = 1; - pi->enable_nb_ps_policy = 0; + pi->enable_nb_ps_policy = false; pi->caps_power_containment = true; pi->caps_cac = true; pi->didt_enabled = false; @@ -2219,6 +2219,7 @@ static void cz_dpm_powergate_vce(struct amdgpu_device *adev, bool gate) } } } else { /*pi->caps_vce_pg*/ + pi->vce_power_gated = gate; cz_update_vce_dpm(adev); cz_enable_vce_dpm(adev, !gate); } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index c90408bc0fde..d4bf133908b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -307,11 +307,10 @@ static void dce_v11_0_page_flip(struct amdgpu_device *adev, struct amdgpu_crtc *amdgpu_crtc = adev->mode_info.crtcs[crtc_id]; u32 tmp; - /* flip at hsync for async, default is vsync */ - /* use UPDATE_IMMEDIATE_EN instead for async? */ + /* flip immediate for async, default is vsync */ tmp = RREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset); tmp = REG_SET_FIELD(tmp, GRPH_FLIP_CONTROL, - GRPH_SURFACE_UPDATE_H_RETRACE_EN, async ? 1 : 0); + GRPH_SURFACE_UPDATE_IMMEDIATE_EN, async ? 1 : 0); WREG32(mmGRPH_FLIP_CONTROL + amdgpu_crtc->crtc_offset, tmp); /* update the scanout addresses */ WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + amdgpu_crtc->crtc_offset, diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index 300ff4aab0fd..4fdfab1e9200 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -526,36 +526,16 @@ static void dce_v8_0_stop_mc_access(struct amdgpu_device *adev, crtc_enabled = REG_GET_FIELD(RREG32(mmCRTC_CONTROL + crtc_offsets[i]), CRTC_CONTROL, CRTC_MASTER_EN); if (crtc_enabled) { -#if 0 - u32 frame_count; - int j; - +#if 1 save->crtc_enabled[i] = true; tmp = RREG32(mmCRTC_BLANK_CONTROL + crtc_offsets[i]); if (REG_GET_FIELD(tmp, CRTC_BLANK_CONTROL, CRTC_BLANK_DATA_EN) == 0) { - amdgpu_display_vblank_wait(adev, i); - WREG32(mmCRTC_UPDATE_LOCK + crtc_offsets[i], 1); + /*it is correct only for RGB ; black is 0*/ + WREG32(mmCRTC_BLANK_DATA_COLOR + crtc_offsets[i], 0); tmp = REG_SET_FIELD(tmp, CRTC_BLANK_CONTROL, CRTC_BLANK_DATA_EN, 1); WREG32(mmCRTC_BLANK_CONTROL + crtc_offsets[i], tmp); - WREG32(mmCRTC_UPDATE_LOCK + crtc_offsets[i], 0); - } - /* wait for the next frame */ - frame_count = amdgpu_display_vblank_get_counter(adev, i); - for (j = 0; j < adev->usec_timeout; j++) { - if (amdgpu_display_vblank_get_counter(adev, i) != frame_count) - break; - udelay(1); - } - tmp = RREG32(mmGRPH_UPDATE + crtc_offsets[i]); - if (REG_GET_FIELD(tmp, GRPH_UPDATE, GRPH_UPDATE_LOCK) == 0) { - tmp = REG_SET_FIELD(tmp, GRPH_UPDATE, GRPH_UPDATE_LOCK, 1); - WREG32(mmGRPH_UPDATE + crtc_offsets[i], tmp); - } - tmp = RREG32(mmMASTER_UPDATE_LOCK + crtc_offsets[i]); - if (REG_GET_FIELD(tmp, MASTER_UPDATE_LOCK, MASTER_UPDATE_LOCK) == 0) { - tmp = REG_SET_FIELD(tmp, MASTER_UPDATE_LOCK, MASTER_UPDATE_LOCK, 1); - WREG32(mmMASTER_UPDATE_LOCK + crtc_offsets[i], tmp); } + mdelay(20); #else /* XXX this is a hack to avoid strange behavior with EFI on certain systems */ WREG32(mmCRTC_UPDATE_LOCK + crtc_offsets[i], 1); @@ -575,55 +555,22 @@ static void dce_v8_0_stop_mc_access(struct amdgpu_device *adev, static void dce_v8_0_resume_mc_access(struct amdgpu_device *adev, struct amdgpu_mode_mc_save *save) { - u32 tmp, frame_count; - int i, j; + u32 tmp; + int i; /* update crtc base addresses */ for (i = 0; i < adev->mode_info.num_crtc; i++) { WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS_HIGH + crtc_offsets[i], upper_32_bits(adev->mc.vram_start)); - WREG32(mmGRPH_SECONDARY_SURFACE_ADDRESS_HIGH + crtc_offsets[i], - upper_32_bits(adev->mc.vram_start)); WREG32(mmGRPH_PRIMARY_SURFACE_ADDRESS + crtc_offsets[i], (u32)adev->mc.vram_start); - WREG32(mmGRPH_SECONDARY_SURFACE_ADDRESS + crtc_offsets[i], - (u32)adev->mc.vram_start); if (save->crtc_enabled[i]) { - tmp = RREG32(mmMASTER_UPDATE_MODE + crtc_offsets[i]); - if (REG_GET_FIELD(tmp, MASTER_UPDATE_MODE, MASTER_UPDATE_MODE) != 3) { - tmp = REG_SET_FIELD(tmp, MASTER_UPDATE_MODE, MASTER_UPDATE_MODE, 3); - WREG32(mmMASTER_UPDATE_MODE + crtc_offsets[i], tmp); - } - tmp = RREG32(mmGRPH_UPDATE + crtc_offsets[i]); - if (REG_GET_FIELD(tmp, GRPH_UPDATE, GRPH_UPDATE_LOCK)) { - tmp = REG_SET_FIELD(tmp, GRPH_UPDATE, GRPH_UPDATE_LOCK, 0); - WREG32(mmGRPH_UPDATE + crtc_offsets[i], tmp); - } - tmp = RREG32(mmMASTER_UPDATE_LOCK + crtc_offsets[i]); - if (REG_GET_FIELD(tmp, MASTER_UPDATE_LOCK, MASTER_UPDATE_LOCK)) { - tmp = REG_SET_FIELD(tmp, MASTER_UPDATE_LOCK, MASTER_UPDATE_LOCK, 0); - WREG32(mmMASTER_UPDATE_LOCK + crtc_offsets[i], tmp); - } - for (j = 0; j < adev->usec_timeout; j++) { - tmp = RREG32(mmGRPH_UPDATE + crtc_offsets[i]); - if (REG_GET_FIELD(tmp, GRPH_UPDATE, GRPH_SURFACE_UPDATE_PENDING) == 0) - break; - udelay(1); - } tmp = RREG32(mmCRTC_BLANK_CONTROL + crtc_offsets[i]); tmp = REG_SET_FIELD(tmp, CRTC_BLANK_CONTROL, CRTC_BLANK_DATA_EN, 0); - WREG32(mmCRTC_UPDATE_LOCK + crtc_offsets[i], 1); WREG32(mmCRTC_BLANK_CONTROL + crtc_offsets[i], tmp); - WREG32(mmCRTC_UPDATE_LOCK + crtc_offsets[i], 0); - /* wait for the next frame */ - frame_count = amdgpu_display_vblank_get_counter(adev, i); - for (j = 0; j < adev->usec_timeout; j++) { - if (amdgpu_display_vblank_get_counter(adev, i) != frame_count) - break; - udelay(1); - } } + mdelay(20); } WREG32(mmVGA_MEMORY_BASE_ADDRESS_HIGH, upper_32_bits(adev->mc.vram_start)); diff --git a/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c b/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c index 245cabf06575..ed03b75175d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/fiji_dpm.c @@ -72,6 +72,11 @@ static int fiji_dpm_sw_init(void *handle) static int fiji_dpm_sw_fini(void *handle) { + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + release_firmware(adev->pm.fw); + adev->pm.fw = NULL; + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/fiji_smc.c b/drivers/gpu/drm/amd/amdgpu/fiji_smc.c index b336c918d6a7..b3e19ba4c57f 100644 --- a/drivers/gpu/drm/amd/amdgpu/fiji_smc.c +++ b/drivers/gpu/drm/amd/amdgpu/fiji_smc.c @@ -173,7 +173,7 @@ static int fiji_send_msg_to_smc(struct amdgpu_device *adev, PPSMC_Msg msg) { if (!fiji_is_smc_ram_running(adev)) { - return -EINVAL;; + return -EINVAL; } if (wait_smu_response(adev)) { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 7f18a53ab53a..d869d058ef24 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -991,6 +991,22 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev) return err; } +static void gfx_v7_0_free_microcode(struct amdgpu_device *adev) +{ + release_firmware(adev->gfx.pfp_fw); + adev->gfx.pfp_fw = NULL; + release_firmware(adev->gfx.me_fw); + adev->gfx.me_fw = NULL; + release_firmware(adev->gfx.ce_fw); + adev->gfx.ce_fw = NULL; + release_firmware(adev->gfx.mec_fw); + adev->gfx.mec_fw = NULL; + release_firmware(adev->gfx.mec2_fw); + adev->gfx.mec2_fw = NULL; + release_firmware(adev->gfx.rlc_fw); + adev->gfx.rlc_fw = NULL; +} + /** * gfx_v7_0_tiling_mode_table_init - init the hw tiling table * @@ -1567,9 +1583,15 @@ static void gfx_v7_0_tiling_mode_table_init(struct amdgpu_device *adev) * registers are instanced per SE or SH. 0xffffffff means * broadcast to all SEs or SHs (CIK). */ -void gfx_v7_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num) +static void gfx_v7_0_select_se_sh(struct amdgpu_device *adev, + u32 se_num, u32 sh_num, u32 instance) { - u32 data = GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES_MASK; + u32 data; + + if (instance == 0xffffffff) + data = REG_SET_FIELD(0, GRBM_GFX_INDEX, INSTANCE_BROADCAST_WRITES, 1); + else + data = REG_SET_FIELD(0, GRBM_GFX_INDEX, INSTANCE_INDEX, instance); if ((se_num == 0xffffffff) && (sh_num == 0xffffffff)) data |= GRBM_GFX_INDEX__SH_BROADCAST_WRITES_MASK | @@ -1643,13 +1665,13 @@ static void gfx_v7_0_setup_rb(struct amdgpu_device *adev) mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { - gfx_v7_0_select_se_sh(adev, i, j); + gfx_v7_0_select_se_sh(adev, i, j, 0xffffffff); data = gfx_v7_0_get_rb_active_bitmap(adev); active_rbs |= data << ((i * adev->gfx.config.max_sh_per_se + j) * rb_bitmap_width_per_sh); } } - gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); mutex_unlock(&adev->grbm_idx_mutex); adev->gfx.config.backend_enable_mask = active_rbs; @@ -1730,7 +1752,7 @@ static void gfx_v7_0_gpu_init(struct amdgpu_device *adev) * making sure that the following register writes will be broadcasted * to all the shaders */ - gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); /* XXX SH_MEM regs */ /* where to put LDS, scratch, GPUVM in FSA64 space */ @@ -2034,17 +2056,6 @@ static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring, unsigned vm_id, bool ctx_switch) { u32 header, control = 0; - u32 next_rptr = ring->wptr + 5; - - if (ctx_switch) - next_rptr += 2; - - next_rptr += 4; - amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); - amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM); - amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc); - amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff); - amdgpu_ring_write(ring, next_rptr); /* insert SWITCH_BUFFER packet before first IB in the ring frame */ if (ctx_switch) { @@ -2073,22 +2084,9 @@ static void gfx_v7_0_ring_emit_ib_compute(struct amdgpu_ring *ring, struct amdgpu_ib *ib, unsigned vm_id, bool ctx_switch) { - u32 header, control = 0; - u32 next_rptr = ring->wptr + 5; + u32 control = INDIRECT_BUFFER_VALID | ib->length_dw | (vm_id << 24); - control |= INDIRECT_BUFFER_VALID; - next_rptr += 4; - amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); - amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM); - amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc); - amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff); - amdgpu_ring_write(ring, next_rptr); - - header = PACKET3(PACKET3_INDIRECT_BUFFER, 2); - - control |= ib->length_dw | (vm_id << 24); - - amdgpu_ring_write(ring, header); + amdgpu_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2)); amdgpu_ring_write(ring, #ifdef __BIG_ENDIAN (2 << 0) | @@ -2107,26 +2105,25 @@ static void gfx_v7_0_ring_emit_ib_compute(struct amdgpu_ring *ring, * Provides a basic gfx ring test to verify that IBs are working. * Returns 0 on success, error on failure. */ -static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring) +static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) { struct amdgpu_device *adev = ring->adev; struct amdgpu_ib ib; struct fence *f = NULL; uint32_t scratch; uint32_t tmp = 0; - unsigned i; - int r; + long r; r = amdgpu_gfx_scratch_get(adev, &scratch); if (r) { - DRM_ERROR("amdgpu: failed to get scratch reg (%d).\n", r); + DRM_ERROR("amdgpu: failed to get scratch reg (%ld).\n", r); return r; } WREG32(scratch, 0xCAFEDEAD); memset(&ib, 0, sizeof(ib)); r = amdgpu_ib_get(adev, NULL, 256, &ib); if (r) { - DRM_ERROR("amdgpu: failed to get ib (%d).\n", r); + DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r); goto err1; } ib.ptr[0] = PACKET3(PACKET3_SET_UCONFIG_REG, 1); @@ -2138,21 +2135,19 @@ static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring) if (r) goto err2; - r = fence_wait(f, false); - if (r) { - DRM_ERROR("amdgpu: fence wait failed (%d).\n", r); + r = fence_wait_timeout(f, false, timeout); + if (r == 0) { + DRM_ERROR("amdgpu: IB test timed out\n"); + r = -ETIMEDOUT; + goto err2; + } else if (r < 0) { + DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r); goto err2; } - for (i = 0; i < adev->usec_timeout; i++) { - tmp = RREG32(scratch); - if (tmp == 0xDEADBEEF) - break; - DRM_UDELAY(1); - } - if (i < adev->usec_timeout) { - DRM_INFO("ib test on ring %d succeeded in %u usecs\n", - ring->idx, i); - goto err2; + tmp = RREG32(scratch); + if (tmp == 0xDEADBEEF) { + DRM_INFO("ib test on ring %d succeeded\n", ring->idx); + r = 0; } else { DRM_ERROR("amdgpu: ib test failed (scratch(0x%04X)=0x%08X)\n", scratch, tmp); @@ -2160,7 +2155,6 @@ static int gfx_v7_0_ring_test_ib(struct amdgpu_ring *ring) } err2: - fence_put(f); amdgpu_ib_free(adev, &ib, NULL); fence_put(f); err1: @@ -3205,7 +3199,8 @@ static int gfx_v7_0_rlc_init(struct amdgpu_device *adev) } } adev->gfx.rlc.cs_data = ci_cs_data; - adev->gfx.rlc.cp_table_size = CP_ME_TABLE_SIZE * 5 * 4; + adev->gfx.rlc.cp_table_size = ALIGN(CP_ME_TABLE_SIZE * 5 * 4, 2048); /* CP JT */ + adev->gfx.rlc.cp_table_size += 64 * 1024; /* GDS */ src_ptr = adev->gfx.rlc.reg_list; dws = adev->gfx.rlc.reg_list_size; @@ -3363,7 +3358,7 @@ static void gfx_v7_0_wait_for_rlc_serdes(struct amdgpu_device *adev) mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { - gfx_v7_0_select_se_sh(adev, i, j); + gfx_v7_0_select_se_sh(adev, i, j, 0xffffffff); for (k = 0; k < adev->usec_timeout; k++) { if (RREG32(mmRLC_SERDES_CU_MASTER_BUSY) == 0) break; @@ -3371,7 +3366,7 @@ static void gfx_v7_0_wait_for_rlc_serdes(struct amdgpu_device *adev) } } } - gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); mutex_unlock(&adev->grbm_idx_mutex); mask = RLC_SERDES_NONCU_MASTER_BUSY__SE_MASTER_BUSY_MASK | @@ -3418,7 +3413,7 @@ static u32 gfx_v7_0_halt_rlc(struct amdgpu_device *adev) return orig; } -void gfx_v7_0_enter_rlc_safe_mode(struct amdgpu_device *adev) +static void gfx_v7_0_enter_rlc_safe_mode(struct amdgpu_device *adev) { u32 tmp, i, mask; @@ -3440,7 +3435,7 @@ void gfx_v7_0_enter_rlc_safe_mode(struct amdgpu_device *adev) } } -void gfx_v7_0_exit_rlc_safe_mode(struct amdgpu_device *adev) +static void gfx_v7_0_exit_rlc_safe_mode(struct amdgpu_device *adev) { u32 tmp; @@ -3455,7 +3450,7 @@ void gfx_v7_0_exit_rlc_safe_mode(struct amdgpu_device *adev) * * Halt the RLC ME (MicroEngine) (CIK). */ -void gfx_v7_0_rlc_stop(struct amdgpu_device *adev) +static void gfx_v7_0_rlc_stop(struct amdgpu_device *adev) { WREG32(mmRLC_CNTL, 0); @@ -3531,7 +3526,7 @@ static int gfx_v7_0_rlc_resume(struct amdgpu_device *adev) WREG32(mmRLC_LB_CNTR_MAX, 0x00008000); mutex_lock(&adev->grbm_idx_mutex); - gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); WREG32(mmRLC_LB_INIT_CU_MASK, 0xffffffff); WREG32(mmRLC_LB_PARAMS, 0x00600408); WREG32(mmRLC_LB_CNTL, 0x80000004); @@ -3571,7 +3566,7 @@ static void gfx_v7_0_enable_cgcg(struct amdgpu_device *adev, bool enable) tmp = gfx_v7_0_halt_rlc(adev); mutex_lock(&adev->grbm_idx_mutex); - gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); WREG32(mmRLC_SERDES_WR_CU_MASTER_MASK, 0xffffffff); WREG32(mmRLC_SERDES_WR_NONCU_MASTER_MASK, 0xffffffff); tmp2 = RLC_SERDES_WR_CTRL__BPM_ADDR_MASK | @@ -3622,7 +3617,7 @@ static void gfx_v7_0_enable_mgcg(struct amdgpu_device *adev, bool enable) tmp = gfx_v7_0_halt_rlc(adev); mutex_lock(&adev->grbm_idx_mutex); - gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); WREG32(mmRLC_SERDES_WR_CU_MASTER_MASK, 0xffffffff); WREG32(mmRLC_SERDES_WR_NONCU_MASTER_MASK, 0xffffffff); data = RLC_SERDES_WR_CTRL__BPM_ADDR_MASK | @@ -3673,7 +3668,7 @@ static void gfx_v7_0_enable_mgcg(struct amdgpu_device *adev, bool enable) tmp = gfx_v7_0_halt_rlc(adev); mutex_lock(&adev->grbm_idx_mutex); - gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); WREG32(mmRLC_SERDES_WR_CU_MASTER_MASK, 0xffffffff); WREG32(mmRLC_SERDES_WR_NONCU_MASTER_MASK, 0xffffffff); data = RLC_SERDES_WR_CTRL__BPM_ADDR_MASK | RLC_SERDES_WR_CTRL__MGCG_OVERRIDE_1_MASK; @@ -3851,6 +3846,20 @@ static void gfx_v7_0_enable_gfx_cgpg(struct amdgpu_device *adev, } } +static void gfx_v7_0_set_user_cu_inactive_bitmap(struct amdgpu_device *adev, + u32 bitmap) +{ + u32 data; + + if (!bitmap) + return; + + data = bitmap << GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS__SHIFT; + data &= GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS_MASK; + + WREG32(mmGC_USER_SHADER_ARRAY_CONFIG, data); +} + static u32 gfx_v7_0_get_cu_active_bitmap(struct amdgpu_device *adev) { u32 data, mask; @@ -4107,7 +4116,7 @@ static void gfx_v7_0_fini_pg(struct amdgpu_device *adev) * Fetches a GPU clock counter snapshot (SI). * Returns the 64 bit clock counter snapshot. */ -uint64_t gfx_v7_0_get_gpu_clock_counter(struct amdgpu_device *adev) +static uint64_t gfx_v7_0_get_gpu_clock_counter(struct amdgpu_device *adev) { uint64_t clock; @@ -4167,12 +4176,24 @@ static void gfx_v7_0_ring_emit_gds_switch(struct amdgpu_ring *ring, amdgpu_ring_write(ring, (1 << (oa_size + oa_base)) - (1 << oa_base)); } +static const struct amdgpu_gfx_funcs gfx_v7_0_gfx_funcs = { + .get_gpu_clock_counter = &gfx_v7_0_get_gpu_clock_counter, + .select_se_sh = &gfx_v7_0_select_se_sh, +}; + +static const struct amdgpu_rlc_funcs gfx_v7_0_rlc_funcs = { + .enter_safe_mode = gfx_v7_0_enter_rlc_safe_mode, + .exit_safe_mode = gfx_v7_0_exit_rlc_safe_mode +}; + static int gfx_v7_0_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; adev->gfx.num_gfx_rings = GFX7_NUM_GFX_RINGS; adev->gfx.num_compute_rings = GFX7_NUM_COMPUTE_RINGS; + adev->gfx.funcs = &gfx_v7_0_gfx_funcs; + adev->gfx.rlc.funcs = &gfx_v7_0_rlc_funcs; gfx_v7_0_set_ring_funcs(adev); gfx_v7_0_set_irq_funcs(adev); gfx_v7_0_set_gds_init(adev); @@ -4489,6 +4510,7 @@ static int gfx_v7_0_sw_fini(void *handle) gfx_v7_0_cp_compute_fini(adev); gfx_v7_0_rlc_fini(adev); gfx_v7_0_mec_fini(adev); + gfx_v7_0_free_microcode(adev); return 0; } @@ -4816,7 +4838,7 @@ static int gfx_v7_0_eop_irq(struct amdgpu_device *adev, case 2: for (i = 0; i < adev->gfx.num_compute_rings; i++) { ring = &adev->gfx.compute_ring[i]; - if ((ring->me == me_id) & (ring->pipe == pipe_id)) + if ((ring->me == me_id) && (ring->pipe == pipe_id)) amdgpu_fence_process(ring); } break; @@ -5015,16 +5037,22 @@ static void gfx_v7_0_get_cu_info(struct amdgpu_device *adev) int i, j, k, counter, active_cu_number = 0; u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0; struct amdgpu_cu_info *cu_info = &adev->gfx.cu_info; + unsigned disable_masks[4 * 2]; memset(cu_info, 0, sizeof(*cu_info)); + amdgpu_gfx_parse_disable_cu(disable_masks, 4, 2); + mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { mask = 1; ao_bitmap = 0; counter = 0; - gfx_v7_0_select_se_sh(adev, i, j); + gfx_v7_0_select_se_sh(adev, i, j, 0xffffffff); + if (i < 4 && j < 2) + gfx_v7_0_set_user_cu_inactive_bitmap( + adev, disable_masks[i * 2 + j]); bitmap = gfx_v7_0_get_cu_active_bitmap(adev); cu_info->bitmap[i][j] = bitmap; @@ -5040,7 +5068,7 @@ static void gfx_v7_0_get_cu_info(struct amdgpu_device *adev) ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8)); } } - gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + gfx_v7_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); mutex_unlock(&adev->grbm_idx_mutex); cu_info->number = active_cu_number; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h index e747aa935c88..94e3ea147c26 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.h @@ -26,11 +26,4 @@ extern const struct amd_ip_funcs gfx_v7_0_ip_funcs; -/* XXX these shouldn't be exported */ -void gfx_v7_0_enter_rlc_safe_mode(struct amdgpu_device *adev); -void gfx_v7_0_exit_rlc_safe_mode(struct amdgpu_device *adev); -void gfx_v7_0_rlc_stop(struct amdgpu_device *adev); -uint64_t gfx_v7_0_get_gpu_clock_counter(struct amdgpu_device *adev); -void gfx_v7_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num); - #endif diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index f19bab68fd83..bff8668e9e6d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -28,6 +28,7 @@ #include "vid.h" #include "amdgpu_ucode.h" #include "amdgpu_atombios.h" +#include "atombios_i2c.h" #include "clearstate_vi.h" #include "gmc/gmc_8_2_d.h" @@ -47,6 +48,8 @@ #include "dce/dce_10_0_d.h" #include "dce/dce_10_0_sh_mask.h" +#include "smu/smu_7_1_3_d.h" + #define GFX8_NUM_GFX_RINGS 1 #define GFX8_NUM_COMPUTE_RINGS 8 @@ -282,6 +285,7 @@ static const u32 golden_settings_polaris11_a11[] = mmTCP_ADDR_CONFIG, 0x000003ff, 0x000000f3, mmTCP_CHAN_STEER_HI, 0xffffffff, 0x00000000, mmTCP_CHAN_STEER_LO, 0xffffffff, 0x00003210, + mmVGT_RESET_DEBUG, 0x00000004, 0x00000004, }; static const u32 polaris11_golden_common_all[] = @@ -297,7 +301,8 @@ static const u32 polaris11_golden_common_all[] = static const u32 golden_settings_polaris10_a11[] = { mmATC_MISC_CG, 0x000c0fc0, 0x000c0200, - mmCB_HW_CONTROL, 0xfffdf3cf, 0x00006208, + mmCB_HW_CONTROL, 0xfffdf3cf, 0x00007208, + mmCB_HW_CONTROL_2, 0, 0x0f000000, mmCB_HW_CONTROL_3, 0x000001ff, 0x00000040, mmDB_DEBUG2, 0xf00fffff, 0x00000400, mmPA_SC_ENHANCE, 0xffffffff, 0x20000001, @@ -311,6 +316,7 @@ static const u32 golden_settings_polaris10_a11[] = mmTCC_CTRL, 0x00100000, 0xf31fff7f, mmTCP_ADDR_CONFIG, 0x000003ff, 0x000000f7, mmTCP_CHAN_STEER_HI, 0xffffffff, 0x00000000, + mmVGT_RESET_DEBUG, 0x00000004, 0x00000004, }; static const u32 polaris10_golden_common_all[] = @@ -692,6 +698,11 @@ static void gfx_v8_0_init_golden_registers(struct amdgpu_device *adev) amdgpu_program_register_sequence(adev, polaris10_golden_common_all, (const u32)ARRAY_SIZE(polaris10_golden_common_all)); + WREG32_SMC(ixCG_ACLK_CNTL, 0x0000001C); + if (adev->pdev->revision == 0xc7) { + amdgpu_atombios_i2c_channel_trans(adev, 0x10, 0x96, 0x1E, 0xDD); + amdgpu_atombios_i2c_channel_trans(adev, 0x10, 0x96, 0x1F, 0xD0); + } break; case CHIP_CARRIZO: amdgpu_program_register_sequence(adev, @@ -776,26 +787,25 @@ static int gfx_v8_0_ring_test_ring(struct amdgpu_ring *ring) return r; } -static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring) +static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) { struct amdgpu_device *adev = ring->adev; struct amdgpu_ib ib; struct fence *f = NULL; uint32_t scratch; uint32_t tmp = 0; - unsigned i; - int r; + long r; r = amdgpu_gfx_scratch_get(adev, &scratch); if (r) { - DRM_ERROR("amdgpu: failed to get scratch reg (%d).\n", r); + DRM_ERROR("amdgpu: failed to get scratch reg (%ld).\n", r); return r; } WREG32(scratch, 0xCAFEDEAD); memset(&ib, 0, sizeof(ib)); r = amdgpu_ib_get(adev, NULL, 256, &ib); if (r) { - DRM_ERROR("amdgpu: failed to get ib (%d).\n", r); + DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r); goto err1; } ib.ptr[0] = PACKET3(PACKET3_SET_UCONFIG_REG, 1); @@ -807,28 +817,25 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring) if (r) goto err2; - r = fence_wait(f, false); - if (r) { - DRM_ERROR("amdgpu: fence wait failed (%d).\n", r); + r = fence_wait_timeout(f, false, timeout); + if (r == 0) { + DRM_ERROR("amdgpu: IB test timed out.\n"); + r = -ETIMEDOUT; + goto err2; + } else if (r < 0) { + DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r); goto err2; } - for (i = 0; i < adev->usec_timeout; i++) { - tmp = RREG32(scratch); - if (tmp == 0xDEADBEEF) - break; - DRM_UDELAY(1); - } - if (i < adev->usec_timeout) { - DRM_INFO("ib test on ring %d succeeded in %u usecs\n", - ring->idx, i); - goto err2; + tmp = RREG32(scratch); + if (tmp == 0xDEADBEEF) { + DRM_INFO("ib test on ring %d succeeded\n", ring->idx); + r = 0; } else { DRM_ERROR("amdgpu: ib test failed (scratch(0x%04X)=0x%08X)\n", scratch, tmp); r = -EINVAL; } err2: - fence_put(f); amdgpu_ib_free(adev, &ib, NULL); fence_put(f); err1: @@ -836,6 +843,26 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring) return r; } + +static void gfx_v8_0_free_microcode(struct amdgpu_device *adev) { + release_firmware(adev->gfx.pfp_fw); + adev->gfx.pfp_fw = NULL; + release_firmware(adev->gfx.me_fw); + adev->gfx.me_fw = NULL; + release_firmware(adev->gfx.ce_fw); + adev->gfx.ce_fw = NULL; + release_firmware(adev->gfx.rlc_fw); + adev->gfx.rlc_fw = NULL; + release_firmware(adev->gfx.mec_fw); + adev->gfx.mec_fw = NULL; + if ((adev->asic_type != CHIP_STONEY) && + (adev->asic_type != CHIP_TOPAZ)) + release_firmware(adev->gfx.mec2_fw); + adev->gfx.mec2_fw = NULL; + + kfree(adev->gfx.rlc.register_list_format); +} + static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) { const char *chip_name; @@ -1129,6 +1156,71 @@ static void gfx_v8_0_get_csb_buffer(struct amdgpu_device *adev, buffer[count++] = cpu_to_le32(0); } +static void cz_init_cp_jump_table(struct amdgpu_device *adev) +{ + const __le32 *fw_data; + volatile u32 *dst_ptr; + int me, i, max_me = 4; + u32 bo_offset = 0; + u32 table_offset, table_size; + + if (adev->asic_type == CHIP_CARRIZO) + max_me = 5; + + /* write the cp table buffer */ + dst_ptr = adev->gfx.rlc.cp_table_ptr; + for (me = 0; me < max_me; me++) { + if (me == 0) { + const struct gfx_firmware_header_v1_0 *hdr = + (const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data; + fw_data = (const __le32 *) + (adev->gfx.ce_fw->data + + le32_to_cpu(hdr->header.ucode_array_offset_bytes)); + table_offset = le32_to_cpu(hdr->jt_offset); + table_size = le32_to_cpu(hdr->jt_size); + } else if (me == 1) { + const struct gfx_firmware_header_v1_0 *hdr = + (const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data; + fw_data = (const __le32 *) + (adev->gfx.pfp_fw->data + + le32_to_cpu(hdr->header.ucode_array_offset_bytes)); + table_offset = le32_to_cpu(hdr->jt_offset); + table_size = le32_to_cpu(hdr->jt_size); + } else if (me == 2) { + const struct gfx_firmware_header_v1_0 *hdr = + (const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data; + fw_data = (const __le32 *) + (adev->gfx.me_fw->data + + le32_to_cpu(hdr->header.ucode_array_offset_bytes)); + table_offset = le32_to_cpu(hdr->jt_offset); + table_size = le32_to_cpu(hdr->jt_size); + } else if (me == 3) { + const struct gfx_firmware_header_v1_0 *hdr = + (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data; + fw_data = (const __le32 *) + (adev->gfx.mec_fw->data + + le32_to_cpu(hdr->header.ucode_array_offset_bytes)); + table_offset = le32_to_cpu(hdr->jt_offset); + table_size = le32_to_cpu(hdr->jt_size); + } else if (me == 4) { + const struct gfx_firmware_header_v1_0 *hdr = + (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec2_fw->data; + fw_data = (const __le32 *) + (adev->gfx.mec2_fw->data + + le32_to_cpu(hdr->header.ucode_array_offset_bytes)); + table_offset = le32_to_cpu(hdr->jt_offset); + table_size = le32_to_cpu(hdr->jt_size); + } + + for (i = 0; i < table_size; i ++) { + dst_ptr[bo_offset + i] = + cpu_to_le32(le32_to_cpu(fw_data[table_offset + i])); + } + + bo_offset += table_size; + } +} + static void gfx_v8_0_rlc_fini(struct amdgpu_device *adev) { int r; @@ -1144,6 +1236,18 @@ static void gfx_v8_0_rlc_fini(struct amdgpu_device *adev) amdgpu_bo_unref(&adev->gfx.rlc.clear_state_obj); adev->gfx.rlc.clear_state_obj = NULL; } + + /* jump table block */ + if (adev->gfx.rlc.cp_table_obj) { + r = amdgpu_bo_reserve(adev->gfx.rlc.cp_table_obj, false); + if (unlikely(r != 0)) + dev_warn(adev->dev, "(%d) reserve RLC cp table bo failed\n", r); + amdgpu_bo_unpin(adev->gfx.rlc.cp_table_obj); + amdgpu_bo_unreserve(adev->gfx.rlc.cp_table_obj); + + amdgpu_bo_unref(&adev->gfx.rlc.cp_table_obj); + adev->gfx.rlc.cp_table_obj = NULL; + } } static int gfx_v8_0_rlc_init(struct amdgpu_device *adev) @@ -1200,6 +1304,46 @@ static int gfx_v8_0_rlc_init(struct amdgpu_device *adev) amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj); } + if ((adev->asic_type == CHIP_CARRIZO) || + (adev->asic_type == CHIP_STONEY)) { + adev->gfx.rlc.cp_table_size = ALIGN(96 * 5 * 4, 2048) + (64 * 1024); /* JT + GDS */ + if (adev->gfx.rlc.cp_table_obj == NULL) { + r = amdgpu_bo_create(adev, adev->gfx.rlc.cp_table_size, PAGE_SIZE, true, + AMDGPU_GEM_DOMAIN_VRAM, + AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED, + NULL, NULL, + &adev->gfx.rlc.cp_table_obj); + if (r) { + dev_warn(adev->dev, "(%d) create RLC cp table bo failed\n", r); + return r; + } + } + + r = amdgpu_bo_reserve(adev->gfx.rlc.cp_table_obj, false); + if (unlikely(r != 0)) { + dev_warn(adev->dev, "(%d) reserve RLC cp table bo failed\n", r); + return r; + } + r = amdgpu_bo_pin(adev->gfx.rlc.cp_table_obj, AMDGPU_GEM_DOMAIN_VRAM, + &adev->gfx.rlc.cp_table_gpu_addr); + if (r) { + amdgpu_bo_unreserve(adev->gfx.rlc.cp_table_obj); + dev_warn(adev->dev, "(%d) pin RLC cp_table bo failed\n", r); + return r; + } + r = amdgpu_bo_kmap(adev->gfx.rlc.cp_table_obj, (void **)&adev->gfx.rlc.cp_table_ptr); + if (r) { + dev_warn(adev->dev, "(%d) map RLC cp table bo failed\n", r); + return r; + } + + cz_init_cp_jump_table(adev); + + amdgpu_bo_kunmap(adev->gfx.rlc.cp_table_obj); + amdgpu_bo_unreserve(adev->gfx.rlc.cp_table_obj); + + } + return 0; } @@ -1581,7 +1725,6 @@ static int gfx_v8_0_do_edc_gpr_workarounds(struct amdgpu_device *adev) RREG32(sec_ded_counter_registers[i]); fail: - fence_put(f); amdgpu_ib_free(adev, &ib, NULL); fence_put(f); @@ -1983,7 +2126,7 @@ static int gfx_v8_0_sw_fini(void *handle) gfx_v8_0_rlc_fini(adev); - kfree(adev->gfx.rlc.register_list_format); + gfx_v8_0_free_microcode(adev); return 0; } @@ -3308,9 +3451,15 @@ static void gfx_v8_0_tiling_mode_table_init(struct amdgpu_device *adev) } } -void gfx_v8_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num) +static void gfx_v8_0_select_se_sh(struct amdgpu_device *adev, + u32 se_num, u32 sh_num, u32 instance) { - u32 data = REG_SET_FIELD(0, GRBM_GFX_INDEX, INSTANCE_BROADCAST_WRITES, 1); + u32 data; + + if (instance == 0xffffffff) + data = REG_SET_FIELD(0, GRBM_GFX_INDEX, INSTANCE_BROADCAST_WRITES, 1); + else + data = REG_SET_FIELD(0, GRBM_GFX_INDEX, INSTANCE_INDEX, instance); if ((se_num == 0xffffffff) && (sh_num == 0xffffffff)) { data = REG_SET_FIELD(data, GRBM_GFX_INDEX, SH_BROADCAST_WRITES, 1); @@ -3360,13 +3509,13 @@ static void gfx_v8_0_setup_rb(struct amdgpu_device *adev) mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { - gfx_v8_0_select_se_sh(adev, i, j); + gfx_v8_0_select_se_sh(adev, i, j, 0xffffffff); data = gfx_v8_0_get_rb_active_bitmap(adev); active_rbs |= data << ((i * adev->gfx.config.max_sh_per_se + j) * rb_bitmap_width_per_sh); } } - gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); mutex_unlock(&adev->grbm_idx_mutex); adev->gfx.config.backend_enable_mask = active_rbs; @@ -3470,7 +3619,7 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev) * making sure that the following register writes will be broadcasted * to all the shaders */ - gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); WREG32(mmPA_SC_FIFO_SIZE, (adev->gfx.config.sc_prim_fifo_size_frontend << @@ -3493,7 +3642,7 @@ static void gfx_v8_0_wait_for_rlc_serdes(struct amdgpu_device *adev) mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { - gfx_v8_0_select_se_sh(adev, i, j); + gfx_v8_0_select_se_sh(adev, i, j, 0xffffffff); for (k = 0; k < adev->usec_timeout; k++) { if (RREG32(mmRLC_SERDES_CU_MASTER_BUSY) == 0) break; @@ -3501,7 +3650,7 @@ static void gfx_v8_0_wait_for_rlc_serdes(struct amdgpu_device *adev) } } } - gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); mutex_unlock(&adev->grbm_idx_mutex); mask = RLC_SERDES_NONCU_MASTER_BUSY__SE_MASTER_BUSY_MASK | @@ -3662,13 +3811,13 @@ static void gfx_v8_0_enable_save_restore_machine(struct amdgpu_device *adev) WREG32(mmRLC_SRM_CNTL, data); } -static void polaris11_init_power_gating(struct amdgpu_device *adev) +static void gfx_v8_0_init_power_gating(struct amdgpu_device *adev) { uint32_t data; if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG | - AMD_PG_SUPPORT_GFX_SMG | - AMD_PG_SUPPORT_GFX_DMG)) { + AMD_PG_SUPPORT_GFX_SMG | + AMD_PG_SUPPORT_GFX_DMG)) { data = RREG32(mmCP_RB_WPTR_POLL_CNTL); data &= ~CP_RB_WPTR_POLL_CNTL__IDLE_POLL_COUNT_MASK; data |= (0x60 << CP_RB_WPTR_POLL_CNTL__IDLE_POLL_COUNT__SHIFT); @@ -3693,6 +3842,53 @@ static void polaris11_init_power_gating(struct amdgpu_device *adev) } } +static void cz_enable_sck_slow_down_on_power_up(struct amdgpu_device *adev, + bool enable) +{ + u32 data, orig; + + orig = data = RREG32(mmRLC_PG_CNTL); + + if (enable) + data |= RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PU_ENABLE_MASK; + else + data &= ~RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PU_ENABLE_MASK; + + if (orig != data) + WREG32(mmRLC_PG_CNTL, data); +} + +static void cz_enable_sck_slow_down_on_power_down(struct amdgpu_device *adev, + bool enable) +{ + u32 data, orig; + + orig = data = RREG32(mmRLC_PG_CNTL); + + if (enable) + data |= RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PD_ENABLE_MASK; + else + data &= ~RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PD_ENABLE_MASK; + + if (orig != data) + WREG32(mmRLC_PG_CNTL, data); +} + +static void cz_enable_cp_power_gating(struct amdgpu_device *adev, bool enable) +{ + u32 data, orig; + + orig = data = RREG32(mmRLC_PG_CNTL); + + if (enable) + data &= ~RLC_PG_CNTL__CP_PG_DISABLE_MASK; + else + data |= RLC_PG_CNTL__CP_PG_DISABLE_MASK; + + if (orig != data) + WREG32(mmRLC_PG_CNTL, data); +} + static void gfx_v8_0_init_pg(struct amdgpu_device *adev) { if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG | @@ -3705,8 +3901,25 @@ static void gfx_v8_0_init_pg(struct amdgpu_device *adev) gfx_v8_0_init_save_restore_list(adev); gfx_v8_0_enable_save_restore_machine(adev); - if (adev->asic_type == CHIP_POLARIS11) - polaris11_init_power_gating(adev); + if ((adev->asic_type == CHIP_CARRIZO) || + (adev->asic_type == CHIP_STONEY)) { + WREG32(mmRLC_JUMP_TABLE_RESTORE, adev->gfx.rlc.cp_table_gpu_addr >> 8); + gfx_v8_0_init_power_gating(adev); + WREG32(mmRLC_PG_ALWAYS_ON_CU_MASK, adev->gfx.cu_info.ao_cu_mask); + if (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS) { + cz_enable_sck_slow_down_on_power_up(adev, true); + cz_enable_sck_slow_down_on_power_down(adev, true); + } else { + cz_enable_sck_slow_down_on_power_up(adev, false); + cz_enable_sck_slow_down_on_power_down(adev, false); + } + if (adev->pg_flags & AMD_PG_SUPPORT_CP) + cz_enable_cp_power_gating(adev, true); + else + cz_enable_cp_power_gating(adev, false); + } else if (adev->asic_type == CHIP_POLARIS11) { + gfx_v8_0_init_power_gating(adev); + } } } @@ -3974,11 +4187,15 @@ static int gfx_v8_0_cp_gfx_start(struct amdgpu_device *adev) amdgpu_ring_write(ring, 0x3a00161a); amdgpu_ring_write(ring, 0x0000002e); break; - case CHIP_TOPAZ: case CHIP_CARRIZO: amdgpu_ring_write(ring, 0x00000002); amdgpu_ring_write(ring, 0x00000000); break; + case CHIP_TOPAZ: + amdgpu_ring_write(ring, adev->gfx.config.num_rbs == 1 ? + 0x00000000 : 0x00000002); + amdgpu_ring_write(ring, 0x00000000); + break; case CHIP_STONEY: amdgpu_ring_write(ring, 0x00000000); amdgpu_ring_write(ring, 0x00000000); @@ -4941,7 +5158,7 @@ static int gfx_v8_0_soft_reset(void *handle) * Fetches a GPU clock counter snapshot. * Returns the 64 bit clock counter snapshot. */ -uint64_t gfx_v8_0_get_gpu_clock_counter(struct amdgpu_device *adev) +static uint64_t gfx_v8_0_get_gpu_clock_counter(struct amdgpu_device *adev) { uint64_t clock; @@ -5001,12 +5218,18 @@ static void gfx_v8_0_ring_emit_gds_switch(struct amdgpu_ring *ring, amdgpu_ring_write(ring, (1 << (oa_size + oa_base)) - (1 << oa_base)); } +static const struct amdgpu_gfx_funcs gfx_v8_0_gfx_funcs = { + .get_gpu_clock_counter = &gfx_v8_0_get_gpu_clock_counter, + .select_se_sh = &gfx_v8_0_select_se_sh, +}; + static int gfx_v8_0_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; adev->gfx.num_gfx_rings = GFX8_NUM_GFX_RINGS; adev->gfx.num_compute_rings = GFX8_NUM_COMPUTE_RINGS; + adev->gfx.funcs = &gfx_v8_0_gfx_funcs; gfx_v8_0_set_ring_funcs(adev); gfx_v8_0_set_irq_funcs(adev); gfx_v8_0_set_gds_init(adev); @@ -5039,51 +5262,43 @@ static int gfx_v8_0_late_init(void *handle) return 0; } -static void polaris11_enable_gfx_static_mg_power_gating(struct amdgpu_device *adev, - bool enable) +static void gfx_v8_0_enable_gfx_static_mg_power_gating(struct amdgpu_device *adev, + bool enable) { uint32_t data, temp; - /* Send msg to SMU via Powerplay */ - amdgpu_set_powergating_state(adev, - AMD_IP_BLOCK_TYPE_SMC, - enable ? AMD_PG_STATE_GATE : AMD_PG_STATE_UNGATE); + if (adev->asic_type == CHIP_POLARIS11) + /* Send msg to SMU via Powerplay */ + amdgpu_set_powergating_state(adev, + AMD_IP_BLOCK_TYPE_SMC, + enable ? + AMD_PG_STATE_GATE : AMD_PG_STATE_UNGATE); - if (enable) { - /* Enable static MGPG */ - temp = data = RREG32(mmRLC_PG_CNTL); + temp = data = RREG32(mmRLC_PG_CNTL); + /* Enable static MGPG */ + if (enable) data |= RLC_PG_CNTL__STATIC_PER_CU_PG_ENABLE_MASK; - - if (temp != data) - WREG32(mmRLC_PG_CNTL, data); - } else { - temp = data = RREG32(mmRLC_PG_CNTL); + else data &= ~RLC_PG_CNTL__STATIC_PER_CU_PG_ENABLE_MASK; - if (temp != data) - WREG32(mmRLC_PG_CNTL, data); - } + if (temp != data) + WREG32(mmRLC_PG_CNTL, data); } -static void polaris11_enable_gfx_dynamic_mg_power_gating(struct amdgpu_device *adev, - bool enable) +static void gfx_v8_0_enable_gfx_dynamic_mg_power_gating(struct amdgpu_device *adev, + bool enable) { uint32_t data, temp; - if (enable) { - /* Enable dynamic MGPG */ - temp = data = RREG32(mmRLC_PG_CNTL); + temp = data = RREG32(mmRLC_PG_CNTL); + /* Enable dynamic MGPG */ + if (enable) data |= RLC_PG_CNTL__DYN_PER_CU_PG_ENABLE_MASK; - - if (temp != data) - WREG32(mmRLC_PG_CNTL, data); - } else { - temp = data = RREG32(mmRLC_PG_CNTL); + else data &= ~RLC_PG_CNTL__DYN_PER_CU_PG_ENABLE_MASK; - if (temp != data) - WREG32(mmRLC_PG_CNTL, data); - } + if (temp != data) + WREG32(mmRLC_PG_CNTL, data); } static void polaris11_enable_gfx_quick_mg_power_gating(struct amdgpu_device *adev, @@ -5091,19 +5306,63 @@ static void polaris11_enable_gfx_quick_mg_power_gating(struct amdgpu_device *ade { uint32_t data, temp; - if (enable) { - /* Enable quick PG */ - temp = data = RREG32(mmRLC_PG_CNTL); - data |= 0x100000; + temp = data = RREG32(mmRLC_PG_CNTL); + /* Enable quick PG */ + if (enable) + data |= RLC_PG_CNTL__QUICK_PG_ENABLE_MASK; + else + data &= ~RLC_PG_CNTL__QUICK_PG_ENABLE_MASK; - if (temp != data) - WREG32(mmRLC_PG_CNTL, data); + if (temp != data) + WREG32(mmRLC_PG_CNTL, data); +} + +static void cz_enable_gfx_cg_power_gating(struct amdgpu_device *adev, + bool enable) +{ + u32 data, orig; + + orig = data = RREG32(mmRLC_PG_CNTL); + + if (enable) + data |= RLC_PG_CNTL__GFX_POWER_GATING_ENABLE_MASK; + else + data &= ~RLC_PG_CNTL__GFX_POWER_GATING_ENABLE_MASK; + + if (orig != data) + WREG32(mmRLC_PG_CNTL, data); +} + +static void cz_enable_gfx_pipeline_power_gating(struct amdgpu_device *adev, + bool enable) +{ + u32 data, orig; + + orig = data = RREG32(mmRLC_PG_CNTL); + + if (enable) + data |= RLC_PG_CNTL__GFX_PIPELINE_PG_ENABLE_MASK; + else + data &= ~RLC_PG_CNTL__GFX_PIPELINE_PG_ENABLE_MASK; + + if (orig != data) + WREG32(mmRLC_PG_CNTL, data); + + /* Read any GFX register to wake up GFX. */ + if (!enable) + data = RREG32(mmDB_RENDER_CONTROL); +} + +static void cz_update_gfx_cg_power_gating(struct amdgpu_device *adev, + bool enable) +{ + if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) && enable) { + cz_enable_gfx_cg_power_gating(adev, true); + if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PIPELINE) + cz_enable_gfx_pipeline_power_gating(adev, true); } else { - temp = data = RREG32(mmRLC_PG_CNTL); - data &= ~0x100000; - - if (temp != data) - WREG32(mmRLC_PG_CNTL, data); + cz_enable_gfx_cg_power_gating(adev, false); + cz_enable_gfx_pipeline_power_gating(adev, false); } } @@ -5111,21 +5370,42 @@ static int gfx_v8_0_set_powergating_state(void *handle, enum amd_powergating_state state) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + bool enable = (state == AMD_PG_STATE_GATE) ? true : false; if (!(adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) return 0; switch (adev->asic_type) { - case CHIP_POLARIS11: - if (adev->pg_flags & AMD_PG_SUPPORT_GFX_SMG) - polaris11_enable_gfx_static_mg_power_gating(adev, - state == AMD_PG_STATE_GATE ? true : false); - else if (adev->pg_flags & AMD_PG_SUPPORT_GFX_DMG) - polaris11_enable_gfx_dynamic_mg_power_gating(adev, - state == AMD_PG_STATE_GATE ? true : false); + case CHIP_CARRIZO: + case CHIP_STONEY: + if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) + cz_update_gfx_cg_power_gating(adev, enable); + + if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_SMG) && enable) + gfx_v8_0_enable_gfx_static_mg_power_gating(adev, true); else - polaris11_enable_gfx_quick_mg_power_gating(adev, - state == AMD_PG_STATE_GATE ? true : false); + gfx_v8_0_enable_gfx_static_mg_power_gating(adev, false); + + if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_DMG) && enable) + gfx_v8_0_enable_gfx_dynamic_mg_power_gating(adev, true); + else + gfx_v8_0_enable_gfx_dynamic_mg_power_gating(adev, false); + break; + case CHIP_POLARIS11: + if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_SMG) && enable) + gfx_v8_0_enable_gfx_static_mg_power_gating(adev, true); + else + gfx_v8_0_enable_gfx_static_mg_power_gating(adev, false); + + if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_DMG) && enable) + gfx_v8_0_enable_gfx_dynamic_mg_power_gating(adev, true); + else + gfx_v8_0_enable_gfx_dynamic_mg_power_gating(adev, false); + + if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_QUICK_MG) && enable) + polaris11_enable_gfx_quick_mg_power_gating(adev, true); + else + polaris11_enable_gfx_quick_mg_power_gating(adev, false); break; default: break; @@ -5139,7 +5419,7 @@ static void gfx_v8_0_send_serdes_cmd(struct amdgpu_device *adev, { uint32_t data; - gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); WREG32(mmRLC_SERDES_WR_CU_MASTER_MASK, 0xffffffff); WREG32(mmRLC_SERDES_WR_NONCU_MASTER_MASK, 0xffffffff); @@ -5527,6 +5807,8 @@ static void gfx_v8_0_update_coarse_grain_clock_gating(struct amdgpu_device *adev WREG32(mmRLC_CGCG_CGLS_CTRL, data); } + gfx_v8_0_wait_for_rlc_serdes(adev); + adev->gfx.rlc.funcs->exit_safe_mode(adev); } static int gfx_v8_0_update_gfx_clock_gating(struct amdgpu_device *adev, @@ -5652,17 +5934,6 @@ static void gfx_v8_0_ring_emit_ib_gfx(struct amdgpu_ring *ring, unsigned vm_id, bool ctx_switch) { u32 header, control = 0; - u32 next_rptr = ring->wptr + 5; - - if (ctx_switch) - next_rptr += 2; - - next_rptr += 4; - amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); - amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM); - amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc); - amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff); - amdgpu_ring_write(ring, next_rptr); /* insert SWITCH_BUFFER packet before first IB in the ring frame */ if (ctx_switch) { @@ -5691,23 +5962,9 @@ static void gfx_v8_0_ring_emit_ib_compute(struct amdgpu_ring *ring, struct amdgpu_ib *ib, unsigned vm_id, bool ctx_switch) { - u32 header, control = 0; - u32 next_rptr = ring->wptr + 5; + u32 control = INDIRECT_BUFFER_VALID | ib->length_dw | (vm_id << 24); - control |= INDIRECT_BUFFER_VALID; - - next_rptr += 4; - amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3)); - amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM); - amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc); - amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff); - amdgpu_ring_write(ring, next_rptr); - - header = PACKET3(PACKET3_INDIRECT_BUFFER, 2); - - control |= ib->length_dw | (vm_id << 24); - - amdgpu_ring_write(ring, header); + amdgpu_ring_write(ring, PACKET3(PACKET3_INDIRECT_BUFFER, 2)); amdgpu_ring_write(ring, #ifdef __BIG_ENDIAN (2 << 0) | @@ -6160,9 +6417,9 @@ static void gfx_v8_0_set_rlc_funcs(struct amdgpu_device *adev) { switch (adev->asic_type) { case CHIP_TOPAZ: - case CHIP_STONEY: adev->gfx.rlc.funcs = &iceland_rlc_funcs; break; + case CHIP_STONEY: case CHIP_CARRIZO: adev->gfx.rlc.funcs = &cz_rlc_funcs; break; @@ -6200,6 +6457,20 @@ static void gfx_v8_0_set_gds_init(struct amdgpu_device *adev) } } +static void gfx_v8_0_set_user_cu_inactive_bitmap(struct amdgpu_device *adev, + u32 bitmap) +{ + u32 data; + + if (!bitmap) + return; + + data = bitmap << GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS__SHIFT; + data &= GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS_MASK; + + WREG32(mmGC_USER_SHADER_ARRAY_CONFIG, data); +} + static u32 gfx_v8_0_get_cu_active_bitmap(struct amdgpu_device *adev) { u32 data, mask; @@ -6220,16 +6491,22 @@ static void gfx_v8_0_get_cu_info(struct amdgpu_device *adev) int i, j, k, counter, active_cu_number = 0; u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0; struct amdgpu_cu_info *cu_info = &adev->gfx.cu_info; + unsigned disable_masks[4 * 2]; memset(cu_info, 0, sizeof(*cu_info)); + amdgpu_gfx_parse_disable_cu(disable_masks, 4, 2); + mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { mask = 1; ao_bitmap = 0; counter = 0; - gfx_v8_0_select_se_sh(adev, i, j); + gfx_v8_0_select_se_sh(adev, i, j, 0xffffffff); + if (i < 4 && j < 2) + gfx_v8_0_set_user_cu_inactive_bitmap( + adev, disable_masks[i * 2 + j]); bitmap = gfx_v8_0_get_cu_active_bitmap(adev); cu_info->bitmap[i][j] = bitmap; @@ -6245,7 +6522,7 @@ static void gfx_v8_0_get_cu_info(struct amdgpu_device *adev) ao_cu_mask |= (ao_bitmap << (i * 16 + j * 8)); } } - gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); mutex_unlock(&adev->grbm_idx_mutex); cu_info->number = active_cu_number; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h index 16a49f53a2fa..bc82c794312c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.h @@ -26,7 +26,6 @@ extern const struct amd_ip_funcs gfx_v8_0_ip_funcs; -uint64_t gfx_v8_0_get_gpu_clock_counter(struct amdgpu_device *adev); void gfx_v8_0_select_se_sh(struct amdgpu_device *adev, u32 se_num, u32 sh_num); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 1feb6439cb0b..d24a82bd0c7a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -39,6 +39,7 @@ static void gmc_v7_0_set_gart_funcs(struct amdgpu_device *adev); static void gmc_v7_0_set_irq_funcs(struct amdgpu_device *adev); +static int gmc_v7_0_wait_for_idle(void *handle); MODULE_FIRMWARE("radeon/bonaire_mc.bin"); MODULE_FIRMWARE("radeon/hawaii_mc.bin"); @@ -73,39 +74,15 @@ static void gmc_v7_0_init_golden_registers(struct amdgpu_device *adev) } } -/** - * gmc7_mc_wait_for_idle - wait for MC idle callback. - * - * @adev: amdgpu_device pointer - * - * Wait for the MC (memory controller) to be idle. - * (evergreen+). - * Returns 0 if the MC is idle, -1 if not. - */ -int gmc_v7_0_mc_wait_for_idle(struct amdgpu_device *adev) -{ - unsigned i; - u32 tmp; - - for (i = 0; i < adev->usec_timeout; i++) { - /* read MC_STATUS */ - tmp = RREG32(mmSRBM_STATUS) & 0x1F00; - if (!tmp) - return 0; - udelay(1); - } - return -1; -} - -void gmc_v7_0_mc_stop(struct amdgpu_device *adev, - struct amdgpu_mode_mc_save *save) +static void gmc_v7_0_mc_stop(struct amdgpu_device *adev, + struct amdgpu_mode_mc_save *save) { u32 blackout; if (adev->mode_info.num_crtc) amdgpu_display_stop_mc_access(adev, save); - amdgpu_asic_wait_for_mc_idle(adev); + gmc_v7_0_wait_for_idle((void *)adev); blackout = RREG32(mmMC_SHARED_BLACKOUT_CNTL); if (REG_GET_FIELD(blackout, MC_SHARED_BLACKOUT_CNTL, BLACKOUT_MODE) != 1) { @@ -120,8 +97,8 @@ void gmc_v7_0_mc_stop(struct amdgpu_device *adev, udelay(100); } -void gmc_v7_0_mc_resume(struct amdgpu_device *adev, - struct amdgpu_mode_mc_save *save) +static void gmc_v7_0_mc_resume(struct amdgpu_device *adev, + struct amdgpu_mode_mc_save *save) { u32 tmp; @@ -311,7 +288,7 @@ static void gmc_v7_0_mc_program(struct amdgpu_device *adev) amdgpu_display_set_vga_render_state(adev, false); gmc_v7_0_mc_stop(adev, &save); - if (amdgpu_asic_wait_for_mc_idle(adev)) { + if (gmc_v7_0_wait_for_idle((void *)adev)) { dev_warn(adev->dev, "Wait for MC idle timedout !\n"); } /* Update configuration */ @@ -331,7 +308,7 @@ static void gmc_v7_0_mc_program(struct amdgpu_device *adev) WREG32(mmMC_VM_AGP_BASE, 0); WREG32(mmMC_VM_AGP_TOP, 0x0FFFFFFF); WREG32(mmMC_VM_AGP_BOT, 0x0FFFFFFF); - if (amdgpu_asic_wait_for_mc_idle(adev)) { + if (gmc_v7_0_wait_for_idle((void *)adev)) { dev_warn(adev->dev, "Wait for MC idle timedout !\n"); } gmc_v7_0_mc_resume(adev, &save); @@ -1137,7 +1114,7 @@ static int gmc_v7_0_soft_reset(void *handle) if (srbm_soft_reset) { gmc_v7_0_mc_stop(adev, &save); - if (gmc_v7_0_wait_for_idle(adev)) { + if (gmc_v7_0_wait_for_idle((void *)adev)) { dev_warn(adev->dev, "Wait for GMC idle timed out !\n"); } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.h b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.h index 36fcbbc46ada..0b386b5d2f7a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.h +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.h @@ -26,11 +26,4 @@ extern const struct amd_ip_funcs gmc_v7_0_ip_funcs; -/* XXX these shouldn't be exported */ -void gmc_v7_0_mc_stop(struct amdgpu_device *adev, - struct amdgpu_mode_mc_save *save); -void gmc_v7_0_mc_resume(struct amdgpu_device *adev, - struct amdgpu_mode_mc_save *save); -int gmc_v7_0_mc_wait_for_idle(struct amdgpu_device *adev); - #endif diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 9945d5bbf1fe..717359d3ba8c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -41,6 +41,7 @@ static void gmc_v8_0_set_gart_funcs(struct amdgpu_device *adev); static void gmc_v8_0_set_irq_funcs(struct amdgpu_device *adev); +static int gmc_v8_0_wait_for_idle(void *handle); MODULE_FIRMWARE("amdgpu/tonga_mc.bin"); MODULE_FIRMWARE("amdgpu/polaris11_mc.bin"); @@ -147,44 +148,15 @@ static void gmc_v8_0_init_golden_registers(struct amdgpu_device *adev) } } -/** - * gmc8_mc_wait_for_idle - wait for MC idle callback. - * - * @adev: amdgpu_device pointer - * - * Wait for the MC (memory controller) to be idle. - * (evergreen+). - * Returns 0 if the MC is idle, -1 if not. - */ -int gmc_v8_0_mc_wait_for_idle(struct amdgpu_device *adev) -{ - unsigned i; - u32 tmp; - - for (i = 0; i < adev->usec_timeout; i++) { - /* read MC_STATUS */ - tmp = RREG32(mmSRBM_STATUS) & (SRBM_STATUS__VMC_BUSY_MASK | - SRBM_STATUS__MCB_BUSY_MASK | - SRBM_STATUS__MCB_NON_DISPLAY_BUSY_MASK | - SRBM_STATUS__MCC_BUSY_MASK | - SRBM_STATUS__MCD_BUSY_MASK | - SRBM_STATUS__VMC1_BUSY_MASK); - if (!tmp) - return 0; - udelay(1); - } - return -1; -} - -void gmc_v8_0_mc_stop(struct amdgpu_device *adev, - struct amdgpu_mode_mc_save *save) +static void gmc_v8_0_mc_stop(struct amdgpu_device *adev, + struct amdgpu_mode_mc_save *save) { u32 blackout; if (adev->mode_info.num_crtc) amdgpu_display_stop_mc_access(adev, save); - amdgpu_asic_wait_for_mc_idle(adev); + gmc_v8_0_wait_for_idle(adev); blackout = RREG32(mmMC_SHARED_BLACKOUT_CNTL); if (REG_GET_FIELD(blackout, MC_SHARED_BLACKOUT_CNTL, BLACKOUT_MODE) != 1) { @@ -199,8 +171,8 @@ void gmc_v8_0_mc_stop(struct amdgpu_device *adev, udelay(100); } -void gmc_v8_0_mc_resume(struct amdgpu_device *adev, - struct amdgpu_mode_mc_save *save) +static void gmc_v8_0_mc_resume(struct amdgpu_device *adev, + struct amdgpu_mode_mc_save *save) { u32 tmp; @@ -393,7 +365,7 @@ static void gmc_v8_0_mc_program(struct amdgpu_device *adev) amdgpu_display_set_vga_render_state(adev, false); gmc_v8_0_mc_stop(adev, &save); - if (amdgpu_asic_wait_for_mc_idle(adev)) { + if (gmc_v8_0_wait_for_idle((void *)adev)) { dev_warn(adev->dev, "Wait for MC idle timedout !\n"); } /* Update configuration */ @@ -413,7 +385,7 @@ static void gmc_v8_0_mc_program(struct amdgpu_device *adev) WREG32(mmMC_VM_AGP_BASE, 0); WREG32(mmMC_VM_AGP_TOP, 0x0FFFFFFF); WREG32(mmMC_VM_AGP_BOT, 0x0FFFFFFF); - if (amdgpu_asic_wait_for_mc_idle(adev)) { + if (gmc_v8_0_wait_for_idle((void *)adev)) { dev_warn(adev->dev, "Wait for MC idle timedout !\n"); } gmc_v8_0_mc_resume(adev, &save); @@ -1140,7 +1112,7 @@ static int gmc_v8_0_soft_reset(void *handle) if (srbm_soft_reset) { gmc_v8_0_mc_stop(adev, &save); - if (gmc_v8_0_wait_for_idle(adev)) { + if (gmc_v8_0_wait_for_idle((void *)adev)) { dev_warn(adev->dev, "Wait for GMC idle timed out !\n"); } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.h b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.h index 973436086b38..fc5001a8119d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.h +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.h @@ -26,11 +26,4 @@ extern const struct amd_ip_funcs gmc_v8_0_ip_funcs; -/* XXX these shouldn't be exported */ -void gmc_v8_0_mc_stop(struct amdgpu_device *adev, - struct amdgpu_mode_mc_save *save); -void gmc_v8_0_mc_resume(struct amdgpu_device *adev, - struct amdgpu_mode_mc_save *save); -int gmc_v8_0_mc_wait_for_idle(struct amdgpu_device *adev); - #endif diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c b/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c index 460bc8ad37e6..2f078ad6095c 100644 --- a/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/iceland_dpm.c @@ -24,7 +24,7 @@ #include #include "drmP.h" #include "amdgpu.h" -#include "iceland_smumgr.h" +#include "iceland_smum.h" MODULE_FIRMWARE("amdgpu/topaz_smc.bin"); @@ -72,6 +72,11 @@ static int iceland_dpm_sw_init(void *handle) static int iceland_dpm_sw_fini(void *handle) { + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + release_firmware(adev->pm.fw); + adev->pm.fw = NULL; + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c index 52ee08193295..211839913728 100644 --- a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c +++ b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c @@ -25,7 +25,7 @@ #include "drmP.h" #include "amdgpu.h" #include "ppsmc.h" -#include "iceland_smumgr.h" +#include "iceland_smum.h" #include "smu_ucode_xfer_vi.h" #include "amdgpu_ucode.h" @@ -211,7 +211,7 @@ static int iceland_send_msg_to_smc_without_waiting(struct amdgpu_device *adev, PPSMC_Msg msg) { if (!iceland_is_smc_ram_running(adev)) - return -EINVAL;; + return -EINVAL; if (wait_smu_response(adev)) { DRM_ERROR("Failed to send previous message\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_smumgr.h b/drivers/gpu/drm/amd/amdgpu/iceland_smum.h similarity index 96% rename from drivers/gpu/drm/amd/amdgpu/iceland_smumgr.h rename to drivers/gpu/drm/amd/amdgpu/iceland_smum.h index 1e0769e110fa..5983e3150cc5 100644 --- a/drivers/gpu/drm/amd/amdgpu/iceland_smumgr.h +++ b/drivers/gpu/drm/amd/amdgpu/iceland_smum.h @@ -21,8 +21,8 @@ * */ -#ifndef ICELAND_SMUMGR_H -#define ICELAND_SMUMGR_H +#ifndef ICELAND_SMUM_H +#define ICELAND_SMUM_H #include "ppsmc.h" diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c index a789a863d677..a845e883f5fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c @@ -191,6 +191,7 @@ static void sumo_construct_vid_mapping_table(struct amdgpu_device *adev, vid_mapping_table->num_entries = i; } +#if 0 static const struct kv_lcac_config_values sx_local_cac_cfg_kv[] = { { 0, 4, 1 }, @@ -289,6 +290,7 @@ static const struct kv_lcac_config_reg cpl_cac_config_reg[] = { { 0xc0400d80, 0x003e0000, 17, 0x3fc00000, 22, 0x0001fffe, 1, 0x00000001, 0 } }; +#endif static const struct kv_pt_config_reg didt_config_kv[] = { @@ -507,19 +509,19 @@ static int kv_enable_didt(struct amdgpu_device *adev, bool enable) pi->caps_db_ramping || pi->caps_td_ramping || pi->caps_tcp_ramping) { - gfx_v7_0_enter_rlc_safe_mode(adev); + adev->gfx.rlc.funcs->enter_safe_mode(adev); if (enable) { ret = kv_program_pt_config_registers(adev, didt_config_kv); if (ret) { - gfx_v7_0_exit_rlc_safe_mode(adev); + adev->gfx.rlc.funcs->exit_safe_mode(adev); return ret; } } kv_do_enable_didt(adev, enable); - gfx_v7_0_exit_rlc_safe_mode(adev); + adev->gfx.rlc.funcs->exit_safe_mode(adev); } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/ppsmc.h b/drivers/gpu/drm/amd/amdgpu/ppsmc.h index 7837f2ecc357..8463245f424f 100644 --- a/drivers/gpu/drm/amd/amdgpu/ppsmc.h +++ b/drivers/gpu/drm/amd/amdgpu/ppsmc.h @@ -90,7 +90,9 @@ typedef uint8_t PPSMC_Result; #define PPSMC_StartFanControl ((uint8_t)0x5B) #define PPSMC_StopFanControl ((uint8_t)0x5C) #define PPSMC_MSG_NoDisplay ((uint8_t)0x5D) +#define PPSMC_NoDisplay ((uint8_t)0x5D) #define PPSMC_MSG_HasDisplay ((uint8_t)0x5E) +#define PPSMC_HasDisplay ((uint8_t)0x5E) #define PPSMC_MSG_UVDPowerOFF ((uint8_t)0x60) #define PPSMC_MSG_UVDPowerON ((uint8_t)0x61) #define PPSMC_MSG_EnableULV ((uint8_t)0x62) @@ -108,6 +110,7 @@ typedef uint8_t PPSMC_Result; #define PPSMC_MSG_DisableDTE ((uint8_t)0x88) #define PPSMC_MSG_ThrottleOVRDSCLKDS ((uint8_t)0x96) #define PPSMC_MSG_CancelThrottleOVRDSCLKDS ((uint8_t)0x97) +#define PPSMC_MSG_EnableACDCGPIOInterrupt ((uint16_t) 0x149) /* CI/KV/KB */ #define PPSMC_MSG_UVDDPM_SetEnabledMask ((uint16_t) 0x12D) @@ -161,6 +164,7 @@ typedef uint8_t PPSMC_Result; #define PPSMC_MSG_MASTER_DeepSleep_OFF ((uint16_t) 0x190) #define PPSMC_MSG_Remove_DC_Clamp ((uint16_t) 0x191) #define PPSMC_MSG_SetFanPwmMax ((uint16_t) 0x19A) +#define PPSMC_MSG_SetFanRpmMax ((uint16_t) 0x205) #define PPSMC_MSG_ENABLE_THERMAL_DPM ((uint16_t) 0x19C) #define PPSMC_MSG_DISABLE_THERMAL_DPM ((uint16_t) 0x19D) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index f4c3130d3fdb..1351c7e834a2 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -105,6 +105,15 @@ static void sdma_v2_4_init_golden_registers(struct amdgpu_device *adev) } } +static void sdma_v2_4_free_microcode(struct amdgpu_device *adev) +{ + int i; + for (i = 0; i < adev->sdma.num_instances; i++) { + release_firmware(adev->sdma.instance[i].fw); + adev->sdma.instance[i].fw = NULL; + } +} + /** * sdma_v2_4_init_microcode - load ucode images from disk * @@ -246,19 +255,6 @@ static void sdma_v2_4_ring_emit_ib(struct amdgpu_ring *ring, unsigned vm_id, bool ctx_switch) { u32 vmid = vm_id & 0xf; - u32 next_rptr = ring->wptr + 5; - - while ((next_rptr & 7) != 2) - next_rptr++; - - next_rptr += 6; - - amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_WRITE) | - SDMA_PKT_HEADER_SUB_OP(SDMA_SUBOP_WRITE_LINEAR)); - amdgpu_ring_write(ring, lower_32_bits(ring->next_rptr_gpu_addr) & 0xfffffffc); - amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr)); - amdgpu_ring_write(ring, SDMA_PKT_WRITE_UNTILED_DW_3_COUNT(1)); - amdgpu_ring_write(ring, next_rptr); /* IB packet must end on a 8 DW boundary */ sdma_v2_4_ring_insert_nop(ring, (10 - (ring->wptr & 7)) % 8); @@ -397,7 +393,7 @@ static void sdma_v2_4_enable(struct amdgpu_device *adev, bool enable) u32 f32_cntl; int i; - if (enable == false) { + if (!enable) { sdma_v2_4_gfx_stop(adev); sdma_v2_4_rlc_stop(adev); } @@ -461,6 +457,8 @@ static int sdma_v2_4_gfx_resume(struct amdgpu_device *adev) /* Initialize the ring buffer's read and write pointers */ WREG32(mmSDMA0_GFX_RB_RPTR + sdma_offsets[i], 0); WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], 0); + WREG32(mmSDMA0_GFX_IB_RPTR + sdma_offsets[i], 0); + WREG32(mmSDMA0_GFX_IB_OFFSET + sdma_offsets[i], 0); /* set the wb address whether it's enabled or not */ WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i], @@ -489,7 +487,11 @@ static int sdma_v2_4_gfx_resume(struct amdgpu_device *adev) WREG32(mmSDMA0_GFX_IB_CNTL + sdma_offsets[i], ib_cntl); ring->ready = true; + } + sdma_v2_4_enable(adev, true); + for (i = 0; i < adev->sdma.num_instances; i++) { + ring = &adev->sdma.instance[i].ring; r = amdgpu_ring_test_ring(ring); if (r) { ring->ready = false; @@ -565,23 +567,25 @@ static int sdma_v2_4_start(struct amdgpu_device *adev) { int r; - if (!adev->firmware.smu_load) { - r = sdma_v2_4_load_microcode(adev); - if (r) - return r; - } else { - r = adev->smu.smumgr_funcs->check_fw_load_finish(adev, - AMDGPU_UCODE_ID_SDMA0); - if (r) - return -EINVAL; - r = adev->smu.smumgr_funcs->check_fw_load_finish(adev, - AMDGPU_UCODE_ID_SDMA1); - if (r) - return -EINVAL; + if (!adev->pp_enabled) { + if (!adev->firmware.smu_load) { + r = sdma_v2_4_load_microcode(adev); + if (r) + return r; + } else { + r = adev->smu.smumgr_funcs->check_fw_load_finish(adev, + AMDGPU_UCODE_ID_SDMA0); + if (r) + return -EINVAL; + r = adev->smu.smumgr_funcs->check_fw_load_finish(adev, + AMDGPU_UCODE_ID_SDMA1); + if (r) + return -EINVAL; + } } - /* unhalt the MEs */ - sdma_v2_4_enable(adev, true); + /* halt the engine before programing */ + sdma_v2_4_enable(adev, false); /* start the gfx rings and rlc compute queues */ r = sdma_v2_4_gfx_resume(adev); @@ -664,20 +668,19 @@ static int sdma_v2_4_ring_test_ring(struct amdgpu_ring *ring) * Test a simple IB in the DMA ring (VI). * Returns 0 on success, error on failure. */ -static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring) +static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) { struct amdgpu_device *adev = ring->adev; struct amdgpu_ib ib; struct fence *f = NULL; - unsigned i; unsigned index; - int r; u32 tmp = 0; u64 gpu_addr; + long r; r = amdgpu_wb_get(adev, &index); if (r) { - dev_err(adev->dev, "(%d) failed to allocate wb slot\n", r); + dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r); return r; } @@ -687,7 +690,7 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring) memset(&ib, 0, sizeof(ib)); r = amdgpu_ib_get(adev, NULL, 256, &ib); if (r) { - DRM_ERROR("amdgpu: failed to get ib (%d).\n", r); + DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r); goto err0; } @@ -706,28 +709,25 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring) if (r) goto err1; - r = fence_wait(f, false); - if (r) { - DRM_ERROR("amdgpu: fence wait failed (%d).\n", r); + r = fence_wait_timeout(f, false, timeout); + if (r == 0) { + DRM_ERROR("amdgpu: IB test timed out\n"); + r = -ETIMEDOUT; + goto err1; + } else if (r) { + DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r); goto err1; } - for (i = 0; i < adev->usec_timeout; i++) { - tmp = le32_to_cpu(adev->wb.wb[index]); - if (tmp == 0xDEADBEEF) - break; - DRM_UDELAY(1); - } - if (i < adev->usec_timeout) { - DRM_INFO("ib test on ring %d succeeded in %u usecs\n", - ring->idx, i); - goto err1; + tmp = le32_to_cpu(adev->wb.wb[index]); + if (tmp == 0xDEADBEEF) { + DRM_INFO("ib test on ring %d succeeded\n", ring->idx); + r = 0; } else { DRM_ERROR("amdgpu: ib test failed (0x%08X)\n", tmp); r = -EINVAL; } err1: - fence_put(f); amdgpu_ib_free(adev, &ib, NULL); fence_put(f); err0: @@ -1012,6 +1012,7 @@ static int sdma_v2_4_sw_fini(void *handle) for (i = 0; i < adev->sdma.num_instances; i++) amdgpu_ring_fini(&adev->sdma.instance[i].ring); + sdma_v2_4_free_microcode(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index 31d99b0010f7..653ce5ed55ae 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -236,6 +236,15 @@ static void sdma_v3_0_init_golden_registers(struct amdgpu_device *adev) } } +static void sdma_v3_0_free_microcode(struct amdgpu_device *adev) +{ + int i; + for (i = 0; i < adev->sdma.num_instances; i++) { + release_firmware(adev->sdma.instance[i].fw); + adev->sdma.instance[i].fw = NULL; + } +} + /** * sdma_v3_0_init_microcode - load ucode images from disk * @@ -406,18 +415,6 @@ static void sdma_v3_0_ring_emit_ib(struct amdgpu_ring *ring, unsigned vm_id, bool ctx_switch) { u32 vmid = vm_id & 0xf; - u32 next_rptr = ring->wptr + 5; - - while ((next_rptr & 7) != 2) - next_rptr++; - next_rptr += 6; - - amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_WRITE) | - SDMA_PKT_HEADER_SUB_OP(SDMA_SUBOP_WRITE_LINEAR)); - amdgpu_ring_write(ring, lower_32_bits(ring->next_rptr_gpu_addr) & 0xfffffffc); - amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr)); - amdgpu_ring_write(ring, SDMA_PKT_WRITE_UNTILED_DW_3_COUNT(1)); - amdgpu_ring_write(ring, next_rptr); /* IB packet must end on a 8 DW boundary */ sdma_v3_0_ring_insert_nop(ring, (10 - (ring->wptr & 7)) % 8); @@ -607,7 +604,7 @@ static void sdma_v3_0_enable(struct amdgpu_device *adev, bool enable) u32 f32_cntl; int i; - if (enable == false) { + if (!enable) { sdma_v3_0_gfx_stop(adev); sdma_v3_0_rlc_stop(adev); } @@ -672,6 +669,8 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev) /* Initialize the ring buffer's read and write pointers */ WREG32(mmSDMA0_GFX_RB_RPTR + sdma_offsets[i], 0); WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], 0); + WREG32(mmSDMA0_GFX_IB_RPTR + sdma_offsets[i], 0); + WREG32(mmSDMA0_GFX_IB_OFFSET + sdma_offsets[i], 0); /* set the wb address whether it's enabled or not */ WREG32(mmSDMA0_GFX_RB_RPTR_ADDR_HI + sdma_offsets[i], @@ -711,7 +710,15 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev) WREG32(mmSDMA0_GFX_IB_CNTL + sdma_offsets[i], ib_cntl); ring->ready = true; + } + /* unhalt the MEs */ + sdma_v3_0_enable(adev, true); + /* enable sdma ring preemption */ + sdma_v3_0_ctx_switch_enable(adev, true); + + for (i = 0; i < adev->sdma.num_instances; i++) { + ring = &adev->sdma.instance[i].ring; r = amdgpu_ring_test_ring(ring); if (r) { ring->ready = false; @@ -804,10 +811,9 @@ static int sdma_v3_0_start(struct amdgpu_device *adev) } } - /* unhalt the MEs */ - sdma_v3_0_enable(adev, true); - /* enable sdma ring preemption */ - sdma_v3_0_ctx_switch_enable(adev, true); + /* disble sdma engine before programing it */ + sdma_v3_0_ctx_switch_enable(adev, false); + sdma_v3_0_enable(adev, false); /* start the gfx rings and rlc compute queues */ r = sdma_v3_0_gfx_resume(adev); @@ -890,20 +896,19 @@ static int sdma_v3_0_ring_test_ring(struct amdgpu_ring *ring) * Test a simple IB in the DMA ring (VI). * Returns 0 on success, error on failure. */ -static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring) +static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) { struct amdgpu_device *adev = ring->adev; struct amdgpu_ib ib; struct fence *f = NULL; - unsigned i; unsigned index; - int r; u32 tmp = 0; u64 gpu_addr; + long r; r = amdgpu_wb_get(adev, &index); if (r) { - dev_err(adev->dev, "(%d) failed to allocate wb slot\n", r); + dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r); return r; } @@ -913,7 +918,7 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring) memset(&ib, 0, sizeof(ib)); r = amdgpu_ib_get(adev, NULL, 256, &ib); if (r) { - DRM_ERROR("amdgpu: failed to get ib (%d).\n", r); + DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r); goto err0; } @@ -932,27 +937,24 @@ static int sdma_v3_0_ring_test_ib(struct amdgpu_ring *ring) if (r) goto err1; - r = fence_wait(f, false); - if (r) { - DRM_ERROR("amdgpu: fence wait failed (%d).\n", r); + r = fence_wait_timeout(f, false, timeout); + if (r == 0) { + DRM_ERROR("amdgpu: IB test timed out\n"); + r = -ETIMEDOUT; + goto err1; + } else if (r < 0) { + DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r); goto err1; } - for (i = 0; i < adev->usec_timeout; i++) { - tmp = le32_to_cpu(adev->wb.wb[index]); - if (tmp == 0xDEADBEEF) - break; - DRM_UDELAY(1); - } - if (i < adev->usec_timeout) { - DRM_INFO("ib test on ring %d succeeded in %u usecs\n", - ring->idx, i); - goto err1; + tmp = le32_to_cpu(adev->wb.wb[index]); + if (tmp == 0xDEADBEEF) { + DRM_INFO("ib test on ring %d succeeded\n", ring->idx); + r = 0; } else { DRM_ERROR("amdgpu: ib test failed (0x%08X)\n", tmp); r = -EINVAL; } err1: - fence_put(f); amdgpu_ib_free(adev, &ib, NULL); fence_put(f); err0: @@ -1247,6 +1249,7 @@ static int sdma_v3_0_sw_fini(void *handle) for (i = 0; i < adev->sdma.num_instances; i++) amdgpu_ring_fini(&adev->sdma.instance[i].ring); + sdma_v3_0_free_microcode(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c index b7615cefcac4..f06f6f4dc3a8 100644 --- a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c @@ -71,6 +71,11 @@ static int tonga_dpm_sw_init(void *handle) static int tonga_dpm_sw_fini(void *handle) { + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + release_firmware(adev->pm.fw); + adev->pm.fw = NULL; + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_smc.c b/drivers/gpu/drm/amd/amdgpu/tonga_smc.c index 083893dd68c0..940de1836f8f 100644 --- a/drivers/gpu/drm/amd/amdgpu/tonga_smc.c +++ b/drivers/gpu/drm/amd/amdgpu/tonga_smc.c @@ -173,7 +173,7 @@ static int tonga_send_msg_to_smc(struct amdgpu_device *adev, PPSMC_Msg msg) { if (!tonga_is_smc_ram_running(adev)) { - return -EINVAL;; + return -EINVAL; } if (wait_smu_response(adev)) { diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c index f07551476a70..132e613ed674 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c @@ -34,6 +34,8 @@ #include "oss/oss_2_0_d.h" #include "oss/oss_2_0_sh_mask.h" +#include "bif/bif_4_1_d.h" + static void uvd_v4_2_mc_resume(struct amdgpu_device *adev); static void uvd_v4_2_init_cg(struct amdgpu_device *adev); static void uvd_v4_2_set_ring_funcs(struct amdgpu_device *adev); @@ -438,6 +440,32 @@ static void uvd_v4_2_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq amdgpu_ring_write(ring, 2); } +/** + * uvd_v4_2_ring_emit_hdp_flush - emit an hdp flush + * + * @ring: amdgpu_ring pointer + * + * Emits an hdp flush. + */ +static void uvd_v4_2_ring_emit_hdp_flush(struct amdgpu_ring *ring) +{ + amdgpu_ring_write(ring, PACKET0(mmHDP_MEM_COHERENCY_FLUSH_CNTL, 0)); + amdgpu_ring_write(ring, 0); +} + +/** + * uvd_v4_2_ring_hdp_invalidate - emit an hdp invalidate + * + * @ring: amdgpu_ring pointer + * + * Emits an hdp invalidate. + */ +static void uvd_v4_2_ring_emit_hdp_invalidate(struct amdgpu_ring *ring) +{ + amdgpu_ring_write(ring, PACKET0(mmHDP_DEBUG0, 0)); + amdgpu_ring_write(ring, 1); +} + /** * uvd_v4_2_ring_test_ring - register write test * @@ -498,49 +526,6 @@ static void uvd_v4_2_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, ib->length_dw); } -/** - * uvd_v4_2_ring_test_ib - test ib execution - * - * @ring: amdgpu_ring pointer - * - * Test if we can successfully execute an IB - */ -static int uvd_v4_2_ring_test_ib(struct amdgpu_ring *ring) -{ - struct amdgpu_device *adev = ring->adev; - struct fence *fence = NULL; - int r; - - r = amdgpu_asic_set_uvd_clocks(adev, 53300, 40000); - if (r) { - DRM_ERROR("amdgpu: failed to raise UVD clocks (%d).