diff options
653 files changed, 14127 insertions, 7862 deletions
@@ -391,6 +391,10 @@ Uwe Kleine-König <ukleinek@strlen.de> Uwe Kleine-König <ukl@pengutronix.de> Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com> Valdis Kletnieks <Valdis.Kletnieks@vt.edu> +Vasily Averin <vasily.averin@linux.dev> <vvs@virtuozzo.com> +Vasily Averin <vasily.averin@linux.dev> <vvs@openvz.org> +Vasily Averin <vasily.averin@linux.dev> <vvs@parallels.com> +Vasily Averin <vasily.averin@linux.dev> <vvs@sw.ru> Vinod Koul <vkoul@kernel.org> <vinod.koul@intel.com> Vinod Koul <vkoul@kernel.org> <vinod.koul@linux.intel.com> Vinod Koul <vkoul@kernel.org> <vkoul@infradead.org> diff --git a/Documentation/dev-tools/kunit/start.rst b/Documentation/dev-tools/kunit/start.rst index ad168d16968f..867a4bba6bf6 100644 --- a/Documentation/dev-tools/kunit/start.rst +++ b/Documentation/dev-tools/kunit/start.rst @@ -41,13 +41,18 @@ or ``VFAT_FS``. To run ``FAT_KUNIT_TEST``, the ``.kunitconfig`` has: CONFIG_MSDOS_FS=y CONFIG_FAT_KUNIT_TEST=y -1. A good starting point for the ``.kunitconfig``, is the KUnit default - config. Run the command: +1. A good starting point for the ``.kunitconfig`` is the KUnit default config. + You can generate it by running: .. code-block:: bash cd $PATH_TO_LINUX_REPO - cp tools/testing/kunit/configs/default.config .kunitconfig + tools/testing/kunit/kunit.py config + cat .kunit/.kunitconfig + +.. note :: + ``.kunitconfig`` lives in the ``--build_dir`` used by kunit.py, which is + ``.kunit`` by default. .. note :: You may want to remove CONFIG_KUNIT_ALL_TESTS from the ``.kunitconfig`` as diff --git a/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml b/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml index 62c3bd4cb28d..4f0b7c71313c 100644 --- a/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml +++ b/Documentation/devicetree/bindings/display/bridge/chipone,icn6211.yaml @@ -41,17 +41,32 @@ properties: properties: port@0: - $ref: /schemas/graph.yaml#/properties/port + $ref: /schemas/graph.yaml#/$defs/port-base + unevaluatedProperties: false description: Video port for MIPI DSI input + properties: + endpoint: + $ref: /schemas/media/video-interfaces.yaml# + unevaluatedProperties: false + + properties: + data-lanes: + description: array of physical DSI data lane indexes. + minItems: 1 + items: + - const: 1 + - const: 2 + - const: 3 + - const: 4 + port@1: $ref: /schemas/graph.yaml#/properties/port description: Video port for MIPI DPI output (panel or connector). required: - - port@0 - port@1 required: diff --git a/Documentation/devicetree/bindings/display/bridge/ite,it66121.yaml b/Documentation/devicetree/bindings/display/bridge/ite,it66121.yaml index 6ec1d5fbb8bc..c6e81f532215 100644 --- a/Documentation/devicetree/bindings/display/bridge/ite,it66121.yaml +++ b/Documentation/devicetree/bindings/display/bridge/ite,it66121.yaml @@ -38,6 +38,9 @@ properties: interrupts: maxItems: 1 + "#sound-dai-cells": + const: 0 + ports: $ref: /schemas/graph.yaml#/properties/ports diff --git a/Documentation/devicetree/bindings/display/bridge/lontium,lt9211.yaml b/Documentation/devicetree/bindings/display/bridge/lontium,lt9211.yaml new file mode 100644 index 000000000000..9a6e9b25d14a --- /dev/null +++ b/Documentation/devicetree/bindings/display/bridge/lontium,lt9211.yaml @@ -0,0 +1,117 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/bridge/lontium,lt9211.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Lontium LT9211 DSI/LVDS/DPI to DSI/LVDS/DPI bridge. + +maintainers: + - Marek Vasut <marex@denx.de> + +description: | + The LT9211 are bridge devices which convert Single/Dual-Link DSI/LVDS + or Single DPI to Single/Dual-Link DSI/LVDS or Single DPI. + +properties: + compatible: + enum: + - lontium,lt9211 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + reset-gpios: + maxItems: 1 + description: GPIO connected to active high RESET pin. + + vccio-supply: + description: Regulator for 1.8V IO power. + + ports: + $ref: /schemas/graph.yaml#/properties/ports + + properties: + port@0: + $ref: /schemas/graph.yaml#/properties/port + description: + Primary MIPI DSI port-1 for MIPI input or + LVDS port-1 for LVDS input or DPI input. + + port@1: + $ref: /schemas/graph.yaml#/properties/port + description: + Additional MIPI port-2 for MIPI input or LVDS port-2 + for LVDS input. Used in combination with primary + port-1 to drive higher resolution displays + + port@2: + $ref: /schemas/graph.yaml#/properties/port + description: + Primary MIPI DSI port-1 for MIPI output or + LVDS port-1 for LVDS output or DPI output. + + port@3: + $ref: /schemas/graph.yaml#/properties/port + description: + Additional MIPI port-2 for MIPI output or LVDS port-2 + for LVDS output. Used in combination with primary + port-1 to drive higher resolution displays. + + required: + - port@0 + - port@2 + +required: + - compatible + - reg + - vccio-supply + - ports + +additionalProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + #include <dt-bindings/interrupt-controller/irq.h> + + i2c { + #address-cells = <1>; + #size-cells = <0>; + + hdmi-bridge@3b { + compatible = "lontium,lt9211"; + reg = <0x3b>; + + reset-gpios = <&tlmm 128 GPIO_ACTIVE_HIGH>; + interrupts-extended = <&tlmm 84 IRQ_TYPE_EDGE_FALLING>; + + vccio-supply = <<9211_1v8>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + endpoint { + remote-endpoint = <&dsi0_out>; + }; + }; + + port@2 { + reg = <2>; + + endpoint { + remote-endpoint = <&panel_in_lvds>; + }; + }; + }; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml index 5216c27fc0ad..a412a1da950f 100644 --- a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml +++ b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358762.yaml @@ -39,7 +39,6 @@ properties: Video port for MIPI DPI output (panel or connector). required: - - port@0 - port@1 required: diff --git a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.yaml b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.yaml index f1541cc05297..ed280053ec62 100644 --- a/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.yaml +++ b/Documentation/devicetree/bindings/display/bridge/toshiba,tc358767.yaml @@ -53,16 +53,32 @@ properties: properties: port@0: - $ref: /schemas/graph.yaml#/properties/port + $ref: /schemas/graph.yaml#/$defs/port-base + unevaluatedProperties: false description: | DSI input port. The remote endpoint phandle should be a reference to a valid DSI output endpoint node + properties: + endpoint: + $ref: /schemas/media/video-interfaces.yaml# + unevaluatedProperties: false + + properties: + data-lanes: + description: array of physical DSI data lane indexes. + minItems: 1 + items: + - const: 1 + - const: 2 + - const: 3 + - const: 4 + port@1: $ref: /schemas/graph.yaml#/properties/port description: | - DPI input port. The remote endpoint phandle should be a - reference to a valid DPI output endpoint node + DPI input/output port. The remote endpoint phandle should be a + reference to a valid DPI output or input endpoint node. port@2: $ref: /schemas/graph.yaml#/properties/port diff --git a/Documentation/devicetree/bindings/display/panel/leadtek,ltk035c5444t.yaml b/Documentation/devicetree/bindings/display/panel/leadtek,ltk035c5444t.yaml new file mode 100644 index 000000000000..817a9bed7d5a --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/leadtek,ltk035c5444t.yaml @@ -0,0 +1,59 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/leadtek,ltk035c5444t.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Leadtek ltk035c5444t 3.5" (640x480 pixels) 24-bit IPS LCD panel + +maintainers: + - Paul Cercueil <paul@crapouillou.net> + - Christophe Branchereau <cbranchereau@gmail.com> + +allOf: + - $ref: panel-common.yaml# + - $ref: /schemas/spi/spi-peripheral-props.yaml# + +properties: + compatible: + const: leadtek,ltk035c5444t + + backlight: true + port: true + power-supply: true + reg: true + reset-gpios: true + +required: + - compatible + - power-supply + - reset-gpios + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + + spi { + #address-cells = <1>; + #size-cells = <0>; + panel@0 { + compatible = "leadtek,ltk035c5444t"; + reg = <0>; + + spi-3wire; + spi-max-frequency = <3125000>; + + reset-gpios = <&gpe 2 GPIO_ACTIVE_LOW>; + + backlight = <&backlight>; + power-supply = <&vcc>; + + port { + panel_input: endpoint { + remote-endpoint = <&panel_output>; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml b/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml index f29789994b18..c2df8d28aaf5 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-mipi-dbi-spi.yaml @@ -83,6 +83,8 @@ properties: required: - compatible - reg + - width-mm + - height-mm - panel-timing unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/display/sitronix,st7735r.yaml b/Documentation/devicetree/bindings/display/sitronix,st7735r.yaml index 0cebaaefda03..157b1a7b18f9 100644 --- a/Documentation/devicetree/bindings/display/sitronix,st7735r.yaml +++ b/Documentation/devicetree/bindings/display/sitronix,st7735r.yaml @@ -32,15 +32,13 @@ properties: - okaya,rh128128t - const: sitronix,st7715r - spi-max-frequency: - maximum: 32000000 - dc-gpios: maxItems: 1 description: Display data/command selection (D/CX) backlight: true reg: true + spi-max-frequency: true reset-gpios: true rotation: true @@ -48,7 +46,6 @@ required: - compatible - reg - dc-gpios - - reset-gpios additionalProperties: false @@ -72,6 +69,7 @@ examples: dc-gpios = <&gpio 43 GPIO_ACTIVE_HIGH>; reset-gpios = <&gpio 80 GPIO_ACTIVE_HIGH>; rotation = <270>; + backlight = <&backlight>; }; }; diff --git a/Documentation/devicetree/bindings/display/solomon,ssd1307fb.yaml b/Documentation/devicetree/bindings/display/solomon,ssd1307fb.yaml index 9baafd0c42dd..3fbd87c2c120 100644 --- a/Documentation/devicetree/bindings/display/solomon,ssd1307fb.yaml +++ b/Documentation/devicetree/bindings/display/solomon,ssd1307fb.yaml @@ -12,11 +12,22 @@ maintainers: properties: compatible: - enum: - - solomon,ssd1305fb-i2c - - solomon,ssd1306fb-i2c - - solomon,ssd1307fb-i2c - - solomon,ssd1309fb-i2c + oneOf: + # Deprecated compatible strings + - items: + - enum: + - solomon,ssd1305fb-i2c + - solomon,ssd1306fb-i2c + - solomon,ssd1307fb-i2c + - solomon,ssd1309fb-i2c + deprecated: true + - items: + - enum: + - sinowealth,sh1106 + - solomon,ssd1305 + - solomon,ssd1306 + - solomon,ssd1307 + - solomon,ssd1309 reg: maxItems: 1 @@ -27,9 +38,20 @@ properties: reset-gpios: maxItems: 1 + # Only required for SPI + dc-gpios: + description: + GPIO connected to the controller's D/C# (Data/Command) pin, + that is needed for 4-wire SPI to tell the controller if the + data sent is for a command register or the display data RAM + maxItems: 1 + vbat-supply: description: The supply for VBAT + # Only required for SPI + spi-max-frequency: true + solomon,height: $ref: /schemas/types.yaml#/definitions/uint32 default: 16 @@ -135,7 +157,21 @@ allOf: properties: compatible: contains: - const: solomon,ssd1305fb-i2c + const: sinowealth,sh1106 + then: + properties: + solomon,dclk-div: + default: 1 + solomon,dclk-frq: + default: 5 + + - if: + properties: + compatible: + contains: + enum: + - solomon,ssd1305-i2c + - solomon,ssd1305 then: properties: solomon,dclk-div: @@ -147,7 +183,9 @@ allOf: properties: compatible: contains: - const: solomon,ssd1306fb-i2c + enum: + - solomon,ssd1306-i2c + - solomon,ssd1306 then: properties: solomon,dclk-div: @@ -159,7 +197,9 @@ allOf: properties: compatible: contains: - const: solomon,ssd1307fb-i2c + enum: + - solomon,ssd1307-i2c + - solomon,ssd1307 then: properties: solomon,dclk-div: @@ -173,7 +213,9 @@ allOf: properties: compatible: contains: - const: solomon,ssd1309fb-i2c + enum: + - solomon,ssd1309-i2c + - solomon,ssd1309 then: properties: solomon,dclk-div: @@ -189,15 +231,15 @@ examples: #address-cells = <1>; #size-cells = <0>; - ssd1307: oled@3c { - compatible = "solomon,ssd1307fb-i2c"; + ssd1307_i2c: oled@3c { + compatible = "solomon,ssd1307"; reg = <0x3c>; pwms = <&pwm 4 3000>; reset-gpios = <&gpio2 7>; }; - ssd1306: oled@3d { - compatible = "solomon,ssd1306fb-i2c"; + ssd1306_i2c: oled@3d { + compatible = "solomon,ssd1306"; reg = <0x3c>; pwms = <&pwm 4 3000>; reset-gpios = <&gpio2 7>; @@ -207,3 +249,30 @@ examples: solomon,lookup-table = /bits/ 8 <0x3f 0x3f 0x3f 0x3f>; }; }; + - | + spi { + #address-cells = <1>; + #size-cells = <0>; + + ssd1307_spi: oled@0 { + compatible = "solomon,ssd1307"; + reg = <0x0>; + pwms = <&pwm 4 3000>; + reset-gpios = <&gpio2 7>; + dc-gpios = <&gpio2 8>; + spi-max-frequency = <10000000>; + }; + + ssd1306_spi: oled@1 { + compatible = "solomon,ssd1306"; + reg = <0x1>; + pwms = <&pwm 4 3000>; + reset-gpios = <&gpio2 7>; + dc-gpios = <&gpio2 8>; + spi-max-frequency = <10000000>; + solomon,com-lrremap; + solomon,com-invdir; + solomon,com-offset = <32>; + solomon,lookup-table = /bits/ 8 <0x3f 0x3f 0x3f 0x3f>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index 817794e56227..4f15463611f8 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -106,6 +106,12 @@ properties: phy-mode: $ref: "#/properties/phy-connection-type" + pcs-handle: + $ref: /schemas/types.yaml#/definitions/phandle + description: + Specifies a reference to a node representing a PCS PHY device on a MDIO + bus to link with an external PHY (phy-handle) if exists. + phy-handle: $ref: /schemas/types.yaml#/definitions/phandle description: diff --git a/Documentation/devicetree/bindings/net/micrel.txt b/Documentation/devicetree/bindings/net/micrel.txt index c5ab62c39133..8d157f0295a5 100644 --- a/Documentation/devicetree/bindings/net/micrel.txt +++ b/Documentation/devicetree/bindings/net/micrel.txt @@ -45,20 +45,3 @@ Optional properties: In fiber mode, auto-negotiation is disabled and the PHY can only work in 100base-fx (full and half duplex) modes. - - - lan8814,ignore-ts: If present the PHY will not support timestamping. - - This option acts as check whether Timestamping is supported by - hardware or not. LAN8814 phy support hardware tmestamping. - - - lan8814,latency_rx_10: Configures Latency value of phy in ingress at 10 Mbps. - - - lan8814,latency_tx_10: Configures Latency value of phy in egress at 10 Mbps. - - - lan8814,latency_rx_100: Configures Latency value of phy in ingress at 100 Mbps. - - - lan8814,latency_tx_100: Configures Latency value of phy in egress at 100 Mbps. - - - lan8814,latency_rx_1000: Configures Latency value of phy in ingress at 1000 Mbps. - - - lan8814,latency_tx_1000: Configures Latency value of phy in egress at 1000 Mbps. diff --git a/Documentation/devicetree/bindings/net/xilinx_axienet.txt b/Documentation/devicetree/bindings/net/xilinx_axienet.txt index b8e4894bc634..1aa4c6006cd0 100644 --- a/Documentation/devicetree/bindings/net/xilinx_axienet.txt +++ b/Documentation/devicetree/bindings/net/xilinx_axienet.txt @@ -26,7 +26,8 @@ Required properties: specified, the TX/RX DMA interrupts should be on that node instead, and only the Ethernet core interrupt is optionally specified here. -- phy-handle : Should point to the external phy device. +- phy-handle : Should point to the external phy device if exists. Pointing + this to the PCS/PMA PHY is deprecated and should be avoided. See ethernet.txt file in the same directory. - xlnx,rxmem : Set to allocated memory buffer for Rx/Tx in the hardware @@ -68,6 +69,11 @@ Optional properties: required through the core's MDIO interface (i.e. always, unless the PHY is accessed through a different bus). + - pcs-handle: Phandle to the internal PCS/PMA PHY in SGMII or 1000Base-X + modes, where "pcs-handle" should be used to point + to the PCS/PMA PHY, and "phy-handle" should point to an + external PHY if exists. + Example: axi_ethernet_eth: ethernet@40c00000 { compatible = "xlnx,axi-ethernet-1.00.a"; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 01430973ecec..79b72e370ade 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -1130,6 +1130,8 @@ patternProperties: description: Sinlinx Electronics Technology Co., LTD "^sinovoip,.*": description: SinoVoip Co., Ltd + "^sinowealth,.*": + description: SINO WEALTH Electronic Ltd. "^sipeed,.*": description: Shenzhen Sipeed Technology Co., Ltd. "^sirf,.*": diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst index 55006678394a..36a76cbe9095 100644 --- a/Documentation/driver-api/dma-buf.rst +++ b/Documentation/driver-api/dma-buf.rst @@ -185,6 +185,12 @@ DMA Fence Chain .. kernel-doc:: include/linux/dma-fence-chain.h :internal: +DMA Fence unwrap +~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/linux/dma-fence-unwrap.h + :internal: + DMA Fence uABI/Sync File ~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst index 198bcc1affa1..f32ccce5722d 100644 --- a/Documentation/gpu/drm-mm.rst +++ b/Documentation/gpu/drm-mm.rst @@ -466,6 +466,15 @@ DRM MM Range Allocator Function References .. kernel-doc:: drivers/gpu/drm/drm_mm.c :export: +DRM Buddy Allocator +=================== + +DRM Buddy Function References +----------------------------- + +.. kernel-doc:: drivers/gpu/drm/drm_buddy.c + :export: + DRM Cache Handling and Fast WC memcpy() ======================================= diff --git a/Documentation/gpu/drm-uapi.rst b/Documentation/gpu/drm-uapi.rst index 199afb503ab1..ce47b4292481 100644 --- a/Documentation/gpu/drm-uapi.rst +++ b/Documentation/gpu/drm-uapi.rst @@ -148,7 +148,9 @@ clients together with the legacy drmAuth authentication procedure. If a driver advertises render node support, DRM core will create a separate render node called renderD<num>. There will be one render node per device. No ioctls except PRIME-related ioctls will be allowed on -this node. Especially GEM_OPEN will be explicitly prohibited. Render +this node. Especially GEM_OPEN will be explicitly prohibited. For a +complete list of driver-independent ioctls that can be used on render +nodes, see the ioctls marked DRM_RENDER_ALLOW in drm_ioctl.c Render nodes are designed to avoid the buffer-leaks, which occur if clients guess the flink names or mmap offsets on the legacy interface. Additionally to this basic interface, drivers must mark their diff --git a/Documentation/networking/dsa/dsa.rst b/Documentation/networking/dsa/dsa.rst index 89bb4fa4c362..ddc1dd039337 100644 --- a/Documentation/networking/dsa/dsa.rst +++ b/Documentation/networking/dsa/dsa.rst @@ -10,21 +10,21 @@ in joining the effort. Design principles ================= -The Distributed Switch Architecture is a subsystem which was primarily designed -to support Marvell Ethernet switches (MV88E6xxx, a.k.a Linkstreet product line) -using Linux, but has since evolved to support other vendors as well. +The Distributed Switch Architecture subsystem was primarily designed to +support Marvell Ethernet switches (MV88E6xxx, a.k.a. Link Street product +line) using Linux, but has since evolved to support other vendors as well. The original philosophy behind this design was to be able to use unmodified Linux tools such as bridge, iproute2, ifconfig to work transparently whether they configured/queried a switch port network device or a regular network device. -An Ethernet switch is typically comprised of multiple front-panel ports, and one -or more CPU or management port. The DSA subsystem currently relies on the +An Ethernet switch typically comprises multiple front-panel ports and one +or more CPU or management ports. The DSA subsystem currently relies on the presence of a management port connected to an Ethernet controller capable of receiving Ethernet frames from the switch. This is a very common setup for all kinds of Ethernet switches found in Small Home and Office products: routers, -gateways, or even top-of-the rack switches. This host Ethernet controller will +gateways, or even top-of-rack switches. This host Ethernet controller will be later referred to as "master" and "cpu" in DSA terminology and code. The D in DSA stands for Distributed, because the subsystem has been designed @@ -33,14 +33,14 @@ using upstream and downstream Ethernet links between switches. These specific ports are referred to as "dsa" ports in DSA terminology and code. A collection of multiple switches connected to each other is called a "switch tree". -For each front-panel port, DSA will create specialized network devices which are +For each front-panel port, DSA creates specialized network devices which are used as controlling and data-flowing endpoints for use by the Linux networking stack. These specialized network interfaces are referred to as "slave" network interfaces in DSA terminology and code. The ideal case for using DSA is when an Ethernet switch supports a "switch tag" which is a hardware feature making the switch insert a specific tag for each -Ethernet frames it received to/from specific ports to help the management +Ethernet frame it receives to/from specific ports to help the management interface figure out: - what port is this frame coming from @@ -125,7 +125,7 @@ other switches from the same fabric, and in this case, the outermost switch ports must decapsulate the packet. Note that in certain cases, it might be the case that the tagging format used -by a leaf switch (not connected directly to the CPU) to not be the same as what +by a leaf switch (not connected directly to the CPU) is not the same as what the network stack sees. This can be seen with Marvell switch trees, where the CPU port can be configured to use either the DSA or the Ethertype DSA (EDSA) format, but the DSA links are configured to use the shorter (without Ethertype) @@ -270,21 +270,21 @@ These interfaces are specialized in order to: to/from specific switch ports - query the switch for ethtool operations: statistics, link state, Wake-on-LAN, register dumps... -- external/internal PHY management: link, auto-negotiation etc. +- manage external/internal PHY: link, auto-negotiation, etc. These slave network devices have custom net_device_ops and ethtool_ops function pointers which allow DSA to introduce a level of layering between the networking -stack/ethtool, and the switch driver implementation. +stack/ethtool and the switch driver implementation. Upon frame transmission from these slave network devices, DSA will look up which -switch tagging protocol is currently registered with these network devices, and +switch tagging protocol is currently registered with these network devices and invoke a specific transmit routine which takes care of adding the relevant switch tag in the Ethernet frames. These frames are then queued for transmission using the master network device -``ndo_start_xmit()`` function, since they contain the appropriate switch tag, the +``ndo_start_xmit()`` function. Since they contain the appropriate switch tag, the Ethernet switch will be able to process these incoming frames from the -management interface and delivers these frames to the physical switch port. +management interface and deliver them to the physical switch port. Graphical representation ------------------------ @@ -330,9 +330,9 @@ MDIO reads/writes towards specific PHY addresses. In most MDIO-connected switches, these functions would utilize direct or indirect PHY addressing mode to return standard MII registers from the switch builtin PHYs, allowing the PHY library and/or to return link status, link partner pages, auto-negotiation -results etc.. +results, etc. -For Ethernet switches which have both external and internal MDIO busses, the +For Ethernet switches which have both external and internal MDIO buses, the slave MII bus can be utilized to mux/demux MDIO reads and writes towards either internal or external MDIO devices this switch might be connected to: internal PHYs, external PHYs, or even external switches. @@ -349,7 +349,7 @@ DSA data structures are defined in ``include/net/dsa.h`` as well as table indication (when cascading switches) - ``dsa_platform_data``: platform device configuration data which can reference - a collection of dsa_chip_data structure if multiples switches are cascaded, + a collection of dsa_chip_data structures if multiple switches are cascaded, the master network device this switch tree is attached to needs to be referenced @@ -426,7 +426,7 @@ logic basically looks like this: "phy-handle" property, if found, this PHY device is created and registered using ``of_phy_connect()`` -- if Device Tree is used, and the PHY device is "fixed", that is, conforms to +- if Device Tree is used and the PHY device is "fixed", that is, conforms to the definition of a non-MDIO managed PHY as defined in ``Documentation/devicetree/bindings/net/fixed-link.txt``, the PHY is registered and connected transparently using the special fixed MDIO bus driver @@ -481,7 +481,7 @@ Device Tree DSA features a standardized binding which is documented in ``Documentation/devicetree/bindings/net/dsa/dsa.txt``. PHY/MDIO library helper functions such as ``of_get_phy_mode()``, ``of_phy_connect()`` are also used to query -per-port PHY specific details: interface connection, MDIO bus location etc.. +per-port PHY specific details: interface connection, MDIO bus location, etc. Driver development ================== @@ -509,7 +509,7 @@ Switch configuration - ``setup``: setup function for the switch, this function is responsible for setting up the ``dsa_switch_ops`` private structure with all it needs: register maps, - interrupts, mutexes, locks etc.. This function is also expected to properly + interrupts, mutexes, locks, etc. This function is also expected to properly configure the switch to separate all network interfaces from each other, that is, they should be isolated by the switch hardware itself, typically by creating a Port-based VLAN ID for each port and allowing only the CPU port and the @@ -526,13 +526,13 @@ PHY devices and link management - ``get_phy_flags``: Some switches are interfaced to various kinds of Ethernet PHYs, if the PHY library PHY driver needs to know about information it cannot obtain on its own (e.g.: coming from switch memory mapped registers), this function - should return a 32-bits bitmask of "flags", that is private between the switch + should return a 32-bit bitmask of "flags" that is private between the switch driver and the Ethernet PHY driver in ``drivers/net/phy/\*``. - ``phy_read``: Function invoked by the DSA slave MDIO bus when attempting to read the switch port MDIO registers. If unavailable, return 0xffff for each read. For builtin switch Ethernet PHYs, this function should allow reading the link - status, auto-negotiation results, link partner pages etc.. + status, auto-negotiation results, link partner pages, etc. - ``phy_write``: Function invoked by the DSA slave MDIO bus when attempting to write to the switch port MDIO registers. If unavailable return a negative error @@ -554,7 +554,7 @@ Ethtool operations ------------------ - ``get_strings``: ethtool function used to query the driver's strings, will - typically return statistics strings, private flags strings etc. + typically return statistics strings, private flags strings, etc. - ``get_ethtool_stats``: ethtool function used to query per-port statistics and return their values. DSA overlays slave network devices general statistics: @@ -564,7 +564,7 @@ Ethtool operations - ``get_sset_count``: ethtool function used to query the number of statistics items - ``get_wol``: ethtool function used to obtain Wake-on-LAN settings per-port, this - function may, for certain implementations also query the master network device + function may for certain implementations also query the master network device Wake-on-LAN settings if this interface needs to participate in Wake-on-LAN - ``set_wol``: ethtool function used to configure Wake-on-LAN settings per-port, @@ -607,14 +607,14 @@ Power management in a fully active state - ``port_enable``: function invoked by the DSA slave network device ndo_open - function when a port is administratively brought up, this function should be - fully enabling a given switch port. DSA takes care of marking the port with + function when a port is administratively brought up, this function should + fully enable a given switch port. DSA takes care of marking the port with ``BR_STATE_BLOCKING`` if the port is a bridge member, or ``BR_STATE_FORWARDING`` if it was not, and propagating these changes down to the hardware - ``port_disable``: function invoked by the DSA slave network device ndo_close - function when a port is administratively brought down, this function should be - fully disabling a given switch port. DSA takes care of marking the port with + function when a port is administratively brought down, this function should + fully disable a given switch port. DSA takes care of marking the port with ``BR_STATE_DISABLED`` and propagating changes to the hardware if this port is disabled while being a bridge member @@ -622,12 +622,12 @@ Bridge layer ------------ - ``port_bridge_join``: bridge layer function invoked when a given switch port is - added to a bridge, this function should be doing the necessary at the switch - level to permit the joining port from being added to the relevant logical + added to a bridge, this function should do what's necessary at the switch + level to permit the joining port to be added to the relevant logical domain for it to ingress/egress traffic with other members of the bridge. - ``port_bridge_leave``: bridge layer function invoked when a given switch port is - removed from a bridge, this function should be doing the necessary at the + removed from a bridge, this function should do what's necessary at the switch level to deny the leaving port from ingress/egress traffic from the remaining bridge members. When the port leaves the bridge, it should be aged out at the switch hardware for the switch to (re) learn MAC addresses behind @@ -663,7 +663,7 @@ Bridge layer point for drivers that need to configure the hardware for enabling this feature. -- ``port_bridge_tx_fwd_unoffload``: bridge layer function invoken when a driver +- ``port_bridge_tx_fwd_unoffload``: bridge layer function invoked when a driver leaves a bridge port which had the TX forwarding offload feature enabled. Bridge VLAN filtering diff --git a/MAINTAINERS b/MAINTAINERS index fd768d43e048..9b2b0dc44506 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4791,6 +4791,7 @@ F: .clang-format CLANG/LLVM BUILD SUPPORT M: Nathan Chancellor <nathan@kernel.org> M: Nick Desaulniers <ndesaulniers@google.com> +R: Tom Rix <trix@redhat.com> L: llvm@lists.linux.dev S: Supported W: https://clangbuiltlinux.github.io/ @@ -5715,7 +5716,7 @@ W: http://lanana.org/docs/device-list/index.html DEVICE RESOURCE MANAGEMENT HELPERS M: Hans de Goede <hdegoede@redhat.com> -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Maintained F: include/linux/devm-helpers.h @@ -6307,6 +6308,11 @@ S: Maintained F: Documentation/devicetree/bindings/display/panel/olimex,lcd-olinuxino.yaml F: drivers/gpu/drm/panel/panel-olimex-lcd-olinuxino.c +DRM DRIVER FOR PARADE PS8640 BRIDGE CHIP +R: Douglas Anderson <dianders@chromium.org> +F: Documentation/devicetree/bindings/display/bridge/ps8640.yaml +F: drivers/gpu/drm/bridge/parade-ps8640.c + DRM DRIVER FOR PERVASIVE DISPLAYS REPAPER PANELS M: Noralf Trønnes <noralf@tronnes.org> S: Maintained @@ -6420,6 +6426,11 @@ DRM DRIVER FOR TDFX VIDEO CARDS S: Orphan / Obsolete F: drivers/gpu/drm/tdfx/ +DRM DRIVER FOR TI SN65DSI86 BRIDGE CHIP +R: Douglas Anderson <dianders@chromium.org> +F: Documentation/devicetree/bindings/display/bridge/ti,sn65dsi86.yaml +F: drivers/gpu/drm/bridge/ti-sn65dsi86.c + DRM DRIVER FOR TPO TPG110 PANELS M: Linus Walleij <linus.walleij@linaro.org> S: Maintained @@ -6539,6 +6550,7 @@ R: Jonas Karlman <jonas@kwiboo.se> R: Jernej Skrabec <jernej.skrabec@gmail.com> S: Maintained T: git git://anongit.freedesktop.org/drm/drm-misc +F: Documentation/devicetree/bindings/display/bridge/ F: drivers/gpu/drm/bridge/ DRM DRIVERS FOR EXYNOS @@ -8675,7 +8687,6 @@ F: include/linux/cciss*.h F: include/uapi/linux/cciss*.h HFI1 DRIVER -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported @@ -9598,6 +9609,7 @@ F: drivers/iio/pressure/dps310.c INFINIBAND SUBSYSTEM M: Jason Gunthorpe <jgg@nvidia.com> +M: Leon Romanovsky <leonro@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported W: https://github.com/linux-rdma/rdma-core @@ -11208,7 +11220,7 @@ F: scripts/spdxcheck.py LINEAR RANGES HELPERS M: Mark Brown <broonie@kernel.org> -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> F: lib/linear_ranges.c F: lib/test_linear_ranges.c F: include/linux/linear_range.h @@ -14656,7 +14668,6 @@ F: drivers/rtc/rtc-optee.c OPA-VNIC DRIVER M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/ulp/opa_vnic @@ -16098,7 +16109,6 @@ F: include/uapi/linux/qemu_fw_cfg.h QIB DRIVER M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/hw/qib/ @@ -16616,7 +16626,6 @@ F: drivers/net/ethernet/rdc/r6040.c RDMAVT - RDMA verbs software M: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> -M: Mike Marciniszyn <mike.marciniszyn@cornelisnetworks.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/sw/rdmavt @@ -17011,8 +17020,7 @@ S: Odd Fixes F: drivers/tty/serial/rp2.* ROHM BD99954 CHARGER IC -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> -L: linux-power@fi.rohmeurope.com +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Supported F: drivers/power/supply/bd99954-charger.c F: drivers/power/supply/bd99954-charger.h @@ -17035,8 +17043,7 @@ F: drivers/regulator/bd9571mwv-regulator.c F: include/linux/mfd/bd9571mwv.h ROHM POWER MANAGEMENT IC DEVICE DRIVERS -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> -L: linux-power@fi.rohmeurope.com +R: Matti Vaittinen <mazziesaccount@gmail.com> S: Supported F: drivers/clk/clk-bd718x7.c F: drivers/gpio/gpio-bd71815.c @@ -21118,7 +21125,7 @@ F: include/linux/regulator/ K: regulator_get_optional VOLTAGE AND CURRENT REGULATOR IRQ HELPERS -R: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com> +R: Matti Vaittinen <mazziesaccount@gmail.com> F: drivers/regulator/irq_helpers.c VRF @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Superb Owl # *DOCUMENTATION* diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 232b439cbaf3..ff8f4511df71 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -75,6 +75,7 @@ #define ARM_CPU_PART_CORTEX_A77 0xD0D #define ARM_CPU_PART_NEOVERSE_V1 0xD40 #define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 @@ -130,6 +131,7 @@ #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) #define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) #define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 7f3c87f7a0ce..c31be7eda9df 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -107,7 +107,7 @@ isb // Make sure SRE is now set mrs_s x0, SYS_ICC_SRE_EL2 // Read SRE back, tbz x0, #0, .Lskip_gicv3_\@ // and check that it sticks - msr_s SYS_ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults + msr_s SYS_ICH_HCR_EL2, xzr // Reset ICH_HCR_EL2 to defaults .Lskip_gicv3_\@: .endm diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 3fb79b76e9d9..7bbf5104b7b7 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -42,7 +42,7 @@ bool alternative_is_applied(u16 cpufeature) /* * Check if the target PC is within an alternative block. */ -static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) +static __always_inline bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) { unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt); return !(pc >= replptr && pc <= (replptr + alt->alt_len)); @@ -50,7 +50,7 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) #define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1)) -static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr) +static __always_inline u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr) { u32 insn; @@ -95,7 +95,7 @@ static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnp return insn; } -static void patch_alternative(struct alt_instr *alt, +static noinstr void patch_alternative(struct alt_instr *alt, __le32 *origptr, __le32 *updptr, int nr_inst) { __le32 *replptr; diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c index 3ed39c61a510..2b3f3d0544b9 100644 --- a/arch/arm64/kernel/elfcore.c +++ b/arch/arm64/kernel/elfcore.c @@ -8,16 +8,9 @@ #include <asm/cpufeature.h> #include <asm/mte.h> -#ifndef VMA_ITERATOR -#define VMA_ITERATOR(name, mm, addr) \ - struct mm_struct *name = mm -#define for_each_vma(vmi, vma) \ - for (vma = vmi->mmap; vma; vma = vma->vm_next) -#endif - -#define for_each_mte_vma(vmi, vma) \ +#define for_each_mte_vma(tsk, vma) \ if (system_supports_mte()) \ - for_each_vma(vmi, vma) \ + for (vma = tsk->mm->mmap; vma; vma = vma->vm_next) \ if (vma->vm_flags & VM_MTE) static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) @@ -32,10 +25,11 @@ static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) static int mte_dump_tag_range(struct coredump_params *cprm, unsigned long start, unsigned long end) { + int ret = 1; unsigned long addr; + void *tags = NULL; for (addr = start; addr < end; addr += PAGE_SIZE) { - char tags[MTE_PAGE_TAG_STORAGE]; struct page *page = get_dump_page(addr); /* @@ -59,22 +53,36 @@ static int mte_dump_tag_range(struct coredump_params *cprm, continue; } + if (!tags) { + tags = mte_allocate_tag_storage(); + if (!tags) { + put_page(page); + ret = 0; + break; + } + } + mte_save_page_tags(page_address(page), tags); put_page(page); - if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) - return 0; + if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) { + mte_free_tag_storage(tags); + ret = 0; + break; + } } - return 1; + if (tags) + mte_free_tag_storage(tags); + + return ret; } Elf_Half elf_core_extra_phdrs(void) { struct vm_area_struct *vma; int vma_count = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(current, vma) vma_count++; return vma_count; @@ -83,9 +91,8 @@ Elf_Half elf_core_extra_phdrs(void) int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) { struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(current, vma) { struct elf_phdr phdr; phdr.p_type = PT_ARM_MEMTAG_MTE; @@ -109,9 +116,8 @@ size_t elf_core_extra_data_size(void) { struct vm_area_struct *vma; size_t data_size = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(current, vma) data_size += mte_vma_tag_dump_size(vma); return data_size; @@ -120,9 +126,8 @@ size_t elf_core_extra_data_size(void) int elf_core_write_extra_data(struct coredump_params *cprm) { struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(current, vma) { if (vma->vm_flags & VM_DONTDUMP) continue; diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 712e97c03e54..cd868084e724 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -701,7 +701,7 @@ NOKPROBE_SYMBOL(breakpoint_handler); * addresses. There is no straight-forward way, short of disassembling the * offending instruction, to map that address back to the watchpoint. This * function computes the distance of the memory access from the watchpoint as a - * heuristic for the likelyhood that a given access triggered the watchpoint. + * heuristic for the likelihood that a given access triggered the watchpoint. * * See Section D2.10.5 "Determining the memory location that caused a Watchpoint * exception" of ARMv8 Architecture Reference Manual for details. diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index e53493d8b208..a3d0494f25a9 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -220,7 +220,7 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, * increasing the section's alignment so that the * resulting address of this instruction is guaranteed * to equal the offset in that particular bit (as well - * as all less signficant bits). This ensures that the + * as all less significant bits). This ensures that the * address modulo 4 KB != 0xfff8 or 0xfffc (which would * have all ones in bits [11:3]) */ diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c index 771f543464e0..33e0fabc0b79 100644 --- a/arch/arm64/kernel/patching.c +++ b/arch/arm64/kernel/patching.c @@ -117,8 +117,8 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg) int i, ret = 0; struct aarch64_insn_patch *pp = arg; - /* The first CPU becomes master */ - if (atomic_inc_return(&pp->cpu_count) == 1) { + /* The last CPU becomes master */ + if (atomic_inc_return(&pp->cpu_count) == num_online_cpus()) { for (i = 0; ret == 0 && i < pp->insn_cnt; i++) ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i], pp->new_insns[i]); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 5777929d35bf..40be3a7c2c53 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -853,6 +853,7 @@ u8 spectre_bhb_loop_affected(int scope) if (scope == SCOPE_LOCAL_CPU) { static const struct midr_range spectre_bhb_k32_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE), MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 27df5c1e6baa..3b46041f2b97 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -234,6 +234,7 @@ asmlinkage notrace void secondary_start_kernel(void) * Log the CPU info before it is marked online and might get read. */ cpuinfo_store_cpu(); + store_cpu_topology(cpu); /* * Enable GIC and timers. @@ -242,7 +243,6 @@ asmlinkage notrace void secondary_start_kernel(void) ipi_setup(cpu); - store_cpu_topology(cpu); numa_add_cpu(cpu); /* diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 19ee7c33769d..2b0887e58a7c 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -140,7 +140,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) /* * Restore pstate flags. OS lock and mdscr have been already * restored, so from this point onwards, debugging is fully - * renabled if it was enabled when core started shutdown. + * reenabled if it was enabled when core started shutdown. */ local_daif_restore(flags); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 8ac25f19084e..1e7b1550e2fc 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -73,7 +73,7 @@ EXPORT_SYMBOL(memstart_addr); * In this scheme a comparatively quicker boot is observed. * * If ZONE_DMA configs are defined, crash kernel memory reservation - * is delayed until DMA zone memory range size initilazation performed in + * is delayed until DMA zone memory range size initialization performed in * zone_sizes_init(). The defer is necessary to steer clear of DMA zone * memory range to avoid overlap allocation. So crash kernel memory boundaries * are not known when mapping all bank memory ranges, which otherwise means @@ -81,7 +81,7 @@ EXPORT_SYMBOL(memstart_addr); * so page-granularity mappings are created for the entire memory range. * Hence a slightly slower boot is observed. * - * Note: Page-granularity mapppings are necessary for crash kernel memory + * Note: Page-granularity mappings are necessary for crash kernel memory * range for shrinking its size via /sys/kernel/kexec_crash_size interface. */ #if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32) diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index 827038a33064..4def2bd17b9b 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -16,18 +16,6 @@ #include <asm/ppc-opcode.h> #include <asm/pte-walk.h> -#ifdef CONFIG_PPC_PSERIES -static inline bool kvmhv_on_pseries(void) -{ - return !cpu_has_feature(CPU_FTR_HVMODE); -} -#else -static inline bool kvmhv_on_pseries(void) -{ - return false; -} -#endif - /* * Structure for a nested guest, that is, for a guest that is managed by * one of our guests. diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index c583d0c37f31..838d4cb460b7 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -586,6 +586,18 @@ static inline bool kvm_hv_mode_active(void) { return false; } #endif +#ifdef CONFIG_PPC_PSERIES +static inline bool kvmhv_on_pseries(void) +{ + return !cpu_has_feature(CPU_FTR_HVMODE); +} +#else +static inline bool kvmhv_on_pseries(void) +{ + return false; +} +#endif + #ifdef CONFIG_KVM_XICS static inline int kvmppc_xics_enabled(struct kvm_vcpu *vcpu) { diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 254687258f42..f2c5c26869f1 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -132,7 +132,11 @@ static inline bool pfn_valid(unsigned long pfn) #define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr)) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) -#define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr)) +#define virt_addr_valid(vaddr) ({ \ + unsigned long _addr = (unsigned long)vaddr; \ + _addr >= PAGE_OFFSET && _addr < (unsigned long)high_memory && \ + pfn_valid(virt_to_pfn(_addr)); \ +}) /* * On Book-E parts we need __va to parse the device tree and we can't diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 049ca26893e6..8fa37ef5da4d 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -28,11 +28,13 @@ void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 #ifdef CONFIG_PPC_PSERIES +extern bool pseries_reloc_on_exception(void); extern bool pseries_enable_reloc_on_exc(void); extern void pseries_disable_reloc_on_exc(void); extern void pseries_big_endian_exceptions(void); void __init pseries_little_endian_exceptions(void); #else +static inline bool pseries_reloc_on_exception(void) { return false; } static inline bool pseries_enable_reloc_on_exc(void) { return false; } static inline void pseries_disable_reloc_on_exc(void) {} static inline void pseries_big_endian_exceptions(void) {} diff --git a/arch/powerpc/include/asm/static_call.h b/arch/powerpc/include/asm/static_call.h index 0a0bc79bd1fa..de1018cc522b 100644 --- a/arch/powerpc/include/asm/static_call.h +++ b/arch/powerpc/include/asm/static_call.h @@ -24,5 +24,6 @@ #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) __PPC_SCT(name, "b " #func) #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) __PPC_SCT(name, "blr") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) __PPC_SCT(name, "b .+20") #endif /* _ASM_POWERPC_STATIC_CALL_H */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 55caeee37c08..b66dd6f775a4 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -809,6 +809,10 @@ __start_interrupts: * - MSR_EE|MSR_RI is clear (no reentrant exceptions) * - Standard kernel environment is set up (stack, paca, etc) * + * KVM: + * These interrupts do not elevate HV 0->1, so HV is not involved. PR KVM + * ensures that FSCR[SCV] is disabled whenever it has to force AIL off. + * * Call convention: * * syscall register convention is in Documentation/powerpc/syscall64-abi.rst diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index e547066a06aa..a96f05063bc9 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -196,6 +196,34 @@ static void __init configure_exceptions(void) /* Under a PAPR hypervisor, we need hypercalls */ if (firmware_has_feature(FW_FEATURE_SET_MODE)) { + /* + * - PR KVM does not support AIL mode interrupts in the host + * while a PR guest is running. + * + * - SCV system call interrupt vectors are only implemented for + * AIL mode interrupts. + * + * - On pseries, AIL mode can only be enabled and disabled + * system-wide so when a PR VM is created on a pseries host, + * all CPUs of the host are set to AIL=0 mode. + * + * - Therefore host CPUs must not execute scv while a PR VM + * exists. + * + * - SCV support can not be disabled dynamically because the + * feature is advertised to host userspace. Disabling the + * facility and emulating it would be possible but is not + * implemented. + * + * - So SCV support is blanket disabled if PR KVM could possibly + * run. That is, PR support compiled in, booting on pseries + * with hash MMU. + */ + if (IS_ENABLED(CONFIG_KVM_BOOK3S_PR_POSSIBLE) && !radix_enabled()) { + init_task.thread.fscr &= ~FSCR_SCV; + cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV; + } + /* Enable AIL if possible */ if (!pseries_enable_reloc_on_exc()) { init_task.thread.fscr &= ~FSCR_SCV; diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index 18e58085447c..ddd88179110a 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -112,12 +112,21 @@ config KVM_BOOK3S_64_PR guest in user mode (problem state) and emulating all privileged instructions and registers. + This is only available for hash MMU mode and only supports + guests that use hash MMU mode. + This is not as fast as using hypervisor mode, but works on machines where hypervisor mode is not available or not usable, and can emulate processors that are different from the host processor, including emulating 32-bit processors on a 64-bit host. + Selecting this option will cause the SCV facility to be + disabled when the kernel is booted on the pseries platform in + hash MMU mode (regardless of PR VMs running). When any PR VMs + are running, "AIL" mode is disabled which may slow interrupts + and system calls on the host. + config KVM_BOOK3S_HV_EXIT_TIMING bool "Detailed timing for hypervisor real-mode code" depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS diff --git a/arch/powerpc/kvm/book3s_64_entry.S b/arch/powerpc/kvm/book3s_64_entry.S index 05e003eb5d90..e42d1c609e47 100644 --- a/arch/powerpc/kvm/book3s_64_entry.S +++ b/arch/powerpc/kvm/book3s_64_entry.S @@ -414,10 +414,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR1) */ ld r10,HSTATE_SCRATCH0(r13) cmpwi r10,BOOK3S_INTERRUPT_MACHINE_CHECK - beq machine_check_common + beq .Lcall_machine_check_common cmpwi r10,BOOK3S_INTERRUPT_SYSTEM_RESET - beq system_reset_common + beq .Lcall_system_reset_common b . + +.Lcall_machine_check_common: + b machine_check_common + +.Lcall_system_reset_common: + b system_reset_common #endif diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index c886557638a1..6fa518f6501d 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -225,6 +225,13 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) int cpu; struct rcuwait *waitp; + /* + * rcuwait_wake_up contains smp_mb() which orders prior stores that + * create pending work vs below loads of cpu fields. The other side + * is the barrier in vcpu run that orders setting the cpu fields vs + * testing for pending work. + */ + waitp = kvm_arch_vcpu_get_wait(vcpu); if (rcuwait_wake_up(waitp)) ++vcpu->stat.generic.halt_wakeup; @@ -1089,7 +1096,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) break; } tvcpu->arch.prodded = 1; - smp_mb(); + smp_mb(); /* This orders prodded store vs ceded load */ if (tvcpu->arch.ceded) kvmppc_fast_vcpu_kick_hv(tvcpu); break; @@ -3766,6 +3773,14 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) pvc = core_info.vc[sub]; pvc->pcpu = pcpu + thr; for_each_runnable_thread(i, vcpu, pvc) { + /* + * XXX: is kvmppc_start_thread called too late here? + * It updates vcpu->cpu and vcpu->arch.thread_cpu + * which are used by kvmppc_fast_vcpu_kick_hv(), but + * kick is called after new exceptions become available + * and exceptions are checked earlier than here, by + * kvmppc_core_prepare_to_enter. + */ kvmppc_start_thread(vcpu, pvc); kvmppc_create_dtl_entry(vcpu, pvc); trace_kvm_guest_enter(vcpu); @@ -4487,6 +4502,21 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, if (need_resched() || !kvm->arch.mmu_ready) goto out; + vcpu->cpu = pcpu; + vcpu->arch.thread_cpu = pcpu; + vc->pcpu = pcpu; + local_paca->kvm_hstate.kvm_vcpu = vcpu; + local_paca->kvm_hstate.ptid = 0; + local_paca->kvm_hstate.fake_suspend = 0; + + /* + * Orders set cpu/thread_cpu vs testing for pending interrupts and + * doorbells below. The other side is when these fields are set vs + * kvmppc_fast_vcpu_kick_hv reading the cpu/thread_cpu fields to + * kick a vCPU to notice the pending interrupt. + */ + smp_mb(); + if (!nested) { kvmppc_core_prepare_to_enter(vcpu); if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, @@ -4506,13 +4536,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, tb = mftb(); - vcpu->cpu = pcpu; - vcpu->arch.thread_cpu = pcpu; - vc->pcpu = pcpu; - local_paca->kvm_hstate.kvm_vcpu = vcpu; - local_paca->kvm_hstate.ptid = 0; - local_paca->kvm_hstate.fake_suspend = 0; - __kvmppc_create_dtl_entry(vcpu, pcpu, tb + vc->tb_offset, 0); trace_kvm_guest_enter(vcpu); @@ -4614,6 +4637,8 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, run->exit_reason = KVM_EXIT_INTR; vcpu->arch.ret = -EINTR; out: + vcpu->cpu = -1; + vcpu->arch.thread_cpu = -1; powerpc_local_irq_pmu_restore(flags); preempt_enable(); goto done; diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 34a801c3604a..7bf9e6ca5c2d 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -137,12 +137,15 @@ static void kvmppc_core_vcpu_load_pr(struct kvm_vcpu *vcpu, int cpu) svcpu->slb_max = to_book3s(vcpu)->slb_shadow_max; svcpu->in_use = 0; svcpu_put(svcpu); -#endif /* Disable AIL if supported */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) - mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL); + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~LPCR_AIL); + if (cpu_has_feature(CPU_FTR_ARCH_300) && (current->thread.fscr & FSCR_SCV)) + mtspr(SPRN_FSCR, mfspr(SPRN_FSCR) & ~FSCR_SCV); + } +#endif vcpu->cpu = smp_processor_id(); #ifdef CONFIG_PPC_BOOK3S_32 @@ -165,6 +168,14 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) memcpy(to_book3s(vcpu)->slb_shadow, svcpu->slb, sizeof(svcpu->slb)); to_book3s(vcpu)->slb_shadow_max = svcpu->slb_max; svcpu_put(svcpu); + + /* Enable AIL if supported */ + if (cpu_has_feature(CPU_FTR_HVMODE)) { + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3); + if (cpu_has_feature(CPU_FTR_ARCH_300) && (current->thread.fscr & FSCR_SCV)) + mtspr(SPRN_FSCR, mfspr(SPRN_FSCR) | FSCR_SCV); + } #endif if (kvmppc_is_split_real(vcpu)) @@ -174,11 +185,6 @@ static void kvmppc_core_vcpu_put_pr(struct kvm_vcpu *vcpu) kvmppc_giveup_fac(vcpu, FSCR_TAR_LG); kvmppc_save_tm_pr(vcpu); - /* Enable AIL if supported */ - if (cpu_has_feature(CPU_FTR_HVMODE) && - cpu_has_feature(CPU_FTR_ARCH_207S)) - mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_AIL_3); - vcpu->cpu = -1; } @@ -1037,6 +1043,8 @@ static int kvmppc_handle_fac(struct kvm_vcpu *vcpu, ulong fac) void kvmppc_set_fscr(struct kvm_vcpu *vcpu, u64 fscr) { + if (fscr & FSCR_SCV) + fscr &= ~FSCR_SCV; /* SCV must not be enabled */ if ((vcpu->arch.fscr & FSCR_TAR) && !(fscr & FSCR_TAR)) { /* TAR got dropped, drop it in shadow too */ kvmppc_giveup_fac(vcpu, FSCR_TAR_LG); diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index 1f10e7dfcdd0..dc4f51ac84bc 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -281,6 +281,22 @@ static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu) return EMULATE_DONE; } +static int kvmppc_h_pr_set_mode(struct kvm_vcpu *vcpu) +{ + unsigned long mflags = kvmppc_get_gpr(vcpu, 4); + unsigned long resource = kvmppc_get_gpr(vcpu, 5); + + if (resource == H_SET_MODE_RESOURCE_ADDR_TRANS_MODE) { + /* KVM PR does not provide AIL!=0 to guests */ + if (mflags == 0) + kvmppc_set_gpr(vcpu, 3, H_SUCCESS); + else + kvmppc_set_gpr(vcpu, 3, H_UNSUPPORTED_FLAG_START - 63); + return EMULATE_DONE; + } + return EMULATE_FAIL; +} + #ifdef CONFIG_SPAPR_TCE_IOMMU static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu) { @@ -384,6 +400,8 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) return kvmppc_h_pr_logical_ci_load(vcpu); case H_LOGICAL_CI_STORE: return kvmppc_h_pr_logical_ci_store(vcpu); + case H_SET_MODE: + return kvmppc_h_pr_set_mode(vcpu); case H_XIRR: case H_CPPR: case H_EOI: @@ -421,6 +439,7 @@ int kvmppc_hcall_impl_pr(unsigned long cmd) case H_CEDE: case H_LOGICAL_CI_LOAD: case H_LOGICAL_CI_STORE: + case H_SET_MODE: #ifdef CONFIG_KVM_XICS case H_XIRR: case H_CPPR: @@ -447,6 +466,7 @@ static unsigned int default_hcall_list[] = { H_BULK_REMOVE, H_PUT_TCE, H_CEDE, + H_SET_MODE, #ifdef CONFIG_KVM_XICS H_XIRR, H_CPPR, diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 9772b176e406..875c30c12db0 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -705,6 +705,23 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 1; break; #endif + case KVM_CAP_PPC_AIL_MODE_3: + r = 0; + /* + * KVM PR, POWER7, and some POWER9s don't support AIL=3 mode. + * The POWER9s can support it if the guest runs in hash mode, + * but QEMU doesn't necessarily query the capability in time. + */ + if (hv_enabled) { + if (kvmhv_on_pseries()) { + if (pseries_reloc_on_exception()) + r = 1; + } else if (cpu_has_feature(CPU_FTR_ARCH_207S) && + !cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) { + r = 1; + } + } + break; default: r = 0; break; diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 8e301cd8925b..4d221d033804 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -255,7 +255,7 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - set_max_mapnr(max_low_pfn); + set_max_mapnr(max_pfn); kasan_late_init(); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b9b7fefbb64b..13022d734951 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1436,7 +1436,7 @@ int find_and_online_cpu_nid(int cpu) if (new_nid < 0 || !node_possible(new_nid)) new_nid = first_online_node; - if (NODE_DATA(new_nid) == NULL) { + if (!node_online(new_nid)) { #ifdef CONFIG_MEMORY_HOTPLUG /* * Need to ensure that NODE_DATA is initialized for a node from diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 069d7b3bb142..955ff8aa1644 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -353,6 +353,14 @@ static void pseries_lpar_idle(void) pseries_idle_epilog(); } +static bool pseries_reloc_on_exception_enabled; + +bool pseries_reloc_on_exception(void) +{ + return pseries_reloc_on_exception_enabled; +} +EXPORT_SYMBOL_GPL(pseries_reloc_on_exception); + /* * Enable relocation on during exceptions. This has partition wide scope and * may take a while to complete, if it takes longer than one second we will @@ -377,6 +385,7 @@ bool pseries_enable_reloc_on_exc(void) " on exceptions: %ld\n", rc); return false; } + pseries_reloc_on_exception_enabled = true; return true; } @@ -404,7 +413,9 @@ void pseries_disable_reloc_on_exc(void) break; mdelay(get_longbusy_msecs(rc)); } - if (rc != H_SUCCESS) + if (rc == H_SUCCESS) + pseries_reloc_on_exception_enabled = false; + else pr_warn("Warning: Failed to disable relocation on exceptions: %ld\n", rc); } diff --git a/arch/powerpc/platforms/pseries/vas-sysfs.c b/arch/powerpc/platforms/pseries/vas-sysfs.c index 4a7fcde5afc0..909535ca513a 100644 --- a/arch/powerpc/platforms/pseries/vas-sysfs.c +++ b/arch/powerpc/platforms/pseries/vas-sysfs.c @@ -99,6 +99,7 @@ static struct attribute *vas_def_capab_attrs[] = { &nr_used_credits_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(vas_def_capab); static struct attribute *vas_qos_capab_attrs[] = { &nr_total_credits_attribute.attr, @@ -106,6 +107,7 @@ static struct attribute *vas_qos_capab_attrs[] = { &update_total_credits_attribute.attr, NULL, }; +ATTRIBUTE_GROUPS(vas_qos_capab); static ssize_t vas_type_show(struct kobject *kobj, struct attribute *attr, char *buf) @@ -154,13 +156,13 @@ static const struct sysfs_ops vas_sysfs_ops = { static struct kobj_type vas_def_attr_type = { .release = vas_type_release, .sysfs_ops = &vas_sysfs_ops, - .default_attrs = vas_def_capab_attrs, + .default_groups = vas_def_capab_groups, }; static struct kobj_type vas_qos_attr_type = { .release = vas_type_release, .sysfs_ops = &vas_sysfs_ops, - .default_attrs = vas_qos_capab_attrs, + .default_groups = vas_qos_capab_groups, }; static char *vas_caps_kobj_name(struct vas_caps_entry *centry, diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b0142e01002e..374d3e85c1f1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -940,6 +940,12 @@ config GART_IOMMU If unsure, say Y. +config BOOT_VESA_SUPPORT + bool + help + If true, at least one selected framebuffer driver can take advantage + of VESA video modes set at an early boot stage via the vga= parameter. + config MAXSMP bool "Enable Maximum number of SMP Processors and NUMA Nodes" depends on X86_64 && SMP && DEBUG_KERNEL diff --git a/arch/x86/boot/video-vesa.c b/arch/x86/boot/video-vesa.c index 7e185977a984..c2c6d35e3a43 100644 --- a/arch/x86/boot/video-vesa.c +++ b/arch/x86/boot/video-vesa.c @@ -83,7 +83,7 @@ static int vesa_probe(void) (vminfo.memory_layout == 4 || vminfo.memory_layout == 6) && vminfo.memory_planes == 1) { -#ifdef CONFIG_FB_BOOT_VESA_SUPPORT +#ifdef CONFIG_BOOT_VESA_SUPPORT /* Graphics mode, color, linear frame buffer supported. Only register the mode if if framebuffer is configured, however, @@ -121,7 +121,7 @@ static int vesa_set_mode(struct mode_info *mode) if ((vminfo.mode_attr & 0x15) == 0x05) { /* It's a supported text mode */ is_graphic = 0; -#ifdef CONFIG_FB_BOOT_VESA_SUPPORT +#ifdef CONFIG_BOOT_VESA_SUPPORT } else if ((vminfo.mode_attr & 0x99) == 0x99) { /* It's a graphics mode with linear frame buffer */ is_graphic = 1; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index e88791b420ee..fc7f458eb3de 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -302,7 +302,7 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = { INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), - INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE), INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0x7, FE), INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE), EVENT_EXTRA_END @@ -5536,7 +5536,11 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con /* Disabled fixed counters which are not in CPUID */ c->idxmsk64 &= intel_ctrl; - if (c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) + /* + * Don't extend the pseudo-encoding to the + * generic counters + */ + if (!use_fixed_pseudo_encoding(c->code)) c->idxmsk64 |= (1ULL << num_counters) - 1; } c->idxmsk64 &= @@ -6212,6 +6216,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: + case INTEL_FAM6_RAPTORLAKE: /* * Alder Lake has 2 types of CPU, core and atom. * diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index c6262b154c3a..5d7762288a24 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -40,7 +40,7 @@ * Model specific counters: * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 - * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL + * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 @@ -51,49 +51,50 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL + * TGL,TNT,RKL,ADL,RPL * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, - * ICL,TGL,RKL,ADL + * ICL,TGL,RKL,ADL,RPL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, - * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL + * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL, + * RPL * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL + * TGL,TNT,RKL,ADL,RPL * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, - * KBL,CML,ICL,TGL,RKL,ADL + * KBL,CML,ICL,TGL,RKL,ADL,RPL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL + * ADL,RPL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, - * TNT,RKL,ADL + * TNT,RKL,ADL,RPL * Scope: Package (physical package) * */ @@ -680,6 +681,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index e497da9bf427..7695dcae280e 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1828,6 +1828,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE, &rkl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &adl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), {}, diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index f698a55bde81..4262351f52b6 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -79,6 +79,10 @@ #define PCI_DEVICE_ID_INTEL_ADL_14_IMC 0x4650 #define PCI_DEVICE_ID_INTEL_ADL_15_IMC 0x4668 #define PCI_DEVICE_ID_INTEL_ADL_16_IMC 0x4670 +#define PCI_DEVICE_ID_INTEL_RPL_1_IMC 0xA700 +#define PCI_DEVICE_ID_INTEL_RPL_2_IMC 0xA702 +#define PCI_DEVICE_ID_INTEL_RPL_3_IMC 0xA706 +#define PCI_DEVICE_ID_INTEL_RPL_4_IMC 0xA709 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -1406,6 +1410,22 @@ static const struct pci_device_id tgl_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ADL_16_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_1_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_2_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_3_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_RPL_4_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, { /* end: all zeroes */ } }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index 96c775abe31f..6d759f88315c 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -103,6 +103,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_ROCKETLAKE: case INTEL_FAM6_ALDERLAKE: case INTEL_FAM6_ALDERLAKE_L: + case INTEL_FAM6_RAPTORLAKE: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index c878fed3056f..fbcfec4dc4cc 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -154,24 +154,24 @@ # define DEFINE_EXTABLE_TYPE_REG \ ".macro extable_type_reg type:req reg:req\n" \ - ".set found, 0\n" \ - ".set regnr, 0\n" \ + ".set .Lfound, 0\n" \ + ".set .Lregnr, 0\n" \ ".irp rs,rax,rcx,rdx,rbx,rsp,rbp,rsi,rdi,r8,r9,r10,r11,r12,r13,r14,r15\n" \ ".ifc \\reg, %%\\rs\n" \ - ".set found, found+1\n" \ - ".long \\type + (regnr << 8)\n" \ + ".set .Lfound, .Lfound+1\n" \ + ".long \\type + (.Lregnr << 8)\n" \ ".endif\n" \ - ".set regnr, regnr+1\n" \ + ".set .Lregnr, .Lregnr+1\n" \ ".endr\n" \ - ".set regnr, 0\n" \ + ".set .Lregnr, 0\n" \ ".irp rs,eax,ecx,edx,ebx,esp,ebp,esi,edi,r8d,r9d,r10d,r11d,r12d,r13d,r14d,r15d\n" \ ".ifc \\reg, %%\\rs\n" \ - ".set found, found+1\n" \ - ".long \\type + (regnr << 8)\n" \ + ".set .Lfound, .Lfound+1\n" \ + ".long \\type + (.Lregnr << 8)\n" \ ".endif\n" \ - ".set regnr, regnr+1\n" \ + ".set .Lregnr, .Lregnr+1\n" \ ".endr\n" \ - ".if (found != 1)\n" \ + ".if (.Lfound != 1)\n" \ ".error \"extable_type_reg: bad register argument\"\n" \ ".endif\n" \ ".endm\n" diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 4d20a293c6fd..aaf0cb0db4ae 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -78,9 +78,9 @@ do { \ */ #define __WARN_FLAGS(flags) \ do { \ - __auto_type f = BUGFLAG_WARNING|(flags); \ + __auto_type __flags = BUGFLAG_WARNING|(flags); \ instrumentation_begin(); \ - _BUG_FLAGS(ASM_UD2, f, ASM_REACHABLE); \ + _BUG_FLAGS(ASM_UD2, __flags, ASM_REACHABLE); \ instrumentation_end(); \ } while (0) diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index b85147d75626..d71c7e8b738d 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -12,14 +12,17 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, /* Structs and defines for the X86 specific MSI message format */ typedef struct x86_msi_data { - u32 vector : 8, - delivery_mode : 3, - dest_mode_logical : 1, - reserved : 2, - active_low : 1, - is_level : 1; - - u32 dmar_subhandle; + union { + struct { + u32 vector : 8, + delivery_mode : 3, + dest_mode_logical : 1, + reserved : 2, + active_low : 1, + is_level : 1; + }; + u32 dmar_subhandle; + }; } __attribute__ ((packed)) arch_msi_msg_data_t; #define arch_msi_msg_data x86_msi_data diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index a3c33b79fb86..13c0d63ed55e 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -38,9 +38,9 @@ #define arch_raw_cpu_ptr(ptr) \ ({ \ unsigned long tcp_ptr__; \ - asm volatile("add " __percpu_arg(1) ", %0" \ - : "=r" (tcp_ptr__) \ - : "m" (this_cpu_off), "0" (ptr)); \ + asm ("add " __percpu_arg(1) ", %0" \ + : "=r" (tcp_ptr__) \ + : "m" (this_cpu_off), "0" (ptr)); \ (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \ }) #else diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 58d9e4b1fa0a..b06e4c573add 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -241,6 +241,11 @@ struct x86_pmu_capability { #define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3) #define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS) +static inline bool use_fixed_pseudo_encoding(u64 code) +{ + return !