\n", r); - return r; - } - - r = amdgpu_uvd_get_create_msg(ring, 1, NULL); - if (r) { - DRM_ERROR("amdgpu: failed to get create msg (%d).\n", r); - goto error; - } - - r = amdgpu_uvd_get_destroy_msg(ring, 1, true, &fence); - if (r) { - DRM_ERROR("amdgpu: failed to get destroy ib (%d).\n", r); - goto error; - } - - r = fence_wait(fence, false); - if (r) { - DRM_ERROR("amdgpu: fence wait failed (%d).\n", r); - goto error; - } - DRM_INFO("ib test on ring %d succeeded\n", ring->idx); -error: - fence_put(fence); - amdgpu_asic_set_uvd_clocks(adev, 0, 0); - return r; -} - /** * uvd_v4_2_mc_resume - memory controller programming * @@ -763,10 +748,14 @@ static const struct amdgpu_ring_funcs uvd_v4_2_ring_funcs = { .parse_cs = amdgpu_uvd_ring_parse_cs, .emit_ib = uvd_v4_2_ring_emit_ib, .emit_fence = uvd_v4_2_ring_emit_fence, + .emit_hdp_flush = uvd_v4_2_ring_emit_hdp_flush, + .emit_hdp_invalidate = uvd_v4_2_ring_emit_hdp_invalidate, .test_ring = uvd_v4_2_ring_test_ring, - .test_ib = uvd_v4_2_ring_test_ib, + .test_ib = amdgpu_uvd_ring_test_ib, .insert_nop = amdgpu_ring_insert_nop, .pad_ib = amdgpu_ring_generic_pad_ib, + .begin_use = amdgpu_uvd_ring_begin_use, + .end_use = amdgpu_uvd_ring_end_use, }; static void uvd_v4_2_set_ring_funcs(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c index e0a76a883d46..101de136ba63 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c @@ -31,6 +31,7 @@ #include "uvd/uvd_5_0_sh_mask.h" #include "oss/oss_2_0_d.h" #include "oss/oss_2_0_sh_mask.h" +#include "bif/bif_5_0_d.h" #include "vi.h" static void uvd_v5_0_set_ring_funcs(struct amdgpu_device *adev); @@ -488,6 +489,32 @@ static void uvd_v5_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq amdgpu_ring_write(ring, 2); } +/** + * uvd_v5_0_ring_emit_hdp_flush - emit an hdp flush + * + * @ring: amdgpu_ring pointer + * + * Emits an hdp flush. + */ +static void uvd_v5_0_ring_emit_hdp_flush(struct amdgpu_ring *ring) +{ + amdgpu_ring_write(ring, PACKET0(mmHDP_MEM_COHERENCY_FLUSH_CNTL, 0)); + amdgpu_ring_write(ring, 0); +} + +/** + * uvd_v5_0_ring_hdp_invalidate - emit an hdp invalidate + * + * @ring: amdgpu_ring pointer + * + * Emits an hdp invalidate. + */ +static void uvd_v5_0_ring_emit_hdp_invalidate(struct amdgpu_ring *ring) +{ + amdgpu_ring_write(ring, PACKET0(mmHDP_DEBUG0, 0)); + amdgpu_ring_write(ring, 1); +} + /** * uvd_v5_0_ring_test_ring - register write test * @@ -550,49 +577,6 @@ static void uvd_v5_0_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, ib->length_dw); } -/** - * uvd_v5_0_ring_test_ib - test ib execution - * - * @ring: amdgpu_ring pointer - * - * Test if we can successfully execute an IB - */ -static int uvd_v5_0_ring_test_ib(struct amdgpu_ring *ring) -{ - struct amdgpu_device *adev = ring->adev; - struct fence *fence = NULL; - int r; - - r = amdgpu_asic_set_uvd_clocks(adev, 53300, 40000); - if (r) { - DRM_ERROR("amdgpu: failed to raise UVD clocks (%d).\n", r); - return r; - } - - r = amdgpu_uvd_get_create_msg(ring, 1, NULL); - if (r) { - DRM_ERROR("amdgpu: failed to get create msg (%d).\n", r); - goto error; - } - - r = amdgpu_uvd_get_destroy_msg(ring, 1, true, &fence); - if (r) { - DRM_ERROR("amdgpu: failed to get destroy ib (%d).\n", r); - goto error; - } - - r = fence_wait(fence, false); - if (r) { - DRM_ERROR("amdgpu: fence wait failed (%d).\n", r); - goto error; - } - DRM_INFO("ib test on ring %d succeeded\n", ring->idx); -error: - fence_put(fence); - amdgpu_asic_set_uvd_clocks(adev, 0, 0); - return r; -} - static bool uvd_v5_0_is_idle(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -815,10 +799,14 @@ static const struct amdgpu_ring_funcs uvd_v5_0_ring_funcs = { .parse_cs = amdgpu_uvd_ring_parse_cs, .emit_ib = uvd_v5_0_ring_emit_ib, .emit_fence = uvd_v5_0_ring_emit_fence, + .emit_hdp_flush = uvd_v5_0_ring_emit_hdp_flush, + .emit_hdp_invalidate = uvd_v5_0_ring_emit_hdp_invalidate, .test_ring = uvd_v5_0_ring_test_ring, - .test_ib = uvd_v5_0_ring_test_ib, + .test_ib = amdgpu_uvd_ring_test_ib, .insert_nop = amdgpu_ring_insert_nop, .pad_ib = amdgpu_ring_generic_pad_ib, + .begin_use = amdgpu_uvd_ring_begin_use, + .end_use = amdgpu_uvd_ring_end_use, }; static void uvd_v5_0_set_ring_funcs(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index c9929d665c01..7f21102bfb99 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -33,6 +33,8 @@ #include "oss/oss_2_0_sh_mask.h" #include "smu/smu_7_1_3_d.h" #include "smu/smu_7_1_3_sh_mask.h" +#include "bif/bif_5_1_d.h" +#include "gmc/gmc_8_1_d.h" #include "vi.h" static void uvd_v6_0_set_ring_funcs(struct amdgpu_device *adev); @@ -385,8 +387,8 @@ static int uvd_v6_0_start(struct amdgpu_device *adev) uint32_t mp_swap_cntl; int i, j, r; - /*disable DPG */ - WREG32_P(mmUVD_POWER_STATUS, 0, ~(1 << 2)); + /* disable DPG */ + WREG32_P(mmUVD_POWER_STATUS, 0, ~UVD_POWER_STATUS__UVD_PG_MODE_MASK); /* disable byte swapping */ lmi_swap_cntl = 0; @@ -405,17 +407,21 @@ static int uvd_v6_0_start(struct amdgpu_device *adev) } /* disable interupt */ - WREG32_P(mmUVD_MASTINT_EN, 0, ~(1 << 1)); + WREG32_P(mmUVD_MASTINT_EN, 0, ~UVD_MASTINT_EN__VCPU_EN_MASK); /* stall UMC and register bus before resetting VCPU */ - WREG32_P(mmUVD_LMI_CTRL2, 1 << 8, ~(1 << 8)); + WREG32_P(mmUVD_LMI_CTRL2, UVD_LMI_CTRL2__STALL_ARB_UMC_MASK, ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); mdelay(1); /* put LMI, VCPU, RBC etc... into reset */ - WREG32(mmUVD_SOFT_RESET, UVD_SOFT_RESET__LMI_SOFT_RESET_MASK | - UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK | UVD_SOFT_RESET__LBSI_SOFT_RESET_MASK | - UVD_SOFT_RESET__RBC_SOFT_RESET_MASK | UVD_SOFT_RESET__CSM_SOFT_RESET_MASK | - UVD_SOFT_RESET__CXW_SOFT_RESET_MASK | UVD_SOFT_RESET__TAP_SOFT_RESET_MASK | + WREG32(mmUVD_SOFT_RESET, + UVD_SOFT_RESET__LMI_SOFT_RESET_MASK | + UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK | + UVD_SOFT_RESET__LBSI_SOFT_RESET_MASK | + UVD_SOFT_RESET__RBC_SOFT_RESET_MASK | + UVD_SOFT_RESET__CSM_SOFT_RESET_MASK | + UVD_SOFT_RESET__CXW_SOFT_RESET_MASK | + UVD_SOFT_RESET__TAP_SOFT_RESET_MASK | UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK); mdelay(5); @@ -424,8 +430,13 @@ static int uvd_v6_0_start(struct amdgpu_device *adev) mdelay(5); /* initialize UVD memory controller */ - WREG32(mmUVD_LMI_CTRL, 0x40 | (1 << 8) | (1 << 13) | - (1 << 21) | (1 << 9) | (1 << 20)); + WREG32(mmUVD_LMI_CTRL, + (0x40 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) | + UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK | + UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK | + UVD_LMI_CTRL__VCPU_DATA_COHERENCY_EN_MASK | + UVD_LMI_CTRL__REQ_MODE_MASK | + UVD_LMI_CTRL__DISABLE_ON_FWV_FAIL_MASK); #ifdef __BIG_ENDIAN /* swap (8 in 32) RB and IB */ @@ -447,10 +458,10 @@ static int uvd_v6_0_start(struct amdgpu_device *adev) mdelay(5); /* enable VCPU clock */ - WREG32(mmUVD_VCPU_CNTL, 1 << 9); + WREG32(mmUVD_VCPU_CNTL, UVD_VCPU_CNTL__CLK_EN_MASK); /* enable UMC */ - WREG32_P(mmUVD_LMI_CTRL2, 0, ~(1 << 8)); + WREG32_P(mmUVD_LMI_CTRL2, 0, ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK); /* boot up the VCPU */ WREG32(mmUVD_SOFT_RESET, 0); @@ -484,10 +495,12 @@ static int uvd_v6_0_start(struct amdgpu_device *adev) return r; } /* enable master interrupt */ - WREG32_P(mmUVD_MASTINT_EN, 3 << 1, ~(3 << 1)); + WREG32_P(mmUVD_MASTINT_EN, + (UVD_MASTINT_EN__VCPU_EN_MASK|UVD_MASTINT_EN__SYS_EN_MASK), + ~(UVD_MASTINT_EN__VCPU_EN_MASK|UVD_MASTINT_EN__SYS_EN_MASK)); /* clear the bit 4 of UVD_STATUS */ - WREG32_P(mmUVD_STATUS, 0, ~(2 << 1)); + WREG32_P(mmUVD_STATUS, 0, ~(2 << UVD_STATUS__VCPU_REPORT__SHIFT)); rb_bufsz = order_base_2(ring->ring_size); tmp = 0; @@ -580,6 +593,32 @@ static void uvd_v6_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq amdgpu_ring_write(ring, 2); } +/** + * uvd_v6_0_ring_emit_hdp_flush - emit an hdp flush + * + * @ring: amdgpu_ring pointer + * + * Emits an hdp flush. + */ +static void uvd_v6_0_ring_emit_hdp_flush(struct amdgpu_ring *ring) +{ + amdgpu_ring_write(ring, PACKET0(mmHDP_MEM_COHERENCY_FLUSH_CNTL, 0)); + amdgpu_ring_write(ring, 0); +} + +/** + * uvd_v6_0_ring_hdp_invalidate - emit an hdp invalidate + * + * @ring: amdgpu_ring pointer + * + * Emits an hdp invalidate. + */ +static void uvd_v6_0_ring_emit_hdp_invalidate(struct amdgpu_ring *ring) +{ + amdgpu_ring_write(ring, PACKET0(mmHDP_DEBUG0, 0)); + amdgpu_ring_write(ring, 1); +} + /** * uvd_v6_0_ring_test_ring - register write test * @@ -634,6 +673,9 @@ static void uvd_v6_0_ring_emit_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib, unsigned vm_id, bool ctx_switch) { + amdgpu_ring_write(ring, PACKET0(mmUVD_LMI_RBC_IB_VMID, 0)); + amdgpu_ring_write(ring, vm_id); + amdgpu_ring_write(ring, PACKET0(mmUVD_LMI_RBC_IB_64BIT_BAR_LOW, 0)); amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr)); amdgpu_ring_write(ring, PACKET0(mmUVD_LMI_RBC_IB_64BIT_BAR_HIGH, 0)); @@ -642,39 +684,55 @@ static void uvd_v6_0_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, ib->length_dw); } -/** - * uvd_v6_0_ring_test_ib - test ib execution - * - * @ring: amdgpu_ring pointer - * - * Test if we can successfully execute an IB - */ -static int uvd_v6_0_ring_test_ib(struct amdgpu_ring *ring) +static void uvd_v6_0_ring_emit_vm_flush(struct amdgpu_ring *ring, + unsigned vm_id, uint64_t pd_addr) { - struct fence *fence = NULL; - int r; + uint32_t reg; - r = amdgpu_uvd_get_create_msg(ring, 1, NULL); - if (r) { - DRM_ERROR("amdgpu: failed to get create msg (%d).\n", r); - goto error; - } + if (vm_id < 8) + reg = mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + vm_id; + else + reg = mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + vm_id - 8; - r = amdgpu_uvd_get_destroy_msg(ring, 1, true, &fence); - if (r) { - DRM_ERROR("amdgpu: failed to get destroy ib (%d).\n", r); - goto error; - } + amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0, 0)); + amdgpu_ring_write(ring, reg << 2); + amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1, 0)); + amdgpu_ring_write(ring, pd_addr >> 12); + amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD, 0)); + amdgpu_ring_write(ring, 0x8); - r = fence_wait(fence, false); - if (r) { - DRM_ERROR("amdgpu: fence wait failed (%d).\n", r); - goto error; - } - DRM_INFO("ib test on ring %d succeeded\n", ring->idx); -error: - fence_put(fence); - return r; + amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0, 0)); + amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST << 2); + amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1, 0)); + amdgpu_ring_write(ring, 1 << vm_id); + amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD, 0)); + amdgpu_ring_write(ring, 0x8); + + amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0, 0)); + amdgpu_ring_write(ring, mmVM_INVALIDATE_REQUEST << 2); + amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1, 0)); + amdgpu_ring_write(ring, 0); + amdgpu_ring_write(ring, PACKET0(mmUVD_GP_SCRATCH8, 0)); + amdgpu_ring_write(ring, 1 << vm_id); /* mask */ + amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD, 0)); + amdgpu_ring_write(ring, 0xC); +} + +static void uvd_v6_0_ring_emit_pipeline_sync(struct amdgpu_ring *ring) +{ + uint32_t seq = ring->fence_drv.sync_seq; + uint64_t addr = ring->fence_drv.gpu_addr; + + amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA0, 0)); + amdgpu_ring_write(ring, lower_32_bits(addr)); + amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_DATA1, 0)); + amdgpu_ring_write(ring, upper_32_bits(addr)); + amdgpu_ring_write(ring, PACKET0(mmUVD_GP_SCRATCH8, 0)); + amdgpu_ring_write(ring, 0xffffffff); /* mask */ + amdgpu_ring_write(ring, PACKET0(mmUVD_GP_SCRATCH9, 0)); + amdgpu_ring_write(ring, seq); + amdgpu_ring_write(ring, PACKET0(mmUVD_GPCOM_VCPU_CMD, 0)); + amdgpu_ring_write(ring, 0xE); } static bool uvd_v6_0_is_idle(void *handle) @@ -847,7 +905,8 @@ static int uvd_v6_0_set_clockgating_state(void *handle, bool enable = (state == AMD_CG_STATE_GATE) ? true : false; static int curstate = -1; - if (adev->asic_type == CHIP_FIJI) + if (adev->asic_type == CHIP_FIJI || + adev->asic_type == CHIP_POLARIS10) uvd_v6_set_bypass_mode(adev, enable); if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG)) @@ -912,22 +971,51 @@ const struct amd_ip_funcs uvd_v6_0_ip_funcs = { .set_powergating_state = uvd_v6_0_set_powergating_state, }; -static const struct amdgpu_ring_funcs uvd_v6_0_ring_funcs = { +static const struct amdgpu_ring_funcs uvd_v6_0_ring_phys_funcs = { .get_rptr = uvd_v6_0_ring_get_rptr, .get_wptr = uvd_v6_0_ring_get_wptr, .set_wptr = uvd_v6_0_ring_set_wptr, .parse_cs = amdgpu_uvd_ring_parse_cs, .emit_ib = uvd_v6_0_ring_emit_ib, .emit_fence = uvd_v6_0_ring_emit_fence, + .emit_hdp_flush = uvd_v6_0_ring_emit_hdp_flush, + .emit_hdp_invalidate = uvd_v6_0_ring_emit_hdp_invalidate, .test_ring = uvd_v6_0_ring_test_ring, - .test_ib = uvd_v6_0_ring_test_ib, + .test_ib = amdgpu_uvd_ring_test_ib, .insert_nop = amdgpu_ring_insert_nop, .pad_ib = amdgpu_ring_generic_pad_ib, + .begin_use = amdgpu_uvd_ring_begin_use, + .end_use = amdgpu_uvd_ring_end_use, +}; + +static const struct amdgpu_ring_funcs uvd_v6_0_ring_vm_funcs = { + .get_rptr = uvd_v6_0_ring_get_rptr, + .get_wptr = uvd_v6_0_ring_get_wptr, + .set_wptr = uvd_v6_0_ring_set_wptr, + .parse_cs = NULL, + .emit_ib = uvd_v6_0_ring_emit_ib, + .emit_fence = uvd_v6_0_ring_emit_fence, + .emit_vm_flush = uvd_v6_0_ring_emit_vm_flush, + .emit_pipeline_sync = uvd_v6_0_ring_emit_pipeline_sync, + .emit_hdp_flush = uvd_v6_0_ring_emit_hdp_flush, + .emit_hdp_invalidate = uvd_v6_0_ring_emit_hdp_invalidate, + .test_ring = uvd_v6_0_ring_test_ring, + .test_ib = amdgpu_uvd_ring_test_ib, + .insert_nop = amdgpu_ring_insert_nop, + .pad_ib = amdgpu_ring_generic_pad_ib, + .begin_use = amdgpu_uvd_ring_begin_use, + .end_use = amdgpu_uvd_ring_end_use, }; static void uvd_v6_0_set_ring_funcs(struct amdgpu_device *adev) { - adev->uvd.ring.funcs = &uvd_v6_0_ring_funcs; + if (adev->asic_type >= CHIP_POLARIS10) { + adev->uvd.ring.funcs = &uvd_v6_0_ring_vm_funcs; + DRM_INFO("UVD is enabled in VM mode\n"); + } else { + adev->uvd.ring.funcs = &uvd_v6_0_ring_phys_funcs; + DRM_INFO("UVD is enabled in physical mode\n"); + } } static const struct amdgpu_irq_src_funcs uvd_v6_0_irq_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c index 45d92aceb485..80a37a602181 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c @@ -594,6 +594,8 @@ static const struct amdgpu_ring_funcs vce_v2_0_ring_funcs = { .test_ib = amdgpu_vce_ring_test_ib, .insert_nop = amdgpu_ring_insert_nop, .pad_ib = amdgpu_ring_generic_pad_ib, + .begin_use = amdgpu_vce_ring_begin_use, + .end_use = amdgpu_vce_ring_end_use, }; static void vce_v2_0_set_ring_funcs(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c index 30e8099e94c5..c271abffd8dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c @@ -43,6 +43,7 @@ #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR0 0x8616 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR1 0x8617 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR2 0x8618 +#define VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK 0x02 #define VCE_V3_0_FW_SIZE (384 * 1024) #define VCE_V3_0_STACK_SIZE (64 * 1024) @@ -51,6 +52,7 @@ static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx); static void vce_v3_0_set_ring_funcs(struct amdgpu_device *adev); static void vce_v3_0_set_irq_funcs(struct amdgpu_device *adev); +static int vce_v3_0_wait_for_idle(void *handle); /** * vce_v3_0_ring_get_rptr - get read pointer @@ -205,6 +207,32 @@ static void vce_v3_0_set_vce_sw_clock_gating(struct amdgpu_device *adev, vce_v3_0_override_vce_clock_gating(adev, false); } +static int vce_v3_0_firmware_loaded(struct amdgpu_device *adev) +{ + int i, j; + + for (i = 0; i < 10; ++i) { + for (j = 0; j < 100; ++j) { + uint32_t status = RREG32(mmVCE_STATUS); + + if (status & VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK) + return 0; + mdelay(10); + } + + DRM_ERROR("VCE not responding, trying to reset the ECPU!!!\n"); + WREG32_P(mmVCE_SOFT_RESET, + VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK, + ~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK); + mdelay(10); + WREG32_P(mmVCE_SOFT_RESET, 0, + ~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK); + mdelay(10); + } + + return -ETIMEDOUT; +} + /** * vce_v3_0_start - start VCE block * @@ -215,11 +243,24 @@ static void vce_v3_0_set_vce_sw_clock_gating(struct amdgpu_device *adev, static int vce_v3_0_start(struct amdgpu_device *adev) { struct amdgpu_ring *ring; - int idx, i, j, r; + int idx, r; + + ring = &adev->vce.ring[0]; + WREG32(mmVCE_RB_RPTR, ring->wptr); + WREG32(mmVCE_RB_WPTR, ring->wptr); + WREG32(mmVCE_RB_BASE_LO, ring->gpu_addr); + WREG32(mmVCE_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); + WREG32(mmVCE_RB_SIZE, ring->ring_size / 4); + + ring = &adev->vce.ring[1]; + WREG32(mmVCE_RB_RPTR2, ring->wptr); + WREG32(mmVCE_RB_WPTR2, ring->wptr); + WREG32(mmVCE_RB_BASE_LO2, ring->gpu_addr); + WREG32(mmVCE_RB_BASE_HI2, upper_32_bits(ring->gpu_addr)); + WREG32(mmVCE_RB_SIZE2, ring->ring_size / 4); mutex_lock(&adev->grbm_idx_mutex); for (idx = 0; idx < 2; ++idx) { - if (adev->vce.harvest_config & (1 << idx)) continue; @@ -233,48 +274,24 @@ static int vce_v3_0_start(struct amdgpu_device *adev) vce_v3_0_mc_resume(adev, idx); - /* set BUSY flag */ - WREG32_P(mmVCE_STATUS, 1, ~1); + WREG32_P(mmVCE_STATUS, VCE_STATUS__JOB_BUSY_MASK, + ~VCE_STATUS__JOB_BUSY_MASK); + if (adev->asic_type >= CHIP_STONEY) WREG32_P(mmVCE_VCPU_CNTL, 1, ~0x200001); else WREG32_P(mmVCE_VCPU_CNTL, VCE_VCPU_CNTL__CLK_EN_MASK, ~VCE_VCPU_CNTL__CLK_EN_MASK); - WREG32_P(mmVCE_SOFT_RESET, - VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK, - ~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK); - - mdelay(100); - WREG32_P(mmVCE_SOFT_RESET, 0, ~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK); - for (i = 0; i < 10; ++i) { - uint32_t status; - for (j = 0; j < 100; ++j) { - status = RREG32(mmVCE_STATUS); - if (status & 2) - break; - mdelay(10); - } - r = 0; - if (status & 2) - break; + mdelay(100); - DRM_ERROR("VCE not responding, trying to reset the ECPU!!!\n"); - WREG32_P(mmVCE_SOFT_RESET, - VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK, - ~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK); - mdelay(10); - WREG32_P(mmVCE_SOFT_RESET, 0, - ~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK); - mdelay(10); - r = -1; - } + r = vce_v3_0_firmware_loaded(adev); /* clear BUSY flag */ - WREG32_P(mmVCE_STATUS, 0, ~1); + WREG32_P(mmVCE_STATUS, 0, ~VCE_STATUS__JOB_BUSY_MASK); /* Set Clock-Gating off */ if (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG) @@ -290,19 +307,46 @@ static int vce_v3_0_start(struct amdgpu_device *adev) WREG32_P(mmGRBM_GFX_INDEX, 0, ~GRBM_GFX_INDEX__VCE_INSTANCE_MASK); mutex_unlock(&adev->grbm_idx_mutex); - ring = &adev->vce.ring[0]; - WREG32(mmVCE_RB_RPTR, ring->wptr); - WREG32(mmVCE_RB_WPTR, ring->wptr); - WREG32(mmVCE_RB_BASE_LO, ring->gpu_addr); - WREG32(mmVCE_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); - WREG32(mmVCE_RB_SIZE, ring->ring_size / 4); + return 0; +} - ring = &adev->vce.ring[1]; - WREG32(mmVCE_RB_RPTR2, ring->wptr); - WREG32(mmVCE_RB_WPTR2, ring->wptr); - WREG32(mmVCE_RB_BASE_LO2, ring->gpu_addr); - WREG32(mmVCE_RB_BASE_HI2, upper_32_bits(ring->gpu_addr)); - WREG32(mmVCE_RB_SIZE2, ring->ring_size / 4); +static int vce_v3_0_stop(struct amdgpu_device *adev) +{ + int idx; + + mutex_lock(&adev->grbm_idx_mutex); + for (idx = 0; idx < 2; ++idx) { + if (adev->vce.harvest_config & (1 << idx)) + continue; + + if (idx == 0) + WREG32_P(mmGRBM_GFX_INDEX, 0, + ~GRBM_GFX_INDEX__VCE_INSTANCE_MASK); + else + WREG32_P(mmGRBM_GFX_INDEX, + GRBM_GFX_INDEX__VCE_INSTANCE_MASK, + ~GRBM_GFX_INDEX__VCE_INSTANCE_MASK); + + if (adev->asic_type >= CHIP_STONEY) + WREG32_P(mmVCE_VCPU_CNTL, 0, ~0x200001); + else + WREG32_P(mmVCE_VCPU_CNTL, 0, + ~VCE_VCPU_CNTL__CLK_EN_MASK); + /* hold on ECPU */ + WREG32_P(mmVCE_SOFT_RESET, + VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK, + ~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK); + + /* clear BUSY flag */ + WREG32_P(mmVCE_STATUS, 0, ~VCE_STATUS__JOB_BUSY_MASK); + + /* Set Clock-Gating off */ + if (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG) + vce_v3_0_set_vce_sw_clock_gating(adev, false); + } + + WREG32_P(mmGRBM_GFX_INDEX, 0, ~GRBM_GFX_INDEX__VCE_INSTANCE_MASK); + mutex_unlock(&adev->grbm_idx_mutex); return 0; } @@ -441,7 +485,14 @@ static int vce_v3_0_hw_init(void *handle) static int vce_v3_0_hw_fini(void *handle) { - return 0; + int r; + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + r = vce_v3_0_wait_for_idle(handle); + if (r) + return r; + + return vce_v3_0_stop(adev); } static int vce_v3_0_suspend(void *handle) @@ -604,6 +655,18 @@ static int vce_v3_0_process_interrupt(struct amdgpu_device *adev, return 0; } +static void vce_v3_set_bypass_mode(struct amdgpu_device *adev, bool enable) +{ + u32 tmp = RREG32_SMC(ixGCK_DFS_BYPASS_CNTL); + + if (enable) + tmp |= GCK_DFS_BYPASS_CNTL__BYPASSECLK_MASK; + else + tmp &= ~GCK_DFS_BYPASS_CNTL__BYPASSECLK_MASK; + + WREG32_SMC(ixGCK_DFS_BYPASS_CNTL, tmp); +} + static int vce_v3_0_set_clockgating_state(void *handle, enum amd_clockgating_state state) { @@ -611,6 +674,9 @@ static int vce_v3_0_set_clockgating_state(void *handle, bool enable = (state == AMD_CG_STATE_GATE) ? true : false; int i; + if (adev->asic_type == CHIP_POLARIS10) + vce_v3_set_bypass_mode(adev, enable); + if (!(adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG)) return 0; @@ -701,6 +767,8 @@ static const struct amdgpu_ring_funcs vce_v3_0_ring_funcs = { .test_ib = amdgpu_vce_ring_test_ib, .insert_nop = amdgpu_ring_insert_nop, .pad_ib = amdgpu_ring_generic_pad_ib, + .begin_use = amdgpu_vce_ring_begin_use, + .end_use = amdgpu_vce_ring_end_use, }; static void vce_v3_0_set_ring_funcs(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 2c88d0b66cf3..03a31c53aec3 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -203,6 +203,29 @@ static void vi_didt_wreg(struct amdgpu_device *adev, u32 reg, u32 v) spin_unlock_irqrestore(&adev->didt_idx_lock, flags); } +static u32 vi_gc_cac_rreg(struct amdgpu_device *adev, u32 reg) +{ + unsigned long flags; + u32 r; + + spin_lock_irqsave(&adev->gc_cac_idx_lock, flags); + WREG32(mmGC_CAC_IND_INDEX, (reg)); + r = RREG32(mmGC_CAC_IND_DATA); + spin_unlock_irqrestore(&adev->gc_cac_idx_lock, flags); + return r; +} + +static void vi_gc_cac_wreg(struct amdgpu_device *adev, u32 reg, u32 v) +{ + unsigned long flags; + + spin_lock_irqsave(&adev->gc_cac_idx_lock, flags); + WREG32(mmGC_CAC_IND_INDEX, (reg)); + WREG32(mmGC_CAC_IND_DATA, (v)); + spin_unlock_irqrestore(&adev->gc_cac_idx_lock, flags); +} + + static const u32 tonga_mgcg_cgcg_init[] = { mmCGTT_DRM_CLK_CTRL0, 0xffffffff, 0x00600100, @@ -421,6 +444,20 @@ static bool vi_read_bios_from_rom(struct amdgpu_device *adev, return true; } +static u32 vi_get_virtual_caps(struct amdgpu_device *adev) +{ + u32 caps = 0; + u32 reg = RREG32(mmBIF_IOV_FUNC_IDENTIFIER); + + if (REG_GET_FIELD(reg, BIF_IOV_FUNC_IDENTIFIER, IOV_ENABLE)) + caps |= AMDGPU_VIRT_CAPS_SRIOV_EN; + + if (REG_GET_FIELD(reg, BIF_IOV_FUNC_IDENTIFIER, FUNC_IDENTIFIER)) + caps |= AMDGPU_VIRT_CAPS_IS_VF; + + return caps; +} + static const struct amdgpu_allowed_register_entry tonga_allowed_read_registers[] = { {mmGB_MACROTILE_MODE7, true}, }; @@ -519,12 +556,12 @@ static uint32_t vi_read_indexed_register(struct amdgpu_device *adev, u32 se_num, mutex_lock(&adev->grbm_idx_mutex); if (se_num != 0xffffffff || sh_num != 0xffffffff) - gfx_v8_0_select_se_sh(adev, se_num, sh_num); + amdgpu_gfx_select_se_sh(adev, se_num, sh_num, 0xffffffff); val = RREG32(reg_offset); if (se_num != 0xffffffff || sh_num != 0xffffffff) - gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff); + amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); mutex_unlock(&adev->grbm_idx_mutex); return val; } @@ -583,7 +620,7 @@ static int vi_read_register(struct amdgpu_device *adev, u32 se_num, return -EINVAL; } -static void vi_gpu_pci_config_reset(struct amdgpu_device *adev) +static int vi_gpu_pci_config_reset(struct amdgpu_device *adev) { u32 i; @@ -598,11 +635,14 @@ static void vi_gpu_pci_config_reset(struct amdgpu_device *adev) /* wait for asic to come out of reset */ for (i = 0; i < adev->usec_timeout; i++) { - if (RREG32(mmCONFIG_MEMSIZE) != 0xffffffff) - break; + if (RREG32(mmCONFIG_MEMSIZE) != 0xffffffff) { + /* enable BM */ + pci_set_master(adev->pdev); + return 0; + } udelay(1); } - + return -EINVAL; } static void vi_set_bios_scratch_engine_hung(struct amdgpu_device *adev, bool hung) @@ -628,13 +668,15 @@ static void vi_set_bios_scratch_engine_hung(struct amdgpu_device *adev, bool hun */ static int vi_asic_reset(struct amdgpu_device *adev) { + int r; + vi_set_bios_scratch_engine_hung(adev, true); - vi_gpu_pci_config_reset(adev); + r = vi_gpu_pci_config_reset(adev); vi_set_bios_scratch_engine_hung(adev, false); - return 0; + return r; } static int vi_set_uvd_clock(struct amdgpu_device *adev, u32 clock, @@ -1118,9 +1160,7 @@ static const struct amdgpu_asic_funcs vi_asic_funcs = .get_xclk = &vi_get_xclk, .set_uvd_clocks = &vi_set_uvd_clocks, .set_vce_clocks = &vi_set_vce_clocks, - /* these should be moved to their own ip modules */ - .get_gpu_clock_counter = &gfx_v8_0_get_gpu_clock_counter, - .wait_for_mc_idle = &gmc_v8_0_mc_wait_for_idle, + .get_virtual_caps = &vi_get_virtual_caps, }; static int vi_common_early_init(void *handle) @@ -1141,6 +1181,8 @@ static int vi_common_early_init(void *handle) adev->uvd_ctx_wreg = &vi_uvd_ctx_wreg; adev->didt_rreg = &vi_didt_rreg; adev->didt_wreg = &vi_didt_wreg; + adev->gc_cac_rreg = &vi_gc_cac_rreg; + adev->gc_cac_wreg = &vi_gc_cac_wreg; adev->asic_funcs = &vi_asic_funcs; @@ -1214,12 +1256,18 @@ static int vi_common_early_init(void *handle) adev->cg_flags = AMD_CG_SUPPORT_UVD_MGCG | AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS | + AMD_CG_SUPPORT_GFX_RLC_LS | + AMD_CG_SUPPORT_GFX_CP_LS | + AMD_CG_SUPPORT_GFX_CGTS | + AMD_CG_SUPPORT_GFX_MGLS | + AMD_CG_SUPPORT_GFX_CGTS_LS | + AMD_CG_SUPPORT_GFX_CGCG | + AMD_CG_SUPPORT_GFX_CGLS | AMD_CG_SUPPORT_BIF_LS | AMD_CG_SUPPORT_HDP_MGCG | AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_SDMA_MGCG | AMD_CG_SUPPORT_SDMA_LS; - adev->pg_flags = 0; adev->external_rev_id = adev->rev_id + 0x1; break; default: diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index ac005796b71c..4f3849ac8c07 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -63,13 +63,12 @@ static struct kfd_process *create_process(const struct task_struct *thread); void kfd_process_create_wq(void) { if (!kfd_process_wq) - kfd_process_wq = create_workqueue("kfd_process_wq"); + kfd_process_wq = alloc_workqueue("kfd_process_wq", 0, 0); } void kfd_process_destroy_wq(void) { if (kfd_process_wq) { - flush_workqueue(kfd_process_wq); destroy_workqueue(kfd_process_wq); kfd_process_wq = NULL; } @@ -242,13 +241,19 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn, pqm_uninit(&p->pqm); /* Iterate over all process device data structure and check - * if we should reset all wavefronts */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) + * if we should delete debug managers and reset all wavefronts + */ + list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + if ((pdd->dev->dbgmgr) && + (pdd->dev->dbgmgr->pasid == p->pasid)) + kfd_dbgmgr_destroy(pdd->dev->dbgmgr); + if (pdd->reset_wavefronts) { pr_warn("amdkfd: Resetting all wave fronts\n"); dbgdev_wave_reset_wavefronts(pdd->dev, p); pdd->reset_wavefronts = false; } + } mutex_unlock(&p->mutex); @@ -324,6 +329,7 @@ static struct kfd_process *create_process(const struct task_struct *thread) synchronize_rcu(); mmu_notifier_unregister_no_release(&process->mmu_notifier, process->mm); err_mmu_notifier: + mutex_destroy(&process->mutex); kfd_pasid_free(process->pasid); err_alloc_pasid: kfree(process->queues); @@ -404,42 +410,52 @@ void kfd_unbind_process_from_device(struct kfd_dev *dev, unsigned int pasid) idx = srcu_read_lock(&kfd_processes_srcu); + /* + * Look for the process that matches the pasid. If there is no such + * process, we either released it in amdkfd's own notifier, or there + * is a bug. Unfortunately, there is no way to tell... + */ hash_for_each_rcu(kfd_processes_table, i, p, kfd_processes) - if (p->pasid == pasid) - break; + if (p->pasid == pasid) { + + srcu_read_unlock(&kfd_processes_srcu, idx); + + pr_debug("Unbinding process %d from IOMMU\n", pasid); + + mutex_lock(&p->mutex); + + if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid)) + kfd_dbgmgr_destroy(dev->dbgmgr); + + pqm_uninit(&p->pqm); + + pdd = kfd_get_process_device_data(dev, p); + + if (!pdd) { + mutex_unlock(&p->mutex); + return; + } + + if (pdd->reset_wavefronts) { + dbgdev_wave_reset_wavefronts(pdd->dev, p); + pdd->reset_wavefronts = false; + } + + /* + * Just mark pdd as unbound, because we still need it + * to call amd_iommu_unbind_pasid() in when the + * process exits. + * We don't call amd_iommu_unbind_pasid() here + * because the IOMMU called us. + */ + pdd->bound = false; + + mutex_unlock(&p->mutex); + + return; + } srcu_read_unlock(&kfd_processes_srcu, idx); - - BUG_ON(p->pasid != pasid); - - mutex_lock(&p->mutex); - - if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid)) - kfd_dbgmgr_destroy(dev->dbgmgr); - - pqm_uninit(&p->pqm); - - pdd = kfd_get_process_device_data(dev, p); - - if (!pdd) { - mutex_unlock(&p->mutex); - return; - } - - if (pdd->reset_wavefronts) { - dbgdev_wave_reset_wavefronts(pdd->dev, p); - pdd->reset_wavefronts = false; - } - - /* - * Just mark pdd as unbound, because we still need it to call - * amd_iommu_unbind_pasid() in when the process exits. - * We don't call amd_iommu_unbind_pasid() here - * because the IOMMU called us. - */ - pdd->bound = false; - - mutex_unlock(&p->mutex); } struct kfd_process_device *kfd_get_first_process_device_data(struct kfd_process *p) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 74909e72a009..884c96f50c3d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -666,7 +666,7 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr, dev->node_props.simd_count); if (dev->mem_bank_count < dev->node_props.mem_banks_count) { - pr_warn("kfd: mem_banks_count truncated from %d to %d\n", + pr_info_once("kfd: mem_banks_count truncated from %d to %d\n", dev->node_props.mem_banks_count, dev->mem_bank_count); sysfs_show_32bit_prop(buffer, "mem_banks_count", diff --git a/drivers/gpu/drm/amd/include/amd_pcie.h b/drivers/gpu/drm/amd/include/amd_pcie.h index 7c2a916c1e63..5eb895fd98bf 100644 --- a/drivers/gpu/drm/amd/include/amd_pcie.h +++ b/drivers/gpu/drm/amd/include/amd_pcie.h @@ -37,6 +37,13 @@ #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_MASK 0x0000FFFF #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_SHIFT 0 +/* gen: chipset 1/2, asic 1/2/3 */ +#define AMDGPU_DEFAULT_PCIE_GEN_MASK (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 \ + | CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2 \ + | CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 \ + | CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 \ + | CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3) + /* Following flags shows PCIe lane width switch supported in driver which are decided by chipset and ASIC */ #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X1 0x00010000 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 0x00020000 @@ -47,4 +54,11 @@ #define CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 0x00400000 #define CAIL_PCIE_LINK_WIDTH_SUPPORT_SHIFT 16 +/* 1/2/4/8/16 lanes */ +#define AMDGPU_DEFAULT_PCIE_MLW_MASK (CAIL_PCIE_LINK_WIDTH_SUPPORT_X1 \ + | CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 \ + | CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 \ + | CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 \ + | CAIL_PCIE_LINK_WIDTH_SUPPORT_X16) + #endif diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 6080951d539d..a74a0d2ff1ca 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -25,15 +25,6 @@ #define AMD_MAX_USEC_TIMEOUT 100000 /* 100 ms */ -/* -* Supported GPU families (aligned with amdgpu_drm.h) -*/ -#define AMD_FAMILY_UNKNOWN 0 -#define AMD_FAMILY_CI 120 /* Bonaire, Hawaii */ -#define AMD_FAMILY_KV 125 /* Kaveri, Kabini, Mullins */ -#define AMD_FAMILY_VI 130 /* Iceland, Tonga */ -#define AMD_FAMILY_CZ 135 /* Carrizo */ - /* * Supported ASIC types */ @@ -120,6 +111,8 @@ enum amd_powergating_state { #define AMD_PG_SUPPORT_SDMA (1 << 8) #define AMD_PG_SUPPORT_ACP (1 << 9) #define AMD_PG_SUPPORT_SAMU (1 << 10) +#define AMD_PG_SUPPORT_GFX_QUICK_MG (1 << 11) +#define AMD_PG_SUPPORT_GFX_PIPELINE (1 << 12) enum amd_pm_state_type { /* not used for dpm */ @@ -157,6 +150,7 @@ struct amd_ip_funcs { int (*hw_init)(void *handle); /* tears down the hw state */ int (*hw_fini)(void *handle); + void (*late_fini)(void *handle); /* handles IP specific hw/sw changes for suspend */ int (*suspend)(void *handle); /* handles IP specific hw/sw changes for resume */ diff --git a/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_d.h b/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_d.h index 293329719bba..809759f7bb81 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_d.h +++ b/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_d.h @@ -27,6 +27,7 @@ #define mmMM_INDEX 0x0 #define mmMM_INDEX_HI 0x6 #define mmMM_DATA 0x1 +#define mmCC_BIF_BX_STRAP2 0x152A #define mmBIF_MM_INDACCESS_CNTL 0x1500 #define mmBIF_DOORBELL_APER_EN 0x1501 #define mmBUS_CNTL 0x1508 diff --git a/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_d.h b/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_d.h index ebaf67bb1589..90ff7c8a6011 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_d.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_d.h @@ -2823,4 +2823,7 @@ #define mmDC_EDC_CSINVOC_CNT 0x3192 #define mmDC_EDC_RESTORE_CNT 0x3193 +#define mmGC_CAC_IND_INDEX 0x129a +#define mmGC_CAC_IND_DATA 0x129b + #endif /* GFX_8_0_D_H */ diff --git a/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_sh_mask.h index 7d722458d9f5..4070ca3a68eb 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gca/gfx_8_0_sh_mask.h @@ -8730,8 +8730,6 @@ #define RLC_GPM_STAT__DYN_CU_POWERING_DOWN__SHIFT 0x10 #define RLC_GPM_STAT__ABORTED_PD_SEQUENCE_MASK 0x20000 #define RLC_GPM_STAT__ABORTED_PD_SEQUENCE__SHIFT 0x11 -#define RLC_GPM_STAT__RESERVED_MASK 0xfc0000 -#define RLC_GPM_STAT__RESERVED__SHIFT 0x12 #define RLC_GPM_STAT__PG_ERROR_STATUS_MASK 0xff000000 #define RLC_GPM_STAT__PG_ERROR_STATUS__SHIFT 0x18 #define RLC_GPU_CLOCK_32_RES_SEL__RES_SEL_MASK 0x3f @@ -8764,8 +8762,10 @@ #define RLC_PG_CNTL__SMU_CLK_SLOWDOWN_ON_PD_ENABLE__SHIFT 0x12 #define RLC_PG_CNTL__SMU_HANDSHAKE_ENABLE_MASK 0x80000 #define RLC_PG_CNTL__SMU_HANDSHAKE_ENABLE__SHIFT 0x13 -#define RLC_PG_CNTL__RESERVED1_MASK 0xf00000 -#define RLC_PG_CNTL__RESERVED1__SHIFT 0x14 +#define RLC_PG_CNTL__QUICK_PG_ENABLE_MASK 0x100000 +#define RLC_PG_CNTL__QUICK_PG_ENABLE__SHIFT 0x14 +#define RLC_PG_CNTL__RESERVED1_MASK 0xe00000 +#define RLC_PG_CNTL__RESERVED1__SHIFT 0x15 #define RLC_GPM_THREAD_PRIORITY__THREAD0_PRIORITY_MASK 0xff #define RLC_GPM_THREAD_PRIORITY__THREAD0_PRIORITY__SHIFT 0x0 #define RLC_GPM_THREAD_PRIORITY__THREAD1_PRIORITY_MASK 0xff00 @@ -9102,8 +9102,6 @@ #define RLC_GPM_LOG_CONT__CONT__SHIFT 0x0 #define RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK 0xff #define RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG__SHIFT 0x0 -#define RLC_PG_DELAY_3__RESERVED_MASK 0xffffff00 -#define RLC_PG_DELAY_3__RESERVED__SHIFT 0x8 #define RLC_GPM_INT_DISABLE_TH0__DISABLE_MASK 0xffffffff #define RLC_GPM_INT_DISABLE_TH0__DISABLE__SHIFT 0x0 #define RLC_GPM_INT_DISABLE_TH1__DISABLE_MASK 0xffffffff @@ -9124,14 +9122,8 @@ #define RLC_SRM_DEBUG_SELECT__RESERVED__SHIFT 0x8 #define RLC_SRM_DEBUG__DATA_MASK 0xffffffff #define RLC_SRM_DEBUG__DATA__SHIFT 0x0 -#define RLC_SRM_ARAM_ADDR__ADDR_MASK 0x3ff -#define RLC_SRM_ARAM_ADDR__ADDR__SHIFT 0x0 -#define RLC_SRM_ARAM_ADDR__RESERVED_MASK 0xfffffc00 -#define RLC_SRM_ARAM_ADDR__RESERVED__SHIFT 0xa #define RLC_SRM_ARAM_DATA__DATA_MASK 0xffffffff #define RLC_SRM_ARAM_DATA__DATA__SHIFT 0x0 -#define RLC_SRM_DRAM_ADDR__ADDR_MASK 0x3ff -#define RLC_SRM_DRAM_ADDR__ADDR__SHIFT 0x0 #define RLC_SRM_DRAM_ADDR__RESERVED_MASK 0xfffffc00 #define RLC_SRM_DRAM_ADDR__RESERVED__SHIFT 0xa #define RLC_SRM_DRAM_DATA__DATA_MASK 0xffffffff @@ -17946,8 +17938,6 @@ #define VGT_TESS_DISTRIBUTION__ACCUM_TRI__SHIFT 0x8 #define VGT_TESS_DISTRIBUTION__ACCUM_QUAD_MASK 0xff0000 #define VGT_TESS_DISTRIBUTION__ACCUM_QUAD__SHIFT 0x10 -#define VGT_TESS_DISTRIBUTION__DONUT_SPLIT_MASK 0xff000000 -#define VGT_TESS_DISTRIBUTION__DONUT_SPLIT__SHIFT 0x18 #define VGT_TF_RING_SIZE__SIZE_MASK 0xffff #define VGT_TF_RING_SIZE__SIZE__SHIFT 0x0 #define VGT_SYS_CONFIG__DUAL_CORE_EN_MASK 0x1 @@ -20502,8 +20492,6 @@ #define DIDT_SQ_CTRL0__DIDT_CTRL_RST__SHIFT 0x4 #define DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK 0x20 #define DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT 0x5 -#define DIDT_SQ_CTRL0__UNUSED_0_MASK 0xffffffc0 -#define DIDT_SQ_CTRL0__UNUSED_0__SHIFT 0x6 #define DIDT_SQ_CTRL1__MIN_POWER_MASK 0xffff #define DIDT_SQ_CTRL1__MIN_POWER__SHIFT 0x0 #define DIDT_SQ_CTRL1__MAX_POWER_MASK 0xffff0000 @@ -20558,8 +20546,6 @@ #define DIDT_DB_CTRL0__DIDT_CTRL_RST__SHIFT 0x4 #define DIDT_DB_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK 0x20 #define DIDT_DB_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT 0x5 -#define DIDT_DB_CTRL0__UNUSED_0_MASK 0xffffffc0 -#define DIDT_DB_CTRL0__UNUSED_0__SHIFT 0x6 #define DIDT_DB_CTRL1__MIN_POWER_MASK 0xffff #define DIDT_DB_CTRL1__MIN_POWER__SHIFT 0x0 #define DIDT_DB_CTRL1__MAX_POWER_MASK 0xffff0000 @@ -20614,8 +20600,6 @@ #define DIDT_TD_CTRL0__DIDT_CTRL_RST__SHIFT 0x4 #define DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK 0x20 #define DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT 0x5 -#define DIDT_TD_CTRL0__UNUSED_0_MASK 0xffffffc0 -#define DIDT_TD_CTRL0__UNUSED_0__SHIFT 0x6 #define DIDT_TD_CTRL1__MIN_POWER_MASK 0xffff #define DIDT_TD_CTRL1__MIN_POWER__SHIFT 0x0 #define DIDT_TD_CTRL1__MAX_POWER_MASK 0xffff0000 @@ -20670,8 +20654,6 @@ #define DIDT_TCP_CTRL0__DIDT_CTRL_RST__SHIFT 0x4 #define DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK 0x20 #define DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT 0x5 -#define DIDT_TCP_CTRL0__UNUSED_0_MASK 0xffffffc0 -#define DIDT_TCP_CTRL0__UNUSED_0__SHIFT 0x6 #define DIDT_TCP_CTRL1__MIN_POWER_MASK 0xffff #define DIDT_TCP_CTRL1__MIN_POWER__SHIFT 0x0 #define DIDT_TCP_CTRL1__MAX_POWER_MASK 0xffff0000 @@ -20726,8 +20708,6 @@ #define DIDT_DBR_CTRL0__DIDT_CTRL_RST__SHIFT 0x4 #define DIDT_DBR_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK 0x20 #define DIDT_DBR_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT 0x5 -#define DIDT_DBR_CTRL0__UNUSED_0_MASK 0xffffffc0 -#define DIDT_DBR_CTRL0__UNUSED_0__SHIFT 0x6 #define DIDT_DBR_CTRL1__MIN_POWER_MASK 0xffff #define DIDT_DBR_CTRL1__MIN_POWER__SHIFT 0x0 #define DIDT_DBR_CTRL1__MAX_POWER_MASK 0xffff0000 @@ -20773,4 +20753,84 @@ #define DIDT_DBR_WEIGHT8_11__WEIGHT11_MASK 0xff000000 #define DIDT_DBR_WEIGHT8_11__WEIGHT11__SHIFT 0x18 +#define DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK 0x00000001 +#define DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT 0x00000000 + +#define DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK 0x0000007e +#define DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK 0x00001f80L +#define DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT 0x00000001 +#define DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT 0x00000007 + +#define DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK 0x1fffe000L +#define DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT 0x0000000d + +#define DIDT_SQ_STALL_CTRL__UNUSED_0_MASK 0xe0000000L +#define DIDT_SQ_STALL_CTRL__UNUSED_0__SHIFT 0x0000001d + +#define DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK 0x00000001L +#define DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT 0x00000000 + +#define DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK 0x00007ffeL +#define DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT 0x00000001 +#define DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK 0x1fff8000L +#define DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT 0x0000000f + +#define DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK 0x00000001L +#define DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT 0x00000000 + +#define DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK 0x0000007eL +#define DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK 0x00001f80L +#define DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT 0x00000001 +#define DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT 0x00000007 + +#define DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK 0x1fffe000L +#define DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT 0x0000000d + +#define DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK 0x00000fc0L +#define DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK 0x0003f000L +#define DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT 0x00000006 +#define DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT 0x0000000c + +#define DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK 0x00000001L +#define DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK 0x00007ffeL +#define DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK 0x1fff8000L + +#define DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT 0x00000000 +#define DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT 0x00000001 +#define DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT 0x0000000f + +#define DIDT_TD_STALL_CTRL__UNUSED_0_MASK 0xe0000000L +#define DIDT_TD_STALL_CTRL__UNUSED_0__SHIFT 0x0000001d + +#define DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK 0x00000fc0L +#define DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK 0x0003f000L +#define DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT 0x00000006 +#define DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT 0x0000000c + +#define DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK 0x00000001L +#define DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT 0x00000000 + +#define DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK 0x0000007eL +#define DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK 0x00001f80L +#define DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT 0x00000001 +#define DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT 0x00000007 + +#define DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK 0x1fffe000L +#define DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT 0x0000000d + +#define DIDT_TCP_STALL_CTRL__UNUSED_0_MASK 0xe0000000L +#define DIDT_TCP_STALL_CTRL__UNUSED_0__SHIFT 0x0000001d + +#define DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK 0x00000001L +#define DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK 0x00007ffeL +#define DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK 0x1fff8000L +#define DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT 0x00000000 +#define DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT 0x00000001 +#define DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT 0x0000000f + +#define DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK 0x00000fc0L +#define DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK 0x0003f000L +#define DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT 0x00000006 +#define DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT 0x0000000c + #endif /* GFX_8_0_SH_MASK_H */ diff --git a/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_6_0_d.h b/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_6_0_d.h index 6f6fb34742d2..ec69869c55ff 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_6_0_d.h +++ b/drivers/gpu/drm/amd/include/asic_reg/uvd/uvd_6_0_d.h @@ -111,6 +111,8 @@ #define mmUVD_MIF_RECON1_ADDR_CONFIG 0x39c5 #define ixUVD_MIF_SCLR_ADDR_CONFIG 0x4 #define mmUVD_JPEG_ADDR_CONFIG 0x3a1f +#define mmUVD_GP_SCRATCH8 0x3c0a +#define mmUVD_GP_SCRATCH9 0x3c0b #define mmUVD_GP_SCRATCH4 0x3d38 #endif /* UVD_6_0_D_H */ diff --git a/drivers/gpu/drm/amd/include/atombios.h b/drivers/gpu/drm/amd/include/atombios.h index 32f3e345de08..3493da5c8f0e 100644 --- a/drivers/gpu/drm/amd/include/atombios.h +++ b/drivers/gpu/drm/amd/include/atombios.h @@ -5538,6 +5538,78 @@ typedef struct _ATOM_ASIC_PROFILING_INFO_V3_5 ULONG ulReserved[12]; }ATOM_ASIC_PROFILING_INFO_V3_5; +/* for Polars10/11 AVFS parameters */ +typedef struct _ATOM_ASIC_PROFILING_INFO_V3_6 +{ + ATOM_COMMON_TABLE_HEADER asHeader; + ULONG ulMaxVddc; + ULONG ulMinVddc; + USHORT usLkgEuseIndex; + UCHAR ucLkgEfuseBitLSB; + UCHAR ucLkgEfuseLength; + ULONG ulLkgEncodeLn_MaxDivMin; + ULONG ulLkgEncodeMax; + ULONG ulLkgEncodeMin; + EFUSE_LINEAR_FUNC_PARAM sRoFuse; + ULONG ulEvvDefaultVddc; + ULONG ulEvvNoCalcVddc; + ULONG ulSpeed_Model; + ULONG ulSM_A0; + ULONG ulSM_A1; + ULONG ulSM_A2; + ULONG ulSM_A3; + ULONG ulSM_A4; + ULONG ulSM_A5; + ULONG ulSM_A6; + ULONG ulSM_A7; + UCHAR ucSM_A0_sign; + UCHAR ucSM_A1_sign; + UCHAR ucSM_A2_sign; + UCHAR ucSM_A3_sign; + UCHAR ucSM_A4_sign; + UCHAR ucSM_A5_sign; + UCHAR ucSM_A6_sign; + UCHAR ucSM_A7_sign; + ULONG ulMargin_RO_a; + ULONG ulMargin_RO_b; + ULONG ulMargin_RO_c; + ULONG ulMargin_fixed; + ULONG ulMargin_Fmax_mean; + ULONG ulMargin_plat_mean; + ULONG ulMargin_Fmax_sigma; + ULONG ulMargin_plat_sigma; + ULONG ulMargin_DC_sigma; + ULONG ulLoadLineSlop; + ULONG ulaTDClimitPerDPM[8]; + ULONG ulaNoCalcVddcPerDPM[8]; + ULONG ulAVFS_meanNsigma_Acontant0; + ULONG ulAVFS_meanNsigma_Acontant1; + ULONG ulAVFS_meanNsigma_Acontant2; + USHORT usAVFS_meanNsigma_DC_tol_sigma; + USHORT usAVFS_meanNsigma_Platform_mean; + USHORT usAVFS_meanNsigma_Platform_sigma; + ULONG ulGB_VDROOP_TABLE_CKSOFF_a0; + ULONG ulGB_VDROOP_TABLE_CKSOFF_a1; + ULONG ulGB_VDROOP_TABLE_CKSOFF_a2; + ULONG ulGB_VDROOP_TABLE_CKSON_a0; + ULONG ulGB_VDROOP_TABLE_CKSON_a1; + ULONG ulGB_VDROOP_TABLE_CKSON_a2; + ULONG ulAVFSGB_FUSE_TABLE_CKSOFF_m1; + USHORT usAVFSGB_FUSE_TABLE_CKSOFF_m2; + ULONG ulAVFSGB_FUSE_TABLE_CKSOFF_b; + ULONG ulAVFSGB_FUSE_TABLE_CKSON_m1; + USHORT usAVFSGB_FUSE_TABLE_CKSON_m2; + ULONG ulAVFSGB_FUSE_TABLE_CKSON_b; + USHORT usMaxVoltage_0_25mv; + UCHAR ucEnableGB_VDROOP_TABLE_CKSOFF; + UCHAR ucEnableGB_VDROOP_TABLE_CKSON; + UCHAR ucEnableGB_FUSE_TABLE_CKSOFF; + UCHAR ucEnableGB_FUSE_TABLE_CKSON; + USHORT usPSM_Age_ComFactor; + UCHAR ucEnableApplyAVFS_CKS_OFF_Voltage; + UCHAR ucReserved; +}ATOM_ASIC_PROFILING_INFO_V3_6; + typedef struct _ATOM_SCLK_FCW_RANGE_ENTRY_V1{ ULONG ulMaxSclkFreq; diff --git a/drivers/gpu/drm/amd/include/cgs_common.h b/drivers/gpu/drm/amd/include/cgs_common.h index a461e155a160..b86aba9d019f 100644 --- a/drivers/gpu/drm/amd/include/cgs_common.h +++ b/drivers/gpu/drm/amd/include/cgs_common.h @@ -49,6 +49,7 @@ enum cgs_ind_reg { CGS_IND_REG__SMC, CGS_IND_REG__UVD_CTX, CGS_IND_REG__DIDT, + CGS_IND_REG_GC_CAC, CGS_IND_REG__AUDIO_ENDPT }; @@ -112,20 +113,23 @@ enum cgs_system_info_id { CGS_SYSTEM_INFO_ADAPTER_BDF_ID = 1, CGS_SYSTEM_INFO_PCIE_GEN_INFO, CGS_SYSTEM_INFO_PCIE_MLW, + CGS_SYSTEM_INFO_PCIE_DEV, + CGS_SYSTEM_INFO_PCIE_REV, CGS_SYSTEM_INFO_CG_FLAGS, CGS_SYSTEM_INFO_PG_FLAGS, CGS_SYSTEM_INFO_GFX_CU_INFO, + CGS_SYSTEM_INFO_GFX_SE_INFO, CGS_SYSTEM_INFO_ID_MAXIMUM, }; struct cgs_system_info { - uint64_t size; - uint64_t info_id; + uint64_t size; + enum cgs_system_info_id info_id; union { - void *ptr; - uint64_t value; + void *ptr; + uint64_t value; }; - uint64_t padding[13]; + uint64_t padding[13]; }; /* @@ -158,6 +162,10 @@ struct cgs_firmware_info { uint16_t feature_version; uint32_t image_size; uint64_t mc_addr; + + /* only for smc firmware */ + uint32_t ucode_start_address; + void *kptr; }; @@ -189,7 +197,6 @@ typedef unsigned long cgs_handle_t; struct cgs_acpi_method_argument { uint32_t type; - uint32_t method_length; uint32_t data_length; union{ uint32_t value; @@ -581,6 +588,9 @@ typedef int (*cgs_get_firmware_info)(struct cgs_device *cgs_device, enum cgs_ucode_id type, struct cgs_firmware_info *info); +typedef int (*cgs_rel_firmware)(struct cgs_device *cgs_device, + enum cgs_ucode_id type); + typedef int(*cgs_set_powergating_state)(struct cgs_device *cgs_device, enum amd_ip_block_type block_type, enum amd_powergating_state state); @@ -645,6 +655,7 @@ struct cgs_ops { cgs_set_camera_voltages_t set_camera_voltages; /* Firmware Info */ cgs_get_firmware_info get_firmware_info; + cgs_rel_firmware rel_firmware; /* cg pg interface*/ cgs_set_powergating_state set_powergating_state; cgs_set_clockgating_state set_clockgating_state; @@ -738,6 +749,8 @@ struct cgs_device CGS_CALL(set_camera_voltages,dev,mask,voltages) #define cgs_get_firmware_info(dev, type, info) \ CGS_CALL(get_firmware_info, dev, type, info) +#define cgs_rel_firmware(dev, type) \ + CGS_CALL(rel_firmware, dev, type) #define cgs_set_powergating_state(dev, block_type, state) \ CGS_CALL(set_powergating_state, dev, block_type, state) #define cgs_set_clockgating_state(dev, block_type, state) \ diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index 8e345bfddb69..abbb658bdc1e 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -73,11 +73,14 @@ static int pp_sw_init(void *handle) ret = hwmgr->hwmgr_func->backend_init(hwmgr); if (ret) - goto err; + goto err1; pr_info("amdgpu: powerplay initialized\n"); return 0; +err1: + if (hwmgr->pptable_func->pptable_fini) + hwmgr->pptable_func->pptable_fini(hwmgr); err: pr_err("amdgpu: powerplay initialization failed\n"); return ret; @@ -100,6 +103,9 @@ static int pp_sw_fini(void *handle) if (hwmgr->hwmgr_func->backend_fini != NULL) ret = hwmgr->hwmgr_func->backend_fini(hwmgr); + if (hwmgr->pptable_func->pptable_fini) + hwmgr->pptable_func->pptable_fini(hwmgr); + return ret; } @@ -170,7 +176,7 @@ static int pp_hw_fini(void *handle) static bool pp_is_idle(void *handle) { - return 0; + return false; } static int pp_wait_for_idle(void *handle) @@ -530,6 +536,10 @@ int pp_dpm_dispatch_tasks(void *handle, enum amd_pp_event event_id, void *input, case AMD_PP_EVENT_COMPLETE_INIT: ret = pem_handle_event(pp_handle->eventmgr, event_id, &data); break; + case AMD_PP_EVENT_READJUST_POWER_STATE: + pp_handle->hwmgr->current_ps = pp_handle->hwmgr->boot_ps; + ret = pem_handle_event(pp_handle->eventmgr, event_id, &data); + break; default: break; } @@ -734,12 +744,12 @@ static int pp_dpm_get_pp_table(void *handle, char **table) PP_CHECK_HW(hwmgr); - if (hwmgr->hwmgr_func->get_pp_table == NULL) { - printk(KERN_INFO "%s was not implemented.\n", __func__); - return 0; - } + if (!hwmgr->soft_pp_table) + return -EINVAL; - return hwmgr->hwmgr_func->get_pp_table(hwmgr, table); + *table = (char *)hwmgr->soft_pp_table; + + return hwmgr->soft_pp_table_size; } static int pp_dpm_set_pp_table(void *handle, const char *buf, size_t size) @@ -753,12 +763,23 @@ static int pp_dpm_set_pp_table(void *handle, const char *buf, size_t size) PP_CHECK_HW(hwmgr); - if (hwmgr->hwmgr_func->set_pp_table == NULL) { - printk(KERN_INFO "%s was not implemented.\n", __func__); - return 0; + if (!hwmgr->hardcode_pp_table) { + hwmgr->hardcode_pp_table = + kzalloc(hwmgr->soft_pp_table_size, GFP_KERNEL); + + if (!hwmgr->hardcode_pp_table) + return -ENOMEM; + + /* to avoid powerplay crash when hardcode pptable is empty */ + memcpy(hwmgr->hardcode_pp_table, hwmgr->soft_pp_table, + hwmgr->soft_pp_table_size); } - return hwmgr->hwmgr_func->set_pp_table(hwmgr, buf, size); + memcpy(hwmgr->hardcode_pp_table, buf, size); + + hwmgr->soft_pp_table = hwmgr->hardcode_pp_table; + + return amd_powerplay_reset(handle); } static int pp_dpm_force_clock_level(void *handle, @@ -800,6 +821,82 @@ static int pp_dpm_print_clock_levels(void *handle, return hwmgr->hwmgr_func->print_clock_levels(hwmgr, type, buf); } +static int pp_dpm_get_sclk_od(void *handle) +{ + struct pp_hwmgr *hwmgr; + + if (!handle) + return -EINVAL; + + hwmgr = ((struct pp_instance *)handle)->hwmgr; + + PP_CHECK_HW(hwmgr); + + if (hwmgr->hwmgr_func->get_sclk_od == NULL) { + printk(KERN_INFO "%s was not implemented.\n", __func__); + return 0; + } + + return hwmgr->hwmgr_func->get_sclk_od(hwmgr); +} + +static int pp_dpm_set_sclk_od(void *handle, uint32_t value) +{ + struct pp_hwmgr *hwmgr; + + if (!handle) + return -EINVAL; + + hwmgr = ((struct pp_instance *)handle)->hwmgr; + + PP_CHECK_HW(hwmgr); + + if (hwmgr->hwmgr_func->set_sclk_od == NULL) { + printk(KERN_INFO "%s was not implemented.\n", __func__); + return 0; + } + + return hwmgr->hwmgr_func->set_sclk_od(hwmgr, value); +} + +static int pp_dpm_get_mclk_od(void *handle) +{ + struct pp_hwmgr *hwmgr; + + if (!handle) + return -EINVAL; + + hwmgr = ((struct pp_instance *)handle)->hwmgr; + + PP_CHECK_HW(hwmgr); + + if (hwmgr->hwmgr_func->get_mclk_od == NULL) { + printk(KERN_INFO "%s was not implemented.\n", __func__); + return 0; + } + + return hwmgr->hwmgr_func->get_mclk_od(hwmgr); +} + +static int pp_dpm_set_mclk_od(void *handle, uint32_t value) +{ + struct pp_hwmgr *hwmgr; + + if (!handle) + return -EINVAL; + + hwmgr = ((struct pp_instance *)handle)->hwmgr; + + PP_CHECK_HW(hwmgr); + + if (hwmgr->hwmgr_func->set_mclk_od == NULL) { + printk(KERN_INFO "%s was not implemented.\n", __func__); + return 0; + } + + return hwmgr->hwmgr_func->set_mclk_od(hwmgr, value); +} + const struct amd_powerplay_funcs pp_dpm_funcs = { .get_temperature = pp_dpm_get_temperature, .load_firmware = pp_dpm_load_fw, @@ -822,6 +919,10 @@ const struct amd_powerplay_funcs pp_dpm_funcs = { .set_pp_table = pp_dpm_set_pp_table, .force_clock_level = pp_dpm_force_clock_level, .print_clock_levels = pp_dpm_print_clock_levels, + .get_sclk_od = pp_dpm_get_sclk_od, + .set_sclk_od = pp_dpm_set_sclk_od, + .get_mclk_od = pp_dpm_get_mclk_od, + .set_mclk_od = pp_dpm_set_mclk_od, }; static int amd_pp_instance_init(struct amd_pp_init *pp_init, @@ -903,6 +1004,44 @@ int amd_powerplay_fini(void *handle) return 0; } +int amd_powerplay_reset(void *handle) +{ + struct pp_instance *instance = (struct pp_instance *)handle; + struct pp_eventmgr *eventmgr; + struct pem_event_data event_data = { {0} }; + int ret; + + if (instance == NULL) + return -EINVAL; + + eventmgr = instance->eventmgr; + if (!eventmgr || !eventmgr->pp_eventmgr_fini) + return -EINVAL; + + eventmgr->pp_eventmgr_fini(eventmgr); + + ret = pp_sw_fini(handle); + if (ret) + return ret; + + kfree(instance->hwmgr->ps); + + ret = pp_sw_init(handle); + if (ret) + return ret; + + hw_init_power_state_table(instance->hwmgr); + + if (eventmgr == NULL || eventmgr->pp_eventmgr_init == NULL) + return -EINVAL; + + ret = eventmgr->pp_eventmgr_init(eventmgr); + if (ret) + return ret; + + return pem_handle_event(eventmgr, AMD_PP_EVENT_COMPLETE_INIT, &event_data); +} + /* export this function to DAL */ int amd_powerplay_display_configuration_change(void *handle, diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c index d6635cc4b0fc..635fc4b48184 100644 --- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c +++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventactionchains.c @@ -30,7 +30,6 @@ static const pem_event_action * const initialize_event[] = { system_config_tasks, setup_asic_tasks, enable_dynamic_state_management_tasks, - enable_clock_power_gatings_tasks, get_2d_performance_state_tasks, set_performance_state_tasks, initialize_thermal_controller_tasks, @@ -140,7 +139,6 @@ static const pem_event_action * const resume_event[] = { setup_asic_tasks, enable_stutter_mode_tasks, /*must do this in boot state and before SMC is started */ enable_dynamic_state_management_tasks, - enable_clock_power_gatings_tasks, enable_disable_bapm_tasks, initialize_thermal_controller_tasks, get_2d_performance_state_tasks, diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c index 46410e3c7349..fb88e4e5d625 100644 --- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c +++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c @@ -58,9 +58,6 @@ static void pem_fini(struct pp_eventmgr *eventmgr) pem_unregister_interrupts(eventmgr); pem_handle_event(eventmgr, AMD_PP_EVENT_UNINITIALIZE, &event_data); - - if (eventmgr != NULL) - kfree(eventmgr); } int eventmgr_init(struct pp_instance *handle) diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventtasks.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventtasks.c index 5cd123472db4..b6f45fd01fa6 100644 --- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventtasks.c +++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventtasks.c @@ -132,8 +132,7 @@ int pem_task_enable_dynamic_state_management(struct pp_eventmgr *eventmgr, struc int pem_task_disable_dynamic_state_management(struct pp_eventmgr *eventmgr, struct pem_event_data *event_data) { - /* TODO */ - return 0; + return phm_disable_dynamic_state_management(eventmgr->hwmgr); } int pem_task_enable_clock_power_gatings_tasks(struct pp_eventmgr *eventmgr, struct pem_event_data *event_data) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c index 436fc16dabb6..2028980f1ed4 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c @@ -177,12 +177,12 @@ int cz_dpm_powergate_uvd(struct pp_hwmgr *hwmgr, bool bgate) cz_dpm_powerdown_uvd(hwmgr); } else { cz_dpm_powerup_uvd(hwmgr); - cgs_set_clockgating_state(hwmgr->device, - AMD_IP_BLOCK_TYPE_UVD, - AMD_PG_STATE_GATE); cgs_set_powergating_state(hwmgr->device, AMD_IP_BLOCK_TYPE_UVD, AMD_CG_STATE_UNGATE); + cgs_set_clockgating_state(hwmgr->device, + AMD_IP_BLOCK_TYPE_UVD, + AMD_PG_STATE_GATE); cz_dpm_update_uvd_dpm(hwmgr, false); } @@ -206,25 +206,26 @@ int cz_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate) AMD_IP_BLOCK_TYPE_VCE, AMD_PG_STATE_GATE); cz_enable_disable_vce_dpm(hwmgr, false); - /* TODO: to figure out why vce can't be poweroff*/ + cz_dpm_powerdown_vce(hwmgr); cz_hwmgr->vce_power_gated = true; } else { cz_dpm_powerup_vce(hwmgr); cz_hwmgr->vce_power_gated = false; - cgs_set_clockgating_state( - hwmgr->device, - AMD_IP_BLOCK_TYPE_VCE, - AMD_PG_STATE_GATE); cgs_set_powergating_state( hwmgr->device, AMD_IP_BLOCK_TYPE_VCE, AMD_CG_STATE_UNGATE); + cgs_set_clockgating_state( + hwmgr->device, + AMD_IP_BLOCK_TYPE_VCE, + AMD_PG_STATE_GATE); cz_dpm_update_vce_dpm(hwmgr); cz_enable_disable_vce_dpm(hwmgr, true); return 0; } } } else { + cz_hwmgr->vce_power_gated = bgate; cz_dpm_update_vce_dpm(hwmgr); cz_enable_disable_vce_dpm(hwmgr, !bgate); return 0; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c index 1f14c477d15d..8cc0df9b534a 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c @@ -1167,9 +1167,9 @@ static int cz_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, cz_ps->action = cz_current_ps->action; - if ((force_high == false) && (cz_ps->action == FORCE_HIGH)) + if (!force_high && (cz_ps->action == FORCE_HIGH)) cz_ps->action = CANCEL_FORCE_HIGH; - else if ((force_high == true) && (cz_ps->action != FORCE_HIGH)) + else if (force_high && (cz_ps->action != FORCE_HIGH)) cz_ps->action = FORCE_HIGH; else cz_ps->action = DO_NOTHING; @@ -1180,6 +1180,13 @@ static int cz_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, static int cz_hwmgr_backend_init(struct pp_hwmgr *hwmgr) { int result = 0; + struct cz_hwmgr *data; + + data = kzalloc(sizeof(struct cz_hwmgr), GFP_KERNEL); + if (data == NULL) + return -ENOMEM; + + hwmgr->backend = data; result = cz_initialize_dpm_defaults(hwmgr); if (result != 0) { @@ -1649,7 +1656,7 @@ static void cz_hw_print_display_cfg( struct cz_hwmgr *hw_data = (struct cz_hwmgr *)(hwmgr->backend); uint32_t data = 0; - if (hw_data->cc6_settings.cc6_setting_changed == true) { + if (hw_data->cc6_settings.cc6_setting_changed) { hw_data->cc6_settings.cc6_setting_changed = false; @@ -1909,15 +1916,7 @@ static const struct pp_hwmgr_func cz_hwmgr_funcs = { int cz_hwmgr_init(struct pp_hwmgr *hwmgr) { - struct cz_hwmgr *cz_hwmgr; - int ret = 0; - - cz_hwmgr = kzalloc(sizeof(struct cz_hwmgr), GFP_KERNEL); - if (cz_hwmgr == NULL) - return -ENOMEM; - - hwmgr->backend = cz_hwmgr; hwmgr->hwmgr_func = &cz_hwmgr_funcs; hwmgr->pptable_func = &pptable_funcs; - return ret; + return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_clockpowergating.c index e1b649bd5344..5afe82068b29 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_clockpowergating.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_clockpowergating.c @@ -56,7 +56,7 @@ int fiji_phm_powergate_uvd(struct pp_hwmgr *hwmgr, bool bgate) fiji_update_uvd_dpm(hwmgr, false); cgs_set_clockgating_state(hwmgr->device, AMD_IP_BLOCK_TYPE_UVD, - AMD_PG_STATE_UNGATE); + AMD_CG_STATE_UNGATE); } return 0; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c index 24a16e49b571..120a9e2c3152 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c @@ -581,25 +581,24 @@ static int fiji_patch_boot_state(struct pp_hwmgr *hwmgr, static int fiji_hwmgr_backend_fini(struct pp_hwmgr *hwmgr) { - struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); - - if (data->soft_pp_table) { - kfree(data->soft_pp_table); - data->soft_pp_table = NULL; - } - return phm_hwmgr_backend_fini(hwmgr); } static int fiji_hwmgr_backend_init(struct pp_hwmgr *hwmgr) { - struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); + struct fiji_hwmgr *data; uint32_t i; struct phm_ppt_v1_information *table_info = (struct phm_ppt_v1_information *)(hwmgr->pptable); bool stay_in_boot; int result; + data = kzalloc(sizeof(struct fiji_hwmgr), GFP_KERNEL); + if (data == NULL) + return -ENOMEM; + + hwmgr->backend = data; + data->dll_default_on = false; data->sram_end = SMC_RAM_END; @@ -633,6 +632,8 @@ static int fiji_hwmgr_backend_init(struct pp_hwmgr *hwmgr) data->vddci_control = FIJI_VOLTAGE_CONTROL_NONE; data->mvdd_control = FIJI_VOLTAGE_CONTROL_NONE; + data->force_pcie_gen = PP_PCIEGenInvalid; + if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr, VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2)) data->voltage_control = FIJI_VOLTAGE_CONTROL_BY_SVID2; @@ -697,7 +698,7 @@ static int fiji_hwmgr_backend_init(struct pp_hwmgr *hwmgr) if (0 == result) { struct cgs_system_info sys_info = {0}; - data->is_tlu_enabled = 0; + data->is_tlu_enabled = false; hwmgr->platform_descriptor.hardwareActivityPerformanceLevels = FIJI_MAX_HARDWARE_POWERLEVELS; hwmgr->platform_descriptor.hardwarePerformanceLevels = 2; @@ -732,7 +733,7 @@ static int fiji_hwmgr_backend_init(struct pp_hwmgr *hwmgr) sys_info.info_id = CGS_SYSTEM_INFO_PCIE_GEN_INFO; result = cgs_query_system_info(hwmgr->device, &sys_info); if (result) - data->pcie_gen_cap = 0x30007; + data->pcie_gen_cap = AMDGPU_DEFAULT_PCIE_GEN_MASK; else data->pcie_gen_cap = (uint32_t)sys_info.value; if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) @@ -741,7 +742,7 @@ static int fiji_hwmgr_backend_init(struct pp_hwmgr *hwmgr) sys_info.info_id = CGS_SYSTEM_INFO_PCIE_MLW; result = cgs_query_system_info(hwmgr->device, &sys_info); if (result) - data->pcie_lane_cap = 0x2f0000; + data->pcie_lane_cap = AMDGPU_DEFAULT_PCIE_MLW_MASK; else data->pcie_lane_cap = (uint32_t)sys_info.value; } else { @@ -1234,6 +1235,34 @@ static int fiji_program_voting_clients(struct pp_hwmgr *hwmgr) return 0; } +static int fiji_clear_voting_clients(struct pp_hwmgr *hwmgr) +{ + /* Reset voting clients before disabling DPM */ + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, + SCLK_PWRMGT_CNTL, RESET_SCLK_CNT, 1); + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, + SCLK_PWRMGT_CNTL, RESET_BUSY_CNT, 1); + + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_0, 0); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_1, 0); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_2, 0); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_3, 0); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_4, 0); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_5, 0); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_6, 0); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_7, 0); + + return 0; +} + /** * Get the location of various tables inside the FW image. * @@ -1360,6 +1389,17 @@ static int fiji_copy_and_switch_arb_sets(struct pp_hwmgr *hwmgr, return 0; } +/** +* Call SMC to reset S0/S1 to S1 and Reset SMIO to initial value +* +* @param hwmgr the address of the powerplay hardware manager. +* @return if success then 0; +*/ +static int fiji_reset_to_default(struct pp_hwmgr *hwmgr) +{ + return smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_ResetToDefaults); +} + /** * Initial switch from ARB F0->F1 * @@ -1373,6 +1413,21 @@ static int fiji_initial_switch_from_arbf0_to_f1(struct pp_hwmgr *hwmgr) MC_CG_ARB_FREQ_F0, MC_CG_ARB_FREQ_F1); } +static int fiji_force_switch_to_arbf0(struct pp_hwmgr *hwmgr) +{ + uint32_t tmp; + + tmp = (cgs_read_ind_register(hwmgr->device, + CGS_IND_REG__SMC, ixSMC_SCRATCH9) & + 0x0000ff00) >> 8; + + if (tmp == MC_CG_ARB_FREQ_F0) + return 0; + + return fiji_copy_and_switch_arb_sets(hwmgr, + tmp, MC_CG_ARB_FREQ_F0); +} + static int fiji_reset_single_dpm_table(struct pp_hwmgr *hwmgr, struct fiji_single_dpm_table *dpm_table, uint32_t count) { @@ -1395,7 +1450,7 @@ static void fiji_setup_pcie_table_entry( { dpm_table->dpm_levels[index].value = pcie_gen; dpm_table->dpm_levels[index].param1 = pcie_lanes; - dpm_table->dpm_levels[index].enabled = 1; + dpm_table->dpm_levels[index].enabled = true; } static int fiji_setup_default_pcie_table(struct pp_hwmgr *hwmgr) @@ -1607,7 +1662,6 @@ static int fiji_populate_cac_table(struct pp_hwmgr *hwmgr, { uint32_t count; uint8_t index; - int result = 0; struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); struct phm_ppt_v1_information *table_info = (struct phm_ppt_v1_information *)(hwmgr->pptable); @@ -1629,7 +1683,7 @@ static int fiji_populate_cac_table(struct pp_hwmgr *hwmgr, VOLTAGE_SCALE)) / 25); } - return result; + return 0; } /** @@ -1830,7 +1884,7 @@ static uint16_t fiji_find_closest_vddci(struct pp_hwmgr *hwmgr, uint16_t vddci) PP_ASSERT_WITH_CODE(false, "VDDCI is larger than max VDDCI in VDDCI Voltage Table!", - return vddci_table->entries[i].value); + return vddci_table->entries[i-1].value); } static int fiji_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr, @@ -3175,6 +3229,17 @@ static int fiji_enable_ulv(struct pp_hwmgr *hwmgr) return 0; } +static int fiji_disable_ulv(struct pp_hwmgr *hwmgr) +{ + struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); + struct fiji_ulv_parm *ulv = &(data->ulv); + + if (ulv->ulv_supported) + return smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_DisableULV); + + return 0; +} + static int fiji_enable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr) { if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, @@ -3195,6 +3260,21 @@ static int fiji_enable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr) return 0; } +static int fiji_disable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr) +{ + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_SclkDeepSleep)) { + if (smum_send_msg_to_smc(hwmgr->smumgr, + PPSMC_MSG_MASTER_DeepSleep_OFF)) { + PP_ASSERT_WITH_CODE(false, + "Attempt to disable Master Deep Sleep switch failed!", + return -1); + } + } + + return 0; +} + static int fiji_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) { struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); @@ -3355,6 +3435,70 @@ static int fiji_start_dpm(struct pp_hwmgr *hwmgr) return 0; } +static int fiji_disable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) +{ + struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); + + /* disable SCLK dpm */ + if (!data->sclk_dpm_key_disabled) + PP_ASSERT_WITH_CODE( + (smum_send_msg_to_smc(hwmgr->smumgr, + PPSMC_MSG_DPM_Disable) == 0), + "Failed to disable SCLK DPM!", + return -1); + + /* disable MCLK dpm */ + if (!data->mclk_dpm_key_disabled) { + PP_ASSERT_WITH_CODE( + (smum_send_msg_to_smc_with_parameter(hwmgr->smumgr, + PPSMC_MSG_MCLKDPM_SetEnabledMask, 1) == 0), + "Failed to force MCLK DPM0!", + return -1); + + PP_ASSERT_WITH_CODE( + (smum_send_msg_to_smc(hwmgr->smumgr, + PPSMC_MSG_MCLKDPM_Disable) == 0), + "Failed to disable MCLK DPM!", + return -1); + } + + return 0; +} + +static int fiji_stop_dpm(struct pp_hwmgr *hwmgr) +{ + struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); + + /* disable general power management */ + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, GENERAL_PWRMGT, + GLOBAL_PWRMGT_EN, 0); + /* disable sclk deep sleep */ + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, SCLK_PWRMGT_CNTL, + DYNAMIC_PM_EN, 0); + + /* disable PCIE dpm */ + if (!data->pcie_dpm_key_disabled) { + PP_ASSERT_WITH_CODE( + (smum_send_msg_to_smc(hwmgr->smumgr, + PPSMC_MSG_PCIeDPM_Disable) == 0), + "Failed to disable pcie DPM during DPM Stop Function!", + return -1); + } + + if (fiji_disable_sclk_mclk_dpm(hwmgr)) { + printk(KERN_ERR "Failed to disable Sclk DPM and Mclk DPM!"); + return -1; + } + + PP_ASSERT_WITH_CODE( + (smum_send_msg_to_smc(hwmgr->smumgr, + PPSMC_MSG_Voltage_Cntl_Disable) == 0), + "Failed to disable voltage DPM during DPM Stop Function!", + return -1); + + return 0; +} + static void fiji_set_dpm_event_sources(struct pp_hwmgr *hwmgr, uint32_t sources) { @@ -3413,6 +3557,23 @@ static int fiji_enable_thermal_auto_throttle(struct pp_hwmgr *hwmgr) return fiji_enable_auto_throttle_source(hwmgr, PHM_AutoThrottleSource_Thermal); } +static int fiji_disable_auto_throttle_source(struct pp_hwmgr *hwmgr, + PHM_AutoThrottleSource source) +{ + struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); + + if (data->active_auto_throttle_sources & (1 << source)) { + data->active_auto_throttle_sources &= ~(1 << source); + fiji_set_dpm_event_sources(hwmgr, data->active_auto_throttle_sources); + } + return 0; +} + +static int fiji_disable_thermal_auto_throttle(struct pp_hwmgr *hwmgr) +{ + return fiji_disable_auto_throttle_source(hwmgr, PHM_AutoThrottleSource_Thermal); +} + static int fiji_enable_dpm_tasks(struct pp_hwmgr *hwmgr) { int tmp_result, result = 0; @@ -3527,6 +3688,64 @@ static int fiji_enable_dpm_tasks(struct pp_hwmgr *hwmgr) return result; } +static int fiji_disable_dpm_tasks(struct pp_hwmgr *hwmgr) +{ + int tmp_result, result = 0; + + tmp_result = (fiji_is_dpm_running(hwmgr)) ? 