(code & 0xff); +} + /* * We model BTS tracing as another fixed-mode PMC. * diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index ed4f8bb6c2d9..2455d721503e 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -38,6 +38,8 @@ #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) \ + ARCH_DEFINE_STATIC_CALL_TRAMP(name, __static_call_return0) #define ARCH_ADD_TRAMP_KEY(name) \ asm(".pushsection .static_call_tramp_key, \"a\" \n" \ diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 531fb4cbb63f..aa72cefdd5be 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -12,10 +12,9 @@ enum insn_type { }; /* - * data16 data16 xorq %rax, %rax - a single 5 byte instruction that clears %rax - * The REX.W cancels the effect of any data16. + * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax */ -static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 }; +static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 }; static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc }; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6eb4d91d5365..d400b6d9d246 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -855,13 +855,11 @@ done: nr_invalidate); } -static bool tlb_is_not_lazy(int cpu) +static bool tlb_is_not_lazy(int cpu, void *data) { return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu); } -static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask); - DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared); EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared); @@ -890,36 +888,11 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask, * up on the new contents of what used to be page tables, while * doing a speculative memory access. */ - if (info->freed_tables) { + if (info->freed_tables) on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true); - } else { - /* - * Although we could have used on_each_cpu_cond_mask(), - * open-coding it has performance advantages, as it eliminates - * the need for indirect calls or retpolines. In addition, it - * allows to use a designated cpumask for evaluating the - * condition, instead of allocating one. - * - * This code works under the assumption that there are no nested - * TLB flushes, an assumption that is already made in - * flush_tlb_mm_range(). - * - * cond_cpumask is logically a stack-local variable, but it is - * more efficient to have it off the stack and not to allocate - * it on demand. Preemption is disabled and this code is - * non-reentrant. - */ - struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask); - int cpu; - - cpumask_clear(cond_cpumask); - - for_each_cpu(cpu, cpumask) { - if (tlb_is_not_lazy(cpu)) - __cpumask_set_cpu(cpu, cond_cpumask); - } - on_each_cpu_mask(cond_cpumask, flush_tlb_func, (void *)info, true); - } + else + on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func, + (void *)info, 1, cpumask); } void flush_tlb_multi(const struct cpumask *cpumask, diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8fe35ed11fd6..16b6efacf7c6 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -412,6 +412,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { + OPTIMIZER_HIDE_VAR(reg); emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); } else #endif diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 9f2b251e83c5..3822666fb73d 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -40,7 +40,8 @@ static void msr_save_context(struct saved_context *ctxt) struct saved_msr *end = msr + ctxt->saved_msrs.num; while (msr < end) { - msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q); + if (msr->valid) + rdmsrl(msr->info.msr_no, msr->info.reg.q); msr++; } } @@ -424,8 +425,10 @@ static int msr_build_context(const u32 *msr_id, const int num) } for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) { + u64 dummy; + msr_array[i].info.msr_no = msr_id[j]; - msr_array[i].valid = false; + msr_array[i].valid = !rdmsrl_safe(msr_id[j], &dummy); msr_array[i].info.reg.q = 0; } saved_msrs->num = total_num; @@ -500,10 +503,24 @@ static int pm_cpu_check(const struct x86_cpu_id *c) return ret; } +static void pm_save_spec_msr(void) +{ + u32 spec_msr_id[] = { + MSR_IA32_SPEC_CTRL, + MSR_IA32_TSX_CTRL, + MSR_TSX_FORCE_ABORT, + MSR_IA32_MCU_OPT_CTRL, + MSR_AMD64_LS_CFG, + }; + + msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id)); +} + static int pm_check_save_msr(void) { dmi_check_system(msr_save_dmi_table); pm_cpu_check(msr_save_cpu_table); + pm_save_spec_msr(); return 0; } diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 32b20efff5f8..4556c86c3465 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -570,8 +570,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index) { struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu); - if (cx->type == ACPI_STATE_C3) - ACPI_FLUSH_CPU_CACHE(); + ACPI_FLUSH_CPU_CACHE(); while (1) { diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 9efbfe087de7..762b61f67e6c 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -588,19 +588,6 @@ static struct acpi_device *handle_to_device(acpi_handle handle, return adev; } -int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device) -{ - if (!device) - return -EINVAL; - - *device = handle_to_device(handle, NULL); - if (!*device) - return -ENODEV; - - return 0; -} -EXPORT_SYMBOL(acpi_bus_get_device); - /** * acpi_fetch_acpi_dev - Retrieve ACPI device object. * @handle: ACPI handle associated with the requested ACPI device object. diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index e5641e6c52ee..bb45a9c00514 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -115,14 +115,16 @@ config SATA_AHCI If unsure, say N. -config SATA_LPM_POLICY +config SATA_MOBILE_LPM_POLICY int "Default SATA Link Power Management policy for low power chipsets" range 0 4 default 0 depends on SATA_AHCI help Select the Default SATA Link Power Management (LPM) policy to use - for chipsets / "South Bridges" designated as supporting low power. + for chipsets / "South Bridges" supporting low-power modes. Such + chipsets are typically found on most laptops but desktops and + servers now also widely use chipsets supporting low power modes. The value set has the following meanings: 0 => Keep firmware settings diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 84456c05e845..397dfd27c90d 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1595,7 +1595,7 @@ static int ahci_init_msi(struct pci_dev *pdev, unsigned int n_ports, static void ahci_update_initial_lpm_policy(struct ata_port *ap, struct ahci_host_priv *hpriv) { - int policy = CONFIG_SATA_LPM_POLICY; + int policy = CONFIG_SATA_MOBILE_LPM_POLICY; /* Ignore processing for chipsets that don't use policy */ diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 6ead58c1b6e5..ad11a4c52fbe 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -236,7 +236,7 @@ enum { AHCI_HFLAG_NO_WRITE_TO_RO = (1 << 24), /* don't write to read only registers */ AHCI_HFLAG_USE_LPM_POLICY = (1 << 25), /* chipset that should use - SATA_LPM_POLICY + SATA_MOBILE_LPM_POLICY as default lpm_policy */ AHCI_HFLAG_SUSPEND_PHYS = (1 << 26), /* handle PHYs during suspend/resume */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index cceedde51126..ca64837641be 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4014,6 +4014,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Crucial_CT*MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, + { "Samsung SSD 840 EVO*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | + ATA_HORKAGE_NO_DMA_LOG | + ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 840*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 850*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index b3be7a8f5bea..b1666adc1c3a 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -1634,7 +1634,7 @@ EXPORT_SYMBOL_GPL(ata_sff_interrupt); void ata_sff_lost_interrupt(struct ata_port *ap) { - u8 status; + u8 status = 0; struct ata_queued_cmd *qc; /* Only one outstanding command per SFF channel */ diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c index bec33d781ae0..e3263e961045 100644 --- a/drivers/ata/sata_dwc_460ex.c +++ b/drivers/ata/sata_dwc_460ex.c @@ -137,7 +137,11 @@ struct sata_dwc_device { #endif }; -#define SATA_DWC_QCMD_MAX 32 +/* + * Allow one extra special slot for commands and DMA management + * to account for libata internal commands. + */ +#define SATA_DWC_QCMD_MAX (ATA_MAX_QUEUE + 1) struct sata_dwc_device_port { struct sata_dwc_device *hsdev; diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 4b55e864a0a3..4d3efaa20b7b 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1638,22 +1638,22 @@ struct sib_info { }; void drbd_bcast_event(struct drbd_device *device, const struct sib_info *sib); -extern void notify_resource_state(struct sk_buff *, +extern int notify_resource_state(struct sk_buff *, unsigned int, struct drbd_resource *, struct resource_info *, enum drbd_notification_type); -extern void notify_device_state(struct sk_buff *, +extern int notify_device_state(struct sk_buff *, unsigned int, struct drbd_device *, struct device_info *, enum drbd_notification_type); -extern void notify_connection_state(struct sk_buff *, +extern int notify_connection_state(struct sk_buff *, unsigned int, struct drbd_connection *, struct connection_info *, enum drbd_notification_type); -extern void notify_peer_device_state(struct sk_buff *, +extern int notify_peer_device_state(struct sk_buff *, unsigned int, struct drbd_peer_device *, struct peer_device_info *, diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 9676a1d214bc..4b0b25cc916e 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2719,6 +2719,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig sprintf(disk->disk_name, "drbd%d", minor); disk->private_data = device; + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue); blk_queue_write_cache(disk->queue, true, true); /* Setting the max_hw_sectors to an odd value of 8kibyte here This triggers a max_bio_size message upon first attach or connect */ @@ -2773,12 +2774,12 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig if (init_submitter(device)) { err = ERR_NOMEM; - goto out_idr_remove_vol; + goto out_idr_remove_from_resource; } err = add_disk(disk); if (err) - goto out_idr_remove_vol; + goto out_idr_remove_from_resource; /* inherit the connection state */ device->state.conn = first_connection(resource)->cstate; @@ -2792,8 +2793,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig drbd_debugfs_device_add(device); return NO_ERROR; -out_idr_remove_vol: - idr_remove(&connection->peer_devices, vnr); out_idr_remove_from_resource: for_each_connection(connection, resource) { peer_device = idr_remove(&connection->peer_devices, vnr); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 02030c9c4d3b..b7216c186ba4 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -4549,7 +4549,7 @@ static int nla_put_notification_header(struct sk_buff *msg, return drbd_notification_header_to_skb(msg, &nh, true); } -void notify_resource_state(struct sk_buff *skb, +int notify_resource_state(struct sk_buff *skb, unsigned int seq, struct drbd_resource *resource, struct resource_info *resource_info, @@ -4591,16 +4591,17 @@ void notify_resource_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(resource, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_device_state(struct sk_buff *skb, +int notify_device_state(struct sk_buff *skb, unsigned int seq, struct drbd_device *device, struct device_info *device_info, @@ -4640,16 +4641,17 @@ void notify_device_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(device, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_connection_state(struct sk_buff *skb, +int notify_connection_state(struct sk_buff *skb, unsigned int seq, struct drbd_connection *connection, struct connection_info *connection_info, @@ -4689,16 +4691,17 @@ void notify_connection_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(connection, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } -void notify_peer_device_state(struct sk_buff *skb, +int notify_peer_device_state(struct sk_buff *skb, unsigned int seq, struct drbd_peer_device *peer_device, struct peer_device_info *peer_device_info, @@ -4739,13 +4742,14 @@ void notify_peer_device_state(struct sk_buff *skb, if (err && err != -ESRCH) goto failed; } - return; + return 0; nla_put_failure: nlmsg_free(skb); failed: drbd_err(peer_device, "Error %d while broadcasting event. Event seq:%u\n", err, seq); + return err; } void notify_helper(enum drbd_notification_type type, @@ -4796,7 +4800,7 @@ fail: err, seq); } -static void notify_initial_state_done(struct sk_buff *skb, unsigned int seq) +static int notify_initial_state_done(struct sk_buff *skb, unsigned int seq) { struct drbd_genlmsghdr *dh; int err; @@ -4810,11 +4814,12 @@ static void notify_initial_state_done(struct sk_buff *skb, unsigned int seq) if (nla_put_notification_header(skb, NOTIFY_EXISTS)) goto nla_put_failure; genlmsg_end(skb, dh); - return; + return 0; nla_put_failure: nlmsg_free(skb); pr_err("Error %d sending event. Event seq:%u\n", err, seq); + return err; } static void free_state_changes(struct list_head *list) @@ -4841,6 +4846,7 @@ static int get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) unsigned int seq = cb->args[2]; unsigned int n; enum drbd_notification_type flags = 0; + int err = 0; /* There is no need for taking notification_mutex here: it doesn't matter if the initial state events mix with later state chage @@ -4849,32 +4855,32 @@ static int get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) cb->args[5]--; if (cb->args[5] == 1) { - notify_initial_state_done(skb, seq); + err = notify_initial_state_done(skb, seq); goto out; } n = cb->args[4]++; if (cb->args[4] < cb->args[3]) flags |= NOTIFY_CONTINUES; if (n < 1) { - notify_resource_state_change(skb, seq, state_change->resource, + err = notify_resource_state_change(skb, seq, state_change->resource, NOTIFY_EXISTS | flags); goto next; } n--; if (n < state_change->n_connections) { - notify_connection_state_change(skb, seq, &state_change->connections[n], + err = notify_connection_state_change(skb, seq, &state_change->connections[n], NOTIFY_EXISTS | flags); goto next; } n -= state_change->n_connections; if (n < state_change->n_devices) { - notify_device_state_change(skb, seq, &state_change->devices[n], + err = notify_device_state_change(skb, seq, &state_change->devices[n], NOTIFY_EXISTS | flags); goto next; } n -= state_change->n_devices; if (n < state_change->n_devices * state_change->n_connections) { - notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n], + err = notify_peer_device_state_change(skb, seq, &state_change->peer_devices[n], NOTIFY_EXISTS | flags); goto next; } @@ -4889,7 +4895,10 @@ next: cb->args[4] = 0; } out: - return skb->len; + if (err) + return err; + else + return skb->len; } int drbd_adm_get_initial_state(struct sk_buff *skb, struct netlink_callback *cb) diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index b8a27818ab3f..4ee11aef6672 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -1537,7 +1537,7 @@ int drbd_bitmap_io_from_worker(struct drbd_device *device, return rv; } -void notify_resource_state_change(struct sk_buff *skb, +int notify_resource_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_resource_state_change *resource_state_change, enum drbd_notification_type type) @@ -1550,10 +1550,10 @@ void notify_resource_state_change(struct sk_buff *skb, .res_susp_fen = resource_state_change->susp_fen[NEW], }; - notify_resource_state(skb, seq, resource, &resource_info, type); + return notify_resource_state(skb, seq, resource, &resource_info, type); } -void notify_connection_state_change(struct sk_buff *skb, +int notify_connection_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_connection_state_change *connection_state_change, enum drbd_notification_type type) @@ -1564,10 +1564,10 @@ void notify_connection_state_change(struct sk_buff *skb, .conn_role = connection_state_change->peer_role[NEW], }; - notify_connection_state(skb, seq, connection, &connection_info, type); + return notify_connection_state(skb, seq, connection, &connection_info, type); } -void notify_device_state_change(struct sk_buff *skb, +int notify_device_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_device_state_change *device_state_change, enum drbd_notification_type type) @@ -1577,10 +1577,10 @@ void notify_device_state_change(struct sk_buff *skb, .dev_disk_state = device_state_change->disk_state[NEW], }; - notify_device_state(skb, seq, device, &device_info, type); + return notify_device_state(skb, seq, device, &device_info, type); } -void notify_peer_device_state_change(struct sk_buff *skb, +int notify_peer_device_state_change(struct sk_buff *skb, unsigned int seq, struct drbd_peer_device_state_change *p, enum drbd_notification_type type) @@ -1594,7 +1594,7 @@ void notify_peer_device_state_change(struct sk_buff *skb, .peer_resync_susp_dependency = p->resync_susp_dependency[NEW], }; - notify_peer_device_state(skb, seq, peer_device, &peer_device_info, type); + return notify_peer_device_state(skb, seq, peer_device, &peer_device_info, type); } static void broadcast_state_change(struct drbd_state_change *state_change) @@ -1602,7 +1602,7 @@ static void broadcast_state_change(struct drbd_state_change *state_change) struct drbd_resource_state_change *resource_state_change = &state_change->resource[0]; bool resource_state_has_changed; unsigned int n_device, n_connection, n_peer_device, n_peer_devices; - void (*last_func)(struct sk_buff *, unsigned int, void *, + int (*last_func)(struct sk_buff *, unsigned int, void *, enum drbd_notification_type) = NULL; void *last_arg = NULL; diff --git a/drivers/block/drbd/drbd_state_change.h b/drivers/block/drbd/drbd_state_change.h index ba80f612d6ab..d5b0479bc9a6 100644 --- a/drivers/block/drbd/drbd_state_change.h +++ b/drivers/block/drbd/drbd_state_change.h @@ -44,19 +44,19 @@ extern struct drbd_state_change *remember_old_state(struct drbd_resource *, gfp_ extern void copy_old_to_new_state_change(struct drbd_state_change *); extern void forget_state_change(struct drbd_state_change *); -extern void notify_resource_state_change(struct sk_buff *, +extern int notify_resource_state_change(struct sk_buff *, unsigned int, struct drbd_resource_state_change *, enum drbd_notification_type type); -extern void notify_connection_state_change(struct sk_buff *, +extern int notify_connection_state_change(struct sk_buff *, unsigned int, struct drbd_connection_state_change *, enum drbd_notification_type type); -extern void notify_device_state_change(struct sk_buff *, +extern int notify_device_state_change(struct sk_buff *, unsigned int, struct drbd_device_state_change *, enum drbd_notification_type type); -extern void notify_peer_device_state_change(struct sk_buff *, +extern int notify_peer_device_state_change(struct sk_buff *, unsigned int, struct drbd_peer_device_state_change *, enum drbd_notification_type type); diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 7bd10d63ddbe..2dc9da683a13 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -1365,7 +1365,6 @@ out_free: */ int cdrom_number_of_slots(struct cdrom_device_info *cdi) { - int status; int nslots = 1; struct cdrom_changer_info *info; @@ -1377,7 +1376,7 @@ int cdrom_number_of_slots(struct cdrom_device_info *cdi) if (!info) return -ENOMEM; - if ((status = cdrom_read_mech_status(cdi, info)) == 0) + if (cdrom_read_mech_status(cdi, info) == 0) nslots = info->hdr.nslots; kfree(info); diff --git a/drivers/char/random.c b/drivers/char/random.c index 1d8242969751..e15063d61460 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -437,11 +437,8 @@ static void crng_make_state(u32 chacha_state[CHACHA_STATE_WORDS], * This shouldn't be set by functions like add_device_randomness(), * where we can't trust the buffer passed to it is guaranteed to be * unpredictable (so it might not have any entropy at all). - * - * Returns the number of bytes processed from input, which is bounded - * by CRNG_INIT_CNT_THRESH if account is true. */ -static size_t crng_pre_init_inject(const void *input, size_t len, bool account) +static void crng_pre_init_inject(const void *input, size_t len, bool account) { static int crng_init_cnt = 0; struct blake2s_state hash; @@ -452,18 +449,15 @@ static size_t crng_pre_init_inject(const void *input, size_t len, bool account) spin_lock_irqsave(&base_crng.lock, flags); if (crng_init != 0) { spin_unlock_irqrestore(&base_crng.lock, flags); - return 0; + return; } - if (account) - len = min_t(size_t, len, CRNG_INIT_CNT_THRESH - crng_init_cnt); - blake2s_update(&hash, base_crng.key, sizeof(base_crng.key)); blake2s_update(&hash, input, len); blake2s_final(&hash, base_crng.key); if (account) { - crng_init_cnt += len; + crng_init_cnt += min_t(size_t, len, CRNG_INIT_CNT_THRESH - crng_init_cnt); if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) { ++base_crng.generation; crng_init = 1; @@ -474,8 +468,6 @@ static size_t crng_pre_init_inject(const void *input, size_t len, bool account) if (crng_init == 1) pr_notice("fast init done\n"); - - return len; } static void _get_random_bytes(void *buf, size_t nbytes) @@ -531,7 +523,6 @@ EXPORT_SYMBOL(get_random_bytes); static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes) { - bool large_request = nbytes > 256; ssize_t ret = 0; size_t len; u32 chacha_state[CHACHA_STATE_WORDS]; @@ -540,22 +531,23 @@ static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes) if (!nbytes) return 0; - len = min_t(size_t, 32, nbytes); - crng_make_state(chacha_state, output, len); - - if (copy_to_user(buf, output, len)) - return -EFAULT; - nbytes -= len; - buf += len; - ret += len; - - while (nbytes) { - if (large_request && need_resched()) { - if (signal_pending(current)) - break; - schedule(); - } + /* + * Immediately overwrite the ChaCha key at index 4 with random + * bytes, in case userspace causes copy_to_user() below to sleep + * forever, so that we still retain forward secrecy in that case. + */ + crng_make_state(chacha_state, (u8 *)&chacha_state[4], CHACHA_KEY_SIZE); + /* + * However, if we're doing a read of len <= 32, we don't need to + * use chacha_state after, so we can simply return those bytes to + * the user directly. + */ + if (nbytes <= CHACHA_KEY_SIZE) { + ret = copy_to_user(buf, &chacha_state[4], nbytes) ? -EFAULT : nbytes; + goto out_zero_chacha; + } + do { chacha20_block(chacha_state, output); if (unlikely(chacha_state[12] == 0)) ++chacha_state[13]; @@ -569,10 +561,18 @@ static ssize_t get_random_bytes_user(void __user *buf, size_t nbytes) nbytes -= len; buf += len; ret += len; - } - memzero_explicit(chacha_state, sizeof(chacha_state)); + BUILD_BUG_ON(PAGE_SIZE % CHACHA_BLOCK_SIZE != 0); + if (!(ret % PAGE_SIZE) && nbytes) { + if (signal_pending(current)) + break; + cond_resched(); + } + } while (nbytes); + memzero_explicit(output, sizeof(output)); +out_zero_chacha: + memzero_explicit(chacha_state, sizeof(chacha_state)); return ret; } @@ -1141,12 +1141,9 @@ void add_hwgenerator_randomness(const void *buffer, size_t count, size_t entropy) { if (unlikely(crng_init == 0 && entropy < POOL_MIN_BITS)) { - size_t ret = crng_pre_init_inject(buffer, count, true); - mix_pool_bytes(buffer, ret); - count -= ret; - buffer += ret; - if (!count || crng_init == 0) - return; + crng_pre_init_inject(buffer, count, true); + mix_pool_bytes(buffer, count); + return; } /* @@ -1545,6 +1542,13 @@ static ssize_t urandom_read(struct file *file, char __user *buf, size_t nbytes, { static int maxwarn = 10; + /* + * Opportunistically attempt to initialize the RNG on platforms that + * have fast cycle counters, but don't (for now) require it to succeed. + */ + if (!crng_ready()) + try_to_generate_entropy(); + if (!crng_ready() && maxwarn > 0) { maxwarn--; if (__ratelimit(&urandom_warning)) diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 8a7267d116b7..3f2182d66829 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -436,7 +436,6 @@ static int wait_for_media_ready(struct cxl_dev_state *cxlds) for (i = mbox_ready_timeout; i; i--) { u32 temp; - int rc; rc = pci_read_config_dword( pdev, d + CXL_DVSEC_RANGE_SIZE_LOW(0), &temp); diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index 511805dbeb75..4c9eb53ba3f8 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -12,6 +12,7 @@ dmabuf_selftests-y := \ selftest.o \ st-dma-fence.o \ st-dma-fence-chain.o \ + st-dma-fence-unwrap.o \ st-dma-resv.o obj-$(CONFIG_DMABUF_SELFTESTS) += dmabuf_selftests.o diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index df23239b04fc..79795857be3e 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -216,7 +216,8 @@ static bool dma_buf_poll_add_cb(struct dma_resv *resv, bool write, struct dma_fence *fence; int r; - dma_resv_for_each_fence(&cursor, resv, write, fence) { + dma_resv_for_each_fence(&cursor, resv, dma_resv_usage_rw(write), + fence) { dma_fence_get(fence); r = dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb); if (!r) @@ -443,7 +444,7 @@ err_alloc_file: * as a file descriptor by calling dma_buf_fd(). * * 2. Userspace passes this file-descriptors to all drivers it wants this buffer - * to share with: First the filedescriptor is converted to a &dma_buf using + * to share with: First the file descriptor is converted to a &dma_buf using * dma_buf_get(). Then the buffer is attached to the device using * dma_buf_attach(). * @@ -660,12 +661,24 @@ static struct sg_table * __map_dma_buf(struct dma_buf_attachment *attach, enum dma_data_direction direction) { struct sg_table *sg_table; + signed long ret; sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction); + if (IS_ERR_OR_NULL(sg_table)) + return sg_table; + + if (!dma_buf_attachment_is_dynamic(attach)) { + ret = dma_resv_wait_timeout(attach->dmabuf->resv, + DMA_RESV_USAGE_KERNEL, true, + MAX_SCHEDULE_TIMEOUT); + if (ret < 0) { + attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, + direction); + return ERR_PTR(ret); + } + } - if (!IS_ERR_OR_NULL(sg_table)) - mangle_sg_table(sg_table); - + mangle_sg_table(sg_table); return sg_table; } @@ -1124,7 +1137,8 @@ static int __dma_buf_begin_cpu_access(struct dma_buf *dmabuf, long ret; /* Wait on any implicit rendering fences */ - ret = dma_resv_wait_timeout(resv, write, true, MAX_SCHEDULE_TIMEOUT); + ret = dma_resv_wait_timeout(resv, dma_resv_usage_rw(write), + true, MAX_SCHEDULE_TIMEOUT); if (ret < 0) return ret; diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c index cb1bacb5a42b..5c8a7084577b 100644 --- a/drivers/dma-buf/dma-fence-array.c +++ b/drivers/dma-buf/dma-fence-array.c @@ -159,6 +159,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence_array *array; size_t size = sizeof(*array); + WARN_ON(!num_fences || !fences); + /* Allocate the callback structures behind the array. */ size += num_fences * sizeof(struct dma_fence_array_cb); array = kzalloc(size, GFP_KERNEL); @@ -219,3 +221,33 @@ bool dma_fence_match_context(struct dma_fence *fence, u64 context) return true; } EXPORT_SYMBOL(dma_fence_match_context); + +struct dma_fence *dma_fence_array_first(struct dma_fence *head) +{ + struct dma_fence_array *array; + + if (!head) + return NULL; + + array = to_dma_fence_array(head); + if (!array) + return head; + + if (!array->num_fences) + return NULL; + + return array->fences[0]; +} +EXPORT_SYMBOL(dma_fence_array_first); + +struct dma_fence *dma_fence_array_next(struct dma_fence *head, + unsigned int index) +{ + struct dma_fence_array *array = to_dma_fence_array(head); + + if (!array || index >= array->num_fences) + return NULL; + + return array->fences[index]; +} +EXPORT_SYMBOL(dma_fence_array_next); diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index b51416405e86..0cce6e4ec946 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -34,6 +34,7 @@ */ #include <linux/dma-resv.h> +#include <linux/dma-fence-array.h> #include <linux/export.h> #include <linux/mm.h> #include <linux/sched/mm.h> @@ -43,12 +44,12 @@ /** * DOC: Reservation Object Overview * - * The reservation object provides a mechanism to manage shared and - * exclusive fences associated with a buffer. A reservation object - * can have attached one exclusive fence (normally associated with - * write operations) or N shared fences (read operations). The RCU - * mechanism is used to protect read access to fences from locked - * write-side updates. + * The reservation object provides a mechanism to manage a container of + * dma_fence object associated with a resource. A reservation object + * can have any number of fences attaches to it. Each fence carries an usage + * parameter determining how the operation represented by the fence is using the + * resource. The RCU mechanism is used to protect read access to fences from + * locked write-side updates. * * See struct dma_resv for more details. */ @@ -56,33 +57,59 @@ DEFINE_WD_CLASS(reservation_ww_class); EXPORT_SYMBOL(reservation_ww_class); -/** - * dma_resv_list_alloc - allocate fence list - * @shared_max: number of fences we need space for - * +/* Mask for the lower fence pointer bits */ +#define DMA_RESV_LIST_MASK 0x3 + +struct dma_resv_list { + struct rcu_head rcu; + u32 num_fences, max_fences; + struct dma_fence __rcu *table[]; +}; + +/* Extract the fence and usage flags from an RCU protected entry in the list. */ +static void dma_resv_list_entry(struct dma_resv_list *list, unsigned int index, + struct dma_resv *resv, struct dma_fence **fence, + enum dma_resv_usage *usage) +{ + long tmp; + + tmp = (long)rcu_dereference_check(list->table[index], + resv ? dma_resv_held(resv) : true); + *fence = (struct dma_fence *)(tmp & ~DMA_RESV_LIST_MASK); + if (usage) + *usage = tmp & DMA_RESV_LIST_MASK; +} + +/* Set the fence and usage flags at the specific index in the list. */ +static void dma_resv_list_set(struct dma_resv_list *list, + unsigned int index, + struct dma_fence *fence, + enum dma_resv_usage usage) +{ + long tmp = ((long)fence) | usage; + + RCU_INIT_POINTER(list->table[index], (struct dma_fence *)tmp); +} + +/* * Allocate a new dma_resv_list and make sure to correctly initialize - * shared_max. + * max_fences. */ -static struct dma_resv_list *dma_resv_list_alloc(unsigned int shared_max) +static struct dma_resv_list *dma_resv_list_alloc(unsigned int max_fences) { struct dma_resv_list *list; - list = kmalloc(struct_size(list, shared, shared_max), GFP_KERNEL); + list = kmalloc(struct_size(list, table, max_fences), GFP_KERNEL); if (!list) return NULL; - list->shared_max = (ksize(list) - offsetof(typeof(*list), shared)) / - sizeof(*list->shared); + list->max_fences = (ksize(list) - offsetof(typeof(*list), table)) / + sizeof(*list->table); return list; } -/** - * dma_resv_list_free - free fence list - * @list: list to free - * - * Free a dma_resv_list and make sure to drop all references. - */ +/* Free a dma_resv_list and make sure to drop all references. */ static void dma_resv_list_free(struct dma_resv_list *list) { unsigned int i; @@ -90,9 +117,12 @@ static void dma_resv_list_free(struct dma_resv_list *list) if (!list) return; - for (i = 0; i < list->shared_count; ++i) - dma_fence_put(rcu_dereference_protected(list->shared[i], true)); + for (i = 0; i < list->num_fences; ++i) { + struct dma_fence *fence; + dma_resv_list_entry(list, i, NULL, &fence, NULL); + dma_fence_put(fence); + } kfree_rcu(list, rcu); } @@ -103,10 +133,8 @@ static void dma_resv_list_free(struct dma_resv_list *list) void dma_resv_init(struct dma_resv *obj) { ww_mutex_init(&obj->lock, &reservation_ww_class); - seqcount_ww_mutex_init(&obj->seq, &obj->lock); - RCU_INIT_POINTER(obj->fence, NULL); - RCU_INIT_POINTER(obj->fence_excl, NULL); + RCU_INIT_POINTER(obj->fences, NULL); } EXPORT_SYMBOL(dma_resv_init); @@ -116,51 +144,48 @@ EXPORT_SYMBOL(dma_resv_init); */ void dma_resv_fini(struct dma_resv *obj) { - struct dma_resv_list *fobj; - struct dma_fence *excl; - /* * This object should be dead and all references must have * been released to it, so no need to be protected with rcu. */ - excl = rcu_dereference_protected(obj->fence_excl, 1); - if (excl) - dma_fence_put(excl); - - fobj = rcu_dereference_protected(obj->fence, 1); - dma_resv_list_free(fobj); + dma_resv_list_free(rcu_dereference_protected(obj->fences, true)); ww_mutex_destroy(&obj->lock); } EXPORT_SYMBOL(dma_resv_fini); +/* Dereference the fences while ensuring RCU rules */ +static inline struct dma_resv_list *dma_resv_fences_list(struct dma_resv *obj) +{ + return rcu_dereference_check(obj->fences, dma_resv_held(obj)); +} + /** - * dma_resv_reserve_shared - Reserve space to add shared fences to - * a dma_resv. + * dma_resv_reserve_fences - Reserve space to add fences to a dma_resv object. * @obj: reservation object * @num_fences: number of fences we want to add * - * Should be called before dma_resv_add_shared_fence(). Must - * be called with @obj locked through dma_resv_lock(). + * Should be called before dma_resv_add_fence(). Must be called with @obj + * locked through dma_resv_lock(). * * Note that the preallocated slots need to be re-reserved if @obj is unlocked - * at any time before calling dma_resv_add_shared_fence(). This is validated - * when CONFIG_DEBUG_MUTEXES is enabled. + * at any time before calling dma_resv_add_fence(). This is validated when + * CONFIG_DEBUG_MUTEXES is enabled. * * RETURNS * Zero for success, or -errno */ -int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences) +int dma_resv_reserve_fences(struct dma_resv *obj, unsigned int num_fences) { struct dma_resv_list *old, *new; unsigned int i, j, k, max; dma_resv_assert_held(obj); - old = dma_resv_shared_list(obj); - if (old && old->shared_max) { - if ((old->shared_count + num_fences) <= old->shared_max) + old = dma_resv_fences_list(obj); + if (old && old->max_fences) { + if ((old->num_fences + num_fences) <= old->max_fences) return 0; - max = max(old->shared_count + num_fences, old->shared_max * 2); + max = max(old->num_fences + num_fences, old->max_fences * 2); } else { max = max(4ul, roundup_pow_of_two(num_fences)); } @@ -175,27 +200,27 @@ int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences) * references from the old struct are carried over to * the new. */ - for (i = 0, j = 0, k = max; i < (old ? old->shared_count : 0); ++i) { + for (i = 0, j = 0, k = max; i < (old ? old->num_fences : 0); ++i) { + enum dma_resv_usage usage; struct dma_fence *fence; - fence = rcu_dereference_protected(old->shared[i], - dma_resv_held(obj)); + dma_resv_list_entry(old, i, obj, &fence, &usage); if (dma_fence_is_signaled(fence)) - RCU_INIT_POINTER(new->shared[--k], fence); + RCU_INIT_POINTER(new->table[--k], fence); else - RCU_INIT_POINTER(new->shared[j++], fence); + dma_resv_list_set(new, j++, fence, usage); } - new->shared_count = j; + new->num_fences = j; /* * We are not changing the effective set of fences here so can * merely update the pointer to the new array; both existing * readers and new readers will see exactly the same set of - * active (unsignaled) shared fences. Individual fences and the + * active (unsignaled) fences. Individual fences and the * old array are protected by RCU and so will not vanish under * the gaze of the rcu_read_lock() readers. */ - rcu_assign_pointer(obj->fence, new); + rcu_assign_pointer(obj->fences, new); if (!old) return 0; @@ -204,7 +229,7 @@ int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences) for (i = k; i < max; ++i) { struct dma_fence *fence; - fence = rcu_dereference_protected(new->shared[i], + fence = rcu_dereference_protected(new->table[i], dma_resv_held(obj)); dma_fence_put(fence); } @@ -212,41 +237,43 @@ int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences) return 0; } -EXPORT_SYMBOL(dma_resv_reserve_shared); +EXPORT_SYMBOL(dma_resv_reserve_fences); #ifdef CONFIG_DEBUG_MUTEXES /** - * dma_resv_reset_shared_max - reset shared fences for debugging + * dma_resv_reset_max_fences - reset fences for debugging * @obj: the dma_resv object to reset * - * Reset the number of pre-reserved shared slots to test that drivers do - * correct slot allocation using dma_resv_reserve_shared(). See also - * &dma_resv_list.shared_max. + * Reset the number of pre-reserved fence slots to test that drivers do + * correct slot allocation using dma_resv_reserve_fences(). See also + * &dma_resv_list.max_fences. */ -void dma_resv_reset_shared_max(struct dma_resv *obj) +void dma_resv_reset_max_fences(struct dma_resv *obj) { - struct dma_resv_list *fences = dma_resv_shared_list(obj); + struct dma_resv_list *fences = dma_resv_fences_list(obj); dma_resv_assert_held(obj); - /* Test shared fence slot reservation */ + /* Test fence slot reservation */ if (fences) - fences->shared_max = fences->shared_count; + fences->max_fences = fences->num_fences; } -EXPORT_SYMBOL(dma_resv_reset_shared_max); +EXPORT_SYMBOL(dma_resv_reset_max_fences); #endif /** - * dma_resv_add_shared_fence - Add a fence to a shared slot + * dma_resv_add_fence - Add a fence to the dma_resv obj * @obj: the reservation object - * @fence: the shared fence to add + * @fence: the fence to add + * @usage: how the fence is used, see enum dma_resv_usage * - * Add a fence to a shared slot, @obj must be locked with dma_resv_lock(), and - * dma_resv_reserve_shared() has been called. + * Add a fence to a slot, @obj must be locked with dma_resv_lock(), and + * dma_resv_reserve_fences() has been called. * * See also &dma_resv.fence for a discussion of the semantics. */ -void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence) +void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence, + enum dma_resv_usage usage) { struct dma_resv_list *fobj; struct dma_fence *old; @@ -261,118 +288,105 @@ void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence) */ WARN_ON(dma_fence_is_container(fence)); - fobj = dma_resv_shared_list(obj); - count = fobj->shared_count; - - write_seqcount_begin(&obj->seq); + fobj = dma_resv_fences_list(obj); + count = fobj->num_fences; for (i = 0; i < count; ++i) { - - old = rcu_dereference_protected(fobj->shared[i], - dma_resv_held(obj)); - if (old->context == fence->context || - dma_fence_is_signaled(old)) - goto replace; + enum dma_resv_usage old_usage; + + dma_resv_list_entry(fobj, i, obj, &old, &old_usage); + if ((old->context == fence->context && old_usage >= usage) || + dma_fence_is_signaled(old)) { + dma_resv_list_set(fobj, i, fence, usage); + dma_fence_put(old); + return; + } } - BUG_ON(fobj->shared_count >= fobj->shared_max); - old = NULL; + BUG_ON(fobj->num_fences >= fobj->max_fences); count++; -replace: - RCU_INIT_POINTER(fobj->shared[i], fence); - /* pointer update must be visible before we extend the shared_count */ - smp_store_mb(fobj->shared_count, count); - - write_seqcount_end(&obj->seq); - dma_fence_put(old); + dma_resv_list_set(fobj, i, fence, usage); + /* pointer update must be visible before we extend the num_fences */ + smp_store_mb(fobj->num_fences, count); } -EXPORT_SYMBOL(dma_resv_add_shared_fence); +EXPORT_SYMBOL(dma_resv_add_fence); /** - * dma_resv_add_excl_fence - Add an exclusive fence. + * dma_resv_replace_fences - replace fences in the dma_resv obj * @obj: the reservation object - * @fence: the exclusive fence to add + * @context: the context of the fences to replace + * @replacement: the new fence to use instead + * @usage: how the new fence is used, see enum dma_resv_usage + * + * Replace fences with a specified context with a new fence. Only valid if the + * operation represented by the original fence has no longer access to the + * resources represented by the dma_resv object when the new fence completes. * - * Add a fence to the exclusive slot. @obj must be locked with dma_resv_lock(). - * Note that this function replaces all fences attached to @obj, see also - * &dma_resv.fence_excl for a discussion of the semantics. + * And example for using this is replacing a preemption fence with a page table + * update fence which makes the resource inaccessible. */ -void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence) +void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context, + struct dma_fence *replacement, + enum dma_resv_usage usage) { - struct dma_fence *old_fence = dma_resv_excl_fence(obj); - struct dma_resv_list *old; - u32 i = 0; + struct dma_resv_list *list; + unsigned int i; dma_resv_assert_held(obj); - old = dma_resv_shared_list(obj); - if (old) - i = old->shared_count; - - dma_fence_get(fence); - - write_seqcount_begin(&obj->seq); - /* write_seqcount_begin provides the necessary memory barrier */ - RCU_INIT_POINTER(obj->fence_excl, fence); - if (old) - old->shared_count = 0; - write_seqcount_end(&obj->seq); + list = dma_resv_fences_list(obj); + for (i = 0; list && i < list->num_fences; ++i) { + struct dma_fence *old; - /* inplace update, no shared fences */ - while (i--) - dma_fence_put(rcu_dereference_protected(old->shared[i], - dma_resv_held(obj))); + dma_resv_list_entry(list, i, obj, &old, NULL); + if (old->context != context) + continue; - dma_fence_put(old_fence); + dma_resv_list_set(list, i, replacement, usage); + dma_fence_put(old); + } } -EXPORT_SYMBOL(dma_resv_add_excl_fence); +EXPORT_SYMBOL(dma_resv_replace_fences); -/* Restart the iterator by initializing all the necessary fields, but not the - * relation to the dma_resv object. */ +/* Restart the unlocked iteration by initializing the cursor object. */ static void dma_resv_iter_restart_unlocked(struct dma_resv_iter *cursor) { - cursor->seq = read_seqcount_begin(&cursor->obj->seq); - cursor->index = -1; - cursor->shared_count = 0; - if (cursor->all_fences) { - cursor->fences = dma_resv_shared_list(cursor->obj); - if (cursor->fences) - cursor->shared_count = cursor->fences->shared_count; - } else { - cursor->fences = NULL; - } + cursor->index = 0; + cursor->num_fences = 0; + cursor->fences = dma_resv_fences_list(cursor->obj); + if (cursor->fences) + cursor->num_fences = cursor->fences->num_fences; cursor->is_restarted = true; } /* Walk to the next not signaled fence and grab a reference to it */ static void dma_resv_iter_walk_unlocked(struct dma_resv_iter *cursor) { - struct dma_resv *obj = cursor->obj; + if (!cursor->fences) + return; do { /* Drop the reference from the previous round */ dma_fence_put(cursor->fence); - if (cursor->index == -1) { - cursor->fence = dma_resv_excl_fence(obj); - cursor->index++; - if (!cursor->fence) - continue; - - } else if (!cursor->fences || - cursor->index >= cursor->shared_count) { + if (cursor->index >= cursor->num_fences) { cursor->fence = NULL; break; - } else { - struct dma_resv_list *fences = cursor->fences; - unsigned int idx = cursor->index++; - - cursor->fence = rcu_dereference(fences->shared[idx]); } + + dma_resv_list_entry(cursor->fences, cursor->index++, + cursor->obj, &cursor->fence, + &cursor->fence_usage); cursor->fence = dma_fence_get_rcu(cursor->fence); - if (!cursor->fence || !dma_fence_is_signaled(cursor->fence)) + if (!cursor->fence) { + dma_resv_iter_restart_unlocked(cursor); + continue; + } + + if (!dma_fence_is_signaled(cursor->fence) && + cursor->usage >= cursor->fence_usage) break; } while (true); } @@ -395,7 +409,7 @@ struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor) do { dma_resv_iter_restart_unlocked(cursor); dma_resv_iter_walk_unlocked(cursor); - } while (read_seqcount_retry(&cursor->obj->seq, cursor->seq)); + } while (dma_resv_fences_list(cursor->obj) != cursor->fences); rcu_read_unlock(); return cursor->fence; @@ -418,13 +432,13 @@ struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor) rcu_read_lock(); cursor->is_restarted = false; - restart = read_seqcount_retry(&cursor->obj->seq, cursor->seq); + restart = dma_resv_fences_list(cursor->obj) != cursor->fences; do { if (restart) dma_resv_iter_restart_unlocked(cursor); dma_resv_iter_walk_unlocked(cursor); restart = true; - } while (read_seqcount_retry(&cursor->obj->seq, cursor->seq)); + } while (dma_resv_fences_list(cursor->obj) != cursor->fences); rcu_read_unlock(); return cursor->fence; @@ -447,15 +461,9 @@ struct dma_fence *dma_resv_iter_first(struct dma_resv_iter *cursor) dma_resv_assert_held(cursor->obj); cursor->index = 0; - if (cursor->all_fences) - cursor->fences = dma_resv_shared_list(cursor->obj); - else - cursor->fences = NULL; - - fence = dma_resv_excl_fence(cursor->obj); - if (!fence) - fence = dma_resv_iter_next(cursor); + cursor->fences = dma_resv_fences_list(cursor->obj); + fence = dma_resv_iter_next(cursor); cursor->is_restarted = true; return fence; } @@ -470,17 +478,22 @@ EXPORT_SYMBOL_GPL(dma_resv_iter_first); */ struct dma_fence *dma_resv_iter_next(struct dma_resv_iter *cursor) { - unsigned int idx; + struct dma_fence *fence; dma_resv_assert_held(cursor->obj); cursor->is_restarted = false; - if (!cursor->fences || cursor->index >= cursor->fences->shared_count) - return NULL; - idx = cursor->index++; - return rcu_dereference_protected(cursor->fences->shared[idx], - dma_resv_held(cursor->obj)); + do { + if (!cursor->fences || + cursor->index >= cursor->fences->num_fences) + return NULL; + + dma_resv_list_entry(cursor->fences, cursor->index++, + cursor->obj, &fence, &cursor->fence_usage); + } while (cursor->fence_usage > cursor->usage); + + return fence; } EXPORT_SYMBOL_GPL(dma_resv_iter_next); @@ -495,60 +508,43 @@ int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src) { struct dma_resv_iter cursor; struct dma_resv_list *list; - struct dma_fence *f, *excl; + struct dma_fence *f; dma_resv_assert_held(dst); list = NULL; - excl = NULL; - dma_resv_iter_begin(&cursor, src, true); + dma_resv_iter_begin(&cursor, src, DMA_RESV_USAGE_BOOKKEEP); dma_resv_for_each_fence_unlocked(&cursor, f) { if (dma_resv_iter_is_restarted(&cursor)) { dma_resv_list_free(list); - dma_fence_put(excl); - - if (cursor.shared_count) { - list = dma_resv_list_alloc(cursor.shared_count); - if (!list) { - dma_resv_iter_end(&cursor); - return -ENOMEM; - } - list->shared_count = 0; - - } else { - list = NULL; + list = dma_resv_list_alloc(cursor.num_fences); + if (!list) { + dma_resv_iter_end(&cursor); + return -ENOMEM; } - excl = NULL; + list->num_fences = 0; } dma_fence_get(f); - if (dma_resv_iter_is_exclusive(&cursor)) - excl = f; - else - RCU_INIT_POINTER(list->shared[list->shared_count++], f); + dma_resv_list_set(list, list->num_fences++, f, + dma_resv_iter_usage(&cursor)); } dma_resv_iter_end(&cursor); - write_seqcount_begin(&dst->seq); - excl = rcu_replace_pointer(dst->fence_excl, excl, dma_resv_held(dst)); - list = rcu_replace_pointer(dst->fence, list, dma_resv_held(dst)); - write_seqcount_end(&dst->seq); - + list = rcu_replace_pointer(dst->fences, list, dma_resv_held(dst)); dma_resv_list_free(list); - dma_fence_put(excl); - return 0; } EXPORT_SYMBOL(dma_resv_copy_fences); /** - * dma_resv_get_fences - Get an object's shared and exclusive + * dma_resv_get_fences - Get an object's fences * fences without update side lock held * @obj: the reservation object - * @write: true if we should return all fences + * @usage: controls which fences to include, see enum dma_resv_usage. * @num_fences: the number of fences returned * @fences: the array of fence ptrs returned (array is krealloc'd to the * required size, and must be freed by caller) @@ -556,7 +552,7 @@ EXPORT_SYMBOL(dma_resv_copy_fences); * Retrieve all fences from the reservation object. * Returns either zero or -ENOMEM. */ -int dma_resv_get_fences(struct dma_resv *obj, bool write, +int dma_resv_get_fences(struct dma_resv *obj, enum dma_resv_usage usage, unsigned int *num_fences, struct dma_fence ***fences) { struct dma_resv_iter cursor; @@ -565,7 +561,7 @@ int dma_resv_get_fences(struct dma_resv *obj, bool write, *num_fences = 0; *fences = NULL; - dma_resv_iter_begin(&cursor, obj, write); + dma_resv_iter_begin(&cursor, obj, usage); dma_resv_for_each_fence_unlocked(&cursor, fence) { if (dma_resv_iter_is_restarted(&cursor)) { @@ -574,7 +570,7 @@ int dma_resv_get_fences(struct dma_resv *obj, bool write, while (*num_fences) dma_fence_put((*fences)[--(*num_fences)]); - count = cursor.shared_count + 1; + count = cursor.num_fences + 1; /* Eventually re-allocate the array */ *fences = krealloc_array(*fences, count, @@ -595,10 +591,62 @@ int dma_resv_get_fences(struct dma_resv *obj, bool write, EXPORT_SYMBOL_GPL(dma_resv_get_fences); /** - * dma_resv_wait_timeout - Wait on reservation's objects - * shared and/or exclusive fences. + * dma_resv_get_singleton - Get a single fence for all the fences + * @obj: the reservation object + * @usage: controls which fences to include, see enum dma_resv_usage. + * @fence: the resulting fence + * + * Get a single fence representing all the fences inside the resv object. + * Returns either 0 for success or -ENOMEM. + * + * Warning: This can't be used like this when adding the fence back to the resv + * object since that can lead to stack corruption when finalizing the + * dma_fence_array. + * + * Returns 0 on success and negative error values on failure. + */ +int dma_resv_get_singleton(struct dma_resv *obj, enum dma_resv_usage usage, + struct dma_fence **fence) +{ + struct dma_fence_array *array; + struct dma_fence **fences; + unsigned count; + int r; + + r = dma_resv_get_fences(obj, usage, &count, &fences); + if (r) + return r; + + if (count == 0) { + *fence = NULL; + return 0; + } + + if (count == 1) { + *fence = fences[0]; + kfree(fences); + return 0; + } + + array = dma_fence_array_create(count, fences, + dma_fence_context_alloc(1), + 1, false); + if (!array) { + while (count--) + dma_fence_put(fences[count]); + kfree(fences); + return -ENOMEM; + } + + *fence = &array->base; + return 0; +} +EXPORT_SYMBOL_GPL(dma_resv_get_singleton); + +/** + * dma_resv_wait_timeout - Wait on reservation's objects fences * @obj: the reservation object - * @wait_all: if true, wait on all fences, else wait on just exclusive fence + * @usage: controls which fences to include, see enum dma_resv_usage. * @intr: if true, do interruptible wait * @timeout: timeout value in jiffies or zero to return immediately * @@ -608,14 +656,14 @@ EXPORT_SYMBOL_GPL(dma_resv_get_fences); * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or * greater than zer on success. */ -long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, - unsigned long timeout) +long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage, + bool intr, unsigned long timeout) { long ret = timeout ? timeout : 1; struct dma_resv_iter cursor; struct dma_fence *fence; - dma_resv_iter_begin(&cursor, obj, wait_all); + dma_resv_iter_begin(&cursor, obj, usage); dma_resv_for_each_fence_unlocked(&cursor, fence) { ret = dma_fence_wait_timeout(fence, intr, ret); @@ -635,8 +683,7 @@ EXPORT_SYMBOL_GPL(dma_resv_wait_timeout); * dma_resv_test_signaled - Test if a reservation object's fences have been * signaled. * @obj: the reservation object - * @test_all: if true, test all fences, otherwise only test the exclusive - * fence + * @usage: controls which fences to include, see enum dma_resv_usage. * * Callers are not required to hold specific locks, but maybe hold * dma_resv_lock() already. @@ -645,12 +692,12 @@ EXPORT_SYMBOL_GPL(dma_resv_wait_timeout); * * True if all fences signaled, else false. */ -bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all) +bool dma_resv_test_signaled(struct dma_resv *obj, enum dma_resv_usage usage) { struct dma_resv_iter cursor; struct dma_fence *fence; - dma_resv_iter_begin(&cursor, obj, test_all); + dma_resv_iter_begin(&cursor, obj, usage); dma_resv_for_each_fence_unlocked(&cursor, fence) { dma_resv_iter_end(&cursor); return false; @@ -670,13 +717,13 @@ EXPORT_SYMBOL_GPL(dma_resv_test_signaled); */ void dma_resv_describe(struct dma_resv *obj, struct seq_file *seq) { + static const char *usage[] = { "kernel", "write", "read", "bookkeep" }; struct dma_resv_iter cursor; struct dma_fence *fence; - dma_resv_for_each_fence(&cursor, obj, true, fence) { + dma_resv_for_each_fence(&cursor, obj, DMA_RESV_USAGE_READ, fence) { seq_printf(seq, "\t%s fence:", - dma_resv_iter_is_exclusive(&cursor) ? - "Exclusive" : "Shared"); + usage[dma_resv_iter_usage(&cursor)]); dma_fence_describe(fence, seq); } } diff --git a/drivers/dma-buf/selftests.h b/drivers/dma-buf/selftests.h index 97d73aaa31da..851965867d9c 100644 --- a/drivers/dma-buf/selftests.h +++ b/drivers/dma-buf/selftests.h @@ -12,4 +12,5 @@ selftest(sanitycheck, __sanitycheck__) /* keep first (igt selfcheck) */ selftest(dma_fence, dma_fence) selftest(dma_fence_chain, dma_fence_chain) +selftest(dma_fence_unwrap, dma_fence_unwrap) selftest(dma_resv, dma_resv) diff --git a/drivers/dma-buf/st-dma-fence-unwrap.c b/drivers/dma-buf/st-dma-fence-unwrap.c new file mode 100644 index 000000000000..039f016b57be --- /dev/null +++ b/drivers/dma-buf/st-dma-fence-unwrap.c @@ -0,0 +1,261 @@ +// SPDX-License-Identifier: MIT + +/* + * Copyright (C) 2022 Advanced Micro Devices, Inc. + */ + +#include <linux/dma-fence-unwrap.h> +#if 0 +#include <linux/kernel.h> +#include <linux/kthread.h> +#include <linux/mm.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/random.h> +#endif + +#include "selftest.h" + +#define CHAIN_SZ (4 << 10) + +static inline struct mock_fence { + struct dma_fence base; + spinlock_t lock; +} *to_mock_fence(struct dma_fence *f) { + return container_of(f, struct mock_fence, base); +} + +static const char *mock_name(struct dma_fence *f) +{ + return "mock"; +} + +static const struct dma_fence_ops mock_ops = { + .get_driver_name = mock_name, + .get_timeline_name = mock_name, +}; + +static struct dma_fence *mock_fence(void) +{ + struct mock_fence *f; + + f = kmalloc(sizeof(*f), GFP_KERNEL); + if (!f) + return NULL; + + spin_lock_init(&f->lock); + dma_fence_init(&f->base, &mock_ops, &f->lock, 0, 0); + + return &f->base; +} + +static struct dma_fence *mock_array(unsigned int num_fences, ...) +{ + struct dma_fence_array *array; + struct dma_fence **fences; + va_list valist; + int i; + + fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL); + if (!fences) + return NULL; + + va_start(valist, num_fences); + for (i = 0; i < num_fences; ++i) + fences[i] = va_arg(valist, typeof(*fences)); + va_end(valist); + + array = dma_fence_array_create(num_fences, fences, + dma_fence_context_alloc(1), + 1, false); + if (!array) + goto cleanup; + return &array->base; + +cleanup: + for (i = 0; i < num_fences; ++i) + dma_fence_put(fences[i]); + kfree(fences); + return NULL; +} + +static struct dma_fence *mock_chain(struct dma_fence *prev, + struct dma_fence *fence) +{ + struct dma_fence_chain *f; + + f = dma_fence_chain_alloc(); + if (!f) { + dma_fence_put(prev); + dma_fence_put(fence); + return NULL; + } + + dma_fence_chain_init(f, prev, fence, 1); + return &f->base; +} + +static int sanitycheck(void *arg) +{ + struct dma_fence *f, *chain, *array; + int err = 0; + + f = mock_fence(); + if (!f) + return -ENOMEM; + + array = mock_array(1, f); + if (!array) + return -ENOMEM; + + chain = mock_chain(NULL, array); + if (!chain) + return -ENOMEM; + + dma_fence_signal(f); + dma_fence_put(chain); + return err; +} + +static int unwrap_array(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *array; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + array = mock_array(2, f1, f2); + if (!array) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, array) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(array); + return 0; +} + +static int unwrap_chain(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *chain; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + chain = mock_chain(f1, f2); + if (!chain) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, chain) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(chain); + return 0; +} + +static int unwrap_chain_array(void *arg) +{ + struct dma_fence *fence, *f1, *f2, *array, *chain; + struct dma_fence_unwrap iter; + int err = 0; + + f1 = mock_fence(); + if (!f1) + return -ENOMEM; + + f2 = mock_fence(); + if (!f2) { + dma_fence_put(f1); + return -ENOMEM; + } + + array = mock_array(2, f1, f2); + if (!array) + return -ENOMEM; + + chain = mock_chain(NULL, array); + if (!chain) + return -ENOMEM; + + dma_fence_unwrap_for_each(fence, &iter, chain) { + if (fence == f1) { + f1 = NULL; + } else if (fence == f2) { + f2 = NULL; + } else { + pr_err("Unexpected fence!\n"); + err = -EINVAL; + } + } + + if (f1 || f2) { + pr_err("Not all fences seen!\n"); + err = -EINVAL; + } + + dma_fence_signal(f1); + dma_fence_signal(f2); + dma_fence_put(chain); + return 0; +} + +int dma_fence_unwrap(void) +{ + static const struct subtest tests[] = { + SUBTEST(sanitycheck), + SUBTEST(unwrap_array), + SUBTEST(unwrap_chain), + SUBTEST(unwrap_chain_array), + }; + + return subtests(tests, NULL); +} diff --git a/drivers/dma-buf/st-dma-resv.c b/drivers/dma-buf/st-dma-resv.c index cbe999c6e7a6..813779e3c9be 100644 --- a/drivers/dma-buf/st-dma-resv.c +++ b/drivers/dma-buf/st-dma-resv.c @@ -58,8 +58,9 @@ static int sanitycheck(void *arg) return r; } -static int test_signaling(void *arg, bool shared) +static int test_signaling(void *arg) { + enum dma_resv_usage usage = (unsigned long)arg; struct dma_resv resv; struct dma_fence *f; int r; @@ -75,25 +76,20 @@ static int test_signaling(void *arg, bool shared) goto err_free; } - if (shared) { - r = dma_resv_reserve_shared(&resv, 1); - if (r) { - pr_err("Resv shared slot allocation failed\n"); - goto err_unlock; - } - - dma_resv_add_shared_fence(&resv, f); - } else { - dma_resv_add_excl_fence(&resv, f); + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + goto err_unlock; } - if (dma_resv_test_signaled(&resv, shared)) { + dma_resv_add_fence(&resv, f, usage); + if (dma_resv_test_signaled(&resv, usage)) { pr_err("Resv unexpectedly signaled\n"); r = -EINVAL; goto err_unlock; } dma_fence_signal(f); - if (!dma_resv_test_signaled(&resv, shared)) { + if (!dma_resv_test_signaled(&resv, usage)) { pr_err("Resv not reporting signaled\n"); r = -EINVAL; goto err_unlock; @@ -106,18 +102,9 @@ err_free: return r; } -static int test_excl_signaling(void *arg) -{ - return test_signaling(arg, false); -} - -static int test_shared_signaling(void *arg) -{ - return test_signaling(arg, true); -} - -static int test_for_each(void *arg, bool shared) +static int test_for_each(void *arg) { + enum dma_resv_usage usage = (unsigned long)arg; struct dma_resv_iter cursor; struct dma_fence *f, *fence; struct dma_resv resv; @@ -134,20 +121,16 @@ static int test_for_each(void *arg, bool shared) goto err_free; } - if (shared) { - r = dma_resv_reserve_shared(&resv, 1); - if (r) { - pr_err("Resv shared slot allocation failed\n"); - goto err_unlock; - } - - dma_resv_add_shared_fence(&resv, f); - } else { - dma_resv_add_excl_fence(&resv, f); + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + goto err_unlock; } + dma_resv_add_fence(&resv, f, usage); + r = -ENOENT; - dma_resv_for_each_fence(&cursor, &resv, shared, fence) { + dma_resv_for_each_fence(&cursor, &resv, usage, fence) { if (!r) { pr_err("More than one fence found\n"); r = -EINVAL; @@ -158,7 +141,7 @@ static int test_for_each(void *arg, bool shared) r = -EINVAL; goto err_unlock; } - if (dma_resv_iter_is_exclusive(&cursor) != !shared) { + if (dma_resv_iter_usage(&cursor) != usage) { pr_err("Unexpected fence usage\n"); r = -EINVAL; goto err_unlock; @@ -178,18 +161,9 @@ err_free: return r; } -static int test_excl_for_each(void *arg) -{ - return test_for_each(arg, false); -} - -static int test_shared_for_each(void *arg) -{ - return test_for_each(arg, true); -} - -static int test_for_each_unlocked(void *arg, bool shared) +static int test_for_each_unlocked(void *arg) { + enum dma_resv_usage usage = (unsigned long)arg; struct dma_resv_iter cursor; struct dma_fence *f, *fence; struct dma_resv resv; @@ -206,22 +180,18 @@ static int test_for_each_unlocked(void *arg, bool shared) goto err_free; } - if (shared) { - r = dma_resv_reserve_shared(&resv, 1); - if (r) { - pr_err("Resv shared slot allocation failed\n"); - dma_resv_unlock(&resv); - goto err_free; - } - - dma_resv_add_shared_fence(&resv, f); - } else { - dma_resv_add_excl_fence(&resv, f); + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + dma_resv_unlock(&resv); + goto err_free; } + + dma_resv_add_fence(&resv, f, usage); dma_resv_unlock(&resv); r = -ENOENT; - dma_resv_iter_begin(&cursor, &resv, shared); + dma_resv_iter_begin(&cursor, &resv, usage); dma_resv_for_each_fence_unlocked(&cursor, fence) { if (!r) { pr_err("More than one fence found\n"); @@ -237,7 +207,7 @@ static int test_for_each_unlocked(void *arg, bool shared) r = -EINVAL; goto err_iter_end; } - if (dma_resv_iter_is_exclusive(&cursor) != !shared) { + if (dma_resv_iter_usage(&cursor) != usage) { pr_err("Unexpected fence usage\n"); r = -EINVAL; goto err_iter_end; @@ -247,7 +217,7 @@ static int test_for_each_unlocked(void *arg, bool shared) if (r == -ENOENT) { r = -EINVAL; /* That should trigger an restart */ - cursor.seq--; + cursor.fences = (void*)~0; } else if (r == -EINVAL) { r = 0; } @@ -263,18 +233,9 @@ err_free: return r; } -static int test_excl_for_each_unlocked(void *arg) -{ - return test_for_each_unlocked(arg, false); -} - -static int test_shared_for_each_unlocked(void *arg) -{ - return test_for_each_unlocked(arg, true); -} - -static int test_get_fences(void *arg, bool shared) +static int test_get_fences(void *arg) { + enum dma_resv_usage usage = (unsigned long)arg; struct dma_fence *f, **fences = NULL; struct dma_resv resv; int r, i; @@ -290,21 +251,17 @@ static int test_get_fences(void *arg, bool shared) goto err_resv; } - if (shared) { - r = dma_resv_reserve_shared(&resv, 1); - if (r) { - pr_err("Resv shared slot allocation failed\n"); - dma_resv_unlock(&resv); - goto err_resv; - } - - dma_resv_add_shared_fence(&resv, f); - } else { - dma_resv_add_excl_fence(&resv, f); + r = dma_resv_reserve_fences(&resv, 1); + if (r) { + pr_err("Resv shared slot allocation failed\n"); + dma_resv_unlock(&resv); + goto err_resv; } + + dma_resv_add_fence(&resv, f, usage); dma_resv_unlock(&resv); - r = dma_resv_get_fences(&resv, shared, &i, &fences); + r = dma_resv_get_fences(&resv, usage, &i, &fences); if (r) { pr_err("get_fences failed\n"); goto err_free; @@ -326,30 +283,24 @@ err_resv: return r; } -static int test_excl_get_fences(void *arg) -{ - return test_get_fences(arg, false); -} - -static int test_shared_get_fences(void *arg) -{ - return test_get_fences(arg, true); -} - int dma_resv(void) { static const struct subtest tests[] = { SUBTEST(sanitycheck), - SUBTEST(test_excl_signaling), - SUBTEST(test_shared_signaling), - SUBTEST(test_excl_for_each), - SUBTEST(test_shared_for_each), - SUBTEST(test_excl_for_each_unlocked), - SUBTEST(test_shared_for_each_unlocked), - SUBTEST(test_excl_get_fences), - SUBTEST(test_shared_get_fences), + SUBTEST(test_signaling), + SUBTEST(test_for_each), + SUBTEST(test_for_each_unlocked), + SUBTEST(test_get_fences), }; + enum dma_resv_usage usage; + int r; spin_lock_init(&fence_lock); - return subtests(tests, NULL); + for (usage = DMA_RESV_USAGE_KERNEL; usage <= DMA_RESV_USAGE_BOOKKEEP; + ++usage) { + r = subtests(tests, (void *)(unsigned long)usage); + if (r) + return r; + } + return 0; } diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index 394e6e1e9686..514d213261df 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -5,6 +5,7 @@ * Copyright (C) 2012 Google, Inc. */ +#include <linux/dma-fence-unwrap.h> #include <linux/export.h> #include <linux/file.h> #include <linux/fs.h> @@ -172,20 +173,6 @@ static int sync_file_set_fence(struct sync_file *sync_file, return 0; } -static struct dma_fence **get_fences(struct sync_file *sync_file, - int *num_fences) -{ - if (dma_fence_is_array(sync_file->fence)) { - struct dma_fence_array *array = to_dma_fence_array(sync_file->fence); - - *num_fences = array->num_fences; - return array->fences; - } - - *num_fences = 1; - return &sync_file->fence; -} - static void add_fence(struct dma_fence **fences, int *i, struct dma_fence *fence) { @@ -210,86 +197,97 @@ static void add_fence(struct dma_fence **fences, static struct sync_file *sync_file_merge(const char *name, struct sync_file *a, struct sync_file *b) { + struct dma_fence *a_fence, *b_fence, **fences; + struct dma_fence_unwrap a_iter, b_iter; + unsigned int index, num_fences; struct sync_file *sync_file; - struct dma_fence **fences = NULL, **nfences, **a_fences, **b_fences; - int i = 0, i_a, i_b, num_fences, a_num_fences, b_num_fences; sync_file = sync_file_alloc(); if (!sync_file) return NULL; - a_fences = get_fences(a, &a_num_fences); - b_fences = get_fences(b, &b_num_fences); - if (a_num_fences > INT_MAX - b_num_fences) - goto err; + num_fences = 0; + dma_fence_unwrap_for_each(a_fence, &a_iter, a->fence) + ++num_fences; + dma_fence_unwrap_for_each(b_fence, &b_iter, b->fence) + ++num_fences; - num_fences = a_num_fences + b_num_fences; + if (num_fences > INT_MAX) + goto err_free_sync_file; fences = kcalloc(num_fences, sizeof(*fences), GFP_KERNEL); if (!fences) - goto err; + goto err_free_sync_file; /* - * Assume sync_file a and b are both ordered and have no - * duplicates with the same context. + * We can't guarantee that fences in both a and b are ordered, but it is + * still quite likely. * - * If a sync_file can only be created with sync_file_merge - * and sync_file_create, this is a reasonable assumption. + * So attempt to order the fences as we pass over them and merge fences + * with the same context. */ - for (i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) { - struct dma_fence *pt_a = a_fences[i_a]; - struct dma_fence *pt_b = b_fences[i_b]; - if (pt_a->context < pt_b->context) { - add_fence(fences, &i, pt_a); + index = 0; + for (a_fence = dma_fence_unwrap_first(a->fence, &a_iter), + b_fence = dma_fence_unwrap_first(b->fence, &b_iter); + a_fence || b_fence; ) { + + if (!b_fence) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + + } else if (!a_fence) { + add_fence(fences, &index, b_fence); + b_fence = dma_fence_unwrap_next(&b_iter); + + } else if (a_fence->context < b_fence->context) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); - i_a++; - } else if (pt_a->context > pt_b->context) { - add_fence(fences, &i, pt_b); + } else if (b_fence->context < a_fence->context) { + add_fence(fences, &index, b_fence); + b_fence = dma_fence_unwrap_next(&b_iter); + + } else if (__dma_fence_is_later(a_fence->seqno, b_fence->seqno, + a_fence->ops)) { + add_fence(fences, &index, a_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + b_fence = dma_fence_unwrap_next(&b_iter); - i_b++; } else { - if (__dma_fence_is_later(pt_a->seqno, pt_b->seqno, - pt_a->ops)) - add_fence(fences, &i, pt_a); - else - add_fence(fences, &i, pt_b); - - i_a++; - i_b++; + add_fence(fences, &index, b_fence); + a_fence = dma_fence_unwrap_next(&a_iter); + b_fence = dma_fence_unwrap_next(&b_iter); } } - for (; i_a < a_num_fences; i_a++) - add_fence(fences, &i, a_fences[i_a]); - - for (; i_b < b_num_fences; i_b++) - add_fence(fences, &i, b_fences[i_b]); - - if (i == 0) - fences[i++] = dma_fence_get(a_fences[0]); + if (index == 0) + fences[index++] = dma_fence_get_stub(); - if (num_fences > i) { - nfences = krealloc_array(fences, i, sizeof(*fences), GFP_KERNEL); - if (!nfences) - goto err; + if (num_fences > index) { + struct dma_fence **tmp; - fences = nfences; + /* Keep going even when reducing the size failed */ + tmp = krealloc_array(fences, index, sizeof(*fences), + GFP_KERNEL); + if (tmp) + fences = tmp; } - if (sync_file_set_fence(sync_file, fences, i) < 0) - goto err; + if (sync_file_set_fence(sync_file, fences, index) < 0) + goto err_put_fences; strlcpy(sync_file->user_name, name, sizeof(sync_file->user_name)); return sync_file; -err: - while (i) - dma_fence_put(fences[--i]); +err_put_fences: + while (index) + dma_fence_put(fences[--index]); kfree(fences); + +err_free_sync_file: fput(sync_file->file); return NULL; - } static int sync_file_release(struct inode *inode, struct file *file) @@ -398,11 +396,13 @@ static int sync_fill_fence_info(struct dma_fence *fence, static long sync_file_ioctl_fence_info(struct sync_file *sync_file, unsigned long arg) { - struct sync_file_info info; struct sync_fence_info *fence_info = NULL; - struct dma_fence **fences; + struct dma_fence_unwrap iter; + struct sync_file_info info; + unsigned int num_fences; + struct dma_fence *fence; + int ret; __u32 size; - int num_fences, ret, i; if (copy_from_user(&info, (void __user *)arg, sizeof(info))) return -EFAULT; @@ -410,7 +410,9 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (info.flags || info.pad) return -EINVAL; - fences = get_fences(sync_file, &num_fences); + num_fences = 0; + dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) + ++num_fences; /* * Passing num_fences = 0 means that userspace doesn't want to @@ -433,8 +435,11 @@ static long sync_file_ioctl_fence_info(struct sync_file *sync_file, if (!fence_info) return -ENOMEM; - for (i = 0; i < num_fences; i++) { - int status = sync_fill_fence_info(fences[i], &fence_info[i]); + num_fences = 0; + dma_fence_unwrap_for_each(fence, &iter, sync_file->fence) { + int status; + + status = sync_fill_fence_info(fence, &fence_info[num_fences++]); info.status = info.status <= 0 ? info.status : status; } diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index e5cfb01353d8..d65964996e8d 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -219,12 +219,12 @@ config QCOM_SCM_DOWNLOAD_MODE_DEFAULT config SYSFB bool - default y - depends on X86 || EFI + select BOOT_VESA_SUPPORT config SYSFB_SIMPLEFB bool "Mark VGA/VBE/EFI FB as generic system framebuffer" - depends on SYSFB + depends on X86 || EFI + select SYSFB help Firmwares often provide initial graphics framebuffers so the BIOS, bootloader or kernel can show basic video-output during boot for diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index e59884cc12a7..085348e08986 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1404,6 +1404,16 @@ static int gpiochip_to_irq(struct gpio_chip *gc, unsigned int offset) { struct irq_domain *domain = gc->irq.domain; +#ifdef CONFIG_GPIOLIB_IRQCHIP + /* + * Avoid race condition with other code, which tries to lookup + * an IRQ before the irqchip has been properly registered, + * i.e. while gpiochip is still being brought up. + */ + if (!gc->irq.initialized) + return -EPROBE_DEFER; +#endif + if (!gpiochip_irqchip_irq_valid(gc, offset)) return -ENXIO; @@ -1593,6 +1603,15 @@ static int