0 : -1; + PP_ASSERT_WITH_CODE(tmp_result == 0, + "DPM is not running right now, no need to disable DPM!", + return 0); + + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_ThermalController)) + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, + GENERAL_PWRMGT, THERMAL_PROTECTION_DIS, 1); + + tmp_result = fiji_disable_power_containment(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to disable power containment!", result = tmp_result); + + tmp_result = fiji_disable_smc_cac(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to disable SMC CAC!", result = tmp_result); + + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, + CG_SPLL_SPREAD_SPECTRUM, SSEN, 0); + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, + GENERAL_PWRMGT, DYN_SPREAD_SPECTRUM_EN, 0); + + tmp_result = fiji_disable_thermal_auto_throttle(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to disable thermal auto throttle!", result = tmp_result); + + tmp_result = fiji_stop_dpm(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to stop DPM!", result = tmp_result); + + tmp_result = fiji_disable_deep_sleep_master_switch(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to disable deep sleep master switch!", result = tmp_result); + + tmp_result = fiji_disable_ulv(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to disable ULV!", result = tmp_result); + + tmp_result = fiji_clear_voting_clients(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to clear voting clients!", result = tmp_result); + + tmp_result = fiji_reset_to_default(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to reset to default!", result = tmp_result); + + tmp_result = fiji_force_switch_to_arbf0(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to force to switch arbf0!", result = tmp_result); + + return result; +} + static int fiji_force_dpm_highest(struct pp_hwmgr *hwmgr) { struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); @@ -4169,8 +4388,9 @@ static int fiji_freeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) if ((0 == data->sclk_dpm_key_disabled) && (data->need_update_smu7_dpm_table & (DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK))) { - PP_ASSERT_WITH_CODE(true == fiji_is_dpm_running(hwmgr), - "Trying to freeze SCLK DPM when DPM is disabled",); + PP_ASSERT_WITH_CODE(fiji_is_dpm_running(hwmgr), + "Trying to freeze SCLK DPM when DPM is disabled", + ); PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_SCLKDPM_FreezeLevel), "Failed to freeze SCLK DPM during FreezeSclkMclkDPM Function!", @@ -4180,8 +4400,9 @@ static int fiji_freeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) if ((0 == data->mclk_dpm_key_disabled) && (data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_MCLK)) { - PP_ASSERT_WITH_CODE(true == fiji_is_dpm_running(hwmgr), - "Trying to freeze MCLK DPM when DPM is disabled",); + PP_ASSERT_WITH_CODE(fiji_is_dpm_running(hwmgr), + "Trying to freeze MCLK DPM when DPM is disabled", + ); PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_MCLKDPM_FreezeLevel), "Failed to freeze MCLK DPM during FreezeSclkMclkDPM Function!", @@ -4351,7 +4572,6 @@ static int fiji_trim_single_dpm_states(struct pp_hwmgr *hwmgr, static int fiji_trim_dpm_states(struct pp_hwmgr *hwmgr, const struct fiji_power_state *fiji_ps) { - int result = 0; struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); uint32_t high_limit_count; @@ -4371,7 +4591,7 @@ static int fiji_trim_dpm_states(struct pp_hwmgr *hwmgr, fiji_ps->performance_levels[0].memory_clock, fiji_ps->performance_levels[high_limit_count].memory_clock); - return result; + return 0; } static int fiji_generate_dpm_level_enable_mask( @@ -4630,8 +4850,9 @@ static int fiji_unfreeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) (data->need_update_smu7_dpm_table & (DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK))) { - PP_ASSERT_WITH_CODE(true == fiji_is_dpm_running(hwmgr), - "Trying to Unfreeze SCLK DPM when DPM is disabled",); + PP_ASSERT_WITH_CODE(fiji_is_dpm_running(hwmgr), + "Trying to Unfreeze SCLK DPM when DPM is disabled", + ); PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_SCLKDPM_UnfreezeLevel), "Failed to unfreeze SCLK DPM during UnFreezeSclkMclkDPM Function!", @@ -4641,8 +4862,9 @@ static int fiji_unfreeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) if ((0 == data->mclk_dpm_key_disabled) && (data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_MCLK)) { - PP_ASSERT_WITH_CODE(true == fiji_is_dpm_running(hwmgr), - "Trying to Unfreeze MCLK DPM when DPM is disabled",); + PP_ASSERT_WITH_CODE(fiji_is_dpm_running(hwmgr), + "Trying to Unfreeze MCLK DPM when DPM is disabled", + ); PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_SCLKDPM_UnfreezeLevel), "Failed to unfreeze MCLK DPM during UnFreezeSclkMclkDPM Function!", @@ -5069,42 +5291,6 @@ static int fiji_get_fan_control_mode(struct pp_hwmgr *hwmgr) CG_FDO_CTRL2, FDO_PWM_MODE); } -static int fiji_get_pp_table(struct pp_hwmgr *hwmgr, char **table) -{ - struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); - - if (!data->soft_pp_table) { - data->soft_pp_table = kmemdup(hwmgr->soft_pp_table, - hwmgr->soft_pp_table_size, - GFP_KERNEL); - if (!data->soft_pp_table) - return -ENOMEM; - } - - *table = (char *)&data->soft_pp_table; - - return hwmgr->soft_pp_table_size; -} - -static int fiji_set_pp_table(struct pp_hwmgr *hwmgr, const char *buf, size_t size) -{ - struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); - - if (!data->soft_pp_table) { - data->soft_pp_table = kzalloc(hwmgr->soft_pp_table_size, GFP_KERNEL); - if (!data->soft_pp_table) - return -ENOMEM; - } - - memcpy(data->soft_pp_table, buf, size); - - hwmgr->soft_pp_table = data->soft_pp_table; - - /* TODO: re-init powerplay to implement modified pptable */ - - return 0; -} - static int fiji_force_clock_level(struct pp_hwmgr *hwmgr, enum pp_clock_type type, uint32_t mask) { @@ -5274,12 +5460,96 @@ bool fiji_check_smc_update_required_for_display_configuration(struct pp_hwmgr *h return is_update_required; } +static int fiji_get_sclk_od(struct pp_hwmgr *hwmgr) +{ + struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); + struct fiji_single_dpm_table *sclk_table = &(data->dpm_table.sclk_table); + struct fiji_single_dpm_table *golden_sclk_table = + &(data->golden_dpm_table.sclk_table); + int value; + + value = (sclk_table->dpm_levels[sclk_table->count - 1].value - + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value) * + 100 / + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value; + + return value; +} + +static int fiji_set_sclk_od(struct pp_hwmgr *hwmgr, uint32_t value) +{ + struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); + struct fiji_single_dpm_table *golden_sclk_table = + &(data->golden_dpm_table.sclk_table); + struct pp_power_state *ps; + struct fiji_power_state *fiji_ps; + + if (value > 20) + value = 20; + + ps = hwmgr->request_ps; + + if (ps == NULL) + return -EINVAL; + + fiji_ps = cast_phw_fiji_power_state(&ps->hardware); + + fiji_ps->performance_levels[fiji_ps->performance_level_count - 1].engine_clock = + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value * + value / 100 + + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value; + + return 0; +} + +static int fiji_get_mclk_od(struct pp_hwmgr *hwmgr) +{ + struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); + struct fiji_single_dpm_table *mclk_table = &(data->dpm_table.mclk_table); + struct fiji_single_dpm_table *golden_mclk_table = + &(data->golden_dpm_table.mclk_table); + int value; + + value = (mclk_table->dpm_levels[mclk_table->count - 1].value - + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value) * + 100 / + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value; + + return value; +} + +static int fiji_set_mclk_od(struct pp_hwmgr *hwmgr, uint32_t value) +{ + struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); + struct fiji_single_dpm_table *golden_mclk_table = + &(data->golden_dpm_table.mclk_table); + struct pp_power_state *ps; + struct fiji_power_state *fiji_ps; + + if (value > 20) + value = 20; + + ps = hwmgr->request_ps; + + if (ps == NULL) + return -EINVAL; + + fiji_ps = cast_phw_fiji_power_state(&ps->hardware); + + fiji_ps->performance_levels[fiji_ps->performance_level_count - 1].memory_clock = + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value * + value / 100 + + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value; + + return 0; +} static const struct pp_hwmgr_func fiji_hwmgr_funcs = { .backend_init = &fiji_hwmgr_backend_init, .backend_fini = &fiji_hwmgr_backend_fini, .asic_setup = &fiji_setup_asic_task, .dynamic_state_management_enable = &fiji_enable_dpm_tasks, + .dynamic_state_management_disable = &fiji_disable_dpm_tasks, .force_dpm_level = &fiji_dpm_force_dpm_level, .get_num_of_pp_table_entries = &tonga_get_number_of_powerplay_table_entries, .get_power_state_size = &fiji_get_power_state_size, @@ -5312,24 +5582,18 @@ static const struct pp_hwmgr_func fiji_hwmgr_funcs = { .get_fan_control_mode = fiji_get_fan_control_mode, .check_states_equal = fiji_check_states_equal, .check_smc_update_required_for_display_configuration = fiji_check_smc_update_required_for_display_configuration, - .get_pp_table = fiji_get_pp_table, - .set_pp_table = fiji_set_pp_table, .force_clock_level = fiji_force_clock_level, .print_clock_levels = fiji_print_clock_levels, + .get_sclk_od = fiji_get_sclk_od, + .set_sclk_od = fiji_set_sclk_od, + .get_mclk_od = fiji_get_mclk_od, + .set_mclk_od = fiji_set_mclk_od, }; int fiji_hwmgr_init(struct pp_hwmgr *hwmgr) { - struct fiji_hwmgr *data; - int ret = 0; - - data = kzalloc(sizeof(struct fiji_hwmgr), GFP_KERNEL); - if (data == NULL) - return -ENOMEM; - - hwmgr->backend = data; hwmgr->hwmgr_func = &fiji_hwmgr_funcs; hwmgr->pptable_func = &tonga_pptable_funcs; pp_fiji_thermal_initialize(hwmgr); - return ret; + return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.h index 170edf5a772d..bf67c2a92c68 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.h @@ -302,9 +302,6 @@ struct fiji_hwmgr { bool pg_acp_init; bool frtc_enabled; bool frtc_status_changed; - - /* soft pptable for re-uploading into smu */ - void *soft_pp_table; }; /* To convert to Q8.8 format for firmware */ diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.c index db23a4068baf..44658451a8d2 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.c @@ -72,18 +72,19 @@ void fiji_initialize_power_tune_defaults(struct pp_hwmgr *hwmgr) fiji_hwmgr->dte_tj_offset = tmp; if (!tmp) { - phm_cap_set(hwmgr->platform_descriptor.platformCaps, - PHM_PlatformCaps_PowerContainment); - phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_CAC); fiji_hwmgr->fast_watermark_threshold = 100; - tmp = 1; - fiji_hwmgr->enable_dte_feature = tmp ? false : true; - fiji_hwmgr->enable_tdc_limit_feature = tmp ? true : false; - fiji_hwmgr->enable_pkg_pwr_tracking_feature = tmp ? true : false; + if (hwmgr->powercontainment_enabled) { + phm_cap_set(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_PowerContainment); + tmp = 1; + fiji_hwmgr->enable_dte_feature = tmp ? false : true; + fiji_hwmgr->enable_tdc_limit_feature = tmp ? true : false; + fiji_hwmgr->enable_pkg_pwr_tracking_feature = tmp ? true : false; + } } } @@ -459,6 +460,23 @@ int fiji_enable_smc_cac(struct pp_hwmgr *hwmgr) return result; } +int fiji_disable_smc_cac(struct pp_hwmgr *hwmgr) +{ + struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); + int result = 0; + + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_CAC) && data->cac_enabled) { + int smc_result = smum_send_msg_to_smc(hwmgr->smumgr, + (uint16_t)(PPSMC_MSG_DisableCac)); + PP_ASSERT_WITH_CODE((smc_result == 0), + "Failed to disable CAC in SMC.", result = -1); + + data->cac_enabled = false; + } + return result; +} + int fiji_set_power_limit(struct pp_hwmgr *hwmgr, uint32_t n) { struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); @@ -528,6 +546,48 @@ int fiji_enable_power_containment(struct pp_hwmgr *hwmgr) return result; } +int fiji_disable_power_containment(struct pp_hwmgr *hwmgr) +{ + struct fiji_hwmgr *data = (struct fiji_hwmgr *)(hwmgr->backend); + int result = 0; + + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_PowerContainment) && + data->power_containment_features) { + int smc_result; + + if (data->power_containment_features & + POWERCONTAINMENT_FEATURE_TDCLimit) { + smc_result = smum_send_msg_to_smc(hwmgr->smumgr, + (uint16_t)(PPSMC_MSG_TDCLimitDisable)); + PP_ASSERT_WITH_CODE((smc_result == 0), + "Failed to disable TDCLimit in SMC.", + result = smc_result); + } + + if (data->power_containment_features & + POWERCONTAINMENT_FEATURE_DTE) { + smc_result = smum_send_msg_to_smc(hwmgr->smumgr, + (uint16_t)(PPSMC_MSG_DisableDTE)); + PP_ASSERT_WITH_CODE((smc_result == 0), + "Failed to disable DTE in SMC.", + result = smc_result); + } + + if (data->power_containment_features & + POWERCONTAINMENT_FEATURE_PkgPwrLimit) { + smc_result = smum_send_msg_to_smc(hwmgr->smumgr, + (uint16_t)(PPSMC_MSG_PkgPwrLimitDisable)); + PP_ASSERT_WITH_CODE((smc_result == 0), + "Failed to disable PkgPwrTracking in SMC.", + result = smc_result); + } + data->power_containment_features = 0; + } + + return result; +} + int fiji_power_control_set_level(struct pp_hwmgr *hwmgr) { struct phm_ppt_v1_information *table_info = diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.h b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.h index 55e58200f33a..fec772421733 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_powertune.h @@ -36,6 +36,19 @@ enum fiji_pt_config_reg_type { #define POWERCONTAINMENT_FEATURE_TDCLimit 0x00000002 #define POWERCONTAINMENT_FEATURE_PkgPwrLimit 0x00000004 +#define DIDT_SQ_CTRL0__UNUSED_0_MASK 0xffffffc0 +#define DIDT_SQ_CTRL0__UNUSED_0__SHIFT 0x6 +#define DIDT_TD_CTRL0__UNUSED_0_MASK 0xffffffc0 +#define DIDT_TD_CTRL0__UNUSED_0__SHIFT 0x6 +#define DIDT_TCP_CTRL0__UNUSED_0_MASK 0xffffffc0 +#define DIDT_TCP_CTRL0__UNUSED_0__SHIFT 0x6 +#define DIDT_SQ_TUNING_CTRL__UNUSED_0_MASK 0xe0000000 +#define DIDT_SQ_TUNING_CTRL__UNUSED_0__SHIFT 0x0000001d +#define DIDT_TD_TUNING_CTRL__UNUSED_0_MASK 0xe0000000 +#define DIDT_TD_TUNING_CTRL__UNUSED_0__SHIFT 0x0000001d +#define DIDT_TCP_TUNING_CTRL__UNUSED_0_MASK 0xe0000000 +#define DIDT_TCP_TUNING_CTRL__UNUSED_0__SHIFT 0x0000001d + struct fiji_pt_config_reg { uint32_t offset; uint32_t mask; @@ -58,7 +71,9 @@ void fiji_initialize_power_tune_defaults(struct pp_hwmgr *hwmgr); int fiji_populate_bapm_parameters_in_dpm_table(struct pp_hwmgr *hwmgr); int fiji_populate_pm_fuses(struct pp_hwmgr *hwmgr); int fiji_enable_smc_cac(struct pp_hwmgr *hwmgr); +int fiji_disable_smc_cac(struct pp_hwmgr *hwmgr); int fiji_enable_power_containment(struct pp_hwmgr *hwmgr); +int fiji_disable_power_containment(struct pp_hwmgr *hwmgr); int fiji_set_power_limit(struct pp_hwmgr *hwmgr, uint32_t n); int fiji_power_control_set_level(struct pp_hwmgr *hwmgr); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/functiontables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/functiontables.c index 7a705cee0cc2..a6abe81bc843 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/functiontables.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/functiontables.c @@ -59,8 +59,8 @@ int phm_dispatch_table(struct pp_hwmgr *hwmgr, struct phm_runtime_table_header *rt_table, void *input, void *output) { - int result = 0; - void *temp_storage = NULL; + int result; + void *temp_storage; if (hwmgr == NULL || rt_table == NULL) { printk(KERN_ERR "[ powerplay ] Invalid Parameter!\n"); @@ -73,12 +73,13 @@ int phm_dispatch_table(struct pp_hwmgr *hwmgr, printk(KERN_ERR "[ powerplay ] Could not allocate table temporary storage\n"); return -ENOMEM; } + } else { + temp_storage = NULL; } result = phm_run_table(hwmgr, rt_table, input, output, temp_storage); - if (NULL != temp_storage) - kfree(temp_storage); + kfree(temp_storage); return result; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c index fa208ada6892..789f98ad2615 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c @@ -154,6 +154,30 @@ int phm_enable_dynamic_state_management(struct pp_hwmgr *hwmgr) return ret; } +int phm_disable_dynamic_state_management(struct pp_hwmgr *hwmgr) +{ + int ret = -1; + bool enabled; + + PHM_FUNC_CHECK(hwmgr); + + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_TablelessHardwareInterface)) { + if (hwmgr->hwmgr_func->dynamic_state_management_disable) + ret = hwmgr->hwmgr_func->dynamic_state_management_disable(hwmgr); + } else { + ret = phm_dispatch_table(hwmgr, + &(hwmgr->disable_dynamic_state_management), + NULL, NULL); + } + + enabled = ret == 0 ? false : true; + + cgs_notify_dpm_enabled(hwmgr->device, enabled); + + return ret; +} + int phm_force_dpm_levels(struct pp_hwmgr *hwmgr, enum amd_dpm_forced_level level) { PHM_FUNC_CHECK(hwmgr); @@ -306,11 +330,15 @@ int phm_store_dal_configuration_data(struct pp_hwmgr *hwmgr, { PHM_FUNC_CHECK(hwmgr); - if (hwmgr->hwmgr_func->store_cc6_data == NULL) + if (display_config == NULL) return -EINVAL; hwmgr->display_config = *display_config; - /* to do pass other display configuration in furture */ + + if (hwmgr->hwmgr_func->store_cc6_data == NULL) + return -EINVAL; + + /* TODO: pass other display configuration in the future */ if (hwmgr->hwmgr_func->store_cc6_data) hwmgr->hwmgr_func->store_cc6_data(hwmgr, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c index 1c48917da3cf..27e07624ac28 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c @@ -24,6 +24,7 @@ #include #include #include +#include #include "cgs_common.h" #include "power_state.h" #include "hwmgr.h" @@ -58,12 +59,13 @@ int hwmgr_init(struct amd_pp_init *pp_init, struct pp_instance *handle) hwmgr->hw_revision = pp_init->rev_id; hwmgr->usec_timeout = AMD_MAX_USEC_TIMEOUT; hwmgr->power_source = PP_PowerSource_AC; + hwmgr->powercontainment_enabled = pp_init->powercontainment_enabled; switch (hwmgr->chip_family) { - case AMD_FAMILY_CZ: + case AMDGPU_FAMILY_CZ: cz_hwmgr_init(hwmgr); break; - case AMD_FAMILY_VI: + case AMDGPU_FAMILY_VI: switch (hwmgr->chip_id) { case CHIP_TONGA: tonga_hwmgr_init(hwmgr); @@ -93,6 +95,15 @@ int hwmgr_fini(struct pp_hwmgr *hwmgr) if (hwmgr == NULL || hwmgr->ps == NULL) return -EINVAL; + /* do hwmgr finish*/ + kfree(hwmgr->hardcode_pp_table); + + kfree(hwmgr->backend); + + kfree(hwmgr->start_thermal_controller.function_list); + + kfree(hwmgr->set_temperature_range.function_list); + kfree(hwmgr->ps); kfree(hwmgr); return 0; @@ -462,7 +473,7 @@ uint16_t phm_find_closest_vddci(struct pp_atomctrl_voltage_table *vddci_table, u PP_ASSERT_WITH_CODE(false, "VDDCI is larger than max VDDCI in VDDCI Voltage Table!", - return vddci_table->entries[i].value); + return vddci_table->entries[i-1].value); } int phm_find_boot_level(void *table, @@ -523,7 +534,7 @@ int phm_initializa_dynamic_state_adjustment_rule_settings(struct pp_hwmgr *hwmgr /* initialize vddc_dep_on_dal_pwrl table */ table_size = sizeof(uint32_t) + 4 * sizeof(struct phm_clock_voltage_dependency_record); - table_clk_vlt = (struct phm_clock_voltage_dependency_table *)kzalloc(table_size, GFP_KERNEL); + table_clk_vlt = kzalloc(table_size, GFP_KERNEL); if (NULL == table_clk_vlt) { printk(KERN_ERR "[ powerplay ] Can not allocate space for vddc_dep_on_dal_pwrl! \n"); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h index 347fef127ce9..2930a3355948 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr_ppt.h @@ -39,6 +39,7 @@ struct phm_ppt_v1_clock_voltage_dependency_record { uint8_t phases; uint8_t cks_enable; uint8_t cks_voffset; + uint32_t sclk_offset; }; typedef struct phm_ppt_v1_clock_voltage_dependency_record phm_ppt_v1_clock_voltage_dependency_record; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_clockpowergating.c index 8f142a74ad08..b5edb5105986 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_clockpowergating.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_clockpowergating.c @@ -106,11 +106,17 @@ int polaris10_phm_powergate_uvd(struct pp_hwmgr *hwmgr, bool bgate) data->uvd_power_gated = bgate; if (bgate) { + cgs_set_clockgating_state(hwmgr->device, + AMD_IP_BLOCK_TYPE_UVD, + AMD_CG_STATE_GATE); polaris10_update_uvd_dpm(hwmgr, true); polaris10_phm_powerdown_uvd(hwmgr); } else { polaris10_phm_powerup_uvd(hwmgr); polaris10_update_uvd_dpm(hwmgr, false); + cgs_set_clockgating_state(hwmgr->device, + AMD_IP_BLOCK_TYPE_UVD, + AMD_CG_STATE_UNGATE); } return 0; @@ -125,11 +131,19 @@ int polaris10_phm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate) data->vce_power_gated = bgate; - if (bgate) + if (bgate) { + cgs_set_clockgating_state(hwmgr->device, + AMD_IP_BLOCK_TYPE_VCE, + AMD_CG_STATE_GATE); + polaris10_update_vce_dpm(hwmgr, true); polaris10_phm_powerdown_vce(hwmgr); - else + } else { polaris10_phm_powerup_vce(hwmgr); - + polaris10_update_vce_dpm(hwmgr, false); + cgs_set_clockgating_state(hwmgr->device, + AMD_IP_BLOCK_TYPE_VCE, + AMD_CG_STATE_UNGATE); + } return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c index aa6be033f21b..769636a0c5b5 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c @@ -389,6 +389,34 @@ static int polaris10_program_voting_clients(struct pp_hwmgr *hwmgr) return 0; } +static int polaris10_clear_voting_clients(struct pp_hwmgr *hwmgr) +{ + /* Reset voting clients before disabling DPM */ + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, + SCLK_PWRMGT_CNTL, RESET_SCLK_CNT, 1); + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, + SCLK_PWRMGT_CNTL, RESET_BUSY_CNT, 1); + + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_0, 0); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_1, 0); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_2, 0); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_3, 0); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_4, 0); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_5, 0); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_6, 0); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + ixCG_FREQ_TRAN_VOTING_7, 0); + + return 0; +} + /** * Get the location of various tables inside the FW image. * @@ -515,6 +543,11 @@ static int polaris10_copy_and_switch_arb_sets(struct pp_hwmgr *hwmgr, return 0; } +static int polaris10_reset_to_default(struct pp_hwmgr *hwmgr) +{ + return smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_ResetToDefaults); +} + /** * Initial switch from ARB F0->F1 * @@ -528,6 +561,21 @@ static int polaris10_initial_switch_from_arbf0_to_f1(struct pp_hwmgr *hwmgr) MC_CG_ARB_FREQ_F0, MC_CG_ARB_FREQ_F1); } +static int polaris10_force_switch_to_arbf0(struct pp_hwmgr *hwmgr) +{ + uint32_t tmp; + + tmp = (cgs_read_ind_register(hwmgr->device, + CGS_IND_REG__SMC, ixSMC_SCRATCH9) & + 0x0000ff00) >> 8; + + if (tmp == MC_CG_ARB_FREQ_F0) + return 0; + + return polaris10_copy_and_switch_arb_sets(hwmgr, + tmp, MC_CG_ARB_FREQ_F0); +} + static int polaris10_setup_default_pcie_table(struct pp_hwmgr *hwmgr) { struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); @@ -732,7 +780,7 @@ static int polaris10_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr, table->Smio[level] |= data->mvdd_voltage_table.entries[level].smio_low; } - table->SmioMask2 = data->vddci_voltage_table.mask_low; + table->SmioMask2 = data->mvdd_voltage_table.mask_low; table->MvddLevelCount = (uint32_t) PP_HOST_TO_SMC_UL(count); } @@ -999,7 +1047,7 @@ static int polaris10_get_dependency_volt_by_clk(struct pp_hwmgr *hwmgr, vddci = phm_find_closest_vddci(&(data->vddci_voltage_table), (dep_table->entries[i].vddc - (uint16_t)data->vddc_vddci_delta)); - *voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT; + *voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT; } if (POLARIS10_VOLTAGE_CONTROL_NONE == data->mvdd_control) @@ -1296,7 +1344,6 @@ static int polaris10_populate_single_memory_level(struct pp_hwmgr *hwmgr, } mem_level->MclkFrequency = clock; - mem_level->StutterEnable = 0; mem_level->EnabledForThrottle = 1; mem_level->EnabledForActivity = 0; mem_level->UpHyst = 0; @@ -1304,7 +1351,6 @@ static int polaris10_populate_single_memory_level(struct pp_hwmgr *hwmgr, mem_level->VoltageDownHyst = 0; mem_level->ActivityLevel = (uint16_t)data->mclk_activity_target; mem_level->StutterEnable = false; - mem_level->DisplayWatermark = PPSMC_DISPLAY_WATERMARK_LOW; data->display_timing.num_existing_displays = info.display_count; @@ -1358,12 +1404,12 @@ static int polaris10_populate_all_memory_levels(struct pp_hwmgr *hwmgr) return result; } - /* in order to prevent MC activity from stutter mode to push DPM up. + /* In order to prevent MC activity from stutter mode to push DPM up, * the UVD change complements this by putting the MCLK in - * a higher state by default such that we are not effected by + * a higher state by default such that we are not affected by * up threshold or and MCLK DPM latency. */ - levels[0].ActivityLevel = (uint16_t)data->mclk_dpm0_activity_target; + levels[0].ActivityLevel = 0x1f; CONVERT_FROM_HOST_TO_SMC_US(levels[0].ActivityLevel); data->smc_state_table.MemoryDpmLevelCount = @@ -1424,22 +1470,19 @@ static int polaris10_populate_smc_acpi_level(struct pp_hwmgr *hwmgr, table->ACPILevel.Flags &= ~PPSMC_SWSTATE_FLAG_DC; - if (!data->sclk_dpm_key_disabled) { - /* Get MinVoltage and Frequency from DPM0, - * already converted to SMC_UL */ - sclk_frequency = data->dpm_table.sclk_table.dpm_levels[0].value; - result = polaris10_get_dependency_volt_by_clk(hwmgr, - table_info->vdd_dep_on_sclk, - table->ACPILevel.SclkFrequency, - &table->ACPILevel.MinVoltage, &mvdd); - PP_ASSERT_WITH_CODE((0 == result), - "Cannot find ACPI VDDC voltage value " - "in Clock Dependency Table", ); - } else { - sclk_frequency = data->vbios_boot_state.sclk_bootup_value; - table->ACPILevel.MinVoltage = - data->vbios_boot_state.vddc_bootup_value * VOLTAGE_SCALE; - } + + /* Get MinVoltage and Frequency from DPM0, + * already converted to SMC_UL */ + sclk_frequency = data->vbios_boot_state.sclk_bootup_value; + result = polaris10_get_dependency_volt_by_clk(hwmgr, + table_info->vdd_dep_on_sclk, + sclk_frequency, + &table->ACPILevel.MinVoltage, &mvdd); + PP_ASSERT_WITH_CODE((0 == result), + "Cannot find ACPI VDDC voltage value " + "in Clock Dependency Table", + ); + result = polaris10_calculate_sclk_params(hwmgr, sclk_frequency, &(table->ACPILevel.SclkSetting)); PP_ASSERT_WITH_CODE(result == 0, "Error retrieving Engine Clock dividers from VBIOS.", return result); @@ -1464,24 +1507,17 @@ static int polaris10_populate_smc_acpi_level(struct pp_hwmgr *hwmgr, CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Fcw1_frac); CONVERT_FROM_HOST_TO_SMC_US(table->ACPILevel.SclkSetting.Sclk_ss_slew_rate); - if (!data->mclk_dpm_key_disabled) { - /* Get MinVoltage and Frequency from DPM0, already converted to SMC_UL */ - table->MemoryACPILevel.MclkFrequency = - data->dpm_table.mclk_table.dpm_levels[0].value; - result = polaris10_get_dependency_volt_by_clk(hwmgr, - table_info->vdd_dep_on_mclk, - table->MemoryACPILevel.MclkFrequency, - &table->MemoryACPILevel.MinVoltage, &mvdd); - PP_ASSERT_WITH_CODE((0 == result), - "Cannot find ACPI VDDCI voltage value " - "in Clock Dependency Table", - ); - } else { - table->MemoryACPILevel.MclkFrequency = - data->vbios_boot_state.mclk_bootup_value; - table->MemoryACPILevel.MinVoltage = - data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE; - } + + /* Get MinVoltage and Frequency from DPM0, already converted to SMC_UL */ + table->MemoryACPILevel.MclkFrequency = data->vbios_boot_state.mclk_bootup_value; + result = polaris10_get_dependency_volt_by_clk(hwmgr, + table_info->vdd_dep_on_mclk, + table->MemoryACPILevel.MclkFrequency, + &table->MemoryACPILevel.MinVoltage, &mvdd); + PP_ASSERT_WITH_CODE((0 == result), + "Cannot find ACPI VDDCI voltage value " + "in Clock Dependency Table", + ); us_mvdd = 0; if ((POLARIS10_VOLTAGE_CONTROL_NONE == data->mvdd_control) || @@ -1526,6 +1562,7 @@ static int polaris10_populate_smc_vce_level(struct pp_hwmgr *hwmgr, struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table = table_info->mm_dep_table; struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + uint32_t vddci; table->VceLevelCount = (uint8_t)(mm_table->count); table->VceBootLevel = 0; @@ -1535,9 +1572,18 @@ static int polaris10_populate_smc_vce_level(struct pp_hwmgr *hwmgr, table->VceLevel[count].MinVoltage = 0; table->VceLevel[count].MinVoltage |= (mm_table->entries[count].vddc * VOLTAGE_SCALE) << VDDC_SHIFT; + + if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control) + vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table), + mm_table->entries[count].vddc - VDDC_VDDCI_DELTA); + else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control) + vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA; + else + vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT; + + table->VceLevel[count].MinVoltage |= - ((mm_table->entries[count].vddc - data->vddc_vddci_delta) * - VOLTAGE_SCALE) << VDDCI_SHIFT; + (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT; table->VceLevel[count].MinVoltage |= 1 << PHASES_SHIFT; /*retrieve divider value for VBIOS */ @@ -1566,6 +1612,7 @@ static int polaris10_populate_smc_samu_level(struct pp_hwmgr *hwmgr, struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table = table_info->mm_dep_table; struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + uint32_t vddci; table->SamuBootLevel = 0; table->SamuLevelCount = (uint8_t)(mm_table->count); @@ -1576,8 +1623,16 @@ static int polaris10_populate_smc_samu_level(struct pp_hwmgr *hwmgr, table->SamuLevel[count].Frequency = mm_table->entries[count].samclock; table->SamuLevel[count].MinVoltage |= (mm_table->entries[count].vddc * VOLTAGE_SCALE) << VDDC_SHIFT; - table->SamuLevel[count].MinVoltage |= ((mm_table->entries[count].vddc - - data->vddc_vddci_delta) * VOLTAGE_SCALE) << VDDCI_SHIFT; + + if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control) + vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table), + mm_table->entries[count].vddc - VDDC_VDDCI_DELTA); + else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control) + vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA; + else + vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT; + + table->SamuLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT; table->SamuLevel[count].MinVoltage |= 1 << PHASES_SHIFT; /* retrieve divider value for VBIOS */ @@ -1660,6 +1715,7 @@ static int polaris10_populate_smc_uvd_level(struct pp_hwmgr *hwmgr, struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table = table_info->mm_dep_table; struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + uint32_t vddci; table->UvdLevelCount = (uint8_t)(mm_table->count); table->UvdBootLevel = 0; @@ -1670,8 +1726,16 @@ static int polaris10_populate_smc_uvd_level(struct pp_hwmgr *hwmgr, table->UvdLevel[count].DclkFrequency = mm_table->entries[count].dclk; table->UvdLevel[count].MinVoltage |= (mm_table->entries[count].vddc * VOLTAGE_SCALE) << VDDC_SHIFT; - table->UvdLevel[count].MinVoltage |= ((mm_table->entries[count].vddc - - data->vddc_vddci_delta) * VOLTAGE_SCALE) << VDDCI_SHIFT; + + if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control) + vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table), + mm_table->entries[count].vddc - VDDC_VDDCI_DELTA); + else if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control) + vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA; + else + vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT; + + table->UvdLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT; table->UvdLevel[count].MinVoltage |= 1 << PHASES_SHIFT; /* retrieve divider value for VBIOS */ @@ -1692,8 +1756,8 @@ static int polaris10_populate_smc_uvd_level(struct pp_hwmgr *hwmgr, CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].VclkFrequency); CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].DclkFrequency); CONVERT_FROM_HOST_TO_SMC_UL(table->UvdLevel[count].MinVoltage); - } + return result; } @@ -1761,12 +1825,9 @@ static int polaris10_populate_smc_initailial_state(struct pp_hwmgr *hwmgr) static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr) { - uint32_t ro, efuse, efuse2, clock_freq, volt_without_cks, - volt_with_cks, value; - uint16_t clock_freq_u16; + uint32_t ro, efuse, volt_without_cks, volt_with_cks, value, max, min; struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); - uint8_t type, i, j, cks_setting, stretch_amount, stretch_amount2, - volt_offset = 0; + uint8_t i, stretch_amount, volt_offset = 0; struct phm_ppt_v1_information *table_info = (struct phm_ppt_v1_information *)(hwmgr->pptable); struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table = @@ -1778,56 +1839,47 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr) * if the part is SS or FF. if RO >= 1660MHz, part is FF. */ efuse = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, - ixSMU_EFUSE_0 + (146 * 4)); - efuse2 = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, - ixSMU_EFUSE_0 + (148 * 4)); + ixSMU_EFUSE_0 + (67 * 4)); efuse &= 0xFF000000; efuse = efuse >> 24; - efuse2 &= 0xF; - if (efuse2 == 1) - ro = (2300 - 1350) * efuse / 255 + 1350; - else - ro = (2500 - 1000) * efuse / 255 + 1000; + if (hwmgr->chip_id == CHIP_POLARIS10) { + min = 1000; + max = 2300; + } else { + min = 1100; + max = 2100; + } - if (ro >= 1660) - type = 0; - else - type = 1; - - /* Populate Stretch amount */ - data->smc_state_table.ClockStretcherAmount = stretch_amount; + ro = efuse * (max -min)/255 + min; /* Populate Sclk_CKS_masterEn0_7 and Sclk_voltageOffset */ for (i = 0; i < sclk_table->count; i++) { data->smc_state_table.Sclk_CKS_masterEn0_7 |= sclk_table->entries[i].cks_enable << i; - volt_without_cks = (uint32_t)((14041 * - (sclk_table->entries[i].clk/100) / 10000 + 3571 + 75 - ro) * 1000 / - (4026 - (13924 * (sclk_table->entries[i].clk/100) / 10000))); - volt_with_cks = (uint32_t)((13946 * - (sclk_table->entries[i].clk/100) / 10000 + 3320 + 45 - ro) * 1000 / - (3664 - (11454 * (sclk_table->entries[i].clk/100) / 10000))); + if (hwmgr->chip_id == CHIP_POLARIS10) { + volt_without_cks = (uint32_t)((2753594000U + (sclk_table->entries[i].clk/100) * 136418 -(ro - 70) * 1000000) / \ + (2424180 - (sclk_table->entries[i].clk/100) * 1132925/1000)); + volt_with_cks = (uint32_t)((2797202000U + sclk_table->entries[i].clk/100 * 3232 - (ro - 65) * 1000000) / \ + (2522480 - sclk_table->entries[i].clk/100 * 115764/100)); + } else { + volt_without_cks = (uint32_t)((2416794800U + (sclk_table->entries[i].clk/100) * 1476925/10 -(ro - 50) * 1000000) / \ + (2625416 - (sclk_table->entries[i].clk/100) * (12586807/10000))); + volt_with_cks = (uint32_t)((2999656000U - sclk_table->entries[i].clk/100 * 392803 - (ro - 44) * 1000000) / \ + (3422454 - sclk_table->entries[i].clk/100 * (18886376/10000))); + } + if (volt_without_cks >= volt_with_cks) volt_offset = (uint8_t)(((volt_without_cks - volt_with_cks + - sclk_table->entries[i].cks_voffset) * 100 / 625) + 1); + sclk_table->entries[i].cks_voffset) * 100 + 624) / 625); + data->smc_state_table.Sclk_voltageOffset[i] = volt_offset; } - PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE, - STRETCH_ENABLE, 0x0); - PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE, - masterReset, 0x1); - /* PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE, staticEnable, 0x1); */ - PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_CKS_ENABLE, - masterReset, 0x0); - + data->smc_state_table.LdoRefSel = (table_info->cac_dtp_table->ucCKS_LDO_REFSEL != 0) ? table_info->cac_dtp_table->ucCKS_LDO_REFSEL : 6; /* Populate CKS Lookup Table */ - if (stretch_amount == 1 || stretch_amount == 2 || stretch_amount == 5) - stretch_amount2 = 0; - else if (stretch_amount == 3 || stretch_amount == 4) - stretch_amount2 = 1; - else { + if (stretch_amount != 1 && stretch_amount != 2 && stretch_amount != 3 && + stretch_amount != 4 && stretch_amount != 5) { phm_cap_unset(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_ClockStretcher); PP_ASSERT_WITH_CODE(false, @@ -1835,69 +1887,6 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr) return -EINVAL); } - value = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, - ixPWR_CKS_CNTL); - value &= 0xFFC2FF87; - data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].minFreq = - polaris10_clock_stretcher_lookup_table[stretch_amount2][0]; - data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].maxFreq = - polaris10_clock_stretcher_lookup_table[stretch_amount2][1]; - clock_freq_u16 = (uint16_t)(PP_SMC_TO_HOST_UL(data->smc_state_table. - GraphicsLevel[data->smc_state_table.GraphicsDpmLevelCount - 1].SclkSetting.SclkFrequency) / 100); - if (polaris10_clock_stretcher_lookup_table[stretch_amount2][0] < clock_freq_u16 - && polaris10_clock_stretcher_lookup_table[stretch_amount2][1] > clock_freq_u16) { - /* Program PWR_CKS_CNTL. CKS_USE_FOR_LOW_FREQ */ - value |= (polaris10_clock_stretcher_lookup_table[stretch_amount2][3]) << 16; - /* Program PWR_CKS_CNTL. CKS_LDO_REFSEL */ - value |= (polaris10_clock_stretcher_lookup_table[stretch_amount2][2]) << 18; - /* Program PWR_CKS_CNTL. CKS_STRETCH_AMOUNT */ - value |= (polaris10_clock_stretch_amount_conversion - [polaris10_clock_stretcher_lookup_table[stretch_amount2][3]] - [stretch_amount]) << 3; - } - CONVERT_FROM_HOST_TO_SMC_US(data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].minFreq); - CONVERT_FROM_HOST_TO_SMC_US(data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].maxFreq); - data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].setting = - polaris10_clock_stretcher_lookup_table[stretch_amount2][2] & 0x7F; - data->smc_state_table.CKS_LOOKUPTable.CKS_LOOKUPTableEntry[0].setting |= - (polaris10_clock_stretcher_lookup_table[stretch_amount2][3]) << 7; - - cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, - ixPWR_CKS_CNTL, value); - - /* Populate DDT Lookup Table */ - for (i = 0; i < 4; i++) { - /* Assign the minimum and maximum VID stored - * in the last row of Clock Stretcher Voltage Table. - */ - data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].minVID = - (uint8_t) polaris10_clock_stretcher_ddt_table[type][i][2]; - data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].maxVID = - (uint8_t) polaris10_clock_stretcher_ddt_table[type][i][3]; - /* Loop through each SCLK and check the frequency - * to see if it lies within the frequency for clock stretcher. - */ - for (j = 0; j < data->smc_state_table.GraphicsDpmLevelCount; j++) { - cks_setting = 0; - clock_freq = PP_SMC_TO_HOST_UL( - data->smc_state_table.GraphicsLevel[j].SclkSetting.SclkFrequency); - /* Check the allowed frequency against the sclk level[j]. - * Sclk's endianness has already been converted, - * and it's in 10Khz unit, - * as opposed to Data table, which is in Mhz unit. - */ - if (clock_freq >= (polaris10_clock_stretcher_ddt_table[type][i][0]) * 100) { - cks_setting |= 0x2; - if (clock_freq < (polaris10_clock_stretcher_ddt_table[type][i][1]) * 100) - cks_setting |= 0x1; - } - data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].setting - |= cks_setting << (j * 2); - } - CONVERT_FROM_HOST_TO_SMC_US( - data->smc_state_table.ClockStretcherDataTable.ClockStretcherDataTableEntry[i].setting); - } - value = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixPWR_CKS_CNTL); value &= 0xFFFFFFFE; cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixPWR_CKS_CNTL, value); @@ -1945,9 +1934,8 @@ static int polaris10_populate_vr_config(struct pp_hwmgr *hwmgr, if (POLARIS10_VOLTAGE_CONTROL_BY_SVID2 == data->mvdd_control) { config = VR_SVI2_PLANE_2; table->VRConfig |= (config << VRCONF_MVDD_SHIFT); - } else if (POLARIS10_VOLTAGE_CONTROL_BY_GPIO == data->mvdd_control) { - config = VR_SMIO_PATTERN_2; - table->VRConfig |= (config << VRCONF_MVDD_SHIFT); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, data->soft_regs_start + + offsetof(SMU74_SoftRegisters, AllowMvddSwitch), 0x1); } else { config = VR_STATIC_VOLTAGE; table->VRConfig |= (config << VRCONF_MVDD_SHIFT); @@ -1956,6 +1944,90 @@ static int polaris10_populate_vr_config(struct pp_hwmgr *hwmgr, return 0; } + +int polaris10_populate_avfs_parameters(struct pp_hwmgr *hwmgr) +{ + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + SMU74_Discrete_DpmTable *table = &(data->smc_state_table); + int result = 0; + struct pp_atom_ctrl__avfs_parameters avfs_params = {0}; + AVFS_meanNsigma_t AVFS_meanNsigma = { {0} }; + AVFS_Sclk_Offset_t AVFS_SclkOffset = { {0} }; + uint32_t tmp, i; + struct pp_smumgr *smumgr = hwmgr->smumgr; + struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(smumgr->backend); + + struct phm_ppt_v1_information *table_info = + (struct phm_ppt_v1_information *)hwmgr->pptable; + struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table = + table_info->vdd_dep_on_sclk; + + + if (smu_data->avfs.avfs_btc_status == AVFS_BTC_NOTSUPPORTED) + return result; + + result = atomctrl_get_avfs_information(hwmgr, &avfs_params); + + if (0 == result) { + table->BTCGB_VDROOP_TABLE[0].a0 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a0); + table->BTCGB_VDROOP_TABLE[0].a1 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a1); + table->BTCGB_VDROOP_TABLE[0].a2 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSON_a2); + table->BTCGB_VDROOP_TABLE[1].a0 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a0); + table->BTCGB_VDROOP_TABLE[1].a1 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a1); + table->BTCGB_VDROOP_TABLE[1].a2 = PP_HOST_TO_SMC_UL(avfs_params.ulGB_VDROOP_TABLE_CKSOFF_a2); + table->AVFSGB_VDROOP_TABLE[0].m1 = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSON_m1); + table->AVFSGB_VDROOP_TABLE[0].m2 = PP_HOST_TO_SMC_US(avfs_params.usAVFSGB_FUSE_TABLE_CKSON_m2); + table->AVFSGB_VDROOP_TABLE[0].b = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSON_b); + table->AVFSGB_VDROOP_TABLE[0].m1_shift = 24; + table->AVFSGB_VDROOP_TABLE[0].m2_shift = 12; + table->AVFSGB_VDROOP_TABLE[1].m1 = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSOFF_m1); + table->AVFSGB_VDROOP_TABLE[1].m2 = PP_HOST_TO_SMC_US(avfs_params.usAVFSGB_FUSE_TABLE_CKSOFF_m2); + table->AVFSGB_VDROOP_TABLE[1].b = PP_HOST_TO_SMC_UL(avfs_params.ulAVFSGB_FUSE_TABLE_CKSOFF_b); + table->AVFSGB_VDROOP_TABLE[1].m1_shift = 24; + table->AVFSGB_VDROOP_TABLE[1].m2_shift = 12; + table->MaxVoltage = PP_HOST_TO_SMC_US(avfs_params.usMaxVoltage_0_25mv); + AVFS_meanNsigma.Aconstant[0] = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant0); + AVFS_meanNsigma.Aconstant[1] = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant1); + AVFS_meanNsigma.Aconstant[2] = PP_HOST_TO_SMC_UL(avfs_params.ulAVFS_meanNsigma_Acontant2); + AVFS_meanNsigma.DC_tol_sigma = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_DC_tol_sigma); + AVFS_meanNsigma.Platform_mean = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_Platform_mean); + AVFS_meanNsigma.PSM_Age_CompFactor = PP_HOST_TO_SMC_US(avfs_params.usPSM_Age_ComFactor); + AVFS_meanNsigma.Platform_sigma = PP_HOST_TO_SMC_US(avfs_params.usAVFS_meanNsigma_Platform_sigma); + + for (i = 0; i < NUM_VFT_COLUMNS; i++) { + AVFS_meanNsigma.Static_Voltage_Offset[i] = (uint8_t)(sclk_table->entries[i].cks_voffset * 100 / 625); + AVFS_SclkOffset.Sclk_Offset[i] = PP_HOST_TO_SMC_US((uint16_t)(sclk_table->entries[i].sclk_offset) / 100); + } + + result = polaris10_read_smc_sram_dword(smumgr, + SMU7_FIRMWARE_HEADER_LOCATION + offsetof(SMU74_Firmware_Header, AvfsMeanNSigma), + &tmp, data->sram_end); + + polaris10_copy_bytes_to_smc(smumgr, + tmp, + (uint8_t *)&AVFS_meanNsigma, + sizeof(AVFS_meanNsigma_t), + data->sram_end); + + result = polaris10_read_smc_sram_dword(smumgr, + SMU7_FIRMWARE_HEADER_LOCATION + offsetof(SMU74_Firmware_Header, AvfsSclkOffsetTable), + &tmp, data->sram_end); + polaris10_copy_bytes_to_smc(smumgr, + tmp, + (uint8_t *)&AVFS_SclkOffset, + sizeof(AVFS_Sclk_Offset_t), + data->sram_end); + + data->avfs_vdroop_override_setting = (avfs_params.ucEnableGB_VDROOP_TABLE_CKSON << BTCGB0_Vdroop_Enable_SHIFT) | + (avfs_params.ucEnableGB_VDROOP_TABLE_CKSOFF << BTCGB1_Vdroop_Enable_SHIFT) | + (avfs_params.ucEnableGB_FUSE_TABLE_CKSON << AVFSGB0_Vdroop_Enable_SHIFT) | + (avfs_params.ucEnableGB_FUSE_TABLE_CKSOFF << AVFSGB1_Vdroop_Enable_SHIFT); + data->apply_avfs_cks_off_voltage = (avfs_params.ucEnableApplyAVFS_CKS_OFF_Voltage == 1) ? true : false; + } + return result; +} + + /** * Initializes the SMC table and uploads it * @@ -2056,6 +2128,10 @@ static int polaris10_init_smc_table(struct pp_hwmgr *hwmgr) "Failed to populate Clock Stretcher Data Table!", return result); } + + result = polaris10_populate_avfs_parameters(hwmgr); + PP_ASSERT_WITH_CODE(0 == result, "Failed to populate AVFS Parameters!", return result;); + table->CurrSclkPllRange = 0xff; table->GraphicsVoltageChangeEnable = 1; table->GraphicsThermThrottleEnable = 1; @@ -2229,6 +2305,17 @@ static int polaris10_enable_ulv(struct pp_hwmgr *hwmgr) return 0; } +static int polaris10_disable_ulv(struct pp_hwmgr *hwmgr) +{ + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + struct polaris10_ulv_parm *ulv = &(data->ulv); + + if (ulv->ulv_supported) + return smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_DisableULV); + + return 0; +} + static int polaris10_enable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr) { if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, @@ -2249,9 +2336,27 @@ static int polaris10_enable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr) return 0; } +static int polaris10_disable_deep_sleep_master_switch(struct pp_hwmgr *hwmgr) +{ + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_SclkDeepSleep)) { + if (smum_send_msg_to_smc(hwmgr->smumgr, + PPSMC_MSG_MASTER_DeepSleep_OFF)) { + PP_ASSERT_WITH_CODE(false, + "Attempt to disable Master Deep Sleep switch failed!", + return -1); + } + } + + return 0; +} + static int polaris10_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) { struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + uint32_t soft_register_value = 0; + uint32_t handshake_disables_offset = data->soft_regs_start + + offsetof(SMU74_SoftRegisters, HandshakeDisables); /* enable SCLK dpm */ if (!data->sclk_dpm_key_disabled) @@ -2262,6 +2367,12 @@ static int polaris10_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) /* enable MCLK dpm */ if (0 == data->mclk_dpm_key_disabled) { +/* Disable UVD - SMU handshake for MCLK. */ + soft_register_value = cgs_read_ind_register(hwmgr->device, + CGS_IND_REG__SMC, handshake_disables_offset); + soft_register_value |= SMU7_UVD_MCLK_HANDSHAKE_DISABLE; + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, + handshake_disables_offset, soft_register_value); PP_ASSERT_WITH_CODE( (0 == smum_send_msg_to_smc(hwmgr->smumgr, @@ -2269,7 +2380,6 @@ static int polaris10_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) "Failed to enable MCLK DPM during DPM Start Function!", return -1); - PHM_WRITE_FIELD(hwmgr->device, MC_SEQ_CNTL_3, CAC_EN, 0x1); cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixLCAC_MC0_CNTL, 0x5); @@ -2338,6 +2448,58 @@ static int polaris10_start_dpm(struct pp_hwmgr *hwmgr) return 0; } +static int polaris10_disable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) +{ + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + + /* disable SCLK dpm */ + if (!data->sclk_dpm_key_disabled) + PP_ASSERT_WITH_CODE( + (smum_send_msg_to_smc(hwmgr->smumgr, + PPSMC_MSG_DPM_Disable) == 0), + "Failed to disable SCLK DPM!", + return -1); + + /* disable MCLK dpm */ + if (!data->mclk_dpm_key_disabled) { + PP_ASSERT_WITH_CODE( + (smum_send_msg_to_smc(hwmgr->smumgr, + PPSMC_MSG_MCLKDPM_Disable) == 0), + "Failed to disable MCLK DPM!", + return -1); + } + + return 0; +} + +static int polaris10_stop_dpm(struct pp_hwmgr *hwmgr) +{ + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + + /* disable general power management */ + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, GENERAL_PWRMGT, + GLOBAL_PWRMGT_EN, 0); + /* disable sclk deep sleep */ + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, SCLK_PWRMGT_CNTL, + DYNAMIC_PM_EN, 0); + + /* disable PCIE dpm */ + if (!data->pcie_dpm_key_disabled) { + PP_ASSERT_WITH_CODE( + (smum_send_msg_to_smc(hwmgr->smumgr, + PPSMC_MSG_PCIeDPM_Disable) == 0), + "Failed to disable pcie DPM during DPM Stop Function!", + return -1); + } + + if (polaris10_disable_sclk_mclk_dpm(hwmgr)) { + printk(KERN_ERR "Failed to disable Sclk DPM and Mclk DPM!"); + return -1; + } + + return 0; +} + static void polaris10_set_dpm_event_sources(struct pp_hwmgr *hwmgr, uint32_t sources) { bool protection; @@ -2395,6 +2557,23 @@ static int polaris10_enable_thermal_auto_throttle(struct pp_hwmgr *hwmgr) return polaris10_enable_auto_throttle_source(hwmgr, PHM_AutoThrottleSource_Thermal); } +static int polaris10_disable_auto_throttle_source(struct pp_hwmgr *hwmgr, + PHM_AutoThrottleSource source) +{ + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + + if (data->active_auto_throttle_sources & (1 << source)) { + data->active_auto_throttle_sources &= ~(1 << source); + polaris10_set_dpm_event_sources(hwmgr, data->active_auto_throttle_sources); + } + return 0; +} + +static int polaris10_disable_thermal_auto_throttle(struct pp_hwmgr *hwmgr) +{ + return polaris10_disable_auto_throttle_source(hwmgr, PHM_AutoThrottleSource_Thermal); +} + int polaris10_pcie_performance_request(struct pp_hwmgr *hwmgr) { struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); @@ -2471,6 +2650,8 @@ int polaris10_enable_dpm_tasks(struct pp_hwmgr *hwmgr) PP_ASSERT_WITH_CODE((0 == tmp_result), "Failed to enable VR hot GPIO interrupt!", result = tmp_result); + smum_send_msg_to_smc(hwmgr->smumgr, (PPSMC_Msg)PPSMC_HasDisplay); + tmp_result = polaris10_enable_sclk_control(hwmgr); PP_ASSERT_WITH_CODE((0 == tmp_result), "Failed to enable SCLK control!", result = tmp_result); @@ -2487,6 +2668,10 @@ int polaris10_enable_dpm_tasks(struct pp_hwmgr *hwmgr) PP_ASSERT_WITH_CODE((0 == tmp_result), "Failed to enable deep sleep master switch!", result = tmp_result); + tmp_result = polaris10_enable_didt_config(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to enable deep sleep master switch!", result = tmp_result); + tmp_result = polaris10_start_dpm(hwmgr); PP_ASSERT_WITH_CODE((0 == tmp_result), "Failed to start DPM!", result = tmp_result); @@ -2516,8 +2701,60 @@ int polaris10_enable_dpm_tasks(struct pp_hwmgr *hwmgr) int polaris10_disable_dpm_tasks(struct pp_hwmgr *hwmgr) { + int tmp_result, result = 0; - return 0; + tmp_result = (polaris10_is_dpm_running(hwmgr)) ? 0 : -1; + PP_ASSERT_WITH_CODE(tmp_result == 0, + "DPM is not running right now, no need to disable DPM!", + return 0); + + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_ThermalController)) + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, + GENERAL_PWRMGT, THERMAL_PROTECTION_DIS, 1); + + tmp_result = polaris10_disable_power_containment(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to disable power containment!", result = tmp_result); + + tmp_result = polaris10_disable_smc_cac(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to disable SMC CAC!", result = tmp_result); + + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, + CG_SPLL_SPREAD_SPECTRUM, SSEN, 0); + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, + GENERAL_PWRMGT, DYN_SPREAD_SPECTRUM_EN, 0); + + tmp_result = polaris10_disable_thermal_auto_throttle(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to disable thermal auto throttle!", result = tmp_result); + + tmp_result = polaris10_stop_dpm(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to stop DPM!", result = tmp_result); + + tmp_result = polaris10_disable_deep_sleep_master_switch(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to disable deep sleep master switch!", result = tmp_result); + + tmp_result = polaris10_disable_ulv(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to disable ULV!", result = tmp_result); + + tmp_result = polaris10_clear_voting_clients(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to clear voting clients!", result = tmp_result); + + tmp_result = polaris10_reset_to_default(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to reset to default!", result = tmp_result); + + tmp_result = polaris10_force_switch_to_arbf0(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to force to switch arbf0!", result = tmp_result); + + return result; } int polaris10_reset_asic_tasks(struct pp_hwmgr *hwmgr) @@ -2528,13 +2765,6 @@ int polaris10_reset_asic_tasks(struct pp_hwmgr *hwmgr) int polaris10_hwmgr_backend_fini(struct pp_hwmgr *hwmgr) { - struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); - - if (data->soft_pp_table) { - kfree(data->soft_pp_table); - data->soft_pp_table = NULL; - } - return phm_hwmgr_backend_fini(hwmgr); } @@ -2581,17 +2811,22 @@ int polaris10_set_features_platform_caps(struct pp_hwmgr *hwmgr) PHM_PlatformCaps_DynamicUVDState); /* power tune caps Assume disabled */ - phm_cap_unset(hwmgr->platform_descriptor.platformCaps, + phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SQRamping); - phm_cap_unset(hwmgr->platform_descriptor.platformCaps, + phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_DBRamping); - phm_cap_unset(hwmgr->platform_descriptor.platformCaps, + phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TDRamping); - phm_cap_unset(hwmgr->platform_descriptor.platformCaps, + phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TCPRamping); - phm_cap_set(hwmgr->platform_descriptor.platformCaps, - PHM_PlatformCaps_PowerContainment); + if (hwmgr->powercontainment_enabled) + phm_cap_set(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_PowerContainment); + else + phm_cap_unset(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_PowerContainment); + phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_CAC); @@ -2606,6 +2841,7 @@ int polaris10_set_features_platform_caps(struct pp_hwmgr *hwmgr) phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_FanSpeedInTableIsRPM); + if (hwmgr->chip_id == CHIP_POLARIS11) phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SPLLShutdownSupport); @@ -2638,7 +2874,7 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr) { struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); uint16_t vv_id; - uint16_t vddc = 0; + uint32_t vddc = 0; uint16_t i, j; uint32_t sclk = 0; struct phm_ppt_v1_information *table_info = @@ -2662,15 +2898,16 @@ static int polaris10_get_evv_voltages(struct pp_hwmgr *hwmgr) } } + if (atomctrl_get_voltage_evv_on_sclk_ai(hwmgr, + VOLTAGE_TYPE_VDDC, + sclk, vv_id, &vddc) != 0) { + printk(KERN_WARNING "failed to retrieving EVV voltage!\n"); + continue; + } - PP_ASSERT_WITH_CODE(0 == atomctrl_get_voltage_evv_on_sclk_ai(hwmgr, - VOLTAGE_TYPE_VDDC, sclk, vv_id, &vddc), - "Error retrieving EVV voltage value!", - continue); - - - /* need to make sure vddc is less than 2v or else, it could burn the ASIC. */ - PP_ASSERT_WITH_CODE((vddc < 2000 && vddc != 0), + /* need to make sure vddc is less than 2v or else, it could burn the ASIC. + * real voltage level in unit of 0.01mv */ + PP_ASSERT_WITH_CODE((vddc < 200000 && vddc != 0), "Invalid VDDC value", result = -EINVAL;); /* the voltage should not be zero nor equal to leakage ID */ @@ -2896,15 +3133,46 @@ static int polaris10_set_private_data_based_on_pptable(struct pp_hwmgr *hwmgr) return 0; } +int polaris10_patch_voltage_workaround(struct pp_hwmgr *hwmgr) +{ + struct phm_ppt_v1_information *table_info = + (struct phm_ppt_v1_information *)(hwmgr->pptable); + struct phm_ppt_v1_clock_voltage_dependency_table *dep_mclk_table = + table_info->vdd_dep_on_mclk; + struct phm_ppt_v1_voltage_lookup_table *lookup_table = + table_info->vddc_lookup_table; + uint32_t i; + + if (hwmgr->chip_id == CHIP_POLARIS10 && hwmgr->hw_revision == 0xC7) { + if (lookup_table->entries[dep_mclk_table->entries[dep_mclk_table->count-1].vddInd].us_vdd >= 1000) + return 0; + + for (i = 0; i < lookup_table->count; i++) { + if (lookup_table->entries[i].us_vdd < 0xff01 && lookup_table->entries[i].us_vdd >= 1000) { + dep_mclk_table->entries[dep_mclk_table->count-1].vddInd = (uint8_t) i; + return 0; + } + } + } + return 0; +} + + int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr) { - struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + struct polaris10_hwmgr *data; struct pp_atomctrl_gpio_pin_assignment gpio_pin_assignment; uint32_t temp_reg; int result; struct phm_ppt_v1_information *table_info = (struct phm_ppt_v1_information *)(hwmgr->pptable); + data = kzalloc(sizeof(struct polaris10_hwmgr), GFP_KERNEL); + if (data == NULL) + return -ENOMEM; + + hwmgr->backend = data; + data->dll_default_on = false; data->sram_end = SMC_RAM_END; data->mclk_dpm0_activity_target = 0xa; @@ -2938,6 +3206,11 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr) data->vddci_control = POLARIS10_VOLTAGE_CONTROL_NONE; data->mvdd_control = POLARIS10_VOLTAGE_CONTROL_NONE; + data->enable_tdc_limit_feature = true; + data->enable_pkg_pwr_tracking_feature = true; + data->force_pcie_gen = PP_PCIEGenInvalid; + data->mclk_stutter_mode_threshold = 40000; + if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr, VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2)) data->voltage_control = POLARIS10_VOLTAGE_CONTROL_BY_SVID2; @@ -2962,8 +3235,13 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr) data->vddci_control = POLARIS10_VOLTAGE_CONTROL_BY_SVID2; } + if (table_info->cac_dtp_table->usClockStretchAmount != 0) + phm_cap_set(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_ClockStretcher); + polaris10_set_features_platform_caps(hwmgr); + polaris10_patch_voltage_workaround(hwmgr); polaris10_init_dpm_defaults(hwmgr); /* Get leakage voltage based on leakage ID. */ @@ -2983,7 +3261,7 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr) if (0 == result) { struct cgs_system_info sys_info = {0}; - data->is_tlu_enabled = 0; + data->is_tlu_enabled = false; hwmgr->platform_descriptor.hardwareActivityPerformanceLevels = POLARIS10_MAX_HARDWARE_POWERLEVELS; @@ -3068,7 +3346,7 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr) sys_info.info_id = CGS_SYSTEM_INFO_PCIE_GEN_INFO; result = cgs_query_system_info(hwmgr->device, &sys_info); if (result) - data->pcie_gen_cap = 0x30007; + data->pcie_gen_cap = AMDGPU_DEFAULT_PCIE_GEN_MASK; else data->pcie_gen_cap = (uint32_t)sys_info.value; if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) @@ -3077,7 +3355,7 @@ int polaris10_hwmgr_backend_init(struct pp_hwmgr *hwmgr) sys_info.info_id = CGS_SYSTEM_INFO_PCIE_MLW; result = cgs_query_system_info(hwmgr->device, &sys_info); if (result) - data->pcie_lane_cap = 0x2f0000; + data->pcie_lane_cap = AMDGPU_DEFAULT_PCIE_MLW_MASK; else data->pcie_lane_cap = (uint32_t)sys_info.value; @@ -3366,6 +3644,7 @@ static int polaris10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_DisableMclkSwitchingForFrameLock); + disable_mclk_switching = (1 < info.display_count) || disable_mclk_switching_for_frame_lock; @@ -3520,10 +3799,11 @@ static int polaris10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr, ATOM_Tonga_State *state_entry = (ATOM_Tonga_State *)state; ATOM_Tonga_POWERPLAYTABLE *powerplay_table = (ATOM_Tonga_POWERPLAYTABLE *)pp_table; - ATOM_Tonga_SCLK_Dependency_Table *sclk_dep_table = - (ATOM_Tonga_SCLK_Dependency_Table *) + PPTable_Generic_SubTable_Header *sclk_dep_table = + (PPTable_Generic_SubTable_Header *) (((unsigned long)powerplay_table) + le16_to_cpu(powerplay_table->usSclkDependencyTableOffset)); + ATOM_Tonga_MCLK_Dependency_Table *mclk_dep_table = (ATOM_Tonga_MCLK_Dependency_Table *) (((unsigned long)powerplay_table) + @@ -3575,7 +3855,11 @@ static int polaris10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr, /* Performance levels are arranged from low to high. */ performance_level->memory_clock = mclk_dep_table->entries [state_entry->ucMemoryClockIndexLow].ulMclk; - performance_level->engine_clock = sclk_dep_table->entries + if (sclk_dep_table->ucRevId == 0) + performance_level->engine_clock = ((ATOM_Tonga_SCLK_Dependency_Table *)sclk_dep_table)->entries + [state_entry->ucEngineClockIndexLow].ulSclk; + else if (sclk_dep_table->ucRevId == 1) + performance_level->engine_clock = ((ATOM_Polaris_SCLK_Dependency_Table *)sclk_dep_table)->entries [state_entry->ucEngineClockIndexLow].ulSclk; performance_level->pcie_gen = get_pcie_gen_support(data->pcie_gen_cap, state_entry->ucPCIEGenLow); @@ -3586,8 +3870,14 @@ static int polaris10_get_pp_table_entry_callback_func(struct pp_hwmgr *hwmgr, [polaris10_power_state->performance_level_count++]); performance_level->memory_clock = mclk_dep_table->entries [state_entry->ucMemoryClockIndexHigh].ulMclk; - performance_level->engine_clock = sclk_dep_table->entries + + if (sclk_dep_table->ucRevId == 0) + performance_level->engine_clock = ((ATOM_Tonga_SCLK_Dependency_Table *)sclk_dep_table)->entries [state_entry->ucEngineClockIndexHigh].ulSclk; + else if (sclk_dep_table->ucRevId == 1) + performance_level->engine_clock = ((ATOM_Polaris_SCLK_Dependency_Table *)sclk_dep_table)->entries + [state_entry->ucEngineClockIndexHigh].ulSclk; + performance_level->pcie_gen = get_pcie_gen_support(data->pcie_gen_cap, state_entry->ucPCIEGenHigh); performance_level->pcie_lane = get_pcie_lane_support(data->pcie_lane_cap, @@ -3645,7 +3935,6 @@ static int polaris10_get_pp_table_entry(struct pp_hwmgr *hwmgr, switch (state->classification.ui_label) { case PP_StateUILabel_Performance: data->use_pcie_performance_levels = true; - for (i = 0; i < ps->performance_level_count; i++) { if (data->pcie_gen_performance.max < ps->performance_levels[i].pcie_gen) @@ -3661,7 +3950,6 @@ static int polaris10_get_pp_table_entry(struct pp_hwmgr *hwmgr, ps->performance_levels[i].pcie_lane) data->pcie_lane_performance.max = ps->performance_levels[i].pcie_lane; - if (data->pcie_lane_performance.min > ps->performance_levels[i].pcie_lane) data->pcie_lane_performance.min = @@ -3861,8 +4149,8 @@ static int polaris10_freeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) if ((0 == data->sclk_dpm_key_disabled) && (data->need_update_smu7_dpm_table & (DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK))) { - PP_ASSERT_WITH_CODE(true == polaris10_is_dpm_running(hwmgr), - "Trying to freeze SCLK DPM when DPM is disabled", + PP_ASSERT_WITH_CODE(polaris10_is_dpm_running(hwmgr), + "Trying to freeze SCLK DPM when DPM is disabled", ); PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_SCLKDPM_FreezeLevel), @@ -3873,8 +4161,8 @@ static int polaris10_freeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) if ((0 == data->mclk_dpm_key_disabled) && (data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_MCLK)) { - PP_ASSERT_WITH_CODE(true == polaris10_is_dpm_running(hwmgr), - "Trying to freeze MCLK DPM when DPM is disabled", + PP_ASSERT_WITH_CODE(polaris10_is_dpm_running(hwmgr), + "Trying to freeze MCLK DPM when DPM is disabled", ); PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_MCLKDPM_FreezeLevel), @@ -4034,7 +4322,6 @@ static int polaris10_trim_single_dpm_states(struct pp_hwmgr *hwmgr, static int polaris10_trim_dpm_states(struct pp_hwmgr *hwmgr, const struct polaris10_power_state *polaris10_ps) { - int result = 0; struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); uint32_t high_limit_count; @@ -4054,7 +4341,7 @@ static int polaris10_trim_dpm_states(struct pp_hwmgr *hwmgr, polaris10_ps->performance_levels[0].memory_clock, polaris10_ps->performance_levels[high_limit_count].memory_clock); - return result; + return 0; } static int polaris10_generate_dpm_level_enable_mask( @@ -4137,25 +4424,20 @@ int polaris10_update_uvd_dpm(struct pp_hwmgr *hwmgr, bool bgate) return polaris10_enable_disable_uvd_dpm(hwmgr, !bgate); } -static int polaris10_update_vce_dpm(struct pp_hwmgr *hwmgr, const void *input) +int polaris10_update_vce_dpm(struct pp_hwmgr *hwmgr, bool bgate) { - const struct phm_set_power_state_input *states = - (const struct phm_set_power_state_input *)input; struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); - const struct polaris10_power_state *polaris10_nps = - cast_const_phw_polaris10_power_state(states->pnew_state); - const struct polaris10_power_state *polaris10_cps = - cast_const_phw_polaris10_power_state(states->pcurrent_state); - uint32_t mm_boot_level_offset, mm_boot_level_value; struct phm_ppt_v1_information *table_info = (struct phm_ppt_v1_information *)(hwmgr->pptable); - if (polaris10_nps->vce_clks.evclk > 0 && - (polaris10_cps == NULL || polaris10_cps->vce_clks.evclk == 0)) { - - data->smc_state_table.VceBootLevel = + if (!bgate) { + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_StablePState)) + data->smc_state_table.VceBootLevel = (uint8_t) (table_info->mm_dep_table->count - 1); + else + data->smc_state_table.VceBootLevel = 0; mm_boot_level_offset = data->dpm_table_start + offsetof(SMU74_Discrete_DpmTable, VceBootLevel); @@ -4168,18 +4450,14 @@ static int polaris10_update_vce_dpm(struct pp_hwmgr *hwmgr, const void *input) cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, mm_boot_level_offset, mm_boot_level_value); - if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_StablePState)) { + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_StablePState)) smum_send_msg_to_smc_with_parameter(hwmgr->smumgr, PPSMC_MSG_VCEDPM_SetEnabledMask, (uint32_t)1 << data->smc_state_table.VceBootLevel); - - polaris10_enable_disable_vce_dpm(hwmgr, true); - } else if (polaris10_nps->vce_clks.evclk == 0 && - polaris10_cps != NULL && - polaris10_cps->vce_clks.evclk > 0) - polaris10_enable_disable_vce_dpm(hwmgr, false); } + polaris10_enable_disable_vce_dpm(hwmgr, !bgate); + return 0; } @@ -4187,12 +4465,9 @@ int polaris10_update_samu_dpm(struct pp_hwmgr *hwmgr, bool bgate) { struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); uint32_t mm_boot_level_offset, mm_boot_level_value; - struct phm_ppt_v1_information *table_info = - (struct phm_ppt_v1_information *)(hwmgr->pptable); if (!bgate) { - data->smc_state_table.SamuBootLevel = - (uint8_t) (table_info->mm_dep_table->count - 1); + data->smc_state_table.SamuBootLevel = 0; mm_boot_level_offset = data->dpm_table_start + offsetof(SMU74_Discrete_DpmTable, SamuBootLevel); mm_boot_level_offset /= 4; @@ -4267,8 +4542,8 @@ static int polaris10_unfreeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) (data->need_update_smu7_dpm_table & (DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK))) { - PP_ASSERT_WITH_CODE(true == polaris10_is_dpm_running(hwmgr), - "Trying to Unfreeze SCLK DPM when DPM is disabled", + PP_ASSERT_WITH_CODE(polaris10_is_dpm_running(hwmgr), + "Trying to Unfreeze SCLK DPM when DPM is disabled", ); PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_SCLKDPM_UnfreezeLevel), @@ -4279,8 +4554,8 @@ static int polaris10_unfreeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) if ((0 == data->mclk_dpm_key_disabled) && (data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_MCLK)) { - PP_ASSERT_WITH_CODE(true == polaris10_is_dpm_running(hwmgr), - "Trying to Unfreeze MCLK DPM when DPM is disabled", + PP_ASSERT_WITH_CODE(polaris10_is_dpm_running(hwmgr), + "Trying to Unfreeze MCLK DPM when DPM is disabled", ); PP_ASSERT_WITH_CODE(0 == smum_send_msg_to_smc(hwmgr->smumgr, PPSMC_MSG_SCLKDPM_UnfreezeLevel), @@ -4327,6 +4602,17 @@ static int polaris10_notify_link_speed_change_after_state_change( return 0; } +static int polaris10_notify_smc_display(struct pp_hwmgr *hwmgr) +{ + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + + smum_send_msg_to_smc_with_parameter(hwmgr->smumgr, + (PPSMC_Msg)PPSMC_MSG_SetVBITimeout, data->frame_time_x2); + return (smum_send_msg_to_smc(hwmgr->smumgr, (PPSMC_Msg)PPSMC_HasDisplay) == 0) ? 