gpiochip_add_irqchip(struct gpio_chip *gc, acpi_gpiochip_request_interrupts(gc); + /* + * Using barrier() here to prevent compiler from reordering + * gc->irq.initialized before initialization of above + * GPIO chip irq members. + */ + barrier(); + + gc->irq.initialized = true; + return 0; } diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index f1422bee3dcc..5133c3f028ab 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -280,6 +280,7 @@ config DRM_AMDGPU select HWMON select BACKLIGHT_CLASS_DEVICE select INTERVAL_TREE + select DRM_BUDDY help Choose this option if you have a recent AMD Radeon graphics card. diff --git a/drivers/gpu/drm/amd/amdgpu/ObjectID.h b/drivers/gpu/drm/amd/amdgpu/ObjectID.h index 5b393622f592..a0f0a17e224f 100644 --- a/drivers/gpu/drm/amd/amdgpu/ObjectID.h +++ b/drivers/gpu/drm/amd/amdgpu/ObjectID.h @@ -119,6 +119,7 @@ #define CONNECTOR_OBJECT_ID_eDP 0x14 #define CONNECTOR_OBJECT_ID_MXM 0x15 #define CONNECTOR_OBJECT_ID_LVDS_eDP 0x16 +#define CONNECTOR_OBJECT_ID_USBC 0x17 /* deleted */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index cd89d2e46852..3dc5ab2764ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -253,53 +253,18 @@ void amdgpu_amdkfd_release_notify(struct amdgpu_bo *bo) static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo, struct amdgpu_amdkfd_fence *ef) { - struct dma_resv *resv = bo->tbo.base.resv; - struct dma_resv_list *old, *new; - unsigned int i, j, k; + struct dma_fence *replacement; if (!ef) return -EINVAL; - old = dma_resv_shared_list(resv); - if (!old) - return 0; - - new = kmalloc(struct_size(new, shared, old->shared_max), GFP_KERNEL); - if (!new) - return -ENOMEM; - - /* Go through all the shared fences in the resevation object and sort - * the interesting ones to the end of the list. + /* TODO: Instead of block before we should use the fence of the page + * table update and TLB flush here directly. */ - for (i = 0, j = old->shared_count, k = 0; i < old->shared_count; ++i) { - struct dma_fence *f; - - f = rcu_dereference_protected(old->shared[i], - dma_resv_held(resv)); - - if (f->context == ef->base.context) - RCU_INIT_POINTER(new->shared[--j], f); - else - RCU_INIT_POINTER(new->shared[k++], f); - } - new->shared_max = old->shared_max; - new->shared_count = k; - - /* Install the new fence list, seqcount provides the barriers */ - write_seqcount_begin(&resv->seq); - RCU_INIT_POINTER(resv->fence, new); - write_seqcount_end(&resv->seq); - - /* Drop the references to the removed fences or move them to ef_list */ - for (i = j; i < old->shared_count; ++i) { - struct dma_fence *f; - - f = rcu_dereference_protected(new->shared[i], - dma_resv_held(resv)); - dma_fence_put(f); - } - kfree_rcu(old, rcu); - + replacement = dma_fence_get_stub(); + dma_resv_replace_fences(bo->tbo.base.resv, ef->base.context, + replacement, DMA_RESV_USAGE_READ); + dma_fence_put(replacement); return 0; } @@ -1268,7 +1233,7 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info, AMDGPU_FENCE_OWNER_KFD, false); if (ret) goto wait_pd_fail; - ret = dma_resv_reserve_shared(vm->root.bo->tbo.base.resv, 1); + ret = dma_resv_reserve_fences(vm->root.bo->tbo.base.resv, 1); if (ret) goto reserve_shared_fail; amdgpu_bo_fence(vm->root.bo, @@ -2482,6 +2447,8 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) struct amdgpu_bo *bo = mem->bo; uint32_t domain = mem->domain; struct kfd_mem_attachment *attachment; + struct dma_resv_iter cursor; + struct dma_fence *fence; total_size += amdgpu_bo_size(bo); @@ -2496,10 +2463,13 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) goto validate_map_fail; } } - ret = amdgpu_sync_fence(&sync_obj, bo->tbo.moving); - if (ret) { - pr_debug("Memory eviction: Sync BO fence failed. Try again\n"); - goto validate_map_fail; + dma_resv_for_each_fence(&cursor, bo->tbo.base.resv, + DMA_RESV_USAGE_KERNEL, fence) { + ret = amdgpu_sync_fence(&sync_obj, fence); + if (ret) { + pr_debug("Memory eviction: Sync BO fence failed. Try again\n"); + goto validate_map_fail; + } } list_for_each_entry(attachment, &mem->attachments, list) { if (!attachment->is_mapped) @@ -2606,7 +2576,7 @@ int amdgpu_amdkfd_add_gws_to_process(void *info, void *gws, struct kgd_mem **mem * Add process eviction fence to bo so they can * evict each other. */ - ret = dma_resv_reserve_shared(gws_bo->tbo.base.resv, 1); + ret = dma_resv_reserve_fences(gws_bo->tbo.base.resv, 1); if (ret) goto reserve_shared_fail; amdgpu_bo_fence(gws_bo, &process_info->eviction_fence->base, true); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h index 044b41f0bfd9..529d52a204cf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h @@ -34,7 +34,6 @@ struct amdgpu_fpriv; struct amdgpu_bo_list_entry { struct ttm_validate_buffer tv; struct amdgpu_bo_va *bo_va; - struct dma_fence_chain *chain; uint32_t priority; struct page **user_pages; bool user_invalidated; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 970b065e9a6b..8de283997769 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -55,8 +55,8 @@ static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p, bo = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj)); p->uf_entry.priority = 0; p->uf_entry.tv.bo = &bo->tbo; - /* One for TTM and one for the CS job */ - p->uf_entry.tv.num_shared = 2; + /* One for TTM and two for the CS job */ + p->uf_entry.tv.num_shared = 3; drm_gem_object_put(gobj); @@ -574,14 +574,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); e->bo_va = amdgpu_vm_bo_find(vm, bo); - - if (bo->tbo.base.dma_buf && !amdgpu_bo_explicit_sync(bo)) { - e->chain = dma_fence_chain_alloc(); - if (!e->chain) { - r = -ENOMEM; - goto error_validate; - } - } } /* Move fence waiting after getting reservation lock of @@ -642,13 +634,8 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, } error_validate: - if (r) { - amdgpu_bo_list_for_each_entry(e, p->bo_list) { - dma_fence_chain_free(e->chain); - e->chain = NULL; - } + if (r) ttm_eu_backoff_reservation(&p->ticket, &p->validated); - } out: return r; } @@ -688,17 +675,9 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, { unsigned i; - if (error && backoff) { - struct amdgpu_bo_list_entry *e; - - amdgpu_bo_list_for_each_entry(e, parser->bo_list) { - dma_fence_chain_free(e->chain); - e->chain = NULL; - } - + if (error && backoff) ttm_eu_backoff_reservation(&parser->ticket, &parser->validated); - } for (i = 0; i < parser->num_post_deps; i++) { drm_syncobj_put(parser->post_deps[i].syncobj); @@ -1272,24 +1251,9 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, amdgpu_vm_move_to_lru_tail(p->adev, &fpriv->vm); - amdgpu_bo_list_for_each_entry(e, p->bo_list) { - struct dma_resv *resv = e->tv.bo->base.resv; - struct dma_fence_chain *chain = e->chain; - - if (!chain) - continue; - - /* - * Work around dma_resv shortcomings by wrapping up the - * submission in a dma_fence_chain and add it as exclusive - * fence. - */ - dma_fence_chain_init(chain, dma_resv_excl_fence(resv), - dma_fence_get(p->fence), 1); - - rcu_assign_pointer(resv->fence_excl, &chain->base); - e->chain = NULL; - } + /* Make sure all BOs are remembered as writers */ + amdgpu_bo_list_for_each_entry(e, p->bo_list) + e->tv.num_shared = 0; ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence); mutex_unlock(&p->adev->notifier_lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 3987ecb24ef4..49f734137f15 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5733,7 +5733,7 @@ void amdgpu_device_flush_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) return; #endif if (adev->gmc.xgmi.connected_to_cpu) @@ -5749,7 +5749,7 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring) { #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) return; #endif if (adev->gmc.xgmi.connected_to_cpu) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index fae5c1debfad..7a6908d71820 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -200,8 +200,7 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc, goto unpin; } - /* TODO: Unify this with other drivers */ - r = dma_resv_get_fences(new_abo->tbo.base.resv, true, + r = dma_resv_get_fences(new_abo->tbo.base.resv, DMA_RESV_USAGE_WRITE, &work->shared_count, &work->shared); if (unlikely(r != 0)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 579adfafe4d0..782cbca37538 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -102,21 +102,9 @@ static int amdgpu_dma_buf_pin(struct dma_buf_attachment *attach) { struct drm_gem_object *obj = attach->dmabuf->priv; struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); - int r; /* pin buffer into GTT */ - r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT); - if (r) - return r; - - if (bo->tbo.moving) { - r = dma_fence_wait(bo->tbo.moving, true); - if (r) { - amdgpu_bo_unpin(bo); - return r; - } - } - return 0; + return amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index bb1c025d9001..b03663f42cc9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -680,7 +680,7 @@ MODULE_PARM_DESC(sched_policy, * Maximum number of processes that HWS can schedule concurrently. The maximum is the * number of VMIDs assigned to the HWS, which is also the default. */ -int hws_max_conc_proc = 8; +int hws_max_conc_proc = -1; module_param(hws_max_conc_proc, int, 0444); MODULE_PARM_DESC(hws_max_conc_proc, "Max # processes HWS can execute concurrently when sched_policy=0 (0 = no concurrency, #VMIDs for KFD = Maximum(default))"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 57b74d35052f..84a53758e18e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -526,7 +526,8 @@ int amdgpu_gem_wait_idle_ioctl(struct drm_device *dev, void *data, return -ENOENT; } robj = gem_to_amdgpu_bo(gobj); - ret = dma_resv_wait_timeout(robj->tbo.base.resv, true, true, timeout); + ret = dma_resv_wait_timeout(robj->tbo.base.resv, DMA_RESV_USAGE_READ, + true, timeout); /* ret == 0 means not signaled, * ret > 0 means signaled diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 8fe939976224..28a736c507bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -266,7 +266,7 @@ static int amdgpu_gfx_kiq_acquire(struct amdgpu_device *adev, * adev->gfx.mec.num_pipe_per_mec * adev->gfx.mec.num_queue_per_pipe; - while (queue_bit-- >= 0) { + while (--queue_bit >= 0) { if (test_bit(queue_bit, adev->gfx.mec.queue_bitmap)) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index ca2cfb65f976..a66a0881a934 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -561,9 +561,15 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(9, 0, 1): + case IP_VERSION(9, 3, 0): case IP_VERSION(9, 4, 0): case IP_VERSION(9, 4, 1): case IP_VERSION(9, 4, 2): + case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 4): + case IP_VERSION(10, 3, 5): + case IP_VERSION(10, 3, 6): + case IP_VERSION(10, 3, 7): /* * noretry = 0 will cause kfd page fault tests fail * for some ASICs, so set default to 1 for these ASICs. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c index dd78402e3cb0..8c6b2284cf56 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -26,23 +26,12 @@ #include "amdgpu.h" -struct amdgpu_gtt_node { - struct ttm_buffer_object *tbo; - struct ttm_range_mgr_node base; -}; - static inline struct amdgpu_gtt_mgr * to_gtt_mgr(struct ttm_resource_manager *man) { return container_of(man, struct amdgpu_gtt_mgr, manager); } -static inline struct amdgpu_gtt_node * -to_amdgpu_gtt_node(struct ttm_resource *res) -{ - return container_of(res, struct amdgpu_gtt_node, base.base); -} - /** * DOC: mem_info_gtt_total * @@ -106,9 +95,9 @@ const struct attribute_group amdgpu_gtt_mgr_attr_group = { */ bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_resource *res) { - struct amdgpu_gtt_node *node = to_amdgpu_gtt_node(res); + struct ttm_range_mgr_node *node = to_ttm_range_mgr_node(res); - return drm_mm_node_allocated(&node->base.mm_nodes[0]); + return drm_mm_node_allocated(&node->mm_nodes[0]); } /** @@ -128,15 +117,14 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man, { struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man); uint32_t num_pages = PFN_UP(tbo->base.size); - struct amdgpu_gtt_node *node; + struct ttm_range_mgr_node *node; int r; - node = kzalloc(struct_size(node, base.mm_nodes, 1), GFP_KERNEL); + node = kzalloc(struct_size(node, mm_nodes, 1), GFP_KERNEL); if (!node) return -ENOMEM; - node->tbo = tbo; - ttm_resource_init(tbo, place, &node->base.base); + ttm_resource_init(tbo, place, &node->base); if (!(place->flags & TTM_PL_FLAG_TEMPORARY) && ttm_resource_manager_usage(man) > man->size) { r = -ENOSPC; @@ -145,8 +133,7 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man, if (place->lpfn) { spin_lock(&mgr->lock); - r = drm_mm_insert_node_in_range(&mgr->mm, - &node->base.mm_nodes[0], + r = drm_mm_insert_node_in_range(&mgr->mm, &node->mm_nodes[0], num_pages, tbo->page_alignment, 0, place->fpfn, place->lpfn, DRM_MM_INSERT_BEST); @@ -154,18 +141,18 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man, if (unlikely(r)) goto err_free; - node->base.base.start = node->base.mm_nodes[0].start; + node->base.start = node->mm_nodes[0].start; } else { - node->base.mm_nodes[0].start = 0; - node->base.mm_nodes[0].size = node->base.base.num_pages; - node->base.base.start = AMDGPU_BO_INVALID_OFFSET; + node->mm_nodes[0].start = 0; + node->mm_nodes[0].size = node->base.num_pages; + node->base.start = AMDGPU_BO_INVALID_OFFSET; } - *res = &node->base.base; + *res = &node->base; return 0; err_free: - ttm_resource_fini(man, &node->base.base); + ttm_resource_fini(man, &node->base); kfree(node); return r; } @@ -181,12 +168,12 @@ err_free: static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man, struct ttm_resource *res) { - struct amdgpu_gtt_node *node = to_amdgpu_gtt_node(res); + struct ttm_range_mgr_node *node = to_ttm_range_mgr_node(res); struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man); spin_lock(&mgr->lock); - if (drm_mm_node_allocated(&node->base.mm_nodes[0])) - drm_mm_remove_node(&node->base.mm_nodes[0]); + if (drm_mm_node_allocated(&node->mm_nodes[0])) + drm_mm_remove_node(&node->mm_nodes[0]); spin_unlock(&mgr->lock); ttm_resource_fini(man, res); @@ -202,15 +189,15 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man, */ void amdgpu_gtt_mgr_recover(struct amdgpu_gtt_mgr *mgr) { - struct amdgpu_gtt_node *node; + struct ttm_range_mgr_node *node; struct drm_mm_node *mm_node; struct amdgpu_device *adev; adev = container_of(mgr, typeof(*adev), mman.gtt_mgr); spin_lock(&mgr->lock); drm_mm_for_each_node(mm_node, &mgr->mm) { - node = container_of(mm_node, typeof(*node), base.mm_nodes[0]); - amdgpu_ttm_recover_gart(node->tbo); + node = container_of(mm_node, typeof(*node), mm_nodes[0]); + amdgpu_ttm_recover_gart(node->base.bo); } spin_unlock(&mgr->lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index 92a70fb57fa3..4ba4b54092f1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -107,36 +107,19 @@ static void amdgpu_pasid_free_cb(struct dma_fence *fence, void amdgpu_pasid_free_delayed(struct dma_resv *resv, u32 pasid) { - struct dma_fence *fence, **fences; struct amdgpu_pasid_cb *cb; - unsigned count; + struct dma_fence *fence; int r; - r = dma_resv_get_fences(resv, true, &count, &fences); + r = dma_resv_get_singleton(resv, DMA_RESV_USAGE_BOOKKEEP, &fence); if (r) goto fallback; - if (count == 0) { + if (!fence) { amdgpu_pasid_free(pasid); return; } - if (count == 1) { - fence = fences[0]; - kfree(fences); - } else { - uint64_t context = dma_fence_context_alloc(1); - struct dma_fence_array *array; - - array = dma_fence_array_create(count, fences, context, - 1, false); - if (!array) { - kfree(fences); - goto fallback; - } - fence = &array->base; - } - cb = kmalloc(sizeof(*cb), GFP_KERNEL); if (!cb) { /* Last resort when we are OOM */ @@ -156,7 +139,8 @@ fallback: /* Not enough memory for the delayed delete, as last resort * block for all the fences to complete. */ - dma_resv_wait_timeout(resv, true, false, MAX_SCHEDULE_TIMEOUT); + dma_resv_wait_timeout(resv, DMA_RESV_USAGE_BOOKKEEP, + false, MAX_SCHEDULE_TIMEOUT); amdgpu_pasid_free(pasid); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index 4b153daf283d..b86c0b8252a5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -75,8 +75,8 @@ static bool amdgpu_mn_invalidate_gfx(struct mmu_interval_notifier *mni, mmu_interval_set_seq(mni, cur_seq); - r = dma_resv_wait_timeout(bo->tbo.base.resv, true, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(bo->tbo.base.resv, DMA_RESV_USAGE_BOOKKEEP, + false, MAX_SCHEDULE_TIMEOUT); mutex_unlock(&adev->notifier_lock); if (r <= 0) DRM_ERROR("(%ld) failed to wait for user bo\n", r); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 25731719c627..e92ecabfa7bd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -612,9 +612,8 @@ int amdgpu_bo_create(struct amdgpu_device *adev, if (unlikely(r)) goto fail_unreserve; - amdgpu_bo_fence(bo, fence, false); - dma_fence_put(bo->tbo.moving); - bo->tbo.moving = dma_fence_get(fence); + dma_resv_add_fence(bo->tbo.base.resv, fence, + DMA_RESV_USAGE_KERNEL); dma_fence_put(fence); } if (!bp->resv) @@ -761,6 +760,11 @@ int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr) if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS) return -EPERM; + r = dma_resv_wait_timeout(bo->tbo.base.resv, DMA_RESV_USAGE_KERNEL, + false, MAX_SCHEDULE_TIMEOUT); + if (r < 0) + return r; + kptr = amdgpu_bo_kptr(bo); if (kptr) { if (ptr) @@ -768,11 +772,6 @@ int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr) return 0; } - r = dma_resv_wait_timeout(bo->tbo.base.resv, false, false, - MAX_SCHEDULE_TIMEOUT); - if (r < 0) - return r; - r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.resource->num_pages, &bo->kmap); if (r) return r; @@ -1284,6 +1283,7 @@ void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem, */ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct dma_fence *fence = NULL; struct amdgpu_bo *abo; int r; @@ -1303,7 +1303,8 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo); if (bo->resource->mem_type != TTM_PL_VRAM || - !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) + !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE) || + adev->in_suspend || adev->shutdown) return; if (WARN_ON_ONCE(!dma_resv_trylock(bo->base.resv))) @@ -1388,11 +1389,17 @@ void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence, bool shared) { struct dma_resv *resv = bo->tbo.base.resv; + int r; - if (shared) - dma_resv_add_shared_fence(resv, fence); - else - dma_resv_add_excl_fence(resv, fence); + r = dma_resv_reserve_fences(resv, 1); + if (r) { + /* As last resort on OOM we block for the fence */ + dma_fence_wait(fence, false); + return; + } + + dma_resv_add_fence(resv, fence, shared ? DMA_RESV_USAGE_READ : + DMA_RESV_USAGE_WRITE); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h index acfa207cf970..6546552e596c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h @@ -30,12 +30,15 @@ #include <drm/ttm/ttm_resource.h> #include <drm/ttm/ttm_range_manager.h> +#include "amdgpu_vram_mgr.h" + /* state back for walking over vram_mgr and gtt_mgr allocations */ struct amdgpu_res_cursor { uint64_t start; uint64_t size; uint64_t remaining; - struct drm_mm_node *node; + void *node; + uint32_t mem_type; }; /** @@ -52,27 +55,63 @@ static inline void amdgpu_res_first(struct ttm_resource *res, uint64_t start, uint64_t size, struct amdgpu_res_cursor *cur) { + struct drm_buddy_block *block; + struct list_head *head, *next; struct drm_mm_node *node; - if (!res || res->mem_type == TTM_PL_SYSTEM) { - cur->start = start; - cur->size = size; - cur->remaining = size; - cur->node = NULL; - WARN_ON(res && start + size > res->num_pages << PAGE_SHIFT); - return; - } + if (!res) + goto fallback; BUG_ON(start + size > res->num_pages << PAGE_SHIFT); - node = to_ttm_range_mgr_node(res)->mm_nodes; - while (start >= node->size << PAGE_SHIFT) - start -= node++->size << PAGE_SHIFT; + cur->mem_type = res->mem_type; + + switch (cur->mem_type) { + case TTM_PL_VRAM: + head = &to_amdgpu_vram_mgr_resource(res)->blocks; + + block = list_first_entry_or_null(head, + struct drm_buddy_block, + link); + if (!block) + goto fallback; + + while (start >= amdgpu_vram_mgr_block_size(block)) { + start -= amdgpu_vram_mgr_block_size(block); + + next = block->link.next; + if (next != head) + block = list_entry(next, struct drm_buddy_block, link); + } + + cur->start = amdgpu_vram_mgr_block_start(block) + start; + cur->size = min(amdgpu_vram_mgr_block_size(block) - start, size); + cur->remaining = size; + cur->node = block; + break; + case TTM_PL_TT: + node = to_ttm_range_mgr_node(res)->mm_nodes; + while (start >= node->size << PAGE_SHIFT) + start -= node++->size << PAGE_SHIFT; + + cur->start = (node->start << PAGE_SHIFT) + start; + cur->size = min((node->size << PAGE_SHIFT) - start, size); + cur->remaining = size; + cur->node = node; + break; + default: + goto fallback; + } - cur->start = (node->start << PAGE_SHIFT) + start; - cur->size = min((node->size << PAGE_SHIFT) - start, size); + return; + +fallback: + cur->start = start; + cur->size = size; cur->remaining = size; - cur->node = node; + cur->node = NULL; + WARN_ON(res && start + size > res->num_pages << PAGE_SHIFT); + return; } /** @@ -85,7 +124,9 @@ static inline void amdgpu_res_first(struct ttm_resource *res, */ static inline void amdgpu_res_next(struct amdgpu_res_cursor *cur, uint64_t size) { - struct drm_mm_node *node = cur->node; + struct drm_buddy_block *block; + struct drm_mm_node *node; + struct list_head *next; BUG_ON(size > cur->remaining); @@ -99,9 +140,27 @@ static inline void amdgpu_res_next(struct amdgpu_res_cursor *cur, uint64_t size) return; } - cur->node = ++node; - cur->start = node->start << PAGE_SHIFT; - cur->size = min(node->size << PAGE_SHIFT, cur->remaining); + switch (cur->mem_type) { + case TTM_PL_VRAM: + block = cur->node; + + next = block->link.next; + block = list_entry(next, struct drm_buddy_block, link); + + cur->node = block; + cur->start = amdgpu_vram_mgr_block_start(block); + cur->size = min(amdgpu_vram_mgr_block_size(block), cur->remaining); + break; + case TTM_PL_TT: + node = cur->node; + + cur->node = ++node; + cur->start = node->start << PAGE_SHIFT; + cur->size = min(node->size << PAGE_SHIFT, cur->remaining); + break; + default: + return; + } } #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h index 5320bb0883d8..317d80209e95 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h @@ -300,8 +300,8 @@ 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); int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, - unsigned int ring_size, struct amdgpu_irq_src *irq_src, - unsigned int irq_type, unsigned int prio, + unsigned int max_dw, struct amdgpu_irq_src *irq_src, + unsigned int irq_type, unsigned int hw_prio, atomic_t *sched_score); void amdgpu_ring_fini(struct amdgpu_ring *ring); void amdgpu_ring_emit_reg_write_reg_wait_helper(struct amdgpu_ring *ring, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index 40e06745fae9..11c46b3e4c60 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -259,7 +259,8 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync, if (resv == NULL) return -EINVAL; - dma_resv_for_each_fence(&cursor, resv, true, f) { + /* TODO: Use DMA_RESV_USAGE_READ here */ + dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP, f) { dma_fence_chain_for_each(f, f) { struct dma_fence *tmp = dma_fence_chain_contained(f); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 4b9ee6e27f74..ec26edd4f4d8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1344,7 +1344,8 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, * If true, then return false as any KFD process needs all its BOs to * be resident to run successfully */ - dma_resv_for_each_fence(&resv_cursor, bo->base.resv, true, f) { + dma_resv_for_each_fence(&resv_cursor, bo->base.resv, + DMA_RESV_USAGE_BOOKKEEP, f) { if (amdkfd_fence_check_mm(f, current->mm)) return false; } @@ -1547,7 +1548,6 @@ static struct ttm_device_funcs amdgpu_bo_driver = { .io_mem_reserve = &amdgpu_ttm_io_mem_reserve, .io_mem_pfn = amdgpu_ttm_io_mem_pfn, .access_memory = &amdgpu_ttm_access_memory, - .del_from_lru_notify = &amdgpu_vm_del_from_lru_notify }; /* @@ -2161,17 +2161,6 @@ int amdgpu_ttm_evict_resources(struct amdgpu_device *adev, int mem_type) #if defined(CONFIG_DEBUG_FS) -static int amdgpu_mm_vram_table_show(struct seq_file *m, void *unused) -{ - struct amdgpu_device *adev = (struct amdgpu_device *)m->private; - struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, - TTM_PL_VRAM); - struct drm_printer p = drm_seq_file_printer(m); - - ttm_resource_manager_debug(man, &p); - return 0; -} - static int amdgpu_ttm_page_pool_show(struct seq_file *m, void *unused) { struct amdgpu_device *adev = (struct amdgpu_device *)m->private; @@ -2179,55 +2168,6 @@ static int amdgpu_ttm_page_pool_show(struct seq_file *m, void *unused) return ttm_pool_debugfs(&adev->mman.bdev.pool, m); } -static int amdgpu_mm_tt_table_show(struct seq_file *m, void *unused) -{ - struct amdgpu_device *adev = (struct amdgpu_device *)m->private; - struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, - TTM_PL_TT); - struct drm_printer p = drm_seq_file_printer(m); - - ttm_resource_manager_debug(man, &p); - return 0; -} - -static int amdgpu_mm_gds_table_show(struct seq_file *m, void *unused) -{ - struct amdgpu_device *adev = (struct amdgpu_device *)m->private; - struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, - AMDGPU_PL_GDS); - struct drm_printer p = drm_seq_file_printer(m); - - ttm_resource_manager_debug(man, &p); - return 0; -} - -static int amdgpu_mm_gws_table_show(struct seq_file *m, void *unused) -{ - struct amdgpu_device *adev = (struct amdgpu_device *)m->private; - struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, - AMDGPU_PL_GWS); - struct drm_printer p = drm_seq_file_printer(m); - - ttm_resource_manager_debug(man, &p); - return 0; -} - -static int amdgpu_mm_oa_table_show(struct seq_file *m, void *unused) -{ - struct amdgpu_device *adev = (struct amdgpu_device *)m->private; - struct ttm_resource_manager *man = ttm_manager_type(&adev->mman.bdev, - AMDGPU_PL_OA); - struct drm_printer p = drm_seq_file_printer(m); - - ttm_resource_manager_debug(man, &p); - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(amdgpu_mm_vram_table); -DEFINE_SHOW_ATTRIBUTE(amdgpu_mm_tt_table); -DEFINE_SHOW_ATTRIBUTE(amdgpu_mm_gds_table); -DEFINE_SHOW_ATTRIBUTE(amdgpu_mm_gws_table); -DEFINE_SHOW_ATTRIBUTE(amdgpu_mm_oa_table); DEFINE_SHOW_ATTRIBUTE(amdgpu_ttm_page_pool); /* @@ -2437,17 +2377,23 @@ void amdgpu_ttm_debugfs_init(struct amdgpu_device *adev) &amdgpu_ttm_vram_fops, adev->gmc.mc_vram_size); debugfs_create_file("amdgpu_iomem", 0444, root, adev, &amdgpu_ttm_iomem_fops); - debugfs_create_file("amdgpu_vram_mm", 0444, root, adev, - &amdgpu_mm_vram_table_fops); - debugfs_create_file("amdgpu_gtt_mm", 0444, root, adev, - &amdgpu_mm_tt_table_fops); - debugfs_create_file("amdgpu_gds_mm", 0444, root, adev, - &amdgpu_mm_gds_table_fops); - debugfs_create_file("amdgpu_gws_mm", 0444, root, adev, - &amdgpu_mm_gws_table_fops); - debugfs_create_file("amdgpu_oa_mm", 0444, root, adev, - &amdgpu_mm_oa_table_fops); debugfs_create_file("ttm_page_pool", 0444, root, adev, &amdgpu_ttm_page_pool_fops); + ttm_resource_manager_create_debugfs(ttm_manager_type(&adev->mman.bdev, + TTM_PL_VRAM), + root, "amdgpu_vram_mm"); + ttm_resource_manager_create_debugfs(ttm_manager_type(&adev->mman.bdev, + TTM_PL_TT), + root, "amdgpu_gtt_mm"); + ttm_resource_manager_create_debugfs(ttm_manager_type(&adev->mman.bdev, + AMDGPU_PL_GDS), + root, "amdgpu_gds_mm"); + ttm_resource_manager_create_debugfs(ttm_manager_type(&adev->mman.bdev, + AMDGPU_PL_GWS), + root, "amdgpu_gws_mm"); + ttm_resource_manager_create_debugfs(ttm_manager_type(&adev->mman.bdev, + AMDGPU_PL_OA), + root, "amdgpu_oa_mm"); + #endif } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 9120ae80ef52..6a70818039dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -26,6 +26,7 @@ #include <linux/dma-direction.h> #include <drm/gpu_scheduler.h> +#include "amdgpu_vram_mgr.h" #include "amdgpu.h" #define AMDGPU_PL_GDS (TTM_PL_PRIV + 0) @@ -38,15 +39,6 @@ #define AMDGPU_POISON 0xd0bed0be -struct amdgpu_vram_mgr { - struct ttm_resource_manager manager; - struct drm_mm mm; - spinlock_t lock; - struct list_head reservations_pending; - struct list_head reserved_pages; - atomic64_t vis_usage; -}; - struct amdgpu_gtt_mgr { struct ttm_resource_manager manager; struct drm_mm mm; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 39c74d9fa7cc..6eac649499d3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -1163,7 +1163,8 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo, ib->length_dw = 16; if (direct) { - r = dma_resv_wait_timeout(bo->tbo.base.resv, true, false, + r = dma_resv_wait_timeout(bo->tbo.base.resv, + DMA_RESV_USAGE_KERNEL, false, msecs_to_jiffies(10)); if (r == 0) r = -ETIMEDOUT; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index e2fde88aaf5e..f06fb7f882e2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -159,6 +159,7 @@ #define AMDGPU_VCN_MULTI_QUEUE_FLAG (1 << 8) #define AMDGPU_VCN_SW_RING_FLAG (1 << 9) #define AMDGPU_VCN_FW_LOGGING_FLAG (1 << 10) +#define AMDGPU_VCN_SMU_VERSION_INFO_FLAG (1 << 11) #define AMDGPU_VCN_IB_FLAG_DECODE_BUFFER 0x00000001 #define AMDGPU_VCN_CMD_FLAG_MSG_BUFFER 0x00000001 @@ -279,6 +280,11 @@ struct amdgpu_fw_shared_fw_logging { uint32_t size; }; +struct amdgpu_fw_shared_smu_interface_info { + uint8_t smu_interface_type; + uint8_t padding[3]; +}; + struct amdgpu_fw_shared { uint32_t present_flag_0; uint8_t pad[44]; @@ -287,6 +293,7 @@ struct amdgpu_fw_shared { struct amdgpu_fw_shared_multi_queue multi_queue; struct amdgpu_fw_shared_sw_ring sw_ring; struct amdgpu_fw_shared_fw_logging fw_log; + struct amdgpu_fw_shared_smu_interface_info smu_interface_info; }; struct amdgpu_vcn_fwlog { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index fc4563cf2828..5277c10d901d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -377,7 +377,7 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base, dma_resv_assert_held(vm->root.bo->tbo.base.resv); - vm->bulk_moveable = false; + ttm_bo_set_bulk_move(&bo->tbo, &vm->lru_bulk_move); if (bo->tbo.type == ttm_bo_type_kernel && bo->parent) amdgpu_vm_bo_relocated(base); else @@ -640,36 +640,6 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm, } /** - * amdgpu_vm_del_from_lru_notify - update bulk_moveable flag - * - * @bo: BO which was removed from the LRU - * - * Make sure the bulk_moveable flag is updated when a BO is removed from the - * LRU. - */ -void amdgpu_vm_del_from_lru_notify(struct ttm_buffer_object *bo) -{ - struct amdgpu_bo *abo; - struct amdgpu_vm_bo_base *bo_base; - - if (!amdgpu_bo_is_amdgpu_bo(bo)) - return; - - if (bo->pin_count) - return; - - abo = ttm_to_amdgpu_bo(bo); - if (!abo->parent) - return; - for (bo_base = abo->vm_bo; bo_base; bo_base = bo_base->next) { - struct amdgpu_vm *vm = bo_base->vm; - - if (abo->tbo.base.resv == vm->root.bo->tbo.base.resv) - vm->bulk_moveable = false; - } - -} -/** * amdgpu_vm_move_to_lru_tail - move all BOs to the end of LRU * * @adev: amdgpu device pointer @@ -681,35 +651,9 @@ void amdgpu_vm_del_from_lru_notify(struct ttm_buffer_object *bo) void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev, struct amdgpu_vm *vm) { - struct amdgpu_vm_bo_base *bo_base; - - if (vm->bulk_moveable) { - spin_lock(&adev->mman.bdev.lru_lock); - ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move); - spin_unlock(&adev->mman.bdev.lru_lock); - return; - } - - memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move)); - spin_lock(&adev->mman.bdev.lru_lock); - list_for_each_entry(bo_base, &vm->idle, vm_status) { - struct amdgpu_bo *bo = bo_base->bo; - struct amdgpu_bo *shadow = amdgpu_bo_shadowed(bo); - - if (!bo->parent) - continue; - - ttm_bo_move_to_lru_tail(&bo->tbo, bo->tbo.resource, - &vm->lru_bulk_move); - if (shadow) - ttm_bo_move_to_lru_tail(&shadow->tbo, - shadow->tbo.resource, - &vm->lru_bulk_move); - } + ttm_lru_bulk_move_tail(&vm->lru_bulk_move); spin_unlock(&adev->mman.bdev.lru_lock); - - vm->bulk_moveable = true; } /** @@ -732,8 +676,6 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct amdgpu_vm_bo_base *bo_base, *tmp; int r; - vm->bulk_moveable &= list_empty(&vm->evicted); - list_for_each_entry_safe(bo_base, tmp, &vm->evicted, vm_status) { struct amdgpu_bo *bo = bo_base->bo; struct amdgpu_bo *shadow = amdgpu_bo_shadowed(bo); @@ -1057,10 +999,16 @@ static void amdgpu_vm_free_table(struct amdgpu_vm_bo_base *entry) if (!entry->bo) return; + shadow = amdgpu_bo_shadowed(entry->bo); + if (shadow) { + ttm_bo_set_bulk_move(&shadow->tbo, NULL); + amdgpu_bo_unref(&shadow); + } + + ttm_bo_set_bulk_move(&entry->bo->tbo, NULL); entry->bo->vm_bo = NULL; list_del(&entry->vm_status); - amdgpu_bo_unref(&shadow); amdgpu_bo_unref(&entry->bo); } @@ -1080,8 +1028,6 @@ static void amdgpu_vm_free_pts(struct amdgpu_device *adev, struct amdgpu_vm_pt_cursor cursor; struct amdgpu_vm_bo_base *entry; - vm->bulk_moveable = false; - for_each_amdgpu_vm_pt_dfs_safe(adev, vm, start, cursor, entry) amdgpu_vm_free_table(entry); @@ -2113,7 +2059,7 @@ static void amdgpu_vm_prt_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) struct dma_resv_iter cursor; struct dma_fence *fence; - dma_resv_for_each_fence(&cursor, resv, true, fence) { + dma_resv_for_each_fence(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP, fence) { /* Add a callback for each fence in the reservation object */ amdgpu_vm_prt_get(adev); amdgpu_vm_add_prt_cb(adev, fence); @@ -2665,7 +2611,7 @@ void amdgpu_vm_bo_del(struct amdgpu_device *adev, if (bo) { dma_resv_assert_held(bo->tbo.base.resv); if (bo->tbo.base.resv == vm->root.bo->tbo.base.resv) - vm->bulk_moveable = false; + ttm_bo_set_bulk_move(&bo->tbo, NULL); for (base = &bo_va->base.bo->vm_bo; *base; base = &(*base)->next) { @@ -2719,7 +2665,7 @@ bool amdgpu_vm_evictable(struct amdgpu_bo *bo) return true; /* Don't evict VM page tables while they are busy */ - if (!dma_resv_test_signaled(bo->tbo.base.resv, true)) + if (!dma_resv_test_signaled(bo->tbo.base.resv, DMA_RESV_USAGE_BOOKKEEP)) return false; /* Try to block ongoing updates */ @@ -2899,7 +2845,8 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size, */ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout) { - timeout = dma_resv_wait_timeout(vm->root.bo->tbo.base.resv, true, + timeout = dma_resv_wait_timeout(vm->root.bo->tbo.base.resv, + DMA_RESV_USAGE_BOOKKEEP, true, timeout); if (timeout <= 0) return timeout; @@ -2980,7 +2927,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) if (r) goto error_free_root; - r = dma_resv_reserve_shared(root_bo->tbo.base.resv, 1); + r = dma_resv_reserve_fences(root_bo->tbo.base.resv, 1); if (r) goto error_unreserve; @@ -3423,7 +3370,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, value = 0; } - r = dma_resv_reserve_shared(root->tbo.base.resv, 1); + r = dma_resv_reserve_fences(root->tbo.base.resv, 1); if (r) { pr_debug("failed %d to reserve fence slot\n", r); goto error_unlock; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index a40a6a993bb0..bd7892482bbf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -317,8 +317,6 @@ struct amdgpu_vm { /* Store positions of group of BOs */ struct ttm_lru_bulk_move lru_bulk_move; - /* mark whether can do the bulk move */ - bool bulk_moveable; /* Flag to indicate if VM is used for compute */ bool is_compute_context; }; @@ -454,7 +452,6 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm); void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev, struct amdgpu_vm *vm); -void amdgpu_vm_del_from_lru_notify(struct ttm_buffer_object *bo); void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem, uint64_t *gtt_mem, uint64_t *cpu_mem); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c index e3fbf0f10add..31913ae86de6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c @@ -74,13 +74,12 @@ static int amdgpu_vm_cpu_update(struct amdgpu_vm_update_params *p, { unsigned int i; uint64_t value; - int r; + long r; - if (vmbo->bo.tbo.moving) { - r = dma_fence_wait(vmbo->bo.tbo.moving, true); - if (r) - return r; - } + r = dma_resv_wait_timeout(vmbo->bo.tbo.base.resv, DMA_RESV_USAGE_KERNEL, + true, MAX_SCHEDULE_TIMEOUT); + if (r < 0) + return r; pe += (unsigned long)amdgpu_bo_kptr(&vmbo->bo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c index dbb551762805..bdb44cee19d3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c @@ -204,14 +204,19 @@ static int amdgpu_vm_sdma_update(struct amdgpu_vm_update_params *p, struct amdgpu_bo *bo = &vmbo->bo; enum amdgpu_ib_pool_type pool = p->immediate ? AMDGPU_IB_POOL_IMMEDIATE : AMDGPU_IB_POOL_DELAYED; + struct dma_resv_iter cursor; unsigned int i, ndw, nptes; + struct dma_fence *fence; uint64_t *pte; int r; /* Wait for PD/PT moves to be completed */ - r = amdgpu_sync_fence(&p->job->sync, bo->tbo.moving); - if (r) - return r; + dma_resv_for_each_fence(&cursor, bo->tbo.base.resv, + DMA_RESV_USAGE_KERNEL, fence) { + r = amdgpu_sync_fence(&p->job->sync, fence); + if (r) + return r; + } do { ndw = p->num_dw_left; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 0a7611648573..49e4092f447f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -32,8 +32,10 @@ #include "atom.h" struct amdgpu_vram_reservation { - struct list_head node; - struct drm_mm_node mm_node; + u64 start; + u64 size; + struct list_head allocated; + struct list_head blocks; }; static inline struct amdgpu_vram_mgr * @@ -186,18 +188,18 @@ const struct attribute_group amdgpu_vram_mgr_attr_group = { }; /** - * amdgpu_vram_mgr_vis_size - Calculate visible node size + * amdgpu_vram_mgr_vis_size - Calculate visible block size * * @adev: amdgpu_device pointer - * @node: MM node structure + * @block: DRM BUDDY block structure * - * Calculate how many bytes of the MM node are inside visible VRAM + * Calculate how many bytes of the DRM BUDDY block are inside visible VRAM */ static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev, - struct drm_mm_node *node) + struct drm_buddy_block *block) { - uint64_t start = node->start << PAGE_SHIFT; - uint64_t end = (node->size + node->start) << PAGE_SHIFT; + u64 start = amdgpu_vram_mgr_block_start(block); + u64 end = start + amdgpu_vram_mgr_block_size(block); if (start >= adev->gmc.visible_vram_size) return 0; @@ -218,9 +220,9 @@ u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct ttm_resource *res = bo->tbo.resource; - unsigned pages = res->num_pages; - struct drm_mm_node *mm; - u64 usage; + struct amdgpu_vram_mgr_resource *vres = to_amdgpu_vram_mgr_resource(res); + struct drm_buddy_block *block; + u64 usage = 0; if (amdgpu_gmc_vram_full_visible(&adev->gmc)) return amdgpu_bo_size(bo); @@ -228,9 +230,8 @@ u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo) if (res->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT) return 0; - mm = &container_of(res, struct ttm_range_mgr_node, base)->mm_nodes[0]; - for (usage = 0; pages; pages -= mm->size, mm++) - usage += amdgpu_vram_mgr_vis_size(adev, mm); + list_for_each_entry(block, &vres->blocks, link) + usage += amdgpu_vram_mgr_vis_size(adev, block); return usage; } @@ -240,23 +241,30 @@ static void amdgpu_vram_mgr_do_reserve(struct ttm_resource_manager *man) { struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); struct amdgpu_device *adev = to_amdgpu_device(mgr); - struct drm_mm *mm = &mgr->mm; + struct drm_buddy *mm = &mgr->mm; struct amdgpu_vram_reservation *rsv, *temp; + struct drm_buddy_block *block; uint64_t vis_usage; - list_for_each_entry_safe(rsv, temp, &mgr->reservations_pending, node) { - if (drm_mm_reserve_node(mm, &rsv->mm_node)) + list_for_each_entry_safe(rsv, temp, &mgr->reservations_pending, blocks) { + if (drm_buddy_alloc_blocks(mm, rsv->start, rsv->start + rsv->size, + rsv->size, mm->chunk_size, &rsv->allocated, + DRM_BUDDY_RANGE_ALLOCATION)) + continue; + + block = amdgpu_vram_mgr_first_block(&rsv->allocated); + if (!block) continue; dev_dbg(adev->dev, "Reservation 0x%llx - %lld, Succeeded\n", - rsv->mm_node.start, rsv->mm_node.size); + rsv->start, rsv->size); - vis_usage = amdgpu_vram_mgr_vis_size(adev, &rsv->mm_node); + vis_usage = amdgpu_vram_mgr_vis_size(adev, block); atomic64_add(vis_usage, &mgr->vis_usage); spin_lock(&man->bdev->lru_lock); - man->usage += rsv->mm_node.size << PAGE_SHIFT; + man->usage += rsv->size; spin_unlock(&man->bdev->lru_lock); - list_move(&rsv->node, &mgr->reserved_pages); + list_move(&rsv->blocks, &mgr->reserved_pages); } } @@ -278,14 +286,16 @@ int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr, if (!rsv) return -ENOMEM; - INIT_LIST_HEAD(&rsv->node); - rsv->mm_node.start = start >> PAGE_SHIFT; - rsv->mm_node.size = size >> PAGE_SHIFT; + INIT_LIST_HEAD(&rsv->allocated); + INIT_LIST_HEAD(&rsv->blocks); - spin_lock(&mgr->lock); - list_add_tail(&rsv->node, &mgr->reservations_pending); + rsv->start = start; + rsv->size = size; + + mutex_lock(&mgr->lock); + list_add_tail(&rsv->blocks, &mgr->reservations_pending); amdgpu_vram_mgr_do_reserve(&mgr->manager); - spin_unlock(&mgr->lock); + mutex_unlock(&mgr->lock); return 0; } @@ -307,19 +317,19 @@ int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr, struct amdgpu_vram_reservation *rsv; int ret; - spin_lock(&mgr->lock); + mutex_lock(&mgr->lock); - list_for_each_entry(rsv, &mgr->reservations_pending, node) { - if ((rsv->mm_node.start <= start) && - (start < (rsv->mm_node.start + rsv->mm_node.size))) { + list_for_each_entry(rsv, &mgr->reservations_pending, blocks) { + if (rsv->start <= start && + (start < (rsv->start + rsv->size))) { ret = -EBUSY; goto out; } } - list_for_each_entry(rsv, &mgr->reserved_pages, node) { - if ((rsv->mm_node.start <= start) && - (start < (rsv->mm_node.start + rsv->mm_node.size))) { + list_for_each_entry(rsv, &mgr->reserved_pages, blocks) { + if (rsv->start <= start && + (start < (rsv->start + rsv->size))) { ret = 0; goto out; } @@ -327,33 +337,11 @@ int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr, ret = -ENOENT; out: - spin_unlock(&mgr->lock); + mutex_unlock(&mgr->lock); return ret; } /** - * amdgpu_vram_mgr_virt_start - update virtual start address - * - * @mem: ttm_resource to update - * @node: just allocated node - * - * Calculate a virtual BO start address to easily check if everything is CPU - * accessible. - */ -static void amdgpu_vram_mgr_virt_start(struct ttm_resource *mem, - struct drm_mm_node *node) -{ - unsigned long start; - - start = node->start + node->size; - if (start > mem->num_pages) - start -= mem->num_pages; - else - start = 0; - mem->start = max(mem->start, start); -} - -/** * amdgpu_vram_mgr_new - allocate new ranges * * @man: TTM memory type manager @@ -368,46 +356,44 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, const struct ttm_place *place, struct ttm_resource **res) { - unsigned long lpfn, num_nodes, pages_per_node, pages_left, pages; + u64 vis_usage = 0, max_bytes, cur_size, min_block_size; struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); struct amdgpu_device *adev = to_amdgpu_device(mgr); - uint64_t vis_usage = 0, mem_bytes, max_bytes; - struct ttm_range_mgr_node *node; - struct drm_mm *mm = &mgr->mm; - enum drm_mm_insert_mode mode; - unsigned i; + struct amdgpu_vram_mgr_resource *vres; + u64 size, remaining_size, lpfn, fpfn; + struct drm_buddy *mm = &mgr->mm; + struct drm_buddy_block *block; + unsigned long pages_per_block; int r; - lpfn = place->lpfn; + lpfn = place->lpfn << PAGE_SHIFT; if (!lpfn) - lpfn = man->size >> PAGE_SHIFT; + lpfn = man->size; + + fpfn = place->fpfn << PAGE_SHIFT; max_bytes = adev->gmc.mc_vram_size; if (tbo->type != ttm_bo_type_kernel) max_bytes -= AMDGPU_VM_RESERVED_VRAM; - mem_bytes = tbo->base.size; if (place->flags & TTM_PL_FLAG_CONTIGUOUS) { - pages_per_node = ~0ul; - num_nodes = 1; + pages_per_block = ~0ul; } else { #ifdef CONFIG_TRANSPARENT_HUGEPAGE - pages_per_node = HPAGE_PMD_NR; + pages_per_block = HPAGE_PMD_NR; #else /* default to 2MB */ - pages_per_node = 2UL << (20UL - PAGE_SHIFT); + pages_per_block = 2UL << (20UL - PAGE_SHIFT); #endif - pages_per_node = max_t(uint32_t, pages_per_node, - tbo->page_alignment); - num_nodes = DIV_ROUND_UP_ULL(PFN_UP(mem_bytes), pages_per_node); + pages_per_block = max_t(uint32_t, pages_per_block, + tbo->page_alignment); } - node = kvmalloc(struct_size(node, mm_nodes, num_nodes), - GFP_KERNEL | __GFP_ZERO); - if (!node) + vres = kzalloc(sizeof(*vres), GFP_KERNEL); + if (!vres) return -ENOMEM; - ttm_resource_init(tbo, place, &node->base); + ttm_resource_init(tbo, place, &vres->base); /* bail out quickly if there's likely not enough VRAM for this BO */ if (ttm_resource_manager_usage(man) > max_bytes) { @@ -415,66 +401,130 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, goto error_fini; } - mode = DRM_MM_INSERT_BEST; + INIT_LIST_HEAD(&vres->blocks); + if (place->flags & TTM_PL_FLAG_TOPDOWN) - mode = DRM_MM_INSERT_HIGH; - - pages_left = node->base.num_pages; - - /* Limit maximum size to 2GB due to SG table limitations */ - pages = min(pages_left, 2UL << (30 - PAGE_SHIFT)); - - i = 0; - spin_lock(&mgr->lock); - while (pages_left) { - uint32_t alignment = tbo->page_alignment; - - if (pages >= pages_per_node) - alignment = pages_per_node; - - r = drm_mm_insert_node_in_range(mm, &node->mm_nodes[i], pages, - alignment, 0, place->fpfn, - lpfn, mode); - if (unlikely(r)) { - if (pages > pages_per_node) { - if (is_power_of_2(pages)) - pages = pages / 2; - else - pages = rounddown_pow_of_two(pages); - continue; + vres->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION; + + if (fpfn || lpfn != man->size) + /* Allocate blocks in desired range */ + vres->flags |= DRM_BUDDY_RANGE_ALLOCATION; + + remaining_size = vres->base.num_pages << PAGE_SHIFT; + + mutex_lock(&mgr->lock); + while (remaining_size) { + if (tbo->page_alignment) + min_block_size = tbo->page_alignment << PAGE_SHIFT; + else + min_block_size = mgr->default_page_size; + + BUG_ON(min_block_size < mm->chunk_size); + + /* Limit maximum size to 2GiB due to SG table limitations */ + size = min(remaining_size, 2ULL << 30); + + if (size >= pages_per_block << PAGE_SHIFT) + min_block_size = pages_per_block << PAGE_SHIFT; + + cur_size = size; + + if (fpfn + size != place->lpfn << PAGE_SHIFT) { + /* + * Except for actual range allocation, modify the size and + * min_block_size conforming to continuous flag enablement + */ + if (place->flags & TTM_PL_FLAG_CONTIGUOUS) { + size = roundup_pow_of_two(size); + min_block_size = size; + /* + * Modify the size value if size is not + * aligned with min_block_size + */ + } else if (!IS_ALIGNED(size, min_block_size)) { + size = round_up(size, min_block_size); } - goto error_free; } - vis_usage += amdgpu_vram_mgr_vis_size(adev, &node->mm_nodes[i]); - amdgpu_vram_mgr_virt_start(&node->base, &node->mm_nodes[i]); - pages_left -= pages; - ++i; + r = drm_buddy_alloc_blocks(mm, fpfn, + lpfn, + size, + min_block_size, + &vres->blocks, + vres->flags); + if (unlikely(r)) + goto error_free_blocks; + + if (size > remaining_size) + remaining_size = 0; + else + remaining_size -= size; + } + mutex_unlock(&mgr->lock); + + if (cur_size != size) { + struct drm_buddy_block *block; + struct list_head *trim_list; + u64 original_size; + LIST_HEAD(temp); + + trim_list = &vres->blocks; + original_size = vres->base.num_pages << PAGE_SHIFT; + + /* + * If size value is rounded up to min_block_size, trim the last + * block to the required size + */ + if (!list_is_singular(&vres->blocks)) { + block = list_last_entry(&vres->blocks, typeof(*block), link); + list_move_tail(&block->link, &temp); + trim_list = &temp; + /* + * Compute the original_size value by subtracting the + * last block size with (aligned size - original size) + */ + original_size = amdgpu_vram_mgr_block_size(block) - (size - cur_size); + } - if (pages > pages_left) - pages = pages_left; + mutex_lock(&mgr->lock); + drm_buddy_block_trim(mm, + original_size, + trim_list); + mutex_unlock(&mgr->lock); + + if (!list_empty(&temp)) + list_splice_tail(trim_list, &vres->blocks); + } + + list_for_each_entry(block, &vres->blocks, link) + vis_usage += amdgpu_vram_mgr_vis_size(adev, block); + + block = amdgpu_vram_mgr_first_block(&vres->blocks); + if (!block) { + r = -EINVAL; + goto error_fini; } - spin_unlock(&mgr->lock); - if (i == 1) - node->base.placement |= TTM_PL_FLAG_CONTIGUOUS; + vres->base.start = amdgpu_vram_mgr_block_start(block) >> PAGE_SHIFT; + + if (amdgpu_is_vram_mgr_blocks_contiguous(&vres->blocks)) + vres->base.placement |= TTM_PL_FLAG_CONTIGUOUS; if (adev->gmc.xgmi.connected_to_cpu) - node->base.bus.caching = ttm_cached; + vres->base.bus.caching = ttm_cached; else - node->base.bus.caching = ttm_write_combined; + vres->base.bus.caching = ttm_write_combined; atomic64_add(vis_usage, &mgr->vis_usage); - *res = &node->base; + *res = &vres->base; return 0; -error_free: - while (i--) - drm_mm_remove_node(&node->mm_nodes[i]); - spin_unlock(&mgr->lock); +error_free_blocks: + drm_buddy_free_list(mm, &vres->blocks); + mutex_unlock(&mgr->lock); error_fini: - ttm_resource_fini(man, &node->base); - kvfree(node); + ttm_resource_fini(man, &vres->base); + kfree(vres); return r; } @@ -490,27 +540,26 @@ error_fini: static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man, struct ttm_resource *res) { - struct ttm_range_mgr_node *node = to_ttm_range_mgr_node(res); + struct amdgpu_vram_mgr_resource *vres = to_amdgpu_vram_mgr_resource(res); struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); struct amdgpu_device *adev = to_amdgpu_device(mgr); + struct drm_buddy *mm = &mgr->mm; + struct drm_buddy_block *block; uint64_t vis_usage = 0; - unsigned i, pages; - spin_lock(&mgr->lock); - for (i = 0, pages = res->num_pages; pages; - pages -= node->mm_nodes[i].size, ++i) { - struct drm_mm_node *mm = &node->mm_nodes[i]; + mutex_lock(&mgr->lock); + list_for_each_entry(block, &vres->blocks, link) + vis_usage += amdgpu_vram_mgr_vis_size(adev, block); - drm_mm_remove_node(mm); - vis_usage += amdgpu_vram_mgr_vis_size(adev, mm); - } amdgpu_vram_mgr_do_reserve(man); - spin_unlock(&mgr->lock); + + drm_buddy_free_list(mm, &vres->blocks); + mutex_unlock(&mgr->lock); atomic64_sub(vis_usage, &mgr->vis_usage); ttm_resource_fini(man, res); - kvfree(node); + kfree(vres); } /** @@ -542,7 +591,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, if (!*sgt) return -ENOMEM; - /* Determine the number of DRM_MM nodes to export */ + /* Determine the number of DRM_BUDDY blocks to export */ amdgpu_res_first(res, offset, length, &cursor); while (cursor.remaining) { num_entries++; @@ -558,10 +607,10 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, sg->length = 0; /* - * Walk down DRM_MM nodes to populate scatterlist nodes - * @note: Use iterator api to get first the DRM_MM node + * Walk down DRM_BUDDY blocks to populate scatterlist nodes + * @note: Use iterator api to get first the DRM_BUDDY block * and the number of bytes from it. Access the following - * DRM_MM node(s) if more buffer needs to exported + * DRM_BUDDY block(s) if more buffer needs to exported */ amdgpu_res_first(res, offset, length, &cursor); for_each_sgtable_sg((*sgt), sg, i) { @@ -648,13 +697,22 @@ static void amdgpu_vram_mgr_debug(struct ttm_resource_manager *man, struct drm_printer *printer) { struct amdgpu_vram_mgr *mgr = to_vram_mgr(man); + struct drm_buddy *mm = &mgr->mm; + struct drm_buddy_block *block; drm_printf(printer, " vis usage:%llu\n", amdgpu_vram_mgr_vis_usage(mgr)); - spin_lock(&mgr->lock); - drm_mm_print(&mgr->mm, printer); - spin_unlock(&mgr->lock); + mutex_lock(&mgr->lock); + drm_printf(printer, "default_page_size: %lluKiB\n", + mgr->default_page_size >> 10); + + drm_buddy_print(mm, printer); + + drm_printf(printer, "reserved:\n"); + list_for_each_entry(block, &mgr->reserved_pages, link) + drm_buddy_block_print(mm, block, printer); + mutex_unlock(&mgr->lock); } static const struct ttm_resource_manager_func amdgpu_vram_mgr_func = { @@ -674,16 +732,21 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev) { struct amdgpu_vram_mgr *mgr = &adev->mman.vram_mgr; struct ttm_resource_manager *man = &mgr->manager; + int err; ttm_resource_manager_init(man, &adev->mman.bdev, adev->gmc.real_vram_size); man->func = &amdgpu_vram_mgr_func; - drm_mm_init(&mgr->mm, 0, man->size >> PAGE_SHIFT); - spin_lock_init(&mgr->lock); + err = drm_buddy_init(&mgr->mm, man->size, PAGE_SIZE); + if (err) + return err; + + mutex_init(&mgr->lock); INIT_LIST_HEAD(&mgr->reservations_pending); INIT_LIST_HEAD(&mgr->reserved_pages); + mgr->default_page_size = PAGE_SIZE; ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_VRAM, &mgr->manager); ttm_resource_manager_set_used(man, true); @@ -711,16 +774,16 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev) if (ret) return; - spin_lock(&mgr->lock); - list_for_each_entry_safe(rsv, temp, &mgr->reservations_pending, node) + mutex_lock(&mgr->lock); + list_for_each_entry_safe(rsv, temp, &mgr->reservations_pending, blocks) kfree(rsv); - list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, node) { - drm_mm_remove_node(&rsv->mm_node); + list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, blocks) { + drm_buddy_free_list(&mgr->mm, &rsv->blocks); kfree(rsv); } - drm_mm_takedown(&mgr->mm); - spin_unlock(&mgr->lock); + drm_buddy_fini(&mgr->mm); + mutex_unlock(&mgr->lock); ttm_resource_manager_cleanup(man); ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_VRAM, NULL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h new file mode 100644 index 000000000000..9a2db87186c7 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: MIT + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + */ + +#ifndef __AMDGPU_VRAM_MGR_H__ +#define __AMDGPU_VRAM_MGR_H__ + +#include <drm/drm_buddy.h> + +struct amdgpu_vram_mgr { + struct ttm_resource_manager manager; + struct drm_buddy mm; + /* protects access to buffer objects */ + struct mutex lock; + struct list_head reservations_pending; + struct list_head reserved_pages; + atomic64_t vis_usage; + u64 default_page_size; +}; + +struct amdgpu_vram_mgr_resource { + struct ttm_resource base; + struct list_head blocks; + unsigned long flags; +}; + +static inline u64 amdgpu_vram_mgr_block_start(struct drm_buddy_block *block) +{ + return drm_buddy_block_offset(block); +} + +static inline u64 amdgpu_vram_mgr_block_size(struct drm_buddy_block *block) +{ + return PAGE_SIZE << drm_buddy_block_order(block); +} + +static inline struct drm_buddy_block * +amdgpu_vram_mgr_first_block(struct list_head *list) +{ + return list_first_entry_or_null(list, struct drm_buddy_block, link); +} + +static inline bool amdgpu_is_vram_mgr_blocks_contiguous(struct list_head *head) +{ + struct drm_buddy_block *block; + u64 start, size; + + block = amdgpu_vram_mgr_first_block(head); + if (!block) + return false; + + while (head != block->link.next) { + start = amdgpu_vram_mgr_block_start(block); + size = amdgpu_vram_mgr_block_size(block); + + block = list_entry(block->link.next, struct drm_buddy_block, link); + if (start + size != amdgpu_vram_mgr_block_start(block)) + return false; + } + + return true; +} + +static inline struct amdgpu_vram_mgr_resource * +to_amdgpu_vram_mgr_resource(struct ttm_resource *res) +{ + return container_of(res, struct amdgpu_vram_mgr_resource, base); +} + +#endif diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f4c6accd3226..9426e252d8aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3293,7 +3293,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_3[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000242), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -3429,7 +3429,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_6[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000042), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x00000044), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -3454,7 +3454,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_7[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0xffffffff, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0xffffffff, 0x00800000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0x0c1807ff, 0x00000041), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x1ff1ffff, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Vangogh, 0x1ff1ffff, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL1_PIPE_STEER, 0x000000ff, 0x000000e4), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_0, 0x77777777, 0x32103210), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2_PIPE_STEER_1, 0x77777777, 0x32103210), @@ -7689,6 +7689,7 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(10, 3, 1): case IP_VERSION(10, 3, 3): + case IP_VERSION(10, 3, 7): preempt_disable(); clock_hi = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh); clock_lo = RREG32_SOC15_NO_KIQ(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 3c1d440824a7..5228421b0f72 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -814,7 +814,7 @@ static int gmc_v10_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) { + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) { adev->gmc.aper_base = adev->gfxhub.funcs->get_mc_fb_offset(adev); adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 344d819b4c1b..979da6f510e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -381,8 +381,9 @@ static int gmc_v7_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU && - adev->gmc.real_vram_size > adev->gmc.aper_size) { + if ((adev->flags & AMD_IS_APU) && + adev->gmc.real_vram_size > adev->gmc.aper_size && + !amdgpu_passthrough(adev)) { adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22; adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index ca9841d5669f..1932a3e4af7e 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -581,7 +581,7 @@ static int gmc_v8_0_mc_init(struct amdgpu_device *adev) adev->gmc.aper_size = pci_resource_len(adev->pdev, 0); #ifdef CONFIG_X86_64 - if (adev->flags & AMD_IS_APU) { + if ((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) { adev->gmc.aper_base = ((u64)RREG32(mmMC_VM_FB_OFFSET)) << 22; adev->gmc.aper_size = adev->gmc.real_vram_size; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 431742eb7811..6009fbfdcc19 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1456,7 +1456,7 @@ static int gmc_v9_0_mc_init(struct amdgpu_device *adev) */ /* check whether both host-gpu and gpu-gpu xgmi links exist */ - if ((adev->flags & AMD_IS_APU) || + if (((adev->flags & AMD_IS_APU) && !amdgpu_passthrough(adev)) || (adev->gmc.xgmi.supported && adev->gmc.xgmi.connected_to_cpu)) { adev->gmc.aper_base = @@ -1721,7 +1721,7 @@ static int gmc_v9_0_sw_fini(void *handle) amdgpu_gem_force_release(adev); amdgpu_vm_manager_fini(adev); amdgpu_gart_table_vram_free(adev); - amdgpu_bo_unref(&adev->gmc.pdb0_bo); + amdgpu_bo_free_kernel(&adev->gmc.pdb0_bo, NULL, &adev->gmc.ptr_pdb0); amdgpu_bo_fini(adev); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index dff54190b96c..f0fbcda76f5e 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -24,6 +24,7 @@ #include <linux/firmware.h> #include "amdgpu.h" +#include "amdgpu_cs.h" #include "amdgpu_vcn.h" #include "amdgpu_pm.h" #include "soc15.h" @@ -1900,6 +1901,75 @@ static const struct amd_ip_funcs vcn_v1_0_ip_funcs = { .set_powergating_state = vcn_v1_0_set_powergating_state, }; +/* + * It is a hardware issue that VCN can't handle a GTT TMZ buffer on + * CHIP_RAVEN series ASIC. Move such a GTT TMZ buffer to VRAM domain + * before command submission as a workaround. + */ +static int vcn_v1_0_validate_bo(struct amdgpu_cs_parser *parser, + struct amdgpu_job *job, + uint64_t addr) +{ + struct ttm_operation_ctx ctx = { false, false }; + struct amdgpu_fpriv *fpriv = parser->filp->driver_priv; + struct amdgpu_vm *vm = &fpriv->vm; + struct amdgpu_bo_va_mapping *mapping; + struct amdgpu_bo *bo; + int r; + + addr &= AMDGPU_GMC_HOLE_MASK; + if (addr & 0x7) { + DRM_ERROR("VCN messages must be 8 byte aligned!\n"); + return -EINVAL; + } + + mapping = amdgpu_vm_bo_lookup_mapping(vm, addr/AMDGPU_GPU_PAGE_SIZE); + if (!mapping || !mapping->bo_va || !mapping->bo_va->base.bo) + return -EINVAL; + + bo = mapping->bo_va->base.bo; + if (!(bo->flags & AMDGPU_GEM_CREATE_ENCRYPTED)) + return 0; + + amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM); + r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); + if (r) { + DRM_ERROR("Failed to validate the VCN message BO (%d)!\n", r); + return r; + } + + return r; +} + +static int vcn_v1_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, + struct amdgpu_job *job, + struct amdgpu_ib *ib) +{ + uint32_t msg_lo = 0, msg_hi = 0; + int i, r; + + if (!(ib->flags & AMDGPU_IB_FLAGS_SECURE)) + return 0; + + for (i = 0; i < ib->length_dw; i += 2) { + uint32_t reg = amdgpu_ib_get_value(ib, i); + uint32_t val = amdgpu_ib_get_value(ib, i + 1); + + if (reg == PACKET0(p->adev->vcn.internal.data0, 0)) { + msg_lo = val; + } else if (reg == PACKET0(p->adev->vcn.internal.data1, 0)) { + msg_hi = val; + } else if (reg == PACKET0(p->adev->vcn.internal.cmd, 0)) { + r = vcn_v1_0_validate_bo(p, job, + ((u64)msg_hi) << 32 | msg_lo); + if (r) + return r; + } + } + + return 0; +} + static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .type = AMDGPU_RING_TYPE_VCN_DEC, .align_mask = 0xf, @@ -1910,6 +1980,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .get_rptr = vcn_v1_0_dec_ring_get_rptr, .get_wptr = vcn_v1_0_dec_ring_get_wptr, .set_wptr = vcn_v1_0_dec_ring_set_wptr, + .patch_cs_in_place = vcn_v1_0_ring_patch_cs_in_place, .emit_frame_size = 6 + 6 + /* hdp invalidate / flush */ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 + diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index c87263ed20ec..cb5f0a12333f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -219,6 +219,11 @@ static int vcn_v3_0_sw_init(void *handle) cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG) | cpu_to_le32(AMDGPU_VCN_FW_SHARED_FLAG_0_RB); fw_shared->sw_ring.is_enabled = cpu_to_le32(DEC_SW_RING_ENABLED); + fw_shared->present_flag_0 |= AMDGPU_VCN_SMU_VERSION_INFO_FLAG; + if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 2)) + fw_shared->smu_interface_info.smu_interface_type = 2; + else if (adev->ip_versions[UVD_HWIP][0] == IP_VERSION(3, 1, 1)) + fw_shared->smu_interface_info.smu_interface_type = 1; if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); @@ -575,8 +580,8 @@ static void vcn_v3_0_mc_resume_dpg_mode(struct amdgpu_device *adev, int inst_idx AMDGPU_GPU_PAGE_ALIGN(sizeof(struct amdgpu_fw_shared)), 0, indirect); /* VCN global tiling registers */ - WREG32_SOC15_DPG_MODE(0, SOC15_DPG_MODE_OFFSET( - UVD, 0, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); + WREG32_SOC15_DPG_MODE(inst_idx, SOC15_DPG_MODE_OFFSET( + UVD, inst_idx, mmUVD_GFX10_ADDR_CONFIG), adev->gfx.config.gb_addr_config, 0, indirect); } static void vcn_v3_0_disable_static_power_gating(struct amdgpu_device *adev, int inst) @@ -1480,8 +1485,11 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) static int vcn_v3_0_stop_dpg_mode(struct amdgpu_device *adev, int inst_idx) { + struct dpg_pause_state state = {.fw_based = VCN_DPG_STATE__UNPAUSE}; uint32_t tmp; + vcn_v3_0_pause_dpg_mode(adev, inst_idx, &state); + /* Wait for power status to be 1 */ SOC15_WAIT_ON_RREG(VCN, inst_idx, mmUVD_POWER_STATUS, 1, UVD_POWER_STATUS__UVD_POWER_STATUS_MASK); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index 339e12c94cff..62aa6c9d5123 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -483,15 +483,10 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, } /* Verify module parameters regarding mapped process number*/ - if ((hws_max_conc_proc < 0) - || (hws_max_conc_proc > kfd->vm_info.vmid_num_kfd)) { - dev_err(kfd_device, - "hws_max_conc_proc %d must be between 0 and %d, use %d instead\n", - hws_max_conc_proc, kfd->vm_info.vmid_num_kfd, - kfd->vm_info.vmid_num_kfd); + if (hws_max_conc_proc >= 0) + kfd->max_proc_per_quantum = min((u32)hws_max_conc_proc, kfd->vm_info.vmid_num_kfd); + else kfd->max_proc_per_quantum = kfd->vm_info.vmid_num_kfd; - } else - kfd->max_proc_per_quantum = hws_max_conc_proc; /* calculate max size of mqds needed for queues */ size = max_num_of_queues_per_device * @@ -536,7 +531,8 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, goto kfd_doorbell_error; } - kfd->hive_id = kfd->adev->gmc.xgmi.hive_id; + if (amdgpu_use_xgmi_p2p) + kfd->hive_id = kfd->adev->gmc.xgmi.hive_id; kfd->noretry = kfd->adev->gmc.noretry; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index deecccebe5b6..64f4a51cc880 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -749,6 +749,8 @@ static struct kfd_event_waiter *alloc_event_waiters(uint32_t num_events) event_waiters = kmalloc_array(num_events, sizeof(struct kfd_event_waiter), GFP_KERNEL); + if (!event_waiters) + return NULL; for (i = 0; (event_waiters) && (i < num_events) ; i++) { init_wait(&event_waiters[i].wait); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index e4beebb1c80a..f2e1d506ba21 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -247,15 +247,6 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd) return ret; } - ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client, - O_RDWR); - if (ret < 0) { - kfifo_free(&client->fifo); - kfree(client); - return ret; - } - *fd = ret; - init_waitqueue_head(&client->wait_queue); spin_lock_init(&client->lock); client->events = 0; @@ -265,5 +256,20 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd) list_add_rcu(&client->list, &dev->smi_clients); spin_unlock(&dev->smi_lock); + ret = anon_inode_getfd(kfd_smi_name, &kfd_smi_ev_fops, (void *)client, + O_RDWR); + if (ret < 0) { + spin_lock(&dev->smi_lock); + list_del_rcu(&client->list); + spin_unlock(&dev->smi_lock); + + synchronize_rcu(); + + kfifo_free(&client->fifo); + kfree(client); + return ret; + } + *fd = ret; + return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 3b8856b4cece..b3fc3e958227 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -548,7 +548,7 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange, goto reserve_bo_failed; } - r = dma_resv_reserve_shared(bo->tbo.base.resv, 1); + r = dma_resv_reserve_fences(bo->tbo.base.resv, 1); if (r) { pr_debug("failed %d to reserve bo\n", r); amdgpu_bo_unreserve(bo); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b30656959fd8..73423b805b54 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2714,7 +2714,8 @@ static int dm_resume(void *handle) * this is the case when traversing through already created * MST connectors, should be skipped */ - if (aconnector->mst_port) + if (aconnector->dc_link && + aconnector->dc_link->type == dc_connection_mst_branch) continue; mutex_lock(&aconnector->hpd_lock); @@ -3972,7 +3973,7 @@ static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *cap max - min); } -static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, +static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, int bl_idx, u32 user_brightness) { @@ -4003,7 +4004,8 @@ static int amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm, DRM_DEBUG("DM: Failed to update backlight on eDP[%d]\n", bl_idx); } - return rc ? 