0 : -EINVAL; +} + + + static int polaris10_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *input) { int tmp_result, result = 0; @@ -4360,11 +4646,6 @@ static int polaris10_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *i "Failed to generate DPM level enabled mask!", result = tmp_result); - tmp_result = polaris10_update_vce_dpm(hwmgr, input); - PP_ASSERT_WITH_CODE((0 == tmp_result), - "Failed to update VCE DPM!", - result = tmp_result); - tmp_result = polaris10_update_sclk_threshold(hwmgr); PP_ASSERT_WITH_CODE((0 == tmp_result), "Failed to update SCLK threshold!", @@ -4375,6 +4656,11 @@ static int polaris10_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *i "Failed to program memory timing parameters!", result = tmp_result); + tmp_result = polaris10_notify_smc_display(hwmgr); + PP_ASSERT_WITH_CODE((0 == tmp_result), + "Failed to notify smc display settings!", + result = tmp_result); + tmp_result = polaris10_unfreeze_sclk_mclk_dpm(hwmgr); PP_ASSERT_WITH_CODE((0 == tmp_result), "Failed to unfreeze SCLK MCLK DPM!", @@ -4409,6 +4695,7 @@ static int polaris10_set_max_fan_pwm_output(struct pp_hwmgr *hwmgr, uint16_t us_ PPSMC_MSG_SetFanPwmMax, us_max_fan_pwm); } + int polaris10_notify_smc_display_change(struct pp_hwmgr *hwmgr, bool has_display) { PPSMC_Msg msg = has_display ? (PPSMC_Msg)PPSMC_HasDisplay : (PPSMC_Msg)PPSMC_NoDisplay; @@ -4428,8 +4715,7 @@ int polaris10_notify_smc_display_config_after_ps_adjustment(struct pp_hwmgr *hwm if (num_active_displays > 1) /* to do && (pHwMgr->pPECI->displayConfiguration.bMultiMonitorInSync != TRUE)) */ polaris10_notify_smc_display_change(hwmgr, false); - else - polaris10_notify_smc_display_change(hwmgr, true); + return 0; } @@ -4470,6 +4756,8 @@ int polaris10_program_display_gap(struct pp_hwmgr *hwmgr) frame_time_in_us = 1000000 / refresh_rate; pre_vbi_time_in_us = frame_time_in_us - 200 - mode_info.vblank_time_us; + data->frame_time_x2 = frame_time_in_us * 2 / 100; + display_gap2 = pre_vbi_time_in_us * (ref_clock / 100); cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixCG_DISPLAY_GAP_CNTL2, display_gap2); @@ -4478,7 +4766,6 @@ int polaris10_program_display_gap(struct pp_hwmgr *hwmgr) cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, data->soft_regs_start + offsetof(SMU74_SoftRegisters, VBlankTimeout), (frame_time_in_us - pre_vbi_time_in_us)); - polaris10_notify_smc_display_change(hwmgr, num_active_displays != 0); return 0; } @@ -4591,7 +4878,7 @@ int polaris10_upload_mc_firmware(struct pp_hwmgr *hwmgr) return 0; } - data->need_long_memory_training = true; + data->need_long_memory_training = false; /* * PPMCME_FirmwareDescriptorEntry *pfd = NULL; @@ -4721,42 +5008,6 @@ int polaris10_setup_asic_task(struct pp_hwmgr *hwmgr) return result; } -static int polaris10_get_pp_table(struct pp_hwmgr *hwmgr, char **table) -{ - struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); - - if (!data->soft_pp_table) { - data->soft_pp_table = kmemdup(hwmgr->soft_pp_table, - hwmgr->soft_pp_table_size, - GFP_KERNEL); - if (!data->soft_pp_table) - return -ENOMEM; - } - - *table = (char *)&data->soft_pp_table; - - return hwmgr->soft_pp_table_size; -} - -static int polaris10_set_pp_table(struct pp_hwmgr *hwmgr, const char *buf, size_t size) -{ - struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); - - if (!data->soft_pp_table) { - data->soft_pp_table = kzalloc(hwmgr->soft_pp_table_size, GFP_KERNEL); - if (!data->soft_pp_table) - return -ENOMEM; - } - - memcpy(data->soft_pp_table, buf, size); - - hwmgr->soft_pp_table = data->soft_pp_table; - - /* TODO: re-init powerplay to implement modified pptable */ - - return 0; -} - static int polaris10_force_clock_level(struct pp_hwmgr *hwmgr, enum pp_clock_type type, uint32_t mask) { @@ -4899,6 +5150,89 @@ static int polaris10_get_fan_control_mode(struct pp_hwmgr *hwmgr) CG_FDO_CTRL2, FDO_PWM_MODE); } +static int polaris10_get_sclk_od(struct pp_hwmgr *hwmgr) +{ + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + struct polaris10_single_dpm_table *sclk_table = &(data->dpm_table.sclk_table); + struct polaris10_single_dpm_table *golden_sclk_table = + &(data->golden_dpm_table.sclk_table); + int value; + + value = (sclk_table->dpm_levels[sclk_table->count - 1].value - + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value) * + 100 / + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value; + + return value; +} + +static int polaris10_set_sclk_od(struct pp_hwmgr *hwmgr, uint32_t value) +{ + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + struct polaris10_single_dpm_table *golden_sclk_table = + &(data->golden_dpm_table.sclk_table); + struct pp_power_state *ps; + struct polaris10_power_state *polaris10_ps; + + if (value > 20) + value = 20; + + ps = hwmgr->request_ps; + + if (ps == NULL) + return -EINVAL; + + polaris10_ps = cast_phw_polaris10_power_state(&ps->hardware); + + polaris10_ps->performance_levels[polaris10_ps->performance_level_count - 1].engine_clock = + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value * + value / 100 + + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value; + + return 0; +} + +static int polaris10_get_mclk_od(struct pp_hwmgr *hwmgr) +{ + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + struct polaris10_single_dpm_table *mclk_table = &(data->dpm_table.mclk_table); + struct polaris10_single_dpm_table *golden_mclk_table = + &(data->golden_dpm_table.mclk_table); + int value; + + value = (mclk_table->dpm_levels[mclk_table->count - 1].value - + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value) * + 100 / + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value; + + return value; +} + +static int polaris10_set_mclk_od(struct pp_hwmgr *hwmgr, uint32_t value) +{ + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + struct polaris10_single_dpm_table *golden_mclk_table = + &(data->golden_dpm_table.mclk_table); + struct pp_power_state *ps; + struct polaris10_power_state *polaris10_ps; + + if (value > 20) + value = 20; + + ps = hwmgr->request_ps; + + if (ps == NULL) + return -EINVAL; + + polaris10_ps = cast_phw_polaris10_power_state(&ps->hardware); + + polaris10_ps->performance_levels[polaris10_ps->performance_level_count - 1].memory_clock = + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value * + value / 100 + + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value; + + return 0; +} static const struct pp_hwmgr_func polaris10_hwmgr_funcs = { .backend_init = &polaris10_hwmgr_backend_init, .backend_fini = &polaris10_hwmgr_backend_fini, @@ -4937,22 +5271,17 @@ static const struct pp_hwmgr_func polaris10_hwmgr_funcs = { .check_states_equal = polaris10_check_states_equal, .set_fan_control_mode = polaris10_set_fan_control_mode, .get_fan_control_mode = polaris10_get_fan_control_mode, - .get_pp_table = polaris10_get_pp_table, - .set_pp_table = polaris10_set_pp_table, .force_clock_level = polaris10_force_clock_level, .print_clock_levels = polaris10_print_clock_levels, .enable_per_cu_power_gating = polaris10_phm_enable_per_cu_power_gating, + .get_sclk_od = polaris10_get_sclk_od, + .set_sclk_od = polaris10_set_sclk_od, + .get_mclk_od = polaris10_get_mclk_od, + .set_mclk_od = polaris10_set_mclk_od, }; int polaris10_hwmgr_init(struct pp_hwmgr *hwmgr) { - struct polaris10_hwmgr *data; - - data = kzalloc (sizeof(struct polaris10_hwmgr), GFP_KERNEL); - if (data == NULL) - return -ENOMEM; - - hwmgr->backend = data; hwmgr->hwmgr_func = &polaris10_hwmgr_funcs; hwmgr->pptable_func = &tonga_pptable_funcs; pp_polaris10_thermal_initialize(hwmgr); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h index beedf35cbfa6..33c33947e827 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h @@ -309,9 +309,9 @@ struct polaris10_hwmgr { uint32_t up_hyst; uint32_t disable_dpm_mask; bool apply_optimized_settings; - - /* soft pptable for re-uploading into smu */ - void *soft_pp_table; + uint32_t avfs_vdroop_override_setting; + bool apply_avfs_cks_off_voltage; + uint32_t frame_time_x2; }; /* To convert to Q8.8 format for firmware */ @@ -352,6 +352,6 @@ int polaris10_hwmgr_init(struct pp_hwmgr *hwmgr); int polaris10_update_uvd_dpm(struct pp_hwmgr *hwmgr, bool bgate); int polaris10_update_samu_dpm(struct pp_hwmgr *hwmgr, bool bgate); int polaris10_enable_disable_vce_dpm(struct pp_hwmgr *hwmgr, bool enable); - +int polaris10_update_vce_dpm(struct pp_hwmgr *hwmgr, bool bgate); #endif diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c index 0b99ab3ba0c5..b9cb240a135d 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.c @@ -28,10 +28,360 @@ #include "polaris10_smumgr.h" #include "smu74_discrete.h" #include "pp_debug.h" +#include "gca/gfx_8_0_d.h" +#include "gca/gfx_8_0_sh_mask.h" +#include "oss/oss_3_0_sh_mask.h" #define VOLTAGE_SCALE 4 #define POWERTUNE_DEFAULT_SET_MAX 1 +uint32_t DIDTBlock_Info = SQ_IR_MASK | TCP_IR_MASK | TD_PCC_MASK; + +struct polaris10_pt_config_reg GCCACConfig_Polaris10[] = { +/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- + * Offset Mask Shift Value Type + * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- + */ + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x00060013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x00860013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x01060013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x01860013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x02060013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x02860013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x03060013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x03860013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x04060013, POLARIS10_CONFIGREG_GC_CAC_IND }, + + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x000E0013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x008E0013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x010E0013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x018E0013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x020E0013, POLARIS10_CONFIGREG_GC_CAC_IND }, + + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x00100013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x00900013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x01100013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x01900013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x02100013, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x02900013, POLARIS10_CONFIGREG_GC_CAC_IND }, + + { 0xFFFFFFFF } +}; + +struct polaris10_pt_config_reg GCCACConfig_Polaris11[] = { +/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- + * Offset Mask Shift Value Type + * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- + */ + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x00060011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x00860011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x01060011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x01860011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x02060011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x02860011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x03060011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x03860011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x04060011, POLARIS10_CONFIGREG_GC_CAC_IND }, + + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x000E0011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x008E0011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x010E0011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x018E0011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x020E0011, POLARIS10_CONFIGREG_GC_CAC_IND }, + + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x00100011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x00900011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x01100011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x01900011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x02100011, POLARIS10_CONFIGREG_GC_CAC_IND }, + { ixGC_CAC_CNTL, 0xFFFFFFFF, 0, 0x02900011, POLARIS10_CONFIGREG_GC_CAC_IND }, + + { 0xFFFFFFFF } +}; + +struct polaris10_pt_config_reg DIDTConfig_Polaris10[] = { +/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- + * Offset Mask Shift Value Type + * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- + */ + { ixDIDT_SQ_WEIGHT0_3, DIDT_SQ_WEIGHT0_3__WEIGHT0_MASK, DIDT_SQ_WEIGHT0_3__WEIGHT0__SHIFT, 0x0073, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT0_3, DIDT_SQ_WEIGHT0_3__WEIGHT1_MASK, DIDT_SQ_WEIGHT0_3__WEIGHT1__SHIFT, 0x00ab, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT0_3, DIDT_SQ_WEIGHT0_3__WEIGHT2_MASK, DIDT_SQ_WEIGHT0_3__WEIGHT2__SHIFT, 0x0084, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT0_3, DIDT_SQ_WEIGHT0_3__WEIGHT3_MASK, DIDT_SQ_WEIGHT0_3__WEIGHT3__SHIFT, 0x005a, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_WEIGHT4_7, DIDT_SQ_WEIGHT4_7__WEIGHT4_MASK, DIDT_SQ_WEIGHT4_7__WEIGHT4__SHIFT, 0x0067, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT4_7, DIDT_SQ_WEIGHT4_7__WEIGHT5_MASK, DIDT_SQ_WEIGHT4_7__WEIGHT5__SHIFT, 0x0084, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT4_7, DIDT_SQ_WEIGHT4_7__WEIGHT6_MASK, DIDT_SQ_WEIGHT4_7__WEIGHT6__SHIFT, 0x0027, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT4_7, DIDT_SQ_WEIGHT4_7__WEIGHT7_MASK, DIDT_SQ_WEIGHT4_7__WEIGHT7__SHIFT, 0x0046, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_WEIGHT8_11, DIDT_SQ_WEIGHT8_11__WEIGHT8_MASK, DIDT_SQ_WEIGHT8_11__WEIGHT8__SHIFT, 0x00aa, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT8_11, DIDT_SQ_WEIGHT8_11__WEIGHT9_MASK, DIDT_SQ_WEIGHT8_11__WEIGHT9__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT8_11, DIDT_SQ_WEIGHT8_11__WEIGHT10_MASK, DIDT_SQ_WEIGHT8_11__WEIGHT10__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT8_11, DIDT_SQ_WEIGHT8_11__WEIGHT11_MASK, DIDT_SQ_WEIGHT8_11__WEIGHT11__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_CTRL1, DIDT_SQ_CTRL1__MIN_POWER_MASK, DIDT_SQ_CTRL1__MIN_POWER__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL1, DIDT_SQ_CTRL1__MAX_POWER_MASK, DIDT_SQ_CTRL1__MAX_POWER__SHIFT, 0xffff, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_CTRL_OCP, DIDT_SQ_CTRL_OCP__UNUSED_0_MASK, DIDT_SQ_CTRL_OCP__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL_OCP, DIDT_SQ_CTRL_OCP__OCP_MAX_POWER_MASK, DIDT_SQ_CTRL_OCP__OCP_MAX_POWER__SHIFT, 0xffff, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__MAX_POWER_DELTA_MASK, DIDT_SQ_CTRL2__MAX_POWER_DELTA__SHIFT, 0x3853, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__UNUSED_0_MASK, DIDT_SQ_CTRL2__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK, DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT, 0x005a, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__UNUSED_1_MASK, DIDT_SQ_CTRL2__UNUSED_1__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK, DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__UNUSED_2_MASK, DIDT_SQ_CTRL2__UNUSED_2__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK, DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK, DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x0ebb, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__UNUSED_0_MASK, DIDT_SQ_STALL_CTRL__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_TUNING_CTRL, DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK, DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_TUNING_CTRL, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT, 0x3853, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_TUNING_CTRL, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT, 0x3153, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_TUNING_CTRL, DIDT_SQ_TUNING_CTRL__UNUSED_0_MASK, DIDT_SQ_TUNING_CTRL__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_CTRL_EN_MASK, DIDT_SQ_CTRL0__DIDT_CTRL_EN__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__USE_REF_CLOCK_MASK, DIDT_SQ_CTRL0__USE_REF_CLOCK__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__PHASE_OFFSET_MASK, DIDT_SQ_CTRL0__PHASE_OFFSET__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_CTRL_RST_MASK, DIDT_SQ_CTRL0__DIDT_CTRL_RST__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK, DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK, DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT, 0x0010, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK, DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT, 0x0010, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__UNUSED_0_MASK, DIDT_SQ_CTRL0__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_WEIGHT0_3, DIDT_TD_WEIGHT0_3__WEIGHT0_MASK, DIDT_TD_WEIGHT0_3__WEIGHT0__SHIFT, 0x000a, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT0_3, DIDT_TD_WEIGHT0_3__WEIGHT1_MASK, DIDT_TD_WEIGHT0_3__WEIGHT1__SHIFT, 0x0010, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT0_3, DIDT_TD_WEIGHT0_3__WEIGHT2_MASK, DIDT_TD_WEIGHT0_3__WEIGHT2__SHIFT, 0x0017, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT0_3, DIDT_TD_WEIGHT0_3__WEIGHT3_MASK, DIDT_TD_WEIGHT0_3__WEIGHT3__SHIFT, 0x002f, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_WEIGHT4_7, DIDT_TD_WEIGHT4_7__WEIGHT4_MASK, DIDT_TD_WEIGHT4_7__WEIGHT4__SHIFT, 0x0046, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT4_7, DIDT_TD_WEIGHT4_7__WEIGHT5_MASK, DIDT_TD_WEIGHT4_7__WEIGHT5__SHIFT, 0x005d, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT4_7, DIDT_TD_WEIGHT4_7__WEIGHT6_MASK, DIDT_TD_WEIGHT4_7__WEIGHT6__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT4_7, DIDT_TD_WEIGHT4_7__WEIGHT7_MASK, DIDT_TD_WEIGHT4_7__WEIGHT7__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_CTRL1, DIDT_TD_CTRL1__MIN_POWER_MASK, DIDT_TD_CTRL1__MIN_POWER__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL1, DIDT_TD_CTRL1__MAX_POWER_MASK, DIDT_TD_CTRL1__MAX_POWER__SHIFT, 0xffff, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_CTRL_OCP, DIDT_TD_CTRL_OCP__UNUSED_0_MASK, DIDT_TD_CTRL_OCP__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL_OCP, DIDT_TD_CTRL_OCP__OCP_MAX_POWER_MASK, DIDT_TD_CTRL_OCP__OCP_MAX_POWER__SHIFT, 0x00ff, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__MAX_POWER_DELTA_MASK, DIDT_TD_CTRL2__MAX_POWER_DELTA__SHIFT, 0x3fff, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__UNUSED_0_MASK, DIDT_TD_CTRL2__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK, DIDT_TD_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT, 0x000f, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__UNUSED_1_MASK, DIDT_TD_CTRL2__UNUSED_1__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK, DIDT_TD_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__UNUSED_2_MASK, DIDT_TD_CTRL2__UNUSED_2__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK, DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK, DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x01aa, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__UNUSED_0_MASK, DIDT_TD_STALL_CTRL__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_TUNING_CTRL, DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK, DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_TUNING_CTRL, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT, 0x0dde, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_TUNING_CTRL, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT, 0x0dde, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_TUNING_CTRL, DIDT_TD_TUNING_CTRL__UNUSED_0_MASK, DIDT_TD_TUNING_CTRL__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_CTRL_EN_MASK, DIDT_TD_CTRL0__DIDT_CTRL_EN__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__USE_REF_CLOCK_MASK, DIDT_TD_CTRL0__USE_REF_CLOCK__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__PHASE_OFFSET_MASK, DIDT_TD_CTRL0__PHASE_OFFSET__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_CTRL_RST_MASK, DIDT_TD_CTRL0__DIDT_CTRL_RST__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK, DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK, DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT, 0x0009, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK, DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT, 0x0009, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__UNUSED_0_MASK, DIDT_TD_CTRL0__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_WEIGHT0_3, DIDT_TCP_WEIGHT0_3__WEIGHT0_MASK, DIDT_TCP_WEIGHT0_3__WEIGHT0__SHIFT, 0x0004, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT0_3, DIDT_TCP_WEIGHT0_3__WEIGHT1_MASK, DIDT_TCP_WEIGHT0_3__WEIGHT1__SHIFT, 0x0037, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT0_3, DIDT_TCP_WEIGHT0_3__WEIGHT2_MASK, DIDT_TCP_WEIGHT0_3__WEIGHT2__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT0_3, DIDT_TCP_WEIGHT0_3__WEIGHT3_MASK, DIDT_TCP_WEIGHT0_3__WEIGHT3__SHIFT, 0x00ff, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_WEIGHT4_7, DIDT_TCP_WEIGHT4_7__WEIGHT4_MASK, DIDT_TCP_WEIGHT4_7__WEIGHT4__SHIFT, 0x0054, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT4_7, DIDT_TCP_WEIGHT4_7__WEIGHT5_MASK, DIDT_TCP_WEIGHT4_7__WEIGHT5__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT4_7, DIDT_TCP_WEIGHT4_7__WEIGHT6_MASK, DIDT_TCP_WEIGHT4_7__WEIGHT6__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT4_7, DIDT_TCP_WEIGHT4_7__WEIGHT7_MASK, DIDT_TCP_WEIGHT4_7__WEIGHT7__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_CTRL1, DIDT_TCP_CTRL1__MIN_POWER_MASK, DIDT_TCP_CTRL1__MIN_POWER__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL1, DIDT_TCP_CTRL1__MAX_POWER_MASK, DIDT_TCP_CTRL1__MAX_POWER__SHIFT, 0xffff, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_CTRL_OCP, DIDT_TCP_CTRL_OCP__UNUSED_0_MASK, DIDT_TCP_CTRL_OCP__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL_OCP, DIDT_TCP_CTRL_OCP__OCP_MAX_POWER_MASK, DIDT_TCP_CTRL_OCP__OCP_MAX_POWER__SHIFT, 0xffff, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__MAX_POWER_DELTA_MASK, DIDT_TCP_CTRL2__MAX_POWER_DELTA__SHIFT, 0x3dde, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__UNUSED_0_MASK, DIDT_TCP_CTRL2__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK, DIDT_TCP_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT, 0x0032, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__UNUSED_1_MASK, DIDT_TCP_CTRL2__UNUSED_1__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK, DIDT_TCP_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__UNUSED_2_MASK, DIDT_TCP_CTRL2__UNUSED_2__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK, DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK, DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x01aa, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__UNUSED_0_MASK, DIDT_TCP_STALL_CTRL__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_TUNING_CTRL, DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK, DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_TUNING_CTRL, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT, 0x3dde, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_TUNING_CTRL, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT, 0x3dde, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_TUNING_CTRL, DIDT_TCP_TUNING_CTRL__UNUSED_0_MASK, DIDT_TCP_TUNING_CTRL__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_CTRL_EN_MASK, DIDT_TCP_CTRL0__DIDT_CTRL_EN__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__USE_REF_CLOCK_MASK, DIDT_TCP_CTRL0__USE_REF_CLOCK__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__PHASE_OFFSET_MASK, DIDT_TCP_CTRL0__PHASE_OFFSET__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_CTRL_RST_MASK, DIDT_TCP_CTRL0__DIDT_CTRL_RST__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK, DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK, DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT, 0x0010, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK, DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT, 0x0010, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__UNUSED_0_MASK, DIDT_TCP_CTRL0__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { 0xFFFFFFFF } +}; + +struct polaris10_pt_config_reg DIDTConfig_Polaris11[] = { +/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- + * Offset Mask Shift Value Type + * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- + */ + { ixDIDT_SQ_WEIGHT0_3, DIDT_SQ_WEIGHT0_3__WEIGHT0_MASK, DIDT_SQ_WEIGHT0_3__WEIGHT0__SHIFT, 0x0073, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT0_3, DIDT_SQ_WEIGHT0_3__WEIGHT1_MASK, DIDT_SQ_WEIGHT0_3__WEIGHT1__SHIFT, 0x00ab, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT0_3, DIDT_SQ_WEIGHT0_3__WEIGHT2_MASK, DIDT_SQ_WEIGHT0_3__WEIGHT2__SHIFT, 0x0084, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT0_3, DIDT_SQ_WEIGHT0_3__WEIGHT3_MASK, DIDT_SQ_WEIGHT0_3__WEIGHT3__SHIFT, 0x005a, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_WEIGHT4_7, DIDT_SQ_WEIGHT4_7__WEIGHT4_MASK, DIDT_SQ_WEIGHT4_7__WEIGHT4__SHIFT, 0x0067, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT4_7, DIDT_SQ_WEIGHT4_7__WEIGHT5_MASK, DIDT_SQ_WEIGHT4_7__WEIGHT5__SHIFT, 0x0084, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT4_7, DIDT_SQ_WEIGHT4_7__WEIGHT6_MASK, DIDT_SQ_WEIGHT4_7__WEIGHT6__SHIFT, 0x0027, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT4_7, DIDT_SQ_WEIGHT4_7__WEIGHT7_MASK, DIDT_SQ_WEIGHT4_7__WEIGHT7__SHIFT, 0x0046, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_WEIGHT8_11, DIDT_SQ_WEIGHT8_11__WEIGHT8_MASK, DIDT_SQ_WEIGHT8_11__WEIGHT8__SHIFT, 0x00aa, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT8_11, DIDT_SQ_WEIGHT8_11__WEIGHT9_MASK, DIDT_SQ_WEIGHT8_11__WEIGHT9__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT8_11, DIDT_SQ_WEIGHT8_11__WEIGHT10_MASK, DIDT_SQ_WEIGHT8_11__WEIGHT10__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT8_11, DIDT_SQ_WEIGHT8_11__WEIGHT11_MASK, DIDT_SQ_WEIGHT8_11__WEIGHT11__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_CTRL1, DIDT_SQ_CTRL1__MIN_POWER_MASK, DIDT_SQ_CTRL1__MIN_POWER__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL1, DIDT_SQ_CTRL1__MAX_POWER_MASK, DIDT_SQ_CTRL1__MAX_POWER__SHIFT, 0xffff, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_CTRL_OCP, DIDT_SQ_CTRL_OCP__UNUSED_0_MASK, DIDT_SQ_CTRL_OCP__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL_OCP, DIDT_SQ_CTRL_OCP__OCP_MAX_POWER_MASK, DIDT_SQ_CTRL_OCP__OCP_MAX_POWER__SHIFT, 0xffff, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__MAX_POWER_DELTA_MASK, DIDT_SQ_CTRL2__MAX_POWER_DELTA__SHIFT, 0x3853, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__UNUSED_0_MASK, DIDT_SQ_CTRL2__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK, DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT, 0x005a, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__UNUSED_1_MASK, DIDT_SQ_CTRL2__UNUSED_1__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK, DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__UNUSED_2_MASK, DIDT_SQ_CTRL2__UNUSED_2__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK, DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK, DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x0ebb, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__UNUSED_0_MASK, DIDT_SQ_STALL_CTRL__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_TUNING_CTRL, DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK, DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_TUNING_CTRL, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT, 0x3853, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_TUNING_CTRL, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT, 0x3153, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_TUNING_CTRL, DIDT_SQ_TUNING_CTRL__UNUSED_0_MASK, DIDT_SQ_TUNING_CTRL__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_CTRL_EN_MASK, DIDT_SQ_CTRL0__DIDT_CTRL_EN__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__USE_REF_CLOCK_MASK, DIDT_SQ_CTRL0__USE_REF_CLOCK__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__PHASE_OFFSET_MASK, DIDT_SQ_CTRL0__PHASE_OFFSET__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_CTRL_RST_MASK, DIDT_SQ_CTRL0__DIDT_CTRL_RST__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK, DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK, DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT, 0x0010, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK, DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT, 0x0010, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__UNUSED_0_MASK, DIDT_SQ_CTRL0__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_WEIGHT0_3, DIDT_TD_WEIGHT0_3__WEIGHT0_MASK, DIDT_TD_WEIGHT0_3__WEIGHT0__SHIFT, 0x000a, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT0_3, DIDT_TD_WEIGHT0_3__WEIGHT1_MASK, DIDT_TD_WEIGHT0_3__WEIGHT1__SHIFT, 0x0010, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT0_3, DIDT_TD_WEIGHT0_3__WEIGHT2_MASK, DIDT_TD_WEIGHT0_3__WEIGHT2__SHIFT, 0x0017, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT0_3, DIDT_TD_WEIGHT0_3__WEIGHT3_MASK, DIDT_TD_WEIGHT0_3__WEIGHT3__SHIFT, 0x002f, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_WEIGHT4_7, DIDT_TD_WEIGHT4_7__WEIGHT4_MASK, DIDT_TD_WEIGHT4_7__WEIGHT4__SHIFT, 0x0046, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT4_7, DIDT_TD_WEIGHT4_7__WEIGHT5_MASK, DIDT_TD_WEIGHT4_7__WEIGHT5__SHIFT, 0x005d, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT4_7, DIDT_TD_WEIGHT4_7__WEIGHT6_MASK, DIDT_TD_WEIGHT4_7__WEIGHT6__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT4_7, DIDT_TD_WEIGHT4_7__WEIGHT7_MASK, DIDT_TD_WEIGHT4_7__WEIGHT7__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_CTRL1, DIDT_TD_CTRL1__MIN_POWER_MASK, DIDT_TD_CTRL1__MIN_POWER__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL1, DIDT_TD_CTRL1__MAX_POWER_MASK, DIDT_TD_CTRL1__MAX_POWER__SHIFT, 0xffff, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_CTRL_OCP, DIDT_TD_CTRL_OCP__UNUSED_0_MASK, DIDT_TD_CTRL_OCP__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL_OCP, DIDT_TD_CTRL_OCP__OCP_MAX_POWER_MASK, DIDT_TD_CTRL_OCP__OCP_MAX_POWER__SHIFT, 0x00ff, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__MAX_POWER_DELTA_MASK, DIDT_TD_CTRL2__MAX_POWER_DELTA__SHIFT, 0x3fff, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__UNUSED_0_MASK, DIDT_TD_CTRL2__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK, DIDT_TD_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT, 0x000f, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__UNUSED_1_MASK, DIDT_TD_CTRL2__UNUSED_1__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK, DIDT_TD_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__UNUSED_2_MASK, DIDT_TD_CTRL2__UNUSED_2__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK, DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK, DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x01aa, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__UNUSED_0_MASK, DIDT_TD_STALL_CTRL__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_TUNING_CTRL, DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK, DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_TUNING_CTRL, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT, 0x0dde, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_TUNING_CTRL, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT, 0x0dde, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_TUNING_CTRL, DIDT_TD_TUNING_CTRL__UNUSED_0_MASK, DIDT_TD_TUNING_CTRL__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_CTRL_EN_MASK, DIDT_TD_CTRL0__DIDT_CTRL_EN__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__USE_REF_CLOCK_MASK, DIDT_TD_CTRL0__USE_REF_CLOCK__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__PHASE_OFFSET_MASK, DIDT_TD_CTRL0__PHASE_OFFSET__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_CTRL_RST_MASK, DIDT_TD_CTRL0__DIDT_CTRL_RST__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK, DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK, DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT, 0x0008, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK, DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT, 0x0008, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__UNUSED_0_MASK, DIDT_TD_CTRL0__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_WEIGHT0_3, DIDT_TCP_WEIGHT0_3__WEIGHT0_MASK, DIDT_TCP_WEIGHT0_3__WEIGHT0__SHIFT, 0x0004, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT0_3, DIDT_TCP_WEIGHT0_3__WEIGHT1_MASK, DIDT_TCP_WEIGHT0_3__WEIGHT1__SHIFT, 0x0037, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT0_3, DIDT_TCP_WEIGHT0_3__WEIGHT2_MASK, DIDT_TCP_WEIGHT0_3__WEIGHT2__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT0_3, DIDT_TCP_WEIGHT0_3__WEIGHT3_MASK, DIDT_TCP_WEIGHT0_3__WEIGHT3__SHIFT, 0x00ff, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_WEIGHT4_7, DIDT_TCP_WEIGHT4_7__WEIGHT4_MASK, DIDT_TCP_WEIGHT4_7__WEIGHT4__SHIFT, 0x0054, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT4_7, DIDT_TCP_WEIGHT4_7__WEIGHT5_MASK, DIDT_TCP_WEIGHT4_7__WEIGHT5__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT4_7, DIDT_TCP_WEIGHT4_7__WEIGHT6_MASK, DIDT_TCP_WEIGHT4_7__WEIGHT6__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT4_7, DIDT_TCP_WEIGHT4_7__WEIGHT7_MASK, DIDT_TCP_WEIGHT4_7__WEIGHT7__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_CTRL1, DIDT_TCP_CTRL1__MIN_POWER_MASK, DIDT_TCP_CTRL1__MIN_POWER__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL1, DIDT_TCP_CTRL1__MAX_POWER_MASK, DIDT_TCP_CTRL1__MAX_POWER__SHIFT, 0xffff, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_CTRL_OCP, DIDT_TCP_CTRL_OCP__UNUSED_0_MASK, DIDT_TCP_CTRL_OCP__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL_OCP, DIDT_TCP_CTRL_OCP__OCP_MAX_POWER_MASK, DIDT_TCP_CTRL_OCP__OCP_MAX_POWER__SHIFT, 0xffff, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__MAX_POWER_DELTA_MASK, DIDT_TCP_CTRL2__MAX_POWER_DELTA__SHIFT, 0x3dde, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__UNUSED_0_MASK, DIDT_TCP_CTRL2__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK, DIDT_TCP_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT, 0x0032, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__UNUSED_1_MASK, DIDT_TCP_CTRL2__UNUSED_1__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK, DIDT_TCP_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__UNUSED_2_MASK, DIDT_TCP_CTRL2__UNUSED_2__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK, DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK, DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x01aa, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__UNUSED_0_MASK, DIDT_TCP_STALL_CTRL__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_TUNING_CTRL, DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK, DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_TUNING_CTRL, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT, 0x3dde, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_TUNING_CTRL, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT, 0x3dde, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_TUNING_CTRL, DIDT_TCP_TUNING_CTRL__UNUSED_0_MASK, DIDT_TCP_TUNING_CTRL__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_CTRL_EN_MASK, DIDT_TCP_CTRL0__DIDT_CTRL_EN__SHIFT, 0x0001, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__USE_REF_CLOCK_MASK, DIDT_TCP_CTRL0__USE_REF_CLOCK__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__PHASE_OFFSET_MASK, DIDT_TCP_CTRL0__PHASE_OFFSET__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_CTRL_RST_MASK, DIDT_TCP_CTRL0__DIDT_CTRL_RST__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK, DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK, DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT, 0x0010, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK, DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT, 0x0010, POLARIS10_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__UNUSED_0_MASK, DIDT_TCP_CTRL0__UNUSED_0__SHIFT, 0x0000, POLARIS10_CONFIGREG_DIDT_IND }, + { 0xFFFFFFFF } +}; + static const struct polaris10_pt_defaults polaris10_power_tune_data_set_array[POWERTUNE_DEFAULT_SET_MAX] = { /* sviLoadLIneEn, SviLoadLineVddC, TDC_VDDC_ThrottleReleaseLimitPerc, TDC_MAWt, * TdcWaterfallCtl, DTEAmbientTempBase, DisplayCac, BAPM_TEMP_GRADIENT */ @@ -209,6 +559,187 @@ static int polaris10_min_max_vgnb_lpml_id_from_bapm_vddc(struct pp_hwmgr *hwmgr) return 0; } +static int polaris10_enable_didt(struct pp_hwmgr *hwmgr, const bool enable) +{ + + uint32_t en = enable ? 1 : 0; + int32_t result = 0; + uint32_t data; + + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SQRamping)) { + data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_SQ_CTRL0); + data &= ~DIDT_SQ_CTRL0__DIDT_CTRL_EN_MASK; + data |= ((en << DIDT_SQ_CTRL0__DIDT_CTRL_EN__SHIFT) & DIDT_SQ_CTRL0__DIDT_CTRL_EN_MASK); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_SQ_CTRL0, data); + DIDTBlock_Info &= ~SQ_Enable_MASK; + DIDTBlock_Info |= en << SQ_Enable_SHIFT; + } + + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_DBRamping)) { + data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_DB_CTRL0); + data &= ~DIDT_DB_CTRL0__DIDT_CTRL_EN_MASK; + data |= ((en << DIDT_DB_CTRL0__DIDT_CTRL_EN__SHIFT) & DIDT_DB_CTRL0__DIDT_CTRL_EN_MASK); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_DB_CTRL0, data); + DIDTBlock_Info &= ~DB_Enable_MASK; + DIDTBlock_Info |= en << DB_Enable_SHIFT; + } + + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TDRamping)) { + data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TD_CTRL0); + data &= ~DIDT_TD_CTRL0__DIDT_CTRL_EN_MASK; + data |= ((en << DIDT_TD_CTRL0__DIDT_CTRL_EN__SHIFT) & DIDT_TD_CTRL0__DIDT_CTRL_EN_MASK); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TD_CTRL0, data); + DIDTBlock_Info &= ~TD_Enable_MASK; + DIDTBlock_Info |= en << TD_Enable_SHIFT; + } + + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TCPRamping)) { + data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TCP_CTRL0); + data &= ~DIDT_TCP_CTRL0__DIDT_CTRL_EN_MASK; + data |= ((en << DIDT_TCP_CTRL0__DIDT_CTRL_EN__SHIFT) & DIDT_TCP_CTRL0__DIDT_CTRL_EN_MASK); + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, ixDIDT_TCP_CTRL0, data); + DIDTBlock_Info &= ~TCP_Enable_MASK; + DIDTBlock_Info |= en << TCP_Enable_SHIFT; + } + + if (enable) + result = smum_send_msg_to_smc_with_parameter(hwmgr->smumgr, PPSMC_MSG_Didt_Block_Function, DIDTBlock_Info); + + return result; +} + +static int polaris10_program_pt_config_registers(struct pp_hwmgr *hwmgr, + struct polaris10_pt_config_reg *cac_config_regs) +{ + struct polaris10_pt_config_reg *config_regs = cac_config_regs; + uint32_t cache = 0; + uint32_t data = 0; + + PP_ASSERT_WITH_CODE((config_regs != NULL), "Invalid config register table.", return -EINVAL); + + while (config_regs->offset != 0xFFFFFFFF) { + if (config_regs->type == POLARIS10_CONFIGREG_CACHE) + cache |= ((config_regs->value << config_regs->shift) & config_regs->mask); + else { + switch (config_regs->type) { + case POLARIS10_CONFIGREG_SMC_IND: + data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, config_regs->offset); + break; + + case POLARIS10_CONFIGREG_DIDT_IND: + data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__DIDT, config_regs->offset); + break; + + case POLARIS10_CONFIGREG_GC_CAC_IND: + data = cgs_read_ind_register(hwmgr->device, CGS_IND_REG_GC_CAC, config_regs->offset); + break; + + default: + data = cgs_read_register(hwmgr->device, config_regs->offset); + break; + } + + data &= ~config_regs->mask; + data |= ((config_regs->value << config_regs->shift) & config_regs->mask); + data |= cache; + + switch (config_regs->type) { + case POLARIS10_CONFIGREG_SMC_IND: + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, config_regs->offset, data); + break; + + case POLARIS10_CONFIGREG_DIDT_IND: + cgs_write_ind_register(hwmgr->device, CGS_IND_REG__DIDT, config_regs->offset, data); + break; + + case POLARIS10_CONFIGREG_GC_CAC_IND: + cgs_write_ind_register(hwmgr->device, CGS_IND_REG_GC_CAC, config_regs->offset, data); + break; + + default: + cgs_write_register(hwmgr->device, config_regs->offset, data); + break; + } + cache = 0; + } + + config_regs++; + } + + return 0; +} + +int polaris10_enable_didt_config(struct pp_hwmgr *hwmgr) +{ + int result; + uint32_t num_se = 0; + uint32_t count, value, value2; + struct cgs_system_info sys_info = {0}; + + sys_info.size = sizeof(struct cgs_system_info); + sys_info.info_id = CGS_SYSTEM_INFO_GFX_SE_INFO; + result = cgs_query_system_info(hwmgr->device, &sys_info); + + + if (result == 0) + num_se = sys_info.value; + + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SQRamping) || + phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_DBRamping) || + phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TDRamping) || + phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TCPRamping)) { + + /* TO DO Pre DIDT disable clock gating */ + value = 0; + value2 = cgs_read_register(hwmgr->device, mmGRBM_GFX_INDEX); + for (count = 0; count < num_se; count++) { + value = SYS_GRBM_GFX_INDEX_DATA__INSTANCE_BROADCAST_WRITES_MASK + | SYS_GRBM_GFX_INDEX_DATA__SH_BROADCAST_WRITES_MASK + | (count << SYS_GRBM_GFX_INDEX_DATA__SE_INDEX__SHIFT); + cgs_write_register(hwmgr->device, mmGRBM_GFX_INDEX, value); + + if (hwmgr->chip_id == CHIP_POLARIS10) { + result = polaris10_program_pt_config_registers(hwmgr, GCCACConfig_Polaris10); + PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result); + result = polaris10_program_pt_config_registers(hwmgr, DIDTConfig_Polaris10); + PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result); + } else if (hwmgr->chip_id == CHIP_POLARIS11) { + result = polaris10_program_pt_config_registers(hwmgr, GCCACConfig_Polaris11); + PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result); + result = polaris10_program_pt_config_registers(hwmgr, DIDTConfig_Polaris11); + PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result); + } + } + cgs_write_register(hwmgr->device, mmGRBM_GFX_INDEX, value2); + + result = polaris10_enable_didt(hwmgr, true); + PP_ASSERT_WITH_CODE((result == 0), "EnableDiDt failed.", return result); + + /* TO DO Post DIDT enable clock gating */ + } + + return 0; +} + +int polaris10_disable_didt_config(struct pp_hwmgr *hwmgr) +{ + int result; + + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SQRamping) || + phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_DBRamping) || + phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TDRamping) || + phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_TCPRamping)) { + /* TO DO Pre DIDT disable clock gating */ + + result = polaris10_enable_didt(hwmgr, false); + PP_ASSERT_WITH_CODE((result == 0), "Post DIDT enable clock gating failed.", return result); + /* TO DO Post DIDT enable clock gating */ + } + + return 0; +} + + static int polaris10_populate_bapm_vddc_base_leakage_sidd(struct pp_hwmgr *hwmgr) { struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); @@ -286,7 +817,7 @@ int polaris10_populate_pm_fuses(struct pp_hwmgr *hwmgr) if (polaris10_copy_bytes_to_smc(hwmgr->smumgr, pm_fuse_table_offset, (uint8_t *)&data->power_tune_table, - sizeof(struct SMU74_Discrete_PmFuses), data->sram_end)) + (sizeof(struct SMU74_Discrete_PmFuses) - 92), data->sram_end)) PP_ASSERT_WITH_CODE(false, "Attempt to download PmFuseTable Failed!", return -EINVAL); @@ -312,6 +843,23 @@ int polaris10_enable_smc_cac(struct pp_hwmgr *hwmgr) return result; } +int polaris10_disable_smc_cac(struct pp_hwmgr *hwmgr) +{ + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + int result = 0; + + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_CAC) && data->cac_enabled) { + int smc_result = smum_send_msg_to_smc(hwmgr->smumgr, + (uint16_t)(PPSMC_MSG_DisableCac)); + PP_ASSERT_WITH_CODE((smc_result == 0), + "Failed to disable CAC in SMC.", result = -1); + + data->cac_enabled = false; + } + return result; +} + int polaris10_set_power_limit(struct pp_hwmgr *hwmgr, uint32_t n) { struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); @@ -373,6 +921,48 @@ int polaris10_enable_power_containment(struct pp_hwmgr *hwmgr) return result; } +int polaris10_disable_power_containment(struct pp_hwmgr *hwmgr) +{ + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); + int result = 0; + + if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, + PHM_PlatformCaps_PowerContainment) && + data->power_containment_features) { + int smc_result; + + if (data->power_containment_features & + POWERCONTAINMENT_FEATURE_TDCLimit) { + smc_result = smum_send_msg_to_smc(hwmgr->smumgr, + (uint16_t)(PPSMC_MSG_TDCLimitDisable)); + PP_ASSERT_WITH_CODE((smc_result == 0), + "Failed to disable TDCLimit in SMC.", + result = smc_result); + } + + if (data->power_containment_features & + POWERCONTAINMENT_FEATURE_DTE) { + smc_result = smum_send_msg_to_smc(hwmgr->smumgr, + (uint16_t)(PPSMC_MSG_DisableDTE)); + PP_ASSERT_WITH_CODE((smc_result == 0), + "Failed to disable DTE in SMC.", + result = smc_result); + } + + if (data->power_containment_features & + POWERCONTAINMENT_FEATURE_PkgPwrLimit) { + smc_result = smum_send_msg_to_smc(hwmgr->smumgr, + (uint16_t)(PPSMC_MSG_PkgPwrLimitDisable)); + PP_ASSERT_WITH_CODE((smc_result == 0), + "Failed to disable PkgPwrTracking in SMC.", + result = smc_result); + } + data->power_containment_features = 0; + } + + return result; +} + int polaris10_power_control_set_level(struct pp_hwmgr *hwmgr) { struct phm_ppt_v1_information *table_info = diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.h b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.h index 68bc1cb6d40c..bc78e28f010d 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_powertune.h @@ -27,15 +27,37 @@ enum polaris10_pt_config_reg_type { POLARIS10_CONFIGREG_MMR = 0, POLARIS10_CONFIGREG_SMC_IND, POLARIS10_CONFIGREG_DIDT_IND, + POLARIS10_CONFIGREG_GC_CAC_IND, POLARIS10_CONFIGREG_CACHE, POLARIS10_CONFIGREG_MAX }; +#define DIDT_SQ_CTRL0__UNUSED_0_MASK 0xfffc0000 +#define DIDT_SQ_CTRL0__UNUSED_0__SHIFT 0x12 +#define DIDT_TD_CTRL0__UNUSED_0_MASK 0xfffc0000 +#define DIDT_TD_CTRL0__UNUSED_0__SHIFT 0x12 +#define DIDT_TCP_CTRL0__UNUSED_0_MASK 0xfffc0000 +#define DIDT_TCP_CTRL0__UNUSED_0__SHIFT 0x12 +#define DIDT_SQ_TUNING_CTRL__UNUSED_0_MASK 0xc0000000 +#define DIDT_SQ_TUNING_CTRL__UNUSED_0__SHIFT 0x0000001e +#define DIDT_TD_TUNING_CTRL__UNUSED_0_MASK 0xc0000000 +#define DIDT_TD_TUNING_CTRL__UNUSED_0__SHIFT 0x0000001e +#define DIDT_TCP_TUNING_CTRL__UNUSED_0_MASK 0xc0000000 +#define DIDT_TCP_TUNING_CTRL__UNUSED_0__SHIFT 0x0000001e + /* PowerContainment Features */ #define POWERCONTAINMENT_FEATURE_DTE 0x00000001 #define POWERCONTAINMENT_FEATURE_TDCLimit 0x00000002 #define POWERCONTAINMENT_FEATURE_PkgPwrLimit 0x00000004 +#define ixGC_CAC_CNTL 0x0000 +#define ixDIDT_SQ_STALL_CTRL 0x0004 +#define ixDIDT_SQ_TUNING_CTRL 0x0005 +#define ixDIDT_TD_STALL_CTRL 0x0044 +#define ixDIDT_TD_TUNING_CTRL 0x0045 +#define ixDIDT_TCP_STALL_CTRL 0x0064 +#define ixDIDT_TCP_TUNING_CTRL 0x0065 + struct polaris10_pt_config_reg { uint32_t offset; uint32_t mask; @@ -62,9 +84,11 @@ void polaris10_initialize_power_tune_defaults(struct pp_hwmgr *hwmgr); int polaris10_populate_bapm_parameters_in_dpm_table(struct pp_hwmgr *hwmgr); int polaris10_populate_pm_fuses(struct pp_hwmgr *hwmgr); int polaris10_enable_smc_cac(struct pp_hwmgr *hwmgr); +int polaris10_disable_smc_cac(struct pp_hwmgr *hwmgr); int polaris10_enable_power_containment(struct pp_hwmgr *hwmgr); +int polaris10_disable_power_containment(struct pp_hwmgr *hwmgr); int polaris10_set_power_limit(struct pp_hwmgr *hwmgr, uint32_t n); int polaris10_power_control_set_level(struct pp_hwmgr *hwmgr); - +int polaris10_enable_didt_config(struct pp_hwmgr *hwmgr); #endif /* POLARIS10_POWERTUNE_H */ diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c index aba167f7d167..b206632d4650 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris10_thermal.c @@ -625,10 +625,14 @@ static int tf_polaris10_thermal_avfs_enable(struct pp_hwmgr *hwmgr, int ret; struct pp_smumgr *smumgr = (struct pp_smumgr *)(hwmgr->smumgr); struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(smumgr->backend); + struct polaris10_hwmgr *data = (struct polaris10_hwmgr *)(hwmgr->backend); - if (smu_data->avfs.avfs_btc_status != AVFS_BTC_ENABLEAVFS) + if (smu_data->avfs.avfs_btc_status == AVFS_BTC_NOTSUPPORTED) return 0; + ret = smum_send_msg_to_smc_with_parameter(hwmgr->smumgr, + PPSMC_MSG_SetGBDroopSettings, data->avfs_vdroop_override_setting); + ret = (smum_send_msg_to_smc(smumgr, PPSMC_MSG_EnableAvfs) == 0) ? 0 : -1; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c index 58742e0d1492..1944d289f846 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/pp_acpi.c @@ -44,6 +44,20 @@ bool acpi_atcs_functions_supported(void *device, uint32_t index) return result == 0 ? (output_buf.function_bits & (1 << (index - 1))) != 0 : false; } +bool acpi_atcs_notify_pcie_device_ready(void *device) +{ + int32_t temp_buffer = 1; + + return cgs_call_acpi_method(device, CGS_ACPI_METHOD_ATCS, + ATCS_FUNCTION_PCIE_DEVICE_READY_NOTIFICATION, + &temp_buffer, + NULL, + 0, + sizeof(temp_buffer), + 0); +} + + int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise) { struct atcs_pref_req_input atcs_input; @@ -52,7 +66,7 @@ int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise) int result; struct cgs_system_info info = {0}; - if (!acpi_atcs_functions_supported(device, ATCS_FUNCTION_PCIE_PERFORMANCE_REQUEST)) + if (acpi_atcs_notify_pcie_device_ready(device)) return -EINVAL; info.size = sizeof(struct cgs_system_info); @@ -77,7 +91,7 @@ int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise) ATCS_FUNCTION_PCIE_PERFORMANCE_REQUEST, &atcs_input, &atcs_output, - 0, + 1, sizeof(atcs_input), sizeof(atcs_output)); if (result != 0) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c index da9f5f1b6dc2..26f3e30d0fef 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c @@ -179,13 +179,12 @@ int atomctrl_set_engine_dram_timings_rv770( /* They are both in 10KHz Units. */ engine_clock_parameters.ulTargetEngineClock = - (uint32_t) engine_clock & SET_CLOCK_FREQ_MASK; - engine_clock_parameters.ulTargetEngineClock |= - (COMPUTE_ENGINE_PLL_PARAM << 24); + cpu_to_le32((engine_clock & SET_CLOCK_FREQ_MASK) | + ((COMPUTE_ENGINE_PLL_PARAM << 24))); /* in 10 khz units.*/ engine_clock_parameters.sReserved.ulClock = - (uint32_t) memory_clock & SET_CLOCK_FREQ_MASK; + cpu_to_le32(memory_clock & SET_CLOCK_FREQ_MASK); return cgs_atom_exec_cmd_table(hwmgr->device, GetIndexIntoMasterTable(COMMAND, DynamicMemorySettings), &engine_clock_parameters); @@ -252,7 +251,7 @@ int atomctrl_get_memory_pll_dividers_si( COMPUTE_MEMORY_CLOCK_PARAM_PARAMETERS_V2_1 mpll_parameters; int result; - mpll_parameters.ulClock = (uint32_t) clock_value; + mpll_parameters.ulClock = cpu_to_le32(clock_value); mpll_parameters.ucInputFlag = (uint8_t)((strobe_mode) ? 1 : 0); result = cgs_atom_exec_cmd_table @@ -262,9 +261,9 @@ int atomctrl_get_memory_pll_dividers_si( if (0 == result) { mpll_param->mpll_fb_divider.clk_frac = - mpll_parameters.ulFbDiv.usFbDivFrac; + le16_to_cpu(mpll_parameters.ulFbDiv.usFbDivFrac); mpll_param->mpll_fb_divider.cl_kf = - mpll_parameters.ulFbDiv.usFbDiv; + le16_to_cpu(mpll_parameters.ulFbDiv.usFbDiv); mpll_param->mpll_post_divider = (uint32_t)mpll_parameters.ucPostDiv; mpll_param->vco_mode = @@ -300,7 +299,7 @@ int atomctrl_get_memory_pll_dividers_vi(struct pp_hwmgr *hwmgr, COMPUTE_MEMORY_CLOCK_PARAM_PARAMETERS_V2_2 mpll_parameters; int result; - mpll_parameters.ulClock.ulClock = (uint32_t)clock_value; + mpll_parameters.ulClock.ulClock = cpu_to_le32(clock_value); result = cgs_atom_exec_cmd_table(hwmgr->device, GetIndexIntoMasterTable(COMMAND, ComputeMemoryClockParam), @@ -320,7 +319,7 @@ int atomctrl_get_engine_pll_dividers_kong(struct pp_hwmgr *hwmgr, COMPUTE_MEMORY_ENGINE_PLL_PARAMETERS_V4 pll_parameters; int result; - pll_parameters.ulClock = clock_value; + pll_parameters.ulClock = cpu_to_le32(clock_value); result = cgs_atom_exec_cmd_table (hwmgr->device, @@ -329,7 +328,7 @@ int atomctrl_get_engine_pll_dividers_kong(struct pp_hwmgr *hwmgr, if (0 == result) { dividers->pll_post_divider = pll_parameters.ucPostDiv; - dividers->real_clock = pll_parameters.ulClock; + dividers->real_clock = le32_to_cpu(pll_parameters.ulClock); } return result; @@ -343,7 +342,7 @@ int atomctrl_get_engine_pll_dividers_vi( COMPUTE_GPU_CLOCK_OUTPUT_PARAMETERS_V1_6 pll_patameters; int result; - pll_patameters.ulClock.ulClock = clock_value; + pll_patameters.ulClock.ulClock = cpu_to_le32(clock_value); pll_patameters.ulClock.ucPostDiv = COMPUTE_GPUCLK_INPUT_FLAG_SCLK; result = cgs_atom_exec_cmd_table @@ -355,12 +354,12 @@ int atomctrl_get_engine_pll_dividers_vi( dividers->pll_post_divider = pll_patameters.ulClock.ucPostDiv; dividers->real_clock = - pll_patameters.ulClock.ulClock; + le32_to_cpu(pll_patameters.ulClock.ulClock); dividers->ul_fb_div.ul_fb_div_frac = - pll_patameters.ulFbDiv.usFbDivFrac; + le16_to_cpu(pll_patameters.ulFbDiv.usFbDivFrac); dividers->ul_fb_div.ul_fb_div = - pll_patameters.ulFbDiv.usFbDiv; + le16_to_cpu(pll_patameters.ulFbDiv.usFbDiv); dividers->uc_pll_ref_div = pll_patameters.ucPllRefDiv; @@ -380,7 +379,7 @@ int atomctrl_get_engine_pll_dividers_ai(struct pp_hwmgr *hwmgr, COMPUTE_GPU_CLOCK_OUTPUT_PARAMETERS_V1_7 pll_patameters; int result; - pll_patameters.ulClock.ulClock = clock_value; + pll_patameters.ulClock.ulClock = cpu_to_le32(clock_value); pll_patameters.ulClock.ucPostDiv = COMPUTE_GPUCLK_INPUT_FLAG_SCLK; result = cgs_atom_exec_cmd_table @@ -412,7 +411,7 @@ int atomctrl_get_dfs_pll_dividers_vi( COMPUTE_GPU_CLOCK_OUTPUT_PARAMETERS_V1_6 pll_patameters; int result; - pll_patameters.ulClock.ulClock = clock_value; + pll_patameters.ulClock.ulClock = cpu_to_le32(clock_value); pll_patameters.ulClock.ucPostDiv = COMPUTE_GPUCLK_INPUT_FLAG_DEFAULT_GPUCLK; @@ -425,12 +424,12 @@ int atomctrl_get_dfs_pll_dividers_vi( dividers->pll_post_divider = pll_patameters.ulClock.ucPostDiv; dividers->real_clock = - pll_patameters.ulClock.ulClock; + le32_to_cpu(pll_patameters.ulClock.ulClock); dividers->ul_fb_div.ul_fb_div_frac = - pll_patameters.ulFbDiv.usFbDivFrac; + le16_to_cpu(pll_patameters.ulFbDiv.usFbDivFrac); dividers->ul_fb_div.ul_fb_div = - pll_patameters.ulFbDiv.usFbDiv; + le16_to_cpu(pll_patameters.ulFbDiv.usFbDiv); dividers->uc_pll_ref_div = pll_patameters.ucPllRefDiv; @@ -519,13 +518,13 @@ int atomctrl_get_voltage_table_v3( for (i = 0; i < voltage_object->asGpioVoltageObj.ucGpioEntryNum; i++) { voltage_table->entries[i].value = - voltage_object->asGpioVoltageObj.asVolGpioLut[i].usVoltageValue; + le16_to_cpu(voltage_object->asGpioVoltageObj.asVolGpioLut[i].usVoltageValue); voltage_table->entries[i].smio_low = - voltage_object->asGpioVoltageObj.asVolGpioLut[i].ulVoltageId; + le32_to_cpu(voltage_object->asGpioVoltageObj.asVolGpioLut[i].ulVoltageId); } voltage_table->mask_low = - voltage_object->asGpioVoltageObj.ulGpioMaskVal; + le32_to_cpu(voltage_object->asGpioVoltageObj.ulGpioMaskVal); voltage_table->count = voltage_object->asGpioVoltageObj.ucGpioEntryNum; voltage_table->phase_delay = @@ -552,13 +551,13 @@ static bool atomctrl_lookup_gpio_pin( pin_assignment->ucGpioPinBitShift; gpio_pin_assignment->us_gpio_pin_aindex = le16_to_cpu(pin_assignment->usGpioPin_AIndex); - return false; + return true; } offset += offsetof(ATOM_GPIO_PIN_ASSIGNMENT, ucGPIO_ID) + 1; } - return true; + return false; } /** @@ -592,12 +591,12 @@ bool atomctrl_get_pp_assign_pin( const uint32_t pinId, pp_atomctrl_gpio_pin_assignment *gpio_pin_assignment) { - bool bRet = 0; + bool bRet = false; ATOM_GPIO_PIN_LUT *gpio_lookup_table = get_gpio_lookup_table(hwmgr->device); PP_ASSERT_WITH_CODE((NULL != gpio_lookup_table), - "Could not find GPIO lookup Table in BIOS.", return -1); + "Could not find GPIO lookup Table in BIOS.", return false); bRet = atomctrl_lookup_gpio_pin(gpio_lookup_table, pinId, gpio_pin_assignment); @@ -650,8 +649,8 @@ int atomctrl_calculate_voltage_evv_on_sclk( return -1; if (getASICProfilingInfo->asHeader.ucTableFormatRevision < 3 || - (getASICProfilingInfo->asHeader.ucTableFormatRevision == 3 && - getASICProfilingInfo->asHeader.ucTableContentRevision < 4)) + (getASICProfilingInfo->asHeader.ucTableFormatRevision == 3 && + getASICProfilingInfo->asHeader.ucTableContentRevision < 4)) return -1; /*----------------------------------------------------------- @@ -662,37 +661,37 @@ int atomctrl_calculate_voltage_evv_on_sclk( switch (dpm_level) { case 1: - fPowerDPMx = Convert_ULONG_ToFraction(getASICProfilingInfo->usPowerDpm1); - fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM1, 1000); + fPowerDPMx = Convert_ULONG_ToFraction(le16_to_cpu(getASICProfilingInfo->usPowerDpm1)); + fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM1), 1000); break; case 2: - fPowerDPMx = Convert_ULONG_ToFraction(getASICProfilingInfo->usPowerDpm2); - fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM2, 1000); + fPowerDPMx = Convert_ULONG_ToFraction(le16_to_cpu(getASICProfilingInfo->usPowerDpm2)); + fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM2), 1000); break; case 3: - fPowerDPMx = Convert_ULONG_ToFraction(getASICProfilingInfo->usPowerDpm3); - fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM3, 1000); + fPowerDPMx = Convert_ULONG_ToFraction(le16_to_cpu(getASICProfilingInfo->usPowerDpm3)); + fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM3), 1000); break; case 4: - fPowerDPMx = Convert_ULONG_ToFraction(getASICProfilingInfo->usPowerDpm4); - fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM4, 1000); + fPowerDPMx = Convert_ULONG_ToFraction(le16_to_cpu(getASICProfilingInfo->usPowerDpm4)); + fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM4), 1000); break; case 5: - fPowerDPMx = Convert_ULONG_ToFraction(getASICProfilingInfo->usPowerDpm5); - fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM5, 1000); + fPowerDPMx = Convert_ULONG_ToFraction(le16_to_cpu(getASICProfilingInfo->usPowerDpm5)); + fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM5), 1000); break; case 6: - fPowerDPMx = Convert_ULONG_ToFraction(getASICProfilingInfo->usPowerDpm6); - fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM6, 1000); + fPowerDPMx = Convert_ULONG_ToFraction(le16_to_cpu(getASICProfilingInfo->usPowerDpm6)); + fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM6), 1000); break; case 7: - fPowerDPMx = Convert_ULONG_ToFraction(getASICProfilingInfo->usPowerDpm7); - fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM7, 1000); + fPowerDPMx = Convert_ULONG_ToFraction(le16_to_cpu(getASICProfilingInfo->usPowerDpm7)); + fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM7), 1000); break; default: printk(KERN_ERR "DPM Level not supported\n"); fPowerDPMx = Convert_ULONG_ToFraction(1); - fDerateTDP = GetScaledFraction(getASICProfilingInfo->ulTdpDerateDPM0, 1000); + fDerateTDP = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulTdpDerateDPM0), 1000); } /*------------------------- @@ -716,9 +715,9 @@ int atomctrl_calculate_voltage_evv_on_sclk( return result; /* Finally, the actual fuse value */ - ul_RO_fused = sOutput_FuseValues.ulEfuseValue; - fMin = GetScaledFraction(sRO_fuse.ulEfuseMin, 1); - fRange = GetScaledFraction(sRO_fuse.ulEfuseEncodeRange, 1); + ul_RO_fused = le32_to_cpu(sOutput_FuseValues.ulEfuseValue); + fMin = GetScaledFraction(le32_to_cpu(sRO_fuse.ulEfuseMin), 1); + fRange = GetScaledFraction(le32_to_cpu(sRO_fuse.ulEfuseEncodeRange), 1); fRO_fused = fDecodeLinearFuse(ul_RO_fused, fMin, fRange, sRO_fuse.ucEfuseLength); sCACm_fuse = getASICProfilingInfo->sCACm; @@ -736,9 +735,9 @@ int atomctrl_calculate_voltage_evv_on_sclk( if (result) return result; - ul_CACm_fused = sOutput_FuseValues.ulEfuseValue; - fMin = GetScaledFraction(sCACm_fuse.ulEfuseMin, 1000); - fRange = GetScaledFraction(sCACm_fuse.ulEfuseEncodeRange, 1000); + ul_CACm_fused = le32_to_cpu(sOutput_FuseValues.ulEfuseValue); + fMin = GetScaledFraction(le32_to_cpu(sCACm_fuse.ulEfuseMin), 1000); + fRange = GetScaledFraction(le32_to_cpu(sCACm_fuse.ulEfuseEncodeRange), 1000); fCACm_fused = fDecodeLinearFuse(ul_CACm_fused, fMin, fRange, sCACm_fuse.ucEfuseLength); @@ -756,9 +755,9 @@ int atomctrl_calculate_voltage_evv_on_sclk( if (result) return result; - ul_CACb_fused = sOutput_FuseValues.ulEfuseValue; - fMin = GetScaledFraction(sCACb_fuse.ulEfuseMin, 1000); - fRange = GetScaledFraction(sCACb_fuse.ulEfuseEncodeRange, 1000); + ul_CACb_fused = le32_to_cpu(sOutput_FuseValues.ulEfuseValue); + fMin = GetScaledFraction(le32_to_cpu(sCACb_fuse.ulEfuseMin), 1000); + fRange = GetScaledFraction(le32_to_cpu(sCACb_fuse.ulEfuseEncodeRange), 1000); fCACb_fused = fDecodeLinearFuse(ul_CACb_fused, fMin, fRange, sCACb_fuse.ucEfuseLength); @@ -777,9 +776,9 @@ int atomctrl_calculate_voltage_evv_on_sclk( if (result) return result; - ul_Kt_Beta_fused = sOutput_FuseValues.ulEfuseValue; - fAverage = GetScaledFraction(sKt_Beta_fuse.ulEfuseEncodeAverage, 1000); - fRange = GetScaledFraction(sKt_Beta_fuse.ulEfuseEncodeRange, 1000); + ul_Kt_Beta_fused = le32_to_cpu(sOutput_FuseValues.ulEfuseValue); + fAverage = GetScaledFraction(le32_to_cpu(sKt_Beta_fuse.ulEfuseEncodeAverage), 1000); + fRange = GetScaledFraction(le32_to_cpu(sKt_Beta_fuse.ulEfuseEncodeRange), 1000); fKt_Beta_fused = fDecodeLogisticFuse(ul_Kt_Beta_fused, fAverage, fRange, sKt_Beta_fuse.ucEfuseLength); @@ -798,9 +797,9 @@ int atomctrl_calculate_voltage_evv_on_sclk( if (result) return result; - ul_Kv_m_fused = sOutput_FuseValues.ulEfuseValue; - fAverage = GetScaledFraction(sKv_m_fuse.ulEfuseEncodeAverage, 1000); - fRange = GetScaledFraction((sKv_m_fuse.ulEfuseEncodeRange & 0x7fffffff), 1000); + ul_Kv_m_fused = le32_to_cpu(sOutput_FuseValues.ulEfuseValue); + fAverage = GetScaledFraction(le32_to_cpu(sKv_m_fuse.ulEfuseEncodeAverage), 1000); + fRange = GetScaledFraction((le32_to_cpu(sKv_m_fuse.ulEfuseEncodeRange) & 0x7fffffff), 1000); fRange = fMultiply(fRange, ConvertToFraction(-1)); fKv_m_fused = fDecodeLogisticFuse(ul_Kv_m_fused, @@ -820,9 +819,9 @@ int atomctrl_calculate_voltage_evv_on_sclk( if (result) return result; - ul_Kv_b_fused = sOutput_FuseValues.ulEfuseValue; - fAverage = GetScaledFraction(sKv_b_fuse.ulEfuseEncodeAverage, 1000); - fRange = GetScaledFraction(sKv_b_fuse.ulEfuseEncodeRange, 1000); + ul_Kv_b_fused = le32_to_cpu(sOutput_FuseValues.ulEfuseValue); + fAverage = GetScaledFraction(le32_to_cpu(sKv_b_fuse.ulEfuseEncodeAverage), 1000); + fRange = GetScaledFraction(le32_to_cpu(sKv_b_fuse.ulEfuseEncodeRange), 1000); fKv_b_fused = fDecodeLogisticFuse(ul_Kv_b_fused, fAverage, fRange, sKv_b_fuse.ucEfuseLength); @@ -851,9 +850,9 @@ int atomctrl_calculate_voltage_evv_on_sclk( if (result) return result; - ul_FT_Lkg_V0NORM = sOutput_FuseValues.ulEfuseValue; - fLn_MaxDivMin = GetScaledFraction(getASICProfilingInfo->ulLkgEncodeLn_MaxDivMin, 10000); - fMin = GetScaledFraction(getASICProfilingInfo->ulLkgEncodeMin, 10000); + ul_FT_Lkg_V0NORM = le32_to_cpu(sOutput_FuseValues.ulEfuseValue); + fLn_MaxDivMin = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulLkgEncodeLn_MaxDivMin), 10000); + fMin = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulLkgEncodeMin), 10000); fFT_Lkg_V0NORM = fDecodeLeakageID(ul_FT_Lkg_V0NORM, fLn_MaxDivMin, fMin, getASICProfilingInfo->ucLkgEfuseLength); @@ -863,40 +862,40 @@ int atomctrl_calculate_voltage_evv_on_sclk( * PART 2 - Grabbing all required values *------------------------------------------- */ - fSM_A0 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A0, 1000000), + fSM_A0 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A0), 1000000), ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A0_sign))); - fSM_A1 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A1, 1000000), + fSM_A1 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A1), 1000000), ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A1_sign))); - fSM_A2 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A2, 100000), + fSM_A2 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A2), 100000), ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A2_sign))); - fSM_A3 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A3, 1000000), + fSM_A3 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A3), 1000000), ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A3_sign))); - fSM_A4 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A4, 1000000), + fSM_A4 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A4), 1000000), ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A4_sign))); - fSM_A5 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A5, 1000), + fSM_A5 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A5), 1000), ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A5_sign))); - fSM_A6 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A6, 1000), + fSM_A6 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A6), 1000), ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A6_sign))); - fSM_A7 = fMultiply(GetScaledFraction(getASICProfilingInfo->ulSM_A7, 1000), + fSM_A7 = fMultiply(GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulSM_A7), 1000), ConvertToFraction(uPow(-1, getASICProfilingInfo->ucSM_A7_sign))); - fMargin_RO_a = ConvertToFraction(getASICProfilingInfo->ulMargin_RO_a); - fMargin_RO_b = ConvertToFraction(getASICProfilingInfo->ulMargin_RO_b); - fMargin_RO_c = ConvertToFraction(getASICProfilingInfo->ulMargin_RO_c); + fMargin_RO_a = ConvertToFraction(le32_to_cpu(getASICProfilingInfo->ulMargin_RO_a)); + fMargin_RO_b = ConvertToFraction(le32_to_cpu(getASICProfilingInfo->ulMargin_RO_b)); + fMargin_RO_c = ConvertToFraction(le32_to_cpu(getASICProfilingInfo->ulMargin_RO_c)); - fMargin_fixed = ConvertToFraction(getASICProfilingInfo->ulMargin_fixed); + fMargin_fixed = ConvertToFraction(le32_to_cpu(getASICProfilingInfo->ulMargin_fixed)); fMargin_FMAX_mean = GetScaledFraction( - getASICProfilingInfo->ulMargin_Fmax_mean, 10000); + le32_to_cpu(getASICProfilingInfo->ulMargin_Fmax_mean), 10000); fMargin_Plat_mean = GetScaledFraction( - getASICProfilingInfo->ulMargin_plat_mean, 10000); + le32_to_cpu(getASICProfilingInfo->ulMargin_plat_mean), 10000); fMargin_FMAX_sigma = GetScaledFraction( - getASICProfilingInfo->ulMargin_Fmax_sigma, 10000); + le32_to_cpu(getASICProfilingInfo->ulMargin_Fmax_sigma), 10000); fMargin_Plat_sigma = GetScaledFraction( - getASICProfilingInfo->ulMargin_plat_sigma, 10000); + le32_to_cpu(getASICProfilingInfo->ulMargin_plat_sigma), 10000); fMargin_DC_sigma = GetScaledFraction( - getASICProfilingInfo->ulMargin_DC_sigma, 100); + le32_to_cpu(getASICProfilingInfo->ulMargin_DC_sigma), 100); fMargin_DC_sigma = fDivide(fMargin_DC_sigma, ConvertToFraction(1000)); fCACm_fused = fDivide(fCACm_fused, ConvertToFraction(100)); @@ -908,14 +907,14 @@ int atomctrl_calculate_voltage_evv_on_sclk( fSclk = GetScaledFraction(sclk, 100); fV_max = fDivide(GetScaledFraction( - getASICProfilingInfo->ulMaxVddc, 1000), ConvertToFraction(4)); - fT_prod = GetScaledFraction(getASICProfilingInfo->ulBoardCoreTemp, 10); - fLKG_Factor = GetScaledFraction(getASICProfilingInfo->ulEvvLkgFactor, 100); - fT_FT = GetScaledFraction(getASICProfilingInfo->ulLeakageTemp, 10); + le32_to_cpu(getASICProfilingInfo->ulMaxVddc), 1000), ConvertToFraction(4)); + fT_prod = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulBoardCoreTemp), 10); + fLKG_Factor = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulEvvLkgFactor), 100); + fT_FT = GetScaledFraction(le32_to_cpu(getASICProfilingInfo->ulLeakageTemp), 10); fV_FT = fDivide(GetScaledFraction( - getASICProfilingInfo->ulLeakageVoltage, 1000), ConvertToFraction(4)); + le32_to_cpu(getASICProfilingInfo->ulLeakageVoltage), 1000), ConvertToFraction(4)); fV_min = fDivide(GetScaledFraction( - getASICProfilingInfo->ulMinVddc, 1000), ConvertToFraction(4)); + le32_to_cpu(getASICProfilingInfo->ulMinVddc), 1000), ConvertToFraction(4)); /*----------------------- * PART 3 @@ -925,7 +924,7 @@ int atomctrl_calculate_voltage_evv_on_sclk( fA_Term = fAdd(fMargin_RO_a, fAdd(fMultiply(fSM_A4, fSclk), fSM_A5)); fB_Term = fAdd(fAdd(fMultiply(fSM_A2, fSclk), fSM_A6), fMargin_RO_b); fC_Term = fAdd(fMargin_RO_c, - fAdd(fMultiply(fSM_A0,fLkg_FT), + fAdd(fMultiply(fSM_A0, fLkg_FT), fAdd(fMultiply(fSM_A1, fMultiply(fLkg_FT, fSclk)), fAdd(fMultiply(fSM_A3, fSclk), fSubtract(fSM_A7, fRO_fused))))); @@ -1063,9 +1062,9 @@ int atomctrl_get_voltage_evv_on_sclk( get_voltage_info_param_space.ucVoltageMode = ATOM_GET_VOLTAGE_EVV_VOLTAGE; get_voltage_info_param_space.usVoltageLevel = - virtual_voltage_Id; + cpu_to_le16(virtual_voltage_Id); get_voltage_info_param_space.ulSCLKFreq = - sclk; + cpu_to_le32(sclk); result = cgs_atom_exec_cmd_table(hwmgr->device, GetIndexIntoMasterTable(COMMAND, GetVoltageInfo), @@ -1074,8 +1073,54 @@ int atomctrl_get_voltage_evv_on_sclk( if (0 != result) return result; - *voltage = ((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 *) - (&get_voltage_info_param_space))->usVoltageLevel; + *voltage = le16_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 *) + (&get_voltage_info_param_space))->usVoltageLevel); + + return result; +} + +/** + * atomctrl_get_voltage_evv gets voltage via call to ATOM COMMAND table. + * @param hwmgr input: pointer to hwManager + * @param virtual_voltage_id input: voltage id which match per voltage DPM state: 0xff01, 0xff02.. 0xff08 + * @param voltage output: real voltage level in unit of mv + */ +int atomctrl_get_voltage_evv(struct pp_hwmgr *hwmgr, + uint16_t virtual_voltage_id, + uint16_t *voltage) +{ + int result; + int entry_id; + GET_VOLTAGE_INFO_INPUT_PARAMETER_V1_2 get_voltage_info_param_space; + + /* search for leakage voltage ID 0xff01 ~ 0xff08 and sckl */ + for (entry_id = 0; entry_id < hwmgr->dyn_state.vddc_dependency_on_sclk->count; entry_id++) { + if (hwmgr->dyn_state.vddc_dependency_on_sclk->entries[entry_id].v == virtual_voltage_id) { + /* found */ + break; + } + } + + PP_ASSERT_WITH_CODE(entry_id < hwmgr->dyn_state.vddc_dependency_on_sclk->count, + "Can't find requested voltage id in vddc_dependency_on_sclk table!", + return -EINVAL; + ); + + get_voltage_info_param_space.ucVoltageType = VOLTAGE_TYPE_VDDC; + get_voltage_info_param_space.ucVoltageMode = ATOM_GET_VOLTAGE_EVV_VOLTAGE; + get_voltage_info_param_space.usVoltageLevel = virtual_voltage_id; + get_voltage_info_param_space.ulSCLKFreq = + cpu_to_le32(hwmgr->dyn_state.vddc_dependency_on_sclk->entries[entry_id].clk); + + result = cgs_atom_exec_cmd_table(hwmgr->device, + GetIndexIntoMasterTable(COMMAND, GetVoltageInfo), + &get_voltage_info_param_space); + + if (0 != result) + return result; + + *voltage = le16_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_2 *) + (&get_voltage_info_param_space))->usVoltageLevel); return result; } @@ -1165,8 +1210,8 @@ static int asic_internal_ss_get_ss_asignment(struct pp_hwmgr *hwmgr, if (entry_found) { ssEntry->speed_spectrum_percentage = - ssInfo->usSpreadSpectrumPercentage; - ssEntry->speed_spectrum_rate = ssInfo->usSpreadRateInKhz; + le16_to_cpu(ssInfo->usSpreadSpectrumPercentage); + ssEntry->speed_spectrum_rate = le16_to_cpu(ssInfo->usSpreadRateInKhz); if (((GET_DATA_TABLE_MAJOR_REVISION(table) == 2) && (GET_DATA_TABLE_MINOR_REVISION(table) >= 2)) || @@ -1222,7 +1267,7 @@ int atomctrl_read_efuse(void *device, uint16_t start_index, int result; READ_EFUSE_VALUE_PARAMETER efuse_param; - efuse_param.sEfuse.usEfuseIndex = (start_index / 32) * 4; + efuse_param.sEfuse.usEfuseIndex = cpu_to_le16((start_index / 32) * 4); efuse_param.sEfuse.ucBitShift = (uint8_t) (start_index - ((start_index / 32) * 32)); efuse_param.sEfuse.ucBitLength = (uint8_t) @@ -1232,19 +1277,21 @@ int atomctrl_read_efuse(void *device, uint16_t start_index, GetIndexIntoMasterTable(COMMAND, ReadEfuseValue), &efuse_param); if (!result) - *efuse = efuse_param.ulEfuseValue & mask; + *efuse = le32_to_cpu(efuse_param.ulEfuseValue) & mask; return result; } int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock, - uint8_t level) + uint8_t level) { DYNAMICE_MEMORY_SETTINGS_PARAMETER_V2_1 memory_clock_parameters; int result; - memory_clock_parameters.asDPMMCReg.ulClock.ulClockFreq = memory_clock & SET_CLOCK_FREQ_MASK; - memory_clock_parameters.asDPMMCReg.ulClock.ulComputeClockFlag = ADJUST_MC_SETTING_PARAM; + memory_clock_parameters.asDPMMCReg.ulClock.ulClockFreq = + memory_clock & SET_CLOCK_FREQ_MASK; + memory_clock_parameters.asDPMMCReg.ulClock.ulComputeClockFlag = + ADJUST_MC_SETTING_PARAM; memory_clock_parameters.asDPMMCReg.ucMclkDPMState = level; result = cgs_atom_exec_cmd_table @@ -1256,7 +1303,7 @@ int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock, } int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type, - uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage) + uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage) { int result; @@ -1264,8 +1311,8 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_ get_voltage_info_param_space.ucVoltageType = voltage_type; get_voltage_info_param_space.ucVoltageMode = ATOM_GET_VOLTAGE_EVV_VOLTAGE; - get_voltage_info_param_space.usVoltageLevel = virtual_voltage_Id; - get_voltage_info_param_space.ulSCLKFreq = sclk; + get_voltage_info_param_space.usVoltageLevel = cpu_to_le16(virtual_voltage_Id); + get_voltage_info_param_space.ulSCLKFreq = cpu_to_le32(sclk); result = cgs_atom_exec_cmd_table(hwmgr->device, GetIndexIntoMasterTable(COMMAND, GetVoltageInfo), @@ -1274,7 +1321,7 @@ int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_ if (0 != result) return result; - *voltage = get_voltage_info_param_space.usVoltageLevel; + *voltage = le32_to_cpu(((GET_EVV_VOLTAGE_INFO_OUTPUT_PARAMETER_V1_3 *)(&get_voltage_info_param_space))->ulVoltageLevel); return result; } @@ -1295,10 +1342,57 @@ int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctr for (i = 0; i < psmu_info->ucSclkEntryNum; i++) { table->entry[i].ucVco_setting = psmu_info->asSclkFcwRangeEntry[i].ucVco_setting; table->entry[i].ucPostdiv = psmu_info->asSclkFcwRangeEntry[i].ucPostdiv; - table->entry[i].usFcw_pcc = psmu_info->asSclkFcwRangeEntry[i].ucFcw_pcc; - table->entry[i].usFcw_trans_upper = psmu_info->asSclkFcwRangeEntry[i].ucFcw_trans_upper; - table->entry[i].usRcw_trans_lower = psmu_info->asSclkFcwRangeEntry[i].ucRcw_trans_lower; + table->entry[i].usFcw_pcc = + le16_to_cpu(psmu_info->asSclkFcwRangeEntry[i].ucFcw_pcc); + table->entry[i].usFcw_trans_upper = + le16_to_cpu(psmu_info->asSclkFcwRangeEntry[i].ucFcw_trans_upper); + table->entry[i].usRcw_trans_lower = + le16_to_cpu(psmu_info->asSclkFcwRangeEntry[i].ucRcw_trans_lower); } return 0; } + +int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, + struct pp_atom_ctrl__avfs_parameters *param) +{ + ATOM_ASIC_PROFILING_INFO_V3_6 *profile = NULL; + + if (param == NULL) + return -EINVAL; + + profile = (ATOM_ASIC_PROFILING_INFO_V3_6 *) + cgs_atom_get_data_table(hwmgr->device, + GetIndexIntoMasterTable(DATA, ASIC_ProfilingInfo), + NULL, NULL, NULL); + if (!profile) + return -1; + + param->ulAVFS_meanNsigma_Acontant0 = le32_to_cpu(profile->ulAVFS_meanNsigma_Acontant0); + param->ulAVFS_meanNsigma_Acontant1 = le32_to_cpu(profile->ulAVFS_meanNsigma_Acontant1); + param->ulAVFS_meanNsigma_Acontant2 = le32_to_cpu(profile->ulAVFS_meanNsigma_Acontant2); + param->usAVFS_meanNsigma_DC_tol_sigma = le16_to_cpu(profile->usAVFS_meanNsigma_DC_tol_sigma); + param->usAVFS_meanNsigma_Platform_mean = le16_to_cpu(profile->usAVFS_meanNsigma_Platform_mean); + param->usAVFS_meanNsigma_Platform_sigma = le16_to_cpu(profile->usAVFS_meanNsigma_Platform_sigma); + param->ulGB_VDROOP_TABLE_CKSOFF_a0 = le32_to_cpu(profile->ulGB_VDROOP_TABLE_CKSOFF_a0); + param->ulGB_VDROOP_TABLE_CKSOFF_a1 = le32_to_cpu(profile->ulGB_VDROOP_TABLE_CKSOFF_a1); + param->ulGB_VDROOP_TABLE_CKSOFF_a2 = le32_to_cpu(profile->ulGB_VDROOP_TABLE_CKSOFF_a2); + param->ulGB_VDROOP_TABLE_CKSON_a0 = le32_to_cpu(profile->ulGB_VDROOP_TABLE_CKSON_a0); + param->ulGB_VDROOP_TABLE_CKSON_a1 = le32_to_cpu(profile->ulGB_VDROOP_TABLE_CKSON_a1); + param->ulGB_VDROOP_TABLE_CKSON_a2 = le32_to_cpu(profile->ulGB_VDROOP_TABLE_CKSON_a2); + param->ulAVFSGB_FUSE_TABLE_CKSOFF_m1 = le32_to_cpu(profile->ulAVFSGB_FUSE_TABLE_CKSOFF_m1); + param->usAVFSGB_FUSE_TABLE_CKSOFF_m2 = le16_to_cpu(profile->usAVFSGB_FUSE_TABLE_CKSOFF_m2); + param->ulAVFSGB_FUSE_TABLE_CKSOFF_b = le32_to_cpu(profile->ulAVFSGB_FUSE_TABLE_CKSOFF_b); + param->ulAVFSGB_FUSE_TABLE_CKSON_m1 = le32_to_cpu(profile->ulAVFSGB_FUSE_TABLE_CKSON_m1); + param->usAVFSGB_FUSE_TABLE_CKSON_m2 = le16_to_cpu(profile->usAVFSGB_FUSE_TABLE_CKSON_m2); + param->ulAVFSGB_FUSE_TABLE_CKSON_b = le32_to_cpu(profile->ulAVFSGB_FUSE_TABLE_CKSON_b); + param->usMaxVoltage_0_25mv = le16_to_cpu(profile->usMaxVoltage_0_25mv); + param->ucEnableGB_VDROOP_TABLE_CKSOFF = profile->ucEnableGB_VDROOP_TABLE_CKSOFF; + param->ucEnableGB_VDROOP_TABLE_CKSON = profile->ucEnableGB_VDROOP_TABLE_CKSON; + param->ucEnableGB_FUSE_TABLE_CKSOFF = profile->ucEnableGB_FUSE_TABLE_CKSOFF; + param->ucEnableGB_FUSE_TABLE_CKSON = profile->ucEnableGB_FUSE_TABLE_CKSON; + param->usPSM_Age_ComFactor = le16_to_cpu(profile->usPSM_Age_ComFactor); + param->ucEnableApplyAVFS_CKS_OFF_Voltage = profile->ucEnableApplyAVFS_CKS_OFF_Voltage; + + return 0; +} diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h index d24ebb566905..fc898afce002 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h @@ -250,8 +250,38 @@ struct pp_atomctrl_gpio_pin_assignment { }; typedef struct pp_atomctrl_gpio_pin_assignment pp_atomctrl_gpio_pin_assignment; +struct pp_atom_ctrl__avfs_parameters { + uint32_t ulAVFS_meanNsigma_Acontant0; + uint32_t ulAVFS_meanNsigma_Acontant1; + uint32_t ulAVFS_meanNsigma_Acontant2; + uint16_t usAVFS_meanNsigma_DC_tol_sigma; + uint16_t usAVFS_meanNsigma_Platform_mean; + uint16_t usAVFS_meanNsigma_Platform_sigma; + uint32_t ulGB_VDROOP_TABLE_CKSOFF_a0; + uint32_t ulGB_VDROOP_TABLE_CKSOFF_a1; + uint32_t ulGB_VDROOP_TABLE_CKSOFF_a2; + uint32_t ulGB_VDROOP_TABLE_CKSON_a0; + uint32_t ulGB_VDROOP_TABLE_CKSON_a1; + uint32_t ulGB_VDROOP_TABLE_CKSON_a2; + uint32_t ulAVFSGB_FUSE_TABLE_CKSOFF_m1; + uint16_t usAVFSGB_FUSE_TABLE_CKSOFF_m2; + uint32_t ulAVFSGB_FUSE_TABLE_CKSOFF_b; + uint32_t ulAVFSGB_FUSE_TABLE_CKSON_m1; + uint16_t usAVFSGB_FUSE_TABLE_CKSON_m2; + uint32_t ulAVFSGB_FUSE_TABLE_CKSON_b; + uint16_t usMaxVoltage_0_25mv; + uint8_t ucEnableGB_VDROOP_TABLE_CKSOFF; + uint8_t ucEnableGB_VDROOP_TABLE_CKSON; + uint8_t ucEnableGB_FUSE_TABLE_CKSOFF; + uint8_t ucEnableGB_FUSE_TABLE_CKSON; + uint16_t usPSM_Age_ComFactor; + uint8_t ucEnableApplyAVFS_CKS_OFF_Voltage; + uint8_t ucReserved; +}; + extern bool atomctrl_get_pp_assign_pin(struct pp_hwmgr *hwmgr, const uint32_t pinId, pp_atomctrl_gpio_pin_assignment *gpio_pin_assignment); extern int atomctrl_get_voltage_evv_on_sclk(struct pp_hwmgr *hwmgr, uint8_t voltage_type, uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage); +extern int atomctrl_get_voltage_evv(struct pp_hwmgr *hwmgr, uint16_t virtual_voltage_id, uint16_t *voltage); extern uint32_t atomctrl_get_mpll_reference_clock(struct pp_hwmgr *hwmgr); extern int atomctrl_get_memory_clock_spread_spectrum(struct pp_hwmgr *hwmgr, const uint32_t memory_clock, pp_atomctrl_internal_ss_info *ssInfo); extern int atomctrl_get_engine_clock_spread_spectrum(struct pp_hwmgr *hwmgr, const uint32_t engine_clock, pp_atomctrl_internal_ss_info *ssInfo); @@ -276,7 +306,10 @@ extern int atomctrl_get_engine_pll_dividers_ai(struct pp_hwmgr *hwmgr, uint32_t extern int atomctrl_set_ac_timing_ai(struct pp_hwmgr *hwmgr, uint32_t memory_clock, uint8_t level); extern int atomctrl_get_voltage_evv_on_sclk_ai(struct pp_hwmgr *hwmgr, uint8_t voltage_type, - uint32_t sclk, uint16_t virtual_voltage_Id, uint16_t *voltage); + uint32_t sclk, uint16_t virtual_voltage_Id, uint32_t *voltage); extern int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl_sclk_range_table *table); + +extern int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param); + #endif diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppevvmath.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppevvmath.h index 009bd5963ed8..8f50a038396c 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppevvmath.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppevvmath.h @@ -50,55 +50,45 @@ typedef union _fInt { * Function Declarations * ------------------------------------------------------------------------------- */ -fInt ConvertToFraction(int); /* Use this to convert an INT to a FINT */ -fInt Convert_ULONG_ToFraction(uint32_t); /* Use this to convert an uint32_t to a FINT */ -fInt GetScaledFraction(int, int); /* Use this to convert an INT to a FINT after scaling it by a factor */ -int ConvertBackToInteger(fInt); /* Convert a FINT back to an INT that is scaled by 1000 (i.e. last 3 digits are the decimal digits) */ +static fInt ConvertToFraction(int); /* Use this to convert an INT to a FINT */ +static fInt Convert_ULONG_ToFraction(uint32_t); /* Use this to convert an uint32_t to a FINT */ +static fInt GetScaledFraction(int, int); /* Use this to convert an INT to a FINT after scaling it by a factor */ +static int ConvertBackToInteger(fInt); /* Convert a FINT back to an INT that is scaled by 1000 (i.e. last 3 digits are the decimal digits) */ -fInt fNegate(fInt); /* Returns -1 * input fInt value */ -fInt fAdd (fInt, fInt); /* Returns the sum of two fInt numbers */ -fInt fSubtract (fInt A, fInt B); /* Returns A-B - Sometimes easier than Adding negative numbers */ -fInt fMultiply (fInt, fInt); /* Returns the product of two fInt numbers */ -fInt fDivide (fInt A, fInt B); /* Returns A/B */ -fInt fGetSquare(fInt); /* Returns the square of a fInt number */ -fInt fSqrt(fInt); /* Returns the Square Root of a fInt number */ +static fInt fNegate(fInt); /* Returns -1 * input fInt value */ +static fInt fAdd (fInt, fInt); /* Returns the sum of two fInt numbers */ +static fInt fSubtract (fInt A, fInt B); /* Returns A-B - Sometimes easier than Adding negative numbers */ +static fInt fMultiply (fInt, fInt); /* Returns the product of two fInt numbers */ +static fInt fDivide (fInt A, fInt B); /* Returns A/B */ +static fInt fGetSquare(fInt); /* Returns the square of a fInt number */ +static fInt fSqrt(fInt); /* Returns the Square Root of a fInt number */ -int uAbs(int); /* Returns the Absolute value of the Int */ -fInt fAbs(fInt); /* Returns the Absolute value of the fInt */ -int uPow(int base, int exponent); /* Returns base^exponent an INT */ +static int uAbs(int); /* Returns the Absolute value of the Int */ +static int uPow(int base, int exponent); /* Returns base^exponent an INT */ -void SolveQuadracticEqn(fInt, fInt, fInt, fInt[]); /* Returns the 2 roots via the array */ -bool Equal(fInt, fInt); /* Returns true if two fInts are equal to each other */ -bool GreaterThan(fInt A, fInt B); /* Returns true if A > B */ +static void SolveQuadracticEqn(fInt, fInt, fInt, fInt[]); /* Returns the 2 roots via the array */ +static bool Equal(fInt, fInt); /* Returns true if two fInts are equal to each other */ +static bool GreaterThan(fInt A, fInt B); /* Returns true if A > B */ -fInt fExponential(fInt exponent); /* Can be used to calculate e^exponent */ -fInt fNaturalLog(fInt value); /* Can be used to calculate ln(value) */ +static fInt fExponential(fInt exponent); /* Can be used to calculate e^exponent */ +static fInt fNaturalLog(fInt value); /* Can be used to calculate ln(value) */ /* Fuse decoding functions * ------------------------------------------------------------------------------------- */ -fInt fDecodeLinearFuse(uint32_t fuse_value, fInt f_min, fInt f_range, uint32_t bitlength); -fInt fDecodeLogisticFuse(uint32_t fuse_value, fInt f_average, fInt f_range, uint32_t bitlength); -fInt fDecodeLeakageID (uint32_t leakageID_fuse, fInt ln_max_div_min, fInt f_min, uint32_t bitlength); +static fInt fDecodeLinearFuse(uint32_t fuse_value, fInt f_min, fInt f_range, uint32_t bitlength); +static fInt fDecodeLogisticFuse(uint32_t fuse_value, fInt f_average, fInt f_range, uint32_t bitlength); +static fInt fDecodeLeakageID (uint32_t leakageID_fuse, fInt ln_max_div_min, fInt f_min, uint32_t bitlength); /* Internal Support Functions - Use these ONLY for testing or adding to internal functions * ------------------------------------------------------------------------------------- * Some of the following functions take two INTs as their input - This is unsafe for a variety of reasons. */ -fInt Add (int, int); /* Add two INTs and return Sum as FINT */ -fInt Multiply (int, int); /* Multiply two INTs and return Product as FINT */ -fInt Divide (int, int); /* You get the idea... */ -fInt fNegate(fInt); +static fInt Divide (int, int); /* Divide two INTs and return result as FINT */ +static fInt fNegate(fInt); -int uGetScaledDecimal (fInt); /* Internal function */ -int GetReal (fInt A); /* Internal function */ - -/* Future Additions and Incomplete Functions - * ------------------------------------------------------------------------------------- - */ -int GetRoundedValue(fInt); /* Incomplete function - Useful only when Precision is lacking */ - /* Let us say we have 2.126 but can only handle 2 decimal points. We could */ - /* either chop of 6 and keep 2.12 or use this function to get 2.13, which is more accurate */ +static int uGetScaledDecimal (fInt); /* Internal function */ +static int GetReal (fInt A); /* Internal function */ /* ------------------------------------------------------------------------------------- * TROUBLESHOOTING INFORMATION @@ -115,7 +105,7 @@ int GetRoundedValue(fInt); /* Incomplete function - Usef * START OF CODE * ------------------------------------------------------------------------------------- */ -fInt fExponential(fInt exponent) /*Can be used to calculate e^exponent*/ +static fInt fExponential(fInt exponent) /*Can be used to calculate e^exponent*/ { uint32_t i; bool bNegated = false; @@ -154,7 +144,7 @@ fInt fExponential(fInt exponent) /*Can be used to calculate e^exponent*/ return solution; } -fInt fNaturalLog(fInt value) +static fInt fNaturalLog(fInt value) { uint32_t i; fInt upper_bound = Divide(8, 1000); @@ -179,7 +169,7 @@ fInt fNaturalLog(fInt value) return (fAdd(solution, error_term)); } -fInt fDecodeLinearFuse(uint32_t fuse_value, fInt f_min, fInt f_range, uint32_t bitlength) +static fInt fDecodeLinearFuse(uint32_t fuse_value, fInt f_min, fInt f_range, uint32_t bitlength) { fInt f_fuse_value = Convert_ULONG_ToFraction(fuse_value); fInt f_bit_max_value = Convert_ULONG_ToFraction((uPow(2, bitlength)) - 1); @@ -194,7 +184,7 @@ fInt fDecodeLinearFuse(uint32_t fuse_value, fInt f_min, fInt f_range, uint32_t b } -fInt fDecodeLogisticFuse(uint32_t fuse_value, fInt f_average, fInt f_range, uint32_t bitlength) +static fInt fDecodeLogisticFuse(uint32_t fuse_value, fInt f_average, fInt f_range, uint32_t bitlength) { fInt f_fuse_value = Convert_ULONG_ToFraction(fuse_value); fInt f_bit_max_value = Convert_ULONG_ToFraction((uPow(2, bitlength)) - 1); @@ -212,7 +202,7 @@ fInt fDecodeLogisticFuse(uint32_t fuse_value, fInt f_average, fInt f_range, uint return f_decoded_value; } -fInt fDecodeLeakageID (uint32_t leakageID_fuse, fInt ln_max_div_min, fInt f_min, uint32_t bitlength) +static fInt fDecodeLeakageID (uint32_t leakageID_fuse, fInt ln_max_div_min, fInt f_min, uint32_t bitlength) { fInt fLeakage; fInt f_bit_max_value = Convert_ULONG_ToFraction((uPow(2, bitlength)) - 1); @@ -225,7 +215,7 @@ fInt fDecodeLeakageID (uint32_t leakageID_fuse, fInt ln_max_div_min, fInt f_min, return fLeakage; } -fInt ConvertToFraction(int X) /*Add all range checking here. Is it possible to make fInt a private declaration? */ +static fInt ConvertToFraction(int X) /*Add all range checking here. Is it possible to make fInt a private declaration? */ { fInt temp; @@ -237,13 +227,13 @@ fInt ConvertToFraction(int X) /*Add all range checking here. Is it possible to m return temp; } -fInt fNegate(fInt X) +static fInt fNegate(fInt X) { fInt CONSTANT_NEGONE = ConvertToFraction(-1); return (fMultiply(X, CONSTANT_NEGONE)); } -fInt Convert_ULONG_ToFraction(uint32_t X) +static fInt Convert_ULONG_ToFraction(uint32_t X) { fInt temp; @@ -255,7 +245,7 @@ fInt Convert_ULONG_ToFraction(uint32_t X) return temp; } -fInt GetScaledFraction(int X, int factor) +static fInt GetScaledFraction(int X, int factor) { int times_shifted, factor_shifted; bool bNEGATED; @@ -304,7 +294,7 @@ fInt GetScaledFraction(int X, int factor) } /* Addition using two fInts */ -fInt fAdd (fInt X, fInt Y) +static fInt fAdd (fInt X, fInt Y) { fInt Sum; @@ -314,7 +304,7 @@ fInt fAdd (fInt X, fInt Y) } /* Addition using two fInts */ -fInt fSubtract (fInt X, fInt Y) +static fInt fSubtract (fInt X, fInt Y) { fInt Difference; @@ -323,7 +313,7 @@ fInt fSubtract (fInt X, fInt Y) return Difference; } -bool Equal(fInt A, fInt B) +static bool Equal(fInt A, fInt B) { if (A.full == B.full) return true; @@ -331,7 +321,7 @@ bool Equal(fInt A, fInt B) return false; } -bool GreaterThan(fInt A, fInt B) +static bool GreaterThan(fInt A, fInt B) { if (A.full > B.full) return true; @@ -339,7 +329,7 @@ bool GreaterThan(fInt A, fInt B) return false; } -fInt fMultiply (fInt X, fInt Y) /* Uses 64-bit integers (int64_t) */ +static fInt fMultiply (fInt X, fInt Y) /* Uses 64-bit integers (int64_t) */ { fInt Product; int64_t tempProduct; @@ -363,7 +353,7 @@ fInt fMultiply (fInt X, fInt Y) /* Uses 64-bit integers (int64_t) */ return Product; } -fInt fDivide (fInt X, fInt Y) +static fInt fDivide (fInt X, fInt Y) { fInt fZERO, fQuotient; int64_t longlongX, longlongY; @@ -384,7 +374,7 @@ fInt fDivide (fInt X, fInt Y) return fQuotient; } -int ConvertBackToInteger (fInt A) /*THIS is the function that will be used to check with the Golden settings table*/ +static int ConvertBackToInteger (fInt A) /*THIS is the function that will be used to check with the Golden settings table*/ { fInt fullNumber, scaledDecimal, scaledReal; @@ -397,13 +387,13 @@ int ConvertBackToInteger (fInt A) /*THIS is the function that will be used to ch return fullNumber.full; } -fInt fGetSquare(fInt A) +static fInt fGetSquare(fInt A) { return fMultiply(A,A); } /* x_new = x_old - (x_old^2 - C) / (2 * x_old) */ -fInt fSqrt(fInt num) +static fInt fSqrt(fInt num) { fInt F_divide_Fprime, Fprime; fInt test; @@ -460,7 +450,7 @@ fInt fSqrt(fInt num) return (x_new); } -void SolveQuadracticEqn(fInt A, fInt B, fInt C, fInt Roots[]) +static void SolveQuadracticEqn(fInt A, fInt B, fInt C, fInt Roots[]) { fInt *pRoots = &Roots[0]; fInt temp, root_first, root_second; @@ -498,52 +488,13 @@ void SolveQuadracticEqn(fInt A, fInt B, fInt C, fInt Roots[]) * ----------------------------------------------------------------------------- */ -/* Addition using two normal ints - Temporary - Use only for testing purposes?. */ -fInt Add (int X, int Y) -{ - fInt A, B, Sum; - - A.full = (X << SHIFT_AMOUNT); - B.full = (Y << SHIFT_AMOUNT); - - Sum.full = A.full + B.full; - - return Sum; -} - /* Conversion Functions */ -int GetReal (fInt A) +static int GetReal (fInt A) { return (A.full >> SHIFT_AMOUNT); } -/* Temporarily Disabled */ -int GetRoundedValue(fInt A) /*For now, round the 3rd decimal place */ -{ - /* ROUNDING TEMPORARLY DISABLED - int temp = A.full; - int decimal_cutoff, decimal_mask = 0x000001FF; - decimal_cutoff = temp & decimal_mask; - if (decimal_cutoff > 0x147) { - temp += 673; - }*/ - - return ConvertBackToInteger(A)/10000; /*Temporary - in case this was used somewhere else */ -} - -fInt Multiply (int X, int Y) -{ - fInt A, B, Product; - - A.full = X << SHIFT_AMOUNT; - B.full = Y << SHIFT_AMOUNT; - - Product = fMultiply(A, B); - - return Product; -} - -fInt Divide (int X, int Y) +static fInt Divide (int X, int Y) { fInt A, B, Quotient; @@ -555,7 +506,7 @@ fInt Divide (int X, int Y) return Quotient; } -int uGetScaledDecimal (fInt A) /*Converts the fractional portion to whole integers - Costly function */ +static int uGetScaledDecimal (fInt A) /*Converts the fractional portion to whole integers - Costly function */ { int dec[PRECISION]; int i, scaledDecimal = 0, tmp = A.partial.decimal; @@ -570,7 +521,7 @@ int uGetScaledDecimal (fInt A) /*Converts the fractional portion to whole intege return scaledDecimal; } -int uPow(int base, int power) +static int uPow(int base, int power) { if (power == 0) return 1; @@ -578,15 +529,7 @@ int uPow(int base, int power) return (base)*uPow(base, power - 1); } -fInt fAbs(fInt A) -{ - if (A.partial.real < 0) - return (fMultiply(A, ConvertToFraction(-1))); - else - return A; -} - -int uAbs(int X) +static int uAbs(int X) { if (X < 0) return (X * -1); @@ -594,7 +537,7 @@ int uAbs(int X) return X; } -fInt fRoundUpByStepSize(fInt A, fInt fStepSize, bool error_term) +static fInt fRoundUpByStepSize(fInt A, fInt fStepSize, bool error_term) { fInt solution; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c index 2f1a14fe05b1..6c321b0d8a1e 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.c @@ -794,19 +794,35 @@ static const ATOM_PPLIB_STATE_V2 *get_state_entry_v2( static const ATOM_PPLIB_POWERPLAYTABLE *get_powerplay_table( struct pp_hwmgr *hwmgr) { - const void *table_addr = NULL; + const void *table_addr = hwmgr->soft_pp_table; uint8_t frev, crev; uint16_t size; - table_addr = cgs_atom_get_data_table(hwmgr->device, - GetIndexIntoMasterTable(DATA, PowerPlayInfo), - &size, &frev, &crev); + if (!table_addr) { + table_addr = cgs_atom_get_data_table(hwmgr->device, + GetIndexIntoMasterTable(DATA, PowerPlayInfo), + &size, &frev, &crev); - hwmgr->soft_pp_table = table_addr; + hwmgr->soft_pp_table = table_addr; + hwmgr->soft_pp_table_size = size; + } return (const ATOM_PPLIB_POWERPLAYTABLE *)table_addr; } +int pp_tables_get_response_times(struct pp_hwmgr *hwmgr, + uint32_t *vol_rep_time, uint32_t *bb_rep_time) +{ + const ATOM_PPLIB_POWERPLAYTABLE *powerplay_tab = get_powerplay_table(hwmgr); + + PP_ASSERT_WITH_CODE(NULL != powerplay_tab, + "Missing PowerPlay Table!", return -EINVAL); + + *vol_rep_time = (uint32_t)le16_to_cpu(powerplay_tab->usVoltageTime); + *bb_rep_time = (uint32_t)le16_to_cpu(powerplay_tab->usBackbiasTime); + + return 0; +} int pp_tables_get_num_of_entries(struct pp_hwmgr *hwmgr, unsigned long *num_of_entries) @@ -1499,7 +1515,7 @@ int get_number_of_vce_state_table_entries( const ATOM_PPLIB_VCE_State_Table *vce_table = get_vce_state_table(hwmgr, table); - if (vce_table > 0) + if (vce_table) return vce_table->numEntries; return 0; @@ -1589,11 +1605,6 @@ static int pp_tables_initialize(struct pp_hwmgr *hwmgr) static int pp_tables_uninitialize(struct pp_hwmgr *hwmgr) { - if (NULL != hwmgr->soft_pp_table) { - kfree(hwmgr->soft_pp_table); - hwmgr->soft_pp_table = NULL; - } - if (NULL != hwmgr->dyn_state.vddc_dependency_on_sclk) { kfree(hwmgr->dyn_state.vddc_dependency_on_sclk); hwmgr->dyn_state.vddc_dependency_on_sclk = NULL; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.h b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.h index 30434802417e..baddaa75693b 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/processpptables.h @@ -32,16 +32,19 @@ struct pp_hw_power_state; extern const struct pp_table_func pptable_funcs; typedef int (*pp_tables_hw_clock_info_callback)(struct pp_hwmgr *hwmgr, - struct pp_hw_power_state *hw_ps, - unsigned int index, - const void *clock_info); + struct pp_hw_power_state *hw_ps, + unsigned int index, + const void *clock_info); int pp_tables_get_num_of_entries(struct pp_hwmgr *hwmgr, - unsigned long *num_of_entries); + unsigned long *num_of_entries); int pp_tables_get_entry(struct pp_hwmgr *hwmgr, - unsigned long entry_index, - struct pp_power_state *ps, - pp_tables_hw_clock_info_callback func); + unsigned long entry_index, + struct pp_power_state *ps, + pp_tables_hw_clock_info_callback func); + +int pp_tables_get_response_times(struct pp_hwmgr *hwmgr, + uint32_t *vol_rep_time, uint32_t *bb_rep_time); #endif diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c index 16fed487973b..c7dc111221c2 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c @@ -571,7 +571,7 @@ int tonga_disable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) if (0 == data->sclk_dpm_key_disabled) { /* Checking if DPM is running. If we discover hang because of this, we should skip this message.*/ PP_ASSERT_WITH_CODE( - (0 == tonga_is_dpm_running(hwmgr)), + !tonga_is_dpm_running(hwmgr), "Trying to Disable SCLK DPM when DPM is disabled", return -1 ); @@ -587,7 +587,7 @@ int tonga_disable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) if (0 == data->mclk_dpm_key_disabled) { /* Checking if DPM is running. If we discover hang because of this, we should skip this message. */ PP_ASSERT_WITH_CODE( - (0 == tonga_is_dpm_running(hwmgr)), + !tonga_is_dpm_running(hwmgr), "Trying to Disable MCLK DPM when DPM is disabled", return -1 ); @@ -614,7 +614,7 @@ int tonga_stop_dpm(struct pp_hwmgr *hwmgr) if (0 == data->pcie_dpm_key_disabled) { /* Checking if DPM is running. If we discover hang because of this, we should skip this message.*/ PP_ASSERT_WITH_CODE( - (0 == tonga_is_dpm_running(hwmgr)), + !tonga_is_dpm_running(hwmgr), "Trying to Disable PCIE DPM when DPM is disabled", return -1 ); @@ -630,7 +630,7 @@ int tonga_stop_dpm(struct pp_hwmgr *hwmgr) /* Checking if DPM is running. If we discover hang because of this, we should skip this message.*/ PP_ASSERT_WITH_CODE( - (0 == tonga_is_dpm_running(hwmgr)), + !tonga_is_dpm_running(hwmgr), "Trying to Disable Voltage CNTL when DPM is disabled", return -1 ); @@ -688,8 +688,9 @@ int tonga_dpm_force_state(struct pp_hwmgr *hwmgr, uint32_t n) uint32_t level_mask = 1 << n; /* Checking if DPM is running. If we discover hang because of this, we should skip this message. */ - PP_ASSERT_WITH_CODE(0 == tonga_is_dpm_running(hwmgr), - "Trying to force SCLK when DPM is disabled", return -1;); + PP_ASSERT_WITH_CODE(!tonga_is_dpm_running(hwmgr), + "Trying to force SCLK when DPM is disabled", + return -1;); if (0 == data->sclk_dpm_key_disabled) return (0 == smum_send_msg_to_smc_with_parameter( hwmgr->smumgr, @@ -712,8 +713,9 @@ int tonga_dpm_force_state_mclk(struct pp_hwmgr *hwmgr, uint32_t n) uint32_t level_mask = 1 << n; /* Checking if DPM is running. If we discover hang because of this, we should skip this message. */ - PP_ASSERT_WITH_CODE(0 == tonga_is_dpm_running(hwmgr), - "Trying to Force MCLK when DPM is disabled", return -1;); + PP_ASSERT_WITH_CODE(!tonga_is_dpm_running(hwmgr), + "Trying to Force MCLK when DPM is disabled", + return -1;); if (0 == data->mclk_dpm_key_disabled) return (0 == smum_send_msg_to_smc_with_parameter( hwmgr->smumgr, @@ -735,8 +737,9 @@ int tonga_dpm_force_state_pcie(struct pp_hwmgr *hwmgr, uint32_t n) tonga_hwmgr *data = (tonga_hwmgr *)(hwmgr->backend); /* Checking if DPM is running. If we discover hang because of this, we should skip this message.*/ - PP_ASSERT_WITH_CODE(0 == tonga_is_dpm_running(hwmgr), - "Trying to Force PCIE level when DPM is disabled", return -1;); + PP_ASSERT_WITH_CODE(!tonga_is_dpm_running(hwmgr), + "Trying to Force PCIE level when DPM is disabled", + return -1;); if (0 == data->pcie_dpm_key_disabled) return (0 == smum_send_msg_to_smc_with_parameter( hwmgr->smumgr, @@ -774,7 +777,7 @@ int tonga_process_firmware_header(struct pp_hwmgr *hwmgr) uint32_t tmp; int result; - bool error = 0; + bool error = false; result = tonga_read_smc_sram_dword(hwmgr->smumgr, SMU72_FIRMWARE_HEADER_LOCATION + @@ -933,11 +936,11 @@ int tonga_init_power_gate_state(struct pp_hwmgr *hwmgr) { tonga_hwmgr *data = (tonga_hwmgr *)(hwmgr->backend); - data->uvd_power_gated = 0; - data->vce_power_gated = 0; - data->samu_power_gated = 0; - data->acp_power_gated = 0; - data->pg_acp_init = 1; + data->uvd_power_gated = false; + data->vce_power_gated = false; + data->samu_power_gated = false; + data->acp_power_gated = false; + data->pg_acp_init = true; return 0; } @@ -955,7 +958,7 @@ int tonga_check_for_dpm_running(struct pp_hwmgr *hwmgr) * because we may have test scenarios that need us intentionly disable SCLK/MCLK DPM, * whereas voltage control is a fundemental change that will not be disabled */ - return (0 == tonga_is_dpm_running(hwmgr) ? 0 : 1); + return (!tonga_is_dpm_running(hwmgr) ? 0 : 1); } /** @@ -968,7 +971,7 @@ int tonga_check_for_dpm_stopped(struct pp_hwmgr *hwmgr) { tonga_hwmgr *data = (tonga_hwmgr *)(hwmgr->backend); - if (0 != tonga_is_dpm_running(hwmgr)) { + if (tonga_is_dpm_running(hwmgr)) { /* If HW Virtualization is enabled, dpm_table_start will not have a valid value */ if (!data->dpm_table_start) { return 1; @@ -991,7 +994,7 @@ static int tonga_trim_voltage_table(struct pp_hwmgr *hwmgr, { uint32_t table_size, i, j; uint16_t vvalue; - bool bVoltageFound = 0; + bool bVoltageFound = false; pp_atomctrl_voltage_table *table; PP_ASSERT_WITH_CODE((NULL != voltage_table), "Voltage Table empty.", return -1;); @@ -1007,11 +1010,11 @@ static int tonga_trim_voltage_table(struct pp_hwmgr *hwmgr, for (i = 0; i < voltage_table->count; i++) { vvalue = voltage_table->entries[i].value; - bVoltageFound = 0; + bVoltageFound = false; for (j = 0; j < table->count; j++) { if (vvalue == table->entries[j].value) { - bVoltageFound = 1; + bVoltageFound = true; break; } } @@ -1302,7 +1305,7 @@ static int tonga_populate_smc_mvdd_table(struct pp_hwmgr *hwmgr, table->Smio[count] |= data->mvdd_voltage_table.entries[count].smio_low; } - table->SmioMask2 = data->vddci_voltage_table.mask_low; + table->SmioMask2 = data->mvdd_voltage_table.mask_low; CONVERT_FROM_HOST_TO_SMC_UL(table->MvddLevelCount); } @@ -1331,7 +1334,6 @@ static int tonga_populate_cac_tables(struct pp_hwmgr *hwmgr, { uint32_t count; uint8_t index; - int result = 0; tonga_hwmgr *data = (tonga_hwmgr *)(hwmgr->backend); struct phm_ppt_v1_information *pptable_info = (struct phm_ppt_v1_information *)(hwmgr->pptable); struct phm_ppt_v1_voltage_lookup_table *vddgfx_lookup_table = pptable_info->vddgfx_lookup_table; @@ -1378,7 +1380,7 @@ static int tonga_populate_cac_tables(struct pp_hwmgr *hwmgr, } } - return result; + return 0; } @@ -2042,7 +2044,7 @@ static int tonga_populate_single_memory_level( if ((data->mclk_stutter_mode_threshold != 0) && (memory_clock <= data->mclk_stutter_mode_threshold) && - (data->is_uvd_enabled == 0) + (!data->is_uvd_enabled) && (PHM_READ_FIELD(hwmgr->device, DPG_PIPE_STUTTER_CONTROL, STUTTER_ENABLE) & 0x1) && (data->display_timing.num_existing_displays <= 2) && (data->display_timing.num_existing_displays != 0)) @@ -2705,7 +2707,7 @@ static int tonga_reset_single_dpm_table( dpm_table->count = count; for (i = 0; i < MAX_REGULAR_DPM_NUMBER; i++) { - dpm_table->dpm_levels[i].enabled = 0; + dpm_table->dpm_levels[i].enabled = false; } return 0; @@ -2718,7 +2720,7 @@ static void tonga_setup_pcie_table_entry( { dpm_table->dpm_levels[index].value = pcie_gen; dpm_table->dpm_levels[index].param1 = pcie_lanes; - dpm_table->dpm_levels[index].enabled = 1; + dpm_table->dpm_levels[index].enabled = true; } static int tonga_setup_default_pcie_tables(struct pp_hwmgr *hwmgr) @@ -2828,7 +2830,7 @@ static int tonga_setup_default_dpm_tables(struct pp_hwmgr *hwmgr) allowed_vdd_sclk_table->entries[i].clk) { data->dpm_table.sclk_table.dpm_levels[data->dpm_table.sclk_table.count].value = allowed_vdd_sclk_table->entries[i].clk; - data->dpm_table.sclk_table.dpm_levels[data->dpm_table.sclk_table.count].enabled = 1; /*(i==0) ? 1 : 0; to do */ + data->dpm_table.sclk_table.dpm_levels[data->dpm_table.sclk_table.count].enabled = true; /*(i==0) ? 1 : 0; to do */ data->dpm_table.sclk_table.count++; } } @@ -2842,32 +2844,11 @@ static int tonga_setup_default_dpm_tables(struct pp_hwmgr *hwmgr) allowed_vdd_mclk_table->entries[i].clk) { data->dpm_table.mclk_table.dpm_levels[data->dpm_table.mclk_table.count].value = allowed_vdd_mclk_table->entries[i].clk; - data->dpm_table.mclk_table.dpm_levels[data->dpm_table.mclk_table.count].enabled = 1; /*(i==0) ? 1 : 0; */ + data->dpm_table.mclk_table.dpm_levels[data->dpm_table.mclk_table.count].enabled = true; /*(i==0) ? 1 : 0; */ data->dpm_table.mclk_table.count++; } } - /* Initialize Vddc DPM table based on allow Vddc values. And populate corresponding std values. */ - for (i = 0; i < allowed_vdd_sclk_table->count; i++) { - data->dpm_table.vddc_table.dpm_levels[i].value = allowed_vdd_mclk_table->entries[i].vddc; - /* tonga_hwmgr->dpm_table.VddcTable.dpm_levels[i].param1 = stdVoltageTable->entries[i].Leakage; */ - /* param1 is for corresponding std voltage */ - data->dpm_table.vddc_table.dpm_levels[i].enabled = 1; - } - data->dpm_table.vddc_table.count = allowed_vdd_sclk_table->count; - - if (NULL != allowed_vdd_mclk_table) { - /* Initialize Vddci DPM table based on allow Mclk values */ - for (i = 0; i < allowed_vdd_mclk_table->count; i++) { - data->dpm_table.vdd_ci_table.dpm_levels[i].value = allowed_vdd_mclk_table->entries[i].vddci; - data->dpm_table.vdd_ci_table.dpm_levels[i].enabled = 1; - data->dpm_table.mvdd_table.dpm_levels[i].value = allowed_vdd_mclk_table->entries[i].mvdd; - data->dpm_table.mvdd_table.dpm_levels[i].enabled = 1; - } - data->dpm_table.vdd_ci_table.count = allowed_vdd_mclk_table->count; - data->dpm_table.mvdd_table.count = allowed_vdd_mclk_table->count; - } - /* setup PCIE gen speed levels*/ tonga_setup_default_pcie_tables(hwmgr); @@ -3047,8 +3028,8 @@ int tonga_init_smc_table(struct pp_hwmgr *hwmgr) reg_value = 0; if ((0 == reg_value) && - (0 == atomctrl_get_pp_assign_pin(hwmgr, - VDDC_VRHOT_GPIO_PINID, &gpio_pin_assignment))) { + (atomctrl_get_pp_assign_pin(hwmgr, VDDC_VRHOT_GPIO_PINID, + &gpio_pin_assignment))) { table->VRHotGpio = gpio_pin_assignment.uc_gpio_pin_bit_shift; phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_RegulatorHot); @@ -3061,8 +3042,8 @@ int tonga_init_smc_table(struct pp_hwmgr *hwmgr) /* ACDC Switch GPIO */ reg_value = 0; if ((0 == reg_value) && - (0 == atomctrl_get_pp_assign_pin(hwmgr, - PP_AC_DC_SWITCH_GPIO_PINID, &gpio_pin_assignment))) { + (atomctrl_get_pp_assign_pin(hwmgr, PP_AC_DC_SWITCH_GPIO_PINID, + &gpio_pin_assignment))) { table->AcDcGpio = gpio_pin_assignment.uc_gpio_pin_bit_shift; phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_AutomaticDCTransition); @@ -3084,8 +3065,7 @@ int tonga_init_smc_table(struct pp_hwmgr *hwmgr) } reg_value = 0; - if ((0 == reg_value) && - (0 == atomctrl_get_pp_assign_pin(hwmgr, + if ((0 == reg_value) && (atomctrl_get_pp_assign_pin(hwmgr, THERMAL_INT_OUTPUT_GPIO_PINID, &gpio_pin_assignment))) { phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_ThermalOutGPIO); @@ -3156,7 +3136,7 @@ int tonga_upload_dpm_level_enable_mask(struct pp_hwmgr *hwmgr) if (0 == data->sclk_dpm_key_disabled) { /* Checking if DPM is running. If we discover hang because of this, we should skip this message.*/ - if (0 != tonga_is_dpm_running(hwmgr)) + if (tonga_is_dpm_running(hwmgr)) printk(KERN_ERR "[ powerplay ] Trying to set Enable Mask when DPM is disabled \n"); if (0 != data->dpm_level_enable_mask.sclk_dpm_enable_mask) { @@ -3171,7 +3151,7 @@ int tonga_upload_dpm_level_enable_mask(struct pp_hwmgr *hwmgr) if (0 == data->mclk_dpm_key_disabled) { /* Checking if DPM is running. If we discover hang because of this, we should skip this message.*/ - if (0 != tonga_is_dpm_running(hwmgr)) + if (tonga_is_dpm_running(hwmgr)) printk(KERN_ERR "[ powerplay ] Trying to set Enable Mask when DPM is disabled \n"); if (0 != data->dpm_level_enable_mask.mclk_dpm_enable_mask) { @@ -3282,7 +3262,7 @@ int tonga_initializa_dynamic_state_adjustment_rule_settings(struct pp_hwmgr *hwm /* initialize vddc_dep_on_dal_pwrl table */ table_size = sizeof(uint32_t) + 4 * sizeof(struct phm_clock_voltage_dependency_record); - table_clk_vlt = (struct phm_clock_voltage_dependency_table *)kzalloc(table_size, GFP_KERNEL); + table_clk_vlt = kzalloc(table_size, GFP_KERNEL); if (NULL == table_clk_vlt) { printk(KERN_ERR "[ powerplay ] Can not allocate space for vddc_dep_on_dal_pwrl! \n"); @@ -3357,9 +3337,9 @@ int tonga_unforce_dpm_levels(struct pp_hwmgr *hwmgr) tonga_hwmgr *data = (tonga_hwmgr *)(hwmgr->backend); int result = 1; - PP_ASSERT_WITH_CODE (0 == tonga_is_dpm_running(hwmgr), - "Trying to Unforce DPM when DPM is disabled. Returning without sending SMC message.", - return result); + PP_ASSERT_WITH_CODE (!tonga_is_dpm_running(hwmgr), + "Trying to Unforce DPM when DPM is disabled. Returning without sending SMC message.", + return result); if (0 == data->pcie_dpm_key_disabled) { PP_ASSERT_WITH_CODE((0 == smum_send_msg_to_smc( @@ -3763,7 +3743,7 @@ uint8_t tonga_get_memory_modile_index(struct pp_hwmgr *hwmgr) bool tonga_check_s0_mc_reg_index(uint16_t inReg, uint16_t *outReg) { - bool result = 1; + bool result = true; switch (inReg) { case mmMC_SEQ_RAS_TIMING: @@ -3847,7 +3827,7 @@ bool tonga_check_s0_mc_reg_index(uint16_t inReg, uint16_t *outReg) break; default: - result = 0; + result = false; break; } @@ -4443,13 +4423,6 @@ int tonga_reset_asic_tasks(struct pp_hwmgr *hwmgr) int tonga_hwmgr_backend_fini(struct pp_hwmgr *hwmgr) { - struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend); - - if (data->soft_pp_table) { - kfree(data->soft_pp_table); - data->soft_pp_table = NULL; - } - return phm_hwmgr_backend_fini(hwmgr); } @@ -4463,7 +4436,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr) { int result = 0; SMU72_Discrete_DpmTable *table = NULL; - tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend); + tonga_hwmgr *data; pp_atomctrl_gpio_pin_assignment gpio_pin_assignment; struct phm_ppt_v1_information *pptable_info = (struct phm_ppt_v1_information *)(hwmgr->pptable); phw_tonga_ulv_parm *ulv; @@ -4472,7 +4445,13 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr) PP_ASSERT_WITH_CODE((NULL != hwmgr), "Invalid Parameter!", return -1;); - data->dll_defaule_on = 0; + data = kzalloc(sizeof(struct tonga_hwmgr), GFP_KERNEL); + if (data == NULL) + return -ENOMEM; + + hwmgr->backend = data; + + data->dll_defaule_on = false; data->sram_end = SMC_RAM_END; data->activity_target[0] = PPTONGA_TARGETACTIVITY_DFLT; @@ -4510,6 +4489,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr) data->vdd_ci_control = TONGA_VOLTAGE_CONTROL_NONE; data->vdd_gfx_control = TONGA_VOLTAGE_CONTROL_NONE; data->mvdd_control = TONGA_VOLTAGE_CONTROL_NONE; + data->force_pcie_gen = PP_PCIEGenInvalid; if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr, VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2)) { @@ -4577,13 +4557,13 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr) /* ULV Support*/ ulv = &(data->ulv); - ulv->ulv_supported = 0; + ulv->ulv_supported = false; /* Initalize Dynamic State Adjustment Rule Settings*/ result = tonga_initializa_dynamic_state_adjustment_rule_settings(hwmgr); if (result) printk(KERN_ERR "[ powerplay ] tonga_initializa_dynamic_state_adjustment_rule_settings failed!\n"); - data->uvd_enabled = 0; + data->uvd_enabled = false; table = &(data->smc_state_table); @@ -4591,7 +4571,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr) * if ucGPIO_ID=VDDC_PCC_GPIO_PINID in GPIO_LUTable, * Peak Current Control feature is enabled and we should program PCC HW register */ - if (0 == atomctrl_get_pp_assign_pin(hwmgr, VDDC_PCC_GPIO_PINID, &gpio_pin_assignment)) { + if (atomctrl_get_pp_assign_pin(hwmgr, VDDC_PCC_GPIO_PINID, &gpio_pin_assignment)) { uint32_t temp_reg = cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixCNB_PWRMGT_CNTL); @@ -4630,7 +4610,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr) phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_SMU7); - data->vddc_phase_shed_control = 0; + data->vddc_phase_shed_control = false; phm_cap_unset(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_UVDPowerGating); @@ -4649,7 +4629,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr) } if (0 == result) { - data->is_tlu_enabled = 0; + data->is_tlu_enabled = false; hwmgr->platform_descriptor.hardwareActivityPerformanceLevels = TONGA_MAX_HARDWARE_POWERLEVELS; hwmgr->platform_descriptor.hardwarePerformanceLevels = 2; @@ -4659,7 +4639,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr) sys_info.info_id = CGS_SYSTEM_INFO_PCIE_GEN_INFO; result = cgs_query_system_info(hwmgr->device, &sys_info); if (result) - data->pcie_gen_cap = 0x30007; + data->pcie_gen_cap = AMDGPU_DEFAULT_PCIE_GEN_MASK; else data->pcie_gen_cap = (uint32_t)sys_info.value; if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) @@ -4668,7 +4648,7 @@ int tonga_hwmgr_backend_init(struct pp_hwmgr *hwmgr) sys_info.info_id = CGS_SYSTEM_INFO_PCIE_MLW; result = cgs_query_system_info(hwmgr->device, &sys_info); if (result) - data->pcie_lane_cap = 0x2f0000; + data->pcie_lane_cap = AMDGPU_DEFAULT_PCIE_MLW_MASK; else data->pcie_lane_cap = (uint32_t)sys_info.value; } else { @@ -5330,9 +5310,8 @@ static int tonga_freeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) if ((0 == data->sclk_dpm_key_disabled) && (data->need_update_smu7_dpm_table & (DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK))) { - PP_ASSERT_WITH_CODE( - 0 == tonga_is_dpm_running(hwmgr), - "Trying to freeze SCLK DPM when DPM is disabled", + PP_ASSERT_WITH_CODE(!tonga_is_dpm_running(hwmgr), + "Trying to freeze SCLK DPM when DPM is disabled", ); PP_ASSERT_WITH_CODE( 0 == smum_send_msg_to_smc(hwmgr->smumgr, @@ -5344,8 +5323,8 @@ static int tonga_freeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) if ((0 == data->mclk_dpm_key_disabled) && (data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_MCLK)) { - PP_ASSERT_WITH_CODE(0 == tonga_is_dpm_running(hwmgr), - "Trying to freeze MCLK DPM when DPM is disabled", + PP_ASSERT_WITH_CODE(!tonga_is_dpm_running(hwmgr), + "Trying to freeze MCLK DPM when DPM is disabled", ); PP_ASSERT_WITH_CODE( 0 == smum_send_msg_to_smc(hwmgr->smumgr, @@ -5480,7 +5459,6 @@ static int tonga_trim_single_dpm_states(struct pp_hwmgr *hwmgr, static int tonga_trim_dpm_states(struct pp_hwmgr *hwmgr, const struct tonga_power_state *hw_state) { - int result = 0; struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend); uint32_t high_limit_count; @@ -5500,7 +5478,7 @@ static int tonga_trim_dpm_states(struct pp_hwmgr *hwmgr, const struct tonga_powe hw_state->performance_levels[0].memory_clock, hw_state->performance_levels[high_limit_count].memory_clock); - return result; + return 0; } static int tonga_generate_dpm_level_enable_mask(struct pp_hwmgr *hwmgr, const void *input) @@ -5647,8 +5625,8 @@ static int tonga_unfreeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) (data->need_update_smu7_dpm_table & (DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK))) { - PP_ASSERT_WITH_CODE(0 == tonga_is_dpm_running(hwmgr), - "Trying to Unfreeze SCLK DPM when DPM is disabled", + PP_ASSERT_WITH_CODE(!tonga_is_dpm_running(hwmgr), + "Trying to Unfreeze SCLK DPM when DPM is disabled", ); PP_ASSERT_WITH_CODE( 0 == smum_send_msg_to_smc(hwmgr->smumgr, @@ -5660,9 +5638,8 @@ static int tonga_unfreeze_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) if ((0 == data->mclk_dpm_key_disabled) && (data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_MCLK)) { - PP_ASSERT_WITH_CODE( - 0 == tonga_is_dpm_running(hwmgr), - "Trying to Unfreeze MCLK DPM when DPM is disabled", + PP_ASSERT_WITH_CODE(!tonga_is_dpm_running(hwmgr), + "Trying to Unfreeze MCLK DPM when DPM is disabled", ); PP_ASSERT_WITH_CODE( 0 == smum_send_msg_to_smc(hwmgr->smumgr, @@ -6051,42 +6028,6 @@ static int tonga_get_fan_control_mode(struct pp_hwmgr *hwmgr) CG_FDO_CTRL2, FDO_PWM_MODE); } -static int tonga_get_pp_table(struct pp_hwmgr *hwmgr, char **table) -{ - struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend); - - if (!data->soft_pp_table) { - data->soft_pp_table = kmemdup(hwmgr->soft_pp_table, - hwmgr->soft_pp_table_size, - GFP_KERNEL); - if (!data->soft_pp_table) - return -ENOMEM; - } - - *table = (char *)&data->soft_pp_table; - - return hwmgr->soft_pp_table_size; -} - -static int tonga_set_pp_table(struct pp_hwmgr *hwmgr, const char *buf, size_t size) -{ - struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend); - - if (!data->soft_pp_table) { - data->soft_pp_table = kzalloc(hwmgr->soft_pp_table_size, GFP_KERNEL); - if (!data->soft_pp_table) - return -ENOMEM; - } - - memcpy(data->soft_pp_table, buf, size); - - hwmgr->soft_pp_table = data->soft_pp_table; - - /* TODO: re-init powerplay to implement modified pptable */ - - return 0; -} - static int tonga_force_clock_level(struct pp_hwmgr *hwmgr, enum pp_clock_type type, uint32_t mask) { @@ -6194,11 +6135,96 @@ static int tonga_print_clock_levels(struct pp_hwmgr *hwmgr, return size; } +static int tonga_get_sclk_od(struct pp_hwmgr *hwmgr) +{ + struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend); + struct tonga_single_dpm_table *sclk_table = &(data->dpm_table.sclk_table); + struct tonga_single_dpm_table *golden_sclk_table = + &(data->golden_dpm_table.sclk_table); + int value; + + value = (sclk_table->dpm_levels[sclk_table->count - 1].value - + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value) * + 100 / + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value; + + return value; +} + +static int tonga_set_sclk_od(struct pp_hwmgr *hwmgr, uint32_t value) +{ + struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend); + struct tonga_single_dpm_table *golden_sclk_table = + &(data->golden_dpm_table.sclk_table); + struct pp_power_state *ps; + struct tonga_power_state *tonga_ps; + + if (value > 20) + value = 20; + + ps = hwmgr->request_ps; + + if (ps == NULL) + return -EINVAL; + + tonga_ps = cast_phw_tonga_power_state(&ps->hardware); + + tonga_ps->performance_levels[tonga_ps->performance_level_count - 1].engine_clock = + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value * + value / 100 + + golden_sclk_table->dpm_levels[golden_sclk_table->count - 1].value; + + return 0; +} + +static int tonga_get_mclk_od(struct pp_hwmgr *hwmgr) +{ + struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend); + struct tonga_single_dpm_table *mclk_table = &(data->dpm_table.mclk_table); + struct tonga_single_dpm_table *golden_mclk_table = + &(data->golden_dpm_table.mclk_table); + int value; + + value = (mclk_table->dpm_levels[mclk_table->count - 1].value - + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value) * + 100 / + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value; + + return value; +} + +static int tonga_set_mclk_od(struct pp_hwmgr *hwmgr, uint32_t value) +{ + struct tonga_hwmgr *data = (struct tonga_hwmgr *)(hwmgr->backend); + struct tonga_single_dpm_table *golden_mclk_table = + &(data->golden_dpm_table.mclk_table); + struct pp_power_state *ps; + struct tonga_power_state *tonga_ps; + + if (value > 20) + value = 20; + + ps = hwmgr->request_ps; + + if (ps == NULL) + return -EINVAL; + + tonga_ps = cast_phw_tonga_power_state(&ps->hardware); + + tonga_ps->performance_levels[tonga_ps->performance_level_count - 1].memory_clock = + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value * + value / 100 + + golden_mclk_table->dpm_levels[golden_mclk_table->count - 1].value; + + return 0; +} + static const struct pp_hwmgr_func tonga_hwmgr_funcs = { .backend_init = &tonga_hwmgr_backend_init, .backend_fini = &tonga_hwmgr_backend_fini, .asic_setup = &tonga_setup_asic_task, .dynamic_state_management_enable = &tonga_enable_dpm_tasks, + .dynamic_state_management_disable = &tonga_disable_dpm_tasks, .apply_state_adjust_rules = tonga_apply_state_adjust_rules, .force_dpm_level = &tonga_force_dpm_level, .power_state_set = tonga_set_power_state_tasks, @@ -6232,22 +6258,16 @@ static const struct pp_hwmgr_func tonga_hwmgr_funcs = { .check_states_equal = tonga_check_states_equal, .set_fan_control_mode = tonga_set_fan_control_mode, .get_fan_control_mode = tonga_get_fan_control_mode, - .get_pp_table = tonga_get_pp_table, - .set_pp_table = tonga_set_pp_table, .force_clock_level = tonga_force_clock_level, .print_clock_levels = tonga_print_clock_levels, + .get_sclk_od = tonga_get_sclk_od, + .set_sclk_od = tonga_set_sclk_od, + .get_mclk_od = tonga_get_mclk_od, + .set_mclk_od = tonga_set_mclk_od, }; int tonga_hwmgr_init(struct pp_hwmgr *hwmgr) { - tonga_hwmgr *data; - - data = kzalloc (sizeof(tonga_hwmgr), GFP_KERNEL); - if (data == NULL) - return -ENOMEM; - memset(data, 0x00, sizeof(tonga_hwmgr)); - - hwmgr->backend = data; hwmgr->hwmgr_func = &tonga_hwmgr_funcs; hwmgr->pptable_func = &tonga_pptable_funcs; pp_tonga_thermal_initialize(hwmgr); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.h index 573cd39fe78d..3961884bfa9b 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.h @@ -352,9 +352,6 @@ struct tonga_hwmgr { bool samu_power_gated; /* 1: gated, 0:not gated */ bool acp_power_gated; /* 1: gated, 0:not gated */ bool pg_acp_init; - - /* soft pptable for re-uploading into smu */ - void *soft_pp_table; }; typedef struct tonga_hwmgr tonga_hwmgr; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h index 1b44f4e9b8f5..f127198aafc4 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_pptable.h @@ -197,6 +197,22 @@ typedef struct _ATOM_Tonga_SCLK_Dependency_Table { ATOM_Tonga_SCLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ } ATOM_Tonga_SCLK_Dependency_Table; +typedef struct _ATOM_Polaris_SCLK_Dependency_Record { + UCHAR ucVddInd; /* Base voltage */ + USHORT usVddcOffset; /* Offset relative to base voltage */ + ULONG ulSclk; + USHORT usEdcCurrent; + UCHAR ucReliabilityTemperature; + UCHAR ucCKSVOffsetandDisable; /* Bits 0~6: Voltage offset for CKS, Bit 7: Disable/enable for the SCLK level. */ + ULONG ulSclkOffset; +} ATOM_Polaris_SCLK_Dependency_Record; + +typedef struct _ATOM_Polaris_SCLK_Dependency_Table { + UCHAR ucRevId; + UCHAR ucNumEntries; /* Number of entries. */ + ATOM_Polaris_SCLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ +} ATOM_Polaris_SCLK_Dependency_Table; + typedef struct _ATOM_Tonga_PCIE_Record { UCHAR ucPCIEGenSpeed; UCHAR usPCIELaneWidth; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c index 10e3630ee39d..cfb647f76cbe 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_processpptables.c @@ -167,8 +167,7 @@ static int get_vddc_lookup_table( table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_voltage_lookup_record) * max_levels; - table = (phm_ppt_v1_voltage_lookup_table *) - kzalloc(table_size, GFP_KERNEL); + table = kzalloc(table_size, GFP_KERNEL); if (NULL == table) return -ENOMEM; @@ -302,7 +301,7 @@ static int init_dpm_2_parameters( (((unsigned long)powerplay_table) + le16_to_cpu(powerplay_table->usPPMTableOffset)); if (0 != powerplay_table->usPPMTableOffset) { - if (1 == get_platform_power_management_table(hwmgr, atom_ppm_table)) { + if (get_platform_power_management_table(hwmgr, atom_ppm_table) == 0) { phm_cap_set(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_EnablePlatformPowerManagement); } @@ -327,7 +326,7 @@ static int get_valid_clk( table_size = sizeof(uint32_t) + sizeof(uint32_t) * clk_volt_pp_table->count; - table = (struct phm_clock_array *)kzalloc(table_size, GFP_KERNEL); + table = kzalloc(table_size, GFP_KERNEL); if (NULL == table) return -ENOMEM; @@ -377,8 +376,7 @@ static int get_mclk_voltage_dependency_table( table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record) * mclk_dep_table->ucNumEntries; - mclk_table = (phm_ppt_v1_clock_voltage_dependency_table *) - kzalloc(table_size, GFP_KERNEL); + mclk_table = kzalloc(table_size, GFP_KERNEL); if (NULL == mclk_table) return -ENOMEM; @@ -408,41 +406,76 @@ static int get_mclk_voltage_dependency_table( static int get_sclk_voltage_dependency_table( struct pp_hwmgr *hwmgr, phm_ppt_v1_clock_voltage_dependency_table **pp_tonga_sclk_dep_table, - const ATOM_Tonga_SCLK_Dependency_Table * sclk_dep_table + const PPTable_Generic_SubTable_Header *sclk_dep_table ) { uint32_t table_size, i; phm_ppt_v1_clock_voltage_dependency_table *sclk_table; - PP_ASSERT_WITH_CODE((0 != sclk_dep_table->ucNumEntries), - "Invalid PowerPlay Table!", return -1); + if (sclk_dep_table->ucRevId < 1) { + const ATOM_Tonga_SCLK_Dependency_Table *tonga_table = + (ATOM_Tonga_SCLK_Dependency_Table *)sclk_dep_table; - table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record) - * sclk_dep_table->ucNumEntries; + PP_ASSERT_WITH_CODE((0 != tonga_table->ucNumEntries), + "Invalid PowerPlay Table!", return -1); - sclk_table = (phm_ppt_v1_clock_voltage_dependency_table *) - kzalloc(table_size, GFP_KERNEL); + table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record) + * tonga_table->ucNumEntries; - if (NULL == sclk_table) - return -ENOMEM; + sclk_table = kzalloc(table_size, GFP_KERNEL); - memset(sclk_table, 0x00, table_size); + if (NULL == sclk_table) + return -ENOMEM; - sclk_table->count = (uint32_t)sclk_dep_table->ucNumEntries; + memset(sclk_table, 0x00, table_size); - for (i = 0; i < sclk_dep_table->ucNumEntries; i++) { - sclk_table->entries[i].vddInd = - sclk_dep_table->entries[i].ucVddInd; - sclk_table->entries[i].vdd_offset = - sclk_dep_table->entries[i].usVddcOffset; - sclk_table->entries[i].clk = - sclk_dep_table->entries[i].ulSclk; - sclk_table->entries[i].cks_enable = - (((sclk_dep_table->entries[i].ucCKSVOffsetandDisable & 0x80) >> 7) == 0) ? 1 : 0; - sclk_table->entries[i].cks_voffset = - (sclk_dep_table->entries[i].ucCKSVOffsetandDisable & 0x7F); + sclk_table->count = (uint32_t)tonga_table->ucNumEntries; + + for (i = 0; i < tonga_table->ucNumEntries; i++) { + sclk_table->entries[i].vddInd = + tonga_table->entries[i].ucVddInd; + sclk_table->entries[i].vdd_offset = + tonga_table->entries[i].usVddcOffset; + sclk_table->entries[i].clk = + tonga_table->entries[i].ulSclk; + sclk_table->entries[i].cks_enable = + (((tonga_table->entries[i].ucCKSVOffsetandDisable & 0x80) >> 7) == 0) ? 1 : 0; + sclk_table->entries[i].cks_voffset = + (tonga_table->entries[i].ucCKSVOffsetandDisable & 0x7F); + } + } else { + const ATOM_Polaris_SCLK_Dependency_Table *polaris_table = + (ATOM_Polaris_SCLK_Dependency_Table *)sclk_dep_table; + + PP_ASSERT_WITH_CODE((0 != polaris_table->ucNumEntries), + "Invalid PowerPlay Table!", return -1); + + table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_clock_voltage_dependency_record) + * polaris_table->ucNumEntries; + + sclk_table = kzalloc(table_size, GFP_KERNEL); + + if (NULL == sclk_table) + return -ENOMEM; + + memset(sclk_table, 0x00, table_size); + + sclk_table->count = (uint32_t)polaris_table->ucNumEntries; + + for (i = 0; i < polaris_table->ucNumEntries; i++) { + sclk_table->entries[i].vddInd = + polaris_table->entries[i].ucVddInd; + sclk_table->entries[i].vdd_offset = + polaris_table->entries[i].usVddcOffset; + sclk_table->entries[i].clk = + polaris_table->entries[i].ulSclk; + sclk_table->entries[i].cks_enable = + (((polaris_table->entries[i].ucCKSVOffsetandDisable & 0x80) >> 7) == 0) ? 