0 : 1; + if (rc) + dm->actual_brightness[bl_idx] = user_brightness; } static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) @@ -9236,7 +9238,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, * deadlock during GPU reset when this fence will not signal * but we hold reservation lock for the BO. */ - r = dma_resv_wait_timeout(abo->tbo.base.resv, true, false, + r = dma_resv_wait_timeout(abo->tbo.base.resv, + DMA_RESV_USAGE_WRITE, false, msecs_to_jiffies(5000)); if (unlikely(r <= 0)) DRM_ERROR("Waiting for fences timed out!"); @@ -9947,7 +9950,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) /* restore the backlight level */ for (i = 0; i < dm->num_of_edps; i++) { if (dm->backlight_dev[i] && - (amdgpu_dm_backlight_get_level(dm, i) != dm->brightness[i])) + (dm->actual_brightness[i] != dm->brightness[i])) amdgpu_dm_backlight_set_level(dm, i, dm->brightness[i]); } #endif diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 6a908d736d6a..7e44b0429448 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -540,6 +540,12 @@ struct amdgpu_display_manager { * cached backlight values. */ u32 brightness[AMDGPU_DM_MAX_NUM_EDP]; + /** + * @actual_brightness: + * + * last successfully applied backlight values. + */ + u32 actual_brightness[AMDGPU_DM_MAX_NUM_EDP]; }; enum dsc_clock_force_state { diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index edda572dc570..8be4c1970628 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -436,57 +436,84 @@ static void dcn315_clk_mgr_helper_populate_bw_params( struct integrated_info *bios_info, const DpmClocks_315_t *clock_table) { - int i, j; + int i; struct clk_bw_params *bw_params = clk_mgr->base.bw_params; - uint32_t max_dispclk = 0, max_dppclk = 0; - - j = -1; - - ASSERT(NUM_DF_PSTATE_LEVELS <= MAX_NUM_DPM_LVL); - - /* Find lowest DPM, FCLK is filled in reverse order*/ - - for (i = NUM_DF_PSTATE_LEVELS - 1; i >= 0; i--) { - if (clock_table->DfPstateTable[i].FClk != 0) { - j = i; - break; + uint32_t max_dispclk, max_dppclk, max_pstate, max_socclk, max_fclk = 0, min_pstate = 0; + struct clk_limit_table_entry def_max = bw_params->clk_table.entries[bw_params->clk_table.num_entries - 1]; + + max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled); + max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled); + max_socclk = find_max_clk_value(clock_table->SocClocks, clock_table->NumSocClkLevelsEnabled); + + /* Find highest fclk pstate */ + for (i = 0; i < clock_table->NumDfPstatesEnabled; i++) { + if (clock_table->DfPstateTable[i].FClk > max_fclk) { + max_fclk = clock_table->DfPstateTable[i].FClk; + max_pstate = i; } } - if (j == -1) { - /* clock table is all 0s, just use our own hardcode */ - ASSERT(0); - return; - } - - bw_params->clk_table.num_entries = j + 1; - - /* dispclk and dppclk can be max at any voltage, same number of levels for both */ - if (clock_table->NumDispClkLevelsEnabled <= NUM_DISPCLK_DPM_LEVELS && - clock_table->NumDispClkLevelsEnabled <= NUM_DPPCLK_DPM_LEVELS) { - max_dispclk = find_max_clk_value(clock_table->DispClocks, clock_table->NumDispClkLevelsEnabled); - max_dppclk = find_max_clk_value(clock_table->DppClocks, clock_table->NumDispClkLevelsEnabled); - } else { - ASSERT(0); - } + /* For 315 we want to base clock table on dcfclk, need at least one entry regardless of pmfw table */ + for (i = 0; i < clock_table->NumDcfClkLevelsEnabled; i++) { + int j; + uint32_t min_fclk = clock_table->DfPstateTable[0].FClk; - for (i = 0; i < bw_params->clk_table.num_entries; i++, j--) { - int temp; + for (j = 1; j < clock_table->NumDfPstatesEnabled; j++) { + if (clock_table->DfPstateTable[j].Voltage <= clock_table->SocVoltage[i] + && clock_table->DfPstateTable[j].FClk < min_fclk) { + min_fclk = clock_table->DfPstateTable[j].FClk; + min_pstate = j; + } + } - bw_params->clk_table.entries[i].fclk_mhz = clock_table->DfPstateTable[j].FClk; - bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[j].MemClk; - bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[j].Voltage; + bw_params->clk_table.entries[i].fclk_mhz = min_fclk; + bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[min_pstate].MemClk; + bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[min_pstate].Voltage; + bw_params->clk_table.entries[i].dcfclk_mhz = clock_table->DcfClocks[i]; + bw_params->clk_table.entries[i].socclk_mhz = clock_table->SocClocks[i]; + bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk; + bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk; bw_params->clk_table.entries[i].wck_ratio = 1; - temp = find_clk_for_voltage(clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[j].Voltage); - if (temp) - bw_params->clk_table.entries[i].dcfclk_mhz = temp; - temp = find_clk_for_voltage(clock_table, clock_table->SocClocks, clock_table->DfPstateTable[j].Voltage); - if (temp) - bw_params->clk_table.entries[i].socclk_mhz = temp; + }; + + /* Make sure to include at least one entry and highest pstate */ + if (max_pstate != min_pstate) { + bw_params->clk_table.entries[i].fclk_mhz = max_fclk; + bw_params->clk_table.entries[i].memclk_mhz = clock_table->DfPstateTable[max_pstate].MemClk; + bw_params->clk_table.entries[i].voltage = clock_table->DfPstateTable[max_pstate].Voltage; + bw_params->clk_table.entries[i].dcfclk_mhz = find_clk_for_voltage( + clock_table, clock_table->DcfClocks, clock_table->DfPstateTable[max_pstate].Voltage); + bw_params->clk_table.entries[i].socclk_mhz = find_clk_for_voltage( + clock_table, clock_table->SocClocks, clock_table->DfPstateTable[max_pstate].Voltage); bw_params->clk_table.entries[i].dispclk_mhz = max_dispclk; bw_params->clk_table.entries[i].dppclk_mhz = max_dppclk; + bw_params->clk_table.entries[i].wck_ratio = 1; + i++; } + bw_params->clk_table.num_entries = i; + + /* Include highest socclk */ + if (bw_params->clk_table.entries[i-1].socclk_mhz < max_socclk) + bw_params->clk_table.entries[i-1].socclk_mhz = max_socclk; + /* Set any 0 clocks to max default setting. Not an issue for + * power since we aren't doing switching in such case anyway + */ + for (i = 0; i < bw_params->clk_table.num_entries; i++) { + if (!bw_params->clk_table.entries[i].fclk_mhz) { + bw_params->clk_table.entries[i].fclk_mhz = def_max.fclk_mhz; + bw_params->clk_table.entries[i].memclk_mhz = def_max.memclk_mhz; + bw_params->clk_table.entries[i].voltage = def_max.voltage; + } + if (!bw_params->clk_table.entries[i].dcfclk_mhz) + bw_params->clk_table.entries[i].dcfclk_mhz = def_max.dcfclk_mhz; + if (!bw_params->clk_table.entries[i].socclk_mhz) + bw_params->clk_table.entries[i].socclk_mhz = def_max.socclk_mhz; + if (!bw_params->clk_table.entries[i].dispclk_mhz) + bw_params->clk_table.entries[i].dispclk_mhz = def_max.dispclk_mhz; + if (!bw_params->clk_table.entries[i].dppclk_mhz) + bw_params->clk_table.entries[i].dppclk_mhz = def_max.dppclk_mhz; + } bw_params->vram_type = bios_info->memory_type; bw_params->num_channels = bios_info->ma_channel_number; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c index 880ffea2afc6..2600313fea57 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c @@ -80,8 +80,8 @@ static const struct IP_BASE NBIO_BASE = { { { { 0x00000000, 0x00000014, 0x00000D #define VBIOSSMC_MSG_SetDppclkFreq 0x06 ///< Set DPP clock frequency in MHZ #define VBIOSSMC_MSG_SetHardMinDcfclkByFreq 0x07 ///< Set DCF clock frequency hard min in MHZ #define VBIOSSMC_MSG_SetMinDeepSleepDcfclk 0x08 ///< Set DCF clock minimum frequency in deep sleep in MHZ -#define VBIOSSMC_MSG_SetPhyclkVoltageByFreq 0x09 ///< Set display phy clock frequency in MHZ in case VMIN does not support phy frequency -#define VBIOSSMC_MSG_GetFclkFrequency 0x0A ///< Get FCLK frequency, return frequemcy in MHZ +#define VBIOSSMC_MSG_GetDtbclkFreq 0x09 ///< Get display dtb clock frequency in MHZ in case VMIN does not support phy frequency +#define VBIOSSMC_MSG_SetDtbClk 0x0A ///< Set dtb clock frequency, return frequemcy in MHZ #define VBIOSSMC_MSG_SetDisplayCount 0x0B ///< Inform PMFW of number of display connected #define VBIOSSMC_MSG_EnableTmdp48MHzRefclkPwrDown 0x0C ///< To ask PMFW turn off TMDP 48MHz refclk during display off to save power #define VBIOSSMC_MSG_UpdatePmeRestore 0x0D ///< To ask PMFW to write into Azalia for PME wake up event @@ -324,15 +324,26 @@ int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr) return (dprefclk_get_mhz * 1000); } -int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr) +int dcn315_smu_get_dtbclk(struct clk_mgr_internal *clk_mgr) { int fclk_get_mhz = -1; if (clk_mgr->smu_present) { fclk_get_mhz = dcn315_smu_send_msg_with_param( clk_mgr, - VBIOSSMC_MSG_GetFclkFrequency, + VBIOSSMC_MSG_GetDtbclkFreq, 0); } return (fclk_get_mhz * 1000); } + +void dcn315_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable) +{ + if (!clk_mgr->smu_present) + return; + + dcn315_smu_send_msg_with_param( + clk_mgr, + VBIOSSMC_MSG_SetDtbClk, + enable); +} diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h index 66fa42f8dd18..5aa3275ac7d8 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.h @@ -37,6 +37,7 @@ #define NUM_SOC_VOLTAGE_LEVELS 4 #define NUM_DF_PSTATE_LEVELS 4 + typedef struct { uint16_t MinClock; // This is either DCFCLK or SOCCLK (in MHz) uint16_t MaxClock; // This is either DCFCLK or SOCCLK (in MHz) @@ -124,5 +125,6 @@ void dcn315_smu_transfer_wm_table_dram_2_smu(struct clk_mgr_internal *clk_mgr); void dcn315_smu_request_voltage_via_phyclk(struct clk_mgr_internal *clk_mgr, int requested_phyclk_khz); void dcn315_smu_enable_pme_wa(struct clk_mgr_internal *clk_mgr); int dcn315_smu_get_dpref_clk(struct clk_mgr_internal *clk_mgr); -int dcn315_smu_get_smu_fclk(struct clk_mgr_internal *clk_mgr); +int dcn315_smu_get_dtbclk(struct clk_mgr_internal *clk_mgr); +void dcn315_smu_set_dtbclk(struct clk_mgr_internal *clk_mgr, bool enable); #endif /* DAL_DC_315_SMU_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index f6e19efea756..c436db416708 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2389,6 +2389,8 @@ static enum surface_update_type check_update_surfaces_for_stream( if (stream_update->mst_bw_update) su_flags->bits.mst_bw = 1; + if (stream_update->crtc_timing_adjust && dc_extended_blank_supported(dc)) + su_flags->bits.crtc_timing_adjust = 1; if (su_flags->raw != 0) overall_type = UPDATE_TYPE_FULL; @@ -2650,6 +2652,9 @@ static void copy_stream_update_to_stream(struct dc *dc, if (update->vrr_infopacket) stream->vrr_infopacket = *update->vrr_infopacket; + if (update->crtc_timing_adjust) + stream->adjust = *update->crtc_timing_adjust; + if (update->dpms_off) stream->dpms_off = *update->dpms_off; @@ -4051,3 +4056,17 @@ void dc_notify_vsync_int_state(struct dc *dc, struct dc_stream_state *stream, bo if (pipe->stream_res.abm && pipe->stream_res.abm->funcs->set_abm_pause) pipe->stream_res.abm->funcs->set_abm_pause(pipe->stream_res.abm, !enable, i, pipe->stream_res.tg->inst); } +/* + * dc_extended_blank_supported: Decide whether extended blank is supported + * + * Extended blank is a freesync optimization feature to be enabled in the future. + * During the extra vblank period gained from freesync, we have the ability to enter z9/z10. + * + * @param [in] dc: Current DC state + * @return: Indicate whether extended blank is supported (true or false) + */ +bool dc_extended_blank_supported(struct dc *dc) +{ + return dc->debug.extended_blank_optimization && !dc->debug.disable_z10 + && dc->caps.zstate_support && dc->caps.is_apu; +} diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index cb87dd643180..bbaa5abdf888 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -983,8 +983,7 @@ static bool should_verify_link_capability_destructively(struct dc_link *link, destrictive = false; } } - } else if (dc_is_hdmi_signal(link->local_sink->sink_signal)) - destrictive = true; + } return destrictive; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 351081f574cb..22dabe596dfc 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -5216,6 +5216,62 @@ static void retrieve_cable_id(struct dc_link *link) &link->dpcd_caps.cable_id, &usbc_cable_id); } +/* DPRX may take some time to respond to AUX messages after HPD asserted. + * If AUX read unsuccessful, try to wake unresponsive DPRX by toggling DPCD SET_POWER (0x600). + */ +static enum dc_status wa_try_to_wake_dprx(struct dc_link *link, uint64_t timeout_ms) +{ + enum dc_status status = DC_ERROR_UNEXPECTED; + uint8_t dpcd_data = 0; + uint64_t start_ts = 0; + uint64_t current_ts = 0; + uint64_t time_taken_ms = 0; + enum dc_connection_type type = dc_connection_none; + + status = core_link_read_dpcd( + link, + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV, + &dpcd_data, + sizeof(dpcd_data)); + + if (status != DC_OK) { + DC_LOG_WARNING("%s: Read DPCD LTTPR_CAP failed - try to toggle DPCD SET_POWER for %lld ms.", + __func__, + timeout_ms); + start_ts = dm_get_timestamp(link->ctx); + + do { + if (!dc_link_detect_sink(link, &type) || type == dc_connection_none) + break; + + dpcd_data = DP_SET_POWER_D3; + status = core_link_write_dpcd( + link, + DP_SET_POWER, + &dpcd_data, + sizeof(dpcd_data)); + + dpcd_data = DP_SET_POWER_D0; + status = core_link_write_dpcd( + link, + DP_SET_POWER, + &dpcd_data, + sizeof(dpcd_data)); + + current_ts = dm_get_timestamp(link->ctx); + time_taken_ms = div_u64(dm_get_elapse_time_in_ns(link->ctx, current_ts, start_ts), 1000000); + } while (status != DC_OK && time_taken_ms < timeout_ms); + + DC_LOG_WARNING("%s: DPCD SET_POWER %s after %lld ms%s", + __func__, + (status == DC_OK) ? "succeeded" : "failed", + time_taken_ms, + (type == dc_connection_none) ? ". Unplugged." : "."); + } + + return status; +} + static bool retrieve_link_cap(struct dc_link *link) { /* DP_ADAPTER_CAP - DP_DPCD_REV + 1 == 16 and also DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT + 1 == 16, @@ -5251,6 +5307,15 @@ static bool retrieve_link_cap(struct dc_link *link) dc_link_aux_try_to_configure_timeout(link->ddc, LINK_AUX_DEFAULT_LTTPR_TIMEOUT_PERIOD); + /* Try to ensure AUX channel active before proceeding. */ + if (link->dc->debug.aux_wake_wa.bits.enable_wa) { + uint64_t timeout_ms = link->dc->debug.aux_wake_wa.bits.timeout_ms; + + if (link->dc->debug.aux_wake_wa.bits.use_default_timeout) + timeout_ms = LINK_AUX_WAKE_TIMEOUT_MS; + status = wa_try_to_wake_dprx(link, timeout_ms); + } + is_lttpr_present = dp_retrieve_lttpr_cap(link); /* Read DP tunneling information. */ status = dpcd_get_tunneling_device_data(link); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 7af153434e9e..d251c3f3a714 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1685,8 +1685,8 @@ bool dc_is_stream_unchanged( if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param) return false; - // Only Have Audio left to check whether it is same or not. This is a corner case for Tiled sinks - if (old_stream->audio_info.mode_count != stream->audio_info.mode_count) + /*compare audio info*/ + if (memcmp(&old_stream->audio_info, &stream->audio_info, sizeof(stream->audio_info)) != 0) return false; return true; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 4ffab7bb1098..77ef9d1f9ea8 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -188,6 +188,7 @@ struct dc_caps { bool psp_setup_panel_mode; bool extended_aux_timeout_support; bool dmcub_support; + bool zstate_support; uint32_t num_of_internal_disp; enum dp_protocol_version max_dp_protocol_version; unsigned int mall_size_per_mem_channel; @@ -525,6 +526,22 @@ union dpia_debug_options { uint32_t raw; }; +/* AUX wake work around options + * 0: enable/disable work around + * 1: use default timeout LINK_AUX_WAKE_TIMEOUT_MS + * 15-2: reserved + * 31-16: timeout in ms + */ +union aux_wake_wa_options { + struct { + uint32_t enable_wa : 1; + uint32_t use_default_timeout : 1; + uint32_t rsvd: 14; + uint32_t timeout_ms : 16; + } bits; + uint32_t raw; +}; + struct dc_debug_data { uint32_t ltFailCount; uint32_t i2cErrorCount; @@ -703,13 +720,15 @@ struct dc_debug_options { bool enable_driver_sequence_debug; enum det_size crb_alloc_policy; int crb_alloc_policy_min_disp_count; -#if defined(CONFIG_DRM_AMD_DC_DCN) bool disable_z10; +#if defined(CONFIG_DRM_AMD_DC_DCN) bool enable_z9_disable_interface; bool enable_sw_cntl_psr; union dpia_debug_options dpia_debug; #endif bool apply_vendor_specific_lttpr_wa; + bool extended_blank_optimization; + union aux_wake_wa_options aux_wake_wa; bool ignore_dpref_ss; uint8_t psr_power_use_phy_fsm; }; @@ -1369,6 +1388,8 @@ struct dc_sink_init_data { bool converter_disable_audio; }; +bool dc_extended_blank_supported(struct dc *dc); + struct dc_sink *dc_sink_create(const struct dc_sink_init_data *init_params); /* Newer interfaces */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 99a750f561f8..c4168c11257c 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -131,6 +131,7 @@ union stream_update_flags { uint32_t wb_update:1; uint32_t dsc_changed : 1; uint32_t mst_bw : 1; + uint32_t crtc_timing_adjust : 1; } bits; uint32_t raw; @@ -289,6 +290,7 @@ struct dc_stream_update { struct dc_3dlut *lut3d_func; struct test_pattern *pending_test_pattern; + struct dc_crtc_timing_adjust *crtc_timing_adjust; }; bool dc_is_stream_unchanged( diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index c3e141c19a77..781334b395ba 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -1497,16 +1497,12 @@ void dcn10_init_hw(struct dc *dc) link->link_status.link_active = true; } - /* Power gate DSCs */ - if (!is_optimized_init_done) { - for (i = 0; i < res_pool->res_cap->num_dsc; i++) - if (hws->funcs.dsc_pg_control != NULL) - hws->funcs.dsc_pg_control(hws, res_pool->dscs[i]->inst, false); - } - /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -1559,8 +1555,6 @@ void dcn10_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (dc->clk_mgr->funcs->notify_wm_ranges) dc->clk_mgr->funcs->notify_wm_ranges(dc->clk_mgr); @@ -2056,7 +2050,7 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, { struct dc_context *dc_ctx = dc->ctx; int i, master = -1, embedded = -1; - struct dc_crtc_timing hw_crtc_timing[MAX_PIPES] = {0}; + struct dc_crtc_timing *hw_crtc_timing; uint64_t phase[MAX_PIPES]; uint64_t modulo[MAX_PIPES]; unsigned int pclk; @@ -2067,6 +2061,10 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, uint32_t dp_ref_clk_100hz = dc->res_pool->dp_clock_source->ctx->dc->clk_mgr->dprefclk_khz*10; + hw_crtc_timing = kcalloc(MAX_PIPES, sizeof(*hw_crtc_timing), GFP_KERNEL); + if (!hw_crtc_timing) + return master; + if (dc->config.vblank_alignment_dto_params && dc->res_pool->dp_clock_source->funcs->override_dp_pix_clk) { embedded_h_total = @@ -2130,6 +2128,8 @@ static int dcn10_align_pixel_clocks(struct dc *dc, int group_size, } } + + kfree(hw_crtc_timing); return master; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index ab910deed481..4290eaf11a04 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1857,6 +1857,7 @@ void dcn20_optimize_bandwidth( struct dc_state *context) { struct hubbub *hubbub = dc->res_pool->hubbub; + int i; /* program dchubbub watermarks */ hubbub->funcs->program_watermarks(hubbub, @@ -1873,6 +1874,17 @@ void dcn20_optimize_bandwidth( dc->clk_mgr, context, true); + if (dc_extended_blank_supported(dc) && context->bw_ctx.bw.dcn.clk.zstate_support == DCN_ZSTATE_SUPPORT_ALLOW) { + for (i = 0; i < dc->res_pool->pipe_count; ++i) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + + if (pipe_ctx->stream && pipe_ctx->plane_res.hubp->funcs->program_extended_blank + && pipe_ctx->stream->adjust.v_total_min == pipe_ctx->stream->adjust.v_total_max + && pipe_ctx->stream->adjust.v_total_max > pipe_ctx->stream->timing.v_total) + pipe_ctx->plane_res.hubp->funcs->program_extended_blank(pipe_ctx->plane_res.hubp, + pipe_ctx->dlg_regs.optimized_min_dst_y_next_start); + } + } /* increase compbuf size */ if (hubbub->funcs->program_compbuf_size) hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index d473708d5399..7802d603f796 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -1976,7 +1976,6 @@ int dcn20_validate_apply_pipe_split_flags( /*If need split for odm but 4 way split already*/ if (split[i] == 2 && ((pipe->prev_odm_pipe && !pipe->prev_odm_pipe->prev_odm_pipe) || !pipe->next_odm_pipe)) { - ASSERT(0); /* NOT expected yet */ merge[i] = true; /* 4 -> 2 ODM */ } else if (split[i] == 0 && pipe->prev_odm_pipe) { ASSERT(0); /* NOT expected yet */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 612732656772..3fe4bfbb98a0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -644,7 +644,7 @@ static const struct dc_debug_options debug_defaults_drv = { .clock_trace = true, .disable_pplib_clock_request = true, .min_disp_clk_khz = 100000, - .pipe_split_policy = MPC_SPLIT_DYNAMIC, + .pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP, .force_single_disp_pipe_split = false, .disable_dcc = DCC_ENABLE, .vsr_support = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index ed0a0e5fd805..f61ec8763844 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -547,6 +547,9 @@ void dcn30_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -624,8 +627,6 @@ void dcn30_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks) dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub); diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c index 3e6d6ebd199e..51c5f3685470 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubbub.c @@ -1042,5 +1042,7 @@ void hubbub31_construct(struct dcn20_hubbub *hubbub31, hubbub31->detile_buf_size = det_size_kb * 1024; hubbub31->pixel_chunk_size = pixel_chunk_size_kb * 1024; hubbub31->crb_size_segs = config_return_buffer_size_kb / DCN31_CRB_SEGMENT_SIZE_KB; + + hubbub31->debug_test_index_pstate = 0x6; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c index 53b792b997b7..8ae6117953ca 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hubp.c @@ -54,6 +54,13 @@ void hubp31_soft_reset(struct hubp *hubp, bool reset) REG_UPDATE(DCHUBP_CNTL, HUBP_SOFT_RESET, reset); } +void hubp31_program_extended_blank(struct hubp *hubp, unsigned int min_dst_y_next_start_optimized) +{ + struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); + + REG_SET(BLANK_OFFSET_1, 0, MIN_DST_Y_NEXT_START, min_dst_y_next_start_optimized); +} + static struct hubp_funcs dcn31_hubp_funcs = { .hubp_enable_tripleBuffer = hubp2_enable_triplebuffer, .hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled, @@ -80,6 +87,7 @@ static struct hubp_funcs dcn31_hubp_funcs = { .set_unbounded_requesting = hubp31_set_unbounded_requesting, .hubp_soft_reset = hubp31_soft_reset, .hubp_in_blank = hubp1_in_blank, + .program_extended_blank = hubp31_program_extended_blank, }; bool hubp31_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c index 4be228680909..631d8ac63aa4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -199,6 +199,9 @@ void dcn31_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc_link_blank_all_dp_displays(dc); + if (hws->funcs.enable_power_gating_plane) + hws->funcs.enable_power_gating_plane(dc->hwseq, true); + /* If taking control over from VBIOS, we may want to optimize our first * mode set, so we need to skip powering down pipes until we know which * pipes we want to use. @@ -248,8 +251,6 @@ void dcn31_init_hw(struct dc *dc) REG_UPDATE(DCFCLK_CNTL, DCFCLK_GATE_DIS, 0); } - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); if (!dcb->funcs->is_accelerated_mode(dcb) && dc->res_pool->hubbub->funcs->init_watermarks) dc->res_pool->hubbub->funcs->init_watermarks(dc->res_pool->hubbub); @@ -338,20 +339,20 @@ void dcn31_enable_power_gating_plane( bool enable) { bool force_on = true; /* disable power gating */ + uint32_t org_ip_request_cntl = 0; if (enable && !hws->ctx->dc->debug.disable_hubp_power_gate) force_on = false; + REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); + if (org_ip_request_cntl == 0) + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); /* DCHUBP0/1/2/3/4/5 */ REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); /* DPP0/1/2/3/4/5 */ REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); force_on = true; /* disable power gating */ if (enable && !hws->ctx->dc->debug.disable_dsc_power_gate) @@ -359,11 +360,11 @@ void dcn31_enable_power_gating_plane( /* DCS0/1/2/3/4/5 */ REG_UPDATE(DOMAIN16_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN16_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN17_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN17_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); REG_UPDATE(DOMAIN18_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_WAIT(DOMAIN18_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, force_on, 1, 1000); + + if (org_ip_request_cntl == 0) + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); } void dcn31_update_info_frame(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c index 8afe2130d7c5..e05527a3a8ba 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_optc.c @@ -124,7 +124,6 @@ static bool optc31_enable_crtc(struct timing_generator *optc) static bool optc31_disable_crtc(struct timing_generator *optc) { struct optc *optc1 = DCN10TG_FROM_TG(optc); - /* disable otg request until end of the first line * in the vertical blank region */ @@ -138,6 +137,7 @@ static bool optc31_disable_crtc(struct timing_generator *optc) REG_WAIT(OTG_CLOCK_CONTROL, OTG_BUSY, 0, 1, 100000); + optc1_clear_optc_underflow(optc); return true; } @@ -158,6 +158,9 @@ static bool optc31_immediate_disable_crtc(struct timing_generator *optc) OTG_BUSY, 0, 1, 100000); + /* clear the false state */ + optc1_clear_optc_underflow(optc); + return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index 89b7b6b7254a..63934ecf6be8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -2032,7 +2032,9 @@ bool dcn31_validate_bandwidth(struct dc *dc, BW_VAL_TRACE_COUNT(); + DC_FP_START(); out = dcn30_internal_validate_bw(dc, context, pipes, &pipe_cnt, &vlevel, fast_validate); + DC_FP_END(); // Disable fast_validate to set min dcfclk in alculate_wm_and_dlg if (pipe_cnt == 0) @@ -2232,6 +2234,7 @@ static bool dcn31_resource_construct( dc->caps.extended_aux_timeout_support = true; dc->caps.dmcub_support = true; dc->caps.is_apu = true; + dc->caps.zstate_support = true; /* Color pipeline capabilities */ dc->caps.color.dpp.dcn_arch = 1; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 2f6122153bdb..f93af45aeab4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -722,8 +722,10 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc { int plane_count; int i; + unsigned int optimized_min_dst_y_next_start_us; plane_count = 0; + optimized_min_dst_y_next_start_us = 0; for (i = 0; i < dc->res_pool->pipe_count; i++) { if (context->res_ctx.pipe_ctx[i].plane_state) plane_count++; @@ -744,11 +746,22 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc struct dc_link *link = context->streams[0]->sink->link; struct dc_stream_status *stream_status = &context->stream_status[0]; + if (dc_extended_blank_supported(dc)) { + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (context->res_ctx.pipe_ctx[i].stream == context->streams[0] + && context->res_ctx.pipe_ctx[i].stream->adjust.v_total_min == context->res_ctx.pipe_ctx[i].stream->adjust.v_total_max + && context->res_ctx.pipe_ctx[i].stream->adjust.v_total_min > context->res_ctx.pipe_ctx[i].stream->timing.v_total) { + optimized_min_dst_y_next_start_us = + context->res_ctx.pipe_ctx[i].dlg_regs.optimized_min_dst_y_next_start_us; + break; + } + } + } /* zstate only supported on PWRSEQ0 and when there's <2 planes*/ if (link->link_index != 0 || stream_status->plane_count > 1) return DCN_ZSTATE_SUPPORT_DISALLOW; - if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0) + if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || optimized_min_dst_y_next_start_us > 5000) return DCN_ZSTATE_SUPPORT_ALLOW; else if (link->psr_settings.psr_version == DC_PSR_VERSION_1 && !dc->debug.disable_psr) return DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY; @@ -786,8 +799,6 @@ void dcn20_calculate_dlg_params( != dm_dram_clock_change_unsupported; context->bw_ctx.bw.dcn.clk.dppclk_khz = 0; - context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); - context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context); if (context->bw_ctx.bw.dcn.clk.dispclk_khz < dc->debug.min_disp_clk_khz) @@ -843,6 +854,7 @@ void dcn20_calculate_dlg_params( &pipes[pipe_idx].pipe); pipe_idx++; } + context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context); } static void swizzle_to_dml_params( diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c index e0fecf127bd5..53d760e169e6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c @@ -1055,6 +1055,7 @@ static void dml_rq_dlg_get_dlg_params( float vba__refcyc_per_req_delivery_pre_l = get_refcyc_per_req_delivery_pre_l_in_us(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; // From VBA float vba__refcyc_per_req_delivery_l = get_refcyc_per_req_delivery_l_in_us(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; // From VBA + int blank_lines; memset(disp_dlg_regs, 0, sizeof(*disp_dlg_regs)); memset(disp_ttu_regs, 0, sizeof(*disp_ttu_regs)); @@ -1080,6 +1081,18 @@ static void dml_rq_dlg_get_dlg_params( dlg_vblank_start = interlaced ? (vblank_start / 2) : vblank_start; disp_dlg_regs->min_dst_y_next_start = (unsigned int) (((double) dlg_vblank_start) * dml_pow(2, 2)); + blank_lines = (dst->vblank_end + dst->vtotal_min - dst->vblank_start - dst->vstartup_start - 1); + if (blank_lines < 0) + blank_lines = 0; + if (blank_lines != 0) { + disp_dlg_regs->optimized_min_dst_y_next_start_us = + ((unsigned int) blank_lines * dst->hactive) / (unsigned int) dst->pixel_rate_mhz; + disp_dlg_regs->optimized_min_dst_y_next_start = + (unsigned int)(((double) (dlg_vblank_start + blank_lines)) * dml_pow(2, 2)); + } else { + // use unoptimized value + disp_dlg_regs->optimized_min_dst_y_next_start = disp_dlg_regs->min_dst_y_next_start; + } ASSERT(disp_dlg_regs->min_dst_y_next_start < (unsigned int)dml_pow(2, 18)); dml_print("DML_DLG: %s: min_ttu_vblank (us) = %3.2f\n", __func__, min_ttu_vblank); diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index 59f0a61c33cf..2df660cd8801 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -446,6 +446,8 @@ struct _vcs_dpi_display_dlg_regs_st { unsigned int refcyc_h_blank_end; unsigned int dlg_vblank_end; unsigned int min_dst_y_next_start; + unsigned int optimized_min_dst_y_next_start; + unsigned int optimized_min_dst_y_next_start_us; unsigned int refcyc_per_htotal; unsigned int refcyc_x_after_scaler; unsigned int dst_y_after_scaler; diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c index efc2339f1fa0..4385d19bc489 100644 --- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c +++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c @@ -864,11 +864,11 @@ static bool setup_dsc_config( min_slices_h = inc_num_slices(dsc_common_caps.slice_caps, min_slices_h); } + is_dsc_possible = (min_slices_h <= max_slices_h); + if (pic_width % min_slices_h != 0) min_slices_h = 0; // DSC TODO: Maybe try increasing the number of slices first? - is_dsc_possible = (min_slices_h <= max_slices_h); - if (min_slices_h == 0 && max_slices_h == 0) is_dsc_possible = false; diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h index ab9939db8cea..44f167d2584f 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h @@ -33,6 +33,7 @@ #define MAX_MTP_SLOT_COUNT 64 #define DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE 0x50 #define TRAINING_AUX_RD_INTERVAL 100 //us +#define LINK_AUX_WAKE_TIMEOUT_MS 1500 // Timeout when trying to wake unresponsive DPRX. struct dc_link; struct dc_stream_state; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h index e45b7993c5c5..ad69d78c4ac3 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h @@ -195,6 +195,9 @@ struct hubp_funcs { void (*hubp_set_flip_int)(struct hubp *hubp); + void (*program_extended_blank)(struct hubp *hubp, + unsigned int min_dst_y_next_start_optimized); + void (*hubp_wait_pipe_read_start)(struct hubp *hubp); }; diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c index b691aa45e84f..79bc207415bc 100644 --- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c +++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c @@ -100,7 +100,8 @@ enum vsc_packet_revision { //PB7 = MD0 #define MASK_VTEM_MD0__VRR_EN 0x01 #define MASK_VTEM_MD0__M_CONST 0x02 -#define MASK_VTEM_MD0__RESERVED2 0x0C +#define MASK_VTEM_MD0__QMS_EN 0x04 +#define MASK_VTEM_MD0__RESERVED2 0x08 #define MASK_VTEM_MD0__FVA_FACTOR_M1 0xF0 //MD1 @@ -109,7 +110,7 @@ enum vsc_packet_revision { //MD2 #define MASK_VTEM_MD2__BASE_REFRESH_RATE_98 0x03 #define MASK_VTEM_MD2__RB 0x04 -#define MASK_VTEM_MD2__RESERVED3 0xF8 +#define MASK_VTEM_MD2__NEXT_TFR 0xF8 //MD3 #define MASK_VTEM_MD3__BASE_REFRESH_RATE_07 0xFF diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 89fbee568be4..5504d81c77b7 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -173,6 +173,17 @@ bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev) if (!pp_funcs || !pp_funcs->get_asic_baco_capability) return false; + /* Don't use baco for reset in S3. + * This is a workaround for some platforms + * where entering BACO during suspend + * seems to cause reboots or hangs. + * This might be related to the fact that BACO controls + * power to the whole GPU including devices like audio and USB. + * Powering down/up everything may adversely affect these other + * devices. Needs more investigation. + */ + if (adev->in_s3) + return false; mutex_lock(&adev->pm.mutex); @@ -500,6 +511,9 @@ int amdgpu_dpm_send_hbm_bad_pages_num(struct amdgpu_device *adev, uint32_t size) struct smu_context *smu = adev->powerplay.pp_handle; int ret = 0; + if (!is_support_sw_smu(adev)) + return -EOPNOTSUPP; + mutex_lock(&adev->pm.mutex); ret = smu_send_hbm_bad_pages_num(smu, size); mutex_unlock(&adev->pm.mutex); @@ -512,6 +526,9 @@ int amdgpu_dpm_send_hbm_bad_channel_flag(struct amdgpu_device *adev, uint32_t si struct smu_context *smu = adev->powerplay.pp_handle; int ret = 0; + if (!is_support_sw_smu(adev)) + return -EOPNOTSUPP; + mutex_lock(&adev->pm.mutex); ret = smu_send_hbm_bad_channel_flag(smu, size); mutex_unlock(&adev->pm.mutex); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index 9ddd8491ff00..ede71de2343d 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -773,13 +773,13 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinFclkByFreq, hwmgr->display_config->num_display > 3 ? - data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk : + (data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk / 100) : min_mclk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinSocclkByFreq, - data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk, + data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinVcn, @@ -792,11 +792,11 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxFclkByFreq, - data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk, + data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxSocclkByFreq, - data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk, + data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk / 100, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxVcn, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c index 7bfac029e513..b81711c4ff33 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c @@ -991,7 +991,7 @@ static int smu_v13_0_5_set_performance_level(struct smu_context *smu, return -EINVAL; } - if (sclk_min && sclk_max) { + if (sclk_min && sclk_max && smu_v13_0_5_clk_dpm_is_enabled(smu, SMU_SCLK)) { ret = smu_v13_0_5_set_soft_freq_limited_range(smu, SMU_SCLK, sclk_min, diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_plane.c b/drivers/gpu/drm/arm/display/komeda/komeda_plane.c index d63d83800a8a..e0b9f7063b20 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_plane.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_plane.c @@ -135,7 +135,6 @@ static void komeda_plane_destroy(struct drm_plane *plane) static void komeda_plane_reset(struct drm_plane *plane) { struct komeda_plane_state *state; - struct komeda_plane *kplane = to_kplane(plane); if (plane->state) __drm_atomic_helper_plane_destroy_state(plane->state); @@ -144,16 +143,8 @@ static void komeda_plane_reset(struct drm_plane *plane) plane->state = NULL; state = kzalloc(sizeof(*state), GFP_KERNEL); - if (state) { - state->base.rotation = DRM_MODE_ROTATE_0; - state->base.pixel_blend_mode = DRM_MODE_BLEND_PREMULTI; - state->base.alpha = DRM_BLEND_ALPHA_OPAQUE; - state->base.zpos = kplane->layer->base.id; - state->base.color_encoding = DRM_COLOR_YCBCR_BT601; - state->base.color_range = DRM_COLOR_YCBCR_LIMITED_RANGE; - plane->state = &state->base; - plane->state->plane = plane; - } + if (state) + __drm_atomic_helper_plane_reset(plane, &state->base); } static struct drm_plane_state * @@ -265,6 +256,10 @@ static int komeda_plane_add(struct komeda_kms_dev *kms, formats = komeda_get_layer_fourcc_list(&mdev->fmt_tbl, layer->layer_type, &n_formats); + if (!formats) { + kfree(kplane); + return -ENOMEM; + } err = drm_universal_plane_init(&kms->base, plane, get_possible_crtcs(kms, c->pipeline), @@ -275,8 +270,10 @@ static int komeda_plane_add(struct komeda_kms_dev *kms, komeda_put_fourcc_list(formats); - if (err) - goto cleanup; + if (err) { + kfree(kplane); + return err; + } drm_plane_helper_add(plane, &komeda_plane_helper_funcs); diff --git a/drivers/gpu/drm/arm/malidp_crtc.c b/drivers/gpu/drm/arm/malidp_crtc.c index 494075ddbef6..b5928b52e279 100644 --- a/drivers/gpu/drm/arm/malidp_crtc.c +++ b/drivers/gpu/drm/arm/malidp_crtc.c @@ -487,7 +487,10 @@ static void malidp_crtc_reset(struct drm_crtc *crtc) if (crtc->state) malidp_crtc_destroy_state(crtc, crtc->state); - __drm_atomic_helper_crtc_reset(crtc, &state->base); + if (state) + __drm_atomic_helper_crtc_reset(crtc, &state->base); + else + __drm_atomic_helper_crtc_reset(crtc, NULL); } static int malidp_crtc_enable_vblank(struct drm_crtc *crtc) diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c index 0562bdaac00c..81d9f5004025 100644 --- a/drivers/gpu/drm/arm/malidp_planes.c +++ b/drivers/gpu/drm/arm/malidp_planes.c @@ -310,17 +310,13 @@ static int malidp_se_check_scaling(struct malidp_plane *mp, static u32 malidp_get_pgsize_bitmap(struct malidp_plane *mp) { - u32 pgsize_bitmap = 0; + struct iommu_domain *mmu_dom; - if (iommu_present(&platform_bus_type)) { - struct iommu_domain *mmu_dom = - iommu_get_domain_for_dev(mp->base.dev->dev); + mmu_dom = iommu_get_domain_for_dev(mp->base.dev->dev); + if (mmu_dom) + return mmu_dom->pgsize_bitmap; - if (mmu_dom) - pgsize_bitmap = mmu_dom->pgsize_bitmap; - } - - return pgsize_bitmap; + return 0; } /* diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index 007e5a282f67..c08ccb4b332b 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -32,6 +32,7 @@ config DRM_CHIPONE_ICN6211 select DRM_KMS_HELPER select DRM_MIPI_DSI select DRM_PANEL_BRIDGE + select REGMAP_I2C help ICN6211 is MIPI-DSI/RGB Converter bridge from chipone. @@ -77,6 +78,7 @@ config DRM_DISPLAY_CONNECTOR config DRM_ITE_IT6505 tristate "ITE IT6505 DisplayPort bridge" depends on OF + select DRM_DP_HELPER select DRM_KMS_HELPER select EXTCON help @@ -98,6 +100,19 @@ config DRM_LONTIUM_LT8912B Say M here if you want to support this hardware as a module. The module will be named "lontium-lt8912b". +config DRM_LONTIUM_LT9211 + tristate "Lontium LT9211 DSI/LVDS/DPI bridge" + depends on OF + select DRM_PANEL_BRIDGE + select DRM_KMS_HELPER + select DRM_MIPI_DSI + select REGMAP_I2C + help + Driver for Lontium LT9211 Single/Dual-Link DSI/LVDS or Single DPI + input to Single-link/Dual-Link DSI/LVDS or Single DPI output bridge + chip. + Please say Y if you have such hardware. + config DRM_LONTIUM_LT9611 tristate "Lontium LT9611 DSI/HDMI bridge" select SND_SOC_HDMI_CODEC if SND_SOC @@ -265,6 +280,7 @@ config DRM_TOSHIBA_TC358767 select DRM_DP_HELPER select DRM_KMS_HELPER select REGMAP_I2C + select DRM_MIPI_DSI select DRM_PANEL help Toshiba TC358767 eDP bridge chip driver. diff --git a/drivers/gpu/drm/bridge/Makefile b/drivers/gpu/drm/bridge/Makefile index 425844c30495..b0edf2022fa0 100644 --- a/drivers/gpu/drm/bridge/Makefile +++ b/drivers/gpu/drm/bridge/Makefile @@ -6,6 +6,7 @@ obj-$(CONFIG_DRM_CROS_EC_ANX7688) += cros-ec-anx7688.o obj-$(CONFIG_DRM_DISPLAY_CONNECTOR) += display-connector.o obj-$(CONFIG_DRM_ITE_IT6505) += ite-it6505.o obj-$(CONFIG_DRM_LONTIUM_LT8912B) += lontium-lt8912b.o +obj-$(CONFIG_DRM_LONTIUM_LT9211) += lontium-lt9211.o obj-$(CONFIG_DRM_LONTIUM_LT9611) += lontium-lt9611.o obj-$(CONFIG_DRM_LONTIUM_LT9611UXC) += lontium-lt9611uxc.o obj-$(CONFIG_DRM_LVDS_CODEC) += lvds-codec.o diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 005bf18682ff..b3f10c54e064 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -1292,8 +1292,10 @@ static int adv7511_probe(struct i2c_client *i2c, const struct i2c_device_id *id) goto err_unregister_cec; adv7511->bridge.funcs = &adv7511_bridge_funcs; - adv7511->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID - | DRM_BRIDGE_OP_HPD; + adv7511->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID; + if (adv7511->i2c_main->irq) + adv7511->bridge.ops |= DRM_BRIDGE_OP_HPD; + adv7511->bridge.of_node = dev->of_node; adv7511->bridge.type = DRM_MODE_CONNECTOR_HDMIA; @@ -1313,6 +1315,7 @@ err_unregister_audio: adv7511_audio_exit(adv7511); drm_bridge_remove(&adv7511->bridge); err_unregister_cec: + cec_unregister_adapter(adv7511->cec_adap); i2c_unregister_device(adv7511->i2c_cec); clk_disable_unprepare(adv7511->cec_clk); err_i2c_unregister_packet: diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c index eb590fb8e8d0..c5afccd46440 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c @@ -1119,9 +1119,7 @@ static int analogix_dp_get_modes(struct drm_connector *connector) return 0; } - pm_runtime_get_sync(dp->dev); edid = drm_get_edid(connector, &dp->aux.ddc); - pm_runtime_put(dp->dev); if (edid) { drm_connector_update_edid_property(&dp->connector, edid); @@ -1632,8 +1630,20 @@ static ssize_t analogix_dpaux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) { struct analogix_dp_device *dp = to_dp(aux); + int ret; + + pm_runtime_get_sync(dp->dev); + + ret = analogix_dp_detect_hpd(dp); + if (ret) + goto out; - return analogix_dp_transfer(dp, msg); + ret = analogix_dp_transfer(dp, msg); +out: + pm_runtime_mark_last_busy(dp->dev); + pm_runtime_put_autosuspend(dp->dev); + + return ret; } struct analogix_dp_device * @@ -1764,6 +1774,8 @@ int analogix_dp_bind(struct analogix_dp_device *dp, struct drm_device *drm_dev) if (ret) return ret; + pm_runtime_use_autosuspend(dp->dev); + pm_runtime_set_autosuspend_delay(dp->dev, 100); pm_runtime_enable(dp->dev); ret = analogix_dp_create_bridge(drm_dev, dp); @@ -1775,6 +1787,7 @@ int analogix_dp_bind(struct analogix_dp_device *dp, struct drm_device *drm_dev) return 0; err_disable_pm_runtime: + pm_runtime_dont_use_autosuspend(dp->dev); pm_runtime_disable(dp->dev); drm_dp_aux_unregister(&dp->aux); @@ -1793,6 +1806,7 @@ void analogix_dp_unbind(struct analogix_dp_device *dp) } drm_dp_aux_unregister(&dp->aux); + pm_runtime_dont_use_autosuspend(dp->dev); pm_runtime_disable(dp->dev); } EXPORT_SYMBOL_GPL(analogix_dp_unbind); diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c index 31ecf5626f1d..376da01243a3 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.c +++ b/drivers/gpu/drm/bridge/analogix/anx7625.c @@ -874,7 +874,10 @@ static int anx7625_hdcp_enable(struct anx7625_data *ctx) } /* Read downstream capability */ - anx7625_aux_trans(ctx, DP_AUX_NATIVE_READ, 0x68028, 1, &bcap); + ret = anx7625_aux_trans(ctx, DP_AUX_NATIVE_READ, 0x68028, 1, &bcap); + if (ret < 0) + return ret; + if (!(bcap & 0x01)) { pr_warn("downstream not support HDCP 1.4, cap(%x).\n", bcap); return 0; @@ -921,12 +924,20 @@ static void anx7625_dp_start(struct anx7625_data *ctx) { int ret; struct device *dev = &ctx->client->dev; + u8 data; if (!ctx->display_timing_valid) { DRM_DEV_ERROR(dev, "mipi not set display timing yet.\n"); return; } + dev_dbg(dev, "set downstream sink into normal\n"); + /* Downstream sink enter into normal mode */ + data = 1; + ret = anx7625_aux_trans(ctx, DP_AUX_NATIVE_WRITE, 0x000600, 1, &data); + if (ret < 0) + dev_err(dev, "IO error : set sink into normal mode fail\n"); + /* Disable HDCP */ anx7625_write_and(ctx, ctx->i2c.rx_p1_client, 0xee, 0x9f); @@ -1475,12 +1486,12 @@ static void anx7625_dp_adjust_swing(struct anx7625_data *ctx) for (i = 0; i < ctx->pdata.dp_lane0_swing_reg_cnt; i++) anx7625_reg_write(ctx, ctx->i2c.tx_p1_client, DP_TX_LANE0_SWING_REG0 + i, - ctx->pdata.lane0_reg_data[i] & 0xFF); + ctx->pdata.lane0_reg_data[i]); for (i = 0; i < ctx->pdata.dp_lane1_swing_reg_cnt; i++) anx7625_reg_write(ctx, ctx->i2c.tx_p1_client, DP_TX_LANE1_SWING_REG0 + i, - ctx->pdata.lane1_reg_data[i] & 0xFF); + ctx->pdata.lane1_reg_data[i]); } static void dp_hpd_change_handler(struct anx7625_data *ctx, bool on) @@ -1587,8 +1598,8 @@ static int anx7625_get_swing_setting(struct device *dev, num_regs = DP_TX_SWING_REG_CNT; pdata->dp_lane0_swing_reg_cnt = num_regs; - of_property_read_u32_array(dev->of_node, "analogix,lane0-swing", - pdata->lane0_reg_data, num_regs); + of_property_read_u8_array(dev->of_node, "analogix,lane0-swing", + pdata->lane0_reg_data, num_regs); } if (of_get_property(dev->of_node, @@ -1597,8 +1608,8 @@ static int anx7625_get_swing_setting(struct device *dev, num_regs = DP_TX_SWING_REG_CNT; pdata->dp_lane1_swing_reg_cnt = num_regs; - of_property_read_u32_array(dev->of_node, "analogix,lane1-swing", - pdata->lane1_reg_data, num_regs); + of_property_read_u8_array(dev->of_node, "analogix,lane1-swing", + pdata->lane1_reg_data, num_regs); } return 0; @@ -1608,8 +1619,6 @@ static int anx7625_parse_dt(struct device *dev, struct anx7625_platform_data *pdata) { struct device_node *np = dev->of_node, *ep0; - struct drm_panel *panel; - int ret; int bus_type, mipi_lanes; anx7625_get_swing_setting(dev, pdata); @@ -1646,18 +1655,14 @@ static int anx7625_parse_dt(struct device *dev, if (of_property_read_bool(np, "analogix,audio-enable")) pdata->audio_en = 1; - ret = drm_of_find_panel_or_bridge(np, 1, 0, &panel, NULL); - if (ret < 0) { - if (ret == -ENODEV) + pdata->panel_bridge = devm_drm_of_get_bridge(dev, np, 1, 0); + if (IS_ERR(pdata->panel_bridge)) { + if (PTR_ERR(pdata->panel_bridge) == -ENODEV) return 0; - return ret; - } - if (!panel) - return -ENODEV; - pdata->panel_bridge = devm_drm_panel_bridge_add(dev, panel); - if (IS_ERR(pdata->panel_bridge)) return PTR_ERR(pdata->panel_bridge); + } + DRM_DEV_DEBUG_DRIVER(dev, "get panel node.\n"); return 0; @@ -1927,14 +1932,14 @@ static int anx7625_audio_get_eld(struct device *dev, void *data, struct anx7625_data *ctx = dev_get_drvdata(dev); if (!ctx->connector) { - dev_err(dev, "connector not initial\n"); - return -EINVAL; + /* Pass en empty ELD if connector not available */ + memset(buf, 0, len); + } else { + dev_dbg(dev, "audio copy eld\n"); + memcpy(buf, ctx->connector->eld, + min(sizeof(ctx->connector->eld), len)); } - dev_dbg(dev, "audio copy eld\n"); - memcpy(buf, ctx->connector->eld, - min(sizeof(ctx->connector->eld), len)); - return 0; } @@ -2011,7 +2016,8 @@ static int anx7625_attach_dsi(struct anx7625_data *ctx) dsi->format = MIPI_DSI_FMT_RGB888; dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE | - MIPI_DSI_MODE_VIDEO_HSE; + MIPI_DSI_MODE_VIDEO_HSE | + MIPI_DSI_HS_PKT_END_ALIGNED; ret = devm_mipi_dsi_attach(dev, dsi); if (ret) { @@ -2654,7 +2660,7 @@ static int anx7625_i2c_probe(struct i2c_client *client, if (ret) { if (ret != -EPROBE_DEFER) DRM_DEV_ERROR(dev, "fail to parse DT : %d\n", ret); - return ret; + goto free_wq; } if (anx7625_register_i2c_dummy_clients(platform, client) != 0) { @@ -2669,7 +2675,7 @@ static int anx7625_i2c_probe(struct i2c_client *client, pm_suspend_ignore_children(dev, true); ret = devm_add_action_or_reset(dev, anx7625_runtime_disable, dev); if (ret) - return ret; + goto free_wq; if (!platform->pdata.low_power_mode) { anx7625_disable_pd_protocol(platform); diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.h b/drivers/gpu/drm/bridge/analogix/anx7625.h index edbbfe410a56..e257a84db962 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.h +++ b/drivers/gpu/drm/bridge/analogix/anx7625.h @@ -426,9 +426,9 @@ struct anx7625_platform_data { int mipi_lanes; int audio_en; int dp_lane0_swing_reg_cnt; - int lane0_reg_data[DP_TX_SWING_REG_CNT]; + u8 lane0_reg_data[DP_TX_SWING_REG_CNT]; int dp_lane1_swing_reg_cnt; - int lane1_reg_data[DP_TX_SWING_REG_CNT]; + u8 lane1_reg_data[DP_TX_SWING_REG_CNT]; u32 low_power_mode; struct device_node *mipi_host_node; }; diff --git a/drivers/gpu/drm/bridge/chipone-icn6211.c b/drivers/gpu/drm/bridge/chipone-icn6211.c index d9b7f48b99fb..47dea657a752 100644 --- a/drivers/gpu/drm/bridge/chipone-icn6211.c +++ b/drivers/gpu/drm/bridge/chipone-icn6211.c @@ -11,12 +11,25 @@ #include <linux/delay.h> #include <linux/gpio/consumer.h> +#include <linux/i2c.h> #include <linux/module.h> #include <linux/of_device.h> +#include <linux/regmap.h> #include <linux/regulator/consumer.h> -#include <video/mipi_display.h> - +#define VENDOR_ID 0x00 +#define DEVICE_ID_H 0x01 +#define DEVICE_ID_L 0x02 +#define VERSION_ID 0x03 +#define FIRMWARE_VERSION 0x08 +#define CONFIG_FINISH 0x09 +#define PD_CTRL(n) (0x0a + ((n) & 0x3)) /* 0..3 */ +#define RST_CTRL(n) (0x0e + ((n) & 0x1)) /* 0..1 */ +#define SYS_CTRL(n) (0x10 + ((n) & 0x7)) /* 0..4 */ +#define RGB_DRV(n) (0x18 + ((n) & 0x3)) /* 0..3 */ +#define RGB_DLY(n) (0x1c + ((n) & 0x1)) /* 0..1 */ +#define RGB_TEST_CTRL 0x1e +#define ATE_PLL_EN 0x1f #define HACTIVE_LI 0x20 #define VACTIVE_LI 0x21 #define VACTIVE_HACTIVE_HI 0x22 @@ -24,19 +37,186 @@ #define HSYNC_LI 0x24 #define HBP_LI 0x25 #define HFP_HSW_HBP_HI 0x26 +#define HFP_HSW_HBP_HI_HFP(n) (((n) & 0x300) >> 4) +#define HFP_HSW_HBP_HI_HS(n) (((n) & 0x300) >> 6) +#define HFP_HSW_HBP_HI_HBP(n) (((n) & 0x300) >> 8) #define VFP 0x27 #define VSYNC 0x28 #define VBP 0x29 +#define BIST_POL 0x2a +#define BIST_POL_BIST_MODE(n) (((n) & 0xf) << 4) +#define BIST_POL_BIST_GEN BIT(3) +#define BIST_POL_HSYNC_POL BIT(2) +#define BIST_POL_VSYNC_POL BIT(1) +#define BIST_POL_DE_POL BIT(0) +#define BIST_RED 0x2b +#define BIST_GREEN 0x2c +#define BIST_BLUE 0x2d +#define BIST_CHESS_X 0x2e +#define BIST_CHESS_Y 0x2f +#define BIST_CHESS_XY_H 0x30 +#define BIST_FRAME_TIME_L 0x31 +#define BIST_FRAME_TIME_H 0x32 +#define FIFO_MAX_ADDR_LOW 0x33 +#define SYNC_EVENT_DLY 0x34 +#define HSW_MIN 0x35 +#define HFP_MIN 0x36 +#define LOGIC_RST_NUM 0x37 +#define OSC_CTRL(n) (0x48 + ((n) & 0x7)) /* 0..5 */ +#define BG_CTRL 0x4e +#define LDO_PLL 0x4f +#define PLL_CTRL(n) (0x50 + ((n) & 0xf)) /* 0..15 */ +#define PLL_CTRL_6_EXTERNAL 0x90 +#define PLL_CTRL_6_MIPI_CLK 0x92 +#define PLL_CTRL_6_INTERNAL 0x93 +#define PLL_REM(n) (0x60 + ((n) & 0x3)) /* 0..2 */ +#define PLL_DIV(n) (0x63 + ((n) & 0x3)) /* 0..2 */ +#define PLL_FRAC(n) (0x66 + ((n) & 0x3)) /* 0..2 */ +#define PLL_INT(n) (0x69 + ((n) & 0x1)) /* 0..1 */ +#define PLL_REF_DIV 0x6b +#define PLL_REF_DIV_P(n) ((n) & 0xf) +#define PLL_REF_DIV_Pe BIT(4) +#define PLL_REF_DIV_S(n) (((n) & 0x7) << 5) +#define PLL_SSC_P(n) (0x6c + ((n) & 0x3)) /* 0..2 */ +#define PLL_SSC_STEP(n) (0x6f + ((n) & 0x3)) /* 0..2 */ +#define PLL_SSC_OFFSET(n) (0x72 + ((n) & 0x3)) /* 0..3 */ +#define GPIO_OEN 0x79 +#define MIPI_CFG_PW 0x7a +#define MIPI_CFG_PW_CONFIG_DSI 0xc1 +#define MIPI_CFG_PW_CONFIG_I2C 0x3e +#define GPIO_SEL(n) (0x7b + ((n) & 0x1)) /* 0..1 */ +#define IRQ_SEL 0x7d +#define DBG_SEL 0x7e +#define DBG_SIGNAL 0x7f +#define MIPI_ERR_VECTOR_L 0x80 +#define MIPI_ERR_VECTOR_H 0x81 +#define MIPI_ERR_VECTOR_EN_L 0x82 +#define MIPI_ERR_VECTOR_EN_H 0x83 +#define MIPI_MAX_SIZE_L 0x84 +#define MIPI_MAX_SIZE_H 0x85 +#define DSI_CTRL 0x86 +#define DSI_CTRL_UNKNOWN 0x28 +#define DSI_CTRL_DSI_LANES(n) ((n) & 0x3) +#define MIPI_PN_SWAP 0x87 +#define MIPI_PN_SWAP_CLK BIT(4) +#define MIPI_PN_SWAP_D(n) BIT((n) & 0x3) +#define MIPI_SOT_SYNC_BIT_(n) (0x88 + ((n) & 0x1)) /* 0..1 */ +#define MIPI_ULPS_CTRL 0x8a +#define MIPI_CLK_CHK_VAR 0x8e +#define MIPI_CLK_CHK_INI 0x8f +#define MIPI_T_TERM_EN 0x90 +#define MIPI_T_HS_SETTLE 0x91 +#define MIPI_T_TA_SURE_PRE 0x92 +#define MIPI_T_LPX_SET 0x94 +#define MIPI_T_CLK_MISS 0x95 +#define MIPI_INIT_TIME_L 0x96 +#define MIPI_INIT_TIME_H 0x97 +#define MIPI_T_CLK_TERM_EN 0x99 +#define MIPI_T_CLK_SETTLE 0x9a +#define MIPI_TO_HS_RX_L 0x9e +#define MIPI_TO_HS_RX_H 0x9f +#define MIPI_PHY_(n) (0xa0 + ((n) & 0x7)) /* 0..5 */ +#define MIPI_PD_RX 0xb0 +#define MIPI_PD_TERM 0xb1 +#define MIPI_PD_HSRX 0xb2 +#define MIPI_PD_LPTX 0xb3 +#define MIPI_PD_LPRX 0xb4 +#define MIPI_PD_CK_LANE 0xb5 +#define MIPI_FORCE_0 0xb6 +#define MIPI_RST_CTRL 0xb7 +#define MIPI_RST_NUM 0xb8 +#define MIPI_DBG_SET_(n) (0xc0 + ((n) & 0xf)) /* 0..9 */ +#define MIPI_DBG_SEL 0xe0 +#define MIPI_DBG_DATA 0xe1 +#define MIPI_ATE_TEST_SEL 0xe2 +#define MIPI_ATE_STATUS_(n) (0xe3 + ((n) & 0x1)) /* 0..1 */ +#define MIPI_ATE_STATUS_1 0xe4 +#define ICN6211_MAX_REGISTER MIPI_ATE_STATUS(1) struct chipone { struct device *dev; + struct regmap *regmap; + struct i2c_client *client; struct drm_bridge bridge; struct drm_display_mode mode; struct drm_bridge *panel_bridge; + struct mipi_dsi_device *dsi; struct gpio_desc *enable_gpio; struct regulator *vdd1; struct regulator *vdd2; struct regulator *vdd3; + bool interface_i2c; +}; + +static const struct regmap_range chipone_dsi_readable_ranges[] = { + regmap_reg_range(VENDOR_ID, VERSION_ID), + regmap_reg_range(FIRMWARE_VERSION, PLL_SSC_OFFSET(3)), + regmap_reg_range(GPIO_OEN, MIPI_ULPS_CTRL), + regmap_reg_range(MIPI_CLK_CHK_VAR, MIPI_T_TA_SURE_PRE), + regmap_reg_range(MIPI_T_LPX_SET, MIPI_INIT_TIME_H), + regmap_reg_range(MIPI_T_CLK_TERM_EN, MIPI_T_CLK_SETTLE), + regmap_reg_range(MIPI_TO_HS_RX_L, MIPI_PHY_(5)), + regmap_reg_range(MIPI_PD_RX, MIPI_RST_NUM), + regmap_reg_range(MIPI_DBG_SET_(0), MIPI_DBG_SET_(9)), + regmap_reg_range(MIPI_DBG_SEL, MIPI_ATE_STATUS_(1)), +}; + +static const struct regmap_access_table chipone_dsi_readable_table = { + .yes_ranges = chipone_dsi_readable_ranges, + .n_yes_ranges = ARRAY_SIZE(chipone_dsi_readable_ranges), +}; + +static const struct regmap_range chipone_dsi_writeable_ranges[] = { + regmap_reg_range(CONFIG_FINISH, PLL_SSC_OFFSET(3)), + regmap_reg_range(GPIO_OEN, MIPI_ULPS_CTRL), + regmap_reg_range(MIPI_CLK_CHK_VAR, MIPI_T_TA_SURE_PRE), + regmap_reg_range(MIPI_T_LPX_SET, MIPI_INIT_TIME_H), + regmap_reg_range(MIPI_T_CLK_TERM_EN, MIPI_T_CLK_SETTLE), + regmap_reg_range(MIPI_TO_HS_RX_L, MIPI_PHY_(5)), + regmap_reg_range(MIPI_PD_RX, MIPI_RST_NUM), + regmap_reg_range(MIPI_DBG_SET_(0), MIPI_DBG_SET_(9)), + regmap_reg_range(MIPI_DBG_SEL, MIPI_ATE_STATUS_(1)), +}; + +static const struct regmap_access_table chipone_dsi_writeable_table = { + .yes_ranges = chipone_dsi_writeable_ranges, + .n_yes_ranges = ARRAY_SIZE(chipone_dsi_writeable_ranges), +}; + +static const struct regmap_config chipone_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .rd_table = &chipone_dsi_readable_table, + .wr_table = &chipone_dsi_writeable_table, + .cache_type = REGCACHE_RBTREE, + .max_register = MIPI_ATE_STATUS_(1), +}; + +static int chipone_dsi_read(void *context, + const void *reg, size_t reg_size, + void *val, size_t val_size) +{ + struct mipi_dsi_device *dsi = context; + const u16 reg16 = (val_size << 8) | *(u8 *)reg; + int ret; + + ret = mipi_dsi_generic_read(dsi, ®16, 2, val, val_size); + + return ret == val_size ? 0 : -EINVAL; +} + +static int chipone_dsi_write(void *context, const void *data, size_t count) +{ + struct mipi_dsi_device *dsi = context; + + return mipi_dsi_generic_write(dsi, data, 2); +} + +static const struct regmap_bus chipone_dsi_regmap_bus = { + .read = chipone_dsi_read, + .write = chipone_dsi_write, + .reg_format_endian_default = REGMAP_ENDIAN_NATIVE, + .val_format_endian_default = REGMAP_ENDIAN_NATIVE, }; static inline struct chipone *bridge_to_chipone(struct drm_bridge *bridge) @@ -44,70 +224,202 @@ static inline struct chipone *bridge_to_chipone(struct drm_bridge *bridge) return container_of(bridge, struct chipone, bridge); } -static inline int chipone_dsi_write(struct chipone *icn, const void *seq, - size_t len) +static void chipone_readb(struct chipone *icn, u8 reg, u8 *val) { - struct mipi_dsi_device *dsi = to_mipi_dsi_device(icn->dev); + int ret, pval; + + ret = regmap_read(icn->regmap, reg, &pval); - return mipi_dsi_generic_write(dsi, seq, len); + *val = ret ? 0 : pval & 0xff; } -#define ICN6211_DSI(icn, seq...) \ - { \ - const u8 d[] = { seq }; \ - chipone_dsi_write(icn, d, ARRAY_SIZE(d)); \ +static int chipone_writeb(struct chipone *icn, u8 reg, u8 val) +{ + return regmap_write(icn->regmap, reg, val); +} + +static void chipone_configure_pll(struct chipone *icn, + const struct drm_display_mode *mode) +{ + unsigned int best_p = 0, best_m = 0, best_s = 0; + unsigned int mode_clock = mode->clock * 1000; + unsigned int delta, min_delta = 0xffffffff; + unsigned int freq_p, freq_s, freq_out; + unsigned int p_min, p_max; + unsigned int p, m, s; + unsigned int fin; + bool best_p_pot; + u8 ref_div; + + /* + * DSI byte clock frequency (input into PLL) is calculated as: + * DSI_CLK = mode clock * bpp / dsi_data_lanes / 8 + * + * DPI pixel clock frequency (output from PLL) is mode clock. + * + * The chip contains fractional PLL which works as follows: + * DPI_CLK = ((DSI_CLK / P) * M) / S + * P is pre-divider, register PLL_REF_DIV[3:0] is 1:n divider + * register PLL_REF_DIV[4] is extra 1:2 divider + * M is integer multiplier, register PLL_INT(0) is multiplier + * S is post-divider, register PLL_REF_DIV[7:5] is 2^(n+1) divider + * + * It seems the PLL input clock after applying P pre-divider have + * to be lower than 20 MHz. + */ + fin = mode_clock * mipi_dsi_pixel_format_to_bpp(icn->dsi->format) / + icn->dsi->lanes / 8; /* in Hz */ + + /* Minimum value of P predivider for PLL input in 5..20 MHz */ + p_min = clamp(DIV_ROUND_UP(fin, 20000000), 1U, 31U); + p_max = clamp(fin / 5000000, 1U, 31U); + + for (p = p_min; p < p_max; p++) { /* PLL_REF_DIV[4,3:0] */ + if (p > 16 && p & 1) /* P > 16 uses extra /2 */ + continue; + freq_p = fin / p; + if (freq_p == 0) /* Divider too high */ + break; + + for (s = 0; s < 0x7; s++) { /* PLL_REF_DIV[7:5] */ + freq_s = freq_p / BIT(s + 1); + if (freq_s == 0) /* Divider too high */ + break; + + m = mode_clock / freq_s; + + /* Multiplier is 8 bit */ + if (m > 0xff) + continue; + + /* Limit PLL VCO frequency to 1 GHz */ + freq_out = (fin * m) / p; + if (freq_out > 1000000000) + continue; + + /* Apply post-divider */ + freq_out /= BIT(s + 1); + + delta = abs(mode_clock - freq_out); + if (delta < min_delta) { + best_p = p; + best_m = m; + best_s = s; + min_delta = delta; + } + } } + best_p_pot = !(best_p & 1); + + dev_dbg(icn->dev, + "PLL: P[3:0]=%d P[4]=2*%d M=%d S[7:5]=2^%d delta=%d => DSI f_in=%d Hz ; DPI f_out=%d Hz\n", + best_p >> best_p_pot, best_p_pot, best_m, best_s + 1, + min_delta, fin, (fin * best_m) / (best_p << (best_s + 1))); + + ref_div = PLL_REF_DIV_P(best_p >> best_p_pot) | PLL_REF_DIV_S(best_s); + if (best_p_pot) /* Prefer /2 pre-divider */ + ref_div |= PLL_REF_DIV_Pe; + + /* Clock source selection fixed to MIPI DSI clock lane */ + chipone_writeb(icn, PLL_CTRL(6), PLL_CTRL_6_MIPI_CLK); + chipone_writeb(icn, PLL_REF_DIV, ref_div); + chipone_writeb(icn, PLL_INT(0), best_m); +} + static void chipone_atomic_enable(struct drm_bridge *bridge, struct drm_bridge_state *old_bridge_state) { struct chipone *icn = bridge_to_chipone(bridge); + struct drm_atomic_state *state = old_bridge_state->base.state; struct drm_display_mode *mode = &icn->mode; + const struct drm_bridge_state *bridge_state; + u16 hfp, hbp, hsync; + u32 bus_flags; + u8 pol, id[4]; + + chipone_readb(icn, VENDOR_ID, id); + chipone_readb(icn, DEVICE_ID_H, id + 1); + chipone_readb(icn, DEVICE_ID_L, id + 2); + chipone_readb(icn, VERSION_ID, id + 3); + + dev_dbg(icn->dev, + "Chip IDs: Vendor=0x%02x Device=0x%02x:0x%02x Version=0x%02x\n", + id[0], id[1], id[2], id[3]); + + if (id[0] != 0xc1 || id[1] != 0x62 || id[2] != 0x11) { + dev_dbg(icn->dev, "Invalid Chip IDs, aborting configuration\n"); + return; + } - ICN6211_DSI(icn, 0x7a, 0xc1); + /* Get the DPI flags from the bridge state. */ + bridge_state = drm_atomic_get_new_bridge_state(state, bridge); + bus_flags = bridge_state->output_bus_cfg.flags; - ICN6211_DSI(icn, HACTIVE_LI, mode->hdisplay & 0xff); + if (icn->interface_i2c) + chipone_writeb(icn, MIPI_CFG_PW, MIPI_CFG_PW_CONFIG_I2C); + else + chipone_writeb(icn, MIPI_CFG_PW, MIPI_CFG_PW_CONFIG_DSI); - ICN6211_DSI(icn, VACTIVE_LI, mode->vdisplay & 0xff); + chipone_writeb(icn, HACTIVE_LI, mode->hdisplay & 0xff); - /** + chipone_writeb(icn, VACTIVE_LI, mode->vdisplay & 0xff); + + /* * lsb nibble: 2nd nibble of hdisplay * msb nibble: 2nd nibble of vdisplay */ - ICN6211_DSI(icn, VACTIVE_HACTIVE_HI, - ((mode->hdisplay >> 8) & 0xf) | - (((mode->vdisplay >> 8) & 0xf) << 4)); + chipone_writeb(icn, VACTIVE_HACTIVE_HI, + ((mode->hdisplay >> 8) & 0xf) | + (((mode->vdisplay >> 8) & 0xf) << 4)); + + hfp = mode->hsync_start - mode->hdisplay; + hsync = mode->hsync_end - mode->hsync_start; + hbp = mode->htotal - mode->hsync_end; - ICN6211_DSI(icn, HFP_LI, mode->hsync_start - mode->hdisplay); + chipone_writeb(icn, HFP_LI, hfp & 0xff); + chipone_writeb(icn, HSYNC_LI, hsync & 0xff); + chipone_writeb(icn, HBP_LI, hbp & 0xff); + /* Top two bits of Horizontal Front porch/Sync/Back porch */ + chipone_writeb(icn, HFP_HSW_HBP_HI, + HFP_HSW_HBP_HI_HFP(hfp) | + HFP_HSW_HBP_HI_HS(hsync) | + HFP_HSW_HBP_HI_HBP(hbp)); - ICN6211_DSI(icn, HSYNC_LI, mode->hsync_end - mode->hsync_start); + chipone_writeb(icn, VFP, mode->vsync_start - mode->vdisplay); - ICN6211_DSI(icn, HBP_LI, mode->htotal - mode->hsync_end); + chipone_writeb(icn, VSYNC, mode->vsync_end - mode->vsync_start); - ICN6211_DSI(icn, HFP_HSW_HBP_HI, 0x00); + chipone_writeb(icn, VBP, mode->vtotal - mode->vsync_end); - ICN6211_DSI(icn, VFP, mode->vsync_start - mode->vdisplay); + /* dsi specific sequence */ + chipone_writeb(icn, SYNC_EVENT_DLY, 0x80); + chipone_writeb(icn, HFP_MIN, hfp & 0xff); - ICN6211_DSI(icn, VSYNC, mode->vsync_end - mode->vsync_start); + /* DSI data lane count */ + chipone_writeb(icn, DSI_CTRL, + DSI_CTRL_UNKNOWN | DSI_CTRL_DSI_LANES(icn->dsi->lanes - 1)); - ICN6211_DSI(icn, VBP, mode->vtotal - mode->vsync_end); + chipone_writeb(icn, MIPI_PD_CK_LANE, 0xa0); + chipone_writeb(icn, PLL_CTRL(12), 0xff); + chipone_writeb(icn, MIPI_PN_SWAP, 0x00); - /* dsi specific sequence */ - ICN6211_DSI(icn, MIPI_DCS_SET_TEAR_OFF, 0x80); - ICN6211_DSI(icn, MIPI_DCS_SET_ADDRESS_MODE, 0x28); - ICN6211_DSI(icn, 0xb5, 0xa0); - ICN6211_DSI(icn, 0x5c, 0xff); - ICN6211_DSI(icn, MIPI_DCS_SET_COLUMN_ADDRESS, 0x01); - ICN6211_DSI(icn, MIPI_DCS_GET_POWER_SAVE, 0x92); - ICN6211_DSI(icn, 0x6b, 0x71); - ICN6211_DSI(icn, 0x69, 0x2b); - ICN6211_DSI(icn, MIPI_DCS_ENTER_SLEEP_MODE, 0x40); - ICN6211_DSI(icn, MIPI_DCS_EXIT_SLEEP_MODE, 0x98); + /* DPI HS/VS/DE polarity */ + pol = ((mode->flags & DRM_MODE_FLAG_PHSYNC) ? BIST_POL_HSYNC_POL : 0) | + ((mode->flags & DRM_MODE_FLAG_PVSYNC) ? BIST_POL_VSYNC_POL : 0) | + ((bus_flags & DRM_BUS_FLAG_DE_HIGH) ? BIST_POL_DE_POL : 0); + chipone_writeb(icn, BIST_POL, pol); + + /* Configure PLL settings */ + chipone_configure_pll(icn, mode); + + chipone_writeb(icn, SYS_CTRL(0), 0x40); + chipone_writeb(icn, SYS_CTRL(1), 0x88); /* icn6211 specific sequence */ - ICN6211_DSI(icn, 0xb6, 0x20); - ICN6211_DSI(icn, 0x51, 0x20); - ICN6211_DSI(icn, 0x09, 0x10); + chipone_writeb(icn, MIPI_FORCE_0, 0x20); + chipone_writeb(icn, PLL_CTRL(1), 0x20); + chipone_writeb(icn, CONFIG_FINISH, 0x10); usleep_range(10000, 11000); } @@ -168,6 +480,81 @@ static void chipone_mode_set(struct drm_bridge *bridge, struct chipone *icn = bridge_to_chipone(bridge); drm_mode_copy(&icn->mode, adjusted_mode); +}; + +static int chipone_dsi_attach(struct chipone *icn) +{ + struct mipi_dsi_device *dsi = icn->dsi; + struct device *dev = icn->dev; + struct device_node *endpoint; + int dsi_lanes, ret; + + endpoint = of_graph_get_endpoint_by_regs(dev->of_node, 0, 0); + dsi_lanes = of_property_count_u32_elems(endpoint, "data-lanes"); + of_node_put(endpoint); + + /* + * If the 'data-lanes' property does not exist in DT or is invalid, + * default to previously hard-coded behavior, which was 4 data lanes. + */ + if (dsi_lanes >= 1 && dsi_lanes <= 4) + icn->dsi->lanes = dsi_lanes; + else + icn->dsi->lanes = 4; + + dsi->format = MIPI_DSI_FMT_RGB888; + dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST | + MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_NO_EOT_PACKET; + + ret = mipi_dsi_attach(dsi); + if (ret < 0) + dev_err(icn->dev, "failed to attach dsi\n"); + + return ret; +} + +static int chipone_dsi_host_attach(struct chipone *icn) +{ + struct device *dev = icn->dev; + struct device_node *host_node; + struct device_node *endpoint; + struct mipi_dsi_device *dsi; + struct mipi_dsi_host *host; + int ret = 0; + + const struct mipi_dsi_device_info info = { + .type = "chipone", + .channel = 0, + .node = NULL, + }; + + endpoint = of_graph_get_endpoint_by_regs(dev->of_node, 0, 0); + host_node = of_graph_get_remote_port_parent(endpoint); + of_node_put(endpoint); + + if (!host_node) + return -EINVAL; + + host = of_find_mipi_dsi_host_by_node(host_node); + of_node_put(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)) { + return dev_err_probe(dev, PTR_ERR(dsi), + "failed to create dsi device\n"); + } + + icn->dsi = dsi; + + ret = chipone_dsi_attach(icn); + if (ret < 0) + mipi_dsi_device_unregister(dsi); + + return ret; } static int chipone_attach(struct drm_bridge *bridge, enum drm_bridge_attach_flags flags) @@ -177,6 +564,32 @@ static int chipone_attach(struct drm_bridge *bridge, enum drm_bridge_attach_flag return drm_bridge_attach(bridge->encoder, icn->panel_bridge, bridge, flags); } +#define MAX_INPUT_SEL_FORMATS 1 + +static u32 * +chipone_atomic_get_input_bus_fmts(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + u32 output_fmt, + unsigned int *num_input_fmts) +{ + u32 *input_fmts; + + *num_input_fmts = 0; + + input_fmts = kcalloc(MAX_INPUT_SEL_FORMATS, sizeof(*input_fmts), + GFP_KERNEL); + if (!input_fmts) + return NULL; + + /* This is the DSI-end bus format */ + input_fmts[0] = MEDIA_BUS_FMT_RGB888_1X24; + *num_input_fmts = 1; + + return input_fmts; +} + static const struct drm_bridge_funcs chipone_bridge_funcs = { .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, @@ -186,6 +599,7 @@ static const struct drm_bridge_funcs chipone_bridge_funcs = { .atomic_post_disable = chipone_atomic_post_disable, .mode_set = chipone_mode_set, .attach = chipone_attach, + .atomic_get_input_bus_fmts = chipone_atomic_get_input_bus_fmts, }; static int chipone_parse_dt(struct chipone *icn) @@ -233,9 +647,8 @@ static int chipone_parse_dt(struct chipone *icn) return 0; } -static int chipone_probe(struct mipi_dsi_device *dsi) +static int chipone_common_probe(struct device *dev, struct chipone **icnr) { - struct device *dev = &dsi->dev; struct chipone *icn; int ret; @@ -243,7 +656,6 @@ static int chipone_probe(struct mipi_dsi_device *dsi) if (!icn) return -ENOMEM; - mipi_dsi_set_drvdata(dsi, icn); icn->dev = dev; ret = chipone_parse_dt(icn); @@ -254,22 +666,66 @@ static int chipone_probe(struct mipi_dsi_device *dsi) icn->bridge.type = DRM_MODE_CONNECTOR_DPI; icn->bridge.of_node = dev->of_node; - drm_bridge_add(&icn->bridge); + *icnr = icn; - dsi->lanes = 4; - dsi->format = MIPI_DSI_FMT_RGB888; - dsi->mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE; + return ret; +} - ret = mipi_dsi_attach(dsi); - if (ret < 0) { +static int chipone_dsi_probe(struct mipi_dsi_device *dsi) +{ + struct device *dev = &dsi->dev; + struct chipone *icn; + int ret; + + ret = chipone_common_probe(dev, &icn); + if (ret) + return ret; + + icn->regmap = devm_regmap_init(dev, &chipone_dsi_regmap_bus, + dsi, &chipone_regmap_config); + if (IS_ERR(icn->regmap)) + return PTR_ERR(icn->regmap); + + icn->interface_i2c = false; + icn->dsi = dsi; + + mipi_dsi_set_drvdata(dsi, icn); + + drm_bridge_add(&icn->bridge); + + ret = chipone_dsi_attach(icn); + if (ret) drm_bridge_remove(&icn->bridge); - dev_err(dev, "failed to attach dsi\n"); - } return ret; } -static int chipone_remove(struct mipi_dsi_device *dsi) +static int chipone_i2c_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct device *dev = &client->dev; + struct chipone *icn; + int ret; + + ret = chipone_common_probe(dev, &icn); + if (ret) + return ret; + + icn->regmap = devm_regmap_init_i2c(client, &chipone_regmap_config); + if (IS_ERR(icn->regmap)) + return PTR_ERR(icn->regmap); + + icn->interface_i2c = true; + icn->client = client; + dev_set_drvdata(dev, icn); + i2c_set_clientdata(client, icn); + + drm_bridge_add(&icn->bridge); + + return chipone_dsi_host_attach(icn); +} + +static int chipone_dsi_remove(struct mipi_dsi_device *dsi) { struct chipone *icn = mipi_dsi_get_drvdata(dsi); @@ -285,16 +741,48 @@ static const struct of_device_id chipone_of_match[] = { }; MODULE_DEVICE_TABLE(of, chipone_of_match); -static struct mipi_dsi_driver chipone_driver = { - .probe = chipone_probe, - .remove = chipone_remove, +static struct mipi_dsi_driver chipone_dsi_driver = { + .probe = chipone_dsi_probe, + .remove = chipone_dsi_remove, .driver = { .name = "chipone-icn6211", .owner = THIS_MODULE, .of_match_table = chipone_of_match, }, }; -module_mipi_dsi_driver(chipone_driver); + +static struct i2c_device_id chipone_i2c_id[] = { + { "chipone,icn6211" }, + {}, +}; +MODULE_DEVICE_TABLE(i2c, chipone_i2c_id); + +static struct i2c_driver chipone_i2c_driver = { + .probe = chipone_i2c_probe, + .id_table = chipone_i2c_id, + .driver = { + .name = "chipone-icn6211-i2c", + .of_match_table = chipone_of_match, + }, +}; + +static int __init chipone_init(void) +{ + if (IS_ENABLED(CONFIG_DRM_MIPI_DSI)) + mipi_dsi_driver_register(&chipone_dsi_driver); + + return i2c_add_driver(&chipone_i2c_driver); +} +module_init(chipone_init); + +static void __exit chipone_exit(void) +{ + i2c_del_driver(&chipone_i2c_driver); + + if (IS_ENABLED(CONFIG_DRM_MIPI_DSI)) + mipi_dsi_driver_unregister(&chipone_dsi_driver); +} +module_exit(chipone_exit); MODULE_AUTHOR("Jagan Teki <jagan@amarulasolutions.com>"); MODULE_DESCRIPTION("Chipone ICN6211 MIPI-DSI to RGB Converter Bridge"); diff --git a/drivers/gpu/drm/bridge/display-connector.c b/drivers/gpu/drm/bridge/display-connector.c index d24f5b90feab..e4d52a7e31b7 100644 --- a/drivers/gpu/drm/bridge/display-connector.c +++ b/drivers/gpu/drm/bridge/display-connector.c @@ -24,6 +24,7 @@ struct display_connector { int hpd_irq; struct regulator *dp_pwr; + struct gpio_desc *ddc_en; }; static inline struct display_connector * @@ -345,6 +346,17 @@ static int display_connector_probe(struct platform_device *pdev) } } + /* enable DDC */ + if (type == DRM_MODE_CONNECTOR_HDMIA) { + conn->ddc_en = devm_gpiod_get_optional(&pdev->dev, "ddc-en", + GPIOD_OUT_HIGH); + + if (IS_ERR(conn->ddc_en)) { + dev_err(&pdev->dev, "Couldn't get ddc-en gpio\n"); + return PTR_ERR(conn->ddc_en); + } + } + conn->bridge.funcs = &display_connector_bridge_funcs; conn->bridge.of_node = pdev->dev.of_node; @@ -373,6 +385,9 @@ static int display_connector_remove(struct platform_device *pdev) { struct display_connector *conn = platform_get_drvdata(pdev); + if (conn->ddc_en) + gpiod_set_value(conn->ddc_en, 0); + if (conn->dp_pwr) regulator_disable(conn->dp_pwr); diff --git a/drivers/gpu/drm/bridge/ite-it66121.c b/drivers/gpu/drm/bridge/ite-it66121.c index 69288cf894b9..448c58e60c11 100644 --- a/drivers/gpu/drm/bridge/ite-it66121.c +++ b/drivers/gpu/drm/bridge/ite-it66121.c @@ -27,6 +27,8 @@ #include <drm/drm_print.h> #include <drm/drm_probe_helper.h> +#include <sound/hdmi-codec.h> + #define IT66121_VENDOR_ID0_REG 0x00 #define IT66121_VENDOR_ID1_REG 0x01 #define IT66121_DEVICE_ID0_REG 0x02 @@ -155,6 +157,9 @@ #define IT66121_AV_MUTE_ON BIT(0) #define IT66121_AV_MUTE_BLUESCR BIT(1) +#define IT66121_PKT_CTS_CTRL_REG 0xC5 +#define IT66121_PKT_CTS_CTRL_SEL BIT(1) + #define IT66121_PKT_GEN_CTRL_REG 0xC6 #define IT66121_PKT_GEN_CTRL_ON BIT(0) #define IT66121_PKT_GEN_CTRL_RPT BIT(1) @@ -202,6 +207,89 @@ #define IT66121_EDID_SLEEP_US 20000 #define IT66121_EDID_TIMEOUT_US 200000 #define IT66121_EDID_FIFO_SIZE 32 + +#define IT66121_CLK_CTRL0_REG 0x58 +#define IT66121_CLK_CTRL0_AUTO_OVER_SAMPLING BIT(4) +#define IT66121_CLK_CTRL0_EXT_MCLK_MASK GENMASK(3, 2) +#define IT66121_CLK_CTRL0_EXT_MCLK_128FS (0 << 2) +#define IT66121_CLK_CTRL0_EXT_MCLK_256FS BIT(2) +#define IT66121_CLK_CTRL0_EXT_MCLK_512FS (2 << 2) +#define IT66121_CLK_CTRL0_EXT_MCLK_1024FS (3 << 2) +#define IT66121_CLK_CTRL0_AUTO_IPCLK BIT(0) +#define IT66121_CLK_STATUS1_REG 0x5E +#define IT66121_CLK_STATUS2_REG 0x5F + +#define IT66121_AUD_CTRL0_REG 0xE0 +#define IT66121_AUD_SWL (3 << 6) +#define IT66121_AUD_16BIT (0 << 6) +#define IT66121_AUD_18BIT BIT(6) +#define IT66121_AUD_20BIT (2 << 6) +#define IT66121_AUD_24BIT (3 << 6) +#define IT66121_AUD_SPDIFTC BIT(5) +#define IT66121_AUD_SPDIF BIT(4) +#define IT66121_AUD_I2S (0 << 4) +#define IT66121_AUD_EN_I2S3 BIT(3) +#define IT66121_AUD_EN_I2S2 BIT(2) +#define IT66121_AUD_EN_I2S1 BIT(1) +#define IT66121_AUD_EN_I2S0 BIT(0) +#define IT66121_AUD_CTRL0_AUD_SEL BIT(4) + +#define IT66121_AUD_CTRL1_REG 0xE1 +#define IT66121_AUD_FIFOMAP_REG 0xE2 +#define IT66121_AUD_CTRL3_REG 0xE3 +#define IT66121_AUD_SRCVALID_FLAT_REG 0xE4 +#define IT66121_AUD_FLAT_SRC0 BIT(4) +#define IT66121_AUD_FLAT_SRC1 BIT(5) +#define IT66121_AUD_FLAT_SRC2 BIT(6) +#define IT66121_AUD_FLAT_SRC3 BIT(7) +#define IT66121_AUD_HDAUDIO_REG 0xE5 + +#define IT66121_AUD_PKT_CTS0_REG 0x130 +#define IT66121_AUD_PKT_CTS1_REG 0x131 +#define IT66121_AUD_PKT_CTS2_REG 0x132 +#define IT66121_AUD_PKT_N0_REG 0x133 +#define IT66121_AUD_PKT_N1_REG 0x134 +#define IT66121_AUD_PKT_N2_REG 0x135 + +#define IT66121_AUD_CHST_MODE_REG 0x191 +#define IT66121_AUD_CHST_CAT_REG 0x192 +#define IT66121_AUD_CHST_SRCNUM_REG 0x193 +#define IT66121_AUD_CHST_CHTNUM_REG 0x194 +#define IT66121_AUD_CHST_CA_FS_REG 0x198 +#define IT66121_AUD_CHST_OFS_WL_REG 0x199 + +#define IT66121_AUD_PKT_CTS_CNT0_REG 0x1A0 +#define IT66121_AUD_PKT_CTS_CNT1_REG 0x1A1 +#define IT66121_AUD_PKT_CTS_CNT2_REG 0x1A2 + +#define IT66121_AUD_FS_22P05K 0x4 +#define IT66121_AUD_FS_44P1K 0x0 +#define IT66121_AUD_FS_88P2K 0x8 +#define IT66121_AUD_FS_176P4K 0xC +#define IT66121_AUD_FS_24K 0x6 +#define IT66121_AUD_FS_48K 0x2 +#define IT66121_AUD_FS_96K 0xA +#define IT66121_AUD_FS_192K 0xE +#define IT66121_AUD_FS_768K 0x9 +#define IT66121_AUD_FS_32K 0x3 +#define IT66121_AUD_FS_OTHER 0x1 + +#define IT66121_AUD_SWL_21BIT 0xD +#define IT66121_AUD_SWL_24BIT 0xB +#define IT66121_AUD_SWL_23BIT 0x9 +#define IT66121_AUD_SWL_22BIT 0x5 +#define IT66121_AUD_SWL_20BIT 0x3 +#define IT66121_AUD_SWL_17BIT 0xC +#define IT66121_AUD_SWL_19BIT 0x8 +#define IT66121_AUD_SWL_18BIT 0x4 +#define IT66121_AUD_SWL_16BIT 0x2 +#define IT66121_AUD_SWL_NOT_INDICATED 0x0 + +#define IT66121_VENDOR_ID0 0x54 +#define IT66121_VENDOR_ID1 0x49 +#define IT66121_DEVICE_ID0 0x12 +#define IT66121_DEVICE_ID1 0x06 +#define IT66121_DEVICE_MASK 0x0F #define IT66121_AFE_CLK_HIGH 80000 /* Khz */ struct it66121_ctx { @@ -216,6 +304,13 @@ struct it66121_ctx { u32 bus_width; struct mutex lock; /* Protects fields below and device registers */ struct hdmi_avi_infoframe hdmi_avi_infoframe; + struct { + struct platform_device *pdev; + u8 ch_enable; + u8 fs; + u8 swl; + bool auto_cts; + } audio; }; static const struct regmap_range_cfg it66121_regmap_banks[] = { @@ -227,7 +322,7 @@ static const struct regmap_range_cfg it66121_regmap_banks[] = { .selector_mask = 0x1, .selector_shift = 0, .window_start = 0x00, - .window_len = 0x130, + .window_len = 0x100, }, }; @@ -886,6 +981,536 @@ unlock: return IRQ_HANDLED; } +static int it661221_set_chstat(struct it66121_ctx *ctx, u8 iec60958_chstat[]) +{ + int ret; + + ret = regmap_write(ctx->regmap, IT66121_AUD_CHST_MODE_REG, iec60958_chstat[0] & 0x7C); + if (ret) + return ret; + + ret = regmap_write(ctx->regmap, IT66121_AUD_CHST_CAT_REG, iec60958_chstat[1]); + if (ret) + return ret; + + ret = regmap_write(ctx->regmap, IT66121_AUD_CHST_SRCNUM_REG, iec60958_chstat[2] & 0x0F); + if (ret) + return ret; + + ret = regmap_write(ctx->regmap, IT66121_AUD_CHST_CHTNUM_REG, + (iec60958_chstat[2] >> 4) & 0x0F); + if (ret) + return ret; + + ret = regmap_write(ctx->regmap, IT66121_AUD_CHST_CA_FS_REG, iec60958_chstat[3]); + if (ret) + return ret; + + return regmap_write(ctx->regmap, IT66121_AUD_CHST_OFS_WL_REG, iec60958_chstat[4]); +} + +static int it661221_set_lpcm_audio(struct it66121_ctx *ctx, u8 audio_src_num, u8 audio_swl) +{ + int ret; + unsigned int audio_enable = 0; + unsigned int audio_format = 0; + + switch (audio_swl) { + case 16: + audio_enable |= IT66121_AUD_16BIT; + break; + case 18: + audio_enable |= IT66121_AUD_18BIT; + break; + case 20: + audio_enable |= IT66121_AUD_20BIT; + break; + case 24: + default: + audio_enable |= IT66121_AUD_24BIT; + break; + } + + audio_format |= 0x40; + switch (audio_src_num) { + case 4: + audio_enable |= IT66121_AUD_EN_I2S3 | IT66121_AUD_EN_I2S2 | + IT66121_AUD_EN_I2S1 | IT66121_AUD_EN_I2S0; + break; + case 3: + audio_enable |= IT66121_AUD_EN_I2S2 | IT66121_AUD_EN_I2S1 | + IT66121_AUD_EN_I2S0; + break; + case 2: + audio_enable |= IT66121_AUD_EN_I2S1 | IT66121_AUD_EN_I2S0; + break; + case 1: + default: + audio_format &= ~0x40; + audio_enable |= IT66121_AUD_EN_I2S0; + break; + } + + audio_format |= 0x01; + ctx->audio.ch_enable = audio_enable; + + ret = regmap_write(ctx->regmap, IT66121_AUD_CTRL0_REG, audio_enable & 0xF0); + if (ret) + return ret; + + ret = regmap_write(ctx->regmap, IT66121_AUD_CTRL1_REG, audio_format); + if (ret) + return ret; + + ret = regmap_write(ctx->regmap, IT66121_AUD_FIFOMAP_REG, 0xE4); + if (ret) + return ret; + + ret = regmap_write(ctx->regmap, IT66121_AUD_CTRL3_REG, 0x00); + if (ret) + return ret; + + ret = regmap_write(ctx->regmap, IT66121_AUD_SRCVALID_FLAT_REG, 0x00); + if (ret) + return ret; + + return regmap_write(ctx->regmap, IT66121_AUD_HDAUDIO_REG, 0x00); +} + +static int it661221_set_ncts(struct it66121_ctx *ctx, u8 fs) +{ + int ret; + unsigned int n; + + switch (fs) { + case IT66121_AUD_FS_32K: + n = 4096; + break; + case IT66121_AUD_FS_44P1K: + n = 6272; + break; + case IT66121_AUD_FS_48K: + n = 6144; + break; + case IT66121_AUD_FS_88P2K: + n = 12544; + break; + case IT66121_AUD_FS_96K: + n = 12288; + break; + case IT66121_AUD_FS_176P4K: + n = 25088; + break; + case IT66121_AUD_FS_192K: + n = 24576; + break; + case IT66121_AUD_FS_768K: + n = 24576; + break; + default: + n = 6144; + break; + } + + ret = regmap_write(ctx->regmap, IT66121_AUD_PKT_N0_REG, (u8)((n) & 0xFF)); + if (ret) + return ret; + + ret = regmap_write(ctx->regmap, IT66121_AUD_PKT_N1_REG, (u8)((n >> 8) & 0xFF)); + if (ret) + return ret; + + ret = regmap_write(ctx->regmap, IT66121_AUD_PKT_N2_REG, (u8)((n >> 16) & 0xF)); + if (ret) + return ret; + + if (ctx->audio.auto_cts) { + u8 loop_cnt = 255; + u8 cts_stable_cnt = 0; + unsigned int sum_cts = 0; + unsigned int cts = 0; + unsigned int last_cts = 0; + unsigned int diff; + unsigned int val; + + while (loop_cnt--) { + msleep(30); + regmap_read(ctx->regmap, IT66121_AUD_PKT_CTS_CNT2_REG, &val); + cts = val << 12; + regmap_read(ctx->regmap, IT66121_AUD_PKT_CTS_CNT1_REG, &val); + cts |= val << 4; + regmap_read(ctx->regmap, IT66121_AUD_PKT_CTS_CNT0_REG, &val); + cts |= val >> 4; + if (cts == 0) { + continue; + } else { + if (last_cts > cts) + diff = last_cts - cts; + else + diff = cts - last_cts; + last_cts = cts; + if (diff < 5) { + cts_stable_cnt++; + sum_cts += cts; + } else { + cts_stable_cnt = 0; + sum_cts = 0; + continue; + } + + if (cts_stable_cnt >= 32) { + last_cts = (sum_cts >> 5); + break; + } + } + } + + regmap_write(ctx->regmap, IT66121_AUD_PKT_CTS0_REG, (u8)((last_cts) & 0xFF)); + regmap_write(ctx->regmap, IT66121_AUD_PKT_CTS1_REG, (u8)((last_cts >> 8) & 0xFF)); + regmap_write(ctx->regmap, IT66121_AUD_PKT_CTS2_REG, (u8)((last_cts >> 16) & 0x0F)); + } + + ret = regmap_write(ctx->regmap, 0xF8, 0xC3); + if (ret) + return ret; + + ret = regmap_write(ctx->regmap, 0xF8, 0xA5); + if (ret) + return ret; + + if (ctx->audio.auto_cts) { + ret = regmap_write_bits(ctx->regmap, IT66121_PKT_CTS_CTRL_REG, + IT66121_PKT_CTS_CTRL_SEL, + 1); + } else { + ret = regmap_write_bits(ctx->regmap, IT66121_PKT_CTS_CTRL_REG, + IT66121_PKT_CTS_CTRL_SEL, + 0); + } + + if (ret) + return ret; + + return regmap_write(ctx->regmap, 0xF8, 0xFF); +} + +static int it661221_audio_output_enable(struct it66121_ctx *ctx, bool enable) +{ + int ret; + + if (enable) { + ret = regmap_write_bits(ctx->regmap, IT66121_SW_RST_REG, + IT66121_SW_RST_AUD | IT66121_SW_RST_AREF, + 0); + if (ret) + return ret; + + ret = regmap_write_bits(ctx->regmap, IT66121_AUD_CTRL0_REG, + IT66121_AUD_EN_I2S3 | IT66121_AUD_EN_I2S2 | + IT66121_AUD_EN_I2S1 | IT66121_AUD_EN_I2S0, + ctx->audio.ch_enable); + } else { + ret = regmap_write_bits(ctx->regmap, IT66121_AUD_CTRL0_REG, + IT66121_AUD_EN_I2S3 | IT66121_AUD_EN_I2S2 | + IT66121_AUD_EN_I2S1 | IT66121_AUD_EN_I2S0, + ctx->audio.ch_enable & 0xF0); + if (ret) + return ret; + + ret = regmap_write_bits(ctx->regmap, IT66121_SW_RST_REG, + IT66121_SW_RST_AUD | IT66121_SW_RST_AREF, + IT66121_SW_RST_AUD | IT66121_SW_RST_AREF); + } + + return ret; +} + +static int it661221_audio_ch_enable(struct it66121_ctx *ctx, bool enable) +{ + int ret; + + if (enable) { + ret = regmap_write(ctx->regmap, IT66121_AUD_SRCVALID_FLAT_REG, 0); + if (ret) + return ret; + + ret = regmap_write(ctx->regmap, IT66121_AUD_CTRL0_REG, ctx->audio.ch_enable); + } else { + ret = regmap_write(ctx->regmap, IT66121_AUD_CTRL0_REG, ctx->audio.ch_enable & 0xF0); + } + + return ret; +} + +static int it66121_audio_hw_params(struct device *dev, void *data, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params) +{ + u8 fs; + u8 swl; + int ret; + struct it66121_ctx *ctx = dev_get_drvdata(dev); + static u8 iec60958_chstat[5]; + unsigned int channels = params->channels; + unsigned int sample_rate = params->sample_rate; + unsigned int sample_width = params->sample_width; + + mutex_lock(&ctx->lock); + dev_dbg(dev, "%s: %u, %u, %u, %u\n", __func__, + daifmt->fmt, sample_rate, sample_width, channels); + + switch (daifmt->fmt) { + case HDMI_I2S: + dev_dbg(dev, "Using HDMI I2S\n"); + break; + default: + dev_err(dev, "Invalid or unsupported DAI format %d\n", daifmt->fmt); + ret = -EINVAL; + goto out; + } + + // Set audio clock recovery (N/CTS) + ret = regmap_write(ctx->regmap, IT66121_CLK_CTRL0_REG, + IT66121_CLK_CTRL0_AUTO_OVER_SAMPLING | + IT66121_CLK_CTRL0_EXT_MCLK_256FS | + IT66121_CLK_CTRL0_AUTO_IPCLK); + if (ret) + goto out; + + ret = regmap_write_bits(ctx->regmap, IT66121_AUD_CTRL0_REG, + IT66121_AUD_CTRL0_AUD_SEL, 0); // remove spdif selection + if (ret) + goto out; + + switch (sample_rate) { + case 44100L: + fs = IT66121_AUD_FS_44P1K; + break; + case 88200L: + fs = IT66121_AUD_FS_88P2K; + break; + case 176400L: + fs = IT66121_AUD_FS_176P4K; + break; + case 32000L: + fs = IT66121_AUD_FS_32K; + break; + case 48000L: + fs = IT66121_AUD_FS_48K; + break; + case 96000L: + fs = IT66121_AUD_FS_96K; + break; + case 192000L: + fs = IT66121_AUD_FS_192K; + break; + case 768000L: + fs = IT66121_AUD_FS_768K; + break; + default: + fs = IT66121_AUD_FS_48K; + break; + } + + ctx->audio.fs = fs; + ret = it661221_set_ncts(ctx, fs); + if (ret) { + dev_err(dev, "Failed to set N/CTS: %d\n", ret); + goto out; + } + + // Set audio format register (except audio channel enable) + ret = it661221_set_lpcm_audio(ctx, (channels + 1) / 2, sample_width); + if (ret) { + dev_err(dev, "Failed to set LPCM audio: %d\n", ret); + goto out; + } + + // Set audio channel status + iec60958_chstat[0] = 0; + if ((channels + 1) / 2 == 1) + iec60958_chstat[0] |= 0x1; + iec60958_chstat[0] &= ~(1 << 1); + iec60958_chstat[1] = 0; + iec60958_chstat[2] = (channels + 1) / 2; + iec60958_chstat[2] |= (channels << 4) & 0xF0; + iec60958_chstat[3] = fs; + + switch (sample_width) { + case 21L: + swl = IT66121_AUD_SWL_21BIT; + break; + case 24L: + swl = IT66121_AUD_SWL_24BIT; + break; + case 23L: + swl = IT66121_AUD_SWL_23BIT; + break; + case 22L: + swl = IT66121_AUD_SWL_22BIT; + break; + case 20L: + swl = IT66121_AUD_SWL_20BIT; + break; + case 17L: + swl = IT66121_AUD_SWL_17BIT; + break; + case 19L: + swl = IT66121_AUD_SWL_19BIT; + break; + case 18L: + swl = IT66121_AUD_SWL_18BIT; + break; + case 16L: + swl = IT66121_AUD_SWL_16BIT; + break; + default: + swl = IT66121_AUD_SWL_NOT_INDICATED; + break; + } + + iec60958_chstat[4] = (((~fs) << 4) & 0xF0) | swl; + ret = it661221_set_chstat(ctx, iec60958_chstat); + if (ret) { + dev_err(dev, "Failed to set channel status: %d\n", ret); + goto out; + } + + // Enable audio channel enable while input clock stable (if SPDIF). + ret = it661221_audio_ch_enable(ctx, true); + if (ret) { + dev_err(dev, "Failed to enable audio channel: %d\n", ret); + goto out; + } + + ret = regmap_write_bits(ctx->regmap, IT66121_INT_MASK1_REG, + IT66121_INT_MASK1_AUD_OVF, + 0); + if (ret) + goto out; + + dev_dbg(dev, "HDMI audio enabled.\n"); +out: + mutex_unlock(&ctx->lock); + + return ret; +} + +static int it66121_audio_startup(struct device *dev, void *data) +{ + int ret; + struct it66121_ctx *ctx = dev_get_drvdata(dev); + + dev_dbg(dev, "%s\n", __func__); + + mutex_lock(&ctx->lock); + ret = it661221_audio_output_enable(ctx, true); + if (ret) + dev_err(dev, "Failed to enable audio output: %d\n", ret); + + mutex_unlock(&ctx->lock); + + return ret; +} + +static void it66121_audio_shutdown(struct device *dev, void *data) +{ + int ret; + struct it66121_ctx *ctx = dev_get_drvdata(dev); + + dev_dbg(dev, "%s\n", __func__); + + mutex_lock(&ctx->lock); + ret = it661221_audio_output_enable(ctx, false); + if (ret) + dev_err(dev, "Failed to disable audio output: %d\n", ret); + + mutex_unlock(&ctx->lock); +} + +static int it66121_audio_mute(struct device *dev, void *data, + bool enable, int direction) +{ + int ret; + struct it66121_ctx *ctx = dev_get_drvdata(dev); + + dev_dbg(dev, "%s: enable=%s, direction=%d\n", + __func__, enable ? "true" : "false", direction); + + mutex_lock(&ctx->lock); + + if (enable) { + ret = regmap_write_bits(ctx->regmap, IT66121_AUD_SRCVALID_FLAT_REG, + IT66121_AUD_FLAT_SRC0 | IT66121_AUD_FLAT_SRC1 | + IT66121_AUD_FLAT_SRC2 | IT66121_AUD_FLAT_SRC3, + IT66121_AUD_FLAT_SRC0 | IT66121_AUD_FLAT_SRC1 | + IT66121_AUD_FLAT_SRC2 | IT66121_AUD_FLAT_SRC3); + } else { + ret = regmap_write_bits(ctx->regmap, IT66121_AUD_SRCVALID_FLAT_REG, + IT66121_AUD_FLAT_SRC0 | IT66121_AUD_FLAT_SRC1 | + IT66121_AUD_FLAT_SRC2 | IT66121_AUD_FLAT_SRC3, + 0); + } + + mutex_unlock(&ctx->lock); + + return ret; +} + +static int it66121_audio_get_eld(struct device *dev, void *data, + u8 *buf, size_t len) +{ + struct it66121_ctx *ctx = dev_get_drvdata(dev); + + mutex_lock(&ctx->lock); + + memcpy(buf, ctx->connector->eld, + min(sizeof(ctx->connector->eld), len)); + + mutex_unlock(&ctx->lock); + + return 0; +} + +static const struct hdmi_codec_ops it66121_audio_codec_ops = { + .hw_params = it66121_audio_hw_params, + .audio_startup = it66121_audio_startup, + .audio_shutdown = it66121_audio_shutdown, + .mute_stream = it66121_audio_mute, + .get_eld = it66121_audio_get_eld, + .no_capture_mute = 1, +}; + +static int it66121_audio_codec_init(struct it66121_ctx *ctx, struct device *dev) +{ + struct hdmi_codec_pdata codec_data = { + .ops = &it66121_audio_codec_ops, + .i2s = 1, /* Only i2s support for now */ + .spdif = 0, + .max_i2s_channels = 8, + }; + + dev_dbg(dev, "%s\n", __func__); + + if (!of_property_read_bool(dev->of_node, "#sound-dai-cells")) { + dev_info(dev, "No \"#sound-dai-cells\", no audio\n"); + return 0; + } + + ctx->audio.pdev = platform_device_register_data(dev, + HDMI_CODEC_DRV_NAME, + PLATFORM_DEVID_AUTO, + &codec_data, + sizeof(codec_data)); + + if (IS_ERR(ctx->audio.pdev)) { + dev_err(dev, "Failed to initialize HDMI audio codec: %d\n", + PTR_ERR_OR_ZERO(ctx->audio.pdev)); + } + + return PTR_ERR_OR_ZERO(ctx->audio.pdev); +} + static int it66121_probe(struct i2c_client *client, const struct i2c_device_id *id) { @@ -988,6 +1613,8 @@ static int it66121_probe(struct i2c_client *client, return ret; } + it66121_audio_codec_init(ctx, dev); + drm_bridge_add(&ctx->bridge); dev_info(ctx->dev, "IT66121 revision %d probed\n", revision_id); diff --git a/drivers/gpu/drm/bridge/lontium-lt9211.c b/drivers/gpu/drm/bridge/lontium-lt9211.c new file mode 100644 index 000000000000..e92821fbc639 --- /dev/null +++ b/drivers/gpu/drm/bridge/lontium-lt9211.c @@ -0,0 +1,802 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Lontium LT9211 bridge driver + * + * LT9211 is capable of converting: + * 2xDSI/2xLVDS/1xDPI -> 2xDSI/2xLVDS/1xDPI + * Currently supported is: + * 1xDSI -> 1xLVDS + * + * Copyright (C) 2022 Marek Vasut <marex@denx.de> + */ + +#include <linux/bits.h> +#include <linux/clk.h> +#include <linux/gpio/consumer.h> +#include <linux/i2c.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/of_graph.h> +#include <linux/regmap.h> +#include <linux/regulator/consumer.h> + +#include <drm/drm_atomic_helper.h> +#include <drm/drm_bridge.h> +#include <drm/drm_mipi_dsi.h> +#include <drm/drm_of.h> +#include <drm/drm_panel.h> +#include <drm/drm_print.h> +#include <drm/drm_probe_helper.h> + +#define REG_PAGE_CONTROL 0xff +#define REG_CHIPID0 0x8100 +#define REG_CHIPID0_VALUE 0x18 +#define REG_CHIPID1 0x8101 +#define REG_CHIPID1_VALUE 0x01 +#define REG_CHIPID2 0x8102 +#define REG_CHIPID2_VALUE 0xe3 + +#define REG_DSI_LANE 0xd000 +/* DSI lane count - 0 means 4 lanes ; 1, 2, 3 means 1, 2, 3 lanes. */ +#define REG_DSI_LANE_COUNT(n) ((n) & 3) + +struct lt9211 { + struct drm_bridge bridge; + struct device *dev; + struct regmap *regmap; + struct mipi_dsi_device *dsi; + struct drm_bridge *panel_bridge; + struct gpio_desc *reset_gpio; + struct regulator *vccio; + bool lvds_dual_link; + bool lvds_dual_link_even_odd_swap; +}; + +static const struct regmap_range lt9211_rw_ranges[] = { + regmap_reg_range(0xff, 0xff), + regmap_reg_range(0x8100, 0x816b), + regmap_reg_range(0x8200, 0x82aa), + regmap_reg_range(0x8500, 0x85ff), + regmap_reg_range(0x8600, 0x86a0), + regmap_reg_range(0x8700, 0x8746), + regmap_reg_range(0xd000, 0xd0a7), + regmap_reg_range(0xd400, 0xd42c), + regmap_reg_range(0xd800, 0xd838), + regmap_reg_range(0xd9c0, 0xd9d5), +}; + +static const struct regmap_access_table lt9211_rw_table = { + .yes_ranges = lt9211_rw_ranges, + .n_yes_ranges = ARRAY_SIZE(lt9211_rw_ranges), +}; + +static const struct regmap_range_cfg lt9211_range = { + .name = "lt9211", + .range_min = 0x0000, + .range_max = 0xda00, + .selector_reg = REG_PAGE_CONTROL, + .selector_mask = 0xff, + .selector_shift = 0, + .window_start = 0, + .window_len = 0x100, +}; + +static const struct regmap_config lt9211_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .rd_table = <9211_rw_table, + .wr_table = <9211_rw_table, + .volatile_table = <9211_rw_table, + .ranges = <9211_range, + .num_ranges = 1, + .cache_type = REGCACHE_RBTREE, + .max_register = 0xda00, +}; + +static struct lt9211 *bridge_to_lt9211(struct drm_bridge *bridge) +{ + return container_of(bridge, struct lt9211, bridge); +} + +static int lt9211_attach(struct drm_bridge *bridge, + enum drm_bridge_attach_flags flags) +{ + struct lt9211 *ctx = bridge_to_lt9211(bridge); + + return drm_bridge_attach(bridge->encoder, ctx->panel_bridge, + &ctx->bridge, flags); +} + +static int lt9211_read_chipid(struct lt9211 *ctx) +{ + u8 chipid[3]; + int ret; + + /* Read Chip ID registers and verify the chip can communicate. */ + ret = regmap_bulk_read(ctx->regmap, REG_CHIPID0, chipid, 3); + if (ret < 0) { + dev_err(ctx->dev, "Failed to read Chip ID: %d\n", ret); + return ret; + } + + /* Test for known Chip ID. */ + if (chipid[0] != REG_CHIPID0_VALUE || chipid[1] != REG_CHIPID1_VALUE || + chipid[2] != REG_CHIPID2_VALUE) { + dev_err(ctx->dev, "Unknown Chip ID: 0x%02x 0x%02x 0x%02x\n", + chipid[0], chipid[1], chipid[2]); + return -EINVAL; + } + + return 0; +} + +static int lt9211_system_init(struct lt9211 *ctx) +{ + const struct reg_sequence lt9211_system_init_seq[] = { + { 0x8201, 0x18 }, + { 0x8606, 0x61 }, + { 0x8607, 0xa8 }, + { 0x8714, 0x08 }, + { 0x8715, 0x00 }, + { 0x8718, 0x0f }, + { 0x8722, 0x08 }, + { 0x8723, 0x00 }, + { 0x8726, 0x0f }, + { 0x810b, 0xfe }, + }; + + return regmap_multi_reg_write(ctx->regmap, lt9211_system_init_seq, + ARRAY_SIZE(lt9211_system_init_seq)); +} + +static int lt9211_configure_rx(struct lt9211 *ctx) +{ + const struct reg_sequence lt9211_rx_phy_seq[] = { + { 0x8202, 0x44 }, + { 0x8204, 0xa0 }, + { 0x8205, 0x22 }, + { 0x8207, 0x9f }, + { 0x8208, 0xfc }, + /* ORR with 0xf8 here to enable DSI DN/DP swap. */ + { 0x8209, 0x01 }, + { 0x8217, 0x0c }, + { 0x8633, 0x1b }, + }; + + const struct reg_sequence lt9211_rx_cal_reset_seq[] = { + { 0x8120, 0x7f }, + { 0x8120, 0xff }, + }; + + const struct reg_sequence lt9211_rx_dig_seq[] = { + { 0x8630, 0x85 }, + /* 0x8588: BIT 6 set = MIPI-RX, BIT 4 unset = LVDS-TX */ + { 0x8588, 0x40 }, + { 0x85ff, 0xd0 }, + { REG_DSI_LANE, REG_DSI_LANE_COUNT(ctx->dsi->lanes) }, + { 0xd002, 0x05 }, + }; + + const struct reg_sequence lt9211_rx_div_reset_seq[] = { + { 0x810a, 0xc0 }, + { 0x8120, 0xbf }, + }; + + const struct reg_sequence lt9211_rx_div_clear_seq[] = { + { 0x810a, 0xc1 }, + { 0x8120, 0xff }, + }; + + int ret; + + ret = regmap_multi_reg_write(ctx->regmap, lt9211_rx_phy_seq, + ARRAY_SIZE(lt9211_rx_phy_seq)); + if (ret) + return ret; + + ret = regmap_multi_reg_write(ctx->regmap, lt9211_rx_cal_reset_seq, + ARRAY_SIZE(lt9211_rx_cal_reset_seq)); + if (ret) + return ret; + + ret = regmap_multi_reg_write(ctx->regmap, lt9211_rx_dig_seq, + ARRAY_SIZE(lt9211_rx_dig_seq)); + if (ret) + return ret; + + ret = regmap_multi_reg_write(ctx->regmap, lt9211_rx_div_reset_seq, + ARRAY_SIZE(lt9211_rx_div_reset_seq)); + if (ret) + return ret; + + usleep_range(10000, 15000); + + return regmap_multi_reg_write(ctx->regmap, lt9211_rx_div_clear_seq, + ARRAY_SIZE(lt9211_rx_div_clear_seq)); +} + +static int lt9211_autodetect_rx(struct lt9211 *ctx, + const struct drm_display_mode *mode) +{ + u16 width, height; + u32 byteclk; + u8 buf[5]; + u8 format; + u8 bc[3]; + int ret; + + /* Measure ByteClock frequency. */ + ret = regmap_write(ctx->regmap, 0x8600, 0x01); + if (ret) + return ret; + + /* Give the chip time to lock onto RX stream. */ + msleep(100); + + /* Read the ByteClock frequency from the chip. */ + ret = regmap_bulk_read(ctx->regmap, 0x8608, bc, sizeof(bc)); + if (ret) + return ret; + + /* RX ByteClock in kHz */ + byteclk = ((bc[0] & 0xf) << 16) | (bc[1] << 8) | bc[2]; + + /* Width/Height/Format Auto-detection */ + ret = regmap_bulk_read(ctx->regmap, 0xd082, buf, sizeof(buf)); + if (ret) + return ret; + + width = (buf[0] << 8) | buf[1]; + height = (buf[3] << 8) | buf[4]; + format = buf[2] & 0xf; + + if (format == 0x3) { /* YUV422 16bit */ + width /= 2; + } else if (format == 0xa) { /* RGB888 24bit */ + width /= 3; + } else { + dev_err(ctx->dev, "Unsupported DSI pixel format 0x%01x\n", + format); + return -EINVAL; + } + + if (width != mode->hdisplay) { + dev_err(ctx->dev, + "RX: Detected DSI width (%d) does not match mode hdisplay (%d)\n", + width, mode->hdisplay); + return -EINVAL; + } + + if (height != mode->vdisplay) { + dev_err(ctx->dev, + "RX: Detected DSI height (%d) does not match mode vdisplay (%d)\n", + height, mode->vdisplay); + return -EINVAL; + } + + dev_dbg(ctx->dev, "RX: %dx%d format=0x%01x byteclock=%d kHz\n", + width, height, format, byteclk); + + return 0; +} + +static int lt9211_configure_timing(struct lt9211 *ctx, + const struct drm_display_mode *mode) +{ + const struct reg_sequence lt9211_timing[] = { + { 0xd00d, (mode->vtotal >> 8) & 0xff }, + { 0xd00e, mode->vtotal & 0xff }, + { 0xd00f, (mode->vdisplay >> 8) & 0xff }, + { 0xd010, mode->vdisplay & 0xff }, + { 0xd011, (mode->htotal >> 8) & 0xff }, + { 0xd012, mode->htotal & 0xff }, + { 0xd013, (mode->hdisplay >> 8) & 0xff }, + { 0xd014, mode->hdisplay & 0xff }, + { 0xd015, (mode->vsync_end - mode->vsync_start) & 0xff }, + { 0xd016, (mode->hsync_end - mode->hsync_start) & 0xff }, + { 0xd017, ((mode->vsync_start - mode->vdisplay) >> 8) & 0xff }, + { 0xd018, (mode->vsync_start - mode->vdisplay) & 0xff }, + { 0xd019, ((mode->hsync_start - mode->hdisplay) >> 8) & 0xff }, + { 0xd01a, (mode->hsync_start - mode->hdisplay) & 0xff }, + }; + + return regmap_multi_reg_write(ctx->regmap, lt9211_timing, + ARRAY_SIZE(lt9211_timing)); +} + +static int lt9211_configure_plls(struct lt9211 *ctx, + const struct drm_display_mode *mode) +{ + const struct reg_sequence lt9211_pcr_seq[] = { + { 0xd026, 0x17 }, + { 0xd027, 0xc3 }, + { 0xd02d, 0x30 }, + { 0xd031, 0x10 }, + { 0xd023, 0x20 }, + { 0xd038, 0x02 }, + { 0xd039, 0x10 }, + { 0xd03a, 0x20 }, + { 0xd03b, 0x60 }, + { 0xd03f, 0x04 }, + { 0xd040, 0x08 }, + { 0xd041, 0x10 }, + { 0x810b, 0xee }, + { 0x810b, 0xfe }, + }; + + unsigned int pval; + int ret; + + /* DeSSC PLL reference clock is 25 MHz XTal. */ + ret = regmap_write(ctx->regmap, 0x822d, 0x48); + if (ret) + return ret; + + if (mode->clock < 44000) { + ret = regmap_write(ctx->regmap, 0x8235, 0x83); + } else if (mode->clock < 88000) { + ret = regmap_write(ctx->regmap, 0x8235, 0x82); + } else if (mode->clock < 176000) { + ret = regmap_write(ctx->regmap, 0x8235, 0x81); + } else { + dev_err(ctx->dev, + "Unsupported mode clock (%d kHz) above 176 MHz.\n", + mode->clock); + return -EINVAL; + } + + if (ret) + return ret; + + /* Wait for the DeSSC PLL to stabilize. */ + msleep(100); + + ret = regmap_multi_reg_write(ctx->regmap, lt9211_pcr_seq, + ARRAY_SIZE(lt9211_pcr_seq)); + if (ret) + return ret; + + /* PCR stability test takes seconds. */ + ret = regmap_read_poll_timeout(ctx->regmap, 0xd087, pval, pval & 0x8, + 20000, 10000000); + if (ret) + dev_err(ctx->dev, "PCR unstable, ret=%i\n", ret); + + return ret; +} + +static int lt9211_configure_tx(struct lt9211 *ctx, bool jeida, + bool bpp24, bool de) +{ + const struct reg_sequence system_lt9211_tx_phy_seq[] = { + /* DPI output disable */ + { 0x8262, 0x00 }, + /* BIT(7) is LVDS dual-port */ + { 0x823b, 0x38 | (ctx->lvds_dual_link ? BIT(7) : 0) }, + { 0x823e, 0x92 }, + { 0x823f, 0x48 }, + { 0x8240, 0x31 }, + { 0x8243, 0x80 }, + { 0x8244, 0x00 }, + { 0x8245, 0x00 }, + { 0x8249, 0x00 }, + { 0x824a, 0x01 }, + { 0x824e, 0x00 }, + { 0x824f, 0x00 }, + { 0x8250, 0x00 }, + { 0x8253, 0x00 }, + { 0x8254, 0x01 }, + /* LVDS channel order, Odd:Even 0x10..A:B, 0x40..B:A */ + { 0x8646, ctx->lvds_dual_link_even_odd_swap ? 0x40 : 0x10 }, + { 0x8120, 0x7b }, + { 0x816b, 0xff }, + }; + + const struct reg_sequence system_lt9211_tx_dig_seq[] = { + { 0x8559, 0x40 | (jeida ? BIT(7) : 0) | + (de ? BIT(5) : 0) | (bpp24 ? BIT(4) : 0) }, + { 0x855a, 0xaa }, + { 0x855b, 0xaa }, + { 0x855c, ctx->lvds_dual_link ? BIT(0) : 0 }, + { 0x85a1, 0x77 }, + { 0x8640, 0x40 }, + { 0x8641, 0x34 }, + { 0x8642, 0x10 }, + { 0x8643, 0x23 }, + { 0x8644, 0x41 }, + { 0x8645, 0x02 }, + }; + + const struct reg_sequence system_lt9211_tx_pll_seq[] = { + /* TX PLL power down */ + { 0x8236, 0x01 }, + { 0x8237, ctx->lvds_dual_link ? 0x2a : 0x29 }, + { 0x8238, 0x06 }, + { 0x8239, 0x30 }, + { 0x823a, 0x8e }, + { 0x8737, 0x14 }, + { 0x8713, 0x00 }, + { 0x8713, 0x80 }, + }; + + unsigned int pval; + int ret; + + ret = regmap_multi_reg_write(ctx->regmap, system_lt9211_tx_phy_seq, + ARRAY_SIZE(system_lt9211_tx_phy_seq)); + if (ret) + return ret; + + ret = regmap_multi_reg_write(ctx->regmap, system_lt9211_tx_dig_seq, + ARRAY_SIZE(system_lt9211_tx_dig_seq)); + if (ret) + return ret; + + ret = regmap_multi_reg_write(ctx->regmap, system_lt9211_tx_pll_seq, + ARRAY_SIZE(system_lt9211_tx_pll_seq)); + if (ret) + return ret; + + ret = regmap_read_poll_timeout(ctx->regmap, 0x871f, pval, pval & 0x80, + 10000, 1000000); + if (ret) { + dev_err(ctx->dev, "TX PLL unstable, ret=%i\n", ret); + return ret; + } + + ret = regmap_read_poll_timeout(ctx->regmap, 0x8720, pval, pval & 0x80, + 10000, 1000000); + if (ret) { + dev_err(ctx->dev, "TX PLL unstable, ret=%i\n", ret); + return ret; + } + + return 0; +} + +static void lt9211_atomic_enable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) +{ + struct lt9211 *ctx = bridge_to_lt9211(bridge); + struct drm_atomic_state *state = old_bridge_state->base.state; + const struct drm_bridge_state *bridge_state; + const struct drm_crtc_state *crtc_state; + const struct drm_display_mode *mode; + struct drm_connector *connector; + struct drm_crtc *crtc; + bool lvds_format_24bpp; + bool lvds_format_jeida; + u32 bus_flags; + int ret; + + ret = regulator_enable(ctx->vccio); + if (ret) { + dev_err(ctx->dev, "Failed to enable vccio: %d\n", ret); + return; + } + + /* Deassert reset */ + gpiod_set_value(ctx->reset_gpio, 1); + usleep_range(20000, 21000); /* Very long post-reset delay. */ + + /* Get the LVDS format from the bridge state. */ + bridge_state = drm_atomic_get_new_bridge_state(state, bridge); + bus_flags = bridge_state->output_bus_cfg.flags; + + switch (bridge_state->output_bus_cfg.format) { + case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG: + lvds_format_24bpp = false; + lvds_format_jeida = true; + break; + case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA: + lvds_format_24bpp = true; + lvds_format_jeida = true; + break; + case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG: + lvds_format_24bpp = true; + lvds_format_jeida = false; + break; + default: + /* + * Some bridges still don't set the correct + * LVDS bus pixel format, use SPWG24 default + * format until those are fixed. + */ + lvds_format_24bpp = true; + lvds_format_jeida = false; + dev_warn(ctx->dev, + "Unsupported LVDS bus format 0x%04x, please check output bridge driver. Falling back to SPWG24.\n", + bridge_state->output_bus_cfg.format); + break; + } + + /* + * Retrieve the CRTC adjusted mode. This requires a little dance to go + * from the bridge to the encoder, to the connector and to the CRTC. + */ + connector = drm_atomic_get_new_connector_for_encoder(state, + bridge->encoder); + crtc = drm_atomic_get_new_connector_state(state, connector)->crtc; + crtc_state = drm_atomic_get_new_crtc_state(state, crtc); + mode = &crtc_state->adjusted_mode; + + ret = lt9211_read_chipid(ctx); + if (ret) + return; + + ret = lt9211_system_init(ctx); + if (ret) + return; + + ret = lt9211_configure_rx(ctx); + if (ret) + return; + + ret = lt9211_autodetect_rx(ctx, mode); + if (ret) + return; + + ret = lt9211_configure_timing(ctx, mode); + if (ret) + return; + + ret = lt9211_configure_plls(ctx, mode); + if (ret) + return; + + ret = lt9211_configure_tx(ctx, lvds_format_jeida, lvds_format_24bpp, + bus_flags & DRM_BUS_FLAG_DE_HIGH); + if (ret) + return; + + dev_dbg(ctx->dev, "LT9211 enabled.\n"); +} + +static void lt9211_atomic_disable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) +{ + struct lt9211 *ctx = bridge_to_lt9211(bridge); + int ret; + + /* + * Put the chip in reset, pull nRST line low, + * and assure lengthy 10ms reset low timing. + */ + gpiod_set_value(ctx->reset_gpio, 0); + usleep_range(10000, 11000); /* Very long reset duration. */ + + ret = regulator_disable(ctx->vccio); + if (ret) + dev_err(ctx->dev, "Failed to disable vccio: %d\n", ret); + + regcache_mark_dirty(ctx->regmap); +} + +static enum drm_mode_status +lt9211_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + /* LVDS output clock range 25..176 MHz */ + if (mode->clock < 25000) + return MODE_CLOCK_LOW; + if (mode->clock > 176000) + return MODE_CLOCK_HIGH; + + return MODE_OK; +} + +#define MAX_INPUT_SEL_FORMATS 1 + +static u32 * +lt9211_atomic_get_input_bus_fmts(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + u32 output_fmt, + unsigned int *num_input_fmts) +{ + u32 *input_fmts; + + *num_input_fmts = 0; + + input_fmts = kcalloc(MAX_INPUT_SEL_FORMATS, sizeof(*input_fmts), + GFP_KERNEL); + if (!input_fmts) + return NULL; + + /* This is the DSI-end bus format */ + input_fmts[0] = MEDIA_BUS_FMT_RGB888_1X24; + *num_input_fmts = 1; + + return input_fmts; +} + +static const struct drm_bridge_funcs lt9211_funcs = { + .attach = lt9211_attach, + .mode_valid = lt9211_mode_valid, + .atomic_enable = lt9211_atomic_enable, + .atomic_disable = lt9211_atomic_disable, + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, + .atomic_get_input_bus_fmts = lt9211_atomic_get_input_bus_fmts, + .atomic_reset = drm_atomic_helper_bridge_reset, +}; + +static int lt9211_parse_dt(struct lt9211 *ctx) +{ + struct device_node *port2, *port3; + struct drm_bridge *panel_bridge; + struct device *dev = ctx->dev; + struct drm_panel *panel; + int dual_link; + int ret; + + ctx->vccio = devm_regulator_get(dev, "vccio"); + if (IS_ERR(ctx->vccio)) + return dev_err_probe(dev, PTR_ERR(ctx->vccio), + "Failed to get supply 'vccio'\n"); + + ctx->lvds_dual_link = false; + ctx->lvds_dual_link_even_odd_swap = false; + + port2 = of_graph_get_port_by_id(dev->of_node, 2); + port3 = of_graph_get_port_by_id(dev->of_node, 3); + dual_link = drm_of_lvds_get_dual_link_pixel_order(port2, port3); + of_node_put(port2); + of_node_put(port3); + + if (dual_link == DRM_LVDS_DUAL_LINK_ODD_EVEN_PIXELS) { + ctx->lvds_dual_link = true; + /* Odd pixels to LVDS Channel A, even pixels to B */ + ctx->lvds_dual_link_even_odd_swap = false; + } else if (dual_link == DRM_LVDS_DUAL_LINK_EVEN_ODD_PIXELS) { + ctx->lvds_dual_link = true; + /* Even pixels to LVDS Channel A, odd pixels to B */ + ctx->lvds_dual_link_even_odd_swap = true; + } + + ret = drm_of_find_panel_or_bridge(dev->of_node, 2, 0, &panel, &panel_bridge); + if (ret < 0) + return ret; + if (panel) { + panel_bridge = devm_drm_panel_bridge_add(dev, panel); + if (IS_ERR(panel_bridge)) + return PTR_ERR(panel_bridge); + } + + ctx->panel_bridge = panel_bridge; + + return 0; +} + +static int lt9211_host_attach(struct lt9211 *ctx) +{ + const struct mipi_dsi_device_info info = { + .type = "lt9211", + .channel = 0, + .node = NULL, + }; + struct device *dev = ctx->dev; + struct device_node *host_node; + struct device_node *endpoint; + struct mipi_dsi_device *dsi; + struct mipi_dsi_host *host; + int dsi_lanes; + int ret; + + endpoint = of_graph_get_endpoint_by_regs(dev->of_node, 0, -1); + dsi_lanes = of_property_count_u32_elems(endpoint, "data-lanes"); + host_node = of_graph_get_remote_port_parent(endpoint); + host = of_find_mipi_dsi_host_by_node(host_node); + of_node_put(host_node); + of_node_put(endpoint); + + if (!host) + return -EPROBE_DEFER; + + if (dsi_lanes < 0 || dsi_lanes > 4) + return -EINVAL; + + dsi = devm_mipi_dsi_device_register_full(dev, host, &info); + if (IS_ERR(dsi)) + return dev_err_probe(dev, PTR_ERR(dsi), + "failed to create dsi device\n"); + + ctx->dsi = dsi; + + dsi->lanes = dsi_lanes; + dsi->format = MIPI_DSI_FMT_RGB888; + dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE | + MIPI_DSI_MODE_VIDEO_HSE; + + ret = devm_mipi_dsi_attach(dev, dsi); + if (ret < 0) { + dev_err(dev, "failed to attach dsi to host: %d\n", ret); + return ret; + } + + return 0; +} + +static int lt9211_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct device *dev = &client->dev; + struct lt9211 *ctx; + int ret; + + ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + ctx->dev = dev; + + /* + * Put the chip in reset, pull nRST line low, + * and assure lengthy 10ms reset low timing. + */ + ctx->reset_gpio = devm_gpiod_get_optional(ctx->dev, "reset", + GPIOD_OUT_LOW); + if (IS_ERR(ctx->reset_gpio)) + return PTR_ERR(ctx->reset_gpio); + + usleep_range(10000, 11000); /* Very long reset duration. */ + + ret = lt9211_parse_dt(ctx); + if (ret) + return ret; + + ctx->regmap = devm_regmap_init_i2c(client, <9211_regmap_config); + if (IS_ERR(ctx->regmap)) + return PTR_ERR(ctx->regmap); + + dev_set_drvdata(dev, ctx); + i2c_set_clientdata(client, ctx); + + ctx->bridge.funcs = <9211_funcs; + ctx->bridge.of_node = dev->of_node; + drm_bridge_add(&ctx->bridge); + + ret = lt9211_host_attach(ctx); + if (ret) + drm_bridge_remove(&ctx->bridge); + + return ret; +} + +static int lt9211_remove(struct i2c_client *client) +{ + struct lt9211 *ctx = i2c_get_clientdata(client); + + drm_bridge_remove(&ctx->bridge); + + return 0; +} + +static struct i2c_device_id lt9211_id[] = { + { "lontium,lt9211" }, + {}, +}; +MODULE_DEVICE_TABLE(i2c, lt9211_id); + +static const struct of_device_id lt9211_match_table[] = { + { .compatible = "lontium,lt9211" }, + {}, +}; +MODULE_DEVICE_TABLE(of, lt9211_match_table); + +static struct i2c_driver lt9211_driver = { + .probe = lt9211_probe, + .remove = lt9211_remove, + .id_table = lt9211_id, + .driver = { + .name = "lt9211", + .of_match_table = lt9211_match_table, + }, +}; +module_i2c_driver(lt9211_driver); + +MODULE_AUTHOR("Marek Vasut <marex@denx.de>"); +MODULE_DESCRIPTION("Lontium LT9211 DSI/LVDS/DPI bridge driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index 63df2e8a8abc..7ef8fe5abc12 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -700,7 +700,9 @@ lt9611_connector_mode_valid(struct drm_connector *connector, } /* bridge funcs */ -static void lt9611_bridge_enable(struct drm_bridge *bridge) +static void +lt9611_bridge_atomic_enable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) { struct lt9611 *lt9611 = bridge_to_lt9611(bridge); @@ -721,7 +723,9 @@ static void lt9611_bridge_enable(struct drm_bridge *bridge) regmap_write(lt9611->regmap, 0x8130, 0xea); } -static void lt9611_bridge_disable(struct drm_bridge *bridge) +static void +lt9611_bridge_atomic_disable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) { struct lt9611 *lt9611 = bridge_to_lt9611(bridge); int ret; @@ -856,7 +860,9 @@ static void lt9611_bridge_pre_enable(struct drm_bridge *bridge) lt9611->sleep = false; } -static void lt9611_bridge_post_disable(struct drm_bridge *bridge) +static void +lt9611_bridge_atomic_post_disable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) { struct lt9611 *lt9611 = bridge_to_lt9611(bridge); @@ -916,16 +922,47 @@ static void lt9611_bridge_hpd_enable(struct drm_bridge *bridge) lt9611_enable_hpd_interrupts(lt9611); } +#define MAX_INPUT_SEL_FORMATS 1 + +static u32 * +lt9611_atomic_get_input_bus_fmts(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + u32 output_fmt, + unsigned int *num_input_fmts) +{ + u32 *input_fmts; + + *num_input_fmts = 0; + + input_fmts = kcalloc(MAX_INPUT_SEL_FORMATS, sizeof(*input_fmts), + GFP_KERNEL); + if (!input_fmts) + return NULL; + + /* This is the DSI-end bus format */ + input_fmts[0] = MEDIA_BUS_FMT_RGB888_1X24; + *num_input_fmts = 1; + + return input_fmts; +} + static const struct drm_bridge_funcs lt9611_bridge_funcs = { .attach = lt9611_bridge_attach, .mode_valid = lt9611_bridge_mode_valid, - .enable = lt9611_bridge_enable, - .disable = lt9611_bridge_disable, - .post_disable = lt9611_bridge_post_disable, .mode_set = lt9611_bridge_mode_set, .detect = lt9611_bridge_detect, .get_edid = lt9611_bridge_get_edid, .hpd_enable = lt9611_bridge_hpd_enable, + + .atomic_enable = lt9611_bridge_atomic_enable, + .atomic_disable = lt9611_bridge_atomic_disable, + .atomic_post_disable = lt9611_bridge_atomic_post_disable, + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, + .atomic_reset = drm_atomic_helper_bridge_reset, + .atomic_get_input_bus_fmts = lt9611_atomic_get_input_bus_fmts, }; static int lt9611_parse_dt(struct device *dev, diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c index d5945501a5ee..ad74e6558eb3 100644 --- a/drivers/gpu/drm/bridge/nwl-dsi.c +++ b/drivers/gpu/drm/bridge/nwl-dsi.c @@ -26,7 +26,6 @@ #include <drm/drm_bridge.h> #include <drm/drm_mipi_dsi.h> #include <drm/drm_of.h> -#include <drm/drm_panel.h> #include <drm/drm_print.h> #include <video/mipi_display.h> @@ -853,7 +852,7 @@ nwl_dsi_bridge_mode_set(struct drm_bridge *bridge, /* Save the new desired phy config */ memcpy(&dsi->phy_cfg, &new_cfg, sizeof(new_cfg)); - memcpy(&dsi->mode, adjusted_mode, sizeof(dsi->mode)); + drm_mode_copy(&dsi->mode, adjusted_mode); drm_mode_debug_printmodeline(adjusted_mode); if (pm_runtime_resume_and_get(dev) < 0) @@ -910,32 +909,14 @@ static int nwl_dsi_bridge_attach(struct drm_bridge *bridge, { struct nwl_dsi *dsi = bridge_to_dsi(bridge); struct drm_bridge *panel_bridge; - struct drm_panel *panel; - int ret; - ret = drm_of_find_panel_or_bridge(dsi->dev->of_node, 1, 0, &panel, - &panel_bridge); - if (ret) - return ret; - - if (panel) { - panel_bridge = drm_panel_bridge_add(panel); - if (IS_ERR(panel_bridge)) - return PTR_ERR(panel_bridge); - } - - if (!panel_bridge) - return -EPROBE_DEFER; + panel_bridge = devm_drm_of_get_bridge(dsi->dev, dsi->dev->of_node, 1, 0); + if (IS_ERR(panel_bridge)) + return PTR_ERR(panel_bridge); return drm_bridge_attach(bridge->encoder, panel_bridge, bridge, flags); } -static void nwl_dsi_bridge_detach(struct drm_bridge *bridge) -{ struct nwl_dsi *dsi = bridge_to_dsi(bridge); - - drm_of_panel_bridge_remove(dsi->dev->of_node, 1, 0); -} - static u32 *nwl_bridge_atomic_get_input_bus_fmts(struct drm_bridge *bridge, struct drm_bridge_state *bridge_state, struct drm_crtc_state *crtc_state, @@ -981,7 +962,6 @@ static const struct drm_bridge_funcs nwl_dsi_bridge_funcs = { .mode_set = nwl_dsi_bridge_mode_set, .mode_valid = nwl_dsi_bridge_mode_valid, .attach = nwl_dsi_bridge_attach, - .detach = nwl_dsi_bridge_detach, }; static int nwl_dsi_parse_dt(struct nwl_dsi *dsi) @@ -1153,7 +1133,7 @@ MODULE_DEVICE_TABLE(of, nwl_dsi_dt_ids); static const struct soc_device_attribute nwl_dsi_quirks_match[] = { { .soc_id = "i.MX8MQ", .revision = "2.0", .data = (void *)E11418_HS_MODE_QUIRK }, - { /* sentinel. */ }, + { /* sentinel. */ } }; static int nwl_dsi_probe(struct platform_device *pdev) diff --git a/drivers/gpu/drm/bridge/nxp-ptn3460.c b/drivers/gpu/drm/bridge/nxp-ptn3460.c index e941c1132598..1ab91f4e057b 100644 --- a/drivers/gpu/drm/bridge/nxp-ptn3460.c +++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c @@ -263,7 +263,6 @@ static int ptn3460_probe(struct i2c_client *client, struct device *dev = &client->dev; struct ptn3460_bridge *ptn_bridge; struct drm_bridge *panel_bridge; - struct drm_panel *panel; int ret; ptn_bridge = devm_kzalloc(dev, sizeof(*ptn_bridge), GFP_KERNEL); @@ -271,11 +270,7 @@ static int ptn3460_probe(struct i2c_client *client, return -ENOMEM; } - ret = drm_of_find_panel_or_bridge(dev->of_node, 0, 0, &panel, NULL); - if (ret) - return ret; - - panel_bridge = devm_drm_panel_bridge_add(dev, panel); + panel_bridge = devm_drm_of_get_bridge(dev, dev->of_node, 0, 0); if (IS_ERR(panel_bridge)) return PTR_ERR(panel_bridge); diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c index 5be057575183..0ee563eb2b6f 100644 --- a/drivers/gpu/drm/bridge/panel.c +++ b/drivers/gpu/drm/bridge/panel.c @@ -83,6 +83,12 @@ static int panel_bridge_attach(struct drm_bridge *bridge, drm_connector_attach_encoder(&panel_bridge->connector, bridge->encoder); + if (bridge->dev->registered) { + if (connector->funcs->reset) + connector->funcs->reset(connector); + drm_connector_register(connector); + } + return 0; } diff --git a/drivers/gpu/drm/bridge/parade-ps8622.c b/drivers/gpu/drm/bridge/parade-ps8622.c index 614b19f0f1b7..37b308850b4e 100644 --- a/drivers/gpu/drm/bridge/parade-ps8622.c +++ b/drivers/gpu/drm/bridge/parade-ps8622.c @@ -452,18 +452,13 @@ static int ps8622_probe(struct i2c_client *client, struct device *dev = &client->dev; struct ps8622_bridge *ps8622; struct drm_bridge *panel_bridge; - struct drm_panel *panel; int ret; ps8622 = devm_kzalloc(dev, sizeof(*ps8622), GFP_KERNEL); if (!ps8622) return -ENOMEM; - ret = drm_of_find_panel_or_bridge(dev->of_node, 0, 0, &panel, NULL); - if (ret) - return ret; - - panel_bridge = devm_drm_panel_bridge_add(dev, panel); + panel_bridge = devm_drm_of_get_bridge(dev, dev->of_node, 0, 0); if (IS_ERR(panel_bridge)) return PTR_ERR(panel_bridge); diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c index 3f17337ee389..9766cbbd62ad 100644 --- a/drivers/gpu/drm/bridge/parade-ps8640.c +++ b/drivers/gpu/drm/bridge/parade-ps8640.c @@ -589,7 +589,6 @@ static int ps8640_probe(struct i2c_client *client) struct device *dev = &client->dev; struct device_node *np = dev->of_node; struct ps8640 *ps_bridge; - struct drm_panel *panel; int ret; u32 i; @@ -674,13 +673,7 @@ static int ps8640_probe(struct i2c_client *client) devm_of_dp_aux_populate_ep_devices(&ps_bridge->aux); /* port@1 is ps8640 output port */ - ret = drm_of_find_panel_or_bridge(np, 1, 0, &panel, NULL); - if (ret < 0) - return ret; - if (!panel) - return -ENODEV; - - ps_bridge->panel_bridge = devm_drm_panel_bridge_add(dev, panel); + ps_bridge->panel_bridge = devm_drm_of_get_bridge(dev, np, 1, 0); if (IS_ERR(ps_bridge->panel_bridge)) return PTR_ERR(ps_bridge->panel_bridge); diff --git a/drivers/gpu/drm/bridge/synopsys/Kconfig b/drivers/gpu/drm/bridge/synopsys/Kconfig index 21a1be3ced0f..a4a31b669b65 100644 --- a/drivers/gpu/drm/bridge/synopsys/Kconfig +++ b/drivers/gpu/drm/bridge/synopsys/Kconfig @@ -25,6 +25,16 @@ config DRM_DW_HDMI_I2S_AUDIO Support the I2S Audio interface which is part of the Synopsys Designware HDMI block. +config DRM_DW_HDMI_GP_AUDIO + tristate "Synopsys Designware GP Audio interface" + depends on DRM_DW_HDMI && SND + select SND_PCM + select SND_PCM_ELD + select SND_PCM_IEC958 + help + Support the GP Audio interface which is part of the Synopsys + Designware HDMI block. + config DRM_DW_HDMI_CEC tristate "Synopsis Designware CEC interface" depends on DRM_DW_HDMI diff --git a/drivers/gpu/drm/bridge/synopsys/Makefile b/drivers/gpu/drm/bridge/synopsys/Makefile index 91d746ad5de1..ce715562e9e5 100644 --- a/drivers/gpu/drm/bridge/synopsys/Makefile +++ b/drivers/gpu/drm/bridge/synopsys/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_DRM_DW_HDMI) += dw-hdmi.o obj-$(CONFIG_DRM_DW_HDMI_AHB_AUDIO) += dw-hdmi-ahb-audio.o +obj-$(CONFIG_DRM_DW_HDMI_GP_AUDIO) += dw-hdmi-gp-audio.o obj-$(CONFIG_DRM_DW_HDMI_I2S_AUDIO) += dw-hdmi-i2s-audio.o obj-$(CONFIG_DRM_DW_HDMI_CEC) += dw-hdmi-cec.o diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-gp-audio.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-gp-audio.c new file mode 100644 index 000000000000..11ea1c84eb35 --- /dev/null +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-gp-audio.c @@ -0,0 +1,199 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * dw-hdmi-gp-audio.c + * + * Copyright 2020-2022 NXP + */ +#include <linux/io.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/dmaengine.h> +#include <linux/dma-mapping.h> +#include <drm/bridge/dw_hdmi.h> +#include <drm/drm_edid.h> +#include <drm/drm_connector.h> + +#include <sound/hdmi-codec.h> +#include <sound/asoundef.h> +#include <sound/core.h> +#include <sound/initval.h> +#include <sound/pcm.h> +#include <sound/pcm_drm_eld.h> +#include <sound/pcm_iec958.h> +#include <sound/dmaengine_pcm.h> + +#include "dw-hdmi-audio.h" + +#define DRIVER_NAME "dw-hdmi-gp-audio" +#define DRV_NAME "hdmi-gp-audio" + +struct snd_dw_hdmi { + struct dw_hdmi_audio_data data; + struct platform_device *audio_pdev; + unsigned int pos; +}; + +struct dw_hdmi_channel_conf { + u8 conf1; + u8 ca; +}; + +/* + * The default mapping of ALSA channels to HDMI channels and speaker + * allocation bits. Note that we can't do channel remapping here - + * channels must be in the same order. + * + * Mappings for alsa-lib pcm/surround*.conf files: + * + * Front Sur4.0 Sur4.1 Sur5.0 Sur5.1 Sur7.1 + * Channels 2 4 6 6 6 8 + * + * Our mapping from ALSA channel to CEA686D speaker name and HDMI channel: + * + * Number of ALSA channels + * ALSA Channel 2 3 4 5 6 7 8 + * 0 FL:0 = = = = = = + * 1 FR:1 = = = = = = + * 2 FC:3 RL:4 LFE:2 = = = + * 3 RR:5 RL:4 FC:3 = = + * 4 RR:5 RL:4 = = + * 5 RR:5 = = + * 6 RC:6 = + * 7 RLC/FRC RLC/FRC + */ +static struct dw_hdmi_channel_conf default_hdmi_channel_config[7] = { + { 0x03, 0x00 }, /* FL,FR */ + { 0x0b, 0x02 }, /* FL,FR,FC */ + { 0x33, 0x08 }, /* FL,FR,RL,RR */ + { 0x37, 0x09 }, /* FL,FR,LFE,RL,RR */ + { 0x3f, 0x0b }, /* FL,FR,LFE,FC,RL,RR */ + { 0x7f, 0x0f }, /* FL,FR,LFE,FC,RL,RR,RC */ + { 0xff, 0x13 }, /* FL,FR,LFE,FC,RL,RR,[FR]RC,[FR]LC */ +}; + +static int audio_hw_params(struct device *dev, void *data, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params) +{ + struct snd_dw_hdmi *dw = dev_get_drvdata(dev); + int ret = 0; + u8 ca; + + dw_hdmi_set_sample_rate(dw->data.hdmi, params->sample_rate); + + ca = default_hdmi_channel_config[params->channels - 2].ca; + + dw_hdmi_set_channel_count(dw->data.hdmi, params->channels); + dw_hdmi_set_channel_allocation(dw->data.hdmi, ca); + + dw_hdmi_set_sample_non_pcm(dw->data.hdmi, + params->iec.status[0] & IEC958_AES0_NONAUDIO); + dw_hdmi_set_sample_width(dw->data.hdmi, params->sample_width); + + return ret; +} + +static void audio_shutdown(struct device *dev, void *data) +{ +} + +static int audio_mute_stream(struct device *dev, void *data, + bool enable, int direction) +{ + struct snd_dw_hdmi *dw = dev_get_drvdata(dev); + int ret = 0; + + if (!enable) + dw_hdmi_audio_enable(dw->data.hdmi); + else + dw_hdmi_audio_disable(dw->data.hdmi); + + return ret; +} + +static int audio_get_eld(struct device *dev, void *data, + u8 *buf, size_t len) +{ + struct dw_hdmi_audio_data *audio = data; + u8 *eld; + + eld = audio->get_eld(audio->hdmi); + if (eld) + memcpy(buf, eld, min_t(size_t, MAX_ELD_BYTES, len)); + else + /* Pass en empty ELD if connector not available */ + memset(buf, 0, len); + + return 0; +} + +static int audio_hook_plugged_cb(struct device *dev, void *data, + hdmi_codec_plugged_cb fn, + struct device *codec_dev) +{ + struct snd_dw_hdmi *dw = dev_get_drvdata(dev); + + return dw_hdmi_set_plugged_cb(dw->data.hdmi, fn, codec_dev); +} + +static const struct hdmi_codec_ops audio_codec_ops = { + .hw_params = audio_hw_params, + .audio_shutdown = audio_shutdown, + .mute_stream = audio_mute_stream, + .get_eld = audio_get_eld, + .hook_plugged_cb = audio_hook_plugged_cb, +}; + +static int snd_dw_hdmi_probe(struct platform_device *pdev) +{ + struct dw_hdmi_audio_data *data = pdev->dev.platform_data; + struct snd_dw_hdmi *dw; + + const struct hdmi_codec_pdata codec_data = { + .i2s = 1, + .spdif = 0, + .ops = &audio_codec_ops, + .max_i2s_channels = 8, + .data = data, + }; + + dw = devm_kzalloc(&pdev->dev, sizeof(*dw), GFP_KERNEL); + if (!dw) + return -ENOMEM; + + dw->data = *data; + + platform_set_drvdata(pdev, dw); + + dw->audio_pdev = platform_device_register_data(&pdev->dev, + HDMI_CODEC_DRV_NAME, 1, + &codec_data, + sizeof(codec_data)); + + return PTR_ERR_OR_ZERO(dw->audio_pdev); +} + +static int snd_dw_hdmi_remove(struct platform_device *pdev) +{ + struct snd_dw_hdmi *dw = platform_get_drvdata(pdev); + + platform_device_unregister(dw->audio_pdev); + + return 0; +} + +static struct platform_driver snd_dw_hdmi_driver = { + .probe = snd_dw_hdmi_probe, + .remove = snd_dw_hdmi_remove, + .driver = { + .name = DRIVER_NAME, + }, +}; + +module_platform_driver(snd_dw_hdmi_driver); + +MODULE_AUTHOR("Shengjiu Wang <shengjiu.wang@nxp.com>"); +MODULE_DESCRIPTION("Synopsys Designware HDMI GPA ALSA interface"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:" DRIVER_NAME); diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index 4befc104d220..f3f82a04c252 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -191,7 +191,10 @@ struct dw_hdmi { spinlock_t audio_lock; struct mutex audio_mutex; + unsigned int sample_non_pcm; + unsigned int sample_width; unsigned int sample_rate; + unsigned int channels; unsigned int audio_cts; unsigned int audio_n; bool audio_enable; @@ -589,6 +592,8 @@ static unsigned int hdmi_compute_n(unsigned int freq, unsigned long pixel_clk) n = 4096; else if (pixel_clk == 74176000 || pixel_clk == 148352000) n = 11648; + else if (pixel_clk == 297000000) + n = 3072; else n = 4096; n *= mult; @@ -601,6 +606,8 @@ static unsigned int hdmi_compute_n(unsigned int freq, unsigned long pixel_clk) n = 17836; else if (pixel_clk == 148352000) n = 8918; + else if (pixel_clk == 297000000) + n = 4704; else n = 6272; n *= mult; @@ -615,6 +622,8 @@ static unsigned int hdmi_compute_n(unsigned int freq, unsigned long pixel_clk) n = 11648; else if (pixel_clk == 148352000) n = 5824; + else if (pixel_clk == 297000000) + n = 5120; else n = 6144; n *= mult; @@ -659,8 +668,8 @@ static void hdmi_set_clk_regenerator(struct dw_hdmi *hdmi, config3 = hdmi_readb(hdmi, HDMI_CONFIG3_ID); - /* Only compute CTS when using internal AHB audio */ - if (config3 & HDMI_CONFIG3_AHBAUDDMA) { + /* Compute CTS when using internal AHB audio or General Parallel audio*/ + if ((config3 & HDMI_CONFIG3_AHBAUDDMA) || (config3 & HDMI_CONFIG3_GPAUD)) { /* * Compute the CTS value from the N value. Note that CTS and N * can be up to 20 bits in total, so we need 64-bit math. Also @@ -702,6 +711,22 @@ static void hdmi_clk_regenerator_update_pixel_clock(struct dw_hdmi *hdmi) mutex_unlock(&hdmi->audio_mutex); } +void dw_hdmi_set_sample_width(struct dw_hdmi *hdmi, unsigned int width) +{ + mutex_lock(&hdmi->audio_mutex); + hdmi->sample_width = width; + mutex_unlock(&hdmi->audio_mutex); +} +EXPORT_SYMBOL_GPL(dw_hdmi_set_sample_width); + +void dw_hdmi_set_sample_non_pcm(struct dw_hdmi *hdmi, unsigned int non_pcm) +{ + mutex_lock(&hdmi->audio_mutex); + hdmi->sample_non_pcm = non_pcm; + mutex_unlock(&hdmi->audio_mutex); +} +EXPORT_SYMBOL_GPL(dw_hdmi_set_sample_non_pcm); + void dw_hdmi_set_sample_rate(struct dw_hdmi *hdmi, unsigned int rate) { mutex_lock(&hdmi->audio_mutex); @@ -717,6 +742,7 @@ void dw_hdmi_set_channel_count(struct dw_hdmi *hdmi, unsigned int cnt) u8 layout; mutex_lock(&hdmi->audio_mutex); + hdmi->channels = cnt; /* * For >2 channel PCM audio, we need to select layout 1 @@ -765,6 +791,89 @@ static u8 *hdmi_audio_get_eld(struct dw_hdmi *hdmi) return hdmi->curr_conn->eld; } +static void dw_hdmi_gp_audio_enable(struct dw_hdmi *hdmi) +{ + const struct dw_hdmi_plat_data *pdata = hdmi->plat_data; + int sample_freq = 0x2, org_sample_freq = 0xD; + int ch_mask = BIT(hdmi->channels) - 1; + + switch (hdmi->sample_rate) { + case 32000: + sample_freq = 0x03; + org_sample_freq = 0x0C; + break; + case 44100: + sample_freq = 0x00; + org_sample_freq = 0x0F; + break; + case 48000: + sample_freq = 0x02; + org_sample_freq = 0x0D; + break; + case 88200: + sample_freq = 0x08; + org_sample_freq = 0x07; + break; + case 96000: + sample_freq = 0x0A; + org_sample_freq = 0x05; + break; + case 176400: + sample_freq = 0x0C; + org_sample_freq = 0x03; + break; + case 192000: + sample_freq = 0x0E; + org_sample_freq = 0x01; + break; + default: + break; + } + + hdmi_set_cts_n(hdmi, hdmi->audio_cts, hdmi->audio_n); + hdmi_enable_audio_clk(hdmi, true); + + hdmi_writeb(hdmi, 0x1, HDMI_FC_AUDSCHNLS0); + hdmi_writeb(hdmi, hdmi->channels, HDMI_FC_AUDSCHNLS2); + hdmi_writeb(hdmi, 0x22, HDMI_FC_AUDSCHNLS3); + hdmi_writeb(hdmi, 0x22, HDMI_FC_AUDSCHNLS4); + hdmi_writeb(hdmi, 0x11, HDMI_FC_AUDSCHNLS5); + hdmi_writeb(hdmi, 0x11, HDMI_FC_AUDSCHNLS6); + hdmi_writeb(hdmi, (0x3 << 4) | sample_freq, HDMI_FC_AUDSCHNLS7); + hdmi_writeb(hdmi, (org_sample_freq << 4) | 0xb, HDMI_FC_AUDSCHNLS8); + + hdmi_writeb(hdmi, ch_mask, HDMI_GP_CONF1); + hdmi_writeb(hdmi, 0x02, HDMI_GP_CONF2); + hdmi_writeb(hdmi, 0x01, HDMI_GP_CONF0); + + hdmi_modb(hdmi, 0x3, 0x3, HDMI_FC_DATAUTO3); + + /* hbr */ + if (hdmi->sample_rate == 192000 && hdmi->channels == 8 && + hdmi->sample_width == 32 && hdmi->sample_non_pcm) + hdmi_modb(hdmi, 0x01, 0x01, HDMI_GP_CONF2); + + if (pdata->enable_audio) + pdata->enable_audio(hdmi, + hdmi->channels, + hdmi->sample_width, + hdmi->sample_rate, + hdmi->sample_non_pcm); +} + +static void dw_hdmi_gp_audio_disable(struct dw_hdmi *hdmi) +{ + const struct dw_hdmi_plat_data *pdata = hdmi->plat_data; + + hdmi_set_cts_n(hdmi, hdmi->audio_cts, 0); + + hdmi_modb(hdmi, 0, 0x3, HDMI_FC_DATAUTO3); + if (pdata->disable_audio) + pdata->disable_audio(hdmi); + + hdmi_enable_audio_clk(hdmi, false); +} + static void dw_hdmi_ahb_audio_enable(struct dw_hdmi *hdmi) { hdmi_set_cts_n(hdmi, hdmi->audio_cts, hdmi->audio_n); @@ -1108,6 +1217,8 @@ static void hdmi_video_packetize(struct dw_hdmi *hdmi) unsigned int output_select = HDMI_VP_CONF_OUTPUT_SELECTOR_PP; struct hdmi_data_info *hdmi_data = &hdmi->hdmi_data; u8 val, vp_conf; + u8 clear_gcp_auto = 0; + if (hdmi_bus_fmt_is_rgb(hdmi->hdmi_data.enc_out_bus_format) || hdmi_bus_fmt_is_yuv444(hdmi->hdmi_data.enc_out_bus_format) || @@ -1117,6 +1228,7 @@ static void hdmi_video_packetize(struct dw_hdmi *hdmi) case 8: color_depth = 4; output_select = HDMI_VP_CONF_OUTPUT_SELECTOR_BYPASS; + clear_gcp_auto = 1; break; case 10: color_depth = 5; @@ -1136,6 +1248,7 @@ static void hdmi_video_packetize(struct dw_hdmi *hdmi) case 0: case 8: remap_size = HDMI_VP_REMAP_YCC422_16bit; + clear_gcp_auto = 1; break; case 10: remap_size = HDMI_VP_REMAP_YCC422_20bit; @@ -1160,6 +1273,19 @@ static void hdmi_video_packetize(struct dw_hdmi *hdmi) HDMI_VP_PR_CD_DESIRED_PR_FACTOR_MASK); hdmi_writeb(hdmi, val, HDMI_VP_PR_CD); + /* HDMI1.4b specification section 6.5.3: + * Source shall only send GCPs with non-zero CD to sinks + * that indicate support for Deep Color. + * GCP only transmit CD and do not handle AVMUTE, PP norDefault_Phase (yet). + * Disable Auto GCP when 24-bit color for sinks that not support Deep Color. + */ + val = hdmi_readb(hdmi, HDMI_FC_DATAUTO3); + if (clear_gcp_auto == 1) + val &= ~HDMI_FC_DATAUTO3_GCP_AUTO; + else + val |= HDMI_FC_DATAUTO3_GCP_AUTO; + hdmi_writeb(hdmi, val, HDMI_FC_DATAUTO3); + hdmi_modb(hdmi, HDMI_VP_STUFF_PR_STUFFING_STUFFING_MODE, HDMI_VP_STUFF_PR_STUFFING_MASK, HDMI_VP_STUFF); @@ -1357,13 +1483,21 @@ static void dw_hdmi_phy_sel_interface_control(struct dw_hdmi *hdmi, u8 enable) HDMI_PHY_CONF0_SELDIPIF_MASK); } -void dw_hdmi_phy_reset(struct dw_hdmi *hdmi) +void dw_hdmi_phy_gen1_reset(struct dw_hdmi *hdmi) +{ + /* PHY reset. The reset signal is active low on Gen1 PHYs. */ + hdmi_writeb(hdmi, 0, HDMI_MC_PHYRSTZ); + hdmi_writeb(hdmi, HDMI_MC_PHYRSTZ_PHYRSTZ, HDMI_MC_PHYRSTZ); +} +EXPORT_SYMBOL_GPL(dw_hdmi_phy_gen1_reset); + +void dw_hdmi_phy_gen2_reset(struct dw_hdmi *hdmi) { /* PHY reset. The reset signal is active high on Gen2 PHYs. */ hdmi_writeb(hdmi, HDMI_MC_PHYRSTZ_PHYRSTZ, HDMI_MC_PHYRSTZ); hdmi_writeb(hdmi, 0, HDMI_MC_PHYRSTZ); } -EXPORT_SYMBOL_GPL(dw_hdmi_phy_reset); +EXPORT_SYMBOL_GPL(dw_hdmi_phy_gen2_reset); void dw_hdmi_phy_i2c_set_addr(struct dw_hdmi *hdmi, u8 address) { @@ -1517,7 +1651,7 @@ static int hdmi_phy_configure(struct dw_hdmi *hdmi, if (phy->has_svsret) dw_hdmi_phy_enable_svsret(hdmi, 1); - dw_hdmi_phy_reset(hdmi); + dw_hdmi_phy_gen2_reset(hdmi); hdmi_writeb(hdmi, HDMI_MC_HEACPHY_RST_ASSERT, HDMI_MC_HEACPHY_RST); @@ -2086,30 +2220,21 @@ static void dw_hdmi_clear_overflow(struct dw_hdmi *hdmi) * then write one of the FC registers several times. * * The number of iterations matters and depends on the HDMI TX revision - * (and possibly on the platform). So far i.MX6Q (v1.30a), i.MX6DL - * (v1.31a) and multiple Allwinner SoCs (v1.32a) have been identified - * as needing the workaround, with 4 iterations for v1.30a and 1 - * iteration for others. - * The Amlogic Meson GX SoCs (v2.01a) have been identified as needing - * the workaround with a single iteration. - * The Rockchip RK3288 SoC (v2.00a) and RK3328/RK3399 SoCs (v2.11a) have - * been identified as needing the workaround with a single iteration. + * (and possibly on the platform). + * 4 iterations for i.MX6Q(v1.30a) and 1 iteration for others. + * i.MX6DL (v1.31a), Allwinner SoCs (v1.32a), Rockchip RK3288 SoC (v2.00a), + * Amlogic Meson GX SoCs (v2.01a), RK3328/RK3399 SoCs (v2.11a) + * and i.MX8MPlus (v2.13a) have been identified as needing the workaround + * with a single iteration. */ switch (hdmi->version) { case 0x130a: count = 4; break; - case 0x131a: - case 0x132a: - case 0x200a: - case 0x201a: - case 0x211a: - case 0x212a: + default: count = 1; break; - default: - return; } /* TMDS software reset */ @@ -2830,7 +2955,7 @@ static void dw_hdmi_bridge_mode_set(struct drm_bridge *bridge, mutex_lock(&hdmi->mutex); /* Store the display mode for plugin/DKMS poweron events */ - memcpy(&hdmi->previous_mode, mode, sizeof(hdmi->previous_mode)); + drm_mode_copy(&hdmi->previous_mode, mode); mutex_unlock(&hdmi->mutex); } @@ -3242,6 +3367,7 @@ struct dw_hdmi *dw_hdmi_probe(struct platform_device *pdev, hdmi->plat_data = plat_data; hdmi->dev = dev; hdmi->sample_rate = 48000; + hdmi->channels = 2; hdmi->disabled = true; hdmi->rxsense = true; hdmi->phy_mask = (u8)~(HDMI_PHY_HPD | HDMI_PHY_RX_SENSE); @@ -3465,6 +3591,24 @@ struct dw_hdmi *dw_hdmi_probe(struct platform_device *pdev, pdevinfo.size_data = sizeof(audio); pdevinfo.dma_mask = DMA_BIT_MASK(32); hdmi->audio = platform_device_register_full(&pdevinfo); + } else if (iores && config3 & HDMI_CONFIG3_GPAUD) { + struct dw_hdmi_audio_data audio; + + audio.phys = iores->start; + audio.base = hdmi->regs; + audio.irq = irq; + audio.hdmi = hdmi; + audio.get_eld = hdmi_audio_get_eld; + + hdmi->enable_audio = dw_hdmi_gp_audio_enable; + hdmi->disable_audio = dw_hdmi_gp_audio_disable; + + pdevinfo.name = "dw-hdmi-gp-audio"; + pdevinfo.id = PLATFORM_DEVID_NONE; + pdevinfo.data = &audio; + pdevinfo.size_data = sizeof(audio); + pdevinfo.dma_mask = DMA_BIT_MASK(32); + hdmi->audio = platform_device_register_full(&pdevinfo); } if (!plat_data->disable_cec && (config0 & HDMI_CONFIG0_CEC)) { diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.h b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.h index 1999db05bc3b..af43a0414b78 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.h +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.h @@ -158,8 +158,17 @@ #define HDMI_FC_SPDDEVICEINF 0x1062 #define HDMI_FC_AUDSCONF 0x1063 #define HDMI_FC_AUDSSTAT 0x1064 -#define HDMI_FC_AUDSCHNLS7 0x106e -#define HDMI_FC_AUDSCHNLS8 0x106f +#define HDMI_FC_AUDSV 0x1065 +#define HDMI_FC_AUDSU 0x1066 +#define HDMI_FC_AUDSCHNLS0 0x1067 +#define HDMI_FC_AUDSCHNLS1 0x1068 +#define HDMI_FC_AUDSCHNLS2 0x1069 +#define HDMI_FC_AUDSCHNLS3 0x106A +#define HDMI_FC_AUDSCHNLS4 0x106B +#define HDMI_FC_AUDSCHNLS5 0x106C +#define HDMI_FC_AUDSCHNLS6 0x106D +#define HDMI_FC_AUDSCHNLS7 0x106E +#define HDMI_FC_AUDSCHNLS8 0x106F #define HDMI_FC_DATACH0FILL 0x1070 #define HDMI_FC_DATACH1FILL 0x1071 #define HDMI_FC_DATACH2FILL 0x1072 @@ -850,6 +859,9 @@ enum { HDMI_FC_DATAUTO0_VSD_MASK = 0x08, HDMI_FC_DATAUTO0_VSD_OFFSET = 3, +/* FC_DATAUTO3 field values */ + HDMI_FC_DATAUTO3_GCP_AUTO = 0x04, + /* PHY_CONF0 field values */ HDMI_PHY_CONF0_PDZ_MASK = 0x80, HDMI_PHY_CONF0_PDZ_OFFSET = 7, diff --git a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c index 11d20b8638cd..b2efecf7d160 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c @@ -246,7 +246,6 @@ struct dw_mipi_dsi { struct clk *pclk; - bool device_found; unsigned int lane_mbps; /* per lane */ u32 channel; u32 lanes; @@ -310,37 +309,12 @@ static inline u32 dsi_read(struct dw_mipi_dsi *dsi, u32 reg) return readl(dsi->base + reg); } -static int dw_mipi_dsi_panel_or_bridge(struct dw_mipi_dsi *dsi, - struct device_node *node) -{ - struct drm_bridge *bridge; - struct drm_panel *panel; - int ret; - - ret = drm_of_find_panel_or_bridge(node, 1, 0, &panel, &bridge); - if (ret) - return ret; - - if (panel) { - bridge = drm_panel_bridge_add_typed(panel, - DRM_MODE_CONNECTOR_DSI); - if (IS_ERR(bridge)) - return PTR_ERR(bridge); - } - - dsi->panel_bridge = bridge; - - if (!dsi->panel_bridge) - return -EPROBE_DEFER; - - return 0; -} - static int dw_mipi_dsi_host_attach(struct mipi_dsi_host *host, struct mipi_dsi_device *device) { struct dw_mipi_dsi *dsi = host_to_dsi(host); const struct dw_mipi_dsi_plat_data *pdata = dsi->plat_data; + struct drm_bridge *bridge; int ret; if (device->lanes > dsi->plat_data->max_data_lanes) { @@ -354,13 +328,13 @@ static int dw_mipi_dsi_host_attach(struct mipi_dsi_host *host, dsi->format = device->format; dsi->mode_flags = device->mode_flags; - if (!dsi->device_found) { - ret = dw_mipi_dsi_panel_or_bridge(dsi, host->dev->of_node); - if (ret) - return ret; + bridge = devm_drm_of_get_bridge(dsi->dev, dsi->dev->of_node, 1, 0); + if (IS_ERR(bridge)) + return PTR_ERR(bridge); - dsi->device_found = true; - } + dsi->panel_bridge = bridge; + + drm_bridge_add(&dsi->bridge); if (pdata->host_ops && pdata->host_ops->attach) { ret = pdata->host_ops->attach(pdata->priv_data, device); @@ -1021,16 +995,6 @@ static int dw_mipi_dsi_bridge_attach(struct drm_bridge *bridge, /* Set the encoder type as caller does not know it */ bridge->encoder->encoder_type = DRM_MODE_ENCODER_DSI; - if (!dsi->device_found) { - int ret; - - ret = dw_mipi_dsi_panel_or_bridge(dsi, dsi->dev->of_node); - if (ret) - return ret; - - dsi->device_found = true; - } - /* Attach the panel-bridge to the dsi bridge */ return drm_bridge_attach(bridge->encoder, dsi->panel_bridge, bridge, flags); @@ -1217,7 +1181,6 @@ __dw_mipi_dsi_probe(struct platform_device *pdev, #ifdef CONFIG_OF dsi->bridge.of_node = pdev->dev.of_node; #endif - drm_bridge_add(&dsi->bridge); return dsi; } diff --git a/drivers/gpu/drm/bridge/tc358762.c b/drivers/gpu/drm/bridge/tc358762.c index 1bfdfc6affaf..7870aceb0a6d 100644 --- a/drivers/gpu/drm/bridge/tc358762.c +++ b/drivers/gpu/drm/bridge/tc358762.c @@ -179,15 +179,8 @@ static int tc358762_parse_dt(struct tc358762 *ctx) { struct drm_bridge *panel_bridge; struct device *dev = ctx->dev; - struct drm_panel *panel; - int ret; - - ret = drm_of_find_panel_or_bridge(dev->of_node, 1, 0, &panel, NULL); - if (ret) - return ret; - - panel_bridge = devm_drm_panel_bridge_add(dev, panel); + panel_bridge = devm_drm_of_get_bridge(dev, dev->of_node, 1, 0); if (IS_ERR(panel_bridge)) return PTR_ERR(panel_bridge); diff --git a/drivers/gpu/drm/bridge/tc358764.c b/drivers/gpu/drm/bridge/tc358764.c index c1e35bdf9232..dca41ed32f8a 100644 --- a/drivers/gpu/drm/bridge/tc358764.c +++ b/drivers/gpu/drm/bridge/tc358764.c @@ -16,14 +16,9 @@ #include <video/mipi_display.h> #include <drm/drm_atomic_helper.h> -#include <drm/drm_bridge.h> -#include <drm/drm_crtc.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_mipi_dsi.h> #include <drm/drm_of.h> -#include <drm/drm_panel.h> #include <drm/drm_print.h> -#include <drm/drm_probe_helper.h> #define FLD_MASK(start, end) (((1 << ((start) - (end) + 1)) - 1) << (end)) #define FLD_VAL(val, start, end) (((val) << (end)) & FLD_MASK(start, end)) @@ -153,10 +148,9 @@ static const char * const tc358764_supplies[] = { struct tc358764 { struct device *dev; struct drm_bridge bridge; - struct drm_connector connector; + struct drm_bridge *next_bridge; struct regulator_bulk_data supplies[ARRAY_SIZE(tc358764_supplies)]; struct gpio_desc *gpio_reset; - struct drm_panel *panel; int error; }; @@ -210,12 +204,6 @@ static inline struct tc358764 *bridge_to_tc358764(struct drm_bridge *bridge) return container_of(bridge, struct tc358764, bridge); } -static inline -struct tc358764 *connector_to_tc358764(struct drm_connector *connector) -{ - return container_of(connector, struct tc358764, connector); -} - static int tc358764_init(struct tc358764 *ctx) { u32 v = 0; @@ -278,43 +266,11 @@ static void tc358764_reset(struct tc358764 *ctx) usleep_range(1000, 2000); } -static int tc358764_get_modes(struct drm_connector *connector) -{ - struct tc358764 *ctx = connector_to_tc358764(connector); - - return drm_panel_get_modes(ctx->panel, connector); -} - -static const -struct drm_connector_helper_funcs tc358764_connector_helper_funcs = { - .get_modes = tc358764_get_modes, -}; - -static const struct drm_connector_funcs tc358764_connector_funcs = { - .fill_modes = drm_helper_probe_single_connector_modes, - .