1 : 0; + sclk_table->entries[i].cks_voffset = + (polaris_table->entries[i].ucCKSVOffsetandDisable & 0x7F); + sclk_table->entries[i].sclk_offset = polaris_table->entries[i].ulSclkOffset; + } } - *pp_tonga_sclk_dep_table = sclk_table; return 0; @@ -467,7 +500,7 @@ static int get_pcie_table( table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_pcie_record) * atom_pcie_table->ucNumEntries; - pcie_table = (phm_ppt_v1_pcie_table *)kzalloc(table_size, GFP_KERNEL); + pcie_table = kzalloc(table_size, GFP_KERNEL); if (pcie_table == NULL) return -ENOMEM; @@ -504,7 +537,7 @@ static int get_pcie_table( table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_pcie_record) * atom_pcie_table->ucNumEntries; - pcie_table = (phm_ppt_v1_pcie_table *)kzalloc(table_size, GFP_KERNEL); + pcie_table = kzalloc(table_size, GFP_KERNEL); if (pcie_table == NULL) return -ENOMEM; @@ -658,8 +691,7 @@ static int get_mm_clock_voltage_table( table_size = sizeof(uint32_t) + sizeof(phm_ppt_v1_mm_clock_voltage_dependency_record) * mm_dependency_table->ucNumEntries; - mm_table = (phm_ppt_v1_mm_clock_voltage_dependency_table *) - kzalloc(table_size, GFP_KERNEL); + mm_table = kzalloc(table_size, GFP_KERNEL); if (NULL == mm_table) return -ENOMEM; @@ -708,8 +740,8 @@ static int init_clock_voltage_dependency( const ATOM_Tonga_MCLK_Dependency_Table *mclk_dep_table = (const ATOM_Tonga_MCLK_Dependency_Table *)(((unsigned long) powerplay_table) + le16_to_cpu(powerplay_table->usMclkDependencyTableOffset)); - const ATOM_Tonga_SCLK_Dependency_Table *sclk_dep_table = - (const ATOM_Tonga_SCLK_Dependency_Table *)(((unsigned long) powerplay_table) + + const PPTable_Generic_SubTable_Header *sclk_dep_table = + (const PPTable_Generic_SubTable_Header *)(((unsigned long) powerplay_table) + le16_to_cpu(powerplay_table->usSclkDependencyTableOffset)); const ATOM_Tonga_Hard_Limit_Table *pHardLimits = (const ATOM_Tonga_Hard_Limit_Table *)(((unsigned long) powerplay_table) + @@ -1036,54 +1068,46 @@ int tonga_pp_tables_initialize(struct pp_hwmgr *hwmgr) int tonga_pp_tables_uninitialize(struct pp_hwmgr *hwmgr) { - int result = 0; struct phm_ppt_v1_information *pp_table_information = (struct phm_ppt_v1_information *)(hwmgr->pptable); - if (NULL != hwmgr->soft_pp_table) { - kfree(hwmgr->soft_pp_table); - hwmgr->soft_pp_table = NULL; - } + kfree(pp_table_information->vdd_dep_on_sclk); + pp_table_information->vdd_dep_on_sclk = NULL; - if (NULL != pp_table_information->vdd_dep_on_sclk) - pp_table_information->vdd_dep_on_sclk = NULL; + kfree(pp_table_information->vdd_dep_on_mclk); + pp_table_information->vdd_dep_on_mclk = NULL; - if (NULL != pp_table_information->vdd_dep_on_mclk) - pp_table_information->vdd_dep_on_mclk = NULL; + kfree(pp_table_information->valid_mclk_values); + pp_table_information->valid_mclk_values = NULL; - if (NULL != pp_table_information->valid_mclk_values) - pp_table_information->valid_mclk_values = NULL; + kfree(pp_table_information->valid_sclk_values); + pp_table_information->valid_sclk_values = NULL; - if (NULL != pp_table_information->valid_sclk_values) - pp_table_information->valid_sclk_values = NULL; + kfree(pp_table_information->vddc_lookup_table); + pp_table_information->vddc_lookup_table = NULL; - if (NULL != pp_table_information->vddc_lookup_table) - pp_table_information->vddc_lookup_table = NULL; + kfree(pp_table_information->vddgfx_lookup_table); + pp_table_information->vddgfx_lookup_table = NULL; - if (NULL != pp_table_information->vddgfx_lookup_table) - pp_table_information->vddgfx_lookup_table = NULL; + kfree(pp_table_information->mm_dep_table); + pp_table_information->mm_dep_table = NULL; - if (NULL != pp_table_information->mm_dep_table) - pp_table_information->mm_dep_table = NULL; + kfree(pp_table_information->cac_dtp_table); + pp_table_information->cac_dtp_table = NULL; - if (NULL != pp_table_information->cac_dtp_table) - pp_table_information->cac_dtp_table = NULL; + kfree(hwmgr->dyn_state.cac_dtp_table); + hwmgr->dyn_state.cac_dtp_table = NULL; - if (NULL != hwmgr->dyn_state.cac_dtp_table) - hwmgr->dyn_state.cac_dtp_table = NULL; + kfree(pp_table_information->ppm_parameter_table); + pp_table_information->ppm_parameter_table = NULL; - if (NULL != pp_table_information->ppm_parameter_table) - pp_table_information->ppm_parameter_table = NULL; + kfree(pp_table_information->pcie_table); + pp_table_information->pcie_table = NULL; - if (NULL != pp_table_information->pcie_table) - pp_table_information->pcie_table = NULL; + kfree(hwmgr->pptable); + hwmgr->pptable = NULL; - if (NULL != hwmgr->pptable) { - kfree(hwmgr->pptable); - hwmgr->pptable = NULL; - } - - return result; + return 0; } const struct pp_table_func tonga_pptable_funcs = { diff --git a/drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h b/drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h index 50b367d44307..b764c8c05ec8 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h +++ b/drivers/gpu/drm/amd/powerplay/inc/amd_powerplay.h @@ -132,6 +132,7 @@ struct amd_pp_init { uint32_t chip_family; uint32_t chip_id; uint32_t rev_id; + bool powercontainment_enabled; }; enum amd_pp_display_config_type{ AMD_PP_DisplayConfigType_None = 0, @@ -342,6 +343,10 @@ struct amd_powerplay_funcs { int (*set_pp_table)(void *handle, const char *buf, size_t size); int (*force_clock_level)(void *handle, enum pp_clock_type type, uint32_t mask); int (*print_clock_levels)(void *handle, enum pp_clock_type type, char *buf); + int (*get_sclk_od)(void *handle); + int (*set_sclk_od)(void *handle, uint32_t value); + int (*get_mclk_od)(void *handle); + int (*set_mclk_od)(void *handle, uint32_t value); }; struct amd_powerplay { @@ -355,6 +360,8 @@ int amd_powerplay_init(struct amd_pp_init *pp_init, int amd_powerplay_fini(void *handle); +int amd_powerplay_reset(void *handle); + int amd_powerplay_display_configuration_change(void *handle, const struct amd_pp_display_configuration *input); diff --git a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h b/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h index 56f712c7d07a..962cb5385951 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h +++ b/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h @@ -340,6 +340,7 @@ extern int phm_powergate_vce(struct pp_hwmgr *hwmgr, bool gate); extern int phm_powerdown_uvd(struct pp_hwmgr *hwmgr); extern int phm_setup_asic(struct pp_hwmgr *hwmgr); extern int phm_enable_dynamic_state_management(struct pp_hwmgr *hwmgr); +extern int phm_disable_dynamic_state_management(struct pp_hwmgr *hwmgr); extern void phm_init_dynamic_caps(struct pp_hwmgr *hwmgr); extern bool phm_is_hw_access_blocked(struct pp_hwmgr *hwmgr); extern int phm_block_hw_access(struct pp_hwmgr *hwmgr, bool block); diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h index 28f571449495..bf0d2accf7bf 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h +++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h @@ -278,6 +278,8 @@ struct pp_hwmgr_func { int (*dynamic_state_management_enable)( struct pp_hwmgr *hw_mgr); + int (*dynamic_state_management_disable)( + struct pp_hwmgr *hw_mgr); int (*patch_boot_state)(struct pp_hwmgr *hwmgr, struct pp_hw_power_state *hw_ps); @@ -333,11 +335,13 @@ struct pp_hwmgr_func { int (*get_clock_by_type)(struct pp_hwmgr *hwmgr, enum amd_pp_clock_type type, struct amd_pp_clocks *clocks); int (*get_max_high_clocks)(struct pp_hwmgr *hwmgr, struct amd_pp_simple_clock_info *clocks); int (*power_off_asic)(struct pp_hwmgr *hwmgr); - int (*get_pp_table)(struct pp_hwmgr *hwmgr, char **table); - int (*set_pp_table)(struct pp_hwmgr *hwmgr, const char *buf, size_t size); int (*force_clock_level)(struct pp_hwmgr *hwmgr, enum pp_clock_type type, uint32_t mask); int (*print_clock_levels)(struct pp_hwmgr *hwmgr, enum pp_clock_type type, char *buf); int (*enable_per_cu_power_gating)(struct pp_hwmgr *hwmgr, bool enable); + int (*get_sclk_od)(struct pp_hwmgr *hwmgr); + int (*set_sclk_od)(struct pp_hwmgr *hwmgr, uint32_t value); + int (*get_mclk_od)(struct pp_hwmgr *hwmgr); + int (*set_mclk_od)(struct pp_hwmgr *hwmgr, uint32_t value); }; struct pp_table_func { @@ -411,6 +415,8 @@ struct phm_cac_tdp_table { uint8_t ucVr_I2C_Line; uint8_t ucPlx_I2C_address; uint8_t ucPlx_I2C_Line; + uint32_t usBoostPowerLimit; + uint8_t ucCKS_LDO_REFSEL; }; struct phm_ppm_table { @@ -578,6 +584,7 @@ struct pp_hwmgr { struct pp_smumgr *smumgr; const void *soft_pp_table; uint32_t soft_pp_table_size; + void *hardcode_pp_table; bool need_pp_table_upload; enum amd_dpm_forced_level dpm_level; bool block_hw_access; @@ -607,6 +614,7 @@ struct pp_hwmgr { uint32_t num_ps; struct pp_thermal_controller_info thermal_controller; bool fan_ctrl_is_in_default_mode; + bool powercontainment_enabled; uint32_t fan_ctrl_default_mode; uint32_t tmin; struct phm_microcode_version_info microcode_version_info; diff --git a/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h index 0c6a413eaa5b..b8f4b73c322e 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h +++ b/drivers/gpu/drm/amd/powerplay/inc/polaris10_ppsmc.h @@ -27,6 +27,7 @@ #pragma pack(push, 1) +#define PPSMC_MSG_SetGBDroopSettings ((uint16_t) 0x305) #define PPSMC_SWSTATE_FLAG_DC 0x01 #define PPSMC_SWSTATE_FLAG_UVD 0x02 @@ -391,6 +392,8 @@ typedef uint16_t PPSMC_Result; #define PPSMC_MSG_SetGpuPllDfsForSclk ((uint16_t) 0x300) #define PPSMC_MSG_Didt_Block_Function ((uint16_t) 0x301) +#define PPSMC_MSG_SetVBITimeout ((uint16_t) 0x306) + #define PPSMC_MSG_SecureSRBMWrite ((uint16_t) 0x600) #define PPSMC_MSG_SecureSRBMRead ((uint16_t) 0x601) #define PPSMC_MSG_SetAddress ((uint16_t) 0x800) diff --git a/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h b/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h index 3bd5e69b9045..3df5de2cdab0 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h +++ b/drivers/gpu/drm/amd/powerplay/inc/pp_acpi.h @@ -26,3 +26,4 @@ extern bool acpi_atcs_functions_supported(void *device, extern int acpi_pcie_perf_request(void *device, uint8_t perf_req, bool advertise); +extern bool acpi_atcs_notify_pcie_device_ready(void *device); diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu74.h b/drivers/gpu/drm/amd/powerplay/inc/smu74.h index 1a12d85b8e97..fd10a9fa843d 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/smu74.h +++ b/drivers/gpu/drm/amd/powerplay/inc/smu74.h @@ -34,6 +34,30 @@ #define SMU__NUM_LCLK_DPM_LEVELS 8 #define SMU__NUM_PCIE_DPM_LEVELS 8 +#define EXP_M1 35 +#define EXP_M2 92821 +#define EXP_B 66629747 + +#define EXP_M1_1 365 +#define EXP_M2_1 658700 +#define EXP_B_1 305506134 + +#define EXP_M1_2 189 +#define EXP_M2_2 379692 +#define EXP_B_2 194609469 + +#define EXP_M1_3 99 +#define EXP_M2_3 217915 +#define EXP_B_3 122255994 + +#define EXP_M1_4 51 +#define EXP_M2_4 122643 +#define EXP_B_4 74893384 + +#define EXP_M1_5 423 +#define EXP_M2_5 1103326 +#define EXP_B_5 728122621 + enum SID_OPTION { SID_OPTION_HI, SID_OPTION_LO, @@ -548,20 +572,20 @@ struct SMU74_Firmware_Header { uint32_t CacConfigTable; uint32_t CacStatusTable; - uint32_t mcRegisterTable; - uint32_t mcArbDramTimingTable; - - - uint32_t PmFuseTable; uint32_t Globals; uint32_t ClockStretcherTable; uint32_t VftTable; - uint32_t Reserved[21]; + uint32_t Reserved1; + uint32_t AvfsTable; + uint32_t AvfsCksOffGbvTable; + uint32_t AvfsMeanNSigma; + uint32_t AvfsSclkOffsetTable; + uint32_t Reserved[16]; uint32_t Signature; }; @@ -701,8 +725,6 @@ VR Config info is contained in dpmTable.VRConfig */ struct SMU_ClockStretcherDataTableEntry { uint8_t minVID; uint8_t maxVID; - - uint16_t setting; }; typedef struct SMU_ClockStretcherDataTableEntry SMU_ClockStretcherDataTableEntry; @@ -769,6 +791,43 @@ struct VFT_TABLE_t { typedef struct VFT_TABLE_t VFT_TABLE_t; +/* Total margin, root mean square of Fmax + DC + Platform */ +struct AVFS_Margin_t { + VFT_CELL_t Cell[NUM_VFT_COLUMNS]; +}; +typedef struct AVFS_Margin_t AVFS_Margin_t; + +#define BTCGB_VDROOP_TABLE_MAX_ENTRIES 2 +#define AVFSGB_VDROOP_TABLE_MAX_ENTRIES 2 + +struct GB_VDROOP_TABLE_t { + int32_t a0; + int32_t a1; + int32_t a2; + uint32_t spare; +}; +typedef struct GB_VDROOP_TABLE_t GB_VDROOP_TABLE_t; + +struct AVFS_CksOff_Gbv_t { + VFT_CELL_t Cell[NUM_VFT_COLUMNS]; +}; +typedef struct AVFS_CksOff_Gbv_t AVFS_CksOff_Gbv_t; + +struct AVFS_meanNsigma_t { + uint32_t Aconstant[3]; + uint16_t DC_tol_sigma; + uint16_t Platform_mean; + uint16_t Platform_sigma; + uint16_t PSM_Age_CompFactor; + uint8_t Static_Voltage_Offset[NUM_VFT_COLUMNS]; +}; +typedef struct AVFS_meanNsigma_t AVFS_meanNsigma_t; + +struct AVFS_Sclk_Offset_t { + uint16_t Sclk_Offset[8]; +}; +typedef struct AVFS_Sclk_Offset_t AVFS_Sclk_Offset_t; + #endif diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h b/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h index 0dfe82336dc7..899d6d8108c2 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h +++ b/drivers/gpu/drm/amd/powerplay/inc/smu74_discrete.h @@ -223,6 +223,16 @@ struct SMU74_Discrete_StateInfo { typedef struct SMU74_Discrete_StateInfo SMU74_Discrete_StateInfo; +struct SMU_QuadraticCoeffs { + int32_t m1; + uint32_t b; + + int16_t m2; + uint8_t m1_shift; + uint8_t m2_shift; +}; +typedef struct SMU_QuadraticCoeffs SMU_QuadraticCoeffs; + struct SMU74_Discrete_DpmTable { SMU74_PIDController GraphicsPIDController; @@ -258,7 +268,15 @@ struct SMU74_Discrete_DpmTable { uint8_t ThermOutPolarity; uint8_t ThermOutMode; uint8_t BootPhases; - uint32_t Reserved[4]; + + uint8_t VRHotLevel; + uint8_t LdoRefSel; + uint8_t Reserved1[2]; + uint16_t FanStartTemperature; + uint16_t FanStopTemperature; + uint16_t MaxVoltage; + uint16_t Reserved2; + uint32_t Reserved[1]; SMU74_Discrete_GraphicsLevel GraphicsLevel[SMU74_MAX_LEVELS_GRAPHICS]; SMU74_Discrete_MemoryLevel MemoryACPILevel; @@ -347,6 +365,8 @@ struct SMU74_Discrete_DpmTable { uint32_t CurrSclkPllRange; sclkFcwRange_t SclkFcwRangeTable[NUM_SCLK_RANGE]; + GB_VDROOP_TABLE_t BTCGB_VDROOP_TABLE[BTCGB_VDROOP_TABLE_MAX_ENTRIES]; + SMU_QuadraticCoeffs AVFSGB_VDROOP_TABLE[AVFSGB_VDROOP_TABLE_MAX_ENTRIES]; }; typedef struct SMU74_Discrete_DpmTable SMU74_Discrete_DpmTable; @@ -550,16 +570,6 @@ struct SMU7_AcpiScoreboard { typedef struct SMU7_AcpiScoreboard SMU7_AcpiScoreboard; -struct SMU_QuadraticCoeffs { - int32_t m1; - uint32_t b; - - int16_t m2; - uint8_t m1_shift; - uint8_t m2_shift; -}; -typedef struct SMU_QuadraticCoeffs SMU_QuadraticCoeffs; - struct SMU74_Discrete_PmFuses { uint8_t BapmVddCVidHiSidd[8]; uint8_t BapmVddCVidLoSidd[8]; @@ -821,6 +831,17 @@ typedef struct SMU7_GfxCuPgScoreboard SMU7_GfxCuPgScoreboard; #define DB_PCC_SHIFT 26 #define DB_EDC_SHIFT 27 +#define BTCGB0_Vdroop_Enable_MASK 0x1 +#define BTCGB1_Vdroop_Enable_MASK 0x2 +#define AVFSGB0_Vdroop_Enable_MASK 0x4 +#define AVFSGB1_Vdroop_Enable_MASK 0x8 + +#define BTCGB0_Vdroop_Enable_SHIFT 0 +#define BTCGB1_Vdroop_Enable_SHIFT 1 +#define AVFSGB0_Vdroop_Enable_SHIFT 2 +#define AVFSGB1_Vdroop_Enable_SHIFT 3 + + #pragma pack(pop) diff --git a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h index fc9e3d1dd409..3c235f0177cd 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h +++ b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h @@ -131,6 +131,12 @@ extern int smu_free_memory(void *device, void *handle); smum_wait_on_indirect_register(smumgr, \ mm##port##_INDEX, index, value, mask) +#define SMUM_WAIT_INDIRECT_REGISTER(smumgr, port, reg, value, mask) \ + SMUM_WAIT_INDIRECT_REGISTER_GIVEN_INDEX(smumgr, port, ix##reg, value, mask) + +#define SMUM_WAIT_INDIRECT_FIELD(smumgr, port, reg, field, fieldval) \ + SMUM_WAIT_INDIRECT_REGISTER(smumgr, port, reg, (fieldval) << SMUM_FIELD_SHIFT(reg, field), \ + SMUM_FIELD_MASK(reg, field) ) #define SMUM_WAIT_REGISTER_UNEQUAL_GIVEN_INDEX(smumgr, \ index, value, mask) \ @@ -158,6 +164,10 @@ extern int smu_free_memory(void *device, void *handle); (SMUM_FIELD_MASK(reg, field) & ((field_val) << \ SMUM_FIELD_SHIFT(reg, field)))) +#define SMUM_READ_INDIRECT_FIELD(device, port, reg, field) \ + SMUM_GET_FIELD(cgs_read_ind_register(device, port, ix##reg), \ + reg, field) + #define SMUM_WAIT_VFPF_INDIRECT_REGISTER_GIVEN_INDEX(smumgr, \ port, index, value, mask) \ smum_wait_on_indirect_register(smumgr, \ @@ -191,6 +201,13 @@ extern int smu_free_memory(void *device, void *handle); SMUM_SET_FIELD(cgs_read_ind_register(device, port, ix##reg), \ reg, field, fieldval)) + +#define SMUM_WRITE_INDIRECT_FIELD(device, port, reg, field, fieldval) \ + cgs_write_ind_register(device, port, ix##reg, \ + SMUM_SET_FIELD(cgs_read_ind_register(device, port, ix##reg), \ + reg, field, fieldval)) + + #define SMUM_WAIT_VFPF_INDIRECT_FIELD(smumgr, port, reg, field, fieldval) \ SMUM_WAIT_VFPF_INDIRECT_REGISTER(smumgr, port, reg, \ (fieldval) << SMUM_FIELD_SHIFT(reg, field), \ @@ -200,4 +217,16 @@ extern int smu_free_memory(void *device, void *handle); SMUM_WAIT_VFPF_INDIRECT_REGISTER_UNEQUAL(smumgr, port, reg, \ (fieldval) << SMUM_FIELD_SHIFT(reg, field), \ SMUM_FIELD_MASK(reg, field)) + +#define SMUM_WAIT_INDIRECT_REGISTER_UNEQUAL_GIVEN_INDEX(smumgr, port, index, value, mask) \ + smum_wait_for_indirect_register_unequal(smumgr, \ + mm##port##_INDEX, index, value, mask) + +#define SMUM_WAIT_INDIRECT_REGISTER_UNEQUAL(smumgr, port, reg, value, mask) \ + SMUM_WAIT_INDIRECT_REGISTER_UNEQUAL_GIVEN_INDEX(smumgr, port, ix##reg, value, mask) + +#define SMUM_WAIT_INDIRECT_FIELD_UNEQUAL(smumgr, port, reg, field, fieldval) \ + SMUM_WAIT_INDIRECT_REGISTER_UNEQUAL(smumgr, port, reg, (fieldval) << SMUM_FIELD_SHIFT(reg, field), \ + SMUM_FIELD_MASK(reg, field) ) + #endif diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c index 673a75c74e18..8e52a2e82db5 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c @@ -1006,10 +1006,16 @@ static int fiji_smu_init(struct pp_smumgr *smumgr) static int fiji_smu_fini(struct pp_smumgr *smumgr) { + struct fiji_smumgr *priv = (struct fiji_smumgr *)(smumgr->backend); + + smu_free_memory(smumgr->device, (void *)priv->header_buffer.handle); + if (smumgr->backend) { kfree(smumgr->backend); smumgr->backend = NULL; } + + cgs_rel_firmware(smumgr->device, CGS_UCODE_ID_SMU); return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c index de618ead9db8..5dba7c509710 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c @@ -52,19 +52,18 @@ static const SMU74_Discrete_GraphicsLevel avfs_graphics_level_polaris10[8] = { /* Min pcie DeepSleep Activity CgSpll CgSpll CcPwr CcPwr Sclk Enabled Enabled Voltage Power */ /* Voltage, DpmLevel, DivId, Level, FuncCntl3, FuncCntl4, DynRm, DynRm1 Did, Padding,ForActivity, ForThrottle, UpHyst, DownHyst, DownHyst, Throttle */ - { 0x3c0fd047, 0x00, 0x03, 0x1e00, 0x00200410, 0x87020000, 0, 0, 0x16, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x30750000, 0, 0, 0, 0, 0, 0, 0 } }, - { 0xa00fd047, 0x01, 0x04, 0x1e00, 0x00800510, 0x87020000, 0, 0, 0x16, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x409c0000, 0, 0, 0, 0, 0, 0, 0 } }, - { 0x0410d047, 0x01, 0x00, 0x1e00, 0x00600410, 0x87020000, 0, 0, 0x0e, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x50c30000, 0, 0, 0, 0, 0, 0, 0 } }, - { 0x6810d047, 0x01, 0x00, 0x1e00, 0x00800410, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x60ea0000, 0, 0, 0, 0, 0, 0, 0 } }, - { 0xcc10d047, 0x01, 0x00, 0x1e00, 0x00e00410, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0xe8fd0000, 0, 0, 0, 0, 0, 0, 0 } }, - { 0x3011d047, 0x01, 0x00, 0x1e00, 0x00400510, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x70110100, 0, 0, 0, 0, 0, 0, 0 } }, - { 0x9411d047, 0x01, 0x00, 0x1e00, 0x00a00510, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0xf8240100, 0, 0, 0, 0, 0, 0, 0 } }, - { 0xf811d047, 0x01, 0x00, 0x1e00, 0x00000610, 0x87020000, 0, 0, 0x0c, 0, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, { 0x80380100, 0, 0, 0, 0, 0, 0, 0 } } + { 0x100ea446, 0x00, 0x03, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x30750000, 0x3000, 0, 0x2600, 0, 0, 0x0004, 0x8f02, 0xffff, 0x2f00, 0x300e, 0x2700 } }, + { 0x400ea446, 0x01, 0x04, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x409c0000, 0x2000, 0, 0x1e00, 1, 1, 0x0004, 0x8300, 0xffff, 0x1f00, 0xcb5e, 0x1a00 } }, + { 0x740ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x50c30000, 0x2800, 0, 0x2000, 1, 1, 0x0004, 0x0c02, 0xffff, 0x2700, 0x6433, 0x2100 } }, + { 0xa40ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x60ea0000, 0x3000, 0, 0x2600, 1, 1, 0x0004, 0x8f02, 0xffff, 0x2f00, 0x300e, 0x2700 } }, + { 0xd80ea446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x70110100, 0x3800, 0, 0x2c00, 1, 1, 0x0004, 0x1203, 0xffff, 0x3600, 0xc9e2, 0x2e00 } }, + { 0x3c0fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x80380100, 0x2000, 0, 0x1e00, 2, 1, 0x0004, 0x8300, 0xffff, 0x1f00, 0xcb5e, 0x1a00 } }, + { 0x6c0fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0x905f0100, 0x2400, 0, 0x1e00, 2, 1, 0x0004, 0x8901, 0xffff, 0x2300, 0x314c, 0x1d00 } }, + { 0xa00fa446, 0x01, 0x00, 0x3200, 0, 0, 0, 0, 0, 0, 0x01, 0x01, 0x0a, 0x00, 0x00, 0x00, { 0xa0860100, 0x2800, 0, 0x2000, 2, 1, 0x0004, 0x0c02, 0xffff, 0x2700, 0x6433, 0x2100 } } }; static const SMU74_Discrete_MemoryLevel avfs_memory_level_polaris10 = - {0x50140000, 0x50140000, 0x00320000, 0x00, 0x00, - 0x00, 0x10, 0x00, 0x00, 0x00, 0x00, 0x0000, 0x00, 0x00}; + {0x100ea446, 0, 0x30750000, 0x01, 0x01, 0x01, 0x00, 0x00, 0x64, 0x00, 0x00, 0x1f00, 0x00, 0x00}; /** * Set the address for reading/writing the SMC SRAM space. @@ -219,6 +218,18 @@ bool polaris10_is_smc_ram_running(struct pp_smumgr *smumgr) && (0x20100 <= cgs_read_ind_register(smumgr->device, CGS_IND_REG__SMC, ixSMC_PC_C))); } +static bool polaris10_is_hw_avfs_present(struct pp_smumgr *smumgr) +{ + uint32_t efuse; + + efuse = cgs_read_ind_register(smumgr->device, CGS_IND_REG__SMC, ixSMU_EFUSE_0 + (49*4)); + efuse &= 0x00000001; + if (efuse) + return true; + + return false; +} + /** * Send a message to the SMC, and wait for its response. * @@ -228,21 +239,27 @@ bool polaris10_is_smc_ram_running(struct pp_smumgr *smumgr) */ int polaris10_send_msg_to_smc(struct pp_smumgr *smumgr, uint16_t msg) { + int ret; + if (!polaris10_is_smc_ram_running(smumgr)) return -1; + SMUM_WAIT_FIELD_UNEQUAL(smumgr, SMC_RESP_0, SMC_RESP, 0); - if (1 != SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP)) - printk("Failed to send Previous Message.\n"); + ret = SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP); + if (ret != 1) + printk("\n failed to send pre message %x ret is %d \n", msg, ret); cgs_write_register(smumgr->device, mmSMC_MESSAGE_0, msg); SMUM_WAIT_FIELD_UNEQUAL(smumgr, SMC_RESP_0, SMC_RESP, 0); - if (1 != SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP)) - printk("Failed to send Message.\n"); + ret = SMUM_READ_FIELD(smumgr->device, SMC_RESP_0, SMC_RESP); + + if (ret != 1) + printk("\n failed to send message %x ret is %d \n", msg, ret); return 0; } @@ -469,6 +486,7 @@ int polaris10_smu_fini(struct pp_smumgr *smumgr) kfree(smumgr->backend); smumgr->backend = NULL; } + cgs_rel_firmware(smumgr->device, CGS_UCODE_ID_SMU); return 0; } @@ -952,6 +970,11 @@ static int polaris10_smu_init(struct pp_smumgr *smumgr) (cgs_handle_t)smu_data->smu_buffer.handle); return -1;); + if (polaris10_is_hw_avfs_present(smumgr)) + smu_data->avfs.avfs_btc_status = AVFS_BTC_BOOT; + else + smu_data->avfs.avfs_btc_status = AVFS_BTC_NOTSUPPORTED; + return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c index c483baf6b4fb..7723473e51a0 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "pp_instance.h" #include "smumgr.h" #include "cgs_common.h" @@ -52,10 +53,10 @@ int smum_init(struct amd_pp_init *pp_init, struct pp_instance *handle) handle->smu_mgr = smumgr; switch (smumgr->chip_family) { - case AMD_FAMILY_CZ: + case AMDGPU_FAMILY_CZ: cz_smum_init(smumgr); break; - case AMD_FAMILY_VI: + case AMDGPU_FAMILY_VI: switch (smumgr->chip_id) { case CHIP_TONGA: tonga_smum_init(smumgr); @@ -81,6 +82,7 @@ int smum_init(struct amd_pp_init *pp_init, struct pp_instance *handle) int smum_fini(struct pp_smumgr *smumgr) { + kfree(smumgr->device); kfree(smumgr); return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c index 32820b680d88..f42c536b3af1 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c @@ -328,10 +328,17 @@ int tonga_write_smc_sram_dword(struct pp_smumgr *smumgr, static int tonga_smu_fini(struct pp_smumgr *smumgr) { + struct tonga_smumgr *priv = (struct tonga_smumgr *)(smumgr->backend); + + smu_free_memory(smumgr->device, (void *)priv->smu_buffer.handle); + smu_free_memory(smumgr->device, (void *)priv->header_buffer.handle); + if (smumgr->backend != NULL) { kfree(smumgr->backend); smumgr->backend = NULL; } + + cgs_rel_firmware(smumgr->device, CGS_UCODE_ID_SMU); return 0; } @@ -472,7 +479,6 @@ static int tonga_request_smu_reload_fw(struct pp_smumgr *smumgr) struct tonga_smumgr *tonga_smu = (struct tonga_smumgr *)(smumgr->backend); uint16_t fw_to_load; - int result = 0; struct SMU_DRAMData_TOC *toc; /** * First time this gets called during SmuMgr init, @@ -556,7 +562,7 @@ static int tonga_request_smu_reload_fw(struct pp_smumgr *smumgr) smumgr, PPSMC_MSG_LoadUcodes, fw_to_load), "Fail to Request SMU Load uCode", return 0); - return result; + return 0; } static int tonga_request_smu_load_specific_fw(struct pp_smumgr *smumgr, diff --git a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h index c89dc777768f..b961a1c6caf3 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h +++ b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h @@ -26,7 +26,7 @@ TRACE_EVENT(amd_sched_job, TP_fast_assign( __entry->entity = sched_job->s_entity; __entry->sched_job = sched_job; - __entry->fence = &sched_job->s_fence->base; + __entry->fence = &sched_job->s_fence->finished; __entry->name = sched_job->sched->name; __entry->job_count = kfifo_len( &sched_job->s_entity->job_queue) / sizeof(sched_job); @@ -46,7 +46,7 @@ TRACE_EVENT(amd_sched_process_job, ), TP_fast_assign( - __entry->fence = &fence->base; + __entry->fence = &fence->finished; ), TP_printk("fence=%p signaled", __entry->fence) ); diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index c16248cee779..ef312bb75fda 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -32,6 +32,7 @@ static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity); static void amd_sched_wakeup(struct amd_gpu_scheduler *sched); +static void amd_sched_process_job(struct fence *f, struct fence_cb *cb); struct kmem_cache *sched_fence_slab; atomic_t sched_fence_slab_ref = ATOMIC_INIT(0); @@ -140,7 +141,7 @@ int amd_sched_entity_init(struct amd_gpu_scheduler *sched, return r; atomic_set(&entity->fence_seq, 0); - entity->fence_context = fence_context_alloc(1); + entity->fence_context = fence_context_alloc(2); return 0; } @@ -251,17 +252,21 @@ static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity) s_fence = to_amd_sched_fence(fence); if (s_fence && s_fence->sched == sched) { - /* Fence is from the same scheduler */ - if (test_bit(AMD_SCHED_FENCE_SCHEDULED_BIT, &fence->flags)) { - /* Ignore it when it is already scheduled */ - fence_put(entity->dependency); - return false; - } - /* Wait for fence to be scheduled */ - entity->cb.func = amd_sched_entity_clear_dep; - list_add_tail(&entity->cb.node, &s_fence->scheduled_cb); - return true; + /* + * Fence is from the same scheduler, only need to wait for + * it to be scheduled + */ + fence = fence_get(&s_fence->scheduled); + fence_put(entity->dependency); + entity->dependency = fence; + if (!fence_add_callback(fence, &entity->cb, + amd_sched_entity_clear_dep)) + return true; + + /* Ignore it when it is already scheduled */ + fence_put(fence); + return false; } if (!fence_add_callback(entity->dependency, &entity->cb, @@ -319,46 +324,114 @@ static bool amd_sched_entity_in(struct amd_sched_job *sched_job) return added; } -static void amd_sched_free_job(struct fence *f, struct fence_cb *cb) { - struct amd_sched_job *job = container_of(cb, struct amd_sched_job, cb_free_job); - schedule_work(&job->work_free_job); -} - /* job_finish is called after hw fence signaled, and * the job had already been deleted from ring_mirror_list */ -void amd_sched_job_finish(struct amd_sched_job *s_job) +static void amd_sched_job_finish(struct work_struct *work) { - struct amd_sched_job *next; + struct amd_sched_job *s_job = container_of(work, struct amd_sched_job, + finish_work); struct amd_gpu_scheduler *sched = s_job->sched; + /* remove job from ring_mirror_list */ + spin_lock(&sched->job_list_lock); + list_del_init(&s_job->node); if (sched->timeout != MAX_SCHEDULE_TIMEOUT) { - if (cancel_delayed_work(&s_job->work_tdr)) - amd_sched_job_put(s_job); + struct amd_sched_job *next; + + spin_unlock(&sched->job_list_lock); + cancel_delayed_work_sync(&s_job->work_tdr); + spin_lock(&sched->job_list_lock); /* queue TDR for next job */ next = list_first_entry_or_null(&sched->ring_mirror_list, struct amd_sched_job, node); - if (next) { - INIT_DELAYED_WORK(&next->work_tdr, s_job->timeout_callback); - amd_sched_job_get(next); + if (next) schedule_delayed_work(&next->work_tdr, sched->timeout); - } } + spin_unlock(&sched->job_list_lock); + sched->ops->free_job(s_job); } -void amd_sched_job_begin(struct amd_sched_job *s_job) +static void amd_sched_job_finish_cb(struct fence *f, struct fence_cb *cb) +{ + struct amd_sched_job *job = container_of(cb, struct amd_sched_job, + finish_cb); + schedule_work(&job->finish_work); +} + +static void amd_sched_job_begin(struct amd_sched_job *s_job) { struct amd_gpu_scheduler *sched = s_job->sched; + spin_lock(&sched->job_list_lock); + list_add_tail(&s_job->node, &sched->ring_mirror_list); if (sched->timeout != MAX_SCHEDULE_TIMEOUT && - list_first_entry_or_null(&sched->ring_mirror_list, struct amd_sched_job, node) == s_job) - { - INIT_DELAYED_WORK(&s_job->work_tdr, s_job->timeout_callback); - amd_sched_job_get(s_job); + list_first_entry_or_null(&sched->ring_mirror_list, + struct amd_sched_job, node) == s_job) schedule_delayed_work(&s_job->work_tdr, sched->timeout); + spin_unlock(&sched->job_list_lock); +} + +static void amd_sched_job_timedout(struct work_struct *work) +{ + struct amd_sched_job *job = container_of(work, struct amd_sched_job, + work_tdr.work); + + job->sched->ops->timedout_job(job); +} + +void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched) +{ + struct amd_sched_job *s_job; + + spin_lock(&sched->job_list_lock); + list_for_each_entry_reverse(s_job, &sched->ring_mirror_list, node) { + if (fence_remove_callback(s_job->s_fence->parent, &s_job->s_fence->cb)) { + fence_put(s_job->s_fence->parent); + s_job->s_fence->parent = NULL; + } } + atomic_set(&sched->hw_rq_count, 0); + spin_unlock(&sched->job_list_lock); +} + +void amd_sched_job_recovery(struct amd_gpu_scheduler *sched) +{ + struct amd_sched_job *s_job, *tmp; + int r; + + spin_lock(&sched->job_list_lock); + s_job = list_first_entry_or_null(&sched->ring_mirror_list, + struct amd_sched_job, node); + if (s_job) + schedule_delayed_work(&s_job->work_tdr, sched->timeout); + + list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) { + struct amd_sched_fence *s_fence = s_job->s_fence; + struct fence *fence; + + spin_unlock(&sched->job_list_lock); + fence = sched->ops->run_job(s_job); + atomic_inc(&sched->hw_rq_count); + if (fence) { + s_fence->parent = fence_get(fence); + r = fence_add_callback(fence, &s_fence->cb, + amd_sched_process_job); + if (r == -ENOENT) + amd_sched_process_job(fence, &s_fence->cb); + else if (r) + DRM_ERROR("fence add callback failed (%d)\n", + r); + fence_put(fence); + } else { + DRM_ERROR("Failed to run job!\n"); + amd_sched_process_job(NULL, &s_fence->cb); + } + spin_lock(&sched->job_list_lock); + } + spin_unlock(&sched->job_list_lock); } /** @@ -372,36 +445,29 @@ void amd_sched_entity_push_job(struct amd_sched_job *sched_job) { struct amd_sched_entity *entity = sched_job->s_entity; - sched_job->use_sched = 1; - fence_add_callback(&sched_job->s_fence->base, - &sched_job->cb_free_job, amd_sched_free_job); trace_amd_sched_job(sched_job); + fence_add_callback(&sched_job->s_fence->finished, &sched_job->finish_cb, + amd_sched_job_finish_cb); wait_event(entity->sched->job_scheduled, amd_sched_entity_in(sched_job)); } /* init a sched_job with basic field */ int amd_sched_job_init(struct amd_sched_job *job, - struct amd_gpu_scheduler *sched, - struct amd_sched_entity *entity, - void (*timeout_cb)(struct work_struct *work), - void (*free_cb)(struct kref *refcount), - void *owner, struct fence **fence) + struct amd_gpu_scheduler *sched, + struct amd_sched_entity *entity, + void *owner) { - INIT_LIST_HEAD(&job->node); - kref_init(&job->refcount); job->sched = sched; job->s_entity = entity; job->s_fence = amd_sched_fence_create(entity, owner); if (!job->s_fence) return -ENOMEM; - job->s_fence->s_job = job; - job->timeout_callback = timeout_cb; - job->free_callback = free_cb; + INIT_WORK(&job->finish_work, amd_sched_job_finish); + INIT_LIST_HEAD(&job->node); + INIT_DELAYED_WORK(&job->work_tdr, amd_sched_job_timedout); - if (fence) - *fence = &job->s_fence->base; return 0; } @@ -450,23 +516,25 @@ static void amd_sched_process_job(struct fence *f, struct fence_cb *cb) struct amd_sched_fence *s_fence = container_of(cb, struct amd_sched_fence, cb); struct amd_gpu_scheduler *sched = s_fence->sched; - unsigned long flags; atomic_dec(&sched->hw_rq_count); - - /* remove job from ring_mirror_list */ - spin_lock_irqsave(&sched->job_list_lock, flags); - list_del_init(&s_fence->s_job->node); - sched->ops->finish_job(s_fence->s_job); - spin_unlock_irqrestore(&sched->job_list_lock, flags); - - amd_sched_fence_signal(s_fence); + amd_sched_fence_finished(s_fence); trace_amd_sched_process_job(s_fence); - fence_put(&s_fence->base); + fence_put(&s_fence->finished); wake_up_interruptible(&sched->wake_up_worker); } +static bool amd_sched_blocked(struct amd_gpu_scheduler *sched) +{ + if (kthread_should_park()) { + kthread_parkme(); + return true; + } + + return false; +} + static int amd_sched_main(void *param) { struct sched_param sparam = {.sched_priority = 1}; @@ -476,14 +544,15 @@ static int amd_sched_main(void *param) sched_setscheduler(current, SCHED_FIFO, &sparam); while (!kthread_should_stop()) { - struct amd_sched_entity *entity; + struct amd_sched_entity *entity = NULL; struct amd_sched_fence *s_fence; struct amd_sched_job *sched_job; struct fence *fence; wait_event_interruptible(sched->wake_up_worker, - (entity = amd_sched_select_entity(sched)) || - kthread_should_stop()); + (!amd_sched_blocked(sched) && + (entity = amd_sched_select_entity(sched))) || + kthread_should_stop()); if (!entity) continue; @@ -495,16 +564,19 @@ static int amd_sched_main(void *param) s_fence = sched_job->s_fence; atomic_inc(&sched->hw_rq_count); - amd_sched_job_pre_schedule(sched, sched_job); + amd_sched_job_begin(sched_job); + fence = sched->ops->run_job(sched_job); amd_sched_fence_scheduled(s_fence); if (fence) { + s_fence->parent = fence_get(fence); r = fence_add_callback(fence, &s_fence->cb, amd_sched_process_job); if (r == -ENOENT) amd_sched_process_job(fence, &s_fence->cb); else if (r) - DRM_ERROR("fence add callback failed (%d)\n", r); + DRM_ERROR("fence add callback failed (%d)\n", + r); fence_put(fence); } else { DRM_ERROR("Failed to run job!\n"); diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h index 070095a9433c..7cbbbfb502ef 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h @@ -27,8 +27,6 @@ #include #include -#define AMD_SCHED_FENCE_SCHEDULED_BIT FENCE_FLAG_USER_BITS - struct amd_gpu_scheduler; struct amd_sched_rq; @@ -68,36 +66,34 @@ struct amd_sched_rq { }; struct amd_sched_fence { - struct fence base; + struct fence scheduled; + struct fence finished; struct fence_cb cb; - struct list_head scheduled_cb; + struct fence *parent; struct amd_gpu_scheduler *sched; spinlock_t lock; void *owner; - struct amd_sched_job *s_job; }; struct amd_sched_job { - struct kref refcount; struct amd_gpu_scheduler *sched; struct amd_sched_entity *s_entity; struct amd_sched_fence *s_fence; - bool use_sched; /* true if the job goes to scheduler */ - struct fence_cb cb_free_job; - struct work_struct work_free_job; - struct list_head node; - struct delayed_work work_tdr; - void (*timeout_callback) (struct work_struct *work); - void (*free_callback)(struct kref *refcount); + struct fence_cb finish_cb; + struct work_struct finish_work; + struct list_head node; + struct delayed_work work_tdr; }; -extern const struct fence_ops amd_sched_fence_ops; +extern const struct fence_ops amd_sched_fence_ops_scheduled; +extern const struct fence_ops amd_sched_fence_ops_finished; static inline struct amd_sched_fence *to_amd_sched_fence(struct fence *f) { - struct amd_sched_fence *__f = container_of(f, struct amd_sched_fence, base); + if (f->ops == &amd_sched_fence_ops_scheduled) + return container_of(f, struct amd_sched_fence, scheduled); - if (__f->base.ops == &amd_sched_fence_ops) - return __f; + if (f->ops == &amd_sched_fence_ops_finished) + return container_of(f, struct amd_sched_fence, finished); return NULL; } @@ -109,8 +105,8 @@ static inline struct amd_sched_fence *to_amd_sched_fence(struct fence *f) struct amd_sched_backend_ops { struct fence *(*dependency)(struct amd_sched_job *sched_job); struct fence *(*run_job)(struct amd_sched_job *sched_job); - void (*begin_job)(struct amd_sched_job *sched_job); - void (*finish_job)(struct amd_sched_job *sched_job); + void (*timedout_job)(struct amd_sched_job *sched_job); + void (*free_job)(struct amd_sched_job *sched_job); }; enum amd_sched_priority { @@ -152,25 +148,11 @@ void amd_sched_entity_push_job(struct amd_sched_job *sched_job); struct amd_sched_fence *amd_sched_fence_create( struct amd_sched_entity *s_entity, void *owner); void amd_sched_fence_scheduled(struct amd_sched_fence *fence); -void amd_sched_fence_signal(struct amd_sched_fence *fence); +void amd_sched_fence_finished(struct amd_sched_fence *fence); int amd_sched_job_init(struct amd_sched_job *job, - struct amd_gpu_scheduler *sched, - struct amd_sched_entity *entity, - void (*timeout_cb)(struct work_struct *work), - void (*free_cb)(struct kref* refcount), - void *owner, struct fence **fence); -void amd_sched_job_pre_schedule(struct amd_gpu_scheduler *sched , - struct amd_sched_job *s_job); -void amd_sched_job_finish(struct amd_sched_job *s_job); -void amd_sched_job_begin(struct amd_sched_job *s_job); -static inline void amd_sched_job_get(struct amd_sched_job *job) { - if (job) - kref_get(&job->refcount); -} - -static inline void amd_sched_job_put(struct amd_sched_job *job) { - if (job) - kref_put(&job->refcount, job->free_callback); -} - + struct amd_gpu_scheduler *sched, + struct amd_sched_entity *entity, + void *owner); +void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched); +void amd_sched_job_recovery(struct amd_gpu_scheduler *sched); #endif diff --git a/drivers/gpu/drm/amd/scheduler/sched_fence.c b/drivers/gpu/drm/amd/scheduler/sched_fence.c index 2a732c490375..6b63beaf7574 100644 --- a/drivers/gpu/drm/amd/scheduler/sched_fence.c +++ b/drivers/gpu/drm/amd/scheduler/sched_fence.c @@ -27,7 +27,8 @@ #include #include "gpu_scheduler.h" -struct amd_sched_fence *amd_sched_fence_create(struct amd_sched_entity *s_entity, void *owner) +struct amd_sched_fence *amd_sched_fence_create(struct amd_sched_entity *entity, + void *owner) { struct amd_sched_fence *fence = NULL; unsigned seq; @@ -36,46 +37,37 @@ struct amd_sched_fence *amd_sched_fence_create(struct amd_sched_entity *s_entity if (fence == NULL) return NULL; - INIT_LIST_HEAD(&fence->scheduled_cb); fence->owner = owner; - fence->sched = s_entity->sched; + fence->sched = entity->sched; spin_lock_init(&fence->lock); - seq = atomic_inc_return(&s_entity->fence_seq); - fence_init(&fence->base, &amd_sched_fence_ops, &fence->lock, - s_entity->fence_context, seq); + seq = atomic_inc_return(&entity->fence_seq); + fence_init(&fence->scheduled, &amd_sched_fence_ops_scheduled, + &fence->lock, entity->fence_context, seq); + fence_init(&fence->finished, &amd_sched_fence_ops_finished, + &fence->lock, entity->fence_context + 1, seq); return fence; } -void amd_sched_fence_signal(struct amd_sched_fence *fence) +void amd_sched_fence_scheduled(struct amd_sched_fence *fence) { - int ret = fence_signal(&fence->base); + int ret = fence_signal(&fence->scheduled); + if (!ret) - FENCE_TRACE(&fence->base, "signaled from irq context\n"); + FENCE_TRACE(&fence->scheduled, "signaled from irq context\n"); else - FENCE_TRACE(&fence->base, "was already signaled\n"); + FENCE_TRACE(&fence->scheduled, "was already signaled\n"); } -void amd_sched_job_pre_schedule(struct amd_gpu_scheduler *sched , - struct amd_sched_job *s_job) +void amd_sched_fence_finished(struct amd_sched_fence *fence) { - unsigned long flags; - spin_lock_irqsave(&sched->job_list_lock, flags); - list_add_tail(&s_job->node, &sched->ring_mirror_list); - sched->ops->begin_job(s_job); - spin_unlock_irqrestore(&sched->job_list_lock, flags); -} + int ret = fence_signal(&fence->finished); -void amd_sched_fence_scheduled(struct amd_sched_fence *s_fence) -{ - struct fence_cb *cur, *tmp; - - set_bit(AMD_SCHED_FENCE_SCHEDULED_BIT, &s_fence->base.flags); - list_for_each_entry_safe(cur, tmp, &s_fence->scheduled_cb, node) { - list_del_init(&cur->node); - cur->func(&s_fence->base, cur); - } + if (!ret) + FENCE_TRACE(&fence->finished, "signaled from irq context\n"); + else + FENCE_TRACE(&fence->finished, "was already signaled\n"); } static const char *amd_sched_fence_get_driver_name(struct fence *fence) @@ -105,6 +97,8 @@ static void amd_sched_fence_free(struct rcu_head *rcu) { struct fence *f = container_of(rcu, struct fence, rcu); struct amd_sched_fence *fence = to_amd_sched_fence(f); + + fence_put(fence->parent); kmem_cache_free(sched_fence_slab, fence); } @@ -116,16 +110,41 @@ static void amd_sched_fence_free(struct rcu_head *rcu) * This function is called when the reference count becomes zero. * It just RCU schedules freeing up the fence. */ -static void amd_sched_fence_release(struct fence *f) +static void amd_sched_fence_release_scheduled(struct fence *f) { - call_rcu(&f->rcu, amd_sched_fence_free); + struct amd_sched_fence *fence = to_amd_sched_fence(f); + + call_rcu(&fence->finished.rcu, amd_sched_fence_free); } -const struct fence_ops amd_sched_fence_ops = { +/** + * amd_sched_fence_release_scheduled - drop extra reference + * + * @f: fence + * + * Drop the extra reference from the scheduled fence to the base fence. + */ +static void amd_sched_fence_release_finished(struct fence *f) +{ + struct amd_sched_fence *fence = to_amd_sched_fence(f); + + fence_put(&fence->scheduled); +} + +const struct fence_ops amd_sched_fence_ops_scheduled = { .get_driver_name = amd_sched_fence_get_driver_name, .get_timeline_name = amd_sched_fence_get_timeline_name, .enable_signaling = amd_sched_fence_enable_signaling, .signaled = NULL, .wait = fence_default_wait, - .release = amd_sched_fence_release, + .release = amd_sched_fence_release_scheduled, +}; + +const struct fence_ops amd_sched_fence_ops_finished = { + .get_driver_name = amd_sched_fence_get_driver_name, + .get_timeline_name = amd_sched_fence_get_timeline_name, + .enable_signaling = amd_sched_fence_enable_signaling, + .signaled = NULL, + .wait = fence_default_wait, + .release = amd_sched_fence_release_finished, }; diff --git a/drivers/gpu/drm/arc/Kconfig b/drivers/gpu/drm/arc/Kconfig index f9a13b658fea..f47d88ba4fa5 100644 --- a/drivers/gpu/drm/arc/Kconfig +++ b/drivers/gpu/drm/arc/Kconfig @@ -2,7 +2,6 @@ config DRM_ARCPGU tristate "ARC PGU" depends on DRM && OF select DRM_KMS_CMA_HELPER - select DRM_KMS_FB_HELPER select DRM_KMS_HELPER help Choose this option if you have an ARC PGU controller. diff --git a/drivers/gpu/drm/arc/arcpgu_drv.c b/drivers/gpu/drm/arc/arcpgu_drv.c index ccbdadb108dc..6d4ff34737cb 100644 --- a/drivers/gpu/drm/arc/arcpgu_drv.c +++ b/drivers/gpu/drm/arc/arcpgu_drv.c @@ -28,8 +28,7 @@ static void arcpgu_fb_output_poll_changed(struct drm_device *dev) { struct arcpgu_drm_private *arcpgu = dev->dev_private; - if (arcpgu->fbdev) - drm_fbdev_cma_hotplug_event(arcpgu->fbdev); + drm_fbdev_cma_hotplug_event(arcpgu->fbdev); } static struct drm_mode_config_funcs arcpgu_drm_modecfg_funcs = { @@ -49,7 +48,7 @@ static void arcpgu_setup_mode_config(struct drm_device *drm) drm->mode_config.funcs = &arcpgu_drm_modecfg_funcs; } -int arcpgu_gem_mmap(struct file *filp, struct vm_area_struct *vma) +static int arcpgu_gem_mmap(struct file *filp, struct vm_area_struct *vma) { int ret; @@ -104,10 +103,8 @@ static int arcpgu_load(struct drm_device *drm) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); arcpgu->regs = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(arcpgu->regs)) { - dev_err(drm->dev, "Could not remap IO mem\n"); + if (IS_ERR(arcpgu->regs)) return PTR_ERR(arcpgu->regs); - } dev_info(drm->dev, "arc_pgu ID: 0x%x\n", arc_pgu_read(arcpgu, ARCPGU_REG_ID)); @@ -127,10 +124,11 @@ static int arcpgu_load(struct drm_device *drm) encoder_node = of_parse_phandle(drm->dev->of_node, "encoder-slave", 0); if (encoder_node) { ret = arcpgu_drm_hdmi_init(drm, encoder_node); + of_node_put(encoder_node); if (ret < 0) return ret; } else { - ret = arcpgu_drm_sim_init(drm, 0); + ret = arcpgu_drm_sim_init(drm, NULL); if (ret < 0) return ret; } @@ -151,7 +149,7 @@ static int arcpgu_load(struct drm_device *drm) return 0; } -int arcpgu_unload(struct drm_device *drm) +static int arcpgu_unload(struct drm_device *drm) { struct arcpgu_drm_private *arcpgu = drm->dev_private; diff --git a/drivers/gpu/drm/arm/Kconfig b/drivers/gpu/drm/arm/Kconfig index 1b2906568a48..9a18e1bd57b4 100644 --- a/drivers/gpu/drm/arm/Kconfig +++ b/drivers/gpu/drm/arm/Kconfig @@ -9,7 +9,6 @@ config DRM_HDLCD depends on COMMON_CLK select DRM_ARM select DRM_KMS_HELPER - select DRM_KMS_FB_HELPER select DRM_KMS_CMA_HELPER help Choose this option if you have an ARM High Definition Colour LCD diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c index 74279be20b75..d83b46a30327 100644 --- a/drivers/gpu/drm/arm/hdlcd_drv.c +++ b/drivers/gpu/drm/arm/hdlcd_drv.c @@ -102,8 +102,7 @@ static void hdlcd_fb_output_poll_changed(struct drm_device *drm) { struct hdlcd_drm_private *hdlcd = drm->dev_private; - if (hdlcd->fbdev) - drm_fbdev_cma_hotplug_event(hdlcd->fbdev); + drm_fbdev_cma_hotplug_event(hdlcd->fbdev); } static const struct drm_mode_config_funcs hdlcd_mode_config_funcs = { diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c index e5b44e92f8cf..82171d223f2d 100644 --- a/drivers/gpu/drm/arm/malidp_drv.c +++ b/drivers/gpu/drm/arm/malidp_drv.c @@ -257,6 +257,7 @@ static int malidp_bind(struct device *dev) { struct resource *res; struct drm_device *drm; + struct device_node *ep; struct malidp_drm *malidp; struct malidp_hw_device *hwdev; struct platform_device *pdev = to_platform_device(dev); @@ -284,10 +285,8 @@ static int malidp_bind(struct device *dev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); hwdev->regs = devm_ioremap_resource(dev, res); - if (IS_ERR(hwdev->regs)) { - DRM_ERROR("Failed to map control registers area\n"); + if (IS_ERR(hwdev->regs)) return PTR_ERR(hwdev->regs); - } hwdev->pclk = devm_clk_get(dev, "pclk"); if (IS_ERR(hwdev->pclk)) @@ -360,11 +359,14 @@ static int malidp_bind(struct device *dev) goto register_fail; /* Set the CRTC's port so that the encoder component can find it */ - malidp->crtc.port = of_graph_get_next_endpoint(dev->of_node, NULL); + ep = of_graph_get_next_endpoint(dev->of_node, NULL); + if (!ep) { + ret = -EINVAL; + goto port_fail; + } + malidp->crtc.port = of_get_next_parent(ep); ret = component_bind_all(dev, drm); - of_node_put(malidp->crtc.port); - if (ret) { DRM_ERROR("Failed to bind all components\n"); goto bind_fail; @@ -402,6 +404,9 @@ static int malidp_bind(struct device *dev) irq_init_fail: component_unbind_all(dev, drm); bind_fail: + of_node_put(malidp->crtc.port); + malidp->crtc.port = NULL; +port_fail: drm_dev_unregister(drm); register_fail: malidp_de_planes_destroy(drm); @@ -435,6 +440,8 @@ static void malidp_unbind(struct device *dev) malidp_de_irq_fini(drm); drm_vblank_cleanup(drm); component_unbind_all(dev, drm); + of_node_put(malidp->crtc.port); + malidp->crtc.port = NULL; drm_dev_unregister(drm); malidp_de_planes_destroy(drm); drm_mode_config_cleanup(drm); diff --git a/drivers/gpu/drm/armada/Kconfig b/drivers/gpu/drm/armada/Kconfig index eb773e9af313..15f3ecfb16f1 100644 --- a/drivers/gpu/drm/armada/Kconfig +++ b/drivers/gpu/drm/armada/Kconfig @@ -1,11 +1,7 @@ config DRM_ARMADA tristate "DRM support for Marvell Armada SoCs" depends on DRM && HAVE_CLK && ARM - select FB_CFB_FILLRECT - select FB_CFB_COPYAREA - select FB_CFB_IMAGEBLIT select DRM_KMS_HELPER - select DRM_KMS_FB_HELPER help Support the "LCD" controllers found on the Marvell Armada 510 devices. There are two controllers on the device, each controller diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c index 34405e4a5d36..2f58e9e2a59c 100644 --- a/drivers/gpu/drm/armada/armada_crtc.c +++ b/drivers/gpu/drm/armada/armada_crtc.c @@ -410,7 +410,7 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat) DRM_ERROR("graphics underflow on crtc %u\n", dcrtc->num); if (stat & VSYNC_IRQ) - drm_handle_vblank(dcrtc->crtc.dev, dcrtc->num); + drm_crtc_handle_vblank(&dcrtc->crtc); spin_lock(&dcrtc->irq_lock); ovl_plane = dcrtc->plane; diff --git a/drivers/gpu/drm/ast/Kconfig b/drivers/gpu/drm/ast/Kconfig index 8a784c460c89..15f6ce7acb2a 100644 --- a/drivers/gpu/drm/ast/Kconfig +++ b/drivers/gpu/drm/ast/Kconfig @@ -2,11 +2,7 @@ config DRM_AST tristate "AST server chips" depends on DRM && PCI select DRM_TTM - select FB_SYS_COPYAREA - select FB_SYS_FILLRECT - select FB_SYS_IMAGEBLIT select DRM_KMS_HELPER - select DRM_KMS_FB_HELPER select DRM_TTM help Say yes for experimental AST GPU driver. Do not enable diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 7bc3aa6dda8c..904beaa932d0 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -295,9 +295,8 @@ static int ast_get_dram_info(struct drm_device *dev) static void ast_user_framebuffer_destroy(struct drm_framebuffer *fb) { struct ast_framebuffer *ast_fb = to_ast_framebuffer(fb); - if (ast_fb->obj) - drm_gem_object_unreference_unlocked(ast_fb->obj); + drm_gem_object_unreference_unlocked(ast_fb->obj); drm_framebuffer_cleanup(fb); kfree(fb); } diff --git a/drivers/gpu/drm/ast/ast_ttm.c b/drivers/gpu/drm/ast/ast_ttm.c index 59f2f93b6f84..b29a41218fc9 100644 --- a/drivers/gpu/drm/ast/ast_ttm.c +++ b/drivers/gpu/drm/ast/ast_ttm.c @@ -186,17 +186,6 @@ static void ast_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_reg * { } -static int ast_bo_move(struct ttm_buffer_object *bo, - bool evict, bool interruptible, - bool no_wait_gpu, - struct ttm_mem_reg *new_mem) -{ - int r; - r = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem); - return r; -} - - static void ast_ttm_backend_destroy(struct ttm_tt *tt) { ttm_tt_fini(tt); @@ -241,7 +230,7 @@ struct ttm_bo_driver ast_bo_driver = { .ttm_tt_unpopulate = ast_ttm_tt_unpopulate, .init_mem_type = ast_bo_init_mem_type, .evict_flags = ast_bo_evict_flags, - .move = ast_bo_move, + .move = NULL, .verify_access = ast_bo_verify_access, .io_mem_reserve = &ast_ttm_io_mem_reserve, .io_mem_free = &ast_ttm_io_mem_free, diff --git a/drivers/gpu/drm/atmel-hlcdc/Kconfig b/drivers/gpu/drm/atmel-hlcdc/Kconfig index 99b4f0698a30..32bcc4bad06a 100644 --- a/drivers/gpu/drm/atmel-hlcdc/Kconfig +++ b/drivers/gpu/drm/atmel-hlcdc/Kconfig @@ -3,7 +3,6 @@ config DRM_ATMEL_HLCDC depends on DRM && OF && COMMON_CLK && MFD_ATMEL_HLCDC && ARM select DRM_GEM_CMA_HELPER select DRM_KMS_HELPER - select DRM_KMS_FB_HELPER select DRM_KMS_CMA_HELPER select DRM_PANEL help diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c index 613f6c99b76a..a978381ef95b 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c @@ -383,7 +383,7 @@ static void atmel_hlcdc_crtc_finish_page_flip(struct atmel_hlcdc_crtc *crtc) void atmel_hlcdc_crtc_irq(struct drm_crtc *c) { - drm_handle_vblank(c->dev, 0); + drm_crtc_handle_vblank(c); atmel_hlcdc_crtc_finish_page_flip(drm_crtc_to_atmel_hlcdc_crtc(c)); } diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c index 473a475f27b1..6119b5085501 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_output.c @@ -254,9 +254,10 @@ int atmel_hlcdc_create_outputs(struct drm_device *dev) if (!ret) ret = atmel_hlcdc_check_endpoint(dev, &ep); - of_node_put(ep_np); - if (ret) + if (ret) { + of_node_put(ep_np); return ret; + } } for_each_endpoint_of_node(dev->dev->of_node, ep_np) { @@ -264,9 +265,10 @@ int atmel_hlcdc_create_outputs(struct drm_device *dev) if (!ret) ret = atmel_hlcdc_attach_endpoint(dev, &ep); - of_node_put(ep_np); - if (ret) + if (ret) { + of_node_put(ep_np); return ret; + } } return 0; diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c index aef3ca8a81fa..016c191221f3 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c @@ -339,6 +339,8 @@ atmel_hlcdc_plane_update_pos_and_size(struct atmel_hlcdc_plane *plane, atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff, factor_reg); + } else { + atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff, 0); } } diff --git a/drivers/gpu/drm/bochs/Kconfig b/drivers/gpu/drm/bochs/Kconfig index 5f8b0c2b9a44..f739763f47ce 100644 --- a/drivers/gpu/drm/bochs/Kconfig +++ b/drivers/gpu/drm/bochs/Kconfig @@ -2,10 +2,6 @@ config DRM_BOCHS tristate "DRM Support for bochs dispi vga interface (qemu stdvga)" depends on DRM && PCI select DRM_KMS_HELPER - select DRM_KMS_FB_HELPER - select FB_SYS_FILLRECT - select FB_SYS_COPYAREA - select FB_SYS_IMAGEBLIT select DRM_TTM help Choose this option for qemu. diff --git a/drivers/gpu/drm/bochs/bochs_mm.c b/drivers/gpu/drm/bochs/bochs_mm.c index 6cf912c45e48..5c5638a777a1 100644 --- a/drivers/gpu/drm/bochs/bochs_mm.c +++ b/drivers/gpu/drm/bochs/bochs_mm.c @@ -165,15 +165,6 @@ static void bochs_ttm_io_mem_free(struct ttm_bo_device *bdev, { } -static int bochs_bo_move(struct ttm_buffer_object *bo, - bool evict, bool interruptible, - bool no_wait_gpu, - struct ttm_mem_reg *new_mem) -{ - return ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem); -} - - static void bochs_ttm_backend_destroy(struct ttm_tt *tt) { ttm_tt_fini(tt); @@ -208,7 +199,7 @@ struct ttm_bo_driver bochs_bo_driver = { .ttm_tt_unpopulate = ttm_pool_unpopulate, .init_mem_type = bochs_bo_init_mem_type, .evict_flags = bochs_bo_evict_flags, - .move = bochs_bo_move, + .move = NULL, .verify_access = bochs_bo_verify_access, .io_mem_reserve = &bochs_ttm_io_mem_reserve, .io_mem_free = &bochs_ttm_io_mem_free, @@ -474,8 +465,8 @@ int bochs_dumb_mmap_offset(struct drm_file *file, struct drm_device *dev, static void bochs_user_framebuffer_destroy(struct drm_framebuffer *fb) { struct bochs_framebuffer *bochs_fb = to_bochs_framebuffer(fb); - if (bochs_fb->obj) - drm_gem_object_unreference_unlocked(bochs_fb->obj); + + drm_gem_object_unreference_unlocked(bochs_fb->obj); drm_framebuffer_cleanup(fb); kfree(fb); } diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index a141921445f4..b590e678052d 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -58,6 +58,17 @@ config DRM_SII902X ---help--- Silicon Image sii902x bridge chip driver. +config DRM_TOSHIBA_TC358767 + tristate "Toshiba TC358767 eDP bridge" + depends on OF + select DRM_KMS_HELPER + select REGMAP_I2C + select DRM_PANEL + ---help--- + Toshiba TC358767 eDP bridge chip driver. + source "drivers/gpu/drm/bridge/analogix/Kconfig" +source "drivers/gpu/drm/bridge/adv7511/Kconfig" + endmenu diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile index bfec9f8cb9d2..efdb07e878f5 100644 --- a/drivers/gpu/drm/bridge/Makefile +++ b/drivers/gpu/drm/bridge/Makefile @@ -6,4 +6,6 @@ obj-$(CONFIG_DRM_DW_HDMI_AHB_AUDIO) += dw-hdmi-ahb-audio.o obj-$(CONFIG_DRM_NXP_PTN3460) += nxp-ptn3460.o obj-$(CONFIG_DRM_PARADE_PS8622) += parade-ps8622.o obj-$(CONFIG_DRM_SII902X) += sii902x.o +obj-$(CONFIG_DRM_TOSHIBA_TC358767) += tc358767.o obj-$(CONFIG_DRM_ANALOGIX_DP) += analogix/ +obj-$(CONFIG_DRM_I2C_ADV7511) += adv7511/ diff --git a/drivers/gpu/drm/bridge/adv7511/Kconfig b/drivers/gpu/drm/bridge/adv7511/Kconfig new file mode 100644 index 000000000000..d2b0499ab7d7 --- /dev/null +++ b/drivers/gpu/drm/bridge/adv7511/Kconfig @@ -0,0 +1,15 @@ +config DRM_I2C_ADV7511 + tristate "AV7511 encoder" + depends on OF + select DRM_KMS_HELPER + select REGMAP_I2C + help + Support for the Analog Device ADV7511(W) and ADV7513 HDMI encoders. + +config DRM_I2C_ADV7533 + bool "ADV7533 encoder" + depends on DRM_I2C_ADV7511 + select DRM_MIPI_DSI + default y + help + Support for the Analog Devices ADV7533 DSI to HDMI encoder. diff --git a/drivers/gpu/drm/bridge/adv7511/Makefile b/drivers/gpu/drm/bridge/adv7511/Makefile new file mode 100644 index 000000000000..9019327fff4c --- /dev/null +++ b/drivers/gpu/drm/bridge/adv7511/Makefile @@ -0,0 +1,3 @@ +adv7511-y := adv7511_drv.o +adv7511-$(CONFIG_DRM_I2C_ADV7533) += adv7533.o +obj-$(CONFIG_DRM_I2C_ADV7511) += adv7511.o diff --git a/drivers/gpu/drm/i2c/adv7511.h b/drivers/gpu/drm/bridge/adv7511/adv7511.h similarity index 82% rename from drivers/gpu/drm/i2c/adv7511.h rename to drivers/gpu/drm/bridge/adv7511/adv7511.h index 38515b30cedf..161c923d6162 100644 --- a/drivers/gpu/drm/i2c/adv7511.h +++ b/drivers/gpu/drm/bridge/adv7511/adv7511.h @@ -10,6 +10,11 @@ #define __DRM_I2C_ADV7511_H__ #include +#include +#include + +#include +#include #define ADV7511_REG_CHIP_REVISION 0x00 #define ADV7511_REG_N0 0x01 @@ -286,4 +291,102 @@ struct adv7511_video_config { struct hdmi_avi_infoframe avi_infoframe; }; +enum adv7511_type { + ADV7511, + ADV7533, +}; + +struct adv7511 { + struct i2c_client *i2c_main; + struct i2c_client *i2c_edid; + struct i2c_client *i2c_cec; + + struct regmap *regmap; + struct regmap *regmap_cec; + enum drm_connector_status status; + bool powered; + + struct drm_display_mode curr_mode; + + unsigned int f_tmds; + + unsigned int current_edid_segment; + uint8_t edid_buf[256]; + bool edid_read; + + wait_queue_head_t wq; + struct drm_bridge bridge; + struct drm_connector connector; + + bool embedded_sync; + enum adv7511_sync_polarity vsync_polarity; + enum adv7511_sync_polarity hsync_polarity; + bool rgb; + + struct edid *edid; + + struct gpio_desc *gpio_pd; + + /* ADV7533 DSI RX related params */ + struct device_node *host_node; + struct mipi_dsi_device *dsi; + u8 num_dsi_lanes; + bool use_timing_gen; + + enum adv7511_type type; +}; + +#ifdef CONFIG_DRM_I2C_ADV7533 +void adv7533_dsi_power_on(struct adv7511 *adv); +void adv7533_dsi_power_off(struct adv7511 *adv); +void adv7533_mode_set(struct adv7511 *adv, struct drm_display_mode *mode); +int adv7533_patch_registers(struct adv7511 *adv); +void adv7533_uninit_cec(struct adv7511 *adv); +int adv7533_init_cec(struct adv7511 *adv); +int adv7533_attach_dsi(struct adv7511 *adv); +void adv7533_detach_dsi(struct adv7511 *adv); +int adv7533_parse_dt(struct device_node *np, struct adv7511 *adv); +#else +static inline void adv7533_dsi_power_on(struct adv7511 *adv) +{ +} + +static inline void adv7533_dsi_power_off(struct adv7511 *adv) +{ +} + +static inline void adv7533_mode_set(struct adv7511 *adv, + struct drm_display_mode *mode) +{ +} + +static inline int adv7533_patch_registers(struct adv7511 *adv) +{ + return -ENODEV; +} + +static inline void adv7533_uninit_cec(struct adv7511 *adv) +{ +} + +static inline int adv7533_init_cec(struct adv7511 *adv) +{ + return -ENODEV; +} + +static inline int adv7533_attach_dsi(struct adv7511 *adv) +{ + return -ENODEV; +} + +static inline void adv7533_detach_dsi(struct adv7511 *adv) +{ +} + +static inline int adv7533_parse_dt(struct device_node *np, struct adv7511 *adv) +{ + return -ENODEV; +} +#endif + #endif /* __DRM_I2C_ADV7511_H__ */ diff --git a/drivers/gpu/drm/i2c/adv7511.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c similarity index 80% rename from drivers/gpu/drm/i2c/adv7511.c rename to drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index a02112ba1c3d..ec8fb2ed3275 100644 --- a/drivers/gpu/drm/i2c/adv7511.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -8,51 +8,17 @@ #include #include -#include #include -#include +#include #include #include -#include +#include +#include #include -#include #include "adv7511.h" -struct adv7511 { - struct i2c_client *i2c_main; - struct i2c_client *i2c_edid; - - struct regmap *regmap; - struct regmap *packet_memory_regmap; - enum drm_connector_status status; - bool powered; - - unsigned int f_tmds; - - unsigned int current_edid_segment; - uint8_t edid_buf[256]; - bool edid_read; - - wait_queue_head_t wq; - struct drm_encoder *encoder; - - bool embedded_sync; - enum adv7511_sync_polarity vsync_polarity; - enum adv7511_sync_polarity hsync_polarity; - bool rgb; - - struct edid *edid; - - struct gpio_desc *gpio_pd; -}; - -static struct adv7511 *encoder_to_adv7511(struct drm_encoder *encoder) -{ - return to_encoder_slave(encoder)->slave_priv; -} - /* ADI recommended values for proper operation. */ static const struct reg_sequence adv7511_fixed_registers[] = { { 0x98, 0x03 }, @@ -394,6 +360,9 @@ static void adv7511_power_on(struct adv7511 *adv7511) */ regcache_sync(adv7511->regmap); + if (adv7511->type == ADV7533) + adv7533_dsi_power_on(adv7511); + adv7511->powered = true; } @@ -405,6 +374,9 @@ static void adv7511_power_off(struct adv7511 *adv7511) ADV7511_POWER_POWER_DOWN); regcache_mark_dirty(adv7511->regmap); + if (adv7511->type == ADV7533) + adv7533_dsi_power_off(adv7511); + adv7511->powered = false; } @@ -430,7 +402,7 @@ static bool adv7511_hpd(struct adv7511 *adv7511) return false; } -static int adv7511_irq_process(struct adv7511 *adv7511) +static int adv7511_irq_process(struct adv7511 *adv7511, bool process_hpd) { unsigned int irq0, irq1; int ret; @@ -446,8 +418,8 @@ static int adv7511_irq_process(struct adv7511 *adv7511) regmap_write(adv7511->regmap, ADV7511_REG_INT(0), irq0); regmap_write(adv7511->regmap, ADV7511_REG_INT(1), irq1); - if (irq0 & ADV7511_INT0_HPD && adv7511->encoder) - drm_helper_hpd_irq_event(adv7511->encoder->dev); + if (process_hpd && irq0 & ADV7511_INT0_HPD && adv7511->bridge.encoder) + drm_helper_hpd_irq_event(adv7511->connector.dev); if (irq0 & ADV7511_INT0_EDID_READY || irq1 & ADV7511_INT1_DDC_ERROR) { adv7511->edid_read = true; @@ -464,7 +436,7 @@ static irqreturn_t adv7511_irq_handler(int irq, void *devid) struct adv7511 *adv7511 = devid; int ret; - ret = adv7511_irq_process(adv7511); + ret = adv7511_irq_process(adv7511, true); return ret < 0 ? IRQ_NONE : IRQ_HANDLED; } @@ -481,7 +453,7 @@ static int adv7511_wait_for_edid(struct adv7511 *adv7511, int timeout) adv7511->edid_read, msecs_to_jiffies(timeout)); } else { for (; timeout > 0; timeout -= 25) { - ret = adv7511_irq_process(adv7511); + ret = adv7511_irq_process(adv7511, false); if (ret < 0) break; @@ -563,13 +535,12 @@ static int adv7511_get_edid_block(void *data, u8 *buf, unsigned int block, } /* ----------------------------------------------------------------------------- - * Encoder operations + * ADV75xx helpers */ -static int adv7511_get_modes(struct drm_encoder *encoder, +static int adv7511_get_modes(struct adv7511 *adv7511, struct drm_connector *connector) { - struct adv7511 *adv7511 = encoder_to_adv7511(encoder); struct edid *edid; unsigned int count; @@ -606,21 +577,9 @@ static int adv7511_get_modes(struct drm_encoder *encoder, return count; } -static void adv7511_encoder_dpms(struct drm_encoder *encoder, int mode) -{ - struct adv7511 *adv7511 = encoder_to_adv7511(encoder); - - if (mode == DRM_MODE_DPMS_ON) - adv7511_power_on(adv7511); - else - adv7511_power_off(adv7511); -} - static enum drm_connector_status -adv7511_encoder_detect(struct drm_encoder *encoder, - struct drm_connector *connector) +adv7511_detect(struct adv7511 *adv7511, struct drm_connector *connector) { - struct adv7511 *adv7511 = encoder_to_adv7511(encoder); enum drm_connector_status status; unsigned int val; bool hpd; @@ -644,7 +603,7 @@ adv7511_encoder_detect(struct drm_encoder *encoder, if (status == connector_status_connected && hpd && adv7511->powered) { regcache_mark_dirty(adv7511->regmap); adv7511_power_on(adv7511); - adv7511_get_modes(encoder, connector); + adv7511_get_modes(adv7511, connector); if (adv7511->status == connector_status_connected) status = connector_status_disconnected; } else { @@ -658,8 +617,8 @@ adv7511_encoder_detect(struct drm_encoder *encoder, return status; } -static int adv7511_encoder_mode_valid(struct drm_encoder *encoder, - struct drm_display_mode *mode) +static int adv7511_mode_valid(struct adv7511 *adv7511, + struct drm_display_mode *mode) { if (mode->clock > 165000) return MODE_CLOCK_HIGH; @@ -667,11 +626,10 @@ static int adv7511_encoder_mode_valid(struct drm_encoder *encoder, return MODE_OK; } -static void adv7511_encoder_mode_set(struct drm_encoder *encoder, - struct drm_display_mode *mode, - struct drm_display_mode *adj_mode) +static void adv7511_mode_set(struct adv7511 *adv7511, + struct drm_display_mode *mode, + struct drm_display_mode *adj_mode) { - struct adv7511 *adv7511 = encoder_to_adv7511(encoder); unsigned int low_refresh_rate; unsigned int hsync_polarity = 0; unsigned int vsync_polarity = 0; @@ -754,6 +712,11 @@ static void adv7511_encoder_mode_set(struct drm_encoder *encoder, regmap_update_bits(adv7511->regmap, 0x17, 0x60, (vsync_polarity << 6) | (hsync_polarity << 5)); + if (adv7511->type == ADV7533) + adv7533_mode_set(adv7511, adj_mode); + + drm_mode_copy(&adv7511->curr_mode, adj_mode); + /* * TODO Test first order 4:2:2 to 4:4:4 up conversion method, which is * supposed to give better results. @@ -762,12 +725,114 @@ static void adv7511_encoder_mode_set(struct drm_encoder *encoder, adv7511->f_tmds = mode->clock; } -static const struct drm_encoder_slave_funcs adv7511_encoder_funcs = { - .dpms = adv7511_encoder_dpms, - .mode_valid = adv7511_encoder_mode_valid, - .mode_set = adv7511_encoder_mode_set, - .detect = adv7511_encoder_detect, - .get_modes = adv7511_get_modes, +/* Connector funcs */ +static struct adv7511 *connector_to_adv7511(struct drm_connector *connector) +{ + return container_of(connector, struct adv7511, connector); +} + +static int adv7511_connector_get_modes(struct drm_connector *connector) +{ + struct adv7511 *adv = connector_to_adv7511(connector); + + return adv7511_get_modes(adv, connector); +} + +static enum drm_mode_status +adv7511_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) +{ + struct adv7511 *adv = connector_to_adv7511(connector); + + return adv7511_mode_valid(adv, mode); +} + +static struct drm_connector_helper_funcs adv7511_connector_helper_funcs = { + .get_modes = adv7511_connector_get_modes, + .mode_valid = adv7511_connector_mode_valid, +}; + +static enum drm_connector_status +adv7511_connector_detect(struct drm_connector *connector, bool force) +{ + struct adv7511 *adv = connector_to_adv7511(connector); + + return adv7511_detect(adv, connector); +} + +static struct drm_connector_funcs adv7511_connector_funcs = { + .dpms = drm_atomic_helper_connector_dpms, + .fill_modes = drm_helper_probe_single_connector_modes, + .detect = adv7511_connector_detect, + .destroy = drm_connector_cleanup, + .reset = drm_atomic_helper_connector_reset, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, +}; + +/* Bridge funcs */ +static struct adv7511 *bridge_to_adv7511(struct drm_bridge *bridge) +{ + return container_of(bridge, struct adv7511, bridge); +} + +static void adv7511_bridge_enable(struct drm_bridge *bridge) +{ + struct adv7511 *adv = bridge_to_adv7511(bridge); + + adv7511_power_on(adv); +} + +static void adv7511_bridge_disable(struct drm_bridge *bridge) +{ + struct adv7511 *adv = bridge_to_adv7511(bridge); + + adv7511_power_off(adv); +} + +static void adv7511_bridge_mode_set(struct drm_bridge *bridge, + struct drm_display_mode *mode, + struct drm_display_mode *adj_mode) +{ + struct adv7511 *adv = bridge_to_adv7511(bridge); + + adv7511_mode_set(adv, mode, adj_mode); +} + +static int adv7511_bridge_attach(struct drm_bridge *bridge) +{ + struct adv7511 *adv = bridge_to_adv7511(bridge); + int ret; + + if (!bridge->encoder) { + DRM_ERROR("Parent encoder object not found"); + return -ENODEV; + } + + adv->connector.polled = DRM_CONNECTOR_POLL_HPD; + + ret = drm_connector_init(bridge->dev, &adv->connector, + &adv7511_connector_funcs, + DRM_MODE_CONNECTOR_HDMIA); + if (ret) { + DRM_ERROR("Failed to initialize connector with drm\n"); + return ret; + } + drm_connector_helper_add(&adv->connector, + &adv7511_connector_helper_funcs); + drm_mode_connector_attach_encoder(&adv->connector, bridge->encoder); + + if (adv->type == ADV7533) + ret = adv7533_attach_dsi(adv); + + return ret; +} + +static struct drm_bridge_funcs adv7511_bridge_funcs = { + .enable = adv7511_bridge_enable, + .disable = adv7511_bridge_disable, + .mode_set = adv7511_bridge_mode_set, + .attach = adv7511_bridge_attach, }; /* ----------------------------------------------------------------------------- @@ -780,8 +845,6 @@ static int adv7511_parse_dt(struct device_node *np, const char *str; int ret; - memset(config, 0, sizeof(*config)); - of_property_read_u32(np, "adi,input-depth", &config->input_color_depth); if (config->input_color_depth != 8 && config->input_color_depth != 10 && config->input_color_depth != 12) @@ -881,7 +944,17 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id) adv7511->powered = false; adv7511->status = connector_status_disconnected; - ret = adv7511_parse_dt(dev->of_node, &link_config); + if (dev->of_node) + adv7511->type = (enum adv7511_type)of_device_get_match_data(dev); + else + adv7511->type = id->driver_data; + + memset(&link_config, 0, sizeof(link_config)); + + if (adv7511->type == ADV7511) + ret = adv7511_parse_dt(dev->of_node, &link_config); + else + ret = adv7533_parse_dt(dev->of_node, adv7511); if (ret) return ret; @@ -907,8 +980,12 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id) return ret; dev_dbg(dev, "Rev. %d\n", val); - ret = regmap_register_patch(adv7511->regmap, adv7511_fixed_registers, - ARRAY_SIZE(adv7511_fixed_registers)); + if (adv7511->type == ADV7511) + ret = regmap_register_patch(adv7511->regmap, + adv7511_fixed_registers, + ARRAY_SIZE(adv7511_fixed_registers)); + else + ret = adv7533_patch_registers(adv7511); if (ret) return ret; @@ -923,6 +1000,12 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id) if (!adv7511->i2c_edid) return -ENOMEM; + if (adv7511->type == ADV7533) { + ret = adv7533_init_cec(adv7511); + if (ret) + goto err_i2c_unregister_edid; + } + if (i2c->irq) { init_waitqueue_head(&adv7511->wq); @@ -931,7 +1014,7 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id) IRQF_ONESHOT, dev_name(dev), adv7511); if (ret) - goto err_i2c_unregister_device; + goto err_unregister_cec; } /* CEC is unused for now */ @@ -942,11 +1025,23 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id) i2c_set_clientdata(i2c, adv7511); - adv7511_set_link_config(adv7511, &link_config); + if (adv7511->type == ADV7511) + adv7511_set_link_config(adv7511, &link_config); + + adv7511->bridge.funcs = &adv7511_bridge_funcs; + adv7511->bridge.of_node = dev->of_node; + + ret = drm_bridge_add(&adv7511->bridge); + if (ret) { + dev_err(dev, "failed to add adv7511 bridge\n"); + goto err_unregister_cec; + } return 0; -err_i2c_unregister_device: +err_unregister_cec: + adv7533_uninit_cec(adv7511); +err_i2c_unregister_edid: i2c_unregister_device(adv7511->i2c_edid); return ret; @@ -956,6 +1051,13 @@ static int adv7511_remove(struct i2c_client *i2c) { struct adv7511 *adv7511 = i2c_get_clientdata(i2c); + if (adv7511->type == ADV7533) { + adv7533_detach_dsi(adv7511); + adv7533_uninit_cec(adv7511); + } + + drm_bridge_remove(&adv7511->bridge); + i2c_unregister_device(adv7511->i2c_edid); kfree(adv7511->edid); @@ -963,59 +1065,57 @@ static int adv7511_remove(struct i2c_client *i2c) return 0; } -static int adv7511_encoder_init(struct i2c_client *i2c, struct drm_device *dev, - struct drm_encoder_slave *encoder) -{ - - struct adv7511 *adv7511 = i2c_get_clientdata(i2c); - - encoder->slave_priv = adv7511; - encoder->slave_funcs = &adv7511_encoder_funcs; - - adv7511->encoder = &encoder->base; - - return 0; -} - static const struct i2c_device_id adv7511_i2c_ids[] = { - { "adv7511", 0 }, - { "adv7511w", 0 }, - { "adv7513", 0 }, + { "adv7511", ADV7511 }, + { "adv7511w", ADV7511 }, + { "adv7513", ADV7511 }, +#ifdef CONFIG_DRM_I2C_ADV7533 + { "adv7533", ADV7533 }, +#endif { } }; MODULE_DEVICE_TABLE(i2c, adv7511_i2c_ids); static const struct of_device_id adv7511_of_ids[] = { - { .compatible = "adi,adv7511", }, - { .compatible = "adi,adv7511w", }, - { .compatible = "adi,adv7513", }, + { .compatible = "adi,adv7511", .data = (void *)ADV7511 }, + { .compatible = "adi,adv7511w", .data = (void *)ADV7511 }, + { .compatible = "adi,adv7513", .data = (void *)ADV7511 }, +#ifdef CONFIG_DRM_I2C_ADV7533 + { .compatible = "adi,adv7533", .data = (void *)ADV7533 }, +#endif { } }; MODULE_DEVICE_TABLE(of, adv7511_of_ids); -static struct drm_i2c_encoder_driver adv7511_driver = { - .i2c_driver = { - .driver = { - .name = "adv7511", - .of_match_table = adv7511_of_ids, - }, - .id_table = adv7511_i2c_ids, - .probe = adv7511_probe, - .remove = adv7511_remove, - }, +static struct mipi_dsi_driver adv7533_dsi_driver = { + .driver.name = "adv7533", +}; - .encoder_init = adv7511_encoder_init, +static struct i2c_driver adv7511_driver = { + .driver = { + .name = "adv7511", + .of_match_table = adv7511_of_ids, + }, + .id_table = adv7511_i2c_ids, + .probe = adv7511_probe, + .remove = adv7511_remove, }; static int __init adv7511_init(void) { - return drm_i2c_encoder_register(THIS_MODULE, &adv7511_driver); + if (IS_ENABLED(CONFIG_DRM_MIPI_DSI)) + mipi_dsi_driver_register(&adv7533_dsi_driver); + + return i2c_add_driver(&adv7511_driver); } module_init(adv7511_init); static void __exit adv7511_exit(void) { - drm_i2c_encoder_unregister(&adv7511_driver); + i2c_del_driver(&adv7511_driver); + + if (IS_ENABLED(CONFIG_DRM_MIPI_DSI)) + mipi_dsi_driver_unregister(&adv7533_dsi_driver); } module_exit(adv7511_exit); diff --git a/drivers/gpu/drm/bridge/adv7511/adv7533.c b/drivers/gpu/drm/bridge/adv7511/adv7533.c new file mode 100644 index 000000000000..5eebd15899b1 --- /dev/null +++ b/drivers/gpu/drm/bridge/adv7511/adv7533.c @@ -0,0 +1,265 @@ +/* + * Copyright (c) 2016, 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 + +#include "adv7511.h" + +static const struct reg_sequence adv7533_fixed_registers[] = { + { 0x16, 0x20 }, + { 0x9a, 0xe0 }, + { 0xba, 0x70 }, + { 0xde, 0x82 }, + { 0xe4, 0x40 }, + { 0xe5, 0x80 }, +}; + +static const struct reg_sequence adv7533_cec_fixed_registers[] = { + { 0x15, 0xd0 }, + { 0x17, 0xd0 }, + { 0x24, 0x20 }, + { 0x57, 0x11 }, +}; + +static const struct regmap_config adv7533_cec_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + + .max_register = 0xff, + .cache_type = REGCACHE_RBTREE, +}; + +static void adv7511_dsi_config_timing_gen(struct adv7511 *adv) +{ + struct mipi_dsi_device *dsi = adv->dsi; + struct drm_display_mode *mode = &adv->curr_mode; + unsigned int hsw, hfp, hbp, vsw, vfp, vbp; + u8 clock_div_by_lanes[] = { 6, 4, 3 }; /* 2, 3, 4 lanes */ + + hsw = mode->hsync_end - mode->hsync_start; + hfp = mode->hsync_start - mode->hdisplay; + hbp = mode->htotal - mode->hsync_end; + vsw = mode->vsync_end - mode->vsync_start; + vfp = mode->vsync_start - mode->vdisplay; + vbp = mode->vtotal - mode->vsync_end; + + /* set pixel clock divider mode */ + regmap_write(adv->regmap_cec, 0x16, + clock_div_by_lanes[dsi->lanes - 2] << 3); + + /* horizontal porch params */ + regmap_write(adv->regmap_cec, 0x28, mode->htotal >> 4); + regmap_write(adv->regmap_cec, 0x29, (mode->htotal << 4) & 0xff); + regmap_write(adv->regmap_cec, 0x2a, hsw >> 4); + regmap_write(adv->regmap_cec, 0x2b, (hsw << 4) & 0xff); + regmap_write(adv->regmap_cec, 0x2c, hfp >> 4); + regmap_write(adv->regmap_cec, 0x2d, (hfp << 4) & 0xff); + regmap_write(adv->regmap_cec, 0x2e, hbp >> 4); + regmap_write(adv->regmap_cec, 0x2f, (hbp << 4) & 0xff); + + /* vertical porch params */ + regmap_write(adv->regmap_cec, 0x30, mode->vtotal >> 4); + regmap_write(adv->regmap_cec, 0x31, (mode->vtotal << 4) & 0xff); + regmap_write(adv->regmap_cec, 0x32, vsw >> 4); + regmap_write(adv->regmap_cec, 0x33, (vsw << 4) & 0xff); + regmap_write(adv->regmap_cec, 0x34, vfp >> 4); + regmap_write(adv->regmap_cec, 0x35, (vfp << 4) & 0xff); + regmap_write(adv->regmap_cec, 0x36, vbp >> 4); + regmap_write(adv->regmap_cec, 0x37, (vbp << 4) & 0xff); +} + +void adv7533_dsi_power_on(struct adv7511 *adv) +{ + struct mipi_dsi_device *dsi = adv->dsi; + + if (adv->use_timing_gen) + adv7511_dsi_config_timing_gen(adv); + + /* set number of dsi lanes */ + regmap_write(adv->regmap_cec, 0x1c, dsi->lanes << 4); + + if (adv->use_timing_gen) { + /* reset internal timing generator */ + regmap_write(adv->regmap_cec, 0x27, 0xcb); + regmap_write(adv->regmap_cec, 0x27, 0x8b); + regmap_write(adv->regmap_cec, 0x27, 0xcb); + } else { + /* disable internal timing generator */ + regmap_write(adv->regmap_cec, 0x27, 0x0b); + } + + /* enable hdmi */ + regmap_write(adv->regmap_cec, 0x03, 0x89); + /* disable test mode */ + regmap_write(adv->regmap_cec, 0x55, 0x00); + + regmap_register_patch(adv->regmap_cec, adv7533_cec_fixed_registers, + ARRAY_SIZE(adv7533_cec_fixed_registers)); +} + +void adv7533_dsi_power_off(struct adv7511 *adv) +{ + /* disable hdmi */ + regmap_write(adv->regmap_cec, 0x03, 0x0b); + /* disable internal timing generator */ + regmap_write(adv->regmap_cec, 0x27, 0x0b); +} + +void adv7533_mode_set(struct adv7511 *adv, struct drm_display_mode *mode) +{ + struct mipi_dsi_device *dsi = adv->dsi; + int lanes, ret; + + if (adv->num_dsi_lanes != 4) + return; + + if (mode->clock > 80000) + lanes = 4; + else + lanes = 3; + + if (lanes != dsi->lanes) { + mipi_dsi_detach(dsi); + dsi->lanes = lanes; + ret = mipi_dsi_attach(dsi); + if (ret) + dev_err(&dsi->dev, "failed to change host lanes\n"); + } +} + +int adv7533_patch_registers(struct adv7511 *adv) +{ + return regmap_register_patch(adv->regmap, + adv7533_fixed_registers, + ARRAY_SIZE(adv7533_fixed_registers)); +} + +void adv7533_uninit_cec(struct adv7511 *adv) +{ + i2c_unregister_device(adv->i2c_cec); +} + +static const int cec_i2c_addr = 0x78; + +int adv7533_init_cec(struct adv7511 *adv) +{ + int ret; + + adv->i2c_cec = i2c_new_dummy(adv->i2c_main->adapter, cec_i2c_addr >> 1); + if (!adv->i2c_cec) + return -ENOMEM; + + adv->regmap_cec = devm_regmap_init_i2c(adv->i2c_cec, + &adv7533_cec_regmap_config); + if (IS_ERR(adv->regmap_cec)) { + ret = PTR_ERR(adv->regmap_cec); + goto err; + } + + ret = regmap_register_patch(adv->regmap_cec, + adv7533_cec_fixed_registers, + ARRAY_SIZE(adv7533_cec_fixed_registers)); + if (ret) + goto err; + + return 0; +err: + adv7533_uninit_cec(adv); + return ret; +} + +int adv7533_attach_dsi(struct adv7511 *adv) +{ + struct device *dev = &adv->i2c_main->dev; + struct mipi_dsi_host *host; + struct mipi_dsi_device *dsi; + int ret = 0; + const struct mipi_dsi_device_info info = { .type = "adv7533", + .channel = 0, + .node = NULL, + }; + + host = of_find_mipi_dsi_host_by_node(adv->host_node); + if (!host) { + dev_err(dev, "failed to find dsi host\n"); + return -EPROBE_DEFER; + } + + dsi = mipi_dsi_device_register_full(host, &info); + if (IS_ERR(dsi)) { + dev_err(dev, "failed to create dsi device\n"); + ret = PTR_ERR(dsi); + goto err_dsi_device; + } + + adv->dsi = dsi; + + dsi->lanes = adv->num_dsi_lanes; + dsi->format = MIPI_DSI_FMT_RGB888; + dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE | + MIPI_DSI_MODE_EOT_PACKET | MIPI_DSI_MODE_VIDEO_HSE; + + ret = mipi_dsi_attach(dsi); + if (ret < 0) { + dev_err(dev, "failed to attach dsi to host\n"); + goto err_dsi_attach; + } + + return 0; + +err_dsi_attach: + mipi_dsi_device_unregister(dsi); +err_dsi_device: + return ret; +} + +void adv7533_detach_dsi(struct adv7511 *adv) +{ + mipi_dsi_detach(adv->dsi); + mipi_dsi_device_unregister(adv->dsi); +} + +int adv7533_parse_dt(struct device_node *np, struct adv7511 *adv) +{ + u32 num_lanes; + struct device_node *endpoint; + + of_property_read_u32(np, "adi,dsi-lanes", &num_lanes); + + if (num_lanes < 1 || num_lanes > 4) + return -EINVAL; + + adv->num_dsi_lanes = num_lanes; + + endpoint = of_graph_get_next_endpoint(np, NULL); + if (!endpoint) + return -ENODEV; + + adv->host_node = of_graph_get_remote_port_parent(endpoint); + if (!adv->host_node) { + of_node_put(endpoint); + return -ENODEV; + } + + of_node_put(endpoint); + of_node_put(adv->host_node); + + adv->use_timing_gen = !of_property_read_bool(np, + "adi,disable-timing-generator"); + + /* TODO: Check if these need to be parsed by DT or not */ + adv->rgb = true; + adv->embedded_sync = false; + + return 0; +} diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c index 7699597070a1..32715daf73cb 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c @@ -938,7 +938,7 @@ int analogix_dp_get_modes(struct drm_connector *connector) num_modes += drm_panel_get_modes(dp->plat_data->panel); if (dp->plat_data->get_modes) - num_modes += dp->plat_data->get_modes(dp->plat_data); + num_modes += dp->plat_data->get_modes(dp->plat_data, connector); return num_modes; } @@ -1208,6 +1208,7 @@ static int analogix_dp_dt_parse_pdata(struct analogix_dp_device *dp) switch (dp->plat_data->dev_type) { case RK3288_DP: + case RK3399_EDP: /* * Like Rk3288 DisplayPort TRM indicate that "Main link * containing 4 physical lanes of 2.7/1.62 Gbps/lane". diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h index f09275d40f70..b45638043ec4 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.h @@ -127,10 +127,10 @@ enum analog_power_block { }; enum dp_irq_type { - DP_IRQ_TYPE_HP_CABLE_IN, - DP_IRQ_TYPE_HP_CABLE_OUT, - DP_IRQ_TYPE_HP_CHANGE, - DP_IRQ_TYPE_UNKNOWN, + DP_IRQ_TYPE_HP_CABLE_IN = BIT(0), + DP_IRQ_TYPE_HP_CABLE_OUT = BIT(1), + DP_IRQ_TYPE_HP_CHANGE = BIT(2), + DP_IRQ_TYPE_UNKNOWN = BIT(3), }; struct video_info { diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c index 49205ef02be3..48030f0cf497 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c @@ -74,8 +74,12 @@ void analogix_dp_init_analog_param(struct analogix_dp_device *dp) reg = SEL_24M | TX_DVDD_BIT_1_0625V; writel(reg, dp->reg_base + ANALOGIX_DP_ANALOG_CTL_2); - if (dp->plat_data && (dp->plat_data->dev_type == RK3288_DP)) { - writel(REF_CLK_24M, dp->reg_base + ANALOGIX_DP_PLL_REG_1); + if (dp->plat_data && is_rockchip(dp->plat_data->dev_type)) { + reg = REF_CLK_24M; + if (dp->plat_data->dev_type == RK3288_DP) + reg ^= REF_CLK_MASK; + + writel(reg, dp->reg_base + ANALOGIX_DP_PLL_REG_1); writel(0x95, dp->reg_base + ANALOGIX_DP_PLL_REG_2); writel(0x40, dp->reg_base + ANALOGIX_DP_PLL_REG_3); writel(0x58, dp->reg_base + ANALOGIX_DP_PLL_REG_4); @@ -244,7 +248,7 @@ void analogix_dp_set_analog_power_down(struct analogix_dp_device *dp, u32 reg; u32 phy_pd_addr = ANALOGIX_DP_PHY_PD; - if (dp->plat_data && (dp->plat_data->dev_type == RK3288_DP)) + if (dp->plat_data && is_rockchip(dp->plat_data->dev_type)) phy_pd_addr = ANALOGIX_DP_PD; switch (block) { @@ -448,7 +452,7 @@ void analogix_dp_init_aux(struct analogix_dp_device *dp) analogix_dp_reset_aux(dp); /* Disable AUX transaction H/W retry */ - if (dp->plat_data && (dp->plat_data->dev_type == RK3288_DP)) + if (dp->plat_data && is_rockchip(dp->plat_data->dev_type)) reg = AUX_BIT_PERIOD_EXPECTED_DELAY(0) | AUX_HW_RETRY_COUNT_SEL(3) | AUX_HW_RETRY_INTERVAL_600_MICROSECONDS; diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h index 337912b0aeab..cdcc6c5add5e 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.h @@ -163,8 +163,9 @@ #define HSYNC_POLARITY_CFG (0x1 << 0) /* ANALOGIX_DP_PLL_REG_1 */ -#define REF_CLK_24M (0x1 << 1) -#define REF_CLK_27M (0x0 << 1) +#define REF_CLK_24M (0x1 << 0) +#define REF_CLK_27M (0x0 << 0) +#define REF_CLK_MASK (0x1 << 0) /* ANALOGIX_DP_LANE_MAP */ #define LANE3_MAP_LOGIC_LANE_0 (0x0 << 6) diff --git a/drivers/gpu/drm/bridge/dw-hdmi.c b/drivers/gpu/drm/bridge/dw-hdmi.c index 70b1f7d4270b..77ab47341658 100644 --- a/drivers/gpu/drm/bridge/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/dw-hdmi.c @@ -1495,14 +1495,6 @@ static void dw_hdmi_connector_force(struct drm_connector *connector) } static const struct drm_connector_funcs dw_hdmi_connector_funcs = { - .dpms = drm_helper_connector_dpms, - .fill_modes = drm_helper_probe_single_connector_modes, - .detect = dw_hdmi_connector_detect, - .destroy = dw_hdmi_connector_destroy, - .force = dw_hdmi_connector_force, -}; - -static const struct drm_connector_funcs dw_hdmi_atomic_connector_funcs = { .dpms = drm_atomic_helper_connector_dpms, .fill_modes = drm_helper_probe_single_connector_modes, .detect = dw_hdmi_connector_detect, @@ -1634,14 +1626,9 @@ static int dw_hdmi_register(struct drm_device *drm, struct dw_hdmi *hdmi) drm_connector_helper_add(&hdmi->connector, &dw_hdmi_connector_helper_funcs); - if (drm_core_check_feature(drm, DRIVER_ATOMIC)) - drm_connector_init(drm, &hdmi->connector, - &dw_hdmi_atomic_connector_funcs, - DRM_MODE_CONNECTOR_HDMIA); - else - drm_connector_init(drm, &hdmi->connector, - &dw_hdmi_connector_funcs, - DRM_MODE_CONNECTOR_HDMIA); + drm_connector_init(drm, &hdmi->connector, + &dw_hdmi_connector_funcs, + DRM_MODE_CONNECTOR_HDMIA); drm_mode_connector_attach_encoder(&hdmi->connector, encoder); diff --git a/drivers/gpu/drm/bridge/parade-ps8622.c b/drivers/gpu/drm/bridge/parade-ps8622.c index 5cd8dd7e5904..583b8ce614e3 100644 --- a/drivers/gpu/drm/bridge/parade-ps8622.c +++ b/drivers/gpu/drm/bridge/parade-ps8622.c @@ -636,9 +636,7 @@ static int ps8622_remove(struct i2c_client *client) { struct ps8622_bridge *ps8622 = i2c_get_clientdata(client); - if (ps8622->bl) - backlight_device_unregister(ps8622->bl); - + backlight_device_unregister(ps8622->bl); drm_bridge_remove(&ps8622->bridge); return 0; diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c new file mode 100644 index 000000000000..a09825d8c94a --- /dev/null +++ b/drivers/gpu/drm/bridge/tc358767.c @@ -0,0 +1,1413 @@ +/* + * tc358767 eDP bridge driver + * + * Copyright (C) 2016 CogentEmbedded Inc + * Author: Andrey Gusakov + * + * Copyright (C) 2016 Pengutronix, Philipp Zabel + * + * Initially based on: drivers/gpu/drm/i2c/tda998x_drv.c + * + * Copyright (C) 2012 Texas Instruments + * Author: Rob Clark + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +/* Registers */ + +/* Display Parallel Interface */ +#define DPIPXLFMT 0x0440 +#define VS_POL_ACTIVE_LOW (1 << 10) +#define HS_POL_ACTIVE_LOW (1 << 9) +#define DE_POL_ACTIVE_HIGH (0 << 8) +#define SUB_CFG_TYPE_CONFIG1 (0 << 2) /* LSB aligned */ +#define SUB_CFG_TYPE_CONFIG2 (1 << 2) /* Loosely Packed */ +#define SUB_CFG_TYPE_CONFIG3 (2 << 2) /* LSB aligned 8-bit */ +#define DPI_BPP_RGB888 (0 << 0) +#define DPI_BPP_RGB666 (1 << 0) +#define DPI_BPP_RGB565 (2 << 0) + +/* Video Path */ +#define VPCTRL0 0x0450 +#define OPXLFMT_RGB666 (0 << 8) +#define OPXLFMT_RGB888 (1 << 8) +#define FRMSYNC_DISABLED (0 << 4) /* Video Timing Gen Disabled */ +#define FRMSYNC_ENABLED (1 << 4) /* Video Timing Gen Enabled */ +#define MSF_DISABLED (0 << 0) /* Magic Square FRC disabled */ +#define MSF_ENABLED (1 << 0) /* Magic Square FRC enabled */ +#define HTIM01 0x0454 +#define HTIM02 0x0458 +#define VTIM01 0x045c +#define VTIM02 0x0460 +#define VFUEN0 0x0464 +#define VFUEN BIT(0) /* Video Frame Timing Upload */ + +/* System */ +#define TC_IDREG 0x0500 +#define SYSCTRL 0x0510 +#define DP0_AUDSRC_NO_INPUT (0 << 3) +#define DP0_AUDSRC_I2S_RX (1 << 3) +#define DP0_VIDSRC_NO_INPUT (0 << 0) +#define DP0_VIDSRC_DSI_RX (1 << 0) +#define DP0_VIDSRC_DPI_RX (2 << 0) +#define DP0_VIDSRC_COLOR_BAR (3 << 0) + +/* Control */ +#define DP0CTL 0x0600 +#define VID_MN_GEN BIT(6) /* Auto-generate M/N values */ +#define EF_EN BIT(5) /* Enable Enhanced Framing */ +#define VID_EN BIT(1) /* Video transmission enable */ +#define DP_EN BIT(0) /* Enable DPTX function */ + +/* Clocks */ +#define DP0_VIDMNGEN0 0x0610 +#define DP0_VIDMNGEN1 0x0614 +#define DP0_VMNGENSTATUS 0x0618 + +/* Main Channel */ +#define DP0_SECSAMPLE 0x0640 +#define DP0_VIDSYNCDELAY 0x0644 +#define DP0_TOTALVAL 0x0648 +#define DP0_STARTVAL 0x064c +#define DP0_ACTIVEVAL 0x0650 +#define DP0_SYNCVAL 0x0654 +#define DP0_MISC 0x0658 +#define TU_SIZE_RECOMMENDED (0x3f << 16) /* LSCLK cycles per TU */ +#define BPC_6 (0 << 5) +#define BPC_8 (1 << 5) + +/* AUX channel */ +#define DP0_AUXCFG0 0x0660 +#define DP0_AUXCFG1 0x0664 +#define AUX_RX_FILTER_EN BIT(16) + +#define DP0_AUXADDR 0x0668 +#define DP0_AUXWDATA(i) (0x066c + (i) * 4) +#define DP0_AUXRDATA(i) (0x067c + (i) * 4) +#define DP0_AUXSTATUS 0x068c +#define AUX_STATUS_MASK 0xf0 +#define AUX_STATUS_SHIFT 4 +#define AUX_TIMEOUT BIT(1) +#define AUX_BUSY BIT(0) +#define DP0_AUXI2CADR 0x0698 + +/* Link Training */ +#define DP0_SRCCTRL 0x06a0 +#define DP0_SRCCTRL_SCRMBLDIS BIT(13) +#define DP0_SRCCTRL_EN810B BIT(12) +#define DP0_SRCCTRL_NOTP (0 << 8) +#define DP0_SRCCTRL_TP1 (1 << 8) +#define DP0_SRCCTRL_TP2 (2 << 8) +#define DP0_SRCCTRL_LANESKEW BIT(7) +#define DP0_SRCCTRL_SSCG BIT(3) +#define DP0_SRCCTRL_LANES_1 (0 << 2) +#define DP0_SRCCTRL_LANES_2 (1 << 2) +#define DP0_SRCCTRL_BW27 (1 << 1) +#define DP0_SRCCTRL_BW162 (0 << 1) +#define DP0_SRCCTRL_AUTOCORRECT BIT(0) +#define DP0_LTSTAT 0x06d0 +#define LT_LOOPDONE BIT(13) +#define LT_STATUS_MASK (0x1f << 8) +#define LT_CHANNEL1_EQ_BITS (DP_CHANNEL_EQ_BITS << 4) +#define LT_INTERLANE_ALIGN_DONE BIT(3) +#define LT_CHANNEL0_EQ_BITS (DP_CHANNEL_EQ_BITS) +#define DP0_SNKLTCHGREQ 0x06d4 +#define DP0_LTLOOPCTRL 0x06d8 +#define DP0_SNKLTCTRL 0x06e4 + +/* PHY */ +#define DP_PHY_CTRL 0x0800 +#define DP_PHY_RST BIT(28) /* DP PHY Global Soft Reset */ +#define BGREN BIT(25) /* AUX PHY BGR Enable */ +#define PWR_SW_EN BIT(24) /* PHY Power Switch Enable */ +#define PHY_M1_RST BIT(12) /* Reset PHY1 Main Channel */ +#define PHY_RDY BIT(16) /* PHY Main Channels Ready */ +#define PHY_M0_RST BIT(8) /* Reset PHY0 Main Channel */ +#define PHY_A0_EN BIT(1) /* PHY Aux Channel0 Enable */ +#define PHY_M0_EN BIT(0) /* PHY Main Channel0 Enable */ + +/* PLL */ +#define DP0_PLLCTRL 0x0900 +#define DP1_PLLCTRL 0x0904 /* not defined in DS */ +#define PXL_PLLCTRL 0x0908 +#define PLLUPDATE BIT(2) +#define PLLBYP BIT(1) +#define PLLEN BIT(0) +#define PXL_PLLPARAM 0x0914 +#define IN_SEL_REFCLK (0 << 14) +#define SYS_PLLPARAM 0x0918 +#define REF_FREQ_38M4 (0 << 8) /* 38.4 MHz */ +#define REF_FREQ_19M2 (1 << 8) /* 19.2 MHz */ +#define REF_FREQ_26M (2 << 8) /* 26 MHz */ +#define REF_FREQ_13M (3 << 8) /* 13 MHz */ +#define SYSCLK_SEL_LSCLK (0 << 4) +#define LSCLK_DIV_1 (0 << 0) +#define LSCLK_DIV_2 (1 << 0) + +/* Test & Debug */ +#define TSTCTL 0x0a00 +#define PLL_DBG 0x0a04 + +static bool tc_test_pattern; +module_param_named(test, tc_test_pattern, bool, 0644); + +struct tc_edp_link { + struct drm_dp_link base; + u8 assr; + int scrambler_dis; + int spread; + int coding8b10b; + u8 swing; + u8 preemp; +}; + +struct tc_data { + struct device *dev; + struct regmap *regmap; + struct drm_dp_aux aux; + + struct drm_bridge bridge; + struct drm_connector connector; + struct drm_panel *panel; + + /* link settings */ + struct tc_edp_link link; + + /* display edid */ + struct edid *edid; + /* current mode */ + struct drm_display_mode *mode; + + u32 rev; + u8 assr; + + struct gpio_desc *sd_gpio; + struct gpio_desc *reset_gpio; + struct clk *refclk; +}; + +static inline struct tc_data *aux_to_tc(struct drm_dp_aux *a) +{ + return container_of(a, struct tc_data, aux); +} + +static inline struct tc_data *bridge_to_tc(struct drm_bridge *b) +{ + return container_of(b, struct tc_data, bridge); +} + +static inline struct tc_data *connector_to_tc(struct drm_connector *c) +{ + return container_of(c, struct tc_data, connector); +} + +/* Simple macros to avoid repeated error checks */ +#define tc_write(reg, var) \ + do { \ + ret = regmap_write(tc->regmap, reg, var); \ + if (ret) \ + goto err; \ + } while (0) +#define tc_read(reg, var) \ + do { \ + ret = regmap_read(tc->regmap, reg, var); \ + if (ret) \ + goto err; \ + } while (0) + +static inline int tc_poll_timeout(struct regmap *map, unsigned int addr, + unsigned int cond_mask, + unsigned int cond_value, + unsigned long sleep_us, u64 timeout_us) +{ + ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); + unsigned int val; + int ret; + + for (;;) { + ret = regmap_read(map, addr, &val); + if (ret) + break; + if ((val & cond_mask) == cond_value) + break; + if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { + ret = regmap_read(map, addr, &val); + break; + } + if (sleep_us) + usleep_range((sleep_us >> 2) + 1, sleep_us); + } + return ret ?: (((val & cond_mask) == cond_value) ? 0 : -ETIMEDOUT); +} + +static int tc_aux_wait_busy(struct tc_data *tc, unsigned int timeout_ms) +{ + return tc_poll_timeout(tc->regmap, DP0_AUXSTATUS, AUX_BUSY, 0, + 1000, 1000 * timeout_ms); +} + +static int tc_aux_get_status(struct tc_data *tc, u8 *reply) +{ + int ret; + u32 value; + + ret = regmap_read(tc->regmap, DP0_AUXSTATUS, &value); + if (ret < 0) + return ret; + if (value & AUX_BUSY) { + if (value & AUX_TIMEOUT) { + dev_err(tc->dev, "i2c access timeout!\n"); + return -ETIMEDOUT; + } + return -EBUSY; + } + + *reply = (value & AUX_STATUS_MASK) >> AUX_STATUS_SHIFT; + return 0; +} + +static ssize_t tc_aux_transfer(struct drm_dp_aux *aux, + struct drm_dp_aux_msg *msg) +{ + struct tc_data *tc = aux_to_tc(aux); + size_t size = min_t(size_t, 8, msg->size); + u8 request = msg->request & ~DP_AUX_I2C_MOT; + u8 *buf = msg->buffer; + u32 tmp = 0; + int i = 0; + int ret; + + if (size == 0) + return 0; + + ret = tc_aux_wait_busy(tc, 100); + if (ret) + goto err; + + if (request == DP_AUX_I2C_WRITE || request == DP_AUX_NATIVE_WRITE) { + /* Store data */ + while (i < size) { + if (request == DP_AUX_NATIVE_WRITE) + tmp = tmp | (buf[i] << (8 * (i & 0x3))); + else + tmp = (tmp << 8) | buf[i]; + i++; + if (((i % 4) == 0) || (i == size)) { + tc_write(DP0_AUXWDATA(i >> 2), tmp); + tmp = 0; + } + } + } else if (request != DP_AUX_I2C_READ && + request != DP_AUX_NATIVE_READ) { + return -EINVAL; + } + + /* Store address */ + tc_write(DP0_AUXADDR, msg->address); + /* Start transfer */ + tc_write(DP0_AUXCFG0, ((size - 1) << 8) | request); + + ret = tc_aux_wait_busy(tc, 100); + if (ret) + goto err; + + ret = tc_aux_get_status(tc, &msg->reply); + if (ret) + goto err; + + if (request == DP_AUX_I2C_READ || request == DP_AUX_NATIVE_READ) { + /* Read data */ + while (i < size) { + if ((i % 4) == 0) + tc_read(DP0_AUXRDATA(i >> 2), &tmp); + buf[i] = tmp & 0xff; + tmp = tmp >> 8; + i++; + } + } + + return size; +err: + return ret; +} + +static const char * const training_pattern1_errors[] = { + "No errors", + "Aux write error", + "Aux read error", + "Max voltage reached error", + "Loop counter expired error", + "res", "res", "res" +}; + +static const char * const training_pattern2_errors[] = { + "No errors", + "Aux write error", + "Aux read error", + "Clock recovery failed error", + "Loop counter expired error", + "res", "res", "res" +}; + +static u32 tc_srcctrl(struct tc_data *tc) +{ + /* + * No training pattern, skew lane 1 data by two LSCLK cycles with + * respect to lane 0 data, AutoCorrect Mode = 0 + */ + u32 reg = DP0_SRCCTRL_NOTP | DP0_SRCCTRL_LANESKEW; + + if (tc->link.scrambler_dis) + reg |= DP0_SRCCTRL_SCRMBLDIS; /* Scrambler Disabled */ + if (tc->link.coding8b10b) + /* Enable 8/10B Encoder (TxData[19:16] not used) */ + reg |= DP0_SRCCTRL_EN810B; + if (tc->link.spread) + reg |= DP0_SRCCTRL_SSCG; /* Spread Spectrum Enable */ + if (tc->link.base.num_lanes == 2) + reg |= DP0_SRCCTRL_LANES_2; /* Two Main Channel Lanes */ + if (tc->link.base.rate != 162000) + reg |= DP0_SRCCTRL_BW27; /* 2.7 Gbps link */ + return reg; +} + +static void tc_wait_pll_lock(struct tc_data *tc) +{ + /* Wait for PLL to lock: up to 2.09 ms, depending on refclk */ + usleep_range(3000, 6000); +} + +static int tc_pxl_pll_en(struct tc_data *tc, u32 refclk, u32 pixelclock) +{ + int ret; + int i_pre, best_pre = 1; + int i_post, best_post = 1; + int div, best_div = 1; + int mul, best_mul = 1; + int delta, best_delta; + int ext_div[] = {1, 2, 3, 5, 7}; + int best_pixelclock = 0; + int vco_hi = 0; + + dev_dbg(tc->dev, "PLL: requested %d pixelclock, ref %d\n", pixelclock, + refclk); + best_delta = pixelclock; + /* Loop over all possible ext_divs, skipping invalid configurations */ + for (i_pre = 0; i_pre < ARRAY_SIZE(ext_div); i_pre++) { + /* + * refclk / ext_pre_div should be in the 1 to 200 MHz range. + * We don't allow any refclk > 200 MHz, only check lower bounds. + */ + if (refclk / ext_div[i_pre] < 1000000) + continue; + for (i_post = 0; i_post < ARRAY_SIZE(ext_div); i_post++) { + for (div = 1; div <= 16; div++) { + u32 clk; + u64 tmp; + + tmp = pixelclock * ext_div[i_pre] * + ext_div[i_post] * div; + do_div(tmp, refclk); + mul = tmp; + + /* Check limits */ + if ((mul < 1) || (mul > 128)) + continue; + + clk = (refclk / ext_div[i_pre] / div) * mul; + /* + * refclk * mul / (ext_pre_div * pre_div) + * should be in the 150 to 650 MHz range + */ + if ((clk > 650000000) || (clk < 150000000)) + continue; + + clk = clk / ext_div[i_post]; + delta = clk - pixelclock; + + if (abs(delta) < abs(best_delta)) { + best_pre = i_pre; + best_post = i_post; + best_div = div; + best_mul = mul; + best_delta = delta; + best_pixelclock = clk; + } + } + } + } + if (best_pixelclock == 0) { + dev_err(tc->dev, "Failed to calc clock for %d pixelclock\n", + pixelclock); + return -EINVAL; + } + + dev_dbg(tc->dev, "PLL: got %d, delta %d\n", best_pixelclock, + best_delta); + dev_dbg(tc->dev, "PLL: %d / %d / %d * %d / %d\n", refclk, + ext_div[best_pre], best_div, best_mul, ext_div[best_post]); + + /* if VCO >= 300 MHz */ + if (refclk / ext_div[best_pre] / best_div * best_mul >= 300000000) + vco_hi = 1; + /* see DS */ + if (best_div == 16) + best_div = 0; + if (best_mul == 128) + best_mul = 0; + + /* Power up PLL and switch to bypass */ + tc_write(PXL_PLLCTRL, PLLBYP | PLLEN); + + tc_write(PXL_PLLPARAM, + (vco_hi << 24) | /* For PLL VCO >= 300 MHz = 1 */ + (ext_div[best_pre] << 20) | /* External Pre-divider */ + (ext_div[best_post] << 16) | /* External Post-divider */ + IN_SEL_REFCLK | /* Use RefClk as PLL input */ + (best_div << 8) | /* Divider for PLL RefClk */ + (best_mul << 0)); /* Multiplier for PLL */ + + /* Force PLL parameter update and disable bypass */ + tc_write(PXL_PLLCTRL, PLLUPDATE | PLLEN); + + tc_wait_pll_lock(tc); + + return 0; +err: + return ret; +} + +static int tc_pxl_pll_dis(struct tc_data *tc) +{ + /* Enable PLL bypass, power down PLL */ + return regmap_write(tc->regmap, PXL_PLLCTRL, PLLBYP); +} + +static int tc_stream_clock_calc(struct tc_data *tc) +{ + int ret; + /* + * If the Stream clock and Link Symbol clock are + * asynchronous with each other, the value of M changes over + * time. This way of generating link clock and stream + * clock is called Asynchronous Clock mode. The value M + * must change while the value N stays constant. The + * value of N in this Asynchronous Clock mode must be set + * to 2^15 or 32,768. + * + * LSCLK = 1/10 of high speed link clock + * + * f_STRMCLK = M/N * f_LSCLK + * M/N = f_STRMCLK / f_LSCLK + * + */ + tc_write(DP0_VIDMNGEN1, 32768); + + return 0; +err: + return ret; +} + +static int tc_aux_link_setup(struct tc_data *tc) +{ + unsigned long rate; + u32 value; + int ret; + + rate = clk_get_rate(tc->refclk); + switch (rate) { + case 38400000: + value = REF_FREQ_38M4; + break; + case 26000000: + value = REF_FREQ_26M; + break; + case 19200000: + value = REF_FREQ_19M2; + break; + case 13000000: + value = REF_FREQ_13M; + break; + default: + dev_err(tc->dev, "Invalid refclk rate: %lu Hz\n", rate); + return -EINVAL; + } + + /* Setup DP-PHY / PLL */ + value |= SYSCLK_SEL_LSCLK | LSCLK_DIV_2; + tc_write(SYS_PLLPARAM, value); + + tc_write(DP_PHY_CTRL, BGREN | PWR_SW_EN | BIT(2) | PHY_A0_EN); + + /* + * Initially PLLs are in bypass. Force PLL parameter update, + * disable PLL bypass, enable PLL + */ + tc_write(DP0_PLLCTRL, PLLUPDATE | PLLEN); + tc_wait_pll_lock(tc); + + tc_write(DP1_PLLCTRL, PLLUPDATE | PLLEN); + tc_wait_pll_lock(tc); + + ret = tc_poll_timeout(tc->regmap, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, + 1000); + if (ret == -ETIMEDOUT) { + dev_err(tc->dev, "Timeout waiting for PHY to become ready"); + return ret; + } else if (ret) + goto err; + + /* Setup AUX link */ + tc_write(DP0_AUXCFG1, AUX_RX_FILTER_EN | + (0x06 << 8) | /* Aux Bit Period Calculator Threshold */ + (0x3f << 0)); /* Aux Response Timeout Timer */ + + return 0; +err: + dev_err(tc->dev, "tc_aux_link_setup failed: %d\n", ret); + return ret; +} + +static int tc_get_display_props(struct tc_data *tc) +{ + int ret; + /* temp buffer */ + u8 tmp[8]; + + /* Read DP Rx Link Capability */ + ret = drm_dp_link_probe(&tc->aux, &tc->link.base); + if (ret < 0) + goto err_dpcd_read; + if ((tc->link.base.rate != 162000) && (tc->link.base.rate != 270000)) + goto err_dpcd_inval; + + ret = drm_dp_dpcd_readb(&tc->aux, DP_MAX_DOWNSPREAD, tmp); + if (ret < 0) + goto err_dpcd_read; + tc->link.spread = tmp[0] & BIT(0); /* 0.5% down spread */ + + ret = drm_dp_dpcd_readb(&tc->aux, DP_MAIN_LINK_CHANNEL_CODING, tmp); + if (ret < 0) + goto err_dpcd_read; + tc->link.coding8b10b = tmp[0] & BIT(0); + tc->link.scrambler_dis = 0; + /* read assr */ + ret = drm_dp_dpcd_readb(&tc->aux, DP_EDP_CONFIGURATION_SET, tmp); + if (ret < 0) + goto err_dpcd_read; + tc->link.assr = tmp[0] & DP_ALTERNATE_SCRAMBLER_RESET_ENABLE; + + dev_dbg(tc->dev, "DPCD rev: %d.%d, rate: %s, lanes: %d, framing: %s\n", + tc->link.base.revision >> 4, tc->link.base.revision & 0x0f, + (tc->link.base.rate == 162000) ? "1.62Gbps" : "2.7Gbps", + tc->link.base.num_lanes, + (tc->link.base.capabilities & DP_LINK_CAP_ENHANCED_FRAMING) ? + "enhanced" : "non-enhanced"); + dev_dbg(tc->dev, "ANSI 8B/10B: %d\n", tc->link.coding8b10b); + dev_dbg(tc->dev, "Display ASSR: %d, TC358767 ASSR: %d\n", + tc->link.assr, tc->assr); + + return 0; + +err_dpcd_read: + dev_err(tc->dev, "failed to read DPCD: %d\n", ret); + return ret; +err_dpcd_inval: + dev_err(tc->dev, "invalid DPCD\n"); + return -EINVAL; +} + +static int tc_set_video_mode(struct tc_data *tc, struct drm_display_mode *mode) +{ + int ret; + int vid_sync_dly; + int max_tu_symbol; + + int left_margin = mode->htotal - mode->hsync_end; + int right_margin = mode->hsync_start - mode->hdisplay; + int hsync_len = mode->hsync_end - mode->hsync_start; + int upper_margin = mode->vtotal - mode->vsync_end; + int lower_margin = mode->vsync_start - mode->vdisplay; + int vsync_len = mode->vsync_end - mode->vsync_start; + + dev_dbg(tc->dev, "set mode %dx%d\n", + mode->hdisplay, mode->vdisplay); + dev_dbg(tc->dev, "H margin %d,%d sync %d\n", + left_margin, right_margin, hsync_len); + dev_dbg(tc->dev, "V margin %d,%d sync %d\n", + upper_margin, lower_margin, vsync_len); + dev_dbg(tc->dev, "total: %dx%d\n", mode->htotal, mode->vtotal); + + + /* LCD Ctl Frame Size */ + tc_write(VPCTRL0, (0x40 << 20) /* VSDELAY */ | + OPXLFMT_RGB888 | FRMSYNC_DISABLED | MSF_DISABLED); + tc_write(HTIM01, (left_margin << 16) | /* H back porch */ + (hsync_len << 0)); /* Hsync */ + tc_write(HTIM02, (right_margin << 16) | /* H front porch */ + (mode->hdisplay << 0)); /* width */ + tc_write(VTIM01, (upper_margin << 16) | /* V back porch */ + (vsync_len << 0)); /* Vsync */ + tc_write(VTIM02, (lower_margin << 16) | /* V front porch */ + (mode->vdisplay << 0)); /* height */ + tc_write(VFUEN0, VFUEN); /* update settings */ + + /* Test pattern settings */ + tc_write(TSTCTL, + (120 << 24) | /* Red Color component value */ + (20 << 16) | /* Green Color component value */ + (99 << 8) | /* Blue Color component value */ + (1 << 4) | /* Enable I2C Filter */ + (2 << 0) | /* Color bar Mode */ + 0); + + /* DP Main Stream Attributes */ + vid_sync_dly = hsync_len + left_margin + mode->hdisplay; + tc_write(DP0_VIDSYNCDELAY, + (0x003e << 16) | /* thresh_dly */ + (vid_sync_dly << 0)); + + tc_write(DP0_TOTALVAL, (mode->vtotal << 16) | (mode->htotal)); + + tc_write(DP0_STARTVAL, + ((upper_margin + vsync_len) << 16) | + ((left_margin + hsync_len) << 0)); + + tc_write(DP0_ACTIVEVAL, (mode->vdisplay << 16) | (mode->hdisplay)); + + tc_write(DP0_SYNCVAL, (vsync_len << 16) | (hsync_len << 0)); + + tc_write(DPIPXLFMT, VS_POL_ACTIVE_LOW | HS_POL_ACTIVE_LOW | + DE_POL_ACTIVE_HIGH | SUB_CFG_TYPE_CONFIG1 | DPI_BPP_RGB888); + + /* + * Recommended maximum number of symbols transferred in a transfer unit: + * DIV_ROUND_UP((input active video bandwidth in bytes) * tu_size, + * (output active video bandwidth in bytes)) + * Must be less than tu_size. + */ + max_tu_symbol = TU_SIZE_RECOMMENDED - 1; + tc_write(DP0_MISC, (max_tu_symbol << 23) | TU_SIZE_RECOMMENDED | BPC_8); + + return 0; +err: + return ret; +} + +static int tc_link_training(struct tc_data *tc, int pattern) +{ + const char * const *errors; + u32 srcctrl = tc_srcctrl(tc) | DP0_SRCCTRL_SCRMBLDIS | + DP0_SRCCTRL_AUTOCORRECT; + int timeout; + int retry; + u32 value; + int ret; + + if (pattern == DP_TRAINING_PATTERN_1) { + srcctrl |= DP0_SRCCTRL_TP1; + errors = training_pattern1_errors; + } else { + srcctrl |= DP0_SRCCTRL_TP2; + errors = training_pattern2_errors; + } + + /* Set DPCD 0x102 for Training Part 1 or 2 */ + tc_write(DP0_SNKLTCTRL, DP_LINK_SCRAMBLING_DISABLE | pattern); + + tc_write(DP0_LTLOOPCTRL, + (0x0f << 28) | /* Defer Iteration Count */ + (0x0f << 24) | /* Loop Iteration Count */ + (0x0d << 0)); /* Loop Timer Delay */ + + retry = 5; + do { + /* Set DP0 Training Pattern */ + tc_write(DP0_SRCCTRL, srcctrl); + + /* Enable DP0 to start Link Training */ + tc_write(DP0CTL, DP_EN); + + /* wait */ + timeout = 1000; + do { + tc_read(DP0_LTSTAT, &value); + udelay(1); + } while ((!(value & LT_LOOPDONE)) && (--timeout)); + if (timeout == 0) { + dev_err(tc->dev, "Link training timeout!\n"); + } else { + int pattern = (value >> 11) & 0x3; + int error = (value >> 8) & 0x7; + + dev_dbg(tc->dev, + "Link training phase %d done after %d uS: %s\n", + pattern, 1000 - timeout, errors[error]); + if (pattern == DP_TRAINING_PATTERN_1 && error == 0) + break; + if (pattern == DP_TRAINING_PATTERN_2) { + value &= LT_CHANNEL1_EQ_BITS | + LT_INTERLANE_ALIGN_DONE | + LT_CHANNEL0_EQ_BITS; + /* in case of two lanes */ + if ((tc->link.base.num_lanes == 2) && + (value == (LT_CHANNEL1_EQ_BITS | + LT_INTERLANE_ALIGN_DONE | + LT_CHANNEL0_EQ_BITS))) + break; + /* in case of one line */ + if ((tc->link.base.num_lanes == 1) && + (value == (LT_INTERLANE_ALIGN_DONE | + LT_CHANNEL0_EQ_BITS))) + break; + } + } + /* restart */ + tc_write(DP0CTL, 0); + usleep_range(10, 20); + } while (--retry); + if (retry == 0) { + dev_err(tc->dev, "Failed to finish training phase %d\n", + pattern); + } + + return 0; +err: + return ret; +} + +static int tc_main_link_setup(struct tc_data *tc) +{ + struct drm_dp_aux *aux = &tc->aux; + struct device *dev = tc->dev; + unsigned int rate; + u32 dp_phy_ctrl; + int timeout; + bool aligned; + bool ready; + u32 value; + int ret; + u8 tmp[8]; + + /* display mode should be set at this point */ + if (!tc->mode) + return -EINVAL; + + /* from excel file - DP0_SrcCtrl */ + tc_write(DP0_SRCCTRL, DP0_SRCCTRL_SCRMBLDIS | DP0_SRCCTRL_EN810B | + DP0_SRCCTRL_LANESKEW | DP0_SRCCTRL_LANES_2 | + DP0_SRCCTRL_BW27 | DP0_SRCCTRL_AUTOCORRECT); + /* from excel file - DP1_SrcCtrl */ + tc_write(0x07a0, 0x00003083); + + rate = clk_get_rate(tc->refclk); + switch (rate) { + case 38400000: + value = REF_FREQ_38M4; + break; + case 26000000: + value = REF_FREQ_26M; + break; + case 19200000: + value = REF_FREQ_19M2; + break; + case 13000000: + value = REF_FREQ_13M; + break; + default: + return -EINVAL; + } + value |= SYSCLK_SEL_LSCLK | LSCLK_DIV_2; + tc_write(SYS_PLLPARAM, value); + /* Setup Main Link */ + dp_phy_ctrl = BGREN | PWR_SW_EN | BIT(2) | PHY_A0_EN | PHY_M0_EN; + tc_write(DP_PHY_CTRL, dp_phy_ctrl); + msleep(100); + + /* PLL setup */ + tc_write(DP0_PLLCTRL, PLLUPDATE | PLLEN); + tc_wait_pll_lock(tc); + + tc_write(DP1_PLLCTRL, PLLUPDATE | PLLEN); + tc_wait_pll_lock(tc); + + /* PXL PLL setup */ + if (tc_test_pattern) { + ret = tc_pxl_pll_en(tc, clk_get_rate(tc->refclk), + 1000 * tc->mode->clock); + if (ret) + goto err; + } + + /* Reset/Enable Main Links */ + dp_phy_ctrl |= DP_PHY_RST | PHY_M1_RST | PHY_M0_RST; + tc_write(DP_PHY_CTRL, dp_phy_ctrl); + usleep_range(100, 200); + dp_phy_ctrl &= ~(DP_PHY_RST | PHY_M1_RST | PHY_M0_RST); + tc_write(DP_PHY_CTRL, dp_phy_ctrl); + + timeout = 1000; + do { + tc_read(DP_PHY_CTRL, &value); + udelay(1); + } while ((!(value & PHY_RDY)) && (--timeout)); + + if (timeout == 0) { + dev_err(dev, "timeout waiting for phy become ready"); + return -ETIMEDOUT; + } + + /* Set misc: 8 bits per color */ + ret = regmap_update_bits(tc->regmap, DP0_MISC, BPC_8, BPC_8); + if (ret) + goto err; + + /* + * ASSR mode + * on TC358767 side ASSR configured through strap pin + * seems there is no way to change this setting from SW + * + * check is tc configured for same mode + */ + if (tc->assr != tc->link.assr) { + dev_dbg(dev, "Trying to set display to ASSR: %d\n", + tc->assr); + /* try to set ASSR on display side */ + tmp[0] = tc->assr; + ret = drm_dp_dpcd_writeb(aux, DP_EDP_CONFIGURATION_SET, tmp[0]); + if (ret < 0) + goto err_dpcd_read; + /* read back */ + ret = drm_dp_dpcd_readb(aux, DP_EDP_CONFIGURATION_SET, tmp); + if (ret < 0) + goto err_dpcd_read; + + if (tmp[0] != tc->assr) { + dev_warn(dev, "Failed to switch display ASSR to %d, falling back to unscrambled mode\n", + tc->assr); + /* trying with disabled scrambler */ + tc->link.scrambler_dis = 1; + } + } + + /* Setup Link & DPRx Config for Training */ + ret = drm_dp_link_configure(aux, &tc->link.base); + if (ret < 0) + goto err_dpcd_write; + + /* DOWNSPREAD_CTRL */ + tmp[0] = tc->link.spread ? DP_SPREAD_AMP_0_5 : 0x00; + /* MAIN_LINK_CHANNEL_CODING_SET */ + tmp[1] = tc->link.coding8b10b ? DP_SET_ANSI_8B10B : 0x00; + ret = drm_dp_dpcd_write(aux, DP_DOWNSPREAD_CTRL, tmp, 2); + if (ret < 0) + goto err_dpcd_write; + + ret = tc_link_training(tc, DP_TRAINING_PATTERN_1); + if (ret) + goto err; + + ret = tc_link_training(tc, DP_TRAINING_PATTERN_2); + if (ret) + goto err; + + /* Clear DPCD 0x102 */ + /* Note: Can Not use DP0_SNKLTCTRL (0x06E4) short cut */ + tmp[0] = tc->link.scrambler_dis ? DP_LINK_SCRAMBLING_DISABLE : 0x00; + ret = drm_dp_dpcd_writeb(aux, DP_TRAINING_PATTERN_SET, tmp[0]); + if (ret < 0) + goto err_dpcd_write; + + /* Clear Training Pattern, set AutoCorrect Mode = 1 */ + tc_write(DP0_SRCCTRL, tc_srcctrl(tc) | DP0_SRCCTRL_AUTOCORRECT); + + /* Wait */ + timeout = 100; + do { + udelay(1); + /* Read DPCD 0x202-0x207 */ + ret = drm_dp_dpcd_read_link_status(aux, tmp + 2); + if (ret < 0) + goto err_dpcd_read; + ready = (tmp[2] == ((DP_CHANNEL_EQ_BITS << 4) | /* Lane1 */ + DP_CHANNEL_EQ_BITS)); /* Lane0 */ + aligned = tmp[4] & DP_INTERLANE_ALIGN_DONE; + } while ((--timeout) && !(ready && aligned)); + + if (timeout == 0) { + /* Read DPCD 0x200-0x201 */ + ret = drm_dp_dpcd_read(aux, DP_SINK_COUNT, tmp, 2); + if (ret < 0) + goto err_dpcd_read; + dev_info(dev, "0x0200 SINK_COUNT: 0x%02x\n", tmp[0]); + dev_info(dev, "0x0201 DEVICE_SERVICE_IRQ_VECTOR: 0x%02x\n", + tmp[1]); + dev_info(dev, "0x0202 LANE0_1_STATUS: 0x%02x\n", tmp[2]); + dev_info(dev, "0x0204 LANE_ALIGN_STATUS_UPDATED: 0x%02x\n", + tmp[4]); + dev_info(dev, "0x0205 SINK_STATUS: 0x%02x\n", tmp[5]); + dev_info(dev, "0x0206 ADJUST_REQUEST_LANE0_1: 0x%02x\n", + tmp[6]); + + if (!ready) + dev_err(dev, "Lane0/1 not ready\n"); + if (!aligned) + dev_err(dev, "Lane0/1 not aligned\n"); + return -EAGAIN; + } + + ret = tc_set_video_mode(tc, tc->mode); + if (ret) + goto err; + + /* Set M/N */ + ret = tc_stream_clock_calc(tc); + if (ret) + goto err; + + return 0; +err_dpcd_read: + dev_err(tc->dev, "Failed to read DPCD: %d\n", ret); + return ret; +err_dpcd_write: + dev_err(tc->dev, "Failed to write DPCD: %d\n", ret); +err: + return ret; +} + +static int tc_main_link_stream(struct tc_data *tc, int state) +{ + int ret; + u32 value; + + dev_dbg(tc->dev, "stream: %d\n", state); + + if (state) { + value = VID_MN_GEN | DP_EN; + if (tc->link.base.capabilities & DP_LINK_CAP_ENHANCED_FRAMING) + value |= EF_EN; + tc_write(DP0CTL, value); + /* + * VID_EN assertion should be delayed by at least N * LSCLK + * cycles from the time VID_MN_GEN is enabled in order to + * generate stable values for VID_M. LSCLK is 270 MHz or + * 162 MHz, VID_N is set to 32768 in tc_stream_clock_calc(), + * so a delay of at least 203 us should suffice. + */ + usleep_range(500, 1000); + value |= VID_EN; + tc_write(DP0CTL, value); + /* Set input interface */ + value = DP0_AUDSRC_NO_INPUT; + if (tc_test_pattern) + value |= DP0_VIDSRC_COLOR_BAR; + else + value |= DP0_VIDSRC_DPI_RX; + tc_write(SYSCTRL, value); + } else { + tc_write(DP0CTL, 0); + } + + return 0; +err: + return ret; +} + +static enum drm_connector_status +tc_connector_detect(struct drm_connector *connector, bool force) +{ + return connector_status_connected; +} + +static void tc_bridge_pre_enable(struct drm_bridge *bridge) +{ + struct tc_data *tc = bridge_to_tc(bridge); + + drm_panel_prepare(tc->panel); +} + +static void tc_bridge_enable(struct drm_bridge *bridge) +{ + struct tc_data *tc = bridge_to_tc(bridge); + int ret; + + ret = tc_main_link_setup(tc); + if (ret < 0) { + dev_err(tc->dev, "main link setup error: %d\n", ret); + return; + } + + ret = tc_main_link_stream(tc, 1); + if (ret < 0) { + dev_err(tc->dev, "main link stream start error: %d\n", ret); + return; + } + + drm_panel_enable(tc->panel); +} + +static void tc_bridge_disable(struct drm_bridge *bridge) +{ + struct tc_data *tc = bridge_to_tc(bridge); + int ret; + + drm_panel_disable(tc->panel); + + ret = tc_main_link_stream(tc, 0); + if (ret < 0) + dev_err(tc->dev, "main link stream stop error: %d\n", ret); +} + +static void tc_bridge_post_disable(struct drm_bridge *bridge) +{ + struct tc_data *tc = bridge_to_tc(bridge); + + drm_panel_unprepare(tc->panel); +} + +static bool tc_bridge_mode_fixup(struct drm_bridge *bridge, + const struct drm_display_mode *mode, + struct drm_display_mode *adj) +{ + /* Fixup sync polarities, both hsync and vsync are active low */ + adj->flags = mode->flags; + adj->flags |= (DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC); + adj->flags &= ~(DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC); + + return true; +} + +static int tc_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) +{ + /* Accept any mode */ + return MODE_OK; +} + +static void tc_bridge_mode_set(struct drm_bridge *bridge, + struct drm_display_mode *mode, + struct drm_display_mode *adj) +{ + struct tc_data *tc = bridge_to_tc(bridge); + + tc->mode = mode; +} + +static int tc_connector_get_modes(struct drm_connector *connector) +{ + struct tc_data *tc = connector_to_tc(connector); + struct edid *edid; + unsigned int count; + + if (tc->panel && tc->panel->funcs && tc->panel->funcs->get_modes) { + count = tc->panel->funcs->get_modes(tc->panel); + if (count > 0) + return count; + } + + edid = drm_get_edid(connector, &tc->aux.ddc); + + kfree(tc->edid); + tc->edid = edid; + if (!edid) + return 0; + + drm_mode_connector_update_edid_property(connector, edid); + count = drm_add_edid_modes(connector, edid); + + return count; +} + +static void tc_connector_set_polling(struct tc_data *tc, + struct drm_connector *connector) +{ + /* TODO: add support for HPD */ + connector->polled = DRM_CONNECTOR_POLL_CONNECT | + DRM_CONNECTOR_POLL_DISCONNECT; +} + +static struct drm_encoder * +tc_connector_best_encoder(struct drm_connector *connector) +{ + struct tc_data *tc = connector_to_tc(connector); + + return tc->bridge.encoder; +} + +static const struct drm_connector_helper_funcs tc_connector_helper_funcs = { + .get_modes = tc_connector_get_modes, + .mode_valid = tc_connector_mode_valid, + .best_encoder = tc_connector_best_encoder, +}; + +static void tc_connector_destroy(struct drm_connector *connector) +{ + drm_connector_unregister(connector); + drm_connector_cleanup(connector); +} + +static const struct drm_connector_funcs tc_connector_funcs = { + .dpms = drm_atomic_helper_connector_dpms, + .fill_modes = drm_helper_probe_single_connector_modes, + .detect = tc_connector_detect, + .destroy = tc_connector_destroy, + .reset = drm_atomic_helper_connector_reset, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, +}; + +static int tc_bridge_attach(struct drm_bridge *bridge) +{ + u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24; + struct tc_data *tc = bridge_to_tc(bridge); + struct drm_device *drm = bridge->dev; + int ret; + + /* Create eDP connector */ + drm_connector_helper_add(&tc->connector, &tc_connector_helper_funcs); + ret = drm_connector_init(drm, &tc->connector, &tc_connector_funcs, + DRM_MODE_CONNECTOR_eDP); + if (ret) + return ret; + + if (tc->panel) + drm_panel_attach(tc->panel, &tc->connector); + + drm_display_info_set_bus_formats(&tc->connector.display_info, + &bus_format, 1); + drm_mode_connector_attach_encoder(&tc->connector, tc->bridge.encoder); + + return 0; +} + +static const struct drm_bridge_funcs tc_bridge_funcs = { + .attach = tc_bridge_attach, + .mode_set = tc_bridge_mode_set, + .pre_enable = tc_bridge_pre_enable, + .enable = tc_bridge_enable, + .disable = tc_bridge_disable, + .post_disable = tc_bridge_post_disable, + .mode_fixup = tc_bridge_mode_fixup, +}; + +static bool tc_readable_reg(struct device *dev, unsigned int reg) +{ + return reg != SYSCTRL; +} + +static const struct regmap_range tc_volatile_ranges[] = { + regmap_reg_range(DP0_AUXWDATA(0), DP0_AUXSTATUS), + regmap_reg_range(DP0_LTSTAT, DP0_SNKLTCHGREQ), + regmap_reg_range(DP_PHY_CTRL, DP_PHY_CTRL), + regmap_reg_range(DP0_PLLCTRL, PXL_PLLCTRL), + regmap_reg_range(VFUEN0, VFUEN0), +}; + +static const struct regmap_access_table tc_volatile_table = { + .yes_ranges = tc_volatile_ranges, + .n_yes_ranges = ARRAY_SIZE(tc_volatile_ranges), +}; + +static bool tc_writeable_reg(struct device *dev, unsigned int reg) +{ + return (reg != TC_IDREG) && + (reg != DP0_LTSTAT) && + (reg != DP0_SNKLTCHGREQ); +} + +static const struct regmap_config tc_regmap_config = { + .name = "tc358767", + .reg_bits = 16, + .val_bits = 32, + .reg_stride = 4, + .max_register = PLL_DBG, + .cache_type = REGCACHE_RBTREE, + .readable_reg = tc_readable_reg, + .volatile_table = &tc_volatile_table, + .writeable_reg = tc_writeable_reg, + .reg_format_endian = REGMAP_ENDIAN_BIG, + .val_format_endian = REGMAP_ENDIAN_LITTLE, +}; + +static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id) +{ + struct device *dev = &client->dev; + struct device_node *ep; + struct tc_data *tc; + int ret; + + tc = devm_kzalloc(dev, sizeof(*tc), GFP_KERNEL); + if (!tc) + return -ENOMEM; + + tc->dev = dev; + + /* port@2 is the output port */ + ep = of_graph_get_endpoint_by_regs(dev->of_node, 2, -1); + if (ep) { + struct device_node *remote; + + remote = of_graph_get_remote_port_parent(ep); + if (!remote) { + dev_warn(dev, "endpoint %s not connected\n", + ep->full_name); + of_node_put(ep); + return -ENODEV; + } + of_node_put(ep); + tc->panel = of_drm_find_panel(remote); + if (tc->panel) { + dev_dbg(dev, "found panel %s\n", remote->full_name); + } else { + dev_dbg(dev, "waiting for panel %s\n", + remote->full_name); + of_node_put(remote); + return -EPROBE_DEFER; + } + of_node_put(remote); + } + + /* Shut down GPIO is optional */ + tc->sd_gpio = devm_gpiod_get_optional(dev, "shutdown", GPIOD_OUT_HIGH); + if (IS_ERR(tc->sd_gpio)) + return PTR_ERR(tc->sd_gpio); + + if (tc->sd_gpio) { + gpiod_set_value_cansleep(tc->sd_gpio, 0); + usleep_range(5000, 10000); + } + + /* Reset GPIO is optional */ + tc->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(tc->reset_gpio)) + return PTR_ERR(tc->reset_gpio); + + if (tc->reset_gpio) { + gpiod_set_value_cansleep(tc->reset_gpio, 1); + usleep_range(5000, 10000); + } + + tc->refclk = devm_clk_get(dev, "ref"); + if (IS_ERR(tc->refclk)) { + ret = PTR_ERR(tc->refclk); + dev_err(dev, "Failed to get refclk: %d\n", ret); + return ret; + } + + tc->regmap = devm_regmap_init_i2c(client, &tc_regmap_config); + if (IS_ERR(tc->regmap)) { + ret = PTR_ERR(tc->regmap); + dev_err(dev, "Failed to initialize regmap: %d\n", ret); + return ret; + } + + ret = regmap_read(tc->regmap, TC_IDREG, &tc->rev); + if (ret) { + dev_err(tc->dev, "can not read device ID: %d\n", ret); + return ret; + } + + if ((tc->rev != 0x6601) && (tc->rev != 0x6603)) { + dev_err(tc->dev, "invalid device ID: 0x%08x\n", tc->rev); + return -EINVAL; + } + + tc->assr = (tc->rev == 0x6601); /* Enable ASSR for eDP panels */ + + ret = tc_aux_link_setup(tc); + if (ret) + return ret; + + /* Register DP AUX channel */ + tc->aux.name = "TC358767 AUX i2c adapter"; + tc->aux.dev = tc->dev; + tc->aux.transfer = tc_aux_transfer; + ret = drm_dp_aux_register(&tc->aux); + if (ret) + return ret; + + ret = tc_get_display_props(tc); + if (ret) + goto err_unregister_aux; + + tc_connector_set_polling(tc, &tc->connector); + + tc->bridge.funcs = &tc_bridge_funcs; + tc->bridge.of_node = dev->of_node; + ret = drm_bridge_add(&tc->bridge); + if (ret) { + dev_err(dev, "Failed to add drm_bridge: %d\n", ret); + goto err_unregister_aux; + } + + i2c_set_clientdata(client, tc); + + return 0; +err_unregister_aux: + drm_dp_aux_unregister(&tc->aux); + return ret; +} + +static int tc_remove(struct i2c_client *client) +{ + struct tc_data *tc = i2c_get_clientdata(client); + + drm_bridge_remove(&tc->bridge); + drm_dp_aux_unregister(&tc->aux); + + tc_pxl_pll_dis(tc); + + return 0; +} + +static const struct i2c_device_id tc358767_i2c_ids[] = { + { "tc358767", 0 }, + { } +}; +MODULE_DEVICE_TABLE(i2c, tc358767_i2c_ids); + +static const struct of_device_id tc358767_of_ids[] = { + { .compatible = "toshiba,tc358767", }, + { } +}; +MODULE_DEVICE_TABLE(of, tc358767_of_ids); + +static struct i2c_driver tc358767_driver = { + .driver = { + .name = "tc358767", + .of_match_table = tc358767_of_ids, + }, + .id_table = tc358767_i2c_ids, + .probe = tc_probe, + .remove = tc_remove, +}; +module_i2c_driver(tc358767_driver); + +MODULE_AUTHOR("Andrey Gusakov "); +MODULE_DESCRIPTION("tc358767 eDP encoder driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/cirrus/Kconfig b/drivers/gpu/drm/cirrus/Kconfig index 9864559e5fb9..04b3c161dfae 100644 --- a/drivers/gpu/drm/cirrus/Kconfig +++ b/drivers/gpu/drm/cirrus/Kconfig @@ -1,11 +1,7 @@ config DRM_CIRRUS_QEMU tristate "Cirrus driver for QEMU emulated device" depends on DRM && PCI - select FB_SYS_FILLRECT - select FB_SYS_COPYAREA - select FB_SYS_IMAGEBLIT select DRM_KMS_HELPER - select DRM_KMS_FB_HELPER select DRM_TTM help This is a KMS driver for emulated cirrus device in qemu. diff --git a/drivers/gpu/drm/cirrus/cirrus_main.c b/drivers/gpu/drm/cirrus/cirrus_main.c index 32d32c5b7b17..80446e2d3ab6 100644 --- a/drivers/gpu/drm/cirrus/cirrus_main.c +++ b/drivers/gpu/drm/cirrus/cirrus_main.c @@ -17,8 +17,8 @@ static void cirrus_user_framebuffer_destroy(struct drm_framebuffer *fb) { struct cirrus_framebuffer *cirrus_fb = to_cirrus_framebuffer(fb); - if (cirrus_fb->obj) - drm_gem_object_unreference_unlocked(cirrus_fb->obj); + + drm_gem_object_unreference_unlocked(cirrus_fb->obj); drm_framebuffer_cleanup(fb); kfree(fb); } diff --git a/drivers/gpu/drm/cirrus/cirrus_ttm.c b/drivers/gpu/drm/cirrus/cirrus_ttm.c index 6768b7b1af32..1cc9ee607128 100644 --- a/drivers/gpu/drm/cirrus/cirrus_ttm.c +++ b/drivers/gpu/drm/cirrus/cirrus_ttm.c @@ -186,17 +186,6 @@ static void cirrus_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_re { } -static int cirrus_bo_move(struct ttm_buffer_object *bo, - bool evict, bool interruptible, - bool no_wait_gpu, - struct ttm_mem_reg *new_mem) -{ - int r; - r = ttm_bo_move_memcpy(bo, evict, no_wait_gpu, new_mem); - return r; -} - - static void cirrus_ttm_backend_destroy(struct ttm_tt *tt) { ttm_tt_fini(tt); @@ -241,7 +230,7 @@ struct ttm_bo_driver cirrus_bo_driver = { .ttm_tt_unpopulate = cirrus_ttm_tt_unpopulate, .init_mem_type = cirrus_bo_init_mem_type, .evict_flags = cirrus_bo_evict_flags, - .move = cirrus_bo_move, + .move = NULL, .verify_access = cirrus_bo_verify_access, .io_mem_reserve = &cirrus_ttm_io_mem_reserve, .io_mem_free = &cirrus_ttm_io_mem_free, diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index d99ab2f6663f..8d2f111fa113 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -404,8 +404,7 @@ drm_atomic_replace_property_blob(struct drm_property_blob **blob, if (old_blob == new_blob) return; - if (old_blob) - drm_property_unreference_blob(old_blob); + drm_property_unreference_blob(old_blob); if (new_blob) drm_property_reference_blob(new_blob); *blob = new_blob; @@ -1299,14 +1298,39 @@ EXPORT_SYMBOL(drm_atomic_add_affected_planes); */ void drm_atomic_legacy_backoff(struct drm_atomic_state *state) { + struct drm_device *dev = state->dev; + unsigned crtc_mask = 0; + struct drm_crtc *crtc; int ret; + bool global = false; + + drm_for_each_crtc(crtc, dev) { + if (crtc->acquire_ctx != state->acquire_ctx) + continue; + + crtc_mask |= drm_crtc_mask(crtc); + crtc->acquire_ctx = NULL; + } + + if (WARN_ON(dev->mode_config.acquire_ctx == state->acquire_ctx)) { + global = true; + + dev->mode_config.acquire_ctx = NULL; + } retry: drm_modeset_backoff(state->acquire_ctx); - ret = drm_modeset_lock_all_ctx(state->dev, state->acquire_ctx); + ret = drm_modeset_lock_all_ctx(dev, state->acquire_ctx); if (ret) goto retry; + + drm_for_each_crtc(crtc, dev) + if (drm_crtc_mask(crtc) & crtc_mask) + crtc->acquire_ctx = state->acquire_ctx; + + if (global) + dev->mode_config.acquire_ctx = state->acquire_ctx; } EXPORT_SYMBOL(drm_atomic_legacy_backoff); diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c index 059f7c39c582..a7916e5f8864 100644 --- a/drivers/gpu/drm/drm_cache.c +++ b/drivers/gpu/drm/drm_cache.c @@ -136,6 +136,7 @@ drm_clflush_virt_range(void *addr, unsigned long length) mb(); for (; addr < end; addr += size) clflushopt(addr); + clflushopt(end - 1); /* force serialisation */ mb(); return; } diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index fd93e9c79d28..f1d9f0569d7f 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -396,6 +396,51 @@ void drm_mode_object_reference(struct drm_mode_object *obj) } EXPORT_SYMBOL(drm_mode_object_reference); +/** + * drm_crtc_force_disable - Forcibly turn off a CRTC + * @crtc: CRTC to turn off + * + * Returns: + * Zero on success, error code on failure. + */ +int drm_crtc_force_disable(struct drm_crtc *crtc) +{ + struct drm_mode_set set = { + .crtc = crtc, + }; + + return drm_mode_set_config_internal(&set); +} +EXPORT_SYMBOL(drm_crtc_force_disable); + +/** + * drm_crtc_force_disable_all - Forcibly turn off all enabled CRTCs + * @dev: DRM device whose CRTCs to turn off + * + * Drivers may want to call this on unload to ensure that all displays are + * unlit and the GPU is in a consistent, low power state. Takes modeset locks. + * + * Returns: + * Zero on success, error code on failure. + */ +int drm_crtc_force_disable_all(struct drm_device *dev) +{ + struct drm_crtc *crtc; + int ret = 0; + + drm_modeset_lock_all(dev); + drm_for_each_crtc(crtc, dev) + if (crtc->enabled) { + ret = drm_crtc_force_disable(crtc); + if (ret) + goto out; + } +out: + drm_modeset_unlock_all(dev); + return ret; +} +EXPORT_SYMBOL(drm_crtc_force_disable_all); + static void drm_framebuffer_free(struct kref *kref) { struct drm_framebuffer *fb = @@ -544,8 +589,6 @@ void drm_framebuffer_remove(struct drm_framebuffer *fb) struct drm_device *dev; struct drm_crtc *crtc; struct drm_plane *plane; - struct drm_mode_set set; - int ret; if (!fb) return; @@ -575,11 +618,7 @@ void drm_framebuffer_remove(struct drm_framebuffer *fb) drm_for_each_crtc(crtc, dev) { if (crtc->primary->fb == fb) { /* should turn off the crtc */ - memset(&set, 0, sizeof(struct drm_mode_set)); - set.crtc = crtc; - set.fb = NULL; - ret = drm_mode_set_config_internal(&set); - if (ret) + if (drm_crtc_force_disable(crtc)) DRM_ERROR("failed to reset crtc %p when fb was deleted\n", crtc); } } @@ -889,11 +928,11 @@ int drm_connector_init(struct drm_device *dev, connector->dev = dev; connector->funcs = funcs; - connector->connector_id = ida_simple_get(&config->connector_ida, 0, 0, GFP_KERNEL); - if (connector->connector_id < 0) { - ret = connector->connector_id; + ret = ida_simple_get(&config->connector_ida, 0, 0, GFP_KERNEL); + if (ret < 0) goto out_put; - } + connector->index = ret; + ret = 0; connector->connector_type = connector_type; connector->connector_type_id = @@ -941,7 +980,7 @@ int drm_connector_init(struct drm_device *dev, ida_remove(connector_ida, connector->connector_type_id); out_put_id: if (ret) - ida_remove(&config->connector_ida, connector->connector_id); + ida_remove(&config->connector_ida, connector->index); out_put: if (ret) drm_mode_object_unregister(dev, &connector->base); @@ -985,7 +1024,7 @@ void drm_connector_cleanup(struct drm_connector *connector) connector->connector_type_id); ida_remove(&dev->mode_config.connector_ida, - connector->connector_id); + connector->index); kfree(connector->display_info.bus_formats); drm_mode_object_unregister(dev, &connector->base); @@ -1068,23 +1107,16 @@ void drm_connector_unregister(struct drm_connector *connector) } EXPORT_SYMBOL(drm_connector_unregister); -/** - * drm_connector_register_all - register all connectors - * @dev: drm device - * - * This function registers all connectors in sysfs and other places so that - * userspace can start to access them. drm_connector_register_all() is called - * automatically from drm_dev_register() to complete the device registration, - * if they don't call drm_connector_register() on each connector individually. - * - * When a device is unplugged and should be removed from userspace access, - * call drm_connector_unregister_all(), which is the inverse of this - * function. - * - * Returns: - * Zero on success, error code on failure. - */ -int drm_connector_register_all(struct drm_device *dev) +static void drm_connector_unregister_all(struct drm_device *dev) +{ + struct drm_connector *connector; + + /* FIXME: taking the mode config mutex ends up in a clash with sysfs */ + list_for_each_entry(connector, &dev->mode_config.connector_list, head) + drm_connector_unregister(connector); +} + +static int drm_connector_register_all(struct drm_device *dev) { struct drm_connector *connector; int ret; @@ -1106,27 +1138,6 @@ int drm_connector_register_all(struct drm_device *dev) drm_connector_unregister_all(dev); return ret; } -EXPORT_SYMBOL(drm_connector_register_all); - -/** - * drm_connector_unregister_all - unregister connector userspace interfaces - * @dev: drm device - * - * This functions unregisters all connectors from sysfs and other places so - * that userspace can no longer access them. Drivers should call this as the - * first step tearing down the device instace, or when the underlying - * physical device disappeared (e.g. USB unplug), right before calling - * drm_dev_unregister(). - */ -void drm_connector_unregister_all(struct drm_device *dev) -{ - struct drm_connector *connector; - - /* FIXME: taking the mode config mutex ends up in a clash with sysfs */ - list_for_each_entry(connector, &dev->mode_config.connector_list, head) - drm_connector_unregister(connector); -} -EXPORT_SYMBOL(drm_connector_unregister_all); static int drm_encoder_register_all(struct drm_device *dev) { diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c index d61591274ff6..604d3ef72ffa 100644 --- a/drivers/gpu/drm/drm_crtc_helper.c +++ b/drivers/gpu/drm/drm_crtc_helper.c @@ -531,11 +531,11 @@ drm_crtc_helper_disable(struct drm_crtc *crtc) int drm_crtc_helper_set_config(struct drm_mode_set *set) { struct drm_device *dev; - struct drm_crtc *new_crtc; - struct drm_encoder *save_encoders, *new_encoder, *encoder; + struct drm_crtc **save_encoder_crtcs, *new_crtc; + struct drm_encoder **save_connector_encoders, *new_encoder, *encoder; bool mode_changed = false; /* if true do a full mode set */ bool fb_changed = false; /* if true and !mode_changed just do a flip */ - struct drm_connector *save_connectors, *connector; + struct drm_connector *connector; int count = 0, ro, fail = 0; const struct drm_crtc_helper_funcs *crtc_funcs; struct drm_mode_set save_set; @@ -577,15 +577,15 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) * Allocate space for the backup of all (non-pointer) encoder and * connector data. */ - save_encoders = kzalloc(dev->mode_config.num_encoder * - sizeof(struct drm_encoder), GFP_KERNEL); - if (!save_encoders) + save_encoder_crtcs = kzalloc(dev->mode_config.num_encoder * + sizeof(struct drm_crtc *), GFP_KERNEL); + if (!save_encoder_crtcs) return -ENOMEM; - save_connectors = kzalloc(dev->mode_config.num_connector * - sizeof(struct drm_connector), GFP_KERNEL); - if (!save_connectors) { - kfree(save_encoders); + save_connector_encoders = kzalloc(dev->mode_config.num_connector * + sizeof(struct drm_encoder *), GFP_KERNEL); + if (!save_connector_encoders) { + kfree(save_encoder_crtcs); return -ENOMEM; } @@ -596,12 +596,12 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) */ count = 0; drm_for_each_encoder(encoder, dev) { - save_encoders[count++] = *encoder; + save_encoder_crtcs[count++] = encoder->crtc; } count = 0; drm_for_each_connector(connector, dev) { - save_connectors[count++] = *connector; + save_connector_encoders[count++] = connector->encoder; } save_set.crtc = set->crtc; @@ -634,8 +634,12 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) mode_changed = true; } - /* take a reference on all connectors in set */ + /* take a reference on all unbound connectors in set, reuse the + * already taken reference for bound connectors + */ for (ro = 0; ro < set->num_connectors; ro++) { + if (set->connectors[ro]->encoder) + continue; drm_connector_reference(set->connectors[ro]); } @@ -757,30 +761,28 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) } } - /* after fail drop reference on all connectors in save set */ - count = 0; - drm_for_each_connector(connector, dev) { - drm_connector_unreference(&save_connectors[count++]); - } - - kfree(save_connectors); - kfree(save_encoders); + kfree(save_connector_encoders); + kfree(save_encoder_crtcs); return 0; fail: /* Restore all previous data. */ count = 0; drm_for_each_encoder(encoder, dev) { - *encoder = save_encoders[count++]; + encoder->crtc = save_encoder_crtcs[count++]; } count = 0; drm_for_each_connector(connector, dev) { - *connector = save_connectors[count++]; + connector->encoder = save_connector_encoders[count++]; } - /* after fail drop reference on all connectors in set */ + /* after fail drop reference on all unbound connectors in set, let + * bound connectors keep their reference + */ for (ro = 0; ro < set->num_connectors; ro++) { + if (set->connectors[ro]->encoder) + continue; drm_connector_unreference(set->connectors[ro]); } @@ -790,8 +792,8 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set) save_set.y, save_set.fb)) DRM_ERROR("failed to restore config after modeset failure\n"); - kfree(save_connectors); - kfree(save_encoders); + kfree(save_connector_encoders); + kfree(save_encoder_crtcs); return ret; } EXPORT_SYMBOL(drm_crtc_helper_set_config); diff --git a/drivers/gpu/drm/drm_dp_aux_dev.c b/drivers/gpu/drm/drm_dp_aux_dev.c index 3334baacf43d..734f86a345f6 100644 --- a/drivers/gpu/drm/drm_dp_aux_dev.c +++ b/drivers/gpu/drm/drm_dp_aux_dev.c @@ -355,8 +355,7 @@ int drm_dp_aux_dev_init(void) drm_dp_aux_dev_class = class_create(THIS_MODULE, "drm_dp_aux_dev"); if (IS_ERR(drm_dp_aux_dev_class)) { - res = PTR_ERR(drm_dp_aux_dev_class); - goto out; + return PTR_ERR(drm_dp_aux_dev_class); } drm_dp_aux_dev_class->dev_groups = drm_dp_aux_groups; diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 091053e995e5..8f11b8741e42 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -203,7 +203,7 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, ret = aux->transfer(aux, &msg); - if (ret > 0) { + if (ret >= 0) { native_reply = msg.reply & DP_AUX_NATIVE_REPLY_MASK; if (native_reply == DP_AUX_NATIVE_REPLY_ACK) { if (ret == size) diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index a13edf5de2d6..04e457117980 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1493,11 +1493,8 @@ static void process_single_down_tx_qlock(struct drm_dp_mst_topology_mgr *mgr) WARN_ON(!mutex_is_locked(&mgr->qlock)); /* construct a chunk from the first msg in the tx_msg queue */ - if (list_empty(&mgr->tx_msg_downq)) { - mgr->tx_down_in_progress = false; + if (list_empty(&mgr->tx_msg_downq)) return; - } - mgr->tx_down_in_progress = true; txmsg = list_first_entry(&mgr->tx_msg_downq, struct drm_dp_sideband_msg_tx, next); ret = process_single_tx_qlock(mgr, txmsg, false); @@ -1512,10 +1509,6 @@ static void process_single_down_tx_qlock(struct drm_dp_mst_topology_mgr *mgr) txmsg->state = DRM_DP_SIDEBAND_TX_TIMEOUT; wake_up(&mgr->tx_waitq); } - if (list_empty(&mgr->tx_msg_downq)) { - mgr->tx_down_in_progress = false; - return; - } } /* called holding qlock */ @@ -1538,7 +1531,7 @@ static void drm_dp_queue_down_tx(struct drm_dp_mst_topology_mgr *mgr, { mutex_lock(&mgr->qlock); list_add_tail(&txmsg->next, &mgr->tx_msg_downq); - if (!mgr->tx_down_in_progress) + if (list_is_singular(&mgr->tx_msg_downq)) process_single_down_tx_qlock(mgr); mutex_unlock(&mgr->qlock); } @@ -2372,6 +2365,7 @@ EXPORT_SYMBOL(drm_dp_mst_hpd_irq); /** * drm_dp_mst_detect_port() - get connection status for an MST port + * @connector: DRM connector for this port * @mgr: manager for this port * @port: unverified pointer to a port * @@ -2887,7 +2881,7 @@ static void drm_dp_tx_work(struct work_struct *work) struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, tx_work); mutex_lock(&mgr->qlock); - if (mgr->tx_down_in_progress) + if (!list_empty(&mgr->tx_msg_downq)) process_single_down_tx_qlock(mgr); mutex_unlock(&mgr->qlock); } @@ -2927,11 +2921,9 @@ static void drm_dp_destroy_connector_work(struct work_struct *work) drm_dp_port_teardown_pdt(port, port->pdt); if (!port->input && port->vcpi.vcpi > 0) { - if (mgr->mst_state) { - drm_dp_mst_reset_vcpi_slots(mgr, port); - drm_dp_update_payload_part1(mgr); - drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi); - } + drm_dp_mst_reset_vcpi_slots(mgr, port); + drm_dp_update_payload_part1(mgr); + drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi); } kref_put(&port->kref, drm_dp_free_mst_port); diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index aead9ffcbe29..be27ed36f56e 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -362,9 +362,7 @@ EXPORT_SYMBOL(drm_put_dev); void drm_unplug_dev(struct drm_device *dev) { /* for a USB device */ - drm_minor_unregister(dev, DRM_MINOR_LEGACY); - drm_minor_unregister(dev, DRM_MINOR_RENDER); - drm_minor_unregister(dev, DRM_MINOR_CONTROL); + drm_dev_unregister(dev); mutex_lock(&drm_global_mutex); diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c index c0b0c718994a..1fd6eac1400c 100644 --- a/drivers/gpu/drm/drm_fb_cma_helper.c +++ b/drivers/gpu/drm/drm_fb_cma_helper.c @@ -596,3 +596,18 @@ void drm_fbdev_cma_hotplug_event(struct drm_fbdev_cma *fbdev_cma) drm_fb_helper_hotplug_event(&fbdev_cma->fb_helper); } EXPORT_SYMBOL_GPL(drm_fbdev_cma_hotplug_event); + +/** + * drm_fbdev_cma_set_suspend - wrapper around drm_fb_helper_set_suspend + * @fbdev_cma: The drm_fbdev_cma struct, may be NULL + * @state: desired state, zero to resume, non-zero to suspend + * + * Calls drm_fb_helper_set_suspend, which is a wrapper around + * fb_set_suspend implemented by fbdev core. + */ +void drm_fbdev_cma_set_suspend(struct drm_fbdev_cma *fbdev_cma, int state) +{ + if (fbdev_cma) + drm_fb_helper_set_suspend(&fbdev_cma->fb_helper, state); +} +EXPORT_SYMBOL(drm_fbdev_cma_set_suspend); diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index 1f84ff5f1bf8..33af4a5ddca1 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -648,7 +648,7 @@ long drm_ioctl(struct file *filp, int retcode = -EINVAL; char stack_kdata[128]; char *kdata = NULL; - unsigned int usize, asize, drv_size; + unsigned int in_size, out_size, drv_size, ksize; bool is_driver_ioctl; dev = file_priv->minor->dev; @@ -671,9 +671,12 @@ long drm_ioctl(struct file *filp, } drv_size = _IOC_SIZE(ioctl->cmd); - usize = _IOC_SIZE(cmd); - asize = max(usize, drv_size); - cmd = ioctl->cmd; + out_size = in_size = _IOC_SIZE(cmd); + if ((cmd & ioctl->cmd & IOC_IN) == 0) + in_size = 0; + if ((cmd & ioctl->cmd & IOC_OUT) == 0) + out_size = 0; + ksize = max(max(in_size, out_size), drv_size); DRM_DEBUG("pid=%d, dev=0x%lx, auth=%d, %s\n", task_pid_nr(current), @@ -693,30 +696,24 @@ long drm_ioctl(struct file *filp, if (unlikely(retcode)) goto err_i1; - if (cmd & (IOC_IN | IOC_OUT)) { - if (asize <= sizeof(stack_kdata)) { - kdata = stack_kdata; - } else { - kdata = kmalloc(asize, GFP_KERNEL); - if (!kdata) { - retcode = -ENOMEM; - goto err_i1; - } - } - if (asize > usize) - memset(kdata + usize, 0, asize - usize); - } - - if (cmd & IOC_IN) { - if (copy_from_user(kdata, (void __user *)arg, - usize) != 0) { - retcode = -EFAULT; + if (ksize <= sizeof(stack_kdata)) { + kdata = stack_kdata; + } else { + kdata = kmalloc(ksize, GFP_KERNEL); + if (!kdata) { + retcode = -ENOMEM; goto err_i1; } - } else if (cmd & IOC_OUT) { - memset(kdata, 0, usize); } + if (copy_from_user(kdata, (void __user *)arg, in_size) != 0) { + retcode = -EFAULT; + goto err_i1; + } + + if (ksize > in_size) + memset(kdata + in_size, 0, ksize - in_size); + /* Enforce sane locking for kms driver ioctls. Core ioctls are * too messy still. */ if ((drm_core_check_feature(dev, DRIVER_MODESET) && is_driver_ioctl) || @@ -728,11 +725,8 @@ long drm_ioctl(struct file *filp, mutex_unlock(&drm_global_mutex); } - if (cmd & IOC_OUT) { - if (copy_to_user((void __user *)arg, kdata, - usize) != 0) - retcode = -EFAULT; - } + if (copy_to_user((void __user *)arg, kdata, out_size) != 0) + retcode = -EFAULT; err_i1: if (!ioctl) @@ -759,7 +753,7 @@ EXPORT_SYMBOL(drm_ioctl); * shouldn't be used by any drivers. * * Returns: - * True if the @nr corresponds to a DRM core ioctl numer, false otherwise. + * True if the @nr corresponds to a DRM core ioctl number, false otherwise. */ bool drm_ioctl_flags(unsigned int nr, unsigned int *flags) { diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 8ca3d2bf2bda..77f357b2c386 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -532,7 +532,7 @@ int drm_irq_uninstall(struct drm_device *dev) /* * Wake up any waiters so they don't hang. This is just to paper over - * isssues for UMS drivers which aren't in full control of their + * issues for UMS drivers which aren't in full control of their * vblank/irq handling. KMS drivers must ensure that vblanks are all * disabled when uninstalling the irq handler. */ @@ -594,7 +594,7 @@ int drm_control(struct drm_device *dev, void *data, return 0; if (drm_core_check_feature(dev, DRIVER_MODESET)) return 0; - /* UMS was only ever support on pci devices. */ + /* UMS was only ever supported on pci devices. */ if (WARN_ON(!dev->pdev)) return -EINVAL; @@ -945,8 +945,8 @@ EXPORT_SYMBOL(drm_crtc_vblank_count); * * This is the legacy version of drm_crtc_vblank_count_and_time(). */ -u32 drm_vblank_count_and_time(struct drm_device *dev, unsigned int pipe, - struct timeval *vblanktime) +static u32 drm_vblank_count_and_time(struct drm_device *dev, unsigned int pipe, + struct timeval *vblanktime) { struct drm_vblank_crtc *vblank = &dev->vblank[pipe]; u32 vblank_count; @@ -963,7 +963,6 @@ u32 drm_vblank_count_and_time(struct drm_device *dev, unsigned int pipe, return vblank_count; } -EXPORT_SYMBOL(drm_vblank_count_and_time); /** * drm_crtc_vblank_count_and_time - retrieve "cooked" vblank counter value @@ -975,8 +974,6 @@ EXPORT_SYMBOL(drm_vblank_count_and_time); * vblank events since the system was booted, including lost events due to * modesetting activity. Returns corresponding system timestamp of the time * of the vblank interval that corresponds to the current vblank counter value. - * - * This is the native KMS version of drm_vblank_count_and_time(). */ u32 drm_crtc_vblank_count_and_time(struct drm_crtc *crtc, struct timeval *vblanktime) @@ -1588,12 +1585,6 @@ static int drm_queue_vblank_event(struct drm_device *dev, unsigned int pipe, seq = drm_vblank_count_and_time(dev, pipe, &now); - if ((vblwait->request.type & _DRM_VBLANK_NEXTONMISS) && - (seq - vblwait->request.sequence) <= (1 << 23)) { - vblwait->request.sequence = seq + 1; - vblwait->reply.sequence = vblwait->request.sequence; - } - DRM_DEBUG("event on vblank count %d, current %d, crtc %u\n", vblwait->request.sequence, seq, pipe); @@ -1690,6 +1681,11 @@ int drm_wait_vblank(struct drm_device *dev, void *data, goto done; } + if ((flags & _DRM_VBLANK_NEXTONMISS) && + (seq - vblwait->request.sequence) <= (1 << 23)) { + vblwait->request.sequence = seq + 1; + } + if (flags & _DRM_VBLANK_EVENT) { /* must hold on to the vblank ref until the event fires * drm_vblank_put will be called asynchronously @@ -1697,14 +1693,8 @@ int drm_wait_vblank(struct drm_device *dev, void *data, return drm_queue_vblank_event(dev, pipe, vblwait, file_priv); } - if ((flags & _DRM_VBLANK_NEXTONMISS) && - (seq - vblwait->request.sequence) <= (1<<23)) { - vblwait->request.sequence = seq + 1; - } - DRM_DEBUG("waiting on vblank count %d, crtc %u\n", vblwait->request.sequence, pipe); - vblank->last_wait = vblwait->request.sequence; DRM_WAIT_ON(ret, vblank->queue, 3 * HZ, (((drm_vblank_count(dev, pipe) - vblwait->request.sequence) <= (1 << 23)) || diff --git a/drivers/gpu/drm/drm_memory.c b/drivers/gpu/drm/drm_memory.c index 87a8cb73366f..fc0ebd273ef8 100644 --- a/drivers/gpu/drm/drm_memory.c +++ b/drivers/gpu/drm/drm_memory.c @@ -44,7 +44,7 @@ # include #else # ifdef __powerpc__ -# define PAGE_AGP __pgprot(_PAGE_KERNEL | _PAGE_NO_CACHE) +# define PAGE_AGP pgprot_noncached_wc(PAGE_KERNEL) # else # define PAGE_AGP PAGE_KERNEL # endif diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c index 49311fc61d5d..af0d471ee246 100644 --- a/drivers/gpu/drm/drm_mipi_dsi.c +++ b/drivers/gpu/drm/drm_mipi_dsi.c @@ -999,17 +999,17 @@ int mipi_dsi_dcs_set_tear_on(struct mipi_dsi_device *dsi, EXPORT_SYMBOL(mipi_dsi_dcs_set_tear_on); /** - * mipi_dsi_set_tear_scanline() - turn on the display module's Tearing Effect - * output signal on the TE signal line when display module reaches line N - * defined by STS[n:0]. + * mipi_dsi_dcs_set_tear_scanline() - set the scanline to use as trigger for + * the Tearing Effect output signal of the display module * @dsi: DSI peripheral device - * @param: STS[10:0] + * @scanline: scanline to use as trigger + * * Return: 0 on success or a negative error code on failure */ -int mipi_dsi_set_tear_scanline(struct mipi_dsi_device *dsi, u16 param) +int mipi_dsi_dcs_set_tear_scanline(struct mipi_dsi_device *dsi, u16 scanline) { - u8 payload[3] = { MIPI_DCS_SET_TEAR_SCANLINE, param >> 8, - param & 0xff }; + u8 payload[3] = { MIPI_DCS_SET_TEAR_SCANLINE, scanline >> 8, + scanline & 0xff }; ssize_t err; err = mipi_dsi_generic_write(dsi, payload, sizeof(payload)); @@ -1018,7 +1018,7 @@ int mipi_dsi_set_tear_scanline(struct mipi_dsi_device *dsi, u16 param) return 0; } -EXPORT_SYMBOL(mipi_dsi_set_tear_scanline); +EXPORT_SYMBOL(mipi_dsi_dcs_set_tear_scanline); /** * mipi_dsi_dcs_set_pixel_format() - sets the pixel format for the RGB image diff --git a/drivers/gpu/drm/drm_scatter.c b/drivers/gpu/drm/drm_scatter.c index 4f0f3b36d537..bf70431073f6 100644 --- a/drivers/gpu/drm/drm_scatter.c +++ b/drivers/gpu/drm/drm_scatter.c @@ -41,7 +41,7 @@ static inline void *drm_vmalloc_dma(unsigned long size) { #if defined(__powerpc__) && defined(CONFIG_NOT_COHERENT_CACHE) - return __vmalloc(size, GFP_KERNEL, PAGE_KERNEL | _PAGE_NO_CACHE); + return __vmalloc(size, GFP_KERNEL, pgprot_noncached_wc(PAGE_KERNEL)); #else return vmalloc_32(size); #endif diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c index 43ff44a2b8e7..caa4e4ca616d 100644 --- a/drivers/gpu/drm/drm_vm.c +++ b/drivers/gpu/drm/drm_vm.c @@ -80,7 +80,7 @@ static pgprot_t drm_dma_prot(uint32_t map_type, struct vm_area_struct *vma) pgprot_t tmp = vm_get_page_prot(vma->vm_flags); #if defined(__powerpc__) && defined(CONFIG_NOT_COHERENT_CACHE) - tmp |= _PAGE_NO_CACHE; + tmp = pgprot_noncached_wc(tmp); #endif return tmp; } @@ -593,7 +593,7 @@ static int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma) * pages and mappings in fault() */ #if defined(__powerpc__) - pgprot_val(vma->vm_page_prot) |= _PAGE_NO_CACHE; + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); #endif vma->vm_ops = &drm_vm_ops; break; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c index 340d390306d8..ffd1b32caa8d 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c @@ -91,10 +91,8 @@ static void load_gpu(struct drm_device *dev) int ret; ret = etnaviv_gpu_init(g); - if (ret) { - dev_err(g->dev, "hw init failed: %d\n", ret); + if (ret) priv->gpu[i] = NULL; - } } } } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index df9bcbab922f..56fb8637bb57 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -535,8 +535,7 @@ void etnaviv_gem_describe_objects(struct etnaviv_drm_private *priv, static void etnaviv_gem_shmem_release(struct etnaviv_gem_object *etnaviv_obj) { - if (etnaviv_obj->vaddr) - vunmap(etnaviv_obj->vaddr); + vunmap(etnaviv_obj->vaddr); put_pages(etnaviv_obj); } @@ -670,9 +669,7 @@ static struct drm_gem_object *__etnaviv_gem_new(struct drm_device *dev, return obj; fail: - if (obj) - drm_gem_object_unreference_unlocked(obj); - + drm_gem_object_unreference_unlocked(obj); return ERR_PTR(ret); } @@ -916,15 +913,12 @@ int etnaviv_gem_new_userptr(struct drm_device *dev, struct drm_file *file, get_task_struct(current); ret = etnaviv_gem_obj_add(dev, &etnaviv_obj->base); - if (ret) { - drm_gem_object_unreference_unlocked(&etnaviv_obj->base); - return ret; - } + if (ret) + goto unreference; ret = drm_gem_handle_create(file, &etnaviv_obj->base, handle); - +unreference: /* drop reference from allocate - handle holds it now */ drm_gem_object_unreference_unlocked(&etnaviv_obj->base); - return ret; } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index ff6aa5dfb2d7..87ef34150d46 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -487,6 +487,47 @@ static int etnaviv_hw_reset(struct etnaviv_gpu *gpu) return 0; } +static void etnaviv_gpu_enable_mlcg(struct etnaviv_gpu *gpu) +{ + u32 pmc, ppc; + + /* enable clock gating */ + ppc = gpu_read(gpu, VIVS_PM_POWER_CONTROLS); + ppc |= VIVS_PM_POWER_CONTROLS_ENABLE_MODULE_CLOCK_GATING; + + /* Disable stall module clock gating for 4.3.0.1 and 4.3.0.2 revs */ + if (gpu->identity.revision == 0x4301 || + gpu->identity.revision == 0x4302) + ppc |= VIVS_PM_POWER_CONTROLS_DISABLE_STALL_MODULE_CLOCK_GATING; + + gpu_write(gpu, VIVS_PM_POWER_CONTROLS, ppc); + + pmc = gpu_read(gpu, VIVS_PM_MODULE_CONTROLS); + + /* Disable PA clock gating for GC400+ except for GC420 */ + if (gpu->identity.model >= chipModel_GC400 && + gpu->identity.model != chipModel_GC420) + pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_PA; + + /* + * Disable PE clock gating on revs < 5.0.0.0 when HZ is + * present without a bug fix. + */ + if (gpu->identity.revision < 0x5000 && + gpu->identity.minor_features0 & chipMinorFeatures0_HZ && + !