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, -}; - -static void tc358764_disable(struct drm_bridge *bridge) -{ - struct tc358764 *ctx = bridge_to_tc358764(bridge); - int ret = drm_panel_disable(bridge_to_tc358764(bridge)->panel); - - if (ret < 0) - dev_err(ctx->dev, "error disabling panel (%d)\n", ret); -} - static void tc358764_post_disable(struct drm_bridge *bridge) { struct tc358764 *ctx = bridge_to_tc358764(bridge); int ret; - ret = drm_panel_unprepare(ctx->panel); - if (ret < 0) - dev_err(ctx->dev, "error unpreparing panel (%d)\n", ret); tc358764_reset(ctx); usleep_range(10000, 15000); ret = regulator_bulk_disable(ARRAY_SIZE(ctx->supplies), ctx->supplies); @@ -335,72 +291,25 @@ static void tc358764_pre_enable(struct drm_bridge *bridge) ret = tc358764_init(ctx); if (ret < 0) dev_err(ctx->dev, "error initializing bridge (%d)\n", ret); - ret = drm_panel_prepare(ctx->panel); - if (ret < 0) - dev_err(ctx->dev, "error preparing panel (%d)\n", ret); -} - -static void tc358764_enable(struct drm_bridge *bridge) -{ - struct tc358764 *ctx = bridge_to_tc358764(bridge); - int ret = drm_panel_enable(ctx->panel); - - if (ret < 0) - dev_err(ctx->dev, "error enabling panel (%d)\n", ret); } static int tc358764_attach(struct drm_bridge *bridge, enum drm_bridge_attach_flags flags) { struct tc358764 *ctx = bridge_to_tc358764(bridge); - struct drm_device *drm = bridge->dev; - int ret; - - if (flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR) { - DRM_ERROR("Fix bridge driver to make connector optional!"); - return -EINVAL; - } - - ctx->connector.polled = DRM_CONNECTOR_POLL_HPD; - ret = drm_connector_init(drm, &ctx->connector, - &tc358764_connector_funcs, - DRM_MODE_CONNECTOR_LVDS); - if (ret) { - DRM_ERROR("Failed to initialize connector\n"); - return ret; - } - - drm_connector_helper_add(&ctx->connector, - &tc358764_connector_helper_funcs); - drm_connector_attach_encoder(&ctx->connector, bridge->encoder); - ctx->connector.funcs->reset(&ctx->connector); - drm_connector_register(&ctx->connector); - - return 0; -} - -static void tc358764_detach(struct drm_bridge *bridge) -{ - struct tc358764 *ctx = bridge_to_tc358764(bridge); - drm_connector_unregister(&ctx->connector); - ctx->panel = NULL; - drm_connector_put(&ctx->connector); + return drm_bridge_attach(bridge->encoder, ctx->next_bridge, bridge, flags); } static const struct drm_bridge_funcs tc358764_bridge_funcs = { - .disable = tc358764_disable, .post_disable = tc358764_post_disable, - .enable = tc358764_enable, .pre_enable = tc358764_pre_enable, .attach = tc358764_attach, - .detach = tc358764_detach, }; static int tc358764_parse_dt(struct tc358764 *ctx) { struct device *dev = ctx->dev; - int ret; ctx->gpio_reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); if (IS_ERR(ctx->gpio_reset)) { @@ -408,12 +317,11 @@ static int tc358764_parse_dt(struct tc358764 *ctx) return PTR_ERR(ctx->gpio_reset); } - ret = drm_of_find_panel_or_bridge(ctx->dev->of_node, 1, 0, &ctx->panel, - NULL); - if (ret && ret != -EPROBE_DEFER) - dev_err(dev, "cannot find panel (%d)\n", ret); + ctx->next_bridge = devm_drm_of_get_bridge(dev, dev->of_node, 1, 0); + if (IS_ERR(ctx->next_bridge)) + return PTR_ERR(ctx->next_bridge); - return ret; + return 0; } static int tc358764_configure_regulators(struct tc358764 *ctx) diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c index c23e0abc65e8..12355daf45ef 100644 --- a/drivers/gpu/drm/bridge/tc358767.c +++ b/drivers/gpu/drm/bridge/tc358767.c @@ -1,6 +1,12 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * tc358767 eDP bridge driver + * TC358767/TC358867/TC9595 DSI/DPI-to-DPI/(e)DP bridge driver + * + * The TC358767/TC358867/TC9595 can operate in multiple modes. + * The following modes are supported: + * DPI->(e)DP -- supported + * DSI->DPI .... supported + * DSI->(e)DP .. NOT supported * * Copyright (C) 2016 CogentEmbedded Inc * Author: Andrey Gusakov <andrey.gusakov@cogentembedded.com> @@ -29,6 +35,7 @@ #include <drm/drm_bridge.h> #include <drm/dp/drm_dp_helper.h> #include <drm/drm_edid.h> +#include <drm/drm_mipi_dsi.h> #include <drm/drm_of.h> #include <drm/drm_panel.h> #include <drm/drm_print.h> @@ -36,7 +43,35 @@ /* Registers */ -/* Display Parallel Interface */ +/* PPI layer registers */ +#define PPI_STARTPPI 0x0104 /* START control bit */ +#define PPI_LPTXTIMECNT 0x0114 /* LPTX timing signal */ +#define LPX_PERIOD 3 +#define PPI_LANEENABLE 0x0134 +#define PPI_TX_RX_TA 0x013c +#define TTA_GET 0x40000 +#define TTA_SURE 6 +#define PPI_D0S_ATMR 0x0144 +#define PPI_D1S_ATMR 0x0148 +#define PPI_D0S_CLRSIPOCOUNT 0x0164 /* Assertion timer for Lane 0 */ +#define PPI_D1S_CLRSIPOCOUNT 0x0168 /* Assertion timer for Lane 1 */ +#define PPI_D2S_CLRSIPOCOUNT 0x016c /* Assertion timer for Lane 2 */ +#define PPI_D3S_CLRSIPOCOUNT 0x0170 /* Assertion timer for Lane 3 */ +#define PPI_START_FUNCTION BIT(0) + +/* DSI layer registers */ +#define DSI_STARTDSI 0x0204 /* START control bit of DSI-TX */ +#define DSI_LANEENABLE 0x0210 /* Enables each lane */ +#define DSI_RX_START BIT(0) + +/* Lane enable PPI and DSI register bits */ +#define LANEENABLE_CLEN BIT(0) +#define LANEENABLE_L0EN BIT(1) +#define LANEENABLE_L1EN BIT(2) +#define LANEENABLE_L2EN BIT(1) +#define LANEENABLE_L3EN BIT(2) + +/* Display Parallel Input Interface */ #define DPIPXLFMT 0x0440 #define VS_POL_ACTIVE_LOW (1 << 10) #define HS_POL_ACTIVE_LOW (1 << 9) @@ -48,6 +83,14 @@ #define DPI_BPP_RGB666 (1 << 0) #define DPI_BPP_RGB565 (2 << 0) +/* Display Parallel Output Interface */ +#define POCTRL 0x0448 +#define POCTRL_S2P BIT(7) +#define POCTRL_PCLK_POL BIT(3) +#define POCTRL_VS_POL BIT(2) +#define POCTRL_HS_POL BIT(1) +#define POCTRL_DE_POL BIT(0) + /* Video Path */ #define VPCTRL0 0x0450 #define VSDELAY GENMASK(31, 20) @@ -247,6 +290,9 @@ struct tc_data { struct drm_bridge *panel_bridge; struct drm_connector connector; + struct mipi_dsi_device *dsi; + u8 dsi_lanes; + /* link settings */ struct tc_edp_link link; @@ -469,10 +515,24 @@ static int tc_pxl_pll_en(struct tc_data *tc, u32 refclk, u32 pixelclock) int mul, best_mul = 1; int delta, best_delta; int ext_div[] = {1, 2, 3, 5, 7}; + int clk_min, clk_max; int best_pixelclock = 0; int vco_hi = 0; u32 pxl_pllparam; + /* + * refclk * mul / (ext_pre_div * pre_div) should be in range: + * - DPI ..... 0 to 100 MHz + * - (e)DP ... 150 to 650 MHz + */ + if (tc->bridge.type == DRM_MODE_CONNECTOR_DPI) { + clk_min = 0; + clk_max = 100000000; + } else { + clk_min = 150000000; + clk_max = 650000000; + } + dev_dbg(tc->dev, "PLL: requested %d pixelclock, ref %d\n", pixelclock, refclk); best_delta = pixelclock; @@ -499,11 +559,7 @@ static int tc_pxl_pll_en(struct tc_data *tc, u32 refclk, u32 pixelclock) 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)) + if ((clk > clk_max) || (clk < clk_min)) continue; clk = clk / ext_div[i_post]; @@ -656,6 +712,12 @@ static int tc_aux_link_setup(struct tc_data *tc) if (ret) goto err; + /* Register DP AUX channel */ + tc->aux.name = "TC358767 AUX i2c adapter"; + tc->aux.dev = tc->dev; + tc->aux.transfer = tc_aux_transfer; + drm_dp_aux_init(&tc->aux); + return 0; err: dev_err(tc->dev, "tc_aux_link_setup failed: %d\n", ret); @@ -728,33 +790,16 @@ err_dpcd_read: return ret; } -static int tc_set_video_mode(struct tc_data *tc, - const struct drm_display_mode *mode) +static int tc_set_common_video_mode(struct tc_data *tc, + const 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; - u32 dp0_syncval; - u32 bits_per_pixel = 24; - u32 in_bw, out_bw; - - /* - * 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. - */ - - in_bw = mode->clock * bits_per_pixel / 8; - out_bw = tc->link.num_lanes * tc->link.rate; - max_tu_symbol = DIV_ROUND_UP(in_bw * TU_SIZE_RECOMMENDED, out_bw); + int ret; dev_dbg(tc->dev, "set mode %dx%d\n", mode->hdisplay, mode->vdisplay); @@ -812,8 +857,49 @@ static int tc_set_video_mode(struct tc_data *tc, FIELD_PREP(COLOR_B, 99) | ENI2CFILTER | FIELD_PREP(COLOR_BAR_MODE, COLOR_BAR_MODE_BARS)); - if (ret) - return ret; + + return ret; +} + +static int tc_set_dpi_video_mode(struct tc_data *tc, + const struct drm_display_mode *mode) +{ + u32 value = POCTRL_S2P; + + if (tc->mode.flags & DRM_MODE_FLAG_NHSYNC) + value |= POCTRL_HS_POL; + + if (tc->mode.flags & DRM_MODE_FLAG_NVSYNC) + value |= POCTRL_VS_POL; + + return regmap_write(tc->regmap, POCTRL, value); +} + +static int tc_set_edp_video_mode(struct tc_data *tc, + const struct drm_display_mode *mode) +{ + int ret; + int vid_sync_dly; + int max_tu_symbol; + + int left_margin = mode->htotal - mode->hsync_end; + int hsync_len = mode->hsync_end - mode->hsync_start; + int upper_margin = mode->vtotal - mode->vsync_end; + int vsync_len = mode->vsync_end - mode->vsync_start; + u32 dp0_syncval; + u32 bits_per_pixel = 24; + u32 in_bw, out_bw; + + /* + * 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. + */ + + in_bw = mode->clock * bits_per_pixel / 8; + out_bw = tc->link.num_lanes * tc->link.rate; + max_tu_symbol = DIV_ROUND_UP(in_bw * TU_SIZE_RECOMMENDED, out_bw); /* DP Main Stream Attributes */ vid_sync_dly = hsync_len + left_margin + mode->hdisplay; @@ -863,10 +949,7 @@ static int tc_set_video_mode(struct tc_data *tc, FIELD_PREP(MAX_TU_SYMBOL, max_tu_symbol) | FIELD_PREP(TU_SIZE, TU_SIZE_RECOMMENDED) | BPC_8); - if (ret) - return ret; - - return 0; + return ret; } static int tc_wait_link_training(struct tc_data *tc) @@ -1164,7 +1247,86 @@ static int tc_main_link_disable(struct tc_data *tc) return regmap_write(tc->regmap, DP0CTL, 0); } -static int tc_stream_enable(struct tc_data *tc) +static int tc_dpi_stream_enable(struct tc_data *tc) +{ + int ret; + u32 value; + + dev_dbg(tc->dev, "enable video stream\n"); + + /* Setup PLL */ + ret = tc_set_syspllparam(tc); + if (ret) + return ret; + + /* + * Initially PLLs are in bypass. Force PLL parameter update, + * disable PLL bypass, enable PLL + */ + ret = tc_pllupdate(tc, DP0_PLLCTRL); + if (ret) + return ret; + + ret = tc_pllupdate(tc, DP1_PLLCTRL); + if (ret) + return ret; + + /* Pixel PLL must always be enabled for DPI mode */ + ret = tc_pxl_pll_en(tc, clk_get_rate(tc->refclk), + 1000 * tc->mode.clock); + if (ret) + return ret; + + regmap_write(tc->regmap, PPI_D0S_CLRSIPOCOUNT, 3); + regmap_write(tc->regmap, PPI_D1S_CLRSIPOCOUNT, 3); + regmap_write(tc->regmap, PPI_D2S_CLRSIPOCOUNT, 3); + regmap_write(tc->regmap, PPI_D3S_CLRSIPOCOUNT, 3); + regmap_write(tc->regmap, PPI_D0S_ATMR, 0); + regmap_write(tc->regmap, PPI_D1S_ATMR, 0); + regmap_write(tc->regmap, PPI_TX_RX_TA, TTA_GET | TTA_SURE); + regmap_write(tc->regmap, PPI_LPTXTIMECNT, LPX_PERIOD); + + value = ((LANEENABLE_L0EN << tc->dsi_lanes) - LANEENABLE_L0EN) | + LANEENABLE_CLEN; + regmap_write(tc->regmap, PPI_LANEENABLE, value); + regmap_write(tc->regmap, DSI_LANEENABLE, value); + + ret = tc_set_common_video_mode(tc, &tc->mode); + if (ret) + return ret; + + ret = tc_set_dpi_video_mode(tc, &tc->mode); + if (ret) + return ret; + + /* Set input interface */ + value = DP0_AUDSRC_NO_INPUT; + if (tc_test_pattern) + value |= DP0_VIDSRC_COLOR_BAR; + else + value |= DP0_VIDSRC_DSI_RX; + ret = regmap_write(tc->regmap, SYSCTRL, value); + if (ret) + return ret; + + usleep_range(120, 150); + + regmap_write(tc->regmap, PPI_STARTPPI, PPI_START_FUNCTION); + regmap_write(tc->regmap, DSI_STARTDSI, DSI_RX_START); + + return 0; +} + +static int tc_dpi_stream_disable(struct tc_data *tc) +{ + dev_dbg(tc->dev, "disable video stream\n"); + + tc_pxl_pll_dis(tc); + + return 0; +} + +static int tc_edp_stream_enable(struct tc_data *tc) { int ret; u32 value; @@ -1179,7 +1341,11 @@ static int tc_stream_enable(struct tc_data *tc) return ret; } - ret = tc_set_video_mode(tc, &tc->mode); + ret = tc_set_common_video_mode(tc, &tc->mode); + if (ret) + return ret; + + ret = tc_set_edp_video_mode(tc, &tc->mode); if (ret) return ret; @@ -1219,7 +1385,7 @@ static int tc_stream_enable(struct tc_data *tc) return 0; } -static int tc_stream_disable(struct tc_data *tc) +static int tc_edp_stream_disable(struct tc_data *tc) { int ret; @@ -1234,7 +1400,37 @@ static int tc_stream_disable(struct tc_data *tc) return 0; } -static void tc_bridge_enable(struct drm_bridge *bridge) +static void +tc_dpi_bridge_atomic_enable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) + +{ + struct tc_data *tc = bridge_to_tc(bridge); + int ret; + + ret = tc_dpi_stream_enable(tc); + if (ret < 0) { + dev_err(tc->dev, "main link stream start error: %d\n", ret); + tc_main_link_disable(tc); + return; + } +} + +static void +tc_dpi_bridge_atomic_disable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) +{ + struct tc_data *tc = bridge_to_tc(bridge); + int ret; + + ret = tc_dpi_stream_disable(tc); + if (ret < 0) + dev_err(tc->dev, "main link stream stop error: %d\n", ret); +} + +static void +tc_edp_bridge_atomic_enable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) { struct tc_data *tc = bridge_to_tc(bridge); int ret; @@ -1251,7 +1447,7 @@ static void tc_bridge_enable(struct drm_bridge *bridge) return; } - ret = tc_stream_enable(tc); + ret = tc_edp_stream_enable(tc); if (ret < 0) { dev_err(tc->dev, "main link stream start error: %d\n", ret); tc_main_link_disable(tc); @@ -1259,12 +1455,14 @@ static void tc_bridge_enable(struct drm_bridge *bridge) } } -static void tc_bridge_disable(struct drm_bridge *bridge) +static void +tc_edp_bridge_atomic_disable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) { struct tc_data *tc = bridge_to_tc(bridge); int ret; - ret = tc_stream_disable(tc); + ret = tc_edp_stream_disable(tc); if (ret < 0) dev_err(tc->dev, "main link stream stop error: %d\n", ret); @@ -1285,9 +1483,57 @@ static bool tc_bridge_mode_fixup(struct drm_bridge *bridge, return true; } -static enum drm_mode_status tc_mode_valid(struct drm_bridge *bridge, - const struct drm_display_info *info, - const struct drm_display_mode *mode) +static int tc_common_atomic_check(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + const unsigned int max_khz) +{ + tc_bridge_mode_fixup(bridge, &crtc_state->mode, + &crtc_state->adjusted_mode); + + if (crtc_state->adjusted_mode.clock > max_khz) + return -EINVAL; + + return 0; +} + +static int tc_dpi_atomic_check(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) +{ + /* DSI->DPI interface clock limitation: upto 100 MHz */ + return tc_common_atomic_check(bridge, bridge_state, crtc_state, + conn_state, 100000); +} + +static int tc_edp_atomic_check(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state) +{ + /* DPI->(e)DP interface clock limitation: upto 154 MHz */ + return tc_common_atomic_check(bridge, bridge_state, crtc_state, + conn_state, 154000); +} + +static enum drm_mode_status +tc_dpi_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + /* DPI interface clock limitation: upto 100 MHz */ + if (mode->clock > 100000) + return MODE_CLOCK_HIGH; + + return MODE_OK; +} + +static enum drm_mode_status +tc_edp_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) { struct tc_data *tc = bridge_to_tc(bridge); u32 req, avail; @@ -1312,7 +1558,7 @@ static void tc_bridge_mode_set(struct drm_bridge *bridge, { struct tc_data *tc = bridge_to_tc(bridge); - tc->mode = *mode; + drm_mode_copy(&tc->mode, mode); } static struct edid *tc_get_edid(struct drm_bridge *bridge, @@ -1395,8 +1641,20 @@ static const struct drm_connector_funcs tc_connector_funcs = { .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; -static int tc_bridge_attach(struct drm_bridge *bridge, - enum drm_bridge_attach_flags flags) +static int tc_dpi_bridge_attach(struct drm_bridge *bridge, + enum drm_bridge_attach_flags flags) +{ + struct tc_data *tc = bridge_to_tc(bridge); + + if (!tc->panel_bridge) + return 0; + + return drm_bridge_attach(tc->bridge.encoder, tc->panel_bridge, + &tc->bridge, flags); +} + +static int tc_edp_bridge_attach(struct drm_bridge *bridge, + enum drm_bridge_attach_flags flags) { u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24; struct tc_data *tc = bridge_to_tc(bridge); @@ -1448,21 +1706,64 @@ aux_unregister: return ret; } -static void tc_bridge_detach(struct drm_bridge *bridge) +static void tc_edp_bridge_detach(struct drm_bridge *bridge) { drm_dp_aux_unregister(&bridge_to_tc(bridge)->aux); } -static const struct drm_bridge_funcs tc_bridge_funcs = { - .attach = tc_bridge_attach, - .detach = tc_bridge_detach, - .mode_valid = tc_mode_valid, +#define MAX_INPUT_SEL_FORMATS 1 + +static u32 * +tc_dpi_atomic_get_input_bus_fmts(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + u32 output_fmt, + unsigned int *num_input_fmts) +{ + u32 *input_fmts; + + *num_input_fmts = 0; + + input_fmts = kcalloc(MAX_INPUT_SEL_FORMATS, sizeof(*input_fmts), + GFP_KERNEL); + if (!input_fmts) + return NULL; + + /* This is the DSI-end bus format */ + input_fmts[0] = MEDIA_BUS_FMT_RGB888_1X24; + *num_input_fmts = 1; + + return input_fmts; +} + +static const struct drm_bridge_funcs tc_dpi_bridge_funcs = { + .attach = tc_dpi_bridge_attach, + .mode_valid = tc_dpi_mode_valid, .mode_set = tc_bridge_mode_set, - .enable = tc_bridge_enable, - .disable = tc_bridge_disable, + .atomic_check = tc_dpi_atomic_check, + .atomic_enable = tc_dpi_bridge_atomic_enable, + .atomic_disable = tc_dpi_bridge_atomic_disable, + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, + .atomic_reset = drm_atomic_helper_bridge_reset, + .atomic_get_input_bus_fmts = tc_dpi_atomic_get_input_bus_fmts, +}; + +static const struct drm_bridge_funcs tc_edp_bridge_funcs = { + .attach = tc_edp_bridge_attach, + .detach = tc_edp_bridge_detach, + .mode_valid = tc_edp_mode_valid, + .mode_set = tc_bridge_mode_set, + .atomic_check = tc_edp_atomic_check, + .atomic_enable = tc_edp_bridge_atomic_enable, + .atomic_disable = tc_edp_bridge_atomic_disable, .mode_fixup = tc_bridge_mode_fixup, .detect = tc_bridge_detect, .get_edid = tc_get_edid, + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, + .atomic_reset = drm_atomic_helper_bridge_reset, }; static bool tc_readable_reg(struct device *dev, unsigned int reg) @@ -1549,18 +1850,87 @@ static irqreturn_t tc_irq_handler(int irq, void *arg) return IRQ_HANDLED; } -static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id) +static int tc_mipi_dsi_host_attach(struct tc_data *tc) { - struct device *dev = &client->dev; + struct device *dev = tc->dev; + struct device_node *host_node; + struct device_node *endpoint; + struct mipi_dsi_device *dsi; + struct mipi_dsi_host *host; + const struct mipi_dsi_device_info info = { + .type = "tc358767", + .channel = 0, + .node = NULL, + }; + int dsi_lanes, ret; + + endpoint = of_graph_get_endpoint_by_regs(dev->of_node, 0, -1); + dsi_lanes = of_property_count_u32_elems(endpoint, "data-lanes"); + host_node = of_graph_get_remote_port_parent(endpoint); + host = of_find_mipi_dsi_host_by_node(host_node); + of_node_put(host_node); + of_node_put(endpoint); + + if (dsi_lanes < 0 || dsi_lanes > 4) + return -EINVAL; + + if (!host) + return -EPROBE_DEFER; + + dsi = mipi_dsi_device_register_full(host, &info); + if (IS_ERR(dsi)) + return dev_err_probe(dev, PTR_ERR(dsi), + "failed to create dsi device\n"); + + tc->dsi = dsi; + + tc->dsi_lanes = dsi_lanes; + dsi->lanes = tc->dsi_lanes; + dsi->format = MIPI_DSI_FMT_RGB888; + dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE; + + ret = mipi_dsi_attach(dsi); + if (ret < 0) { + dev_err(dev, "failed to attach dsi to host: %d\n", ret); + return ret; + } + + return 0; +} + +static int tc_probe_dpi_bridge_endpoint(struct tc_data *tc) +{ + struct device *dev = tc->dev; struct drm_panel *panel; - struct tc_data *tc; int ret; - tc = devm_kzalloc(dev, sizeof(*tc), GFP_KERNEL); - if (!tc) - return -ENOMEM; + /* port@1 is the DPI input/output port */ + ret = drm_of_find_panel_or_bridge(dev->of_node, 1, 0, &panel, NULL); + if (ret && ret != -ENODEV) + return ret; - tc->dev = dev; + if (panel) { + struct drm_bridge *panel_bridge; + + panel_bridge = devm_drm_panel_bridge_add(dev, panel); + if (IS_ERR(panel_bridge)) + return PTR_ERR(panel_bridge); + + tc->panel_bridge = panel_bridge; + tc->bridge.type = DRM_MODE_CONNECTOR_DPI; + tc->bridge.funcs = &tc_dpi_bridge_funcs; + + return 0; + } + + return ret; +} + +static int tc_probe_edp_bridge_endpoint(struct tc_data *tc) +{ + struct device *dev = tc->dev; + struct drm_panel *panel; + int ret; /* port@2 is the output port */ ret = drm_of_find_panel_or_bridge(dev->of_node, 2, 0, &panel, NULL); @@ -1580,6 +1950,74 @@ static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id) tc->bridge.type = DRM_MODE_CONNECTOR_DisplayPort; } + tc->bridge.funcs = &tc_edp_bridge_funcs; + if (tc->hpd_pin >= 0) + tc->bridge.ops |= DRM_BRIDGE_OP_DETECT; + tc->bridge.ops |= DRM_BRIDGE_OP_EDID; + + return ret; +} + +static int tc_probe_bridge_endpoint(struct tc_data *tc) +{ + struct device *dev = tc->dev; + struct of_endpoint endpoint; + struct device_node *node = NULL; + const u8 mode_dpi_to_edp = BIT(1) | BIT(2); + const u8 mode_dsi_to_edp = BIT(0) | BIT(2); + const u8 mode_dsi_to_dpi = BIT(0) | BIT(1); + u8 mode = 0; + + /* + * Determine bridge configuration. + * + * Port allocation: + * port@0 - DSI input + * port@1 - DPI input/output + * port@2 - eDP output + * + * Possible connections: + * DPI -> port@1 -> port@2 -> eDP :: [port@0 is not connected] + * DSI -> port@0 -> port@2 -> eDP :: [port@1 is not connected] + * DSI -> port@0 -> port@1 -> DPI :: [port@2 is not connected] + */ + + for_each_endpoint_of_node(dev->of_node, node) { + of_graph_parse_endpoint(node, &endpoint); + if (endpoint.port > 2) + return -EINVAL; + + mode |= BIT(endpoint.port); + } + + if (mode == mode_dpi_to_edp) + return tc_probe_edp_bridge_endpoint(tc); + else if (mode == mode_dsi_to_dpi) + return tc_probe_dpi_bridge_endpoint(tc); + else if (mode == mode_dsi_to_edp) + dev_warn(dev, "The mode DSI-to-(e)DP is not supported!\n"); + else + dev_warn(dev, "Invalid mode (0x%x) is not supported!\n", mode); + + return -EINVAL; +} + +static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id) +{ + struct device *dev = &client->dev; + struct tc_data *tc; + int ret; + + tc = devm_kzalloc(dev, sizeof(*tc), GFP_KERNEL); + if (!tc) + return -ENOMEM; + + tc->dev = dev; + + ret = tc_probe_bridge_endpoint(tc); + if (ret) + return ret; + /* Shut down GPIO is optional */ tc->sd_gpio = devm_gpiod_get_optional(dev, "shutdown", GPIOD_OUT_HIGH); if (IS_ERR(tc->sd_gpio)) @@ -1686,26 +2124,25 @@ static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id) } } - 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; - drm_dp_aux_init(&tc->aux); - - tc->bridge.funcs = &tc_bridge_funcs; - if (tc->hpd_pin >= 0) - tc->bridge.ops |= DRM_BRIDGE_OP_DETECT; - tc->bridge.ops |= DRM_BRIDGE_OP_EDID; + if (tc->bridge.type != DRM_MODE_CONNECTOR_DPI) { /* (e)DP output */ + ret = tc_aux_link_setup(tc); + if (ret) + return ret; + } tc->bridge.of_node = dev->of_node; drm_bridge_add(&tc->bridge); i2c_set_clientdata(client, tc); + if (tc->bridge.type == DRM_MODE_CONNECTOR_DPI) { /* DPI output */ + ret = tc_mipi_dsi_host_attach(tc); + if (ret) { + drm_bridge_remove(&tc->bridge); + return ret; + } + } + return 0; } diff --git a/drivers/gpu/drm/bridge/tc358775.c b/drivers/gpu/drm/bridge/tc358775.c index 695af3badcc7..b987e5ac80f0 100644 --- a/drivers/gpu/drm/bridge/tc358775.c +++ b/drivers/gpu/drm/bridge/tc358775.c @@ -649,7 +649,6 @@ static int tc_attach_host(struct tc_data *tc) static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct device *dev = &client->dev; - struct drm_panel *panel; struct tc_data *tc; int ret; @@ -660,14 +659,8 @@ static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id) tc->dev = dev; tc->i2c = client; - ret = drm_of_find_panel_or_bridge(dev->of_node, TC358775_LVDS_OUT0, - 0, &panel, NULL); - if (ret < 0) - return ret; - if (!panel) - return -ENODEV; - - tc->panel_bridge = devm_drm_panel_bridge_add(dev, panel); + tc->panel_bridge = devm_drm_of_get_bridge(dev, dev->of_node, + TC358775_LVDS_OUT0, 0); if (IS_ERR(tc->panel_bridge)) return PTR_ERR(tc->panel_bridge); diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index 19daaddd29a4..2831f0813c3a 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -488,6 +488,11 @@ static void sn65dsi83_atomic_enable(struct drm_bridge *bridge, /* Clear all errors that got asserted during initialization. */ regmap_read(ctx->regmap, REG_IRQ_STAT, &pval); regmap_write(ctx->regmap, REG_IRQ_STAT, pval); + + usleep_range(10000, 12000); + regmap_read(ctx->regmap, REG_IRQ_STAT, &pval); + if (pval) + dev_err(ctx->dev, "Unexpected link status 0x%02x\n", pval); } static void sn65dsi83_atomic_disable(struct drm_bridge *bridge, @@ -565,7 +570,6 @@ static int sn65dsi83_parse_dt(struct sn65dsi83 *ctx, enum sn65dsi83_model model) struct drm_bridge *panel_bridge; struct device *dev = ctx->dev; struct device_node *endpoint; - struct drm_panel *panel; int ret; endpoint = of_graph_get_endpoint_by_regs(dev->of_node, 0, 0); @@ -605,15 +609,10 @@ static int sn65dsi83_parse_dt(struct sn65dsi83 *ctx, enum sn65dsi83_model model) } } - ret = drm_of_find_panel_or_bridge(dev->of_node, 2, 0, &panel, &panel_bridge); - if (ret < 0) + panel_bridge = devm_drm_of_get_bridge(dev, dev->of_node, 2, 0); + if (IS_ERR(panel_bridge)) { + ret = PTR_ERR(panel_bridge); goto err_put_node; - if (panel) { - panel_bridge = devm_drm_panel_bridge_add(dev, panel); - if (IS_ERR(panel_bridge)) { - ret = PTR_ERR(panel_bridge); - goto err_put_node; - } } ctx->panel_bridge = panel_bridge; diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index fb6c588b0f71..28d91ea5f9fd 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -1188,15 +1188,9 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev, { struct ti_sn65dsi86 *pdata = dev_get_drvdata(adev->dev.parent); struct device_node *np = pdata->dev->of_node; - struct drm_panel *panel; int ret; - ret = drm_of_find_panel_or_bridge(np, 1, 0, &panel, NULL); - if (ret) - return dev_err_probe(&adev->dev, ret, - "could not find any panel node\n"); - - pdata->next_bridge = devm_drm_panel_bridge_add(pdata->dev, panel); + pdata->next_bridge = devm_drm_of_get_bridge(pdata->dev, np, 1, 0); if (IS_ERR(pdata->next_bridge)) { DRM_ERROR("failed to create panel bridge\n"); return PTR_ERR(pdata->next_bridge); diff --git a/drivers/gpu/drm/dp/drm_dp.c b/drivers/gpu/drm/dp/drm_dp.c index 580016a1b9eb..2a1f5ff6633c 100644 --- a/drivers/gpu/drm/dp/drm_dp.c +++ b/drivers/gpu/drm/dp/drm_dp.c @@ -528,6 +528,31 @@ unlock: } /** + * drm_dp_dpcd_probe() - probe a given DPCD address with a 1-byte read access + * @aux: DisplayPort AUX channel (SST) + * @offset: address of the register to probe + * + * Probe the provided DPCD address by reading 1 byte from it. The function can + * be used to trigger some side-effect the read access has, like waking up the + * sink, without the need for the read-out value. + * + * Returns 0 if the read access suceeded, or a negative error code on failure. + */ +int drm_dp_dpcd_probe(struct drm_dp_aux *aux, unsigned int offset) +{ + u8 buffer; + int ret; + + ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, offset, &buffer, 1); + WARN_ON(ret == 0); + + drm_dp_dump_access(aux, DP_AUX_NATIVE_READ, offset, &buffer, ret); + + return ret < 0 ? ret : 0; +} +EXPORT_SYMBOL(drm_dp_dpcd_probe); + +/** * drm_dp_dpcd_read() - read a series of bytes from the DPCD * @aux: DisplayPort AUX channel (SST or MST) * @offset: address of the (first) register to read @@ -559,10 +584,9 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, * monitor doesn't power down exactly after the throw away read. */ if (!aux->is_remote) { - ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, DP_DPCD_REV, - buffer, 1); - if (ret != 1) - goto out; + ret = drm_dp_dpcd_probe(aux, DP_DPCD_REV); + if (ret < 0) + return ret; } if (aux->is_remote) @@ -571,7 +595,6 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, offset, buffer, size); -out: drm_dp_dump_access(aux, DP_AUX_NATIVE_READ, offset, buffer, ret); return ret; } diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 88cd992df356..58c0283fb6b0 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -789,6 +789,8 @@ drm_atomic_private_obj_init(struct drm_device *dev, obj->state = state; obj->funcs = funcs; list_add_tail(&obj->head, &dev->mode_config.privobj_list); + + state->obj = obj; } EXPORT_SYMBOL(drm_atomic_private_obj_init); @@ -1423,8 +1425,12 @@ EXPORT_SYMBOL(drm_atomic_check_only); int drm_atomic_commit(struct drm_atomic_state *state) { struct drm_mode_config *config = &state->dev->mode_config; + struct drm_printer p = drm_info_printer(state->dev->dev); int ret; + if (drm_debug_enabled(DRM_UT_STATE)) + drm_atomic_print_new_state(state, &p); + ret = drm_atomic_check_only(state); if (ret) return ret; @@ -1632,6 +1638,15 @@ commit: } EXPORT_SYMBOL(__drm_atomic_helper_set_config); +static void drm_atomic_private_obj_print_state(struct drm_printer *p, + const struct drm_private_state *state) +{ + struct drm_private_obj *obj = state->obj; + + if (obj->funcs->atomic_print_state) + obj->funcs->atomic_print_state(p, state); +} + /** * drm_atomic_print_new_state - prints drm atomic state * @state: atomic configuration to check @@ -1652,6 +1667,8 @@ void drm_atomic_print_new_state(const struct drm_atomic_state *state, struct drm_crtc_state *crtc_state; struct drm_connector *connector; struct drm_connector_state *connector_state; + struct drm_private_obj *obj; + struct drm_private_state *obj_state; int i; if (!p) { @@ -1669,6 +1686,9 @@ void drm_atomic_print_new_state(const struct drm_atomic_state *state, for_each_new_connector_in_state(state, connector, connector_state, i) drm_atomic_connector_print_state(p, connector_state); + + for_each_new_private_obj_in_state(state, obj, obj_state, i) + drm_atomic_private_obj_print_state(p, obj_state); } EXPORT_SYMBOL(drm_atomic_print_new_state); diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c index 54d62fdb4ef9..c6394ba13b24 100644 --- a/drivers/gpu/drm/drm_atomic_uapi.c +++ b/drivers/gpu/drm/drm_atomic_uapi.c @@ -1328,7 +1328,6 @@ int drm_mode_atomic_ioctl(struct drm_device *dev, struct drm_out_fence_state *fence_state; int ret = 0; unsigned int i, j, num_fences; - struct drm_printer p = drm_info_printer(dev->dev); /* disallow for drivers not supporting atomic: */ if (!drm_core_check_feature(dev, DRIVER_ATOMIC)) @@ -1460,9 +1459,6 @@ retry: } else if (arg->flags & DRM_MODE_ATOMIC_NONBLOCK) { ret = drm_atomic_nonblocking_commit(state); } else { - if (drm_debug_enabled(DRM_UT_STATE)) - drm_atomic_print_new_state(state, &p); - ret = drm_atomic_commit(state); } diff --git a/drivers/gpu/drm/drm_blend.c b/drivers/gpu/drm/drm_blend.c index ec37cbfabb50..46ee5d5df6b4 100644 --- a/drivers/gpu/drm/drm_blend.c +++ b/drivers/gpu/drm/drm_blend.c @@ -317,7 +317,7 @@ EXPORT_SYMBOL(drm_plane_create_rotation_property); * DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_180 | * DRM_MODE_ROTATE_270 | DRM_MODE_REFLECT_Y); * - * to eliminate the DRM_MODE_ROTATE_X flag. Depending on what kind of + * to eliminate the DRM_MODE_REFLECT_X flag. Depending on what kind of * transforms the hardware supports, this function may not * be able to produce a supported transform, so the caller should * check the result afterwards. diff --git a/drivers/gpu/drm/drm_bridge_connector.c b/drivers/gpu/drm/drm_bridge_connector.c index 60923cdfe8e1..6b3dad03d77d 100644 --- a/drivers/gpu/drm/drm_bridge_connector.c +++ b/drivers/gpu/drm/drm_bridge_connector.c @@ -384,8 +384,10 @@ struct drm_connector *drm_bridge_connector_init(struct drm_device *drm, connector_type, ddc); drm_connector_helper_add(connector, &drm_bridge_connector_helper_funcs); - if (bridge_connector->bridge_hpd) + if (bridge_connector->bridge_hpd) { connector->polled = DRM_CONNECTOR_POLL_HPD; + drm_bridge_connector_enable_hpd(connector); + } else if (bridge_connector->bridge_detect) connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT; diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index 72f52f293249..11bb59399471 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -665,6 +665,9 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm, if (start + size == end) return __drm_buddy_alloc_range(mm, start, size, blocks); + if (!IS_ALIGNED(size, min_page_size)) + return -EINVAL; + pages = size >> ilog2(mm->chunk_size); order = fls(pages) - 1; min_order = ilog2(min_page_size) - ilog2(mm->chunk_size); diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c index bff917531f33..b632825654a9 100644 --- a/drivers/gpu/drm/drm_crtc_helper.c +++ b/drivers/gpu/drm/drm_crtc_helper.c @@ -297,15 +297,15 @@ bool drm_crtc_helper_set_mode(struct drm_crtc *crtc, return false; } - saved_mode = crtc->mode; - saved_hwmode = crtc->hwmode; + drm_mode_init(&saved_mode, &crtc->mode); + drm_mode_init(&saved_hwmode, &crtc->hwmode); saved_x = crtc->x; saved_y = crtc->y; /* Update crtc values up front so the driver can rely on them for mode * setting. */ - crtc->mode = *mode; + drm_mode_copy(&crtc->mode, mode); crtc->x = x; crtc->y = y; @@ -341,7 +341,7 @@ bool drm_crtc_helper_set_mode(struct drm_crtc *crtc, } DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name); - crtc->hwmode = *adjusted_mode; + drm_mode_copy(&crtc->hwmode, adjusted_mode); /* Prepare the encoders and CRTCs before setting the mode. */ drm_for_each_encoder(encoder, dev) { @@ -411,8 +411,8 @@ done: drm_mode_destroy(dev, adjusted_mode); if (!ret) { crtc->enabled = saved_enabled; - crtc->mode = saved_mode; - crtc->hwmode = saved_hwmode; + drm_mode_copy(&crtc->mode, &saved_mode); + drm_mode_copy(&crtc->hwmode, &saved_hwmode); crtc->x = saved_x; crtc->y = saved_y; } diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index cc7bd58369df..324ce8467915 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -97,7 +97,7 @@ static int oui(u8 first, u8 second, u8 third) struct detailed_mode_closure { struct drm_connector *connector; - struct edid *edid; + const struct edid *edid; bool preferred; u32 quirks; int modes; @@ -1568,10 +1568,47 @@ static const struct drm_display_mode edid_4k_modes[] = { /*** DDC fetch and block validation ***/ +static int edid_extension_block_count(const struct edid *edid) +{ + return edid->extensions; +} + +static int edid_block_count(const struct edid *edid) +{ + return edid_extension_block_count(edid) + 1; +} + +static int edid_size_by_blocks(int num_blocks) +{ + return num_blocks * EDID_LENGTH; +} + +static int edid_size(const struct edid *edid) +{ + return edid_size_by_blocks(edid_block_count(edid)); +} + +static const void *edid_block_data(const struct edid *edid, int index) +{ + BUILD_BUG_ON(sizeof(*edid) != EDID_LENGTH); + + return edid + index; +} + +static const void *edid_extension_block_data(const struct edid *edid, int index) +{ + return edid_block_data(edid, index + 1); +} + static const u8 edid_header[] = { 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00 }; +static void edid_header_fix(void *edid) +{ + memcpy(edid, edid_header, sizeof(edid_header)); +} + /** * drm_edid_header_is_valid - sanity check the header of the base EDID block * @raw_edid: pointer to raw base EDID block @@ -1580,13 +1617,15 @@ static const u8 edid_header[] = { * * Return: 8 if the header is perfect, down to 0 if it's totally wrong. */ -int drm_edid_header_is_valid(const u8 *raw_edid) +int drm_edid_header_is_valid(const void *_edid) { + const struct edid *edid = _edid; int i, score = 0; - for (i = 0; i < sizeof(edid_header); i++) - if (raw_edid[i] == edid_header[i]) + for (i = 0; i < sizeof(edid_header); i++) { + if (edid->header[i] == edid_header[i]) score++; + } return score; } @@ -1597,33 +1636,37 @@ module_param_named(edid_fixup, edid_fixup, int, 0400); MODULE_PARM_DESC(edid_fixup, "Minimum number of valid EDID header bytes (0-8, default 6)"); -static int drm_edid_block_checksum(const u8 *raw_edid) +static int edid_block_compute_checksum(const void *_block) { + const u8 *block = _block; int i; u8 csum = 0, crc = 0; for (i = 0; i < EDID_LENGTH - 1; i++) - csum += raw_edid[i]; + csum += block[i]; crc = 0x100 - csum; return crc; } -static bool drm_edid_block_checksum_diff(const u8 *raw_edid, u8 real_checksum) +static int edid_block_get_checksum(const void *_block) { - if (raw_edid[EDID_LENGTH - 1] != real_checksum) - return true; - else - return false; + const struct edid *block = _block; + + return block->checksum; } -static bool drm_edid_is_zero(const u8 *in_edid, int length) +static int edid_block_tag(const void *_block) { - if (memchr_inv(in_edid, 0, length)) - return false; + const u8 *block = _block; - return true; + return block[0]; +} + +static bool edid_block_is_zero(const void *edid) +{ + return !memchr_inv(edid, 0, EDID_LENGTH); } /** @@ -1643,8 +1686,8 @@ bool drm_edid_are_equal(const struct edid *edid1, const struct edid *edid2) return false; if (edid1) { - edid1_len = EDID_LENGTH * (1 + edid1->extensions); - edid2_len = EDID_LENGTH * (1 + edid2->extensions); + edid1_len = edid_size(edid1); + edid2_len = edid_size(edid2); if (edid1_len != edid2_len) return false; @@ -1657,10 +1700,136 @@ bool drm_edid_are_equal(const struct edid *edid1, const struct edid *edid2) } EXPORT_SYMBOL(drm_edid_are_equal); +enum edid_block_status { + EDID_BLOCK_OK = 0, + EDID_BLOCK_READ_FAIL, + EDID_BLOCK_NULL, + EDID_BLOCK_ZERO, + EDID_BLOCK_HEADER_CORRUPT, + EDID_BLOCK_HEADER_REPAIR, + EDID_BLOCK_HEADER_FIXED, + EDID_BLOCK_CHECKSUM, + EDID_BLOCK_VERSION, +}; + +static enum edid_block_status edid_block_check(const void *_block, + bool is_base_block) +{ + const struct edid *block = _block; + + if (!block) + return EDID_BLOCK_NULL; + + if (is_base_block) { + int score = drm_edid_header_is_valid(block); + + if (score < clamp(edid_fixup, 0, 8)) { + if (edid_block_is_zero(block)) + return EDID_BLOCK_ZERO; + else + return EDID_BLOCK_HEADER_CORRUPT; + } + + if (score < 8) + return EDID_BLOCK_HEADER_REPAIR; + } + + if (edid_block_compute_checksum(block) != edid_block_get_checksum(block)) { + if (edid_block_is_zero(block)) + return EDID_BLOCK_ZERO; + else + return EDID_BLOCK_CHECKSUM; + } + + if (is_base_block) { + if (block->version != 1) + return EDID_BLOCK_VERSION; + } + + return EDID_BLOCK_OK; +} + +static bool edid_block_status_valid(enum edid_block_status status, int tag) +{ + return status == EDID_BLOCK_OK || + status == EDID_BLOCK_HEADER_FIXED || + (status == EDID_BLOCK_CHECKSUM && tag == CEA_EXT); +} + +static bool edid_block_valid(const void *block, bool base) +{ + return edid_block_status_valid(edid_block_check(block, base), + edid_block_tag(block)); +} + +static void edid_block_status_print(enum edid_block_status status, + const struct edid *block, + int block_num) +{ + switch (status) { + case EDID_BLOCK_OK: + break; + case EDID_BLOCK_READ_FAIL: + pr_debug("EDID block %d read failed\n", block_num); + break; + case EDID_BLOCK_NULL: + pr_debug("EDID block %d pointer is NULL\n", block_num); + break; + case EDID_BLOCK_ZERO: + pr_notice("EDID block %d is all zeroes\n", block_num); + break; + case EDID_BLOCK_HEADER_CORRUPT: + pr_notice("EDID has corrupt header\n"); + break; + case EDID_BLOCK_HEADER_REPAIR: + pr_debug("EDID corrupt header needs repair\n"); + break; + case EDID_BLOCK_HEADER_FIXED: + pr_debug("EDID corrupt header fixed\n"); + break; + case EDID_BLOCK_CHECKSUM: + if (edid_block_status_valid(status, edid_block_tag(block))) { + pr_debug("EDID block %d (tag 0x%02x) checksum is invalid, remainder is %d, ignoring\n", + block_num, edid_block_tag(block), + edid_block_compute_checksum(block)); + } else { + pr_notice("EDID block %d (tag 0x%02x) checksum is invalid, remainder is %d\n", + block_num, edid_block_tag(block), + edid_block_compute_checksum(block)); + } + break; + case EDID_BLOCK_VERSION: + pr_notice("EDID has major version %d, instead of 1\n", + block->version); + break; + default: + WARN(1, "EDID block %d unknown edid block status code %d\n", + block_num, status); + break; + } +} + +static void edid_block_dump(const char *level, const void *block, int block_num) +{ + enum edid_block_status status; + char prefix[20]; + + status = edid_block_check(block, block_num == 0); + if (status == EDID_BLOCK_ZERO) + sprintf(prefix, "\t[%02x] ZERO ", block_num); + else if (!edid_block_status_valid(status, edid_block_tag(block))) + sprintf(prefix, "\t[%02x] BAD ", block_num); + else + sprintf(prefix, "\t[%02x] GOOD ", block_num); + + print_hex_dump(level, prefix, DUMP_PREFIX_NONE, 16, 1, + block, EDID_LENGTH, false); +} + /** * drm_edid_block_valid - Sanity check the EDID block (base or extension) * @raw_edid: pointer to raw EDID block - * @block: type of block to validate (0 for base, extension otherwise) + * @block_num: type of block to validate (0 for base, extension otherwise) * @print_bad_edid: if true, dump bad EDID blocks to the console * @edid_corrupt: if true, the header or checksum is invalid * @@ -1669,88 +1838,51 @@ EXPORT_SYMBOL(drm_edid_are_equal); * * Return: True if the block is valid, false otherwise. */ -bool drm_edid_block_valid(u8 *raw_edid, int block, bool print_bad_edid, +bool drm_edid_block_valid(u8 *_block, int block_num, bool print_bad_edid, bool *edid_corrupt) { - u8 csum; - struct edid *edid = (struct edid *)raw_edid; + struct edid *block = (struct edid *)_block; + enum edid_block_status status; + bool is_base_block = block_num == 0; + bool valid; - if (WARN_ON(!raw_edid)) + if (WARN_ON(!block)) return false; - if (edid_fixup > 8 || edid_fixup < 0) - edid_fixup = 6; - - if (block == 0) { - int score = drm_edid_header_is_valid(raw_edid); + status = edid_block_check(block, is_base_block); + if (status == EDID_BLOCK_HEADER_REPAIR) { + DRM_DEBUG("Fixing EDID header, your hardware may be failing\n"); + edid_header_fix(block); - if (score == 8) { - if (edid_corrupt) - *edid_corrupt = false; - } else if (score >= edid_fixup) { - /* Displayport Link CTS Core 1.2 rev1.1 test 4.2.2.6 - * The corrupt flag needs to be set here otherwise, the - * fix-up code here will correct the problem, the - * checksum is correct and the test fails - */ - if (edid_corrupt) - *edid_corrupt = true; - DRM_DEBUG("Fixing EDID header, your hardware may be failing\n"); - memcpy(raw_edid, edid_header, sizeof(edid_header)); - } else { - if (edid_corrupt) - *edid_corrupt = true; - goto bad; - } + /* Retry with fixed header, update status if that worked. */ + status = edid_block_check(block, is_base_block); + if (status == EDID_BLOCK_OK) + status = EDID_BLOCK_HEADER_FIXED; } - csum = drm_edid_block_checksum(raw_edid); - if (drm_edid_block_checksum_diff(raw_edid, csum)) { - if (edid_corrupt) + if (edid_corrupt) { + /* + * Unknown major version isn't corrupt but we can't use it. Only + * the base block can reset edid_corrupt to false. + */ + if (is_base_block && + (status == EDID_BLOCK_OK || status == EDID_BLOCK_VERSION)) + *edid_corrupt = false; + else if (status != EDID_BLOCK_OK) *edid_corrupt = true; - - /* allow CEA to slide through, switches mangle this */ - if (raw_edid[0] == CEA_EXT) { - DRM_DEBUG("EDID checksum is invalid, remainder is %d\n", csum); - DRM_DEBUG("Assuming a KVM switch modified the CEA block but left the original checksum\n"); - } else { - if (print_bad_edid) - DRM_NOTE("EDID checksum is invalid, remainder is %d\n", csum); - - goto bad; - } } - /* per-block-type checks */ - switch (raw_edid[0]) { - case 0: /* base */ - if (edid->version != 1) { - DRM_NOTE("EDID has major version %d, instead of 1\n", edid->version); - goto bad; - } + edid_block_status_print(status, block, block_num); - if (edid->revision > 4) - DRM_DEBUG("EDID minor > 4, assuming backward compatibility\n"); - break; + /* Determine whether we can use this block with this status. */ + valid = edid_block_status_valid(status, edid_block_tag(block)); - default: - break; + if (!valid && print_bad_edid && status != EDID_BLOCK_ZERO) { + pr_notice("Raw EDID:\n"); + edid_block_dump(KERN_NOTICE, block, block_num); } - return true; - -bad: - if (print_bad_edid) { - if (drm_edid_is_zero(raw_edid, EDID_LENGTH)) { - pr_notice("EDID block is all zeroes\n"); - } else { - pr_notice("Raw EDID:\n"); - print_hex_dump(KERN_NOTICE, - " \t", DUMP_PREFIX_NONE, 16, 1, - raw_edid, EDID_LENGTH, false); - } - } - return false; + return valid; } EXPORT_SYMBOL(drm_edid_block_valid); @@ -1765,19 +1897,49 @@ EXPORT_SYMBOL(drm_edid_block_valid); bool drm_edid_is_valid(struct edid *edid) { int i; - u8 *raw = (u8 *)edid; if (!edid) return false; - for (i = 0; i <= edid->extensions; i++) - if (!drm_edid_block_valid(raw + i * EDID_LENGTH, i, true, NULL)) + for (i = 0; i < edid_block_count(edid); i++) { + void *block = (void *)edid_block_data(edid, i); + + if (!drm_edid_block_valid(block, i, true, NULL)) return false; + } return true; } EXPORT_SYMBOL(drm_edid_is_valid); +static struct edid *edid_filter_invalid_blocks(const struct edid *edid, + int invalid_blocks) +{ + struct edid *new, *dest_block; + int valid_extensions = edid->extensions - invalid_blocks; + int i; + + new = kmalloc(edid_size_by_blocks(valid_extensions + 1), GFP_KERNEL); + if (!new) + goto out; + + dest_block = new; + for (i = 0; i < edid_block_count(edid); i++) { + const void *block = edid_block_data(edid, i); + + if (edid_block_valid(block, i == 0)) + memcpy(dest_block++, block, EDID_LENGTH); + } + + new->extensions = valid_extensions; + new->checksum = edid_block_compute_checksum(new); + +out: + kfree(edid); + + return new; +} + #define DDC_SEGMENT_ADDR 0x30 /** * drm_do_probe_ddc_edid() - get EDID information via I2C @@ -1843,7 +2005,7 @@ drm_do_probe_ddc_edid(void *data, u8 *buf, unsigned int block, size_t len) } static void connector_bad_edid(struct drm_connector *connector, - u8 *edid, int num_blocks) + const struct edid *edid, int num_blocks) { int i; u8 last_block; @@ -1854,32 +2016,19 @@ static void connector_bad_edid(struct drm_connector *connector, * of 0x7e in the EDID of the _index_ of the last block in the * combined chunk of memory. */ - last_block = edid[0x7e]; + last_block = edid->extensions; /* Calculate real checksum for the last edid extension block data */ if (last_block < num_blocks) connector->real_edid_checksum = - drm_edid_block_checksum(edid + last_block * EDID_LENGTH); + edid_block_compute_checksum(edid + last_block); if (connector->bad_edid_counter++ && !drm_debug_enabled(DRM_UT_KMS)) return; drm_dbg_kms(connector->dev, "%s: EDID is invalid:\n", connector->name); - for (i = 0; i < num_blocks; i++) { - u8 *block = edid + i * EDID_LENGTH; - char prefix[20]; - - if (drm_edid_is_zero(block, EDID_LENGTH)) - sprintf(prefix, "\t[%02x] ZERO ", i); - else if (!drm_edid_block_valid(block, i, false, NULL)) - sprintf(prefix, "\t[%02x] BAD ", i); - else - sprintf(prefix, "\t[%02x] GOOD ", i); - - print_hex_dump(KERN_DEBUG, - prefix, DUMP_PREFIX_NONE, 16, 1, - block, EDID_LENGTH, false); - } + for (i = 0; i < num_blocks; i++) + edid_block_dump(KERN_DEBUG, edid + i, i); } /* Get override or firmware EDID */ @@ -1926,43 +2075,39 @@ int drm_add_override_edid_modes(struct drm_connector *connector) } EXPORT_SYMBOL(drm_add_override_edid_modes); -static struct edid *drm_do_get_edid_base_block(struct drm_connector *connector, - int (*get_edid_block)(void *data, u8 *buf, unsigned int block, - size_t len), - void *data) +typedef int read_block_fn(void *context, u8 *buf, unsigned int block, size_t len); + +static enum edid_block_status edid_block_read(void *block, unsigned int block_num, + read_block_fn read_block, + void *context) { - int *null_edid_counter = connector ? &connector->null_edid_counter : NULL; - bool *edid_corrupt = connector ? &connector->edid_corrupt : NULL; - void *edid; - int i; + enum edid_block_status status; + bool is_base_block = block_num == 0; + int try; - edid = kmalloc(EDID_LENGTH, GFP_KERNEL); - if (edid == NULL) - return NULL; + for (try = 0; try < 4; try++) { + if (read_block(context, block, block_num, EDID_LENGTH)) + return EDID_BLOCK_READ_FAIL; - /* base block fetch */ - for (i = 0; i < 4; i++) { - if (get_edid_block(data, edid, 0, EDID_LENGTH)) - goto out; - if (drm_edid_block_valid(edid, 0, false, edid_corrupt)) - break; - if (i == 0 && drm_edid_is_zero(edid, EDID_LENGTH)) { - if (null_edid_counter) - (*null_edid_counter)++; - goto carp; + status = edid_block_check(block, is_base_block); + if (status == EDID_BLOCK_HEADER_REPAIR) { + edid_header_fix(block); + + /* Retry with fixed header, update status if that worked. */ + status = edid_block_check(block, is_base_block); + if (status == EDID_BLOCK_OK) + status = EDID_BLOCK_HEADER_FIXED; } - } - if (i == 4) - goto carp; - return edid; + if (edid_block_status_valid(status, edid_block_tag(block))) + break; -carp: - if (connector) - connector_bad_edid(connector, edid, 1); -out: - kfree(edid); - return NULL; + /* Fail early for unrepairable base block all zeros. */ + if (try == 0 && is_base_block && status == EDID_BLOCK_ZERO) + break; + } + + return status; } /** @@ -1986,77 +2131,74 @@ out: * Return: Pointer to valid EDID or NULL if we couldn't find any. */ struct edid *drm_do_get_edid(struct drm_connector *connector, - int (*get_edid_block)(void *data, u8 *buf, unsigned int block, - size_t len), - void *data) + read_block_fn read_block, + void *context) { - int i, j = 0, valid_extensions = 0; - u8 *edid, *new; - struct edid *override; + enum edid_block_status status; + int i, invalid_blocks = 0; + struct edid *edid, *new; - override = drm_get_override_edid(connector); - if (override) - return override; + edid = drm_get_override_edid(connector); + if (edid) + goto ok; - edid = (u8 *)drm_do_get_edid_base_block(connector, get_edid_block, data); + edid = kmalloc(EDID_LENGTH, GFP_KERNEL); if (!edid) return NULL; - /* if there's no extensions or no connector, we're done */ - valid_extensions = edid[0x7e]; - if (valid_extensions == 0) - return (struct edid *)edid; + status = edid_block_read(edid, 0, read_block, context); - new = krealloc(edid, (valid_extensions + 1) * EDID_LENGTH, GFP_KERNEL); - if (!new) - goto out; - edid = new; + edid_block_status_print(status, edid, 0); - for (j = 1; j <= edid[0x7e]; j++) { - u8 *block = edid + j * EDID_LENGTH; + if (status == EDID_BLOCK_READ_FAIL) + goto fail; - for (i = 0; i < 4; i++) { - if (get_edid_block(data, block, j, EDID_LENGTH)) - goto out; - if (drm_edid_block_valid(block, j, false, NULL)) - break; - } + /* FIXME: Clarify what a corrupt EDID actually means. */ + if (status == EDID_BLOCK_OK || status == EDID_BLOCK_VERSION) + connector->edid_corrupt = false; + else + connector->edid_corrupt = true; - if (i == 4) - valid_extensions--; - } + if (!edid_block_status_valid(status, edid_block_tag(edid))) { + if (status == EDID_BLOCK_ZERO) + connector->null_edid_counter++; - if (valid_extensions != edid[0x7e]) { - u8 *base; + connector_bad_edid(connector, edid, 1); + goto fail; + } - connector_bad_edid(connector, edid, edid[0x7e] + 1); + if (!edid_extension_block_count(edid)) + goto ok; - edid[EDID_LENGTH-1] += edid[0x7e] - valid_extensions; - edid[0x7e] = valid_extensions; + new = krealloc(edid, edid_size(edid), GFP_KERNEL); + if (!new) + goto fail; + edid = new; - new = kmalloc_array(valid_extensions + 1, EDID_LENGTH, - GFP_KERNEL); - if (!new) - goto out; + for (i = 1; i < edid_block_count(edid); i++) { + void *block = (void *)edid_block_data(edid, i); - base = new; - for (i = 0; i <= edid[0x7e]; i++) { - u8 *block = edid + i * EDID_LENGTH; + status = edid_block_read(block, i, read_block, context); - if (!drm_edid_block_valid(block, i, false, NULL)) - continue; + edid_block_status_print(status, block, i); - memcpy(base, block, EDID_LENGTH); - base += EDID_LENGTH; + if (!edid_block_status_valid(status, edid_block_tag(block))) { + if (status == EDID_BLOCK_READ_FAIL) + goto fail; + invalid_blocks++; } + } - kfree(edid); - edid = new; + if (invalid_blocks) { + connector_bad_edid(connector, edid, edid_block_count(edid)); + + edid = edid_filter_invalid_blocks(edid, invalid_blocks); } - return (struct edid *)edid; +ok: + return edid; -out: +fail: kfree(edid); return NULL; } @@ -2150,20 +2292,27 @@ static u32 edid_extract_panel_id(const struct edid *edid) u32 drm_edid_get_panel_id(struct i2c_adapter *adapter) { - struct edid *edid; - u32 panel_id; - - edid = drm_do_get_edid_base_block(NULL, drm_do_probe_ddc_edid, adapter); + enum edid_block_status status; + void *base_block; + u32 panel_id = 0; /* * There are no manufacturer IDs of 0, so if there is a problem reading * the EDID then we'll just return 0. */ - if (!edid) + + base_block = kmalloc(EDID_LENGTH, GFP_KERNEL); + if (!base_block) return 0; - panel_id = edid_extract_panel_id(edid); - kfree(edid); + status = edid_block_read(base_block, 0, drm_do_probe_ddc_edid, adapter); + + edid_block_status_print(status, base_block, 0); + + if (edid_block_status_valid(status, edid_block_tag(base_block))) + panel_id = edid_extract_panel_id(base_block); + + kfree(base_block); return panel_id; } @@ -2206,7 +2355,7 @@ EXPORT_SYMBOL(drm_get_edid_switcheroo); */ struct edid *drm_edid_duplicate(const struct edid *edid) { - return kmemdup(edid, (edid->extensions + 1) * EDID_LENGTH, GFP_KERNEL); + return kmemdup(edid, edid_size(edid), GFP_KERNEL); } EXPORT_SYMBOL(drm_edid_duplicate); @@ -2331,52 +2480,58 @@ struct drm_display_mode *drm_mode_find_dmt(struct drm_device *dev, } EXPORT_SYMBOL(drm_mode_find_dmt); -static bool is_display_descriptor(const u8 d[18], u8 tag) +static bool is_display_descriptor(const struct detailed_timing *descriptor, u8 type) { - return d[0] == 0x00 && d[1] == 0x00 && - d[2] == 0x00 && d[3] == tag; + BUILD_BUG_ON(offsetof(typeof(*descriptor), pixel_clock) != 0); + BUILD_BUG_ON(offsetof(typeof(*descriptor), data.other_data.pad1) != 2); + BUILD_BUG_ON(offsetof(typeof(*descriptor), data.other_data.type) != 3); + + return descriptor->pixel_clock == 0 && + descriptor->data.other_data.pad1 == 0 && + descriptor->data.other_data.type == type; } -static bool is_detailed_timing_descriptor(const u8 d[18]) +static bool is_detailed_timing_descriptor(const struct detailed_timing *descriptor) { - return d[0] != 0x00 || d[1] != 0x00; + BUILD_BUG_ON(offsetof(typeof(*descriptor), pixel_clock) != 0); + + return descriptor->pixel_clock != 0; } -typedef void detailed_cb(struct detailed_timing *timing, void *closure); +typedef void detailed_cb(const struct detailed_timing *timing, void *closure); static void -cea_for_each_detailed_block(u8 *ext, detailed_cb *cb, void *closure) +cea_for_each_detailed_block(const u8 *ext, detailed_cb *cb, void *closure) { int i, n; u8 d = ext[0x02]; - u8 *det_base = ext + d; + const u8 *det_base = ext + d; if (d < 4 || d > 127) return; n = (127 - d) / 18; for (i = 0; i < n; i++) - cb((struct detailed_timing *)(det_base + 18 * i), closure); + cb((const struct detailed_timing *)(det_base + 18 * i), closure); } static void -vtb_for_each_detailed_block(u8 *ext, detailed_cb *cb, void *closure) +vtb_for_each_detailed_block(const u8 *ext, detailed_cb *cb, void *closure) { unsigned int i, n = min((int)ext[0x02], 6); - u8 *det_base = ext + 5; + const u8 *det_base = ext + 5; if (ext[0x01] != 1) return; /* unknown version */ for (i = 0; i < n; i++) - cb((struct detailed_timing *)(det_base + 18 * i), closure); + cb((const struct detailed_timing *)(det_base + 18 * i), closure); } static void -drm_for_each_detailed_block(u8 *raw_edid, detailed_cb *cb, void *closure) +drm_for_each_detailed_block(const struct edid *edid, detailed_cb *cb, void *closure) { int i; - struct edid *edid = (struct edid *)raw_edid; if (edid == NULL) return; @@ -2384,8 +2539,8 @@ drm_for_each_detailed_block(u8 *raw_edid, detailed_cb *cb, void *closure) for (i = 0; i < EDID_DETAILED_TIMINGS; i++) cb(&(edid->detailed_timings[i]), closure); - for (i = 1; i <= raw_edid[0x7e]; i++) { - u8 *ext = raw_edid + (i * EDID_LENGTH); + for (i = 0; i < edid_extension_block_count(edid); i++) { + const u8 *ext = edid_extension_block_data(edid, i); switch (*ext) { case CEA_EXT: @@ -2401,25 +2556,29 @@ drm_for_each_detailed_block(u8 *raw_edid, detailed_cb *cb, void *closure) } static void -is_rb(struct detailed_timing *t, void *data) +is_rb(const struct detailed_timing *descriptor, void *data) { - u8 *r = (u8 *)t; + bool *res = data; - if (!is_display_descriptor(r, EDID_DETAIL_MONITOR_RANGE)) + if (!is_display_descriptor(descriptor, EDID_DETAIL_MONITOR_RANGE)) return; - if (r[15] & 0x10) - *(bool *)data = true; + BUILD_BUG_ON(offsetof(typeof(*descriptor), data.other_data.data.range.flags) != 10); + BUILD_BUG_ON(offsetof(typeof(*descriptor), data.other_data.data.range.formula.cvt.flags) != 15); + + if (descriptor->data.other_data.data.range.flags == DRM_EDID_CVT_SUPPORT_FLAG && + descriptor->data.other_data.data.range.formula.cvt.flags & 0x10) + *res = true; } /* EDID 1.4 defines this explicitly. For EDID 1.3, we guess, badly. */ static bool -drm_monitor_supports_rb(struct edid *edid) +drm_monitor_supports_rb(const struct edid *edid) { if (edid->revision >= 4) { bool ret = false; - drm_for_each_detailed_block((u8 *)edid, is_rb, &ret); + drm_for_each_detailed_block(edid, is_rb, &ret); return ret; } @@ -2427,68 +2586,85 @@ drm_monitor_supports_rb(struct edid *edid) } static void -find_gtf2(struct detailed_timing *t, void *data) +find_gtf2(const struct detailed_timing *descriptor, void *data) { - u8 *r = (u8 *)t; + const struct detailed_timing **res = data; - if (!is_display_descriptor(r, EDID_DETAIL_MONITOR_RANGE)) + if (!is_display_descriptor(descriptor, EDID_DETAIL_MONITOR_RANGE)) return; - if (r[10] == 0x02) - *(u8 **)data = r; + BUILD_BUG_ON(offsetof(typeof(*descriptor), data.other_data.data.range.flags) != 10); + + if (descriptor->data.other_data.data.range.flags == 0x02) + *res = descriptor; } /* Secondary GTF curve kicks in above some break frequency */ static int -drm_gtf2_hbreak(struct edid *edid) +drm_gtf2_hbreak(const struct edid *edid) { - u8 *r = NULL; + const struct detailed_timing *descriptor = NULL; + + drm_for_each_detailed_block(edid, find_gtf2, &descriptor); - drm_for_each_detailed_block((u8 *)edid, find_gtf2, &r); - return r ? (r[12] * 2) : 0; + BUILD_BUG_ON(offsetof(typeof(*descriptor), data.other_data.data.range.formula.gtf2.hfreq_start_khz) != 12); + + return descriptor ? descriptor->data.other_data.data.range.formula.gtf2.hfreq_start_khz * 2 : 0; } static int -drm_gtf2_2c(struct edid *edid) +drm_gtf2_2c(const struct edid *edid) { - u8 *r = NULL; + const struct detailed_timing *descriptor = NULL; + + drm_for_each_detailed_block(edid, find_gtf2, &descriptor); - drm_for_each_detailed_block((u8 *)edid, find_gtf2, &r); - return r ? r[13] : 0; + BUILD_BUG_ON(offsetof(typeof(*descriptor), data.other_data.data.range.formula.gtf2.c) != 13); + + return descriptor ? descriptor->data.other_data.data.range.formula.gtf2.c : 0; } static int -drm_gtf2_m(struct edid *edid) +drm_gtf2_m(const struct edid *edid) { - u8 *r = NULL; + const struct detailed_timing *descriptor = NULL; + + drm_for_each_detailed_block(edid, find_gtf2, &descriptor); - drm_for_each_detailed_block((u8 *)edid, find_gtf2, &r); - return r ? (r[15] << 8) + r[14] : 0; + BUILD_BUG_ON(offsetof(typeof(*descriptor), data.other_data.data.range.formula.gtf2.m) != 14); + + return descriptor ? le16_to_cpu(descriptor->data.other_data.data.range.formula.gtf2.m) : 0; } static int -drm_gtf2_k(struct edid *edid) +drm_gtf2_k(const struct edid *edid) { - u8 *r = NULL; + const struct detailed_timing *descriptor = NULL; + + drm_for_each_detailed_block(edid, find_gtf2, &descriptor); - drm_for_each_detailed_block((u8 *)edid, find_gtf2, &r); - return r ? r[16] : 0; + BUILD_BUG_ON(offsetof(typeof(*descriptor), data.other_data.data.range.formula.gtf2.k) != 16); + + return descriptor ? descriptor->data.other_data.data.range.formula.gtf2.k : 0; } static int -drm_gtf2_2j(struct edid *edid) +drm_gtf2_2j(const struct edid *edid) { - u8 *r = NULL; + const struct detailed_timing *descriptor = NULL; + + drm_for_each_detailed_block(edid, find_gtf2, &descriptor); - drm_for_each_detailed_block((u8 *)edid, find_gtf2, &r); - return r ? r[17] : 0; + BUILD_BUG_ON(offsetof(typeof(*descriptor), data.other_data.data.range.formula.gtf2.j) != 17); + + return descriptor ? descriptor->data.other_data.data.range.formula.gtf2.j : 0; } /** * standard_timing_level - get std. timing level(CVT/GTF/DMT) * @edid: EDID block to scan */ -static int standard_timing_level(struct edid *edid) +static int standard_timing_level(const struct edid *edid) { if (edid->revision >= 2) { if (edid->revision >= 4 && (edid->features & DRM_EDID_FEATURE_DEFAULT_GTF)) @@ -2531,8 +2707,8 @@ static int drm_mode_hsync(const struct drm_display_mode *mode) * and convert them into a real mode using CVT/GTF/DMT. */ static struct drm_display_mode * -drm_mode_std(struct drm_connector *connector, struct edid *edid, - struct std_timing *t) +drm_mode_std(struct drm_connector *connector, const struct edid *edid, + const struct std_timing *t) { struct drm_device *dev = connector->dev; struct drm_display_mode *m, *mode = NULL; @@ -2650,7 +2826,7 @@ drm_mode_std(struct drm_connector *connector, struct edid *edid, */ static void drm_mode_do_interlace_quirk(struct drm_display_mode *mode, - struct detailed_pixel_timing *pt) + const struct detailed_pixel_timing *pt) { int i; static const struct { @@ -2693,12 +2869,12 @@ drm_mode_do_interlace_quirk(struct drm_display_mode *mode, * return a new struct drm_display_mode. */ static struct drm_display_mode *drm_mode_detailed(struct drm_device *dev, - struct edid *edid, - struct detailed_timing *timing, + const struct edid *edid, + const struct detailed_timing *timing, u32 quirks) { struct drm_display_mode *mode; - struct detailed_pixel_timing *pt = &timing->data.pixel_data; + const struct detailed_pixel_timing *pt = &timing->data.pixel_data; unsigned hactive = (pt->hactive_hblank_hi & 0xf0) << 4 | pt->hactive_lo; unsigned vactive = (pt->vactive_vblank_hi & 0xf0) << 4 | pt->vactive_lo; unsigned hblank = (pt->hactive_hblank_hi & 0xf) << 8 | pt->hblank_lo; @@ -2740,9 +2916,9 @@ static struct drm_display_mode *drm_mode_detailed(struct drm_device *dev, return NULL; if (quirks & EDID_QUIRK_135_CLOCK_TOO_HIGH) - timing->pixel_clock = cpu_to_le16(1088); - - mode->clock = le16_to_cpu(timing->pixel_clock) * 10; + mode->clock = 1088 * 10; + else + mode->clock = le16_to_cpu(timing->pixel_clock) * 10; mode->hdisplay = hactive; mode->hsync_start = mode->hdisplay + hsync_offset; @@ -2763,14 +2939,14 @@ static struct drm_display_mode *drm_mode_detailed(struct drm_device *dev, drm_mode_do_interlace_quirk(mode, pt); if (quirks & EDID_QUIRK_DETAILED_SYNC_PP) { - pt->misc |= DRM_EDID_PT_HSYNC_POSITIVE | DRM_EDID_PT_VSYNC_POSITIVE; + mode->flags |= DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC; + } else { + mode->flags |= (pt->misc & DRM_EDID_PT_HSYNC_POSITIVE) ? + DRM_MODE_FLAG_PHSYNC : DRM_MODE_FLAG_NHSYNC; + mode->flags |= (pt->misc & DRM_EDID_PT_VSYNC_POSITIVE) ? + DRM_MODE_FLAG_PVSYNC : DRM_MODE_FLAG_NVSYNC; } - mode->flags |= (pt->misc & DRM_EDID_PT_HSYNC_POSITIVE) ? - DRM_MODE_FLAG_PHSYNC : DRM_MODE_FLAG_NHSYNC; - mode->flags |= (pt->misc & DRM_EDID_PT_VSYNC_POSITIVE) ? - DRM_MODE_FLAG_PVSYNC : DRM_MODE_FLAG_NVSYNC; - set_size: mode->width_mm = pt->width_mm_lo | (pt->width_height_mm_hi & 0xf0) << 4; mode->height_mm = pt->height_mm_lo | (pt->width_height_mm_hi & 0xf) << 8; @@ -2793,7 +2969,7 @@ set_size: static bool mode_in_hsync_range(const struct drm_display_mode *mode, - struct edid *edid, u8 *t) + const struct edid *edid, const u8 *t) { int hsync, hmin, hmax; @@ -2810,7 +2986,7 @@ mode_in_hsync_range(const struct drm_display_mode *mode, static bool mode_in_vsync_range(const struct drm_display_mode *mode, - struct edid *edid, u8 *t) + const struct edid *edid, const u8 *t) { int vsync, vmin, vmax; @@ -2826,7 +3002,7 @@ mode_in_vsync_range(const struct drm_display_mode *mode, } static u32 -range_pixel_clock(struct edid *edid, u8 *t) +range_pixel_clock(const struct edid *edid, const u8 *t) { /* unspecified */ if (t[9] == 0 || t[9] == 255) @@ -2841,11 +3017,11 @@ range_pixel_clock(struct edid *edid, u8 *t) } static bool -mode_in_range(const struct drm_display_mode *mode, struct edid *edid, - struct detailed_timing *timing) +mode_in_range(const struct drm_display_mode *mode, const struct edid *edid, + const struct detailed_timing *timing) { u32 max_clock; - u8 *t = (u8 *)timing; + const u8 *t = (const u8 *)timing; if (!mode_in_hsync_range(mode, edid, t)) return false; @@ -2887,8 +3063,8 @@ static bool valid_inferred_mode(const struct drm_connector *connector, } static int -drm_dmt_modes_for_range(struct drm_connector *connector, struct edid *edid, - struct detailed_timing *timing) +drm_dmt_modes_for_range(struct drm_connector *connector, const struct edid *edid, + const struct detailed_timing *timing) { int i, modes = 0; struct drm_display_mode *newmode; @@ -2922,8 +3098,8 @@ void drm_mode_fixup_1366x768(struct drm_display_mode *mode) } static int -drm_gtf_modes_for_range(struct drm_connector *connector, struct edid *edid, - struct detailed_timing *timing) +drm_gtf_modes_for_range(struct drm_connector *connector, const struct edid *edid, + const struct detailed_timing *timing) { int i, modes = 0; struct drm_display_mode *newmode; @@ -2951,8 +3127,8 @@ drm_gtf_modes_for_range(struct drm_connector *connector, struct edid *edid, } static int -drm_cvt_modes_for_range(struct drm_connector *connector, struct edid *edid, - struct detailed_timing *timing) +drm_cvt_modes_for_range(struct drm_connector *connector, const struct edid *edid, + const struct detailed_timing *timing) { int i, modes = 0; struct drm_display_mode *newmode; @@ -2981,13 +3157,13 @@ drm_cvt_modes_for_range(struct drm_connector *connector, struct edid *edid, } static void -do_inferred_modes(struct detailed_timing *timing, void *c) +do_inferred_modes(const struct detailed_timing *timing, void *c) { struct detailed_mode_closure *closure = c; - struct detailed_non_pixel *data = &timing->data.other_data; - struct detailed_data_monitor_range *range = &data->data.range; + const struct detailed_non_pixel *data = &timing->data.other_data; + const struct detailed_data_monitor_range *range = &data->data.range; - if (!is_display_descriptor((const u8 *)timing, EDID_DETAIL_MONITOR_RANGE)) + if (!is_display_descriptor(timing, EDID_DETAIL_MONITOR_RANGE)) return; closure->modes += drm_dmt_modes_for_range(closure->connector, @@ -3019,7 +3195,7 @@ do_inferred_modes(struct detailed_timing *timing, void *c) } static int -add_inferred_modes(struct drm_connector *connector, struct edid *edid) +add_inferred_modes(struct drm_connector *connector, const struct edid *edid) { struct detailed_mode_closure closure = { .connector = connector, @@ -3027,18 +3203,17 @@ add_inferred_modes(struct drm_connector *connector, struct edid *edid) }; if (version_greater(edid, 1, 0)) - drm_for_each_detailed_block((u8 *)edid, do_inferred_modes, - &closure); + drm_for_each_detailed_block(edid, do_inferred_modes, &closure); return closure.modes; } static int -drm_est3_modes(struct drm_connector *connector, struct detailed_timing *timing) +drm_est3_modes(struct drm_connector *connector, const struct detailed_timing *timing) { int i, j, m, modes = 0; struct drm_display_mode *mode; - u8 *est = ((u8 *)timing) + 6; + const u8 *est = ((const u8 *)timing) + 6; for (i = 0; i < 6; i++) { for (j = 7; j >= 0; j--) { @@ -3063,11 +3238,11 @@ drm_est3_modes(struct drm_connector *connector, struct detailed_timing *timing) } static void -do_established_modes(struct detailed_timing *timing, void *c) +do_established_modes(const struct detailed_timing *timing, void *c) { struct detailed_mode_closure *closure = c; - if (!is_display_descriptor((const u8 *)timing, EDID_DETAIL_EST_TIMINGS)) + if (!is_display_descriptor(timing, EDID_DETAIL_EST_TIMINGS)) return; closure->modes += drm_est3_modes(closure->connector, timing); @@ -3082,7 +3257,7 @@ do_established_modes(struct detailed_timing *timing, void *c) * (defined above). Tease them out and add them to the global modes list. */ static int -add_established_modes(struct drm_connector *connector, struct edid *edid) +add_established_modes(struct drm_connector *connector, const struct edid *edid) { struct drm_device *dev = connector->dev; unsigned long est_bits = edid->established_timings.t1 | @@ -3107,26 +3282,26 @@ add_established_modes(struct drm_connector *connector, struct edid *edid) } if (version_greater(edid, 1, 0)) - drm_for_each_detailed_block((u8 *)edid, - do_established_modes, &closure); + drm_for_each_detailed_block(edid, do_established_modes, + &closure); return modes + closure.modes; } static void -do_standard_modes(struct detailed_timing *timing, void *c) +do_standard_modes(const struct detailed_timing *timing, void *c) { struct detailed_mode_closure *closure = c; - struct detailed_non_pixel *data = &timing->data.other_data; + const struct detailed_non_pixel *data = &timing->data.other_data; struct drm_connector *connector = closure->connector; - struct edid *edid = closure->edid; + const struct edid *edid = closure->edid; int i; - if (!is_display_descriptor((const u8 *)timing, EDID_DETAIL_STD_MODES)) + if (!is_display_descriptor(timing, EDID_DETAIL_STD_MODES)) return; for (i = 0; i < 6; i++) { - struct std_timing *std = &data->data.timings[i]; + const struct std_timing *std = &data->data.timings[i]; struct drm_display_mode *newmode; newmode = drm_mode_std(connector, edid, std); @@ -3146,7 +3321,7 @@ do_standard_modes(struct detailed_timing *timing, void *c) * GTF or CVT. Grab them from @edid and add them to the list. */ static int -add_standard_modes(struct drm_connector *connector, struct edid *edid) +add_standard_modes(struct drm_connector *connector, const struct edid *edid) { int i, modes = 0; struct detailed_mode_closure closure = { @@ -3166,7 +3341,7 @@ add_standard_modes(struct drm_connector *connector, struct edid *edid) } if (version_greater(edid, 1, 0)) - drm_for_each_detailed_block((u8 *)edid, do_standard_modes, + drm_for_each_detailed_block(edid, do_standard_modes, &closure); /* XXX should also look for standard codes in VTB blocks */ @@ -3175,12 +3350,12 @@ add_standard_modes(struct drm_connector *connector, struct edid *edid) } static int drm_cvt_modes(struct drm_connector *connector, - struct detailed_timing *timing) + const struct detailed_timing *timing) { int i, j, modes = 0; struct drm_display_mode *newmode; struct drm_device *dev = connector->dev; - struct cvt_timing *cvt; + const struct cvt_timing *cvt; const int rates[] = { 60, 85, 75, 60, 50 }; const u8 empty[3] = { 0, 0, 0 }; @@ -3227,18 +3402,18 @@ static int drm_cvt_modes(struct drm_connector *connector, } static void -do_cvt_mode(struct detailed_timing *timing, void *c) +do_cvt_mode(const struct detailed_timing *timing, void *c) { struct detailed_mode_closure *closure = c; - if (!is_display_descriptor((const u8 *)timing, EDID_DETAIL_CVT_3BYTE)) + if (!is_display_descriptor(timing, EDID_DETAIL_CVT_3BYTE)) return; closure->modes += drm_cvt_modes(closure->connector, timing); } static int -add_cvt_modes(struct drm_connector *connector, struct edid *edid) +add_cvt_modes(struct drm_connector *connector, const struct edid *edid) { struct detailed_mode_closure closure = { .connector = connector, @@ -3246,7 +3421,7 @@ add_cvt_modes(struct drm_connector *connector, struct edid *edid) }; if (version_greater(edid, 1, 2)) - drm_for_each_detailed_block((u8 *)edid, do_cvt_mode, &closure); + drm_for_each_detailed_block(edid, do_cvt_mode, &closure); /* XXX should also look for CVT codes in VTB blocks */ @@ -3256,12 +3431,12 @@ add_cvt_modes(struct drm_connector *connector, struct edid *edid) static void fixup_detailed_cea_mode_clock(struct drm_display_mode *mode); static void -do_detailed_mode(struct detailed_timing *timing, void *c) +do_detailed_mode(const struct detailed_timing *timing, void *c) { struct detailed_mode_closure *closure = c; struct drm_display_mode *newmode; - if (!is_detailed_timing_descriptor((const u8 *)timing)) + if (!is_detailed_timing_descriptor(timing)) return; newmode = drm_mode_detailed(closure->connector->dev, @@ -3292,7 +3467,7 @@ do_detailed_mode(struct detailed_timing *timing, void *c) * @quirks: quirks to apply */ static int -add_detailed_modes(struct drm_connector *connector, struct edid *edid, +add_detailed_modes(struct drm_connector *connector, const struct edid *edid, u32 quirks) { struct detailed_mode_closure closure = { @@ -3306,7 +3481,7 @@ add_detailed_modes(struct drm_connector *connector, struct edid *edid, closure.preferred = (edid->features & DRM_EDID_FEATURE_PREFERRED_TIMING); - drm_for_each_detailed_block((u8 *)edid, do_detailed_mode, &closure); + drm_for_each_detailed_block(edid, do_detailed_mode, &closure); return closure.modes; } @@ -3335,17 +3510,17 @@ const u8 *drm_find_edid_extension(const struct edid *edid, int i; /* No EDID or EDID extensions */ - if (edid == NULL || edid->extensions == 0) + if (!edid || !edid_extension_block_count(edid)) return NULL; /* Find CEA extension */ - for (i = *ext_index; i < edid->extensions; i++) { - edid_ext = (const u8 *)edid + EDID_LENGTH * (i + 1); - if (edid_ext[0] == ext_id) + for (i = *ext_index; i < edid_extension_block_count(edid); i++) { + edid_ext = edid_extension_block_data(edid, i); + if (edid_block_tag(edid_ext) == ext_id) break; } - if (i >= edid->extensions) + if (i >= edid_extension_block_count(edid)) return NULL; *ext_index = i + 1; @@ -3476,9 +3651,11 @@ static u8 drm_match_cea_mode_clock_tolerance(const struct drm_display_mode *to_m match_flags |= DRM_MODE_MATCH_ASPECT_RATIO; for (vic = 1; vic < cea_num_vics(); vic = cea_next_vic(vic)) { - struct drm_display_mode cea_mode = *cea_mode_for_vic(vic); + struct drm_display_mode cea_mode; unsigned int clock1, clock2; + drm_mode_init(&cea_mode, cea_mode_for_vic(vic)); + /* Check both 60Hz and 59.94Hz */ clock1 = cea_mode.clock; clock2 = cea_mode_alternate_clock(&cea_mode); @@ -3515,9 +3692,11 @@ u8 drm_match_cea_mode(const struct drm_display_mode *to_match) match_flags |= DRM_MODE_MATCH_ASPECT_RATIO; for (vic = 1; vic < cea_num_vics(); vic = cea_next_vic(vic)) { - struct drm_display_mode cea_mode = *cea_mode_for_vic(vic); + struct drm_display_mode cea_mode; unsigned int clock1, clock2; + drm_mode_init(&cea_mode, cea_mode_for_vic(vic)); + /* Check both 60Hz and 59.94Hz */ clock1 = cea_mode.clock; clock2 = cea_mode_alternate_clock(&cea_mode); @@ -3638,7 +3817,7 @@ static bool drm_valid_hdmi_vic(u8 vic) } static int -add_alternate_cea_modes(struct drm_connector *connector, struct edid *edid) +add_alternate_cea_modes(struct drm_connector *connector, const struct edid *edid) { struct drm_device *dev = connector->dev; struct drm_display_mode *mode, *tmp; @@ -4319,7 +4498,7 @@ static void drm_parse_y420cmdb_bitmap(struct drm_connector *connector, } static int -add_cea_modes(struct drm_connector *connector, struct edid *edid) +add_cea_modes(struct drm_connector *connector, const struct edid *edid) { const u8 *cea = drm_find_cea_extension(edid); const u8 *db, *hdmi = NULL, *video = NULL; @@ -4489,23 +4668,25 @@ drm_parse_hdmi_vsdb_audio(struct drm_connector *connector, const u8 *db) } static void -monitor_name(struct detailed_timing *t, void *data) +monitor_name(const struct detailed_timing *timing, void *data) { - if (!is_display_descriptor((const u8 *)t, EDID_DETAIL_MONITOR_NAME)) + const char **res = data; + + if (!is_display_descriptor(timing, EDID_DETAIL_MONITOR_NAME)) return; - *(u8 **)data = t->data.other_data.data.str.str; + *res = timing->data.other_data.data.str.str; } -static int get_monitor_name(struct edid *edid, char name[13]) +static int get_monitor_name(const struct edid *edid, char name[13]) { - char *edid_name = NULL; + const char *edid_name = NULL; int mnl; if (!edid || !name) return 0; - drm_for_each_detailed_block((u8 *)edid, monitor_name, &edid_name); + drm_for_each_detailed_block(edid, monitor_name, &edid_name); for (mnl = 0; edid_name && mnl < 13; mnl++) { if (edid_name[mnl] == 0x0a) break; @@ -4523,7 +4704,7 @@ static int get_monitor_name(struct edid *edid, char name[13]) * @bufsize: The size of the name buffer (should be at least 14 chars.) * */ -void drm_edid_get_monitor_name(struct edid *edid, char *name, int bufsize) +void drm_edid_get_monitor_name(const struct edid *edid, char *name, int bufsize) { int name_length; char buf[13]; @@ -4557,7 +4738,8 @@ static void clear_eld(struct drm_connector *connector) * Fill the ELD (EDID-Like Data) buffer for passing to the audio driver. The * HDCP and Port_ID ELD fields are left for the graphics driver to fill in. */ -static void drm_edid_to_eld(struct drm_connector *connector, struct edid *edid) +static void drm_edid_to_eld(struct drm_connector *connector, + const struct edid *edid) { uint8_t *eld = connector->eld; const u8 *cea; @@ -4653,7 +4835,7 @@ static void drm_edid_to_eld(struct drm_connector *connector, struct edid *edid) * * Return: The number of found SADs or negative number on error. */ -int drm_edid_to_sad(struct edid *edid, struct cea_sad **sads) +int drm_edid_to_sad(const struct edid *edid, struct cea_sad **sads) { int count = 0; int i, start, end, dbl; @@ -4715,7 +4897,7 @@ EXPORT_SYMBOL(drm_edid_to_sad); * Return: The number of found Speaker Allocation Blocks or negative number on * error. */ -int drm_edid_to_speaker_allocation(struct edid *edid, u8 **sadb) +int drm_edid_to_speaker_allocation(const struct edid *edid, u8 **sadb) { int count = 0; int i, start, end, dbl; @@ -4810,7 +4992,7 @@ EXPORT_SYMBOL(drm_av_sync_delay); * * Return: True if the monitor is HDMI, false if not or unknown. */ -bool drm_detect_hdmi_monitor(struct edid *edid) +bool drm_detect_hdmi_monitor(const struct edid *edid) { const u8 *edid_ext; int i; @@ -4848,7 +5030,7 @@ EXPORT_SYMBOL(drm_detect_hdmi_monitor); * * Return: True if the monitor supports audio, false otherwise. */ -bool drm_detect_monitor_audio(struct edid *edid) +bool drm_detect_monitor_audio(const struct edid *edid) { const u8 *edid_ext; int i, j; @@ -5219,14 +5401,14 @@ static void drm_parse_cea_ext(struct drm_connector *connector, } static -void get_monitor_range(struct detailed_timing *timing, +void get_monitor_range(const struct detailed_timing *timing, void *info_monitor_range) { struct drm_monitor_range_info *monitor_range = info_monitor_range; const struct detailed_non_pixel *data = &timing->data.other_data; const struct detailed_data_monitor_range *range = &data->data.range; - if (!is_display_descriptor((const u8 *)timing, EDID_DETAIL_MONITOR_RANGE)) + if (!is_display_descriptor(timing, EDID_DETAIL_MONITOR_RANGE)) return; /* @@ -5251,7 +5433,7 @@ void drm_get_monitor_range(struct drm_connector *connector, if (!version_greater(edid, 1, 1)) return; - drm_for_each_detailed_block((u8 *)edid, get_monitor_range, + drm_for_each_detailed_block(edid, get_monitor_range, &info->monitor_range); DRM_DEBUG_KMS("Supported Monitor Refresh rate range is %d Hz - %d Hz\n", @@ -5515,7 +5697,7 @@ static int add_displayid_detailed_1_modes(struct drm_connector *connector, } static int add_displayid_detailed_modes(struct drm_connector *connector, - struct edid *edid) + const struct edid *edid) { const struct displayid_block *block; struct displayid_iter iter; @@ -5532,18 +5714,8 @@ static int add_displayid_detailed_modes(struct drm_connector *connector, return num_modes; } -/** - * drm_add_edid_modes - add modes from EDID data, if available - * @connector: connector we're probing - * @edid: EDID data - * - * Add the specified modes to the connector's mode list. Also fills out the - * &drm_display_info structure and ELD in @connector with any information which - * can be derived from the edid. - * - * Return: The number of modes added or 0 if we couldn't find any. - */ -int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid) +static int drm_edid_connector_update(struct drm_connector *connector, + const struct edid *edid) { int num_modes = 0; u32 quirks; @@ -5552,12 +5724,6 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid) clear_eld(connector); return 0; } - if (!drm_edid_is_valid(edid)) { - clear_eld(connector); - drm_warn(connector->dev, "%s: EDID invalid.\n", - connector->name); - return 0; - } drm_edid_to_eld(connector, edid); @@ -5609,6 +5775,28 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid) return num_modes; } + +/** + * drm_add_edid_modes - add modes from EDID data, if available + * @connector: connector we're probing + * @edid: EDID data + * + * Add the specified modes to the connector's mode list. Also fills out the + * &drm_display_info structure and ELD in @connector with any information which + * can be derived from the edid. + * + * Return: The number of modes added or 0 if we couldn't find any. + */ +int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid) +{ + if (edid && !drm_edid_is_valid(edid)) { + drm_warn(connector->dev, "%s: EDID invalid.\n", + connector->name); + edid = NULL; + } + + return drm_edid_connector_update(connector, edid); +} EXPORT_SYMBOL(drm_add_edid_modes); /** diff --git a/drivers/gpu/drm/drm_format_helper.c b/drivers/gpu/drm/drm_format_helper.c index bc0f49773868..0e7135114728 100644 --- a/drivers/gpu/drm/drm_format_helper.c +++ b/drivers/gpu/drm/drm_format_helper.c @@ -594,37 +594,26 @@ int drm_fb_blit_toio(void __iomem *dst, unsigned int dst_pitch, uint32_t dst_for } EXPORT_SYMBOL(drm_fb_blit_toio); -static void drm_fb_gray8_to_mono_reversed_line(u8 *dst, const u8 *src, unsigned int pixels, - unsigned int start_offset, unsigned int end_len) -{ - unsigned int xb, i; - - for (xb = 0; xb < pixels; xb++) { - unsigned int start = 0, end = 8; - u8 byte = 0x00; - - if (xb == 0 && start_offset) - start = start_offset; - - if (xb == pixels - 1 && end_len) - end = end_len; - for (i = start; i < end; i++) { - unsigned int x = xb * 8 + i; +static void drm_fb_gray8_to_mono_line(u8 *dst, const u8 *src, unsigned int pixels) +{ + while (pixels) { + unsigned int i, bits = min(pixels, 8U); + u8 byte = 0; - byte >>= 1; - if (src[x] >> 7) - byte |= BIT(7); + for (i = 0; i < bits; i++, pixels--) { + if (*src++ >= 128) + byte |= BIT(i); } *dst++ = byte; } } /** - * drm_fb_xrgb8888_to_mono_reversed - Convert XRGB8888 to reversed monochrome - * @dst: reversed monochrome destination buffer + * drm_fb_xrgb8888_to_mono - Convert XRGB8888 to monochrome + * @dst: monochrome destination buffer (0=black, 1=white) * @dst_pitch: Number of bytes between two consecutive scanlines within dst - * @src: XRGB8888 source buffer + * @vaddr: XRGB8888 source buffer * @fb: DRM framebuffer * @clip: Clip rectangle area to copy * @@ -633,17 +622,23 @@ static void drm_fb_gray8_to_mono_reversed_line(u8 *dst, const u8 *src, unsigned * and use this function to convert to the native format. * * This function uses drm_fb_xrgb8888_to_gray8() to convert to grayscale and - * then the result is converted from grayscale to reversed monohrome. + * then the result is converted from grayscale to monochrome. + * + * The first pixel (upper left corner of the clip rectangle) will be converted + * and copied to the first bit (LSB) in the first byte of the monochrome + * destination buffer. + * If the caller requires that the first pixel in a byte must be located at an + * x-coordinate that is a multiple of 8, then the caller must take care itself + * of supplying a suitable clip rectangle. */ -void drm_fb_xrgb8888_to_mono_reversed(void *dst, unsigned int dst_pitch, const void *vaddr, - const struct drm_framebuffer *fb, const struct drm_rect *clip) +void drm_fb_xrgb8888_to_mono(void *dst, unsigned int dst_pitch, const void *vaddr, + const struct drm_framebuffer *fb, const struct drm_rect *clip) { unsigned int linepixels = drm_rect_width(clip); - unsigned int lines = clip->y2 - clip->y1; + unsigned int lines = drm_rect_height(clip); unsigned int cpp = fb->format->cpp[0]; unsigned int len_src32 = linepixels * cpp; struct drm_device *dev = fb->dev; - unsigned int start_offset, end_len; unsigned int y; u8 *mono = dst, *gray8; u32 *src32; @@ -652,21 +647,18 @@ void drm_fb_xrgb8888_to_mono_reversed(void *dst, unsigned int dst_pitch, const v return; /* - * The reversed mono destination buffer contains 1 bit per pixel - * and destination scanlines have to be in multiple of 8 pixels. + * The mono destination buffer contains 1 bit per pixel */ if (!dst_pitch) dst_pitch = DIV_ROUND_UP(linepixels, 8); - drm_WARN_ONCE(dev, dst_pitch % 8 != 0, "dst_pitch is not a multiple of 8\n"); - /* * The cma memory is write-combined so reads are uncached. * Speed up by fetching one line at a time. * - * Also, format conversion from XR24 to reversed monochrome - * are done line-by-line but are converted to 8-bit grayscale - * as an intermediate step. + * Also, format conversion from XR24 to monochrome are done + * line-by-line but are converted to 8-bit grayscale as an + * intermediate step. * * Allocate a buffer to be used for both copying from the cma * memory and to store the intermediate grayscale line pixels. @@ -677,27 +669,15 @@ void drm_fb_xrgb8888_to_mono_reversed(void *dst, unsigned int dst_pitch, const v gray8 = (u8 *)src32 + len_src32; - /* - * For damage handling, it is possible that only parts of the source - * buffer is copied and this could lead to start and end pixels that - * are not aligned to multiple of 8. - * - * Calculate if the start and end pixels are not aligned and set the - * offsets for the reversed mono line conversion function to adjust. - */ - start_offset = clip->x1 % 8; - end_len = clip->x2 % 8; - vaddr += clip_offset(clip, fb->pitches[0], cpp); for (y = 0; y < lines; y++) { src32 = memcpy(src32, vaddr, len_src32); drm_fb_xrgb8888_to_gray8_line(gray8, src32, linepixels); - drm_fb_gray8_to_mono_reversed_line(mono, gray8, dst_pitch, - start_offset, end_len); + drm_fb_gray8_to_mono_line(mono, gray8, linepixels); vaddr += fb->pitches[0]; mono += dst_pitch; } kfree(src32); } -EXPORT_SYMBOL(drm_fb_xrgb8888_to_mono_reversed); +EXPORT_SYMBOL(drm_fb_xrgb8888_to_mono); diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 56fb87885146..eb0c2d041f13 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -771,7 +771,8 @@ long drm_gem_dma_resv_wait(struct drm_file *filep, u32 handle, return -EINVAL; } - ret = dma_resv_wait_timeout(obj->resv, wait_all, true, timeout); + ret = dma_resv_wait_timeout(obj->resv, dma_resv_usage_rw(wait_all), + true, timeout); if (ret == 0) ret = -ETIME; else if (ret > 0) @@ -1273,83 +1274,3 @@ drm_gem_unlock_reservations(struct drm_gem_object **objs, int count, ww_acquire_fini(acquire_ctx); } EXPORT_SYMBOL(drm_gem_unlock_reservations); - -/** - * drm_gem_fence_array_add - Adds the fence to an array of fences to be - * waited on, deduplicating fences from the same context. - * - * @fence_array: array of dma_fence * for the job to block on. - * @fence: the dma_fence to add to the list of dependencies. - * - * This functions consumes the reference for @fence both on success and error - * cases. - * - * Returns: - * 0 on success, or an error on failing to expand the array. - */ -int drm_gem_fence_array_add(struct xarray *fence_array, - struct dma_fence *fence) -{ - struct dma_fence *entry; - unsigned long index; - u32 id = 0; - int ret; - - if (!fence) - return 0; - - /* Deduplicate if we already depend on a fence from the same context. - * This lets the size of the array of deps scale with the number of - * engines involved, rather than the number of BOs. - */ - xa_for_each(fence_array, index, entry) { - if (entry->context != fence->context) - continue; - - if (dma_fence_is_later(fence, entry)) { - dma_fence_put(entry); - xa_store(fence_array, index, fence, GFP_KERNEL); - } else { - dma_fence_put(fence); - } - return 0; - } - - ret = xa_alloc(fence_array, &id, fence, xa_limit_32b, GFP_KERNEL); - if (ret != 0) - dma_fence_put(fence); - - return ret; -} -EXPORT_SYMBOL(drm_gem_fence_array_add); - -/** - * drm_gem_fence_array_add_implicit - Adds the implicit dependencies tracked - * in the GEM object's reservation object to an array of dma_fences for use in - * scheduling a rendering job. - * - * This should be called after drm_gem_lock_reservations() on your array of - * GEM objects used in the job but before updating the reservations with your - * own fences. - * - * @fence_array: array of dma_fence * for the job to block on. - * @obj: the gem object to add new dependencies from. - * @write: whether the job might write the object (so we need to depend on - * shared fences in the reservation object). - */ -int drm_gem_fence_array_add_implicit(struct xarray *fence_array, - struct drm_gem_object *obj, - bool write) -{ - struct dma_resv_iter cursor; - struct dma_fence *fence; - int ret = 0; - - dma_resv_for_each_fence(&cursor, obj->resv, write, fence) { - ret = drm_gem_fence_array_add(fence_array, fence); - if (ret) - break; - } - return ret; -} -EXPORT_SYMBOL(drm_gem_fence_array_add_implicit); diff --git a/drivers/gpu/drm/drm_gem_atomic_helper.c b/drivers/gpu/drm/drm_gem_atomic_helper.c index c3189afe10cb..a6d89aed0bda 100644 --- a/drivers/gpu/drm/drm_gem_atomic_helper.c +++ b/drivers/gpu/drm/drm_gem_atomic_helper.c @@ -143,25 +143,21 @@ */ int drm_gem_plane_helper_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) { - struct dma_resv_iter cursor; struct drm_gem_object *obj; struct dma_fence *fence; + int ret; if (!state->fb) return 0; obj = drm_gem_fb_get_obj(state->fb, 0); - dma_resv_iter_begin(&cursor, obj->resv, false); - dma_resv_for_each_fence_unlocked(&cursor, fence) { - /* TODO: Currently there should be only one write fence, so this - * here works fine. But drm_atomic_set_fence_for_plane() should - * be changed to be able to handle more fences in general for - * multiple BOs per fb anyway. */ - dma_fence_get(fence); - break; - } - dma_resv_iter_end(&cursor); + ret = dma_resv_get_singleton(obj->resv, DMA_RESV_USAGE_WRITE, &fence); + if (ret) + return ret; + /* TODO: drm_atomic_set_fence_for_plane() should be changed to be able + * to handle more fences in general for multiple BOs per fb. + */ drm_atomic_set_fence_for_plane(state, fence); return 0; } diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index dc7f938bfff2..123045b58fec 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -867,7 +867,7 @@ static struct ttm_tt *bo_driver_ttm_tt_create(struct ttm_buffer_object *bo, if (!tt) return NULL; - ret = ttm_tt_init(tt, bo, page_flags, ttm_cached); + ret = ttm_tt_init(tt, bo, page_flags, ttm_cached, 0); if (ret < 0) goto err_ttm_tt_init; diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 3f819c7a021b..e699950cc34d 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -837,7 +837,9 @@ EXPORT_SYMBOL(drm_mode_vrefresh); void drm_mode_get_hv_timing(const struct drm_display_mode *mode, int *hdisplay, int *vdisplay) { - struct drm_display_mode adjusted = *mode; + struct drm_display_mode adjusted; + + drm_mode_init(&adjusted, mode); drm_mode_set_crtcinfo(&adjusted, CRTC_STEREO_DOUBLE_ONLY); *hdisplay = adjusted.crtc_hdisplay; @@ -942,6 +944,23 @@ void drm_mode_copy(struct drm_display_mode *dst, const struct drm_display_mode * EXPORT_SYMBOL(drm_mode_copy); /** + * drm_mode_init - initialize the mode from another mode + * @dst: mode to overwrite + * @src: mode to copy + * + * Copy an existing mode into another mode, zeroing the + * list head of the destination mode. Typically used + * to guarantee the list head is not left with stack + * garbage in on-stack modes. + */ +void drm_mode_init(struct drm_display_mode *dst, const struct drm_display_mode *src) +{ + memset(dst, 0, sizeof(*dst)); + drm_mode_copy(dst, src); +} +EXPORT_SYMBOL(drm_mode_init); + +/** * drm_mode_duplicate - allocate and duplicate an existing mode * @dev: drm_device to allocate the duplicated mode for * @mode: mode to duplicate diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c index 026e4e29a0f3..f4df344509a8 100644 --- a/drivers/gpu/drm/drm_of.c +++ b/drivers/gpu/drm/drm_of.c @@ -214,6 +214,29 @@ int drm_of_encoder_active_endpoint(struct device_node *node, } EXPORT_SYMBOL_GPL(drm_of_encoder_active_endpoint); +static int find_panel_or_bridge(struct device_node *node, + struct drm_panel **panel, + struct drm_bridge **bridge) +{ + if (panel) { + *panel = of_drm_find_panel(node); + if (!IS_ERR(*panel)) + return 0; + + /* Clear the panel pointer in case of error. */ + *panel = NULL; + } + + /* No panel found yet, check for a bridge next. */ + if (bridge) { + *bridge = of_drm_find_bridge(node); + if (*bridge) + return 0; + } + + return -EPROBE_DEFER; +} + /** * drm_of_find_panel_or_bridge - return connected panel or bridge device * @np: device tree node containing encoder output ports @@ -236,66 +259,44 @@ int drm_of_find_panel_or_bridge(const struct device_node *np, struct drm_panel **panel, struct drm_bridge **bridge) { - int ret = -EPROBE_DEFER; - struct device_node *remote; + struct device_node *node; + int ret; if (!panel && !bridge) return -EINVAL; + if (panel) *panel = NULL; - - /** - * Devices can also be child nodes when we also control that device - * through the upstream device (ie, MIPI-DCS for a MIPI-DSI device). - * - * Lookup for a child node of the given parent that isn't either port - * or ports. - */ - for_each_available_child_of_node(np, remote) { - if (of_node_name_eq(remote, "port") || - of_node_name_eq(remote, "ports")) - continue; - - goto of_find_panel_or_bridge; + if (bridge) + *bridge = NULL; + + /* Check for a graph on the device node first. */ + if (of_graph_is_present(np)) { + node = of_graph_get_remote_node(np, port, endpoint); + if (node) { + ret = find_panel_or_bridge(node, panel, bridge); + of_node_put(node); + + if (!ret) + return 0; + } } - /* - * of_graph_get_remote_node() produces a noisy error message if port - * node isn't found and the absence of the port is a legit case here, - * so at first we silently check whether graph presents in the - * device-tree node. - */ - if (!of_graph_is_present(np)) - return -ENODEV; - - remote = of_graph_get_remote_node(np, port, endpoint); - -of_find_panel_or_bridge: - if (!remote) - return -ENODEV; + /* Otherwise check for any child node other than port/ports. */ + for_each_available_child_of_node(np, node) { + if (of_node_name_eq(node, "port") || + of_node_name_eq(node, "ports")) + continue; - if (panel) { - *panel = of_drm_find_panel(remote); - if (!IS_ERR(*panel)) - ret = 0; - else - *panel = NULL; - } - - /* No panel found yet, check for a bridge next. */ - if (bridge) { - if (ret) { - *bridge = of_drm_find_bridge(remote); - if (*bridge) - ret = 0; - } else { - *bridge = NULL; - } + ret = find_panel_or_bridge(node, panel, bridge); + of_node_put(node); + /* Stop at the first found occurrence. */ + if (!ret) + return 0; } - of_node_put(remote); - return ret; + return -EPROBE_DEFER; } EXPORT_SYMBOL_GPL(drm_of_find_panel_or_bridge); diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c index b701cda86d0c..2ff31717a3de 100644 --- a/drivers/gpu/drm/drm_vblank.c +++ b/drivers/gpu/drm/drm_vblank.c @@ -644,7 +644,7 @@ void drm_calc_timestamping_constants(struct drm_crtc *crtc, vblank->linedur_ns = linedur_ns; vblank->framedur_ns = framedur_ns; - vblank->hwmode = *mode; + drm_mode_copy(&vblank->hwmode, mode); drm_dbg_core(dev, "crtc %u: hwmode: htotal %d, vtotal %d, vdisplay %d\n", diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index d5314aa28ff7..507172e2780b 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -380,12 +380,14 @@ int etnaviv_gem_cpu_prep(struct drm_gem_object *obj, u32 op, } if (op & ETNA_PREP_NOSYNC) { - if (!dma_resv_test_signaled(obj->resv, write)) + if (!dma_resv_test_signaled(obj->resv, + dma_resv_usage_rw(write))) return -EBUSY; } else { unsigned long remain = etnaviv_timeout_to_jiffies(timeout); - ret = dma_resv_wait_timeout(obj->resv, write, true, remain); + ret = dma_resv_wait_timeout(obj->resv, dma_resv_usage_rw(write), + true, remain); if (ret <= 0) return ret == 0 ? -ETIMEDOUT : ret; } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.h b/drivers/gpu/drm/etnaviv/etnaviv_gem.h index 98e60df882b6..63688e6e4580 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.h @@ -80,9 +80,6 @@ struct etnaviv_gem_submit_bo { u64 va; struct etnaviv_gem_object *obj; struct etnaviv_vram_mapping *mapping; - struct dma_fence *excl; - unsigned int nr_shared; - struct dma_fence **shared; }; /* Created per submit-ioctl, to track bo's and cmdstream bufs, etc, @@ -95,7 +92,7 @@ struct etnaviv_gem_submit { struct etnaviv_file_private *ctx; struct etnaviv_gpu *gpu; struct etnaviv_iommu_context *mmu_context, *prev_mmu_context; - struct dma_fence *out_fence, *in_fence; + struct dma_fence *out_fence; int out_fence_id; struct list_head node; /* GPU active submit list */ struct etnaviv_cmdbuf cmdbuf; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c index 4eb00a0cb650..98bb5c9239de 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c @@ -179,24 +179,18 @@ static int submit_fence_sync(struct etnaviv_gem_submit *submit) struct etnaviv_gem_submit_bo *bo = &submit->bos[i]; struct dma_resv *robj = bo->obj->base.resv; - if (!(bo->flags & ETNA_SUBMIT_BO_WRITE)) { - ret = dma_resv_reserve_shared(robj, 1); - if (ret) - return ret; - } + ret = dma_resv_reserve_fences(robj, 1); + if (ret) + return ret; if (submit->flags & ETNA_SUBMIT_NO_IMPLICIT) continue; - if (bo->flags & ETNA_SUBMIT_BO_WRITE) { - ret = dma_resv_get_fences(robj, true, &bo->nr_shared, - &bo->shared); - if (ret) - return ret; - } else { - bo->excl = dma_fence_get(dma_resv_excl_fence(robj)); - } - + ret = drm_sched_job_add_implicit_dependencies(&submit->sched_job, + &bo->obj->base, + bo->flags & ETNA_SUBMIT_BO_WRITE); + if (ret) + return ret; } return ret; @@ -208,14 +202,10 @@ static void submit_attach_object_fences(struct etnaviv_gem_submit *submit) for (i = 0; i < submit->nr_bos; i++) { struct drm_gem_object *obj = &submit->bos[i].obj->base; + bool write = submit->bos[i].flags & ETNA_SUBMIT_BO_WRITE; - if (submit->bos[i].flags & ETNA_SUBMIT_BO_WRITE) - dma_resv_add_excl_fence(obj->resv, - submit->out_fence); - else - dma_resv_add_shared_fence(obj->resv, - submit->out_fence); - + dma_resv_add_fence(obj->resv, submit->out_fence, write ? + DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ); submit_unlock_object(submit, i); } } @@ -402,8 +392,6 @@ static void submit_cleanup(struct kref *kref) wake_up_all(&submit->gpu->fence_event); - if (submit->in_fence) - dma_fence_put(submit->in_fence); if (submit->out_fence) { /* first remove from IDR, so fence can not be found anymore */ mutex_lock(&submit->gpu->fence_lock); @@ -534,58 +522,69 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, ret = etnaviv_cmdbuf_init(priv->cmdbuf_suballoc, &submit->cmdbuf, ALIGN(args->stream_size, 8) + 8); if (ret) - goto err_submit_objects; + goto err_submit_put; submit->ctx = file->driver_priv; submit->mmu_context = etnaviv_iommu_context_get(submit->ctx->mmu); submit->exec_state = args->exec_state; submit->flags = args->flags; + ret = drm_sched_job_init(&submit->sched_job, + &ctx->sched_entity[args->pipe], + submit->ctx); + if (ret) + goto err_submit_put; + ret = submit_lookup_objects(submit, file, bos, args->nr_bos); if (ret) - goto err_submit_objects; + goto err_submit_job; if ((priv->mmu_global->version != ETNAVIV_IOMMU_V2) && !etnaviv_cmd_validate_one(gpu, stream, args->stream_size / 4, relocs, args->nr_relocs)) { ret = -EINVAL; - goto err_submit_objects; + goto err_submit_job; } if (args->flags & ETNA_SUBMIT_FENCE_FD_IN) { - submit->in_fence = sync_file_get_fence(args->fence_fd); - if (!submit->in_fence) { + struct dma_fence *in_fence = sync_file_get_fence(args->fence_fd); + if (!in_fence) { ret = -EINVAL; - goto err_submit_objects; + goto err_submit_job; } + + ret = drm_sched_job_add_dependency(&submit->sched_job, + in_fence); + if (ret) + goto err_submit_job; } ret = submit_pin_objects(submit); if (ret) - goto err_submit_objects; + goto err_submit_job; ret = submit_reloc(submit, stream, args->stream_size / 4, relocs, args->nr_relocs); if (ret) - goto err_submit_objects; + goto err_submit_job; ret = submit_perfmon_validate(submit, args->exec_state, pmrs); if (ret) - goto err_submit_objects; + goto err_submit_job; memcpy(submit->cmdbuf.vaddr, stream, args->stream_size); ret = submit_lock_objects(submit, &ticket); if (ret) - goto err_submit_objects; + goto err_submit_job; ret = submit_fence_sync(submit); if (ret) - goto err_submit_objects; + goto err_submit_job; - ret = etnaviv_sched_push_job(&ctx->sched_entity[args->pipe], submit); + ret = etnaviv_sched_push_job(submit); if (ret) - goto err_submit_objects; + goto err_submit_job; submit_attach_object_fences(submit); @@ -599,7 +598,7 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, sync_file = sync_file_create(submit->out_fence); if (!sync_file) { ret = -ENOMEM; - goto err_submit_objects; + goto err_submit_job; } fd_install(out_fence_fd, sync_file->file); } @@ -607,7 +606,9 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data, args->fence_fd = out_fence_fd; args->fence = submit->out_fence_id; -err_submit_objects: +err_submit_job: + drm_sched_job_cleanup(&submit->sched_job); +err_submit_put: etnaviv_submit_put(submit); err_submit_ww_acquire: diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 35e5ef7dbdcc..72e2553fbc98 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -17,58 +17,6 @@ module_param_named(job_hang_limit, etnaviv_job_hang_limit, int , 0444); static int etnaviv_hw_jobs_limit = 4; module_param_named(hw_job_limit, etnaviv_hw_jobs_limit, int , 0444); -static struct dma_fence * -etnaviv_sched_dependency(struct drm_sched_job *sched_job, - struct drm_sched_entity *entity) -{ - struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job); - struct dma_fence *fence; - int i; - - if (unlikely(submit->in_fence)) { - fence = submit->in_fence; - submit->in_fence = NULL; - - if (!dma_fence_is_signaled(fence)) - return fence; - - dma_fence_put(fence); - } - - for (i = 0; i < submit->nr_bos; i++) { - struct etnaviv_gem_submit_bo *bo = &submit->bos[i]; - int j; - - if (bo->excl) { - fence = bo->excl; - bo->excl = NULL; - - if (!dma_fence_is_signaled(fence)) - return fence; - - dma_fence_put(fence); - } - - for (j = 0; j < bo->nr_shared; j++) { - if (!bo->shared[j]) - continue; - - fence = bo->shared[j]; - bo->shared[j] = NULL; - - if (!dma_fence_is_signaled(fence)) - return fence; - - dma_fence_put(fence); - } - kfree(bo->shared); - bo->nr_shared = 0; - bo->shared = NULL; - } - - return NULL; -} - static struct dma_fence *etnaviv_sched_run_job(struct drm_sched_job *sched_job) { struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job); @@ -142,29 +90,22 @@ static void etnaviv_sched_free_job(struct drm_sched_job *sched_job) } static const struct drm_sched_backend_ops etnaviv_sched_ops = { - .dependency = etnaviv_sched_dependency, .run_job = etnaviv_sched_run_job, .timedout_job = etnaviv_sched_timedout_job, .free_job = etnaviv_sched_free_job, }; -int etnaviv_sched_push_job(struct drm_sched_entity *sched_entity, - struct etnaviv_gem_submit *submit) +int etnaviv_sched_push_job(struct etnaviv_gem_submit *submit) { int ret = 0; /* * Hold the fence lock across the whole operation to avoid jobs being * pushed out of order with regard to their sched fence seqnos as - * allocated in drm_sched_job_init. + * allocated in drm_sched_job_arm. */ mutex_lock(&submit->gpu->fence_lock); - ret = drm_sched_job_init(&submit->sched_job, sched_entity, - submit->ctx); - if (ret) - goto out_unlock; - drm_sched_job_arm(&submit->sched_job); submit->out_fence = dma_fence_get(&submit->sched_job.s_fence->finished); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.h b/drivers/gpu/drm/etnaviv/etnaviv_sched.h index c0a6796e22c9..baebfa069afc 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.h +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.h @@ -18,7 +18,6 @@ struct etnaviv_gem_submit *to_etnaviv_submit(struct drm_sched_job *sched_job) int etnaviv_sched_init(struct etnaviv_gpu *gpu); void etnaviv_sched_fini(struct etnaviv_gpu *gpu); -int etnaviv_sched_push_job(struct drm_sched_entity *sched_entity, - struct etnaviv_gem_submit *submit); +int etnaviv_sched_push_job(struct etnaviv_gem_submit *submit); #endif /* __ETNAVIV_SCHED_H__ */ diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 334862d422e2..f067c86b0b12 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -24,9 +24,7 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_bridge.h> -#include <drm/drm_fb_helper.h> #include <drm/drm_mipi_dsi.h> -#include <drm/drm_panel.h> #include <drm/drm_print.h> #include <drm/drm_probe_helper.h> #include <drm/drm_simple_kms_helper.h> @@ -253,9 +251,7 @@ struct exynos_dsi_driver_data { struct exynos_dsi { struct drm_encoder encoder; struct mipi_dsi_host dsi_host; - struct drm_connector connector; - struct drm_panel *panel; - struct list_head bridge_chain; + struct drm_bridge bridge; struct drm_bridge *out_bridge; struct device *dev; struct drm_display_mode mode; @@ -285,11 +281,10 @@ struct exynos_dsi { }; #define host_to_dsi(host) container_of(host, struct exynos_dsi, dsi_host) -#define connector_to_dsi(c) container_of(c, struct exynos_dsi, connector) -static inline struct exynos_dsi *encoder_to_dsi(struct drm_encoder *e) +static inline struct exynos_dsi *bridge_to_dsi(struct drm_bridge *b) { - return container_of(e, struct exynos_dsi, encoder); + return container_of(b, struct exynos_dsi, bridge); } enum reg_idx { @@ -1365,10 +1360,10 @@ static void exynos_dsi_unregister_te_irq(struct exynos_dsi *dsi) } } -static void exynos_dsi_enable(struct drm_encoder *encoder) +static void exynos_dsi_atomic_pre_enable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) { - struct exynos_dsi *dsi = encoder_to_dsi(encoder); - struct drm_bridge *iter; + struct exynos_dsi *dsi = bridge_to_dsi(bridge); int ret; if (dsi->state & DSIM_STATE_ENABLED) @@ -1381,151 +1376,70 @@ static void exynos_dsi_enable(struct drm_encoder *encoder) } dsi->state |= DSIM_STATE_ENABLED; +} - if (dsi->panel) { - ret = drm_panel_prepare(dsi->panel); - if (ret < 0) - goto err_put_sync; - } else { - list_for_each_entry_reverse(iter, &dsi->bridge_chain, - chain_node) { - if (iter->funcs->pre_enable) - iter->funcs->pre_enable(iter); - } - } +static void exynos_dsi_atomic_enable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) +{ + struct exynos_dsi *dsi = bridge_to_dsi(bridge); exynos_dsi_set_display_mode(dsi); exynos_dsi_set_display_enable(dsi, true); - if (dsi->panel) { - ret = drm_panel_enable(dsi->panel); - if (ret < 0) - goto err_display_disable; - } else { - list_for_each_entry(iter, &dsi->bridge_chain, chain_node) { - if (iter->funcs->enable) - iter->funcs->enable(iter); - } - } - dsi->state |= DSIM_STATE_VIDOUT_AVAILABLE; - return; - -err_display_disable: - exynos_dsi_set_display_enable(dsi, false); - drm_panel_unprepare(dsi->panel); -err_put_sync: - dsi->state &= ~DSIM_STATE_ENABLED; - pm_runtime_put(dsi->dev); + return; } -static void exynos_dsi_disable(struct drm_encoder *encoder) +static void exynos_dsi_atomic_disable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) { - struct exynos_dsi *dsi = encoder_to_dsi(encoder); - struct drm_bridge *iter; + struct exynos_dsi *dsi = bridge_to_dsi(bridge); if (!(dsi->state & DSIM_STATE_ENABLED)) return; dsi->state &= ~DSIM_STATE_VIDOUT_AVAILABLE; +} - drm_panel_disable(dsi->panel); - - list_for_each_entry_reverse(iter, &dsi->bridge_chain, chain_node) { - if (iter->funcs->disable) - iter->funcs->disable(iter); - } +static void exynos_dsi_atomic_post_disable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) +{ + struct exynos_dsi *dsi = bridge_to_dsi(bridge); exynos_dsi_set_display_enable(dsi, false); - drm_panel_unprepare(dsi->panel); - - list_for_each_entry(iter, &dsi->bridge_chain, chain_node) { - if (iter->funcs->post_disable) - iter->funcs->post_disable(iter); - } dsi->state &= ~DSIM_STATE_ENABLED; pm_runtime_put_sync(dsi->dev); } -static void exynos_dsi_mode_set(struct drm_encoder *encoder, - struct drm_display_mode *mode, - struct drm_display_mode *adjusted_mode) +static void exynos_dsi_mode_set(struct drm_bridge *bridge, + const struct drm_display_mode *mode, + const struct drm_display_mode *adjusted_mode) { - struct exynos_dsi *dsi = encoder_to_dsi(encoder); + struct exynos_dsi *dsi = bridge_to_dsi(bridge); drm_mode_copy(&dsi->mode, adjusted_mode); } -static enum drm_connector_status -exynos_dsi_detect(struct drm_connector *connector, bool force) -{ - return connector->status; -} - -static void exynos_dsi_connector_destroy(struct drm_connector *connector) -{ - drm_connector_unregister(connector); - drm_connector_cleanup(connector); - connector->dev = NULL; -} - -static const struct drm_connector_funcs exynos_dsi_connector_funcs = { - .detect = exynos_dsi_detect, - .fill_modes = drm_helper_probe_single_connector_modes, - .destroy = exynos_dsi_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 exynos_dsi_get_modes(struct drm_connector *connector) +static int exynos_dsi_attach(struct drm_bridge *bridge, + enum drm_bridge_attach_flags flags) { - struct exynos_dsi *dsi = connector_to_dsi(connector); - - if (dsi->panel) - return drm_panel_get_modes(dsi->panel, connector); + struct exynos_dsi *dsi = bridge_to_dsi(bridge); - return 0; + return drm_bridge_attach(bridge->encoder, dsi->out_bridge, NULL, flags); } -static const struct drm_connector_helper_funcs exynos_dsi_connector_helper_funcs = { - .get_modes = exynos_dsi_get_modes, -}; - -static int exynos_dsi_create_connector(struct drm_encoder *encoder) -{ - struct exynos_dsi *dsi = encoder_to_dsi(encoder); - struct drm_connector *connector = &dsi->connector; - struct drm_device *drm = encoder->dev; - int ret; - - connector->polled = DRM_CONNECTOR_POLL_HPD; - - ret = drm_connector_init(drm, connector, &exynos_dsi_connector_funcs, - DRM_MODE_CONNECTOR_DSI); - if (ret) { - DRM_DEV_ERROR(dsi->dev, - "Failed to initialize connector with drm\n"); - return ret; - } - - connector->status = connector_status_disconnected; - drm_connector_helper_add(connector, &exynos_dsi_connector_helper_funcs); - drm_connector_attach_encoder(connector, encoder); - if (!drm->registered) - return 0; - - connector->funcs->reset(connector); - drm_connector_register(connector); - return 0; -} - -static const struct drm_encoder_helper_funcs exynos_dsi_encoder_helper_funcs = { - .enable = exynos_dsi_enable, - .disable = exynos_dsi_disable, - .mode_set = exynos_dsi_mode_set, +static const struct drm_bridge_funcs exynos_dsi_bridge_funcs = { + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, + .atomic_reset = drm_atomic_helper_bridge_reset, + .atomic_pre_enable = exynos_dsi_atomic_pre_enable, + .atomic_enable = exynos_dsi_atomic_enable, + .atomic_disable = exynos_dsi_atomic_disable, + .atomic_post_disable = exynos_dsi_atomic_post_disable, + .mode_set = exynos_dsi_mode_set, + .attach = exynos_dsi_attach, }; MODULE_DEVICE_TABLE(of, exynos_dsi_of_match); @@ -1534,33 +1448,24 @@ static int exynos_dsi_host_attach(struct mipi_dsi_host *host, struct mipi_dsi_device *device) { struct exynos_dsi *dsi = host_to_dsi(host); + struct device *dev = dsi->dev; struct drm_encoder *encoder = &dsi->encoder; struct drm_device *drm = encoder->dev; - struct drm_bridge *out_bridge; - - out_bridge = of_drm_find_bridge(device->dev.of_node); - if (out_bridge) { - drm_bridge_attach(encoder, out_bridge, NULL, 0); - dsi->out_bridge = out_bridge; - list_splice_init(&encoder->bridge_chain, &dsi->bridge_chain); - } else { - int ret = exynos_dsi_create_connector(encoder); - - if (ret) { - DRM_DEV_ERROR(dsi->dev, - "failed to create connector ret = %d\n", - ret); - drm_encoder_cleanup(encoder); - return ret; - } + int ret; - dsi->panel = of_drm_find_panel(device->dev.of_node); - if (IS_ERR(dsi->panel)) - dsi->panel = NULL; - else - dsi->connector.status = connector_status_connected; + dsi->out_bridge = devm_drm_of_get_bridge(dev, dev->of_node, 1, 0); + if (IS_ERR(dsi->out_bridge)) { + ret = PTR_ERR(dsi->out_bridge); + DRM_DEV_ERROR(dev, "failed to find the bridge: %d\n", ret); + return ret; } + DRM_DEV_INFO(dev, "Attached %s device\n", device->name); + + drm_bridge_add(&dsi->bridge); + + drm_bridge_attach(encoder, &dsi->bridge, NULL, 0); + /* * This is a temporary solution and should be made by more generic way. * @@ -1568,7 +1473,7 @@ static int exynos_dsi_host_attach(struct mipi_dsi_host *host, * TE interrupt handler. */ if (!(device->mode_flags & MIPI_DSI_MODE_VIDEO)) { - int ret = exynos_dsi_register_te_irq(dsi, &device->dev); + ret = exynos_dsi_register_te_irq(dsi, &device->dev); if (ret) return ret; } @@ -1595,24 +1500,17 @@ static int exynos_dsi_host_detach(struct mipi_dsi_host *host, struct exynos_dsi *dsi = host_to_dsi(host); struct drm_device *drm = dsi->encoder.dev; - if (dsi->panel) { - mutex_lock(&drm->mode_config.mutex); - exynos_dsi_disable(&dsi->encoder); - dsi->panel = NULL; - dsi->connector.status = connector_status_disconnected; - mutex_unlock(&drm->mode_config.mutex); - } else { - if (dsi->out_bridge->funcs->detach) - dsi->out_bridge->funcs->detach(dsi->out_bridge); - dsi->out_bridge = NULL; - INIT_LIST_HEAD(&dsi->bridge_chain); - } + if (dsi->out_bridge->funcs->detach) + dsi->out_bridge->funcs->detach(dsi->out_bridge); + dsi->out_bridge = NULL; if (drm->mode_config.poll_enabled) drm_kms_helper_hotplug_event(drm); exynos_dsi_unregister_te_irq(dsi); + drm_bridge_remove(&dsi->bridge); + return 0; } @@ -1662,11 +1560,6 @@ static int exynos_dsi_of_read_u32(const struct device_node *np, return ret; } -enum { - DSI_PORT_IN, - DSI_PORT_OUT -}; - static int exynos_dsi_parse_dt(struct exynos_dsi *dsi) { struct device *dev = dsi->dev; @@ -1697,26 +1590,14 @@ static int exynos_dsi_bind(struct device *dev, struct device *master, struct exynos_dsi *dsi = dev_get_drvdata(dev); struct drm_encoder *encoder = &dsi->encoder; struct drm_device *drm_dev = data; - struct device_node *in_bridge_node; - struct drm_bridge *in_bridge; int ret; drm_simple_encoder_init(drm_dev, encoder, DRM_MODE_ENCODER_TMDS); - drm_encoder_helper_add(encoder, &exynos_dsi_encoder_helper_funcs); - ret = exynos_drm_set_possible_crtcs(encoder, EXYNOS_DISPLAY_TYPE_LCD); if (ret < 0) return ret; - in_bridge_node = of_graph_get_remote_node(dev->of_node, DSI_PORT_IN, 0); - if (in_bridge_node) { - in_bridge = of_drm_find_bridge(in_bridge_node); - if (in_bridge) - drm_bridge_attach(encoder, in_bridge, NULL, 0); - of_node_put(in_bridge_node); - } - return mipi_dsi_host_register(&dsi->dsi_host); } @@ -1724,9 +1605,8 @@ static void exynos_dsi_unbind(struct device *dev, struct device *master, void *data) { struct exynos_dsi *dsi = dev_get_drvdata(dev); - struct drm_encoder *encoder = &dsi->encoder; - exynos_dsi_disable(encoder); + exynos_dsi_atomic_disable(&dsi->bridge, NULL); mipi_dsi_host_unregister(&dsi->dsi_host); } @@ -1749,7 +1629,6 @@ static int exynos_dsi_probe(struct platform_device *pdev) init_completion(&dsi->completed); spin_lock_init(&dsi->transfer_lock); INIT_LIST_HEAD(&dsi->transfer_list); - INIT_LIST_HEAD(&dsi->bridge_chain); dsi->dsi_host.ops = &exynos_dsi_ops; dsi->dsi_host.dev = dev; @@ -1817,6 +1696,10 @@ static int exynos_dsi_probe(struct platform_device *pdev) pm_runtime_enable(dev); + dsi->bridge.funcs = &exynos_dsi_bridge_funcs; + dsi->bridge.of_node = dev->of_node; + dsi->bridge.type = DRM_MODE_CONNECTOR_DSI; + ret = component_add(dev, &exynos_dsi_component_ops); if (ret) goto err_disable_runtime; diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c index 32672bf8ae4a..9e06f8e2a863 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_mic.c +++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c @@ -102,6 +102,7 @@ struct exynos_mic { struct videomode vm; struct drm_encoder *encoder; struct drm_bridge bridge; + struct drm_bridge *next_bridge; bool enabled; }; @@ -298,12 +299,22 @@ unlock: static void mic_enable(struct drm_bridge *bridge) { } +static int mic_attach(struct drm_bridge *bridge, + enum drm_bridge_attach_flags flags) +{ + struct exynos_mic *mic = bridge->driver_private; + + return drm_bridge_attach(bridge->encoder, mic->next_bridge, + &mic->bridge, flags); +} + static const struct drm_bridge_funcs mic_bridge_funcs = { .disable = mic_disable, .post_disable = mic_post_disable, .mode_set = mic_mode_set, .pre_enable = mic_pre_enable, .enable = mic_enable, + .attach = mic_attach, }; static int exynos_mic_bind(struct device *dev, struct device *master, @@ -377,6 +388,7 @@ static int exynos_mic_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct exynos_mic *mic; + struct device_node *remote; struct resource res; int ret, i; @@ -420,6 +432,16 @@ static int exynos_mic_probe(struct platform_device *pdev) } } + remote = of_graph_get_remote_node(dev->of_node, 1, 0); + mic->next_bridge = of_drm_find_bridge(remote); + if (IS_ERR(mic->next_bridge)) { + DRM_DEV_ERROR(dev, "mic: Failed to find next bridge\n"); + ret = PTR_ERR(mic->next_bridge); + goto err; + } + + of_node_put(remote); + platform_set_drvdata(pdev, mic); mic->bridge.funcs = &mic_bridge_funcs; diff --git a/drivers/gpu/drm/gma500/cdv_device.c b/drivers/gpu/drm/gma500/cdv_device.c index d7c6cca23e94..dd32b484dd82 100644 --- a/drivers/gpu/drm/gma500/cdv_device.c +++ b/drivers/gpu/drm/gma500/cdv_device.c @@ -262,6 +262,7 @@ static int cdv_save_display_registers(struct drm_device *dev) struct drm_psb_private *dev_priv = to_drm_psb_private(dev); struct pci_dev *pdev = to_pci_dev(dev->dev); struct psb_save_area *regs = &dev_priv->regs; + struct drm_connector_list_iter conn_iter; struct drm_connector *connector; dev_dbg(dev->dev, "Saving GPU registers.\n"); @@ -298,8 +299,10 @@ static int cdv_save_display_registers(struct drm_device *dev) regs->cdv.saveIER = REG_READ(PSB_INT_ENABLE_R); regs->cdv.saveIMR = REG_READ(PSB_INT_MASK_R); - list_for_each_entry(connector, &dev->mode_config.connector_list, head) + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) connector->funcs->dpms(connector, DRM_MODE_DPMS_OFF); + drm_connector_list_iter_end(&conn_iter); return 0; } @@ -317,6 +320,7 @@ static int cdv_restore_display_registers(struct drm_device *dev) struct drm_psb_private *dev_priv = to_drm_psb_private(dev); struct pci_dev *pdev = to_pci_dev(dev->dev); struct psb_save_area *regs = &dev_priv->regs; + struct drm_connector_list_iter conn_iter; struct drm_connector *connector; u32 temp; @@ -373,8 +377,10 @@ static int cdv_restore_display_registers(struct drm_device *dev) drm_mode_config_reset(dev); - list_for_each_entry(connector, &dev->mode_config.connector_list, head) + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) connector->funcs->dpms(connector, DRM_MODE_DPMS_ON); + drm_connector_list_iter_end(&conn_iter); /* Resume the modeset for every activated CRTC */ drm_helper_resume_force_mode(dev); @@ -603,7 +609,6 @@ const struct psb_ops cdv_chip_ops = { .errata = cdv_errata, .crtc_helper = &cdv_intel_helper_funcs, - .crtc_funcs = &gma_intel_crtc_funcs, .clock_funcs = &cdv_clock_funcs, .output_init = cdv_output_init, diff --git a/drivers/gpu/drm/gma500/cdv_intel_crt.c b/drivers/gpu/drm/gma500/cdv_intel_crt.c index 4a9bb4994a26..6bcd18c63c31 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_crt.c +++ b/drivers/gpu/drm/gma500/cdv_intel_crt.c @@ -191,12 +191,12 @@ static enum drm_connector_status cdv_intel_crt_detect( static void cdv_intel_crt_destroy(struct drm_connector *connector) { + struct gma_connector *gma_connector = to_gma_connector(connector); struct gma_encoder *gma_encoder = gma_attached_encoder(connector); psb_intel_i2c_destroy(gma_encoder->ddc_bus); - drm_connector_unregister(connector); drm_connector_cleanup(connector); - kfree(connector); + kfree(gma_connector); } static int cdv_intel_crt_get_modes(struct drm_connector *connector) @@ -281,8 +281,6 @@ void cdv_intel_crt_init(struct drm_device *dev, drm_connector_helper_add(connector, &cdv_intel_crt_connector_helper_funcs); - drm_connector_register(connector); - return; failed_ddc: drm_encoder_cleanup(&gma_encoder->base); diff --git a/drivers/gpu/drm/gma500/cdv_intel_display.c b/drivers/gpu/drm/gma500/cdv_intel_display.c index 94ebc48a4349..0c3ddcdc29dc 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_display.c +++ b/drivers/gpu/drm/gma500/cdv_intel_display.c @@ -584,13 +584,14 @@ static int cdv_intel_crtc_mode_set(struct drm_crtc *crtc, bool ok; bool is_lvds = false; bool is_dp = false; - struct drm_mode_config *mode_config = &dev->mode_config; + struct drm_connector_list_iter conn_iter; struct drm_connector *connector; const struct gma_limit_t *limit; u32 ddi_select = 0; bool is_edp = false; - list_for_each_entry(connector, &mode_config->connector_list, head) { + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { struct gma_encoder *gma_encoder = gma_attached_encoder(connector); @@ -613,10 +614,14 @@ static int cdv_intel_crtc_mode_set(struct drm_crtc *crtc, is_edp = true; break; default: + drm_connector_list_iter_end(&conn_iter); DRM_ERROR("invalid output type.\n"); return 0; } + + break; } + drm_connector_list_iter_end(&conn_iter); if (dev_priv->dplla_96mhz) /* low-end sku, 96/100 mhz */ diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c index f562e91337c7..72b1b2fc3c27 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_dp.c +++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c @@ -1857,6 +1857,7 @@ done: static void cdv_intel_dp_destroy(struct drm_connector *connector) { + struct gma_connector *gma_connector = to_gma_connector(connector); struct gma_encoder *gma_encoder = gma_attached_encoder(connector); struct cdv_intel_dp *intel_dp = gma_encoder->dev_priv; @@ -1866,9 +1867,8 @@ cdv_intel_dp_destroy(struct drm_connector *connector) intel_dp->panel_fixed_mode = NULL; } i2c_del_adapter(&intel_dp->adapter); - drm_connector_unregister(connector); drm_connector_cleanup(connector); - kfree(connector); + kfree(gma_connector); } static const struct drm_encoder_helper_funcs cdv_intel_dp_helper_funcs = { @@ -1990,8 +1990,6 @@ cdv_intel_dp_init(struct drm_device *dev, struct psb_intel_mode_device *mode_dev connector->interlace_allowed = false; connector->doublescan_allowed = false; - drm_connector_register(connector); - /* Set up the DDC bus. */ switch (output_reg) { case DP_B: diff --git a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c index e525689f84f0..8987e555e113 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c +++ b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c @@ -242,12 +242,12 @@ static enum drm_mode_status cdv_hdmi_mode_valid(struct drm_connector *connector, static void cdv_hdmi_destroy(struct drm_connector *connector) { + struct gma_connector *gma_connector = to_gma_connector(connector); struct gma_encoder *gma_encoder = gma_attached_encoder(connector); psb_intel_i2c_destroy(gma_encoder->i2c_bus); - drm_connector_unregister(connector); drm_connector_cleanup(connector); - kfree(connector); + kfree(gma_connector); } static const struct drm_encoder_helper_funcs cdv_hdmi_helper_funcs = { @@ -352,7 +352,6 @@ void cdv_hdmi_init(struct drm_device *dev, hdmi_priv->hdmi_i2c_adapter = &(gma_encoder->i2c_bus->adapter); hdmi_priv->dev = dev; - drm_connector_register(connector); return; failed_ddc: diff --git a/drivers/gpu/drm/gma500/cdv_intel_lvds.c b/drivers/gpu/drm/gma500/cdv_intel_lvds.c index 9e1cdb11023c..98d9f5483a7c 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_lvds.c +++ b/drivers/gpu/drm/gma500/cdv_intel_lvds.c @@ -326,12 +326,12 @@ static int cdv_intel_lvds_get_modes(struct drm_connector *connector) */ static void cdv_intel_lvds_destroy(struct drm_connector *connector) { + struct gma_connector *gma_connector = to_gma_connector(connector); struct gma_encoder *gma_encoder = gma_attached_encoder(connector); psb_intel_i2c_destroy(gma_encoder->i2c_bus); - drm_connector_unregister(connector); drm_connector_cleanup(connector); - kfree(connector); + kfree(gma_connector); } static int cdv_intel_lvds_set_property(struct drm_connector *connector, @@ -647,7 +647,6 @@ void cdv_intel_lvds_init(struct drm_device *dev, out: mutex_unlock(&dev->mode_config.mutex); - drm_connector_register(connector); return; failed_find: diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c index 45df9de22007..0ac6ea5fd3a1 100644 --- a/drivers/gpu/drm/gma500/framebuffer.c +++ b/drivers/gpu/drm/gma500/framebuffer.c @@ -451,6 +451,7 @@ static const struct drm_mode_config_funcs psb_mode_funcs = { static void psb_setup_outputs(struct drm_device *dev) { struct drm_psb_private *dev_priv = to_drm_psb_private(dev); + struct drm_connector_list_iter conn_iter; struct drm_connector *connector; drm_mode_create_scaling_mode_property(dev); @@ -461,8 +462,8 @@ static void psb_setup_outputs(struct drm_device *dev) "backlight", 0, 100); dev_priv->ops->output_init(dev); - list_for_each_entry(connector, &dev->mode_config.connector_list, - head) { + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { struct gma_encoder *gma_encoder = gma_attached_encoder(connector); struct drm_encoder *encoder = &gma_encoder->base; int crtc_mask = 0, clone_mask = 0; @@ -505,6 +506,7 @@ static void psb_setup_outputs(struct drm_device *dev) encoder->possible_clones = gma_connector_clones(dev, clone_mask); } + drm_connector_list_iter_end(&conn_iter); } void psb_modeset_init(struct drm_device *dev) @@ -514,7 +516,8 @@ void psb_modeset_init(struct drm_device *dev) struct pci_dev *pdev = to_pci_dev(dev->dev); int i; - drm_mode_config_init(dev); + if (drmm_mode_config_init(dev)) + return; dev->mode_config.min_width = 0; dev->mode_config.min_height = 0; @@ -546,6 +549,5 @@ void psb_modeset_cleanup(struct drm_device *dev) if (dev_priv->modeset) { drm_kms_helper_poll_fini(dev); psb_fbdev_fini(dev); - drm_mode_config_cleanup(dev); } } diff --git a/drivers/gpu/drm/gma500/gem.c b/drivers/gpu/drm/gma500/gem.c index 8d65af80bb08..dffe37490206 100644 --- a/drivers/gpu/drm/gma500/gem.c +++ b/drivers/gpu/drm/gma500/gem.c @@ -21,6 +21,10 @@ #include "gem.h" #include "psb_drv.h" +/* + * PSB GEM object + */ + int psb_gem_pin(struct psb_gem_object *pobj) { struct drm_gem_object *obj = &pobj->base; @@ -31,7 +35,9 @@ int psb_gem_pin(struct psb_gem_object *pobj) unsigned int npages; int ret; - mutex_lock(&dev_priv->gtt_mutex); + ret = dma_resv_lock(obj->resv, NULL); + if (drm_WARN_ONCE(dev, ret, "dma_resv_lock() failed, ret=%d\n", ret)) + return ret; if (pobj->in_gart || pobj->stolen) goto out; /* already mapped */ @@ -39,7 +45,7 @@ int psb_gem_pin(struct psb_gem_object *pobj) pages = drm_gem_get_pages(obj); if (IS_ERR(pages)) { ret = PTR_ERR(pages); - goto err_mutex_unlock; + goto err_dma_resv_unlock; } npages = obj->size / PAGE_SIZE; @@ -51,17 +57,16 @@ int psb_gem_pin(struct psb_gem_object *pobj) (gpu_base + pobj->offset), npages, 0, 0, PSB_MMU_CACHED_MEMORY); - pobj->npage = npages; pobj->pages = pages; out: ++pobj->in_gart; - mutex_unlock(&dev_priv->gtt_mutex); + dma_resv_unlock(obj->resv); return 0; -err_mutex_unlock: - mutex_unlock(&dev_priv->gtt_mutex); +err_dma_resv_unlock: + dma_resv_unlock(obj->resv); return ret; } @@ -71,8 +76,12 @@ void psb_gem_unpin(struct psb_gem_object *pobj) struct drm_device *dev = obj->dev; struct drm_psb_private *dev_priv = to_drm_psb_private(dev); u32 gpu_base = dev_priv->gtt.gatt_start; + unsigned long npages; + int ret; - mutex_lock(&dev_priv->gtt_mutex); + ret = dma_resv_lock(obj->resv, NULL); + if (drm_WARN_ONCE(dev, ret, "dma_resv_lock() failed, ret=%d\n", ret)) + return; WARN_ON(!pobj->in_gart); @@ -81,19 +90,20 @@ void psb_gem_unpin(struct psb_gem_object *pobj) if (pobj->in_gart || pobj->stolen) goto out; + npages = obj->size / PAGE_SIZE; + psb_mmu_remove_pages(psb_mmu_get_default_pd(dev_priv->mmu), - (gpu_base + pobj->offset), pobj->npage, 0, 0); + (gpu_base + pobj->offset), npages, 0, 0); psb_gtt_remove_pages(dev_priv, &pobj->resource); /* Reset caching flags */ - set_pages_array_wb(pobj->pages, pobj->npage); + set_pages_array_wb(pobj->pages, npages); drm_gem_put_pages(obj, pobj->pages, true, false); pobj->pages = NULL; - pobj->npage = 0; out: - mutex_unlock(&dev_priv->gtt_mutex); + dma_resv_unlock(obj->resv); } static vm_fault_t psb_gem_fault(struct vm_fault *vmf); @@ -290,3 +300,132 @@ fail: return ret; } + +/* + * Memory management + */ + +/* Insert vram stolen pages into the GTT. */ +static void psb_gem_mm_populate_stolen(struct drm_psb_private *pdev) +{ + struct drm_device *dev = &pdev->dev; + unsigned int pfn_base; + unsigned int i, num_pages; + uint32_t pte; + + pfn_base = pdev->stolen_base >> PAGE_SHIFT; + num_pages = pdev->vram_stolen_size >> PAGE_SHIFT; + + drm_dbg(dev, "Set up %u stolen pages starting at 0x%08x, GTT offset %dK\n", + num_pages, pfn_base << PAGE_SHIFT, 0); + + for (i = 0; i < num_pages; ++i) { + pte = psb_gtt_mask_pte(pfn_base + i, PSB_MMU_CACHED_MEMORY); + iowrite32(pte, pdev->gtt_map + i); + } + + (void)ioread32(pdev->gtt_map + i - 1); +} + +int psb_gem_mm_init(struct drm_device *dev) +{ + struct drm_psb_private *dev_priv = to_drm_psb_private(dev); + struct pci_dev *pdev = to_pci_dev(dev->dev); + unsigned long stolen_size, vram_stolen_size; + struct psb_gtt *pg; + int ret; + + mutex_init(&dev_priv->mmap_mutex); + + pg = &dev_priv->gtt; + + pci_read_config_dword(pdev, PSB_BSM, &dev_priv->stolen_base); + vram_stolen_size = pg->gtt_phys_start - dev_priv->stolen_base - PAGE_SIZE; + + stolen_size = vram_stolen_size; + + dev_dbg(dev->dev, "Stolen memory base 0x%x, size %luK\n", + dev_priv->stolen_base, vram_stolen_size / 1024); + + pg->stolen_size = stolen_size; + dev_priv->vram_stolen_size = vram_stolen_size; + + dev_priv->vram_addr = ioremap_wc(dev_priv->stolen_base, stolen_size); + if (!dev_priv->vram_addr) { + dev_err(dev->dev, "Failure to map stolen base.\n"); + ret = -ENOMEM; + goto err_mutex_destroy; + } + + psb_gem_mm_populate_stolen(dev_priv); + + return 0; + +err_mutex_destroy: + mutex_destroy(&dev_priv->mmap_mutex); + return ret; +} + +void psb_gem_mm_fini(struct drm_device *dev) +{ + struct drm_psb_private *dev_priv = to_drm_psb_private(dev); + + iounmap(dev_priv->vram_addr); + + mutex_destroy(&dev_priv->mmap_mutex); +} + +/* Re-insert all pinned GEM objects into GTT. */ +static void psb_gem_mm_populate_resources(struct drm_psb_private *pdev) +{ + unsigned int restored = 0, total = 0, size = 0; + struct resource *r = pdev->gtt_mem->child; + struct drm_device *dev = &pdev->dev; + struct psb_gem_object *pobj; + + while (r) { + /* + * TODO: GTT restoration needs a refactoring, so that we don't have to touch + * struct psb_gem_object here. The type represents a GEM object and is + * not related to the GTT itself. + */ + pobj = container_of(r, struct psb_gem_object, resource); + if (pobj->pages) { + psb_gtt_insert_pages(pdev, &pobj->resource, pobj->pages); + size += resource_size(&pobj->resource); + ++restored; + } + r = r->sibling; + ++total; + } + + drm_dbg(dev, "Restored %u of %u gtt ranges (%u KB)", restored, total, (size / 1024)); +} + +int psb_gem_mm_resume(struct drm_device *dev) +{ + struct drm_psb_private *dev_priv = to_drm_psb_private(dev); + struct pci_dev *pdev = to_pci_dev(dev->dev); + unsigned long stolen_size, vram_stolen_size; + struct psb_gtt *pg; + + pg = &dev_priv->gtt; + + pci_read_config_dword(pdev, PSB_BSM, &dev_priv->stolen_base); + vram_stolen_size = pg->gtt_phys_start - dev_priv->stolen_base - PAGE_SIZE; + + stolen_size = vram_stolen_size; + + dev_dbg(dev->dev, "Stolen memory base 0x%x, size %luK\n", dev_priv->stolen_base, + vram_stolen_size / 1024); + + if (stolen_size != pg->stolen_size) { + dev_err(dev->dev, "GTT resume error.\n"); + return -EINVAL; + } + + psb_gem_mm_populate_stolen(dev_priv); + psb_gem_mm_populate_resources(dev_priv); + + return 0; +} diff --git a/drivers/gpu/drm/gma500/gem.h b/drivers/gpu/drm/gma500/gem.h index 79cced40c87f..27df6ff4ed37 100644 --- a/drivers/gpu/drm/gma500/gem.h +++ b/drivers/gpu/drm/gma500/gem.h @@ -14,6 +14,10 @@ struct drm_device; +/* + * PSB GEM object + */ + struct psb_gem_object { struct drm_gem_object base; @@ -23,7 +27,6 @@ struct psb_gem_object { bool stolen; /* Backed from stolen RAM */ bool mmapping; /* Is mmappable */ struct page **pages; /* Backing pages if present */ - int npage; /* Number of backing pages */ }; static inline struct psb_gem_object *to_psb_gem_object(struct drm_gem_object *obj) @@ -37,4 +40,12 @@ psb_gem_create(struct drm_device *dev, u64 size, const char *name, bool stolen, int psb_gem_pin(struct psb_gem_object *pobj); void psb_gem_unpin(struct psb_gem_object *pobj); +/* + * Memory management + */ + +int psb_gem_mm_init(struct drm_device *dev); +void psb_gem_mm_fini(struct drm_device *dev); +int psb_gem_mm_resume(struct drm_device *dev); + #endif diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c index 60ba7de59139..34ec3fca09ba 100644 --- a/drivers/gpu/drm/gma500/gma_display.c +++ b/drivers/gpu/drm/gma500/gma_display.c @@ -17,7 +17,7 @@ #include "framebuffer.h" #include "gem.h" #include "gma_display.h" -#include "psb_drv.h" +#include "psb_irq.h" #include "psb_intel_drv.h" #include "psb_intel_reg.h" @@ -27,17 +27,21 @@ bool gma_pipe_has_type(struct drm_crtc *crtc, int type) { struct drm_device *dev = crtc->dev; - struct drm_mode_config *mode_config = &dev->mode_config; - struct drm_connector *l_entry; + struct drm_connector_list_iter conn_iter; + struct drm_connector *connector; - list_for_each_entry(l_entry, &mode_config->connector_list, head) { - if (l_entry->encoder && l_entry->encoder->crtc == crtc) { + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { + if (connector->encoder && connector->encoder->crtc == crtc) { struct gma_encoder *gma_encoder = - gma_attached_encoder(l_entry); - if (gma_encoder->type == type) + gma_attached_encoder(connector); + if (gma_encoder->type == type) { + drm_connector_list_iter_end(&conn_iter); return true; + } } } + drm_connector_list_iter_end(&conn_iter); return false; } @@ -172,9 +176,9 @@ void gma_crtc_load_lut(struct drm_crtc *crtc) } } -int gma_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, u16 *blue, - u32 size, - struct drm_modeset_acquire_ctx *ctx) +static int gma_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, + u16 *blue, u32 size, + struct drm_modeset_acquire_ctx *ctx) { gma_crtc_load_lut(crtc); @@ -319,10 +323,9 @@ void gma_crtc_dpms(struct drm_crtc *crtc, int mode) REG_WRITE(DSPARB, 0x3F3E); } -int gma_crtc_cursor_set(struct drm_crtc *crtc, - struct drm_file *file_priv, - uint32_t handle, - uint32_t width, uint32_t height) +static int gma_crtc_cursor_set(struct drm_crtc *crtc, + struct drm_file *file_priv, uint32_t handle, + uint32_t width, uint32_t height) { struct drm_device *dev = crtc->dev; struct drm_psb_private *dev_priv = to_drm_psb_private(dev); @@ -391,11 +394,9 @@ int gma_crtc_cursor_set(struct drm_crtc *crtc, goto unref_cursor; } - /* Prevent overflow */ - if (pobj->npage > 4) - cursor_pages = 4; - else - cursor_pages = pobj->npage; + cursor_pages = obj->size / PAGE_SIZE; + if (cursor_pages > 4) + cursor_pages = 4; /* Prevent overflow */ /* Copy the cursor to cursor mem */ tmp_dst = dev_priv->vram_addr + cursor_pobj->offset; @@ -437,7 +438,7 @@ unref_cursor: return ret; } -int gma_crtc_cursor_move(struct drm_crtc *crtc, int x, int y) +static int gma_crtc_cursor_move(struct drm_crtc *crtc, int x, int y) { struct drm_device *dev = crtc->dev; struct gma_crtc *gma_crtc = to_gma_crtc(crtc); @@ -567,6 +568,18 @@ int gma_crtc_set_config(struct drm_mode_set *set, return ret; } +const struct drm_crtc_funcs gma_crtc_funcs = { + .cursor_set = gma_crtc_cursor_set, + .cursor_move = gma_crtc_cursor_move, + .gamma_set = gma_crtc_gamma_set, + .set_config = gma_crtc_set_config, + .destroy = gma_crtc_destroy, + .page_flip = gma_crtc_page_flip, + .enable_vblank = gma_crtc_enable_vblank, + .disable_vblank = gma_crtc_disable_vblank, + .get_vblank_counter = gma_crtc_get_vblank_counter, +}; + /* * Save HW states of given crtc */ diff --git a/drivers/gpu/drm/gma500/gma_display.h b/drivers/gpu/drm/gma500/gma_display.h index 7bd6c1ee8b21..113cf048105e 100644 --- a/drivers/gpu/drm/gma500/gma_display.h +++ b/drivers/gpu/drm/gma500/gma_display.h @@ -58,15 +58,7 @@ extern bool gma_pipe_has_type(struct drm_crtc *crtc, int type); extern void gma_wait_for_vblank(struct drm_device *dev); extern int gma_pipe_set_base(struct drm_crtc *crtc, int x, int y, struct drm_framebuffer *old_fb); -extern int gma_crtc_cursor_set(struct drm_crtc *crtc, - struct drm_file *file_priv, - uint32_t handle, - uint32_t width, uint32_t height); -extern int gma_crtc_cursor_move(struct drm_crtc *crtc, int x, int y); extern void gma_crtc_load_lut(struct drm_crtc *crtc); -extern int gma_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green, - u16 *blue, u32 size, - struct drm_modeset_acquire_ctx *ctx); extern void gma_crtc_dpms(struct drm_crtc *crtc, int mode); extern void gma_crtc_prepare(struct drm_crtc *crtc); extern void gma_crtc_commit(struct drm_crtc *crtc); @@ -83,6 +75,8 @@ extern int gma_crtc_set_config(struct drm_mode_set *set, extern void gma_crtc_save(struct drm_crtc *crtc); extern void gma_crtc_restore(struct drm_crtc *crtc); +extern const struct drm_crtc_funcs gma_crtc_funcs; + extern void gma_encoder_prepare(struct drm_encoder *encoder); extern void gma_encoder_commit(struct drm_encoder *encoder); extern void gma_encoder_destroy(struct drm_encoder *encoder); diff --git a/drivers/gpu/drm/gma500/gtt.c b/drivers/gpu/drm/gma500/gtt.c index 309ffe921bfd..379bc218aa6b 100644 --- a/drivers/gpu/drm/gma500/gtt.c +++ b/drivers/gpu/drm/gma500/gtt.c @@ -49,7 +49,7 @@ int psb_gtt_allocate_resource(struct drm_psb_private *pdev, struct resource *res * * Set the GTT entry for the appropriate memory type. */ -static inline uint32_t psb_gtt_mask_pte(uint32_t pfn, int type) +uint32_t psb_gtt_mask_pte(uint32_t pfn, int type) { uint32_t mask = PSB_PTE_VALID; @@ -74,11 +74,7 @@ static u32 __iomem *psb_gtt_entry(struct drm_psb_private *pdev, const struct res return pdev->gtt_map + (offset >> PAGE_SHIFT); } -/* - * Take our preallocated GTT range and insert the GEM object into - * the GTT. This is protected via the gtt mutex which the caller - * must hold. - */ +/* Acquires GTT mutex internally. */ void psb_gtt_insert_pages(struct drm_psb_private *pdev, const struct resource *res, struct page **pages) { @@ -86,6 +82,8 @@ void psb_gtt_insert_pages(struct drm_psb_private *pdev, const struct resource *r u32 __iomem *gtt_slot; u32 pte; + mutex_lock(&pdev->gtt_mutex); + /* Write our page entries into the GTT itself */ npages = resource_size(res) >> PAGE_SHIFT; @@ -98,19 +96,19 @@ void psb_gtt_insert_pages(struct drm_psb_private *pdev, const struct resource *r /* Make sure all the entries are set before we return */ ioread32(gtt_slot - 1); + + mutex_unlock(&pdev->gtt_mutex); } -/* - * Remove a preallocated GTT range from the GTT. Overwrite all the - * page table entries with the dummy page. This is protected via the gtt - * mutex which the caller must hold. - */ +/* Acquires GTT mutex internally. */ void psb_gtt_remove_pages(struct drm_psb_private *pdev, const struct resource *res) { resource_size_t npages, i; u32 __iomem *gtt_slot; u32 pte; + mutex_lock(&pdev->gtt_mutex); + /* Install scratch page for the resource */ pte = psb_gtt_mask_pte(page_to_pfn(pdev->scratch_page), PSB_MMU_CACHED_MEMORY); @@ -123,211 +121,192 @@ void psb_gtt_remove_pages(struct drm_psb_private *pdev, const struct resource *r /* Make sure all the entries are set before we return */ ioread32(gtt_slot - 1); + + mutex_unlock(&pdev->gtt_mutex); } -static void psb_gtt_alloc(struct drm_device *dev) +static int psb_gtt_enable(struct drm_psb_private *dev_priv) { - struct drm_psb_private *dev_priv = to_drm_psb_private(dev); - init_rwsem(&dev_priv->gtt.sem); + struct drm_device *dev = &dev_priv->dev; + struct pci_dev *pdev = to_pci_dev(dev->dev); + int ret; + + ret = pci_read_config_word(pdev, PSB_GMCH_CTRL, &dev_priv->gmch_ctrl); + if (ret) + return pcibios_err_to_errno(ret); + ret = pci_write_config_word(pdev, PSB_GMCH_CTRL, dev_priv->gmch_ctrl | _PSB_GMCH_ENABLED); + if (ret) + return pcibios_err_to_errno(ret); + + dev_priv->pge_ctl = PSB_RVDC32(PSB_PGETBL_CTL); + PSB_WVDC32(dev_priv->pge_ctl | _PSB_PGETBL_ENABLED, PSB_PGETBL_CTL); + + (void)PSB_RVDC32(PSB_PGETBL_CTL); + + return 0; } -void psb_gtt_takedown(struct drm_device *dev) +static void psb_gtt_disable(struct drm_psb_private *dev_priv) { - struct drm_psb_private *dev_priv = to_drm_psb_private(dev); + struct drm_device *dev = &dev_priv->dev; struct pci_dev *pdev = to_pci_dev(dev->dev); - if (dev_priv->gtt_map) { - iounmap(dev_priv->gtt_map); - dev_priv->gtt_map = NULL; - } - if (dev_priv->gtt_initialized) { - pci_write_config_word(pdev, PSB_GMCH_CTRL, - dev_priv->gmch_ctrl); - PSB_WVDC32(dev_priv->pge_ctl, PSB_PGETBL_CTL); - (void) PSB_RVDC32(PSB_PGETBL_CTL); - } - if (dev_priv->vram_addr) - iounmap(dev_priv->gtt_map); + pci_write_config_word(pdev, PSB_GMCH_CTRL, dev_priv->gmch_ctrl); + PSB_WVDC32(dev_priv->pge_ctl, PSB_PGETBL_CTL); + + (void)PSB_RVDC32(PSB_PGETBL_CTL); } -int psb_gtt_init(struct drm_device *dev, int resume) +void psb_gtt_fini(struct drm_device *dev) { struct drm_psb_private *dev_priv = to_drm_psb_private(dev); - struct pci_dev *pdev = to_pci_dev(dev->dev); - unsigned gtt_pages; - unsigned long stolen_size, vram_stolen_size; - unsigned i, num_pages; - unsigned pfn_base; - struct psb_gtt *pg; - int ret = 0; + iounmap(dev_priv->gtt_map); + psb_gtt_disable(dev_priv); + mutex_destroy(&dev_priv->gtt_mutex); +} + +/* Clear GTT. Use a scratch page to avoid accidents or scribbles. */ +static void psb_gtt_clear(struct drm_psb_private *pdev) +{ + resource_size_t pfn_base; + unsigned long i; uint32_t pte; - if (!resume) { - mutex_init(&dev_priv->gtt_mutex); - mutex_init(&dev_priv->mmap_mutex); - psb_gtt_alloc(dev); - } + pfn_base = page_to_pfn(pdev->scratch_page); + pte = psb_gtt_mask_pte(pfn_base, PSB_MMU_CACHED_MEMORY); - pg = &dev_priv->gtt; + for (i = 0; i < pdev->gtt.gtt_pages; ++i) + iowrite32(pte, pdev->gtt_map + i); - /* Enable the GTT */ - pci_read_config_word(pdev, PSB_GMCH_CTRL, &dev_priv->gmch_ctrl); - pci_write_config_word(pdev, PSB_GMCH_CTRL, - dev_priv->gmch_ctrl | _PSB_GMCH_ENABLED); + (void)ioread32(pdev->gtt_map + i - 1); +} - dev_priv->pge_ctl = PSB_RVDC32(PSB_PGETBL_CTL); - PSB_WVDC32(dev_priv->pge_ctl | _PSB_PGETBL_ENABLED, PSB_PGETBL_CTL); - (void) PSB_RVDC32(PSB_PGETBL_CTL); +static void psb_gtt_init_ranges(struct drm_psb_private *dev_priv) +{ + struct drm_device *dev = &dev_priv->dev; + struct pci_dev *pdev = to_pci_dev(dev->dev); + struct psb_gtt *pg = &dev_priv->gtt; + resource_size_t gtt_phys_start, mmu_gatt_start, gtt_start, gtt_pages, + gatt_start, gatt_pages; + struct resource *gtt_mem; /* The root resource we allocate address space from */ - dev_priv->gtt_initialized = 1; - - pg->gtt_phys_start = dev_priv->pge_ctl & PAGE_MASK; + gtt_phys_start = dev_priv->pge_ctl & PAGE_MASK; /* - * The video mmu has a hw bug when accessing 0x0D0000000. - * Make gatt start at 0x0e000,0000. This doesn't actually - * matter for us but may do if the video acceleration ever - * gets opened up. + * The video MMU has a HW bug when accessing 0x0d0000000. Make + * GATT start at 0x0e0000000. This doesn't actually matter for + * us now, but maybe will if the video acceleration ever gets + * opened up. */ - pg->mmu_gatt_start = 0xE0000000; + mmu_gatt_start = 0xe0000000; + + gtt_start = pci_resource_start(pdev, PSB_GTT_RESOURCE); + gtt_pages = pci_resource_len(pdev, PSB_GTT_RESOURCE) >> PAGE_SHIFT; - pg->gtt_start = pci_resource_start(pdev, PSB_GTT_RESOURCE); - gtt_pages = pci_resource_len(pdev, PSB_GTT_RESOURCE) - >> PAGE_SHIFT; /* CDV doesn't report this. In which case the system has 64 gtt pages */ - if (pg->gtt_start == 0 || gtt_pages == 0) { + if (!gtt_start || !gtt_pages) { dev_dbg(dev->dev, "GTT PCI BAR not initialized.