(gpu->identity.minor_features1 & + chipMinorFeatures1_DISABLE_PE_GATING)) + pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_PE; + + if (gpu->identity.revision < 0x5422) + pmc |= BIT(15); /* Unknown bit */ + + pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA_HZ; + pmc |= VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA_EZ; + + gpu_write(gpu, VIVS_PM_MODULE_CONTROLS, pmc); +} + static void etnaviv_gpu_hw_init(struct etnaviv_gpu *gpu) { u16 prefetch; @@ -506,6 +547,9 @@ static void etnaviv_gpu_hw_init(struct etnaviv_gpu *gpu) gpu_write(gpu, VIVS_MC_DEBUG_MEMORY, mc_memory_debug); } + /* enable module-level clock gating */ + etnaviv_gpu_enable_mlcg(gpu); + /* * Update GPU AXI cache atttribute to "cacheable, no allocate". * This is necessary to prevent the iMX6 SoC locking up. @@ -553,8 +597,10 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) bool mmuv2; ret = pm_runtime_get_sync(gpu->dev); - if (ret < 0) + if (ret < 0) { + dev_err(gpu->dev, "Failed to enable GPU power domain\n"); return ret; + } etnaviv_hw_identify(gpu); @@ -591,8 +637,10 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) } ret = etnaviv_hw_reset(gpu); - if (ret) + if (ret) { + dev_err(gpu->dev, "GPU reset failed\n"); goto fail; + } /* Setup IOMMU.. eventually we will (I think) do this once per context * and have separate page tables per context. For now, to keep things @@ -610,12 +658,14 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu) } if (!iommu) { + dev_err(gpu->dev, "Failed to allocate GPU IOMMU domain\n"); ret = -ENOMEM; goto fail; } gpu->mmu = etnaviv_iommu_new(gpu, iommu, version); if (!gpu->mmu) { + dev_err(gpu->dev, "Failed to instantiate GPU IOMMU\n"); iommu_domain_free(iommu); ret = -ENOMEM; goto fail; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c index 522cfd447892..16353ee81651 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_iommu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu.c @@ -225,6 +225,7 @@ struct iommu_domain *etnaviv_iommu_domain_alloc(struct etnaviv_gpu *gpu) etnaviv_domain->domain.type = __IOMMU_DOMAIN_PAGING; etnaviv_domain->domain.ops = &etnaviv_iommu_ops.ops; + etnaviv_domain->domain.pgsize_bitmap = SZ_4K; etnaviv_domain->domain.geometry.aperture_start = GPU_MEM_START; etnaviv_domain->domain.geometry.aperture_end = GPU_MEM_START + PT_ENTRIES * SZ_4K - 1; diff --git a/drivers/gpu/drm/etnaviv/state_hi.xml.h b/drivers/gpu/drm/etnaviv/state_hi.xml.h index 6a7de5f1454a..807a3d9e0dd5 100644 --- a/drivers/gpu/drm/etnaviv/state_hi.xml.h +++ b/drivers/gpu/drm/etnaviv/state_hi.xml.h @@ -218,6 +218,13 @@ Copyright (C) 2015 #define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_FE 0x00000001 #define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_DE 0x00000002 #define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_PE 0x00000004 +#define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_SH 0x00000008 +#define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_PA 0x00000010 +#define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_SE 0x00000020 +#define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA 0x00000040 +#define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_TX 0x00000080 +#define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA_EZ 0x00010000 +#define VIVS_PM_MODULE_CONTROLS_DISABLE_MODULE_CLOCK_GATING_RA_HZ 0x00020000 #define VIVS_PM_MODULE_STATUS 0x00000108 #define VIVS_PM_MODULE_STATUS_MODULE_CLOCK_GATED_FE 0x00000001 diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig index d814b3048ee5..83f61c513b7e 100644 --- a/drivers/gpu/drm/exynos/Kconfig +++ b/drivers/gpu/drm/exynos/Kconfig @@ -2,10 +2,6 @@ config DRM_EXYNOS tristate "DRM Support for Samsung SoC EXYNOS Series" depends on OF && DRM && (ARCH_S3C64XX || ARCH_EXYNOS || ARCH_MULTIPLATFORM) select DRM_KMS_HELPER - select DRM_KMS_FB_HELPER - select FB_CFB_FILLRECT - select FB_CFB_COPYAREA - select FB_CFB_IMAGEBLIT select VIDEOMODE_HELPERS help Choose this option if you have a Samsung SoC EXYNOS chipset. @@ -15,7 +11,7 @@ if DRM_EXYNOS config DRM_EXYNOS_IOMMU bool - depends on EXYNOS_IOMMU && ARM_DMA_USE_IOMMU + depends on EXYNOS_IOMMU default y comment "CRTCs" diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c index f6223f907c15..7f9901b7777b 100644 --- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c @@ -31,7 +31,6 @@ #include "exynos_drm_plane.h" #include "exynos_drm_drv.h" #include "exynos_drm_fb.h" -#include "exynos_drm_fbdev.h" #include "exynos_drm_iommu.h" /* diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c index 468498e3fec1..4f0850585b8e 100644 --- a/drivers/gpu/drm/exynos/exynos_dp.c +++ b/drivers/gpu/drm/exynos/exynos_dp.c @@ -34,7 +34,7 @@ struct exynos_dp_device { struct drm_encoder encoder; - struct drm_connector connector; + struct drm_connector *connector; struct drm_bridge *ptn_bridge; struct drm_device *drm_dev; struct device *dev; @@ -67,10 +67,10 @@ static int exynos_dp_poweroff(struct analogix_dp_plat_data *plat_data) return exynos_dp_crtc_clock_enable(plat_data, false); } -static int exynos_dp_get_modes(struct analogix_dp_plat_data *plat_data) +static int exynos_dp_get_modes(struct analogix_dp_plat_data *plat_data, + struct drm_connector *connector) { struct exynos_dp_device *dp = to_dp(plat_data); - struct drm_connector *connector = &dp->connector; struct drm_display_mode *mode; int num_modes = 0; @@ -103,6 +103,7 @@ static int exynos_dp_bridge_attach(struct analogix_dp_plat_data *plat_data, int ret; drm_connector_register(connector); + dp->connector = connector; /* Pre-empt DP connector creation if there's a bridge */ if (dp->ptn_bridge) { diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c index 011211e4167d..edbd98ff293e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_core.c +++ b/drivers/gpu/drm/exynos/exynos_drm_core.c @@ -15,7 +15,6 @@ #include #include "exynos_drm_drv.h" #include "exynos_drm_crtc.h" -#include "exynos_drm_fbdev.h" static LIST_HEAD(exynos_drm_subdrv_list); diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index 13d28d4229e2..877d2efa28e2 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -159,12 +159,7 @@ static int exynos_drm_load(struct drm_device *dev, unsigned long flags) DRM_INFO("Exynos DRM: using %s device for DMA mapping operations\n", dev_name(private->dma_dev)); - /* - * create mapping to manage iommu table and set a pointer to iommu - * mapping structure to iommu_mapping of private data. - * also this iommu_mapping can be used to check if iommu is supported - * or not. - */ + /* create common IOMMU mapping for all devices attached to Exynos DRM */ ret = drm_create_iommu_mapping(dev); if (ret < 0) { DRM_ERROR("failed to create iommu mapping.\n"); diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h index cc33ec9296e7..b39d521f093d 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.h +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h @@ -224,8 +224,6 @@ struct exynos_drm_private { struct drm_property *plane_zpos_property; struct device *dma_dev; - unsigned long da_start; - unsigned long da_space_size; void *mapping; unsigned int pipe; diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index 67dcd6831291..fb49443bfd32 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -269,8 +269,7 @@ static void exynos_drm_fbdev_destroy(struct drm_device *dev, struct exynos_drm_gem *exynos_gem = exynos_fbd->exynos_gem; struct drm_framebuffer *fb; - if (exynos_gem->kvaddr) - vunmap(exynos_gem->kvaddr); + vunmap(exynos_gem->kvaddr); /* release drm framebuffer and real buffer */ if (fb_helper->fb && fb_helper->fb->funcs) { diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index 3efe1aa89416..d47216488985 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -30,7 +30,6 @@ #include "exynos_drm_drv.h" #include "exynos_drm_fb.h" -#include "exynos_drm_fbdev.h" #include "exynos_drm_crtc.h" #include "exynos_drm_plane.h" #include "exynos_drm_iommu.h" @@ -120,7 +119,6 @@ static struct fimd_driver_data s3c64xx_fimd_driver_data = { .timing_base = 0x0, .has_clksel = 1, .has_limited_fmt = 1, - .has_hw_trigger = 1, }; static struct fimd_driver_data exynos3_fimd_driver_data = { @@ -171,14 +169,11 @@ static struct fimd_driver_data exynos5420_fimd_driver_data = { .lcdblk_vt_shift = 24, .lcdblk_bypass_shift = 15, .lcdblk_mic_bypass_shift = 11, - .trg_type = I80_HW_TRG, .has_shadowcon = 1, .has_vidoutcon = 1, .has_vtsel = 1, .has_mic_bypass = 1, .has_dp_clk = 1, - .has_hw_trigger = 1, - .has_trigger_per_te = 1, }; struct fimd_context { diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 493552368295..8564c3da0d22 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -48,13 +48,13 @@ /* registers for base address */ #define G2D_SRC_BASE_ADDR 0x0304 -#define G2D_SRC_STRIDE_REG 0x0308 +#define G2D_SRC_STRIDE 0x0308 #define G2D_SRC_COLOR_MODE 0x030C #define G2D_SRC_LEFT_TOP 0x0310 #define G2D_SRC_RIGHT_BOTTOM 0x0314 #define G2D_SRC_PLANE2_BASE_ADDR 0x0318 #define G2D_DST_BASE_ADDR 0x0404 -#define G2D_DST_STRIDE_REG 0x0408 +#define G2D_DST_STRIDE 0x0408 #define G2D_DST_COLOR_MODE 0x040C #define G2D_DST_LEFT_TOP 0x0410 #define G2D_DST_RIGHT_BOTTOM 0x0414 @@ -563,7 +563,7 @@ static enum g2d_reg_type g2d_get_reg_type(int reg_offset) switch (reg_offset) { case G2D_SRC_BASE_ADDR: - case G2D_SRC_STRIDE_REG: + case G2D_SRC_STRIDE: case G2D_SRC_COLOR_MODE: case G2D_SRC_LEFT_TOP: case G2D_SRC_RIGHT_BOTTOM: @@ -573,7 +573,7 @@ static enum g2d_reg_type g2d_get_reg_type(int reg_offset) reg_type = REG_TYPE_SRC_PLANE2; break; case G2D_DST_BASE_ADDR: - case G2D_DST_STRIDE_REG: + case G2D_DST_STRIDE: case G2D_DST_COLOR_MODE: case G2D_DST_LEFT_TOP: case G2D_DST_RIGHT_BOTTOM: @@ -968,8 +968,8 @@ static int g2d_check_reg_offset(struct device *dev, } else buf_info->types[reg_type] = BUF_TYPE_GEM; break; - case G2D_SRC_STRIDE_REG: - case G2D_DST_STRIDE_REG: + case G2D_SRC_STRIDE: + case G2D_DST_STRIDE: if (for_addr) goto err; diff --git a/drivers/gpu/drm/exynos/exynos_drm_iommu.c b/drivers/gpu/drm/exynos/exynos_drm_iommu.c index 7ca09ee19656..0f373702414e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_iommu.c +++ b/drivers/gpu/drm/exynos/exynos_drm_iommu.c @@ -14,13 +14,27 @@ #include #include -#include - -#include #include "exynos_drm_drv.h" #include "exynos_drm_iommu.h" +static inline int configure_dma_max_seg_size(struct device *dev) +{ + if (!dev->dma_parms) + dev->dma_parms = kzalloc(sizeof(*dev->dma_parms), GFP_KERNEL); + if (!dev->dma_parms) + return -ENOMEM; + + dma_set_max_seg_size(dev, DMA_BIT_MASK(32)); + return 0; +} + +static inline void clear_dma_max_seg_size(struct device *dev) +{ + kfree(dev->dma_parms); + dev->dma_parms = NULL; +} + /* * drm_create_iommu_mapping - create a mapping structure * @@ -28,38 +42,22 @@ */ int drm_create_iommu_mapping(struct drm_device *drm_dev) { - struct dma_iommu_mapping *mapping = NULL; struct exynos_drm_private *priv = drm_dev->dev_private; - if (!priv->da_start) - priv->da_start = EXYNOS_DEV_ADDR_START; - if (!priv->da_space_size) - priv->da_space_size = EXYNOS_DEV_ADDR_SIZE; - - mapping = arm_iommu_create_mapping(&platform_bus_type, priv->da_start, - priv->da_space_size); - - if (IS_ERR(mapping)) - return PTR_ERR(mapping); - - priv->mapping = mapping; - - return 0; + return __exynos_iommu_create_mapping(priv, EXYNOS_DEV_ADDR_START, + EXYNOS_DEV_ADDR_SIZE); } /* * drm_release_iommu_mapping - release iommu mapping structure * * @drm_dev: DRM device - * - * if mapping->kref becomes 0 then all things related to iommu mapping - * will be released */ void drm_release_iommu_mapping(struct drm_device *drm_dev) { struct exynos_drm_private *priv = drm_dev->dev_private; - arm_iommu_release_mapping(priv->mapping); + __exynos_iommu_release_mapping(priv); } /* @@ -77,26 +75,20 @@ int drm_iommu_attach_device(struct drm_device *drm_dev, struct exynos_drm_private *priv = drm_dev->dev_private; int ret; - if (!priv->mapping) - return 0; - - subdrv_dev->dma_parms = devm_kzalloc(subdrv_dev, - sizeof(*subdrv_dev->dma_parms), - GFP_KERNEL); - if (!subdrv_dev->dma_parms) - return -ENOMEM; - - dma_set_max_seg_size(subdrv_dev, 0xffffffffu); - - if (subdrv_dev->archdata.mapping) - arm_iommu_detach_device(subdrv_dev); - - ret = arm_iommu_attach_device(subdrv_dev, priv->mapping); - if (ret < 0) { - DRM_DEBUG_KMS("failed iommu attach.\n"); - return ret; + if (get_dma_ops(priv->dma_dev) != get_dma_ops(subdrv_dev)) { + DRM_ERROR("Device %s lacks support for IOMMU\n", + dev_name(subdrv_dev)); + return -EINVAL; } + ret = configure_dma_max_seg_size(subdrv_dev); + if (ret) + return ret; + + ret = __exynos_iommu_attach(priv, subdrv_dev); + if (ret) + clear_dma_max_seg_size(subdrv_dev); + return 0; } @@ -113,10 +105,7 @@ void drm_iommu_detach_device(struct drm_device *drm_dev, struct device *subdrv_dev) { struct exynos_drm_private *priv = drm_dev->dev_private; - struct dma_iommu_mapping *mapping = priv->mapping; - if (!mapping || !mapping->domain) - return; - - arm_iommu_detach_device(subdrv_dev); + __exynos_iommu_detach(priv, subdrv_dev); + clear_dma_max_seg_size(subdrv_dev); } diff --git a/drivers/gpu/drm/exynos/exynos_drm_iommu.h b/drivers/gpu/drm/exynos/exynos_drm_iommu.h index 5ffebe02ee4d..c8de4913fdbe 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_iommu.h +++ b/drivers/gpu/drm/exynos/exynos_drm_iommu.h @@ -17,6 +17,97 @@ #ifdef CONFIG_DRM_EXYNOS_IOMMU +#if defined(CONFIG_ARM_DMA_USE_IOMMU) +#include + +static inline int __exynos_iommu_create_mapping(struct exynos_drm_private *priv, + unsigned long start, unsigned long size) +{ + priv->mapping = arm_iommu_create_mapping(&platform_bus_type, start, + size); + return IS_ERR(priv->mapping); +} + +static inline void +__exynos_iommu_release_mapping(struct exynos_drm_private *priv) +{ + arm_iommu_release_mapping(priv->mapping); +} + +static inline int __exynos_iommu_attach(struct exynos_drm_private *priv, + struct device *dev) +{ + if (dev->archdata.mapping) + arm_iommu_detach_device(dev); + + return arm_iommu_attach_device(dev, priv->mapping); +} + +static inline void __exynos_iommu_detach(struct exynos_drm_private *priv, + struct device *dev) +{ + arm_iommu_detach_device(dev); +} + +#elif defined(CONFIG_IOMMU_DMA) +#include + +static inline int __exynos_iommu_create_mapping(struct exynos_drm_private *priv, + unsigned long start, unsigned long size) +{ + struct iommu_domain *domain; + int ret; + + domain = iommu_domain_alloc(priv->dma_dev->bus); + if (!domain) + return -ENOMEM; + + ret = iommu_get_dma_cookie(domain); + if (ret) + goto free_domain; + + ret = iommu_dma_init_domain(domain, start, size); + if (ret) + goto put_cookie; + + priv->mapping = domain; + return 0; + +put_cookie: + iommu_put_dma_cookie(domain); +free_domain: + iommu_domain_free(domain); + return ret; +} + +static inline void __exynos_iommu_release_mapping(struct exynos_drm_private *priv) +{ + struct iommu_domain *domain = priv->mapping; + + iommu_put_dma_cookie(domain); + iommu_domain_free(domain); + priv->mapping = NULL; +} + +static inline int __exynos_iommu_attach(struct exynos_drm_private *priv, + struct device *dev) +{ + struct iommu_domain *domain = priv->mapping; + + return iommu_attach_device(domain, dev); +} + +static inline void __exynos_iommu_detach(struct exynos_drm_private *priv, + struct device *dev) +{ + struct iommu_domain *domain = priv->mapping; + + iommu_detach_device(domain, dev); +} +#else +#error Unsupported architecture and IOMMU/DMA-mapping glue code +#endif + int drm_create_iommu_mapping(struct drm_device *drm_dev); void drm_release_iommu_mapping(struct drm_device *drm_dev); diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 1625d7c8a319..2275efe41acd 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -1820,6 +1820,7 @@ static int hdmi_probe(struct platform_device *pdev) DRM_ERROR("Failed to find ddc node in device tree\n"); return -ENODEV; } + of_node_put(dev->of_node); out_get_ddc_adpt: hdata->ddc_adpt = of_find_i2c_adapter_by_node(ddc_node); @@ -1838,6 +1839,7 @@ static int hdmi_probe(struct platform_device *pdev) ret = -ENODEV; goto err_ddc; } + of_node_put(dev->of_node); out_get_phy_port: if (hdata->drv_data->is_apb_phy) { diff --git a/drivers/gpu/drm/fsl-dcu/Kconfig b/drivers/gpu/drm/fsl-dcu/Kconfig index b9c714de6e40..14a72c4c496d 100644 --- a/drivers/gpu/drm/fsl-dcu/Kconfig +++ b/drivers/gpu/drm/fsl-dcu/Kconfig @@ -5,12 +5,7 @@ config DRM_FSL_DCU select BACKLIGHT_LCD_SUPPORT select DRM_KMS_HELPER select DRM_KMS_CMA_HELPER - select DRM_KMS_FB_HELPER select DRM_PANEL - select FB_SYS_FILLRECT - select FB_SYS_COPYAREA - select FB_SYS_IMAGEBLIT - select FB_SYS_FOPS select REGMAP_MMIO select VIDEOMODE_HELPERS help diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c index 706de3278f1c..3371635cd4d7 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_crtc.c @@ -44,6 +44,8 @@ static void fsl_dcu_drm_disable_crtc(struct drm_crtc *crtc) struct drm_device *dev = crtc->dev; struct fsl_dcu_drm_device *fsl_dev = dev->dev_private; + drm_crtc_vblank_off(crtc); + regmap_update_bits(fsl_dev->regmap, DCU_DCU_MODE, DCU_MODE_DCU_MODE_MASK, DCU_MODE_DCU_MODE(DCU_MODE_OFF)); @@ -61,6 +63,8 @@ static void fsl_dcu_drm_crtc_enable(struct drm_crtc *crtc) DCU_MODE_DCU_MODE(DCU_MODE_NORMAL)); regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE, DCU_UPDATE_MODE_READREG); + + drm_crtc_vblank_on(crtc); } static void fsl_dcu_drm_crtc_mode_set_nofb(struct drm_crtc *crtc) @@ -137,9 +141,10 @@ int fsl_dcu_drm_crtc_create(struct fsl_dcu_drm_device *fsl_dev) { struct drm_plane *primary; struct drm_crtc *crtc = &fsl_dev->crtc; - unsigned int i, j, reg_num; int ret; + fsl_dcu_drm_init_planes(fsl_dev->drm); + primary = fsl_dcu_drm_primary_create_plane(fsl_dev->drm); if (!primary) return -ENOMEM; @@ -153,19 +158,5 @@ int fsl_dcu_drm_crtc_create(struct fsl_dcu_drm_device *fsl_dev) drm_crtc_helper_add(crtc, &fsl_dcu_drm_crtc_helper_funcs); - if (!strcmp(fsl_dev->soc->name, "ls1021a")) - reg_num = LS1021A_LAYER_REG_NUM; - else - reg_num = VF610_LAYER_REG_NUM; - for (i = 0; i < fsl_dev->soc->total_layer; i++) { - for (j = 1; j <= reg_num; j++) - regmap_write(fsl_dev->regmap, DCU_CTRLDESCLN(i, j), 0); - } - regmap_update_bits(fsl_dev->regmap, DCU_DCU_MODE, - DCU_MODE_DCU_MODE_MASK, - DCU_MODE_DCU_MODE(DCU_MODE_OFF)); - regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE, - DCU_UPDATE_MODE_READREG); - return 0; } diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c index 33727d5d826a..7882387f9bff 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.c @@ -11,6 +11,7 @@ #include #include +#include #include #include #include @@ -22,6 +23,7 @@ #include #include +#include #include #include #include @@ -42,7 +44,6 @@ static const struct regmap_config fsl_dcu_regmap_config = { .reg_bits = 32, .reg_stride = 4, .val_bits = 32, - .cache_type = REGCACHE_RBTREE, .volatile_reg = fsl_dcu_drm_is_volatile_reg, }; @@ -228,11 +229,26 @@ static int fsl_dcu_drm_pm_suspend(struct device *dev) if (!fsl_dev) return 0; + disable_irq(fsl_dev->irq); drm_kms_helper_poll_disable(fsl_dev->drm); - regcache_cache_only(fsl_dev->regmap, true); - regcache_mark_dirty(fsl_dev->regmap); - clk_disable(fsl_dev->clk); - clk_unprepare(fsl_dev->clk); + + console_lock(); + drm_fbdev_cma_set_suspend(fsl_dev->fbdev, 1); + console_unlock(); + + fsl_dev->state = drm_atomic_helper_suspend(fsl_dev->drm); + if (IS_ERR(fsl_dev->state)) { + console_lock(); + drm_fbdev_cma_set_suspend(fsl_dev->fbdev, 0); + console_unlock(); + + drm_kms_helper_poll_enable(fsl_dev->drm); + enable_irq(fsl_dev->irq); + return PTR_ERR(fsl_dev->state); + } + + clk_disable_unprepare(fsl_dev->pix_clk); + clk_disable_unprepare(fsl_dev->clk); return 0; } @@ -245,21 +261,27 @@ static int fsl_dcu_drm_pm_resume(struct device *dev) if (!fsl_dev) return 0; - ret = clk_enable(fsl_dev->clk); + ret = clk_prepare_enable(fsl_dev->clk); if (ret < 0) { dev_err(dev, "failed to enable dcu clk\n"); - clk_unprepare(fsl_dev->clk); - return ret; - } - ret = clk_prepare(fsl_dev->clk); - if (ret < 0) { - dev_err(dev, "failed to prepare dcu clk\n"); return ret; } + ret = clk_prepare_enable(fsl_dev->pix_clk); + if (ret < 0) { + dev_err(dev, "failed to enable pix clk\n"); + return ret; + } + + fsl_dcu_drm_init_planes(fsl_dev->drm); + drm_atomic_helper_resume(fsl_dev->drm, fsl_dev->state); + + console_lock(); + drm_fbdev_cma_set_suspend(fsl_dev->fbdev, 0); + console_unlock(); + drm_kms_helper_poll_enable(fsl_dev->drm); - regcache_cache_only(fsl_dev->regmap, false); - regcache_sync(fsl_dev->regmap); + enable_irq(fsl_dev->irq); return 0; } @@ -273,12 +295,14 @@ static const struct fsl_dcu_soc_data fsl_dcu_ls1021a_data = { .name = "ls1021a", .total_layer = 16, .max_layer = 4, + .layer_regs = LS1021A_LAYER_REG_NUM, }; static const struct fsl_dcu_soc_data fsl_dcu_vf610_data = { .name = "vf610", .total_layer = 64, .max_layer = 6, + .layer_regs = VF610_LAYER_REG_NUM, }; static const struct of_device_id fsl_dcu_of_match[] = { diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.h b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.h index c275f900ff23..3b371fe7491e 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.h +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_drv.h @@ -175,6 +175,7 @@ struct fsl_dcu_soc_data { unsigned int total_layer; /*max layer number DCU supported*/ unsigned int max_layer; + unsigned int layer_regs; }; struct fsl_dcu_drm_device { @@ -193,6 +194,7 @@ struct fsl_dcu_drm_device { struct drm_encoder encoder; struct fsl_dcu_drm_connector connector; const struct fsl_dcu_soc_data *soc; + struct drm_atomic_state *state; }; void fsl_dcu_fbdev_init(struct drm_device *dev); diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_kms.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_kms.c index a6e4cd591960..d9d6cc1c8e39 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_kms.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_kms.c @@ -43,7 +43,7 @@ int fsl_dcu_drm_modeset_init(struct fsl_dcu_drm_device *fsl_dev) if (ret) goto err; - ret = fsl_dcu_drm_connector_create(fsl_dev, &fsl_dev->encoder); + ret = fsl_dcu_create_outputs(fsl_dev); if (ret) goto err; diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_output.h b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_output.h index 7093109fbc21..5a7b88e19e44 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_output.h +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_output.h @@ -25,9 +25,8 @@ to_fsl_dcu_connector(struct drm_connector *con) : NULL; } -int fsl_dcu_drm_connector_create(struct fsl_dcu_drm_device *fsl_dev, - struct drm_encoder *encoder); int fsl_dcu_drm_encoder_create(struct fsl_dcu_drm_device *fsl_dev, struct drm_crtc *crtc); +int fsl_dcu_create_outputs(struct fsl_dcu_drm_device *fsl_dev); #endif /* __FSL_DCU_DRM_CONNECTOR_H__ */ diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c index 274558b3b32b..e50467a0deb0 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.c @@ -217,6 +217,22 @@ static const u32 fsl_dcu_drm_plane_formats[] = { DRM_FORMAT_YUV422, }; +void fsl_dcu_drm_init_planes(struct drm_device *dev) +{ + struct fsl_dcu_drm_device *fsl_dev = dev->dev_private; + int i, j; + + for (i = 0; i < fsl_dev->soc->total_layer; i++) { + for (j = 1; j <= fsl_dev->soc->layer_regs; j++) + regmap_write(fsl_dev->regmap, DCU_CTRLDESCLN(i, j), 0); + } + regmap_update_bits(fsl_dev->regmap, DCU_DCU_MODE, + DCU_MODE_DCU_MODE_MASK, + DCU_MODE_DCU_MODE(DCU_MODE_OFF)); + regmap_write(fsl_dev->regmap, DCU_UPDATE_MODE, + DCU_UPDATE_MODE_READREG); +} + struct drm_plane *fsl_dcu_drm_primary_create_plane(struct drm_device *dev) { struct drm_plane *primary; diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.h b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.h index d657f088d859..8ee45f813ee8 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.h +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_plane.h @@ -12,6 +12,7 @@ #ifndef __FSL_DCU_DRM_PLANE_H__ #define __FSL_DCU_DRM_PLANE_H__ +void fsl_dcu_drm_init_planes(struct drm_device *dev); struct drm_plane *fsl_dcu_drm_primary_create_plane(struct drm_device *dev); #endif /* __FSL_DCU_DRM_PLANE_H__ */ diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c index 0b0989e503ea..26edcc899712 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c @@ -10,6 +10,7 @@ */ #include +#include #include #include @@ -132,12 +133,12 @@ static const struct drm_connector_helper_funcs connector_helper_funcs = { .mode_valid = fsl_dcu_drm_connector_mode_valid, }; -int fsl_dcu_drm_connector_create(struct fsl_dcu_drm_device *fsl_dev, - struct drm_encoder *encoder) +static int fsl_dcu_attach_panel(struct fsl_dcu_drm_device *fsl_dev, + struct drm_panel *panel) { + struct drm_encoder *encoder = &fsl_dev->encoder; struct drm_connector *connector = &fsl_dev->connector.base; struct drm_mode_config *mode_config = &fsl_dev->drm->mode_config; - struct device_node *panel_node; int ret; fsl_dev->connector.encoder = encoder; @@ -161,21 +162,7 @@ int fsl_dcu_drm_connector_create(struct fsl_dcu_drm_device *fsl_dev, mode_config->dpms_property, DRM_MODE_DPMS_OFF); - panel_node = of_parse_phandle(fsl_dev->np, "fsl,panel", 0); - if (!panel_node) { - dev_err(fsl_dev->dev, "fsl,panel property not found\n"); - ret = -ENODEV; - goto err_sysfs; - } - - fsl_dev->connector.panel = of_drm_find_panel(panel_node); - if (!fsl_dev->connector.panel) { - ret = -EPROBE_DEFER; - goto err_panel; - } - of_node_put(panel_node); - - ret = drm_panel_attach(fsl_dev->connector.panel, connector); + ret = drm_panel_attach(panel, connector); if (ret) { dev_err(fsl_dev->dev, "failed to attach panel\n"); goto err_sysfs; @@ -183,11 +170,62 @@ int fsl_dcu_drm_connector_create(struct fsl_dcu_drm_device *fsl_dev, return 0; -err_panel: - of_node_put(panel_node); err_sysfs: drm_connector_unregister(connector); err_cleanup: drm_connector_cleanup(connector); return ret; } + +static int fsl_dcu_attach_endpoint(struct fsl_dcu_drm_device *fsl_dev, + const struct of_endpoint *ep) +{ + struct drm_bridge *bridge; + struct device_node *np; + + np = of_graph_get_remote_port_parent(ep->local_node); + + fsl_dev->connector.panel = of_drm_find_panel(np); + if (fsl_dev->connector.panel) { + of_node_put(np); + return fsl_dcu_attach_panel(fsl_dev, fsl_dev->connector.panel); + } + + bridge = of_drm_find_bridge(np); + of_node_put(np); + if (!bridge) + return -ENODEV; + + fsl_dev->encoder.bridge = bridge; + bridge->encoder = &fsl_dev->encoder; + + return drm_bridge_attach(fsl_dev->drm, bridge); +} + +int fsl_dcu_create_outputs(struct fsl_dcu_drm_device *fsl_dev) +{ + struct of_endpoint ep; + struct device_node *ep_node, *panel_node; + int ret; + + /* This is for backward compatibility */ + panel_node = of_parse_phandle(fsl_dev->np, "fsl,panel", 0); + if (panel_node) { + fsl_dev->connector.panel = of_drm_find_panel(panel_node); + of_node_put(panel_node); + if (!fsl_dev->connector.panel) + return -EPROBE_DEFER; + return fsl_dcu_attach_panel(fsl_dev, fsl_dev->connector.panel); + } + + ep_node = of_graph_get_next_endpoint(fsl_dev->np, NULL); + if (!ep_node) + return -ENODEV; + + ret = of_graph_parse_endpoint(ep_node, &ep); + of_node_put(ep_node); + if (ret) + return -ENODEV; + + return fsl_dcu_attach_endpoint(fsl_dev, &ep); +} diff --git a/drivers/gpu/drm/fsl-dcu/fsl_tcon.c b/drivers/gpu/drm/fsl-dcu/fsl_tcon.c index bbe34f1c0505..bca09ea24632 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_tcon.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_tcon.c @@ -92,6 +92,7 @@ struct fsl_tcon *fsl_tcon_init(struct device *dev) goto err_node_put; } + of_node_put(np); clk_prepare_enable(tcon->ipg_clk); dev_info(dev, "Using TCON in bypass mode\n"); diff --git a/drivers/gpu/drm/gma500/Kconfig b/drivers/gpu/drm/gma500/Kconfig index 17f928ec84ea..8906d67494fc 100644 --- a/drivers/gpu/drm/gma500/Kconfig +++ b/drivers/gpu/drm/gma500/Kconfig @@ -1,11 +1,7 @@ config DRM_GMA500 tristate "Intel GMA5/600 KMS Framebuffer" depends on DRM && PCI && X86 - select FB_CFB_COPYAREA - select FB_CFB_FILLRECT - select FB_CFB_IMAGEBLIT select DRM_KMS_HELPER - select DRM_KMS_FB_HELPER select DRM_TTM # GMA500 depends on ACPI_VIDEO when ACPI is enabled, just like i915 select ACPI_VIDEO if ACPI diff --git a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c index 28f9d90988ff..563f193fcfac 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c +++ b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c @@ -246,8 +246,7 @@ static void cdv_hdmi_destroy(struct drm_connector *connector) { struct gma_encoder *gma_encoder = gma_attached_encoder(connector); - if (gma_encoder->i2c_bus) - psb_intel_i2c_destroy(gma_encoder->i2c_bus); + psb_intel_i2c_destroy(gma_encoder->i2c_bus); drm_connector_unregister(connector); drm_connector_cleanup(connector); kfree(connector); diff --git a/drivers/gpu/drm/gma500/cdv_intel_lvds.c b/drivers/gpu/drm/gma500/cdv_intel_lvds.c index 813ef23a8054..38dc89083148 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_lvds.c +++ b/drivers/gpu/drm/gma500/cdv_intel_lvds.c @@ -444,8 +444,7 @@ static void cdv_intel_lvds_destroy(struct drm_connector *connector) { struct gma_encoder *gma_encoder = gma_attached_encoder(connector); - if (gma_encoder->i2c_bus) - psb_intel_i2c_destroy(gma_encoder->i2c_bus); + psb_intel_i2c_destroy(gma_encoder->i2c_bus); drm_connector_unregister(connector); drm_connector_cleanup(connector); kfree(connector); @@ -780,12 +779,10 @@ void cdv_intel_lvds_init(struct drm_device *dev, failed_find: mutex_unlock(&dev->mode_config.mutex); printk(KERN_ERR "Failed find\n"); - if (gma_encoder->ddc_bus) - psb_intel_i2c_destroy(gma_encoder->ddc_bus); + psb_intel_i2c_destroy(gma_encoder->ddc_bus); failed_ddc: printk(KERN_ERR "Failed DDC\n"); - if (gma_encoder->i2c_bus) - psb_intel_i2c_destroy(gma_encoder->i2c_bus); + psb_intel_i2c_destroy(gma_encoder->i2c_bus); failed_blc_i2c: printk(KERN_ERR "Failed BLC\n"); drm_encoder_cleanup(encoder); diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c index 7440bf90ac9c..0fcdce0817de 100644 --- a/drivers/gpu/drm/gma500/framebuffer.c +++ b/drivers/gpu/drm/gma500/framebuffer.c @@ -184,12 +184,6 @@ static int psbfb_mmap(struct fb_info *info, struct vm_area_struct *vma) return 0; } -static int psbfb_ioctl(struct fb_info *info, unsigned int cmd, - unsigned long arg) -{ - return -ENOTTY; -} - static struct fb_ops psbfb_ops = { .owner = THIS_MODULE, .fb_check_var = drm_fb_helper_check_var, @@ -201,7 +195,6 @@ static struct fb_ops psbfb_ops = { .fb_imageblit = drm_fb_helper_cfb_imageblit, .fb_mmap = psbfb_mmap, .fb_sync = psbfb_sync, - .fb_ioctl = psbfb_ioctl, }; static struct fb_ops psbfb_roll_ops = { @@ -215,7 +208,6 @@ static struct fb_ops psbfb_roll_ops = { .fb_imageblit = drm_fb_helper_cfb_imageblit, .fb_pan_display = psbfb_pan, .fb_mmap = psbfb_mmap, - .fb_ioctl = psbfb_ioctl, }; static struct fb_ops psbfb_unaccel_ops = { @@ -228,7 +220,6 @@ static struct fb_ops psbfb_unaccel_ops = { .fb_copyarea = drm_fb_helper_cfb_copyarea, .fb_imageblit = drm_fb_helper_cfb_imageblit, .fb_mmap = psbfb_mmap, - .fb_ioctl = psbfb_ioctl, }; /** diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index 82b8ce418b27..50eb944fb78a 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -210,10 +210,8 @@ static int psb_driver_unload(struct drm_device *dev) iounmap(dev_priv->aux_reg); dev_priv->aux_reg = NULL; } - if (dev_priv->aux_pdev) - pci_dev_put(dev_priv->aux_pdev); - if (dev_priv->lpc_pdev) - pci_dev_put(dev_priv->lpc_pdev); + pci_dev_put(dev_priv->aux_pdev); + pci_dev_put(dev_priv->lpc_pdev); /* Destroy VBT data */ psb_intel_destroy_bios(dev); diff --git a/drivers/gpu/drm/gma500/psb_intel_lvds.c b/drivers/gpu/drm/gma500/psb_intel_lvds.c index b1b93317d054..e55733ca46d2 100644 --- a/drivers/gpu/drm/gma500/psb_intel_lvds.c +++ b/drivers/gpu/drm/gma500/psb_intel_lvds.c @@ -561,8 +561,7 @@ void psb_intel_lvds_destroy(struct drm_connector *connector) struct gma_encoder *gma_encoder = gma_attached_encoder(connector); struct psb_intel_lvds_priv *lvds_priv = gma_encoder->dev_priv; - if (lvds_priv->ddc_bus) - psb_intel_i2c_destroy(lvds_priv->ddc_bus); + psb_intel_i2c_destroy(lvds_priv->ddc_bus); drm_connector_unregister(connector); drm_connector_cleanup(connector); kfree(connector); @@ -835,11 +834,9 @@ void psb_intel_lvds_init(struct drm_device *dev, failed_find: mutex_unlock(&dev->mode_config.mutex); - if (lvds_priv->ddc_bus) - psb_intel_i2c_destroy(lvds_priv->ddc_bus); + psb_intel_i2c_destroy(lvds_priv->ddc_bus); failed_ddc: - if (lvds_priv->i2c_bus) - psb_intel_i2c_destroy(lvds_priv->i2c_bus); + psb_intel_i2c_destroy(lvds_priv->i2c_bus); failed_blc_i2c: drm_encoder_cleanup(encoder); drm_connector_cleanup(connector); diff --git a/drivers/gpu/drm/hisilicon/kirin/Kconfig b/drivers/gpu/drm/hisilicon/kirin/Kconfig index ea0df6115f7e..499f64405dac 100644 --- a/drivers/gpu/drm/hisilicon/kirin/Kconfig +++ b/drivers/gpu/drm/hisilicon/kirin/Kconfig @@ -4,6 +4,7 @@ config DRM_HISI_KIRIN select DRM_KMS_HELPER select DRM_GEM_CMA_HELPER select DRM_KMS_CMA_HELPER + select HISI_KIRIN_DW_DSI help Choose this option if you have a hisilicon Kirin chipsets(hi6220). If M is selected the module will be called kirin-drm. diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c index ed76baad525f..c3707d47cd89 100644 --- a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c +++ b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c @@ -487,6 +487,7 @@ static void ade_crtc_enable(struct drm_crtc *crtc) ade_set_medianoc_qos(acrtc); ade_display_enable(acrtc); ade_dump_regs(ctx->base); + drm_crtc_vblank_on(crtc); acrtc->enable = true; } @@ -498,6 +499,7 @@ static void ade_crtc_disable(struct drm_crtc *crtc) if (!acrtc->enable) return; + drm_crtc_vblank_off(crtc); ade_power_down(ctx); acrtc->enable = false; } @@ -965,21 +967,21 @@ static int ade_dts_parse(struct platform_device *pdev, struct ade_hw_ctx *ctx) } ctx->ade_core_clk = devm_clk_get(dev, "clk_ade_core"); - if (!ctx->ade_core_clk) { + if (IS_ERR(ctx->ade_core_clk)) { DRM_ERROR("failed to parse clk ADE_CORE\n"); - return -ENODEV; + return PTR_ERR(ctx->ade_core_clk); } ctx->media_noc_clk = devm_clk_get(dev, "clk_codec_jpeg"); - if (!ctx->media_noc_clk) { + if (IS_ERR(ctx->media_noc_clk)) { DRM_ERROR("failed to parse clk CODEC_JPEG\n"); - return -ENODEV; + return PTR_ERR(ctx->media_noc_clk); } ctx->ade_pix_clk = devm_clk_get(dev, "clk_ade_pix"); - if (!ctx->ade_pix_clk) { + if (IS_ERR(ctx->ade_pix_clk)) { DRM_ERROR("failed to parse clk ADE_PIX\n"); - return -ENODEV; + return PTR_ERR(ctx->ade_pix_clk); } return 0; diff --git a/drivers/gpu/drm/i2c/Kconfig b/drivers/gpu/drm/i2c/Kconfig index 22c7ed63a001..4d341db462a2 100644 --- a/drivers/gpu/drm/i2c/Kconfig +++ b/drivers/gpu/drm/i2c/Kconfig @@ -1,12 +1,6 @@ menu "I2C encoder or helper chips" depends on DRM && DRM_KMS_HELPER && I2C -config DRM_I2C_ADV7511 - tristate "AV7511 encoder" - select REGMAP_I2C - help - Support for the Analog Device ADV7511(W) and ADV7513 HDMI encoders. - config DRM_I2C_CH7006 tristate "Chrontel ch7006 TV encoder" default m if DRM_NOUVEAU diff --git a/drivers/gpu/drm/i2c/Makefile b/drivers/gpu/drm/i2c/Makefile index 2c72eb584ab7..43aa33baebed 100644 --- a/drivers/gpu/drm/i2c/Makefile +++ b/drivers/gpu/drm/i2c/Makefile @@ -1,7 +1,5 @@ ccflags-y := -Iinclude/drm -obj-$(CONFIG_DRM_I2C_ADV7511) += adv7511.o - ch7006-y := ch7006_drv.o ch7006_mode.o obj-$(CONFIG_DRM_I2C_CH7006) += ch7006.o diff --git a/drivers/gpu/drm/i2c/ch7006_drv.c b/drivers/gpu/drm/i2c/ch7006_drv.c index 0594c45f7164..e9e8ae2ec06b 100644 --- a/drivers/gpu/drm/i2c/ch7006_drv.c +++ b/drivers/gpu/drm/i2c/ch7006_drv.c @@ -361,13 +361,8 @@ static int ch7006_encoder_set_property(struct drm_encoder *encoder, /* Disable the crtc to ensure a full modeset is * performed whenever it's turned on again. */ - if (crtc) { - struct drm_mode_set modeset = { - .crtc = crtc, - }; - - drm_mode_set_config_internal(&modeset); - } + if (crtc) + drm_crtc_force_disable(crtc); } return 0; diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 1ea0e1f43397..fb27d187876c 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -34,15 +34,15 @@ * low-power state and comes back to normal. */ -#define I915_CSR_KBL "i915/kbl_dmc_ver1_01.bin" +#define I915_CSR_KBL "i915/kbl_dmc_ver1.bin" MODULE_FIRMWARE(I915_CSR_KBL); #define KBL_CSR_VERSION_REQUIRED CSR_VERSION(1, 1) -#define I915_CSR_SKL "i915/skl_dmc_ver1_26.bin" +#define I915_CSR_SKL "i915/skl_dmc_ver1.bin" MODULE_FIRMWARE(I915_CSR_SKL); -#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 26) +#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 23) -#define I915_CSR_BXT "i915/bxt_dmc_ver1_07.bin" +#define I915_CSR_BXT "i915/bxt_dmc_ver1.bin" MODULE_FIRMWARE(I915_CSR_BXT); #define BXT_CSR_VERSION_REQUIRED CSR_VERSION(1, 7) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 361977fd1170..a07da548ff49 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -928,6 +928,7 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, uint32_t *batch, uint32_t index) { + struct drm_i915_private *dev_priv = engine->i915; uint32_t l3sqc4_flush = (0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES); /* @@ -936,8 +937,8 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, * this batch updates GEN8_L3SQCREG4 with default value we need to * set this bit here to retain the WA during flush. */ - if (IS_SKL_REVID(engine->i915, 0, SKL_REVID_E0) || - IS_KBL_REVID(engine->i915, 0, KBL_REVID_E0)) + if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_E0) || + IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0)) l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS; wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 | @@ -1077,11 +1078,12 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine, uint32_t *offset) { int ret; + struct drm_i915_private *dev_priv = engine->i915; uint32_t index = wa_ctx_start(wa_ctx, *offset, CACHELINE_DWORDS); /* WaDisableCtxRestoreArbitration:skl,bxt */ - if (IS_SKL_REVID(engine->i915, 0, SKL_REVID_D0) || - IS_BXT_REVID(engine->i915, 0, BXT_REVID_A1)) + if (IS_SKL_REVID(dev_priv, 0, SKL_REVID_D0) || + IS_BXT_REVID(dev_priv, 0, BXT_REVID_A1)) wa_ctx_emit(batch, index, MI_ARB_ON_OFF | MI_ARB_DISABLE); /* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt */ @@ -1099,7 +1101,7 @@ static int gen9_init_indirectctx_bb(struct intel_engine_cs *engine, /* WaClearSlmSpaceAtContextSwitch:kbl */ /* Actual scratch location is at 128 bytes offset */ - if (IS_KBL_REVID(engine->i915, 0, KBL_REVID_A0)) { + if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_A0)) { uint32_t scratch_addr = engine->scratch.gtt_offset + 2*CACHELINE_BYTES; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 948f24418eac..6bd352a8f30e 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -57,7 +57,7 @@ static void gen9_init_clock_gating(struct drm_device *dev) { - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = dev->dev_private; /* See Bspec note for PSR2_CTL bit 31, Wa#828:skl,bxt,kbl */ I915_WRITE(CHICKEN_PAR1_1, @@ -7044,7 +7044,7 @@ static void gen8_set_l3sqc_credits(struct drm_i915_private *dev_priv, static void kabylake_init_clock_gating(struct drm_device *dev) { - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = dev->dev_private; gen9_init_clock_gating(dev); @@ -7065,7 +7065,7 @@ static void kabylake_init_clock_gating(struct drm_device *dev) static void skylake_init_clock_gating(struct drm_device *dev) { - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *dev_priv = dev->dev_private; gen9_init_clock_gating(dev); diff --git a/drivers/gpu/drm/imx/Kconfig b/drivers/gpu/drm/imx/Kconfig index a1844b50546c..f2c9ae822149 100644 --- a/drivers/gpu/drm/imx/Kconfig +++ b/drivers/gpu/drm/imx/Kconfig @@ -1,7 +1,6 @@ config DRM_IMX tristate "DRM Support for Freescale i.MX" select DRM_KMS_HELPER - select DRM_KMS_FB_HELPER select VIDEOMODE_HELPERS select DRM_GEM_CMA_HELPER select DRM_KMS_CMA_HELPER diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c index a24631fdf4ad..359cd2765552 100644 --- a/drivers/gpu/drm/imx/dw_hdmi-imx.c +++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c @@ -28,6 +28,11 @@ struct imx_hdmi { struct regmap *regmap; }; +static inline struct imx_hdmi *enc_to_imx_hdmi(struct drm_encoder *e) +{ + return container_of(e, struct imx_hdmi, encoder); +} + static const struct dw_hdmi_mpll_config imx_mpll_cfg[] = { { 45250000, { @@ -109,15 +114,9 @@ static void dw_hdmi_imx_encoder_disable(struct drm_encoder *encoder) { } -static void dw_hdmi_imx_encoder_mode_set(struct drm_encoder *encoder, - struct drm_display_mode *mode, - struct drm_display_mode *adj_mode) +static void dw_hdmi_imx_encoder_enable(struct drm_encoder *encoder) { -} - -static void dw_hdmi_imx_encoder_commit(struct drm_encoder *encoder) -{ - struct imx_hdmi *hdmi = container_of(encoder, struct imx_hdmi, encoder); + struct imx_hdmi *hdmi = enc_to_imx_hdmi(encoder); int mux = drm_of_encoder_active_port_id(hdmi->dev->of_node, encoder); regmap_update_bits(hdmi->regmap, IOMUXC_GPR3, @@ -125,16 +124,23 @@ static void dw_hdmi_imx_encoder_commit(struct drm_encoder *encoder) mux << IMX6Q_GPR3_HDMI_MUX_CTL_SHIFT); } -static void dw_hdmi_imx_encoder_prepare(struct drm_encoder *encoder) +static int dw_hdmi_imx_atomic_check(struct drm_encoder *encoder, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) { - imx_drm_set_bus_format(encoder, MEDIA_BUS_FMT_RGB888_1X24); + struct imx_crtc_state *imx_crtc_state = to_imx_crtc_state(crtc_state); + + imx_crtc_state->bus_format = MEDIA_BUS_FMT_RGB888_1X24; + imx_crtc_state->di_hsync_pin = 2; + imx_crtc_state->di_vsync_pin = 3; + + return 0; } static const struct drm_encoder_helper_funcs dw_hdmi_imx_encoder_helper_funcs = { - .mode_set = dw_hdmi_imx_encoder_mode_set, - .prepare = dw_hdmi_imx_encoder_prepare, - .commit = dw_hdmi_imx_encoder_commit, + .enable = dw_hdmi_imx_encoder_enable, .disable = dw_hdmi_imx_encoder_disable, + .atomic_check = dw_hdmi_imx_atomic_check, }; static const struct drm_encoder_funcs dw_hdmi_imx_encoder_funcs = { diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index 7746418a4c08..9f7dafce3a4c 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -15,10 +15,14 @@ */ #include #include +#include #include #include #include +#include #include +#include +#include #include #include #include @@ -41,6 +45,7 @@ struct imx_drm_device { struct imx_drm_crtc *crtc[MAX_CRTC]; unsigned int pipes; struct drm_fbdev_cma *fbhelper; + struct drm_atomic_state *state; }; struct imx_drm_crtc { @@ -85,45 +90,6 @@ static int imx_drm_driver_unload(struct drm_device *drm) return 0; } -static struct imx_drm_crtc *imx_drm_find_crtc(struct drm_crtc *crtc) -{ - struct imx_drm_device *imxdrm = crtc->dev->dev_private; - unsigned i; - - for (i = 0; i < MAX_CRTC; i++) - if (imxdrm->crtc[i] && imxdrm->crtc[i]->crtc == crtc) - return imxdrm->crtc[i]; - - return NULL; -} - -int imx_drm_set_bus_config(struct drm_encoder *encoder, u32 bus_format, - int hsync_pin, int vsync_pin, u32 bus_flags) -{ - struct imx_drm_crtc_helper_funcs *helper; - struct imx_drm_crtc *imx_crtc; - - imx_crtc = imx_drm_find_crtc(encoder->crtc); - if (!imx_crtc) - return -EINVAL; - - helper = &imx_crtc->imx_drm_helper_funcs; - if (helper->set_interface_pix_fmt) - return helper->set_interface_pix_fmt(encoder->crtc, - bus_format, hsync_pin, vsync_pin, - bus_flags); - return 0; -} -EXPORT_SYMBOL_GPL(imx_drm_set_bus_config); - -int imx_drm_set_bus_format(struct drm_encoder *encoder, u32 bus_format) -{ - return imx_drm_set_bus_config(encoder, bus_format, 2, 3, - DRM_BUS_FLAG_DE_HIGH | - DRM_BUS_FLAG_PIXDATA_NEGEDGE); -} -EXPORT_SYMBOL_GPL(imx_drm_set_bus_format); - int imx_drm_crtc_vblank_get(struct imx_drm_crtc *imx_drm_crtc) { return drm_crtc_vblank_get(imx_drm_crtc->crtc); @@ -208,6 +174,63 @@ static void imx_drm_output_poll_changed(struct drm_device *drm) static const struct drm_mode_config_funcs imx_drm_mode_config_funcs = { .fb_create = drm_fb_cma_create, .output_poll_changed = imx_drm_output_poll_changed, + .atomic_check = drm_atomic_helper_check, + .atomic_commit = drm_atomic_helper_commit, +}; + +static void imx_drm_atomic_commit_tail(struct drm_atomic_state *state) +{ + struct drm_device *dev = state->dev; + struct drm_crtc *crtc; + struct drm_crtc_state *crtc_state; + struct drm_plane_state *plane_state; + struct drm_gem_cma_object *cma_obj; + struct fence *excl; + unsigned shared_count; + struct fence **shared; + unsigned int i, j; + int ret; + + /* Wait for fences. */ + for_each_crtc_in_state(state, crtc, crtc_state, i) { + plane_state = crtc->primary->state; + if (plane_state->fb) { + cma_obj = drm_fb_cma_get_gem_obj(plane_state->fb, 0); + if (cma_obj->base.dma_buf) { + ret = reservation_object_get_fences_rcu( + cma_obj->base.dma_buf->resv, &excl, + &shared_count, &shared); + if (unlikely(ret)) + DRM_ERROR("failed to get fences " + "for buffer\n"); + + if (excl) { + fence_wait(excl, false); + fence_put(excl); + } + for (j = 0; j < shared_count; i++) { + fence_wait(shared[j], false); + fence_put(shared[j]); + } + } + } + } + + drm_atomic_helper_commit_modeset_disables(dev, state); + + drm_atomic_helper_commit_planes(dev, state, true); + + drm_atomic_helper_commit_modeset_enables(dev, state); + + drm_atomic_helper_commit_hw_done(state); + + drm_atomic_helper_wait_for_vblanks(dev, state); + + drm_atomic_helper_cleanup_planes(dev, state); +} + +static struct drm_mode_config_helper_funcs imx_drm_mode_config_helpers = { + .atomic_commit_tail = imx_drm_atomic_commit_tail, }; /* @@ -249,6 +272,7 @@ static int imx_drm_driver_load(struct drm_device *drm, unsigned long flags) drm->mode_config.max_width = 4096; drm->mode_config.max_height = 4096; drm->mode_config.funcs = &imx_drm_mode_config_funcs; + drm->mode_config.helper_private = &imx_drm_mode_config_helpers; drm_mode_config_init(drm); @@ -279,6 +303,8 @@ static int imx_drm_driver_load(struct drm_device *drm, unsigned long flags) } } + drm_mode_config_reset(drm); + /* * All components are now initialised, so setup the fb helper. * The fb helper takes copies of key hardware information, so the @@ -289,7 +315,6 @@ static int imx_drm_driver_load(struct drm_device *drm, unsigned long flags) dev_warn(drm->dev, "Invalid legacyfb_depth. Defaulting to 16bpp\n"); legacyfb_depth = 16; } - drm_helper_disable_unused_functions(drm); imxdrm->fbhelper = drm_fbdev_cma_init(drm, legacyfb_depth, drm->mode_config.num_crtc, MAX_CRTC); if (IS_ERR(imxdrm->fbhelper)) { @@ -403,7 +428,8 @@ static const struct drm_ioctl_desc imx_drm_ioctls[] = { }; static struct drm_driver imx_drm_driver = { - .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME, + .driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME | + DRIVER_ATOMIC, .load = imx_drm_driver_load, .unload = imx_drm_driver_unload, .lastclose = imx_drm_driver_lastclose, @@ -491,6 +517,7 @@ 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) @@ -498,17 +525,26 @@ static int imx_drm_suspend(struct device *dev) 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; } 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; - drm_helper_resume_force_mode(drm_dev); + imx_drm = drm_dev->dev_private; + drm_atomic_helper_resume(drm_dev, imx_drm->state); drm_kms_helper_poll_enable(drm_dev); return 0; diff --git a/drivers/gpu/drm/imx/imx-drm.h b/drivers/gpu/drm/imx/imx-drm.h index 74320a1723b7..07d33e45f90f 100644 --- a/drivers/gpu/drm/imx/imx-drm.h +++ b/drivers/gpu/drm/imx/imx-drm.h @@ -15,12 +15,22 @@ struct platform_device; unsigned int imx_drm_crtc_id(struct imx_drm_crtc *crtc); +struct imx_crtc_state { + struct drm_crtc_state base; + u32 bus_format; + u32 bus_flags; + int di_hsync_pin; + int di_vsync_pin; +}; + +static inline struct imx_crtc_state *to_imx_crtc_state(struct drm_crtc_state *s) +{ + return container_of(s, struct imx_crtc_state, base); +} + struct imx_drm_crtc_helper_funcs { int (*enable_vblank)(struct drm_crtc *crtc); void (*disable_vblank)(struct drm_crtc *crtc); - int (*set_interface_pix_fmt)(struct drm_crtc *crtc, - u32 bus_format, int hsync_pin, int vsync_pin, - u32 bus_flags); const struct drm_crtc_helper_funcs *crtc_helper_funcs; const struct drm_crtc_funcs *crtc_funcs; }; @@ -42,11 +52,6 @@ void imx_drm_mode_config_init(struct drm_device *drm); struct drm_gem_cma_object *imx_drm_fb_get_obj(struct drm_framebuffer *fb); -int imx_drm_set_bus_config(struct drm_encoder *encoder, u32 bus_format, - int hsync_pin, int vsync_pin, u32 bus_flags); -int imx_drm_set_bus_format(struct drm_encoder *encoder, - u32 bus_format); - int imx_drm_encoder_parse_of(struct drm_device *drm, struct drm_encoder *encoder, struct device_node *np); diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index beff793bb717..b03919ed60ba 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -17,6 +17,8 @@ #include #include #include +#include +#include #include #include #include @@ -49,9 +51,6 @@ #define LDB_DI1_VS_POL_ACT_LOW (1 << 10) #define LDB_BGREF_RMODE_INT (1 << 15) -#define con_to_imx_ldb_ch(x) container_of(x, struct imx_ldb_channel, connector) -#define enc_to_imx_ldb_ch(x) container_of(x, struct imx_ldb_channel, encoder) - struct imx_ldb; struct imx_ldb_channel { @@ -66,9 +65,19 @@ struct imx_ldb_channel { int edid_len; struct drm_display_mode mode; int mode_valid; - int bus_format; + u32 bus_format; }; +static inline struct imx_ldb_channel *con_to_imx_ldb_ch(struct drm_connector *c) +{ + return container_of(c, struct imx_ldb_channel, connector); +} + +static inline struct imx_ldb_channel *enc_to_imx_ldb_ch(struct drm_encoder *e) +{ + return container_of(e, struct imx_ldb_channel, encoder); +} + struct bus_mux { int reg; int shift; @@ -93,6 +102,32 @@ static enum drm_connector_status imx_ldb_connector_detect( return connector_status_connected; } +static void imx_ldb_ch_set_bus_format(struct imx_ldb_channel *imx_ldb_ch, + u32 bus_format) +{ + struct imx_ldb *ldb = imx_ldb_ch->ldb; + int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN; + + switch (bus_format) { + case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG: + break; + case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG: + if (imx_ldb_ch->chno == 0 || dual) + ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH0_24; + if (imx_ldb_ch->chno == 1 || dual) + ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH1_24; + break; + case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA: + if (imx_ldb_ch->chno == 0 || dual) + ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH0_24 | + LDB_BIT_MAP_CH0_JEIDA; + if (imx_ldb_ch->chno == 1 || dual) + ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH1_24 | + LDB_BIT_MAP_CH1_JEIDA; + break; + } +} + static int imx_ldb_connector_get_modes(struct drm_connector *connector) { struct imx_ldb_channel *imx_ldb_ch = con_to_imx_ldb_ch(connector); @@ -100,11 +135,7 @@ static int imx_ldb_connector_get_modes(struct drm_connector *connector) if (imx_ldb_ch->panel && imx_ldb_ch->panel->funcs && imx_ldb_ch->panel->funcs->get_modes) { - struct drm_display_info *di = &connector->display_info; - num_modes = imx_ldb_ch->panel->funcs->get_modes(imx_ldb_ch->panel); - if (!imx_ldb_ch->bus_format && di->num_bus_formats) - imx_ldb_ch->bus_format = di->bus_formats[0]; if (num_modes > 0) return num_modes; } @@ -141,10 +172,6 @@ static struct drm_encoder *imx_ldb_connector_best_encoder( return &imx_ldb_ch->encoder; } -static void imx_ldb_encoder_dpms(struct drm_encoder *encoder, int mode) -{ -} - static void imx_ldb_set_clock(struct imx_ldb *ldb, int mux, int chno, unsigned long serial_clk, unsigned long di_clk) { @@ -173,43 +200,7 @@ static void imx_ldb_set_clock(struct imx_ldb *ldb, int mux, int chno, chno); } -static void imx_ldb_encoder_prepare(struct drm_encoder *encoder) -{ - struct imx_ldb_channel *imx_ldb_ch = enc_to_imx_ldb_ch(encoder); - struct imx_ldb *ldb = imx_ldb_ch->ldb; - int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN; - u32 bus_format; - - switch (imx_ldb_ch->bus_format) { - default: - dev_warn(ldb->dev, - "could not determine data mapping, default to 18-bit \"spwg\"\n"); - /* fallthrough */ - case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG: - bus_format = MEDIA_BUS_FMT_RGB666_1X18; - break; - case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG: - bus_format = MEDIA_BUS_FMT_RGB888_1X24; - if (imx_ldb_ch->chno == 0 || dual) - ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH0_24; - if (imx_ldb_ch->chno == 1 || dual) - ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH1_24; - break; - case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA: - bus_format = MEDIA_BUS_FMT_RGB888_1X24; - if (imx_ldb_ch->chno == 0 || dual) - ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH0_24 | - LDB_BIT_MAP_CH0_JEIDA; - if (imx_ldb_ch->chno == 1 || dual) - ldb->ldb_ctrl |= LDB_DATA_WIDTH_CH1_24 | - LDB_BIT_MAP_CH1_JEIDA; - break; - } - - imx_drm_set_bus_format(encoder, bus_format); -} - -static void imx_ldb_encoder_commit(struct drm_encoder *encoder) +static void imx_ldb_encoder_enable(struct drm_encoder *encoder) { struct imx_ldb_channel *imx_ldb_ch = enc_to_imx_ldb_ch(encoder); struct imx_ldb *ldb = imx_ldb_ch->ldb; @@ -219,8 +210,13 @@ static void imx_ldb_encoder_commit(struct drm_encoder *encoder) drm_panel_prepare(imx_ldb_ch->panel); if (dual) { + clk_set_parent(ldb->clk_sel[mux], ldb->clk[0]); + clk_set_parent(ldb->clk_sel[mux], ldb->clk[1]); + clk_prepare_enable(ldb->clk[0]); clk_prepare_enable(ldb->clk[1]); + } else { + clk_set_parent(ldb->clk_sel[mux], ldb->clk[imx_ldb_ch->chno]); } if (imx_ldb_ch == &ldb->channel[0] || dual) { @@ -265,6 +261,7 @@ static void imx_ldb_encoder_mode_set(struct drm_encoder *encoder, unsigned long serial_clk; unsigned long di_clk = mode->clock * 1000; int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder); + u32 bus_format = imx_ldb_ch->bus_format; if (mode->clock > 170000) { dev_warn(ldb->dev, @@ -286,18 +283,33 @@ static void imx_ldb_encoder_mode_set(struct drm_encoder *encoder, } /* FIXME - assumes straight connections DI0 --> CH0, DI1 --> CH1 */ - if (imx_ldb_ch == &ldb->channel[0]) { + if (imx_ldb_ch == &ldb->channel[0] || dual) { if (mode->flags & DRM_MODE_FLAG_NVSYNC) ldb->ldb_ctrl |= LDB_DI0_VS_POL_ACT_LOW; else if (mode->flags & DRM_MODE_FLAG_PVSYNC) ldb->ldb_ctrl &= ~LDB_DI0_VS_POL_ACT_LOW; } - if (imx_ldb_ch == &ldb->channel[1]) { + if (imx_ldb_ch == &ldb->channel[1] || dual) { if (mode->flags & DRM_MODE_FLAG_NVSYNC) ldb->ldb_ctrl |= LDB_DI1_VS_POL_ACT_LOW; else if (mode->flags & DRM_MODE_FLAG_PVSYNC) ldb->ldb_ctrl &= ~LDB_DI1_VS_POL_ACT_LOW; } + + if (!bus_format) { + struct drm_connector *connector; + + drm_for_each_connector(connector, encoder->dev) { + struct drm_display_info *di = &connector->display_info; + + if (connector->encoder == encoder && + di->num_bus_formats) { + bus_format = di->bus_formats[0]; + break; + } + } + } + imx_ldb_ch_set_bus_format(imx_ldb_ch, bus_format); } static void imx_ldb_encoder_disable(struct drm_encoder *encoder) @@ -357,11 +369,45 @@ static void imx_ldb_encoder_disable(struct drm_encoder *encoder) drm_panel_unprepare(imx_ldb_ch->panel); } +static int imx_ldb_encoder_atomic_check(struct drm_encoder *encoder, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) +{ + struct imx_crtc_state *imx_crtc_state = to_imx_crtc_state(crtc_state); + struct imx_ldb_channel *imx_ldb_ch = enc_to_imx_ldb_ch(encoder); + struct drm_display_info *di = &conn_state->connector->display_info; + u32 bus_format = imx_ldb_ch->bus_format; + + /* Bus format description in DT overrides connector display info. */ + if (!bus_format && di->num_bus_formats) + bus_format = di->bus_formats[0]; + switch (bus_format) { + case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG: + imx_crtc_state->bus_format = MEDIA_BUS_FMT_RGB666_1X18; + break; + case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG: + case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA: + imx_crtc_state->bus_format = MEDIA_BUS_FMT_RGB888_1X24; + break; + default: + return -EINVAL; + } + + imx_crtc_state->di_hsync_pin = 2; + imx_crtc_state->di_vsync_pin = 3; + + return 0; +} + + static const struct drm_connector_funcs imx_ldb_connector_funcs = { - .dpms = drm_helper_connector_dpms, + .dpms = drm_atomic_helper_connector_dpms, .fill_modes = drm_helper_probe_single_connector_modes, .detect = imx_ldb_connector_detect, .destroy = imx_drm_connector_destroy, + .reset = drm_atomic_helper_connector_reset, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; static const struct drm_connector_helper_funcs imx_ldb_connector_helper_funcs = { @@ -374,11 +420,10 @@ static const struct drm_encoder_funcs imx_ldb_encoder_funcs = { }; static const struct drm_encoder_helper_funcs imx_ldb_encoder_helper_funcs = { - .dpms = imx_ldb_encoder_dpms, - .prepare = imx_ldb_encoder_prepare, - .commit = imx_ldb_encoder_commit, .mode_set = imx_ldb_encoder_mode_set, + .enable = imx_ldb_encoder_enable, .disable = imx_ldb_encoder_disable, + .atomic_check = imx_ldb_encoder_atomic_check, }; static int imx_ldb_get_clk(struct imx_ldb *ldb, int chno) @@ -400,10 +445,10 @@ static int imx_ldb_register(struct drm_device *drm, struct imx_ldb_channel *imx_ldb_ch) { struct imx_ldb *ldb = imx_ldb_ch->ldb; + struct drm_encoder *encoder = &imx_ldb_ch->encoder; int ret; - ret = imx_drm_encoder_parse_of(drm, &imx_ldb_ch->encoder, - imx_ldb_ch->child); + ret = imx_drm_encoder_parse_of(drm, encoder, imx_ldb_ch->child); if (ret) return ret; @@ -417,9 +462,8 @@ static int imx_ldb_register(struct drm_device *drm, return ret; } - drm_encoder_helper_add(&imx_ldb_ch->encoder, - &imx_ldb_encoder_helper_funcs); - drm_encoder_init(drm, &imx_ldb_ch->encoder, &imx_ldb_encoder_funcs, + drm_encoder_helper_add(encoder, &imx_ldb_encoder_helper_funcs); + drm_encoder_init(drm, encoder, &imx_ldb_encoder_funcs, DRM_MODE_ENCODER_LVDS, NULL); drm_connector_helper_add(&imx_ldb_ch->connector, @@ -427,11 +471,14 @@ static int imx_ldb_register(struct drm_device *drm, drm_connector_init(drm, &imx_ldb_ch->connector, &imx_ldb_connector_funcs, DRM_MODE_CONNECTOR_LVDS); - if (imx_ldb_ch->panel) - drm_panel_attach(imx_ldb_ch->panel, &imx_ldb_ch->connector); + if (imx_ldb_ch->panel) { + ret = drm_panel_attach(imx_ldb_ch->panel, + &imx_ldb_ch->connector); + if (ret) + return ret; + } - drm_mode_connector_attach_encoder(&imx_ldb_ch->connector, - &imx_ldb_ch->encoder); + drm_mode_connector_attach_encoder(&imx_ldb_ch->connector, encoder); return 0; } @@ -560,6 +607,7 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) struct imx_ldb_channel *channel; struct device_node *ddc_node; struct device_node *ep; + int bus_format; ret = of_property_read_u32(child, "reg", &i); if (ret || i < 0 || i > 1) @@ -632,21 +680,22 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) } } - channel->bus_format = of_get_bus_format(dev, child); - if (channel->bus_format == -EINVAL) { + bus_format = of_get_bus_format(dev, child); + if (bus_format == -EINVAL) { /* * If no bus format was specified in the device tree, * we can still get it from the connected panel later. */ if (channel->panel && channel->panel->funcs && channel->panel->funcs->get_modes) - channel->bus_format = 0; + bus_format = 0; } - if (channel->bus_format < 0) { + if (bus_format < 0) { dev_err(dev, "could not determine data mapping: %d\n", - channel->bus_format); - return channel->bus_format; + bus_format); + return bus_format; } + channel->bus_format = bus_format; ret = imx_ldb_register(drm, channel); if (ret) diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c index baf788121287..5e875944ffa2 100644 --- a/drivers/gpu/drm/imx/imx-tve.c +++ b/drivers/gpu/drm/imx/imx-tve.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include