\n"); gtt_pages = 64; - pg->gtt_start = dev_priv->pge_ctl; + gtt_start = dev_priv->pge_ctl; } - pg->gatt_start = pci_resource_start(pdev, PSB_GATT_RESOURCE); - pg->gatt_pages = pci_resource_len(pdev, PSB_GATT_RESOURCE) - >> PAGE_SHIFT; - dev_priv->gtt_mem = &pdev->resource[PSB_GATT_RESOURCE]; + gatt_start = pci_resource_start(pdev, PSB_GATT_RESOURCE); + gatt_pages = pci_resource_len(pdev, PSB_GATT_RESOURCE) >> PAGE_SHIFT; - if (pg->gatt_pages == 0 || pg->gatt_start == 0) { + if (!gatt_pages || !gatt_start) { static struct resource fudge; /* Preferably peppermint */ - /* This can occur on CDV systems. Fudge it in this case. - We really don't care what imaginary space is being allocated - at this point */ + + /* + * This can occur on CDV systems. Fudge it in this case. We + * really don't care what imaginary space is being allocated + * at this point. + */ dev_dbg(dev->dev, "GATT PCI BAR not initialized.\n"); - pg->gatt_start = 0x40000000; - pg->gatt_pages = (128 * 1024 * 1024) >> PAGE_SHIFT; - /* This is a little confusing but in fact the GTT is providing - a view from the GPU into memory and not vice versa. As such - this is really allocating space that is not the same as the - CPU address space on CDV */ + gatt_start = 0x40000000; + gatt_pages = (128 * 1024 * 1024) >> PAGE_SHIFT; + + /* + * This is a little confusing but in fact the GTT is providing + * a view from the GPU into memory and not vice versa. As such + * this is really allocating space that is not the same as the + * CPU address space on CDV. + */ fudge.start = 0x40000000; fudge.end = 0x40000000 + 128 * 1024 * 1024 - 1; fudge.name = "fudge"; fudge.flags = IORESOURCE_MEM; - dev_priv->gtt_mem = &fudge; + + gtt_mem = &fudge; + } else { + gtt_mem = &pdev->resource[PSB_GATT_RESOURCE]; } - pci_read_config_dword(pdev, PSB_BSM, &dev_priv->stolen_base); - vram_stolen_size = pg->gtt_phys_start - dev_priv->stolen_base - - PAGE_SIZE; + pg->gtt_phys_start = gtt_phys_start; + pg->mmu_gatt_start = mmu_gatt_start; + pg->gtt_start = gtt_start; + pg->gtt_pages = gtt_pages; + pg->gatt_start = gatt_start; + pg->gatt_pages = gatt_pages; + dev_priv->gtt_mem = gtt_mem; +} - stolen_size = vram_stolen_size; +int psb_gtt_init(struct drm_device *dev) +{ + struct drm_psb_private *dev_priv = to_drm_psb_private(dev); + struct psb_gtt *pg = &dev_priv->gtt; + int ret; - dev_dbg(dev->dev, "Stolen memory base 0x%x, size %luK\n", - dev_priv->stolen_base, vram_stolen_size / 1024); + mutex_init(&dev_priv->gtt_mutex); - if (resume && (gtt_pages != pg->gtt_pages) && - (stolen_size != pg->stolen_size)) { - dev_err(dev->dev, "GTT resume error.\n"); - ret = -EINVAL; - goto out_err; - } + ret = psb_gtt_enable(dev_priv); + if (ret) + goto err_mutex_destroy; - pg->gtt_pages = gtt_pages; - pg->stolen_size = stolen_size; - dev_priv->vram_stolen_size = vram_stolen_size; + psb_gtt_init_ranges(dev_priv); - /* - * Map the GTT and the stolen memory area - */ - if (!resume) - dev_priv->gtt_map = ioremap(pg->gtt_phys_start, - gtt_pages << PAGE_SHIFT); + dev_priv->gtt_map = ioremap(pg->gtt_phys_start, pg->gtt_pages << PAGE_SHIFT); if (!dev_priv->gtt_map) { dev_err(dev->dev, "Failure to map gtt.\n"); ret = -ENOMEM; - goto out_err; - } - - if (!resume) - dev_priv->vram_addr = ioremap_wc(dev_priv->stolen_base, - stolen_size); - - if (!dev_priv->vram_addr) { - dev_err(dev->dev, "Failure to map stolen base.\n"); - ret = -ENOMEM; - goto out_err; + goto err_psb_gtt_disable; } - /* - * Insert vram stolen pages into the GTT - */ - - pfn_base = dev_priv->stolen_base >> PAGE_SHIFT; - num_pages = vram_stolen_size >> PAGE_SHIFT; - dev_dbg(dev->dev, "Set up %d stolen pages starting at 0x%08x, GTT offset %dK\n", - num_pages, pfn_base << PAGE_SHIFT, 0); - for (i = 0; i < num_pages; ++i) { - pte = psb_gtt_mask_pte(pfn_base + i, PSB_MMU_CACHED_MEMORY); - iowrite32(pte, dev_priv->gtt_map + i); - } - - /* - * Init rest of GTT to the scratch page to avoid accidents or scribbles - */ + psb_gtt_clear(dev_priv); - pfn_base = page_to_pfn(dev_priv->scratch_page); - pte = psb_gtt_mask_pte(pfn_base, PSB_MMU_CACHED_MEMORY); - for (; i < gtt_pages; ++i) - iowrite32(pte, dev_priv->gtt_map + i); - - (void) ioread32(dev_priv->gtt_map + i - 1); return 0; -out_err: - psb_gtt_takedown(dev); +err_psb_gtt_disable: + psb_gtt_disable(dev_priv); +err_mutex_destroy: + mutex_destroy(&dev_priv->gtt_mutex); return ret; } -int psb_gtt_restore(struct drm_device *dev) +int psb_gtt_resume(struct drm_device *dev) { struct drm_psb_private *dev_priv = to_drm_psb_private(dev); - struct resource *r = dev_priv->gtt_mem->child; - struct psb_gem_object *pobj; - unsigned int restored = 0, total = 0, size = 0; + struct psb_gtt *pg = &dev_priv->gtt; + unsigned int old_gtt_pages = pg->gtt_pages; + int ret; - /* On resume, the gtt_mutex is already initialized */ - mutex_lock(&dev_priv->gtt_mutex); - psb_gtt_init(dev, 1); + /* Enable the GTT */ + ret = psb_gtt_enable(dev_priv); + if (ret) + return ret; - while (r != NULL) { - /* - * TODO: GTT restoration needs a refactoring, so that we don't have to touch - * struct psb_gem_object here. The type represents a GEM object and is - * not related to the GTT itself. - */ - pobj = container_of(r, struct psb_gem_object, resource); - if (pobj->pages) { - psb_gtt_insert_pages(dev_priv, &pobj->resource, pobj->pages); - size += pobj->resource.end - pobj->resource.start; - restored++; - } - r = r->sibling; - total++; + psb_gtt_init_ranges(dev_priv); + + if (old_gtt_pages != pg->gtt_pages) { + dev_err(dev->dev, "GTT resume error.\n"); + ret = -ENODEV; + goto err_psb_gtt_disable; } - mutex_unlock(&dev_priv->gtt_mutex); - DRM_DEBUG_DRIVER("Restored %u of %u gtt ranges (%u KB)", restored, - total, (size / 1024)); - return 0; + psb_gtt_clear(dev_priv); + +err_psb_gtt_disable: + psb_gtt_disable(dev_priv); + return ret; } diff --git a/drivers/gpu/drm/gma500/gtt.h b/drivers/gpu/drm/gma500/gtt.h index ff1dcdd1ff52..d5a5fd4466c1 100644 --- a/drivers/gpu/drm/gma500/gtt.h +++ b/drivers/gpu/drm/gma500/gtt.h @@ -22,18 +22,18 @@ struct psb_gtt { unsigned gatt_pages; unsigned long stolen_size; unsigned long vram_stolen_size; - struct rw_semaphore sem; }; /* Exported functions */ -extern int psb_gtt_init(struct drm_device *dev, int resume); -extern void psb_gtt_takedown(struct drm_device *dev); -extern int psb_gtt_restore(struct drm_device *dev); +int psb_gtt_init(struct drm_device *dev); +void psb_gtt_fini(struct drm_device *dev); +int psb_gtt_resume(struct drm_device *dev); int psb_gtt_allocate_resource(struct drm_psb_private *pdev, struct resource *res, const char *name, resource_size_t size, resource_size_t align, bool stolen, u32 *offset); +uint32_t psb_gtt_mask_pte(uint32_t pfn, int type); void psb_gtt_insert_pages(struct drm_psb_private *pdev, const struct resource *res, struct page **pages); void psb_gtt_remove_pages(struct drm_psb_private *pdev, const struct resource *res); diff --git a/drivers/gpu/drm/gma500/oaktrail_crtc.c b/drivers/gpu/drm/gma500/oaktrail_crtc.c index 36c7c2686c90..22398d34853a 100644 --- a/drivers/gpu/drm/gma500/oaktrail_crtc.c +++ b/drivers/gpu/drm/gma500/oaktrail_crtc.c @@ -372,9 +372,9 @@ static int oaktrail_crtc_mode_set(struct drm_crtc *crtc, bool ok, is_sdvo = false; bool is_lvds = false; bool is_mipi = false; - struct drm_mode_config *mode_config = &dev->mode_config; struct gma_encoder *gma_encoder = NULL; uint64_t scalingType = DRM_MODE_SCALE_FULLSCREEN; + struct drm_connector_list_iter conn_iter; struct drm_connector *connector; int i; int need_aux = gma_pipe_has_type(crtc, INTEL_OUTPUT_SDVO) ? 1 : 0; @@ -385,14 +385,11 @@ static int oaktrail_crtc_mode_set(struct drm_crtc *crtc, if (!gma_power_begin(dev, true)) return 0; - memcpy(&gma_crtc->saved_mode, - mode, - sizeof(struct drm_display_mode)); - memcpy(&gma_crtc->saved_adjusted_mode, - adjusted_mode, - sizeof(struct drm_display_mode)); + drm_mode_copy(&gma_crtc->saved_mode, mode); + drm_mode_copy(&gma_crtc->saved_adjusted_mode, adjusted_mode); - list_for_each_entry(connector, &mode_config->connector_list, head) { + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { if (!connector->encoder || connector->encoder->crtc != crtc) continue; @@ -409,8 +406,16 @@ static int oaktrail_crtc_mode_set(struct drm_crtc *crtc, is_mipi = true; break; } + + break; } + if (gma_encoder) + drm_object_property_get_value(&connector->base, + dev->mode_config.scaling_mode_property, &scalingType); + + drm_connector_list_iter_end(&conn_iter); + /* Disable the VGA plane that we never use */ for (i = 0; i <= need_aux; i++) REG_WRITE_WITH_AUX(VGACNTRL, VGA_DISP_DISABLE, i); @@ -424,10 +429,6 @@ static int oaktrail_crtc_mode_set(struct drm_crtc *crtc, (mode->crtc_vdisplay - 1), i); } - if (gma_encoder) - drm_object_property_get_value(&connector->base, - dev->mode_config.scaling_mode_property, &scalingType); - if (scalingType == DRM_MODE_SCALE_NO_SCALE) { /* Moorestown doesn't have register support for centering so * we need to mess with the h/vblank and h/vsync start and diff --git a/drivers/gpu/drm/gma500/oaktrail_device.c b/drivers/gpu/drm/gma500/oaktrail_device.c index 5c75eae630b5..5923a9c89312 100644 --- a/drivers/gpu/drm/gma500/oaktrail_device.c +++ b/drivers/gpu/drm/gma500/oaktrail_device.c @@ -545,7 +545,6 @@ const struct psb_ops oaktrail_chip_ops = { .chip_setup = oaktrail_chip_setup, .chip_teardown = oaktrail_teardown, .crtc_helper = &oaktrail_helper_funcs, - .crtc_funcs = &gma_intel_crtc_funcs, .output_init = oaktrail_output_init, diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi.c b/drivers/gpu/drm/gma500/oaktrail_hdmi.c index 6eef60a5ac27..b5946a1cdcd5 100644 --- a/drivers/gpu/drm/gma500/oaktrail_hdmi.c +++ b/drivers/gpu/drm/gma500/oaktrail_hdmi.c @@ -654,7 +654,6 @@ void oaktrail_hdmi_init(struct drm_device *dev, connector->display_info.subpixel_order = SubPixelHorizontalRGB; connector->interlace_allowed = false; connector->doublescan_allowed = false; - drm_connector_register(connector); dev_info(dev->dev, "HDMI initialised.\n"); return; diff --git a/drivers/gpu/drm/gma500/oaktrail_lvds.c b/drivers/gpu/drm/gma500/oaktrail_lvds.c index 28b995ef2844..aed5de8f8245 100644 --- a/drivers/gpu/drm/gma500/oaktrail_lvds.c +++ b/drivers/gpu/drm/gma500/oaktrail_lvds.c @@ -85,7 +85,7 @@ static void oaktrail_lvds_mode_set(struct drm_encoder *encoder, struct drm_device *dev = encoder->dev; struct drm_psb_private *dev_priv = to_drm_psb_private(dev); struct psb_intel_mode_device *mode_dev = &dev_priv->mode_dev; - struct drm_mode_config *mode_config = &dev->mode_config; + struct drm_connector_list_iter conn_iter; struct drm_connector *connector = NULL; struct drm_crtc *crtc = encoder->crtc; u32 lvds_port; @@ -112,21 +112,22 @@ static void oaktrail_lvds_mode_set(struct drm_encoder *encoder, REG_WRITE(LVDS, lvds_port); /* Find the connector we're trying to set up */ - list_for_each_entry(connector, &mode_config->connector_list, head) { + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { if (connector->encoder && connector->encoder->crtc == crtc) break; } - if (list_entry_is_head(connector, &mode_config->connector_list, head)) { + if (!connector) { + drm_connector_list_iter_end(&conn_iter); DRM_ERROR("Couldn't find connector when setting mode"); gma_power_end(dev); return; } - drm_object_property_get_value( - &connector->base, - dev->mode_config.scaling_mode_property, - &v); + drm_object_property_get_value( &connector->base, + dev->mode_config.scaling_mode_property, &v); + drm_connector_list_iter_end(&conn_iter); if (v == DRM_MODE_SCALE_NO_SCALE) REG_WRITE(PFIT_CONTROL, 0); @@ -400,7 +401,6 @@ void oaktrail_lvds_init(struct drm_device *dev, out: mutex_unlock(&dev->mode_config.mutex); - drm_connector_register(connector); return; failed_find: diff --git a/drivers/gpu/drm/gma500/opregion.c b/drivers/gpu/drm/gma500/opregion.c index fef04ff8c3a9..dc494df71a48 100644 --- a/drivers/gpu/drm/gma500/opregion.c +++ b/drivers/gpu/drm/gma500/opregion.c @@ -23,6 +23,7 @@ */ #include <linux/acpi.h> #include "psb_drv.h" +#include "psb_irq.h" #include "psb_intel_reg.h" #define PCI_ASLE 0xe4 @@ -217,8 +218,8 @@ void psb_intel_opregion_enable_asle(struct drm_device *dev) if (asle && system_opregion ) { /* Don't do this on Medfield or other non PC like devices, they use the bit for something different altogether */ - psb_enable_pipestat(dev_priv, 0, PIPE_LEGACY_BLC_EVENT_ENABLE); - psb_enable_pipestat(dev_priv, 1, PIPE_LEGACY_BLC_EVENT_ENABLE); + gma_enable_pipestat(dev_priv, 0, PIPE_LEGACY_BLC_EVENT_ENABLE); + gma_enable_pipestat(dev_priv, 1, PIPE_LEGACY_BLC_EVENT_ENABLE); asle->tche = ASLE_ALS_EN | ASLE_BLC_EN | ASLE_PFIT_EN | ASLE_PFMB_EN; diff --git a/drivers/gpu/drm/gma500/power.c b/drivers/gpu/drm/gma500/power.c index d2a46d96e746..b91de6d36e41 100644 --- a/drivers/gpu/drm/gma500/power.c +++ b/drivers/gpu/drm/gma500/power.c @@ -28,6 +28,7 @@ * Alan Cox <alan@linux.intel.com> */ +#include "gem.h" #include "power.h" #include "psb_drv.h" #include "psb_reg.h" @@ -112,7 +113,9 @@ static void gma_resume_display(struct pci_dev *pdev) pci_write_config_word(pdev, PSB_GMCH_CTRL, dev_priv->gmch_ctrl | _PSB_GMCH_ENABLED); - psb_gtt_restore(dev); /* Rebuild our GTT mappings */ + /* Rebuild our GTT mappings */ + psb_gtt_resume(dev); + psb_gem_mm_resume(dev); dev_priv->ops->restore_regs(dev); } @@ -198,7 +201,7 @@ int gma_power_suspend(struct device *_dev) dev_err(dev->dev, "GPU hardware busy, cannot suspend\n"); return -EBUSY; } - psb_irq_uninstall(dev); + gma_irq_uninstall(dev); gma_suspend_display(dev); gma_suspend_pci(pdev); } @@ -220,8 +223,8 @@ int gma_power_resume(struct device *_dev) mutex_lock(&power_mutex); gma_resume_pci(pdev); gma_resume_display(pdev); - psb_irq_preinstall(dev); - psb_irq_postinstall(dev); + gma_irq_preinstall(dev); + gma_irq_postinstall(dev); mutex_unlock(&power_mutex); return 0; } @@ -267,8 +270,8 @@ bool gma_power_begin(struct drm_device *dev, bool force_on) /* Ok power up needed */ ret = gma_resume_pci(pdev); if (ret == 0) { - psb_irq_preinstall(dev); - psb_irq_postinstall(dev); + gma_irq_preinstall(dev); + gma_irq_postinstall(dev); pm_runtime_get(dev->dev); dev_priv->display_count++; spin_unlock_irqrestore(&power_ctrl_lock, flags); diff --git a/drivers/gpu/drm/gma500/psb_device.c b/drivers/gpu/drm/gma500/psb_device.c index 3030f18ba022..71534f4ca834 100644 --- a/drivers/gpu/drm/gma500/psb_device.c +++ b/drivers/gpu/drm/gma500/psb_device.c @@ -168,8 +168,10 @@ static void psb_init_pm(struct drm_device *dev) static int psb_save_display_registers(struct drm_device *dev) { struct drm_psb_private *dev_priv = to_drm_psb_private(dev); + struct gma_connector *gma_connector; struct drm_crtc *crtc; - struct gma_connector *connector; + struct drm_connector_list_iter conn_iter; + struct drm_connector *connector; struct psb_state *regs = &dev_priv->regs.psb; /* Display arbitration control + watermarks */ @@ -189,9 +191,13 @@ static int psb_save_display_registers(struct drm_device *dev) dev_priv->ops->save_crtc(crtc); } - list_for_each_entry(connector, &dev->mode_config.connector_list, base.head) - if (connector->save) - connector->save(&connector->base); + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { + gma_connector = to_gma_connector(connector); + if (gma_connector->save) + gma_connector->save(connector); + } + drm_connector_list_iter_end(&conn_iter); drm_modeset_unlock_all(dev); return 0; @@ -206,8 +212,10 @@ static int psb_save_display_registers(struct drm_device *dev) static int psb_restore_display_registers(struct drm_device *dev) { struct drm_psb_private *dev_priv = to_drm_psb_private(dev); + struct gma_connector *gma_connector; struct drm_crtc *crtc; - struct gma_connector *connector; + struct drm_connector_list_iter conn_iter; + struct drm_connector *connector; struct psb_state *regs = &dev_priv->regs.psb; /* Display arbitration + watermarks */ @@ -228,9 +236,13 @@ static int psb_restore_display_registers(struct drm_device *dev) if (drm_helper_crtc_in_use(crtc)) dev_priv->ops->restore_crtc(crtc); - list_for_each_entry(connector, &dev->mode_config.connector_list, base.head) - if (connector->restore) - connector->restore(&connector->base); + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { + gma_connector = to_gma_connector(connector); + if (gma_connector->restore) + gma_connector->restore(connector); + } + drm_connector_list_iter_end(&conn_iter); drm_modeset_unlock_all(dev); return 0; @@ -329,7 +341,6 @@ const struct psb_ops psb_chip_ops = { .chip_teardown = psb_chip_teardown, .crtc_helper = &psb_intel_helper_funcs, - .crtc_funcs = &gma_intel_crtc_funcs, .clock_funcs = &psb_clock_funcs, .output_init = psb_output_init, diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c index eeb681be9c95..1d8744f3e702 100644 --- a/drivers/gpu/drm/gma500/psb_drv.c +++ b/drivers/gpu/drm/gma500/psb_drv.c @@ -28,6 +28,7 @@ #include <drm/drm_vblank.h> #include "framebuffer.h" +#include "gem.h" #include "intel_bios.h" #include "mid_bios.h" #include "power.h" @@ -99,7 +100,7 @@ static const struct drm_ioctl_desc psb_ioctls[] = { * * Soft reset the graphics engine and then reload the necessary registers. */ -void psb_spank(struct drm_psb_private *dev_priv) +static void psb_spank(struct drm_psb_private *dev_priv) { PSB_WSGX32(_PSB_CS_RESET_BIF_RESET | _PSB_CS_RESET_DPM_RESET | _PSB_CS_RESET_TA_RESET | _PSB_CS_RESET_USE_RESET | @@ -172,6 +173,8 @@ static void psb_driver_unload(struct drm_device *dev) gma_backlight_exit(dev); psb_modeset_cleanup(dev); + gma_irq_uninstall(dev); + if (dev_priv->ops->chip_teardown) dev_priv->ops->chip_teardown(dev); @@ -184,17 +187,16 @@ static void psb_driver_unload(struct drm_device *dev) if (dev_priv->mmu) { struct psb_gtt *pg = &dev_priv->gtt; - down_read(&pg->sem); psb_mmu_remove_pfn_sequence( psb_mmu_get_default_pd (dev_priv->mmu), pg->mmu_gatt_start, dev_priv->vram_stolen_size >> PAGE_SHIFT); - up_read(&pg->sem); psb_mmu_driver_takedown(dev_priv->mmu); dev_priv->mmu = NULL; } - psb_gtt_takedown(dev); + psb_gem_mm_fini(dev); + psb_gtt_fini(dev); if (dev_priv->scratch_page) { set_pages_wb(dev_priv->scratch_page, 1); __free_page(dev_priv->scratch_page); @@ -234,10 +236,11 @@ static int psb_driver_load(struct drm_device *dev, unsigned long flags) struct drm_psb_private *dev_priv = to_drm_psb_private(dev); unsigned long resource_start, resource_len; unsigned long irqflags; - int ret = -ENOMEM; + struct drm_connector_list_iter conn_iter; struct drm_connector *connector; struct gma_encoder *gma_encoder; struct psb_gtt *pg; + int ret = -ENOMEM; /* initializing driver private data */ @@ -326,7 +329,10 @@ static int psb_driver_load(struct drm_device *dev, unsigned long flags) set_pages_uc(dev_priv->scratch_page, 1); - ret = psb_gtt_init(dev, 0); + ret = psb_gtt_init(dev); + if (ret) + goto out_err; + ret = psb_gem_mm_init(dev); if (ret) goto out_err; @@ -345,12 +351,10 @@ static int psb_driver_load(struct drm_device *dev, unsigned long flags) return ret; /* Add stolen memory to SGX MMU */ - down_read(&pg->sem); ret = psb_mmu_insert_pfn_sequence(psb_mmu_get_default_pd(dev_priv->mmu), dev_priv->stolen_base >> PAGE_SHIFT, pg->gatt_start, pg->stolen_size >> PAGE_SHIFT, 0); - up_read(&pg->sem); psb_mmu_set_pd_context(psb_mmu_get_default_pd(dev_priv->mmu), 0); psb_mmu_set_pd_context(dev_priv->pf_pd, 1); @@ -379,7 +383,7 @@ static int psb_driver_load(struct drm_device *dev, unsigned long flags) PSB_WVDC32(0xFFFFFFFF, PSB_INT_MASK_R); spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags); - psb_irq_install(dev, pdev->irq); + gma_irq_install(dev, pdev->irq); dev->max_vblank_count = 0xffffff; /* only 24 bits of frame count */ @@ -387,18 +391,18 @@ static int psb_driver_load(struct drm_device *dev, unsigned long flags) psb_fbdev_init(dev); drm_kms_helper_poll_init(dev); - /* Only add backlight support if we have LVDS output */ - list_for_each_entry(connector, &dev->mode_config.connector_list, - head) { + /* Only add backlight support if we have LVDS or MIPI output */ + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { gma_encoder = gma_attached_encoder(connector); - switch (gma_encoder->type) { - case INTEL_OUTPUT_LVDS: - case INTEL_OUTPUT_MIPI: + if (gma_encoder->type == INTEL_OUTPUT_LVDS || + gma_encoder->type == INTEL_OUTPUT_MIPI) { ret = gma_backlight_init(dev); break; } } + drm_connector_list_iter_end(&conn_iter); if (ret) return ret; diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h index 0439b10d3db5..0ddfec1a0851 100644 --- a/drivers/gpu/drm/gma500/psb_drv.h +++ b/drivers/gpu/drm/gma500/psb_drv.h @@ -13,7 +13,6 @@ #include <drm/drm_device.h> -#include "gma_display.h" #include "gtt.h" #include "intel_bios.h" #include "mmu.h" @@ -36,12 +35,6 @@ /* Append new drm mode definition here, align with libdrm definition */ #define DRM_MODE_SCALE_NO_SCALE 2 -enum { - CHIP_PSB_8108 = 0, /* Poulsbo */ - CHIP_PSB_8109 = 1, /* Poulsbo */ - CHIP_MRST_4100 = 2, /* Moorestown/Oaktrail */ -}; - #define IS_PSB(drm) ((to_pci_dev((drm)->dev)->device & 0xfffe) == 0x8108) #define IS_MRST(drm) ((to_pci_dev((drm)->dev)->device & 0xfff0) == 0x4100) #define IS_CDV(drm) ((to_pci_dev((drm)->dev)->device & 0xfff0) == 0x0be0) @@ -408,7 +401,6 @@ struct drm_psb_private { uint32_t stolen_base; u8 __iomem *vram_addr; unsigned long vram_stolen_size; - int gtt_initialized; u16 gmch_ctrl; /* Saved GTT setup */ u32 pge_ctl; @@ -586,7 +578,6 @@ struct psb_ops { /* Sub functions */ struct drm_crtc_helper_funcs const *crtc_helper; - struct drm_crtc_funcs const *crtc_funcs; const struct gma_clock_funcs *clock_funcs; /* Setup hooks */ @@ -618,36 +609,9 @@ struct psb_ops { int i2c_bus; /* I2C bus identifier for Moorestown */ }; - - -extern int drm_crtc_probe_output_modes(struct drm_device *dev, int, int); -extern int drm_pick_crtcs(struct drm_device *dev); - -/* psb_irq.c */ -extern void psb_irq_uninstall_islands(struct drm_device *dev, int hw_islands); -extern int psb_vblank_wait2(struct drm_device *dev, unsigned int *sequence); -extern int psb_vblank_wait(struct drm_device *dev, unsigned int *sequence); -extern int psb_enable_vblank(struct drm_crtc *crtc); -extern void psb_disable_vblank(struct drm_crtc *crtc); -void -psb_enable_pipestat(struct drm_psb_private *dev_priv, int pipe, u32 mask); - -void -psb_disable_pipestat(struct drm_psb_private *dev_priv, int pipe, u32 mask); - -extern u32 psb_get_vblank_counter(struct drm_crtc *crtc); - -/* framebuffer.c */ -extern int psbfb_probed(struct drm_device *dev); -extern int psbfb_remove(struct drm_device *dev, - struct drm_framebuffer *fb); -/* psb_drv.c */ -extern void psb_spank(struct drm_psb_private *dev_priv); - -/* psb_reset.c */ +/* psb_lid.c */ extern void psb_lid_timer_init(struct drm_psb_private *dev_priv); extern void psb_lid_timer_takedown(struct drm_psb_private *dev_priv); -extern void psb_print_pagefault(struct drm_psb_private *dev_priv); /* modesetting */ extern void psb_modeset_init(struct drm_device *dev); @@ -670,7 +634,6 @@ extern void oaktrail_lvds_init(struct drm_device *dev, /* psb_intel_display.c */ extern const struct drm_crtc_helper_funcs psb_intel_helper_funcs; -extern const struct drm_crtc_funcs gma_intel_crtc_funcs; /* psb_intel_lvds.c */ extern const struct drm_connector_helper_funcs @@ -690,43 +653,7 @@ extern const struct psb_ops oaktrail_chip_ops; /* cdv_device.c */ extern const struct psb_ops cdv_chip_ops; -/* Debug print bits setting */ -#define PSB_D_GENERAL (1 << 0) -#define PSB_D_INIT (1 << 1) -#define PSB_D_IRQ (1 << 2) -#define PSB_D_ENTRY (1 << 3) -/* debug the get H/V BP/FP count */ -#define PSB_D_HV (1 << 4) -#define PSB_D_DBI_BF (1 << 5) -#define PSB_D_PM (1 << 6) -#define PSB_D_RENDER (1 << 7) -#define PSB_D_REG (1 << 8) -#define PSB_D_MSVDX (1 << 9) -#define PSB_D_TOPAZ (1 << 10) - -extern int drm_idle_check_interval; - /* Utilities */ -static inline u32 MRST_MSG_READ32(int domain, uint port, uint offset) -{ - int mcr = (0xD0<<24) | (port << 16) | (offset << 8); - uint32_t ret_val = 0; - struct pci_dev *pci_root = pci_get_domain_bus_and_slot(domain, 0, 0); - pci_write_config_dword(pci_root, 0xD0, mcr); - pci_read_config_dword(pci_root, 0xD4, &ret_val); - pci_dev_put(pci_root); - return ret_val; -} -static inline void MRST_MSG_WRITE32(int domain, uint port, uint offset, - u32 value) -{ - int mcr = (0xE0<<24) | (port << 16) | (offset << 8) | 0xF0; - struct pci_dev *pci_root = pci_get_domain_bus_and_slot(domain, 0, 0); - pci_write_config_dword(pci_root, 0xD4, value); - pci_write_config_dword(pci_root, 0xD0, mcr); - pci_dev_put(pci_root); -} - static inline uint32_t REGISTER_READ(struct drm_device *dev, uint32_t reg) { struct drm_psb_private *dev_priv = to_drm_psb_private(dev); @@ -807,24 +734,9 @@ static inline void REGISTER_WRITE8(struct drm_device *dev, #define PSB_WVDC32(_val, _offs) iowrite32(_val, dev_priv->vdc_reg + (_offs)) #define PSB_RVDC32(_offs) ioread32(dev_priv->vdc_reg + (_offs)) -/* #define TRAP_SGX_PM_FAULT 1 */ -#ifdef TRAP_SGX_PM_FAULT -#define PSB_RSGX32(_offs) \ -({ \ - if (inl(dev_priv->apm_base + PSB_APM_STS) & 0x3) { \ - pr_err("access sgx when it's off!! (READ) %s, %d\n", \ - __FILE__, __LINE__); \ - melay(1000); \ - } \ - ioread32(dev_priv->sgx_reg + (_offs)); \ -}) -#else #define PSB_RSGX32(_offs) ioread32(dev_priv->sgx_reg + (_offs)) -#endif #define PSB_WSGX32(_val, _offs) iowrite32(_val, dev_priv->sgx_reg + (_offs)) -#define MSVDX_REG_DUMP 0 - #define PSB_WMSVDX32(_val, _offs) iowrite32(_val, dev_priv->msvdx_reg + (_offs)) #define PSB_RMSVDX32(_offs) ioread32(dev_priv->msvdx_reg + (_offs)) diff --git a/drivers/gpu/drm/gma500/psb_intel_display.c b/drivers/gpu/drm/gma500/psb_intel_display.c index d5f95212934e..9a5ea06a1a8e 100644 --- a/drivers/gpu/drm/gma500/psb_intel_display.c +++ b/drivers/gpu/drm/gma500/psb_intel_display.c @@ -106,7 +106,7 @@ static int psb_intel_crtc_mode_set(struct drm_crtc *crtc, u32 dpll = 0, fp = 0, dspcntr, pipeconf; bool ok, is_sdvo = false; bool is_lvds = false, is_tv = false; - struct drm_mode_config *mode_config = &dev->mode_config; + struct drm_connector_list_iter conn_iter; struct drm_connector *connector; const struct gma_limit_t *limit; @@ -116,7 +116,8 @@ static int psb_intel_crtc_mode_set(struct drm_crtc *crtc, return 0; } - list_for_each_entry(connector, &mode_config->connector_list, head) { + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { struct gma_encoder *gma_encoder = gma_attached_encoder(connector); if (!connector->encoder @@ -134,7 +135,10 @@ static int psb_intel_crtc_mode_set(struct drm_crtc *crtc, is_tv = true; break; } + + break; } + drm_connector_list_iter_end(&conn_iter); refclk = 96000; @@ -427,18 +431,6 @@ const struct drm_crtc_helper_funcs psb_intel_helper_funcs = { .disable = gma_crtc_disable, }; -const struct drm_crtc_funcs gma_intel_crtc_funcs = { - .cursor_set = gma_crtc_cursor_set, - .cursor_move = gma_crtc_cursor_move, - .gamma_set = gma_crtc_gamma_set, - .set_config = gma_crtc_set_config, - .destroy = gma_crtc_destroy, - .page_flip = gma_crtc_page_flip, - .enable_vblank = psb_enable_vblank, - .disable_vblank = psb_disable_vblank, - .get_vblank_counter = psb_get_vblank_counter, -}; - const struct gma_clock_funcs psb_clock_funcs = { .clock = psb_intel_clock, .limit = psb_intel_limit, @@ -500,8 +492,7 @@ void psb_intel_crtc_init(struct drm_device *dev, int pipe, return; } - /* Set the CRTC operations from the chip specific data */ - drm_crtc_init(dev, &gma_crtc->base, dev_priv->ops->crtc_funcs); + drm_crtc_init(dev, &gma_crtc->base, &gma_crtc_funcs); /* Set the CRTC clock functions from chip specific data */ gma_crtc->clock_funcs = dev_priv->ops->clock_funcs; @@ -535,28 +526,32 @@ void psb_intel_crtc_init(struct drm_device *dev, int pipe, struct drm_crtc *psb_intel_get_crtc_from_pipe(struct drm_device *dev, int pipe) { - struct drm_crtc *crtc = NULL; + struct drm_crtc *crtc; list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { struct gma_crtc *gma_crtc = to_gma_crtc(crtc); + if (gma_crtc->pipe == pipe) - break; + return crtc; } - return crtc; + return NULL; } int gma_connector_clones(struct drm_device *dev, int type_mask) { - int index_mask = 0; + struct drm_connector_list_iter conn_iter; struct drm_connector *connector; + int index_mask = 0; int entry = 0; - list_for_each_entry(connector, &dev->mode_config.connector_list, - head) { + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector, &conn_iter) { struct gma_encoder *gma_encoder = gma_attached_encoder(connector); if (type_mask & (1 << gma_encoder->type)) index_mask |= (1 << entry); entry++; } + drm_connector_list_iter_end(&conn_iter); + return index_mask; } diff --git a/drivers/gpu/drm/gma500/psb_intel_lvds.c b/drivers/gpu/drm/gma500/psb_intel_lvds.c index ac97e0d3c7dd..cad00380b386 100644 --- a/drivers/gpu/drm/gma500/psb_intel_lvds.c +++ b/drivers/gpu/drm/gma500/psb_intel_lvds.c @@ -521,13 +521,13 @@ static int psb_intel_lvds_get_modes(struct drm_connector *connector) */ void psb_intel_lvds_destroy(struct drm_connector *connector) { + struct gma_connector *gma_connector = to_gma_connector(connector); struct gma_encoder *gma_encoder = gma_attached_encoder(connector); struct psb_intel_lvds_priv *lvds_priv = gma_encoder->dev_priv; psb_intel_i2c_destroy(lvds_priv->ddc_bus); - drm_connector_unregister(connector); drm_connector_cleanup(connector); - kfree(connector); + kfree(gma_connector); } int psb_intel_lvds_set_property(struct drm_connector *connector, @@ -782,7 +782,6 @@ void psb_intel_lvds_init(struct drm_device *dev, */ out: mutex_unlock(&dev->mode_config.mutex); - drm_connector_register(connector); return; failed_find: diff --git a/drivers/gpu/drm/gma500/psb_intel_sdvo.c b/drivers/gpu/drm/gma500/psb_intel_sdvo.c index 042c4392e676..a85aace25548 100644 --- a/drivers/gpu/drm/gma500/psb_intel_sdvo.c +++ b/drivers/gpu/drm/gma500/psb_intel_sdvo.c @@ -1542,9 +1542,10 @@ static int psb_intel_sdvo_get_modes(struct drm_connector *connector) static void psb_intel_sdvo_destroy(struct drm_connector *connector) { - drm_connector_unregister(connector); + struct gma_connector *gma_connector = to_gma_connector(connector); + drm_connector_cleanup(connector); - kfree(connector); + kfree(gma_connector); } static bool psb_intel_sdvo_detect_hdmi_audio(struct drm_connector *connector) @@ -1932,7 +1933,6 @@ psb_intel_sdvo_connector_init(struct psb_intel_sdvo_connector *connector, connector->base.restore = psb_intel_sdvo_restore; gma_connector_attach_encoder(&connector->base, &encoder->base); - drm_connector_register(&connector->base.base); } static void diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c index ccf402007beb..e6e6d61bbeab 100644 --- a/drivers/gpu/drm/gma500/psb_irq.c +++ b/drivers/gpu/drm/gma500/psb_irq.c @@ -21,8 +21,7 @@ * inline functions */ -static inline u32 -psb_pipestat(int pipe) +static inline u32 gma_pipestat(int pipe) { if (pipe == 0) return PIPEASTAT; @@ -33,8 +32,7 @@ psb_pipestat(int pipe) BUG(); } -static inline u32 -mid_pipe_event(int pipe) +static inline u32 gma_pipe_event(int pipe) { if (pipe == 0) return _PSB_PIPEA_EVENT_FLAG; @@ -45,20 +43,7 @@ mid_pipe_event(int pipe) BUG(); } -static inline u32 -mid_pipe_vsync(int pipe) -{ - if (pipe == 0) - return _PSB_VSYNC_PIPEA_FLAG; - if (pipe == 1) - return _PSB_VSYNC_PIPEB_FLAG; - if (pipe == 2) - return _MDFLD_PIPEC_VBLANK_FLAG; - BUG(); -} - -static inline u32 -mid_pipeconf(int pipe) +static inline u32 gma_pipeconf(int pipe) { if (pipe == 0) return PIPEACONF; @@ -69,11 +54,10 @@ mid_pipeconf(int pipe) BUG(); } -void -psb_enable_pipestat(struct drm_psb_private *dev_priv, int pipe, u32 mask) +void gma_enable_pipestat(struct drm_psb_private *dev_priv, int pipe, u32 mask) { if ((dev_priv->pipestat[pipe] & mask) != mask) { - u32 reg = psb_pipestat(pipe); + u32 reg = gma_pipestat(pipe); dev_priv->pipestat[pipe] |= mask; /* Enable the interrupt, clear any pending status */ if (gma_power_begin(&dev_priv->dev, false)) { @@ -86,11 +70,10 @@ psb_enable_pipestat(struct drm_psb_private *dev_priv, int pipe, u32 mask) } } -void -psb_disable_pipestat(struct drm_psb_private *dev_priv, int pipe, u32 mask) +void gma_disable_pipestat(struct drm_psb_private *dev_priv, int pipe, u32 mask) { if ((dev_priv->pipestat[pipe] & mask) != 0) { - u32 reg = psb_pipestat(pipe); + u32 reg = gma_pipestat(pipe); dev_priv->pipestat[pipe] &= ~mask; if (gma_power_begin(&dev_priv->dev, false)) { u32 writeVal = PSB_RVDC32(reg); @@ -105,12 +88,12 @@ psb_disable_pipestat(struct drm_psb_private *dev_priv, int pipe, u32 mask) /* * Display controller interrupt handler for pipe event. */ -static void mid_pipe_event_handler(struct drm_device *dev, int pipe) +static void gma_pipe_event_handler(struct drm_device *dev, int pipe) { struct drm_psb_private *dev_priv = to_drm_psb_private(dev); uint32_t pipe_stat_val = 0; - uint32_t pipe_stat_reg = psb_pipestat(pipe); + uint32_t pipe_stat_reg = gma_pipestat(pipe); uint32_t pipe_enable = dev_priv->pipestat[pipe]; uint32_t pipe_status = dev_priv->pipestat[pipe] >> 16; uint32_t pipe_clear; @@ -160,22 +143,22 @@ static void mid_pipe_event_handler(struct drm_device *dev, int pipe) /* * Display controller interrupt handler. */ -static void psb_vdc_interrupt(struct drm_device *dev, uint32_t vdc_stat) +static void gma_vdc_interrupt(struct drm_device *dev, uint32_t vdc_stat) { if (vdc_stat & _PSB_IRQ_ASLE) psb_intel_opregion_asle_intr(dev); if (vdc_stat & _PSB_VSYNC_PIPEA_FLAG) - mid_pipe_event_handler(dev, 0); + gma_pipe_event_handler(dev, 0); if (vdc_stat & _PSB_VSYNC_PIPEB_FLAG) - mid_pipe_event_handler(dev, 1); + gma_pipe_event_handler(dev, 1); } /* * SGX interrupt handler */ -static void psb_sgx_interrupt(struct drm_device *dev, u32 stat_1, u32 stat_2) +static void gma_sgx_interrupt(struct drm_device *dev, u32 stat_1, u32 stat_2) { struct drm_psb_private *dev_priv = to_drm_psb_private(dev); u32 val, addr; @@ -222,7 +205,7 @@ static void psb_sgx_interrupt(struct drm_device *dev, u32 stat_1, u32 stat_2) PSB_RSGX32(PSB_CR_EVENT_HOST_CLEAR2); } -static irqreturn_t psb_irq_handler(int irq, void *arg) +static irqreturn_t gma_irq_handler(int irq, void *arg) { struct drm_device *dev = arg; struct drm_psb_private *dev_priv = to_drm_psb_private(dev); @@ -246,14 +229,14 @@ static irqreturn_t psb_irq_handler(int irq, void *arg) spin_unlock(&dev_priv->irqmask_lock); if (dsp_int && gma_power_is_on(dev)) { - psb_vdc_interrupt(dev, vdc_stat); + gma_vdc_interrupt(dev, vdc_stat); handled = 1; } if (sgx_int) { sgx_stat_1 = PSB_RSGX32(PSB_CR_EVENT_STATUS); sgx_stat_2 = PSB_RSGX32(PSB_CR_EVENT_STATUS2); - psb_sgx_interrupt(dev, sgx_stat_1, sgx_stat_2); + gma_sgx_interrupt(dev, sgx_stat_1, sgx_stat_2); handled = 1; } @@ -274,7 +257,7 @@ static irqreturn_t psb_irq_handler(int irq, void *arg) return IRQ_HANDLED; } -void psb_irq_preinstall(struct drm_device *dev) +void gma_irq_preinstall(struct drm_device *dev) { struct drm_psb_private *dev_priv = to_drm_psb_private(dev); unsigned long irqflags; @@ -303,7 +286,7 @@ void psb_irq_preinstall(struct drm_device *dev) spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags); } -void psb_irq_postinstall(struct drm_device *dev) +void gma_irq_postinstall(struct drm_device *dev) { struct drm_psb_private *dev_priv = to_drm_psb_private(dev); unsigned long irqflags; @@ -322,9 +305,9 @@ void psb_irq_postinstall(struct drm_device *dev) for (i = 0; i < dev->num_crtcs; ++i) { if (dev->vblank[i].enabled) - psb_enable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); + gma_enable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); else - psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); + gma_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); } if (dev_priv->ops->hotplug_enable) @@ -333,26 +316,26 @@ void psb_irq_postinstall(struct drm_device *dev) spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags); } -int psb_irq_install(struct drm_device *dev, unsigned int irq) +int gma_irq_install(struct drm_device *dev, unsigned int irq) { int ret; if (irq == IRQ_NOTCONNECTED) return -ENOTCONN; - psb_irq_preinstall(dev); + gma_irq_preinstall(dev); /* PCI devices require shared interrupts. */ - ret = request_irq(irq, psb_irq_handler, IRQF_SHARED, dev->driver->name, dev); + ret = request_irq(irq, gma_irq_handler, IRQF_SHARED, dev->driver->name, dev); if (ret) return ret; - psb_irq_postinstall(dev); + gma_irq_postinstall(dev); return 0; } -void psb_irq_uninstall(struct drm_device *dev) +void gma_irq_uninstall(struct drm_device *dev) { struct drm_psb_private *dev_priv = to_drm_psb_private(dev); struct pci_dev *pdev = to_pci_dev(dev->dev); @@ -368,7 +351,7 @@ void psb_irq_uninstall(struct drm_device *dev) for (i = 0; i < dev->num_crtcs; ++i) { if (dev->vblank[i].enabled) - psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); + gma_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); } dev_priv->vdc_irq_mask &= _PSB_IRQ_SGX_FLAG | @@ -388,17 +371,14 @@ void psb_irq_uninstall(struct drm_device *dev) free_irq(pdev->irq, dev); } -/* - * It is used to enable VBLANK interrupt - */ -int psb_enable_vblank(struct drm_crtc *crtc) +int gma_crtc_enable_vblank(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; unsigned int pipe = crtc->index; struct drm_psb_private *dev_priv = to_drm_psb_private(dev); unsigned long irqflags; uint32_t reg_val = 0; - uint32_t pipeconf_reg = mid_pipeconf(pipe); + uint32_t pipeconf_reg = gma_pipeconf(pipe); if (gma_power_begin(dev, false)) { reg_val = REG_READ(pipeconf_reg); @@ -417,17 +397,14 @@ int psb_enable_vblank(struct drm_crtc *crtc) PSB_WVDC32(~dev_priv->vdc_irq_mask, PSB_INT_MASK_R); PSB_WVDC32(dev_priv->vdc_irq_mask, PSB_INT_ENABLE_R); - psb_enable_pipestat(dev_priv, pipe, PIPE_VBLANK_INTERRUPT_ENABLE); + gma_enable_pipestat(dev_priv, pipe, PIPE_VBLANK_INTERRUPT_ENABLE); spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags); return 0; } -/* - * It is used to disable VBLANK interrupt - */ -void psb_disable_vblank(struct drm_crtc *crtc) +void gma_crtc_disable_vblank(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; unsigned int pipe = crtc->index; @@ -443,7 +420,7 @@ void psb_disable_vblank(struct drm_crtc *crtc) PSB_WVDC32(~dev_priv->vdc_irq_mask, PSB_INT_MASK_R); PSB_WVDC32(dev_priv->vdc_irq_mask, PSB_INT_ENABLE_R); - psb_disable_pipestat(dev_priv, pipe, PIPE_VBLANK_INTERRUPT_ENABLE); + gma_disable_pipestat(dev_priv, pipe, PIPE_VBLANK_INTERRUPT_ENABLE); spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags); } @@ -451,7 +428,7 @@ void psb_disable_vblank(struct drm_crtc *crtc) /* Called from drm generic code, passed a 'crtc', which * we use as a pipe index */ -u32 psb_get_vblank_counter(struct drm_crtc *crtc) +u32 gma_crtc_get_vblank_counter(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; unsigned int pipe = crtc->index; @@ -486,8 +463,8 @@ u32 psb_get_vblank_counter(struct drm_crtc *crtc) if (!(reg_val & PIPEACONF_ENABLE)) { dev_err(dev->dev, "trying to get vblank count for disabled pipe %u\n", - pipe); - goto psb_get_vblank_counter_exit; + pipe); + goto err_gma_power_end; } /* @@ -506,8 +483,7 @@ u32 psb_get_vblank_counter(struct drm_crtc *crtc) count = (high1 << 8) | low; -psb_get_vblank_counter_exit: - +err_gma_power_end: gma_power_end(dev); return count; diff --git a/drivers/gpu/drm/gma500/psb_irq.h b/drivers/gpu/drm/gma500/psb_irq.h index a97cb49393d8..b51e395194ff 100644 --- a/drivers/gpu/drm/gma500/psb_irq.h +++ b/drivers/gpu/drm/gma500/psb_irq.h @@ -15,16 +15,15 @@ struct drm_crtc; struct drm_device; -bool sysirq_init(struct drm_device *dev); -void sysirq_uninit(struct drm_device *dev); +void gma_irq_preinstall(struct drm_device *dev); +void gma_irq_postinstall(struct drm_device *dev); +int gma_irq_install(struct drm_device *dev, unsigned int irq); +void gma_irq_uninstall(struct drm_device *dev); -void psb_irq_preinstall(struct drm_device *dev); -void psb_irq_postinstall(struct drm_device *dev); -int psb_irq_install(struct drm_device *dev, unsigned int irq); -void psb_irq_uninstall(struct drm_device *dev); - -int psb_enable_vblank(struct drm_crtc *crtc); -void psb_disable_vblank(struct drm_crtc *crtc); -u32 psb_get_vblank_counter(struct drm_crtc *crtc); +int gma_crtc_enable_vblank(struct drm_crtc *crtc); +void gma_crtc_disable_vblank(struct drm_crtc *crtc); +u32 gma_crtc_get_vblank_counter(struct drm_crtc *crtc); +void gma_enable_pipestat(struct drm_psb_private *dev_priv, int pipe, u32 mask); +void gma_disable_pipestat(struct drm_psb_private *dev_priv, int pipe, u32 mask); #endif /* _PSB_IRQ_H_ */ diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c index 3d87da283cfa..efe8591619e3 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c @@ -1047,7 +1047,8 @@ intel_prepare_plane_fb(struct drm_plane *_plane, if (ret < 0) goto unpin_fb; - dma_resv_iter_begin(&cursor, obj->base.resv, false); + dma_resv_iter_begin(&cursor, obj->base.resv, + DMA_RESV_USAGE_WRITE); dma_resv_for_each_fence_unlocked(&cursor, fence) { add_rps_boost_after_vblank(new_plane_state->hw.crtc, fence); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_busy.c b/drivers/gpu/drm/i915/gem/i915_gem_busy.c index 470fdfd61a0f..ddda468241ef 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_busy.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_busy.c @@ -138,21 +138,21 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data, * Alternatively, we can trade that extra information on read/write * activity with * args->busy = - * !dma_resv_test_signaled(obj->resv, true); + * !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ); * to report the overall busyness. This is what the wait-ioctl does. * */ args->busy = 0; - dma_resv_iter_begin(&cursor, obj->base.resv, true); + dma_resv_iter_begin(&cursor, obj->base.resv, DMA_RESV_USAGE_READ); dma_resv_for_each_fence_unlocked(&cursor, fence) { if (dma_resv_iter_is_restarted(&cursor)) args->busy = 0; - if (dma_resv_iter_is_exclusive(&cursor)) - /* Translate the exclusive fence to the READ *and* WRITE engine */ + if (dma_resv_iter_usage(&cursor) <= DMA_RESV_USAGE_WRITE) + /* Translate the write fences to the READ *and* WRITE engine */ args->busy |= busy_check_writer(fence); else - /* Translate shared fences to READ set of engines */ + /* Translate read fences to READ set of engines */ args->busy |= busy_check_reader(fence); } dma_resv_iter_end(&cursor); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c index ce91b23385cf..0512afdd20d8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_clflush.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_clflush.c @@ -108,14 +108,16 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj, trace_i915_gem_object_clflush(obj); clflush = NULL; - if (!(flags & I915_CLFLUSH_SYNC)) + if (!(flags & I915_CLFLUSH_SYNC) && + dma_resv_reserve_fences(obj->base.resv, 1) == 0) clflush = clflush_work_create(obj); if (clflush) { i915_sw_fence_await_reservation(&clflush->base.chain, obj->base.resv, NULL, true, i915_fence_timeout(i915), I915_FENCE_GFP); - dma_resv_add_excl_fence(obj->base.resv, &clflush->base.dma); + dma_resv_add_fence(obj->base.resv, &clflush->base.dma, + DMA_RESV_USAGE_KERNEL); dma_fence_work_commit(&clflush->base); /* * We must have successfully populated the pages(since we are diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index b9427d82bbc7..fd0e15d9573c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -999,11 +999,9 @@ static int eb_validate_vmas(struct i915_execbuffer *eb) } } - if (!(ev->flags & EXEC_OBJECT_WRITE)) { - err = dma_resv_reserve_shared(vma->obj->base.resv, 1); - if (err) - return err; - } + err = dma_resv_reserve_fences(vma->obj->base.resv, 1); + if (err) + return err; GEM_BUG_ON(drm_mm_node_allocated(&vma->node) && eb_vma_misplaced(&eb->exec[i], vma, ev->flags)); @@ -2304,7 +2302,7 @@ static int eb_parse(struct i915_execbuffer *eb) if (IS_ERR(batch)) return PTR_ERR(batch); - err = dma_resv_reserve_shared(shadow->obj->base.resv, 1); + err = dma_resv_reserve_fences(shadow->obj->base.resv, 1); if (err) return err; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c index ede084f36ca9..02ed3b269326 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c @@ -68,7 +68,7 @@ bool __i915_gem_object_is_lmem(struct drm_i915_gem_object *obj) struct intel_memory_region *mr = READ_ONCE(obj->mm.region); #ifdef CONFIG_LOCKDEP - GEM_WARN_ON(dma_resv_test_signaled(obj->base.resv, true) && + GEM_WARN_ON(dma_resv_test_signaled(obj->base.resv, DMA_RESV_USAGE_BOOKKEEP) && i915_gem_object_evictable(obj)); #endif return mr && (mr->type == INTEL_MEMORY_LOCAL || diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index c1c3b510b9e2..747ac65e060f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -742,30 +742,19 @@ static const struct drm_gem_object_funcs i915_gem_object_funcs = { /** * i915_gem_object_get_moving_fence - Get the object's moving fence if any * @obj: The object whose moving fence to get. + * @fence: The resulting fence * * A non-signaled moving fence means that there is an async operation * pending on the object that needs to be waited on before setting up * any GPU- or CPU PTEs to the object's pages. * - * Return: A refcounted pointer to the object's moving fence if any, - * NULL otherwise. + * Return: Negative error code or 0 for success. */ -struct dma_fence * -i915_gem_object_get_moving_fence(struct drm_i915_gem_object *obj) +int i915_gem_object_get_moving_fence(struct drm_i915_gem_object *obj, + struct dma_fence **fence) { - return dma_fence_get(i915_gem_to_ttm(obj)->moving); -} - -void i915_gem_object_set_moving_fence(struct drm_i915_gem_object *obj, - struct dma_fence *fence) -{ - struct dma_fence **moving = &i915_gem_to_ttm(obj)->moving; - - if (*moving == fence) - return; - - dma_fence_put(*moving); - *moving = dma_fence_get(fence); + return dma_resv_get_singleton(obj->base.resv, DMA_RESV_USAGE_KERNEL, + fence); } /** @@ -783,23 +772,16 @@ void i915_gem_object_set_moving_fence(struct drm_i915_gem_object *obj, int i915_gem_object_wait_moving_fence(struct drm_i915_gem_object *obj, bool intr) { - struct dma_fence *fence = i915_gem_to_ttm(obj)->moving; - int ret; + long ret; assert_object_held(obj); - if (!fence) - return 0; - ret = dma_fence_wait(fence, intr); - if (ret) - return ret; + ret = dma_resv_wait_timeout(obj->base. resv, DMA_RESV_USAGE_KERNEL, + intr, MAX_SCHEDULE_TIMEOUT); + if (!ret) + ret = -ETIME; - if (fence->error) - return fence->error; - - i915_gem_to_ttm(obj)->moving = NULL; - dma_fence_put(fence); - return 0; + return ret < 0 ? ret : 0; } #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 02c37fe4a535..e11d82a9f7c3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -520,12 +520,8 @@ i915_gem_object_finish_access(struct drm_i915_gem_object *obj) i915_gem_object_unpin_pages(obj); } -struct dma_fence * -i915_gem_object_get_moving_fence(struct drm_i915_gem_object *obj); - -void i915_gem_object_set_moving_fence(struct drm_i915_gem_object *obj, - struct dma_fence *fence); - +int i915_gem_object_get_moving_fence(struct drm_i915_gem_object *obj, + struct dma_fence **fence); int i915_gem_object_wait_moving_fence(struct drm_i915_gem_object *obj, bool intr); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 45cc5837ce00..b9ae6b02f304 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -283,7 +283,7 @@ static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, i915_tt->is_shmem = true; } - ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags, caching); + ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags, caching, 0); if (ret) goto err_free; @@ -936,7 +936,7 @@ void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj) bo->priority = I915_TTM_PRIO_HAS_PAGES; } - ttm_bo_move_to_lru_tail(bo, bo->resource, NULL); + ttm_bo_move_to_lru_tail(bo); spin_unlock(&bo->bdev->lru_lock); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c index 1ebe6e4086a1..a10716f4e717 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c @@ -467,19 +467,6 @@ out: return fence; } -static int -prev_deps(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, - struct i915_deps *deps) -{ - int ret; - - ret = i915_deps_add_dependency(deps, bo->moving, ctx); - if (!ret) - ret = i915_deps_add_resv(deps, bo->base.resv, ctx); - - return ret; -} - /** * i915_ttm_move - The TTM move callback used by i915. * @bo: The buffer object. @@ -534,7 +521,7 @@ int i915_ttm_move(struct ttm_buffer_object *bo, bool evict, struct i915_deps deps; i915_deps_init(&deps, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); - ret = prev_deps(bo, ctx, &deps); + ret = i915_deps_add_resv(&deps, bo->base.resv, ctx); if (ret) { i915_refct_sgt_put(dst_rsgt); return ret; @@ -611,7 +598,11 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst, assert_object_held(src); i915_deps_init(&deps, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); - ret = dma_resv_reserve_shared(src_bo->base.resv, 1); + ret = dma_resv_reserve_fences(src_bo->base.resv, 1); + if (ret) + return ret; + + ret = dma_resv_reserve_fences(dst_bo->base.resv, 1); if (ret) return ret; @@ -633,9 +624,8 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst, if (IS_ERR_OR_NULL(copy_fence)) return PTR_ERR_OR_ZERO(copy_fence); - dma_resv_add_excl_fence(dst_bo->base.resv, copy_fence); - dma_resv_add_shared_fence(src_bo->base.resv, copy_fence); - + dma_resv_add_fence(dst_bo->base.resv, copy_fence, DMA_RESV_USAGE_WRITE); + dma_resv_add_fence(src_bo->base.resv, copy_fence, DMA_RESV_USAGE_READ); dma_fence_put(copy_fence); return 0; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 6d1a71d6404c..094f06b4ce33 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -86,7 +86,7 @@ static bool i915_gem_userptr_invalidate(struct mmu_interval_notifier *mni, return true; /* we will unbind on next submission, still have userptr pins */ - r = dma_resv_wait_timeout(obj->base.resv, true, false, + r = dma_resv_wait_timeout(obj->base.resv, DMA_RESV_USAGE_BOOKKEEP, false, MAX_SCHEDULE_TIMEOUT); if (r <= 0) drm_err(&i915->drm, "(%ld) failed to wait for idle\n", r); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c index dab3d30c09a0..319936f91ac5 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c @@ -40,7 +40,8 @@ i915_gem_object_wait_reservation(struct dma_resv *resv, struct dma_fence *fence; long ret = timeout ?: 1; - dma_resv_iter_begin(&cursor, resv, flags & I915_WAIT_ALL); + dma_resv_iter_begin(&cursor, resv, + dma_resv_usage_rw(flags & I915_WAIT_ALL)); dma_resv_for_each_fence_unlocked(&cursor, fence) { ret = i915_gem_object_wait_fence(fence, flags, timeout); if (ret <= 0) @@ -117,7 +118,8 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj, struct dma_resv_iter cursor; struct dma_fence *fence; - dma_resv_iter_begin(&cursor, obj->base.resv, flags & I915_WAIT_ALL); + dma_resv_iter_begin(&cursor, obj->base.resv, + dma_resv_usage_rw(flags & I915_WAIT_ALL)); dma_resv_for_each_fence_unlocked(&cursor, fence) i915_gem_fence_wait_priority(fence, attr); dma_resv_iter_end(&cursor); diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c index b071a58dd6da..b4275b55e5b8 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c @@ -219,7 +219,8 @@ static int igt_dmabuf_import_same_driver(struct drm_i915_private *i915, goto out_detach; } - timeout = dma_resv_wait_timeout(dmabuf->resv, false, true, 5 * HZ); + timeout = dma_resv_wait_timeout(dmabuf->resv, DMA_RESV_USAGE_WRITE, + true, 5 * HZ); if (!timeout) { pr_err("dmabuf wait for exclusive fence timed out.\n"); timeout = -ETIME; diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c index d534141b2cf7..0ad443a90c8b 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c @@ -216,8 +216,10 @@ static int __igt_lmem_pages_migrate(struct intel_gt *gt, i915_gem_object_is_lmem(obj), 0xdeadbeaf, &rq); if (rq) { - dma_resv_add_excl_fence(obj->base.resv, &rq->fence); - i915_gem_object_set_moving_fence(obj, &rq->fence); + err = dma_resv_reserve_fences(obj->base.resv, 1); + if (!err) + dma_resv_add_fence(obj->base.resv, &rq->fence, + DMA_RESV_USAGE_KERNEL); i915_request_put(rq); } if (err) diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index c4c2c91a2ee7..5bc93a1ce3e3 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -1221,8 +1221,8 @@ static int __igt_mmap_migrate(struct intel_memory_region **placements, expand32(POISON_INUSE), &rq); i915_gem_object_unpin_pages(obj); if (rq) { - dma_resv_add_excl_fence(obj->base.resv, &rq->fence); - i915_gem_object_set_moving_fence(obj, &rq->fence); + dma_resv_add_fence(obj->base.resv, &rq->fence, + DMA_RESV_USAGE_KERNEL); i915_request_put(rq); } i915_gem_object_unlock(obj); diff --git a/drivers/gpu/drm/i915/i915_deps.c b/drivers/gpu/drm/i915/i915_deps.c index 999210b37325..297b8e4e42ee 100644 --- a/drivers/gpu/drm/i915/i915_deps.c +++ b/drivers/gpu/drm/i915/i915_deps.c @@ -226,7 +226,7 @@ int i915_deps_add_resv(struct i915_deps *deps, struct dma_resv *resv, struct dma_fence *fence; dma_resv_assert_held(resv); - dma_resv_for_each_fence(&iter, resv, true, fence) { + dma_resv_for_each_fence(&iter, resv, dma_resv_usage_rw(true), fence) { int ret = i915_deps_add_dependency(deps, fence, ctx); if (ret) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 582770360ad1..73d5195146b0 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1598,7 +1598,8 @@ i915_request_await_object(struct i915_request *to, struct dma_fence *fence; int ret = 0; - dma_resv_for_each_fence(&cursor, obj->base.resv, write, fence) { + dma_resv_for_each_fence(&cursor, obj->base.resv, + dma_resv_usage_rw(write), fence) { ret = i915_request_await_dma_fence(to, fence); if (ret) break; diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index 2a74a9a1cafe..ae984c66c48a 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -585,7 +585,7 @@ int i915_sw_fence_await_reservation(struct i915_sw_fence *fence, debug_fence_assert(fence); might_sleep_if(gfpflags_allow_blocking(gfp)); - dma_resv_iter_begin(&cursor, resv, write); + dma_resv_iter_begin(&cursor, resv, dma_resv_usage_rw(write)); dma_resv_for_each_fence_unlocked(&cursor, f) { pending = i915_sw_fence_await_dma_fence(fence, f, timeout, gfp); diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 94fcdb7bd21d..d077f7b9eaad 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1357,10 +1357,17 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww, if (err) return err; + if (vma->obj) { + err = i915_gem_object_get_moving_fence(vma->obj, &moving); + if (err) + return err; + } else { + moving = NULL; + } + if (flags & PIN_GLOBAL) wakeref = intel_runtime_pm_get(&vma->vm->i915->runtime_pm); - moving = vma->obj ? i915_gem_object_get_moving_fence(vma->obj) : NULL; if (flags & vma->vm->bind_async_flags || moving) { /* lock VM */ err = i915_vm_lock_objects(vma->vm, ww); @@ -1819,20 +1826,28 @@ int _i915_vma_move_to_active(struct i915_vma *vma, intel_frontbuffer_put(front); } + if (!(flags & __EXEC_OBJECT_NO_RESERVE)) { + err = dma_resv_reserve_fences(vma->obj->base.resv, 1); + if (unlikely(err)) + return err; + } + if (fence) { - dma_resv_add_excl_fence(vma->obj->base.resv, fence); + dma_resv_add_fence(vma->obj->base.resv, fence, + DMA_RESV_USAGE_WRITE); obj->write_domain = I915_GEM_DOMAIN_RENDER; obj->read_domains = 0; } } else { if (!(flags & __EXEC_OBJECT_NO_RESERVE)) { - err = dma_resv_reserve_shared(vma->obj->base.resv, 1); + err = dma_resv_reserve_fences(vma->obj->base.resv, 1); if (unlikely(err)) return err; } if (fence) { - dma_resv_add_shared_fence(vma->obj->base.resv, fence); + dma_resv_add_fence(vma->obj->base.resv, fence, + DMA_RESV_USAGE_READ); obj->write_domain = 0; } } @@ -2044,7 +2059,7 @@ int i915_vma_unbind_async(struct i915_vma *vma, bool trylock_vm) if (!obj->mm.rsgt) return -EBUSY; - err = dma_resv_reserve_shared(obj->base.resv, 1); + err = dma_resv_reserve_fences(obj->base.resv, 1); if (err) return -EBUSY; @@ -2072,7 +2087,7 @@ int i915_vma_unbind_async(struct i915_vma *vma, bool trylock_vm) goto out_rpm; } - dma_resv_add_shared_fence(obj->base.resv, fence); + dma_resv_add_fence(obj->base.resv, fence, DMA_RESV_USAGE_READ); dma_fence_put(fence); out_rpm: diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c index ba32893e0873..73eb53edb8de 100644 --- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c +++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c @@ -1043,13 +1043,21 @@ static int igt_lmem_write_cpu(void *arg) } i915_gem_object_lock(obj, NULL); + + err = dma_resv_reserve_fences(obj->base.resv, 1); + if (err) { + i915_gem_object_unlock(obj); + goto out_put; + } + /* Put the pages into a known state -- from the gpu for added fun */ intel_engine_pm_get(engine); err = intel_context_migrate_clear(engine->gt->migrate.context, NULL, obj->mm.pages->sgl, I915_CACHE_NONE, true, 0xdeadbeaf, &rq); if (rq) { - dma_resv_add_excl_fence(obj->base.resv, &rq->fence); + dma_resv_add_fence(obj->base.resv, &rq->fence, + DMA_RESV_USAGE_WRITE); i915_request_put(rq); } diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c index 87428fb23d9f..a2277a0d6d06 100644 --- a/drivers/gpu/drm/imx/dw_hdmi-imx.c +++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c @@ -222,6 +222,7 @@ static int dw_hdmi_imx_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; const struct of_device_id *match = of_match_node(dw_hdmi_imx_dt_ids, np); struct imx_hdmi *hdmi; + int ret; hdmi = devm_kzalloc(&pdev->dev, sizeof(*hdmi), GFP_KERNEL); if (!hdmi) @@ -243,10 +244,15 @@ static int dw_hdmi_imx_probe(struct platform_device *pdev) hdmi->bridge = of_drm_find_bridge(np); if (!hdmi->bridge) { dev_err(hdmi->dev, "Unable to find bridge\n"); + dw_hdmi_remove(hdmi->hdmi); return -ENODEV; } - return component_add(&pdev->dev, &dw_hdmi_imx_ops); + ret = component_add(&pdev->dev, &dw_hdmi_imx_ops); + if (ret) + dw_hdmi_remove(hdmi->hdmi); + + return ret; } static int dw_hdmi_imx_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index e5078d03020d..14a058a42854 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -150,10 +150,9 @@ static int imx_ldb_connector_get_modes(struct drm_connector *connector) if (imx_ldb_ch->mode_valid) { struct drm_display_mode *mode; - mode = drm_mode_create(connector->dev); + mode = drm_mode_duplicate(connector->dev, &imx_ldb_ch->mode); if (!mode) return -EINVAL; - drm_mode_copy(mode, &imx_ldb_ch->mode); mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; drm_mode_probed_add(connector, mode); num_modes++; @@ -572,6 +571,8 @@ static int imx_ldb_panel_ddc(struct device *dev, edidp = of_get_property(child, "edid", &edid_len); if (edidp) { channel->edid = kmemdup(edidp, edid_len, GFP_KERNEL); + if (!channel->edid) + return -ENOMEM; } else if (!channel->panel) { /* fallback to display-timings node */ ret = of_get_drm_display_mode(child, diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 06cb1a59b9bc..63ba2ad84679 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -75,8 +75,10 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector) ret = of_get_drm_display_mode(np, &imxpd->mode, &imxpd->bus_flags, OF_USE_NATIVE_MODE); - if (ret) + if (ret) { + drm_mode_destroy(connector->dev, mode); return ret; + } drm_mode_copy(mode, &imxpd->mode); mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; diff --git a/drivers/gpu/drm/ingenic/Kconfig b/drivers/gpu/drm/ingenic/Kconfig index 001f59fb06d5..090830bcbde7 100644 --- a/drivers/gpu/drm/ingenic/Kconfig +++ b/drivers/gpu/drm/ingenic/Kconfig @@ -24,4 +24,13 @@ config DRM_INGENIC_IPU The Image Processing Unit (IPU) will appear as a second primary plane. +config DRM_INGENIC_DW_HDMI + tristate "Ingenic specific support for Synopsys DW HDMI" + depends on MACH_JZ4780 + select DRM_DW_HDMI + help + Choose this option to enable Synopsys DesignWare HDMI based driver. + If you want to enable HDMI on Ingenic JZ4780 based SoC, you should + select this option. + endif diff --git a/drivers/gpu/drm/ingenic/Makefile b/drivers/gpu/drm/ingenic/Makefile index d313326bdddb..f10cc1c5a5f2 100644 --- a/drivers/gpu/drm/ingenic/Makefile +++ b/drivers/gpu/drm/ingenic/Makefile @@ -1,3 +1,4 @@ obj-$(CONFIG_DRM_INGENIC) += ingenic-drm.o ingenic-drm-y = ingenic-drm-drv.o ingenic-drm-$(CONFIG_DRM_INGENIC_IPU) += ingenic-ipu.o +obj-$(CONFIG_DRM_INGENIC_DW_HDMI) += ingenic-dw-hdmi.o diff --git a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c index ac52b49bf901..8eb0ad501a7b 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c @@ -226,6 +226,18 @@ static int ingenic_drm_update_pixclk(struct notifier_block *nb, } } +static void ingenic_drm_bridge_atomic_enable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) +{ + struct ingenic_drm *priv = drm_device_get_priv(bridge->dev); + + regmap_write(priv->map, JZ_REG_LCD_STATE, 0); + + regmap_update_bits(priv->map, JZ_REG_LCD_CTRL, + JZ_LCD_CTRL_ENABLE | JZ_LCD_CTRL_DISABLE, + JZ_LCD_CTRL_ENABLE); +} + static void ingenic_drm_crtc_atomic_enable(struct drm_crtc *crtc, struct drm_atomic_state *state) { @@ -237,28 +249,20 @@ static void ingenic_drm_crtc_atomic_enable(struct drm_crtc *crtc, if (WARN_ON(IS_ERR(priv_state))) return; - regmap_write(priv->map, JZ_REG_LCD_STATE, 0); - /* Set addresses of our DMA descriptor chains */ next_id = priv_state->use_palette ? HWDESC_PALETTE : 0; regmap_write(priv->map, JZ_REG_LCD_DA0, dma_hwdesc_addr(priv, next_id)); regmap_write(priv->map, JZ_REG_LCD_DA1, dma_hwdesc_addr(priv, 1)); - regmap_update_bits(priv->map, JZ_REG_LCD_CTRL, - JZ_LCD_CTRL_ENABLE | JZ_LCD_CTRL_DISABLE, - JZ_LCD_CTRL_ENABLE); - drm_crtc_vblank_on(crtc); } -static void ingenic_drm_crtc_atomic_disable(struct drm_crtc *crtc, - struct drm_atomic_state *state) +static void ingenic_drm_bridge_atomic_disable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) { - struct ingenic_drm *priv = drm_crtc_get_priv(crtc); + struct ingenic_drm *priv = drm_device_get_priv(bridge->dev); unsigned int var; - drm_crtc_vblank_off(crtc); - regmap_update_bits(priv->map, JZ_REG_LCD_CTRL, JZ_LCD_CTRL_DISABLE, JZ_LCD_CTRL_DISABLE); @@ -267,6 +271,12 @@ static void ingenic_drm_crtc_atomic_disable(struct drm_crtc *crtc, 1000, 0); } +static void ingenic_drm_crtc_atomic_disable(struct drm_crtc *crtc, + struct drm_atomic_state *state) +{ + drm_crtc_vblank_off(crtc); +} + static void ingenic_drm_crtc_update_timings(struct ingenic_drm *priv, struct drm_display_mode *mode) { @@ -823,6 +833,32 @@ static int ingenic_drm_bridge_atomic_check(struct drm_bridge *bridge, } } +static u32 * +ingenic_drm_bridge_atomic_get_input_bus_fmts(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + u32 output_fmt, + unsigned int *num_input_fmts) +{ + switch (output_fmt) { + case MEDIA_BUS_FMT_RGB888_1X24: + case MEDIA_BUS_FMT_RGB666_1X18: + case MEDIA_BUS_FMT_RGB565_1X16: + case MEDIA_BUS_FMT_RGB888_3X8: + case MEDIA_BUS_FMT_RGB888_3X8_DELTA: + break; + default: + *num_input_fmts = 0; + return NULL; + } + + return drm_atomic_helper_bridge_propagate_bus_fmt(bridge, bridge_state, + crtc_state, conn_state, + output_fmt, + num_input_fmts); +} + static irqreturn_t ingenic_drm_irq_handler(int irq, void *arg) { struct ingenic_drm *priv = drm_device_get_priv(arg); @@ -968,11 +1004,13 @@ static const struct drm_encoder_helper_funcs ingenic_drm_encoder_helper_funcs = static const struct drm_bridge_funcs ingenic_drm_bridge_funcs = { .attach = ingenic_drm_bridge_attach, + .atomic_enable = ingenic_drm_bridge_atomic_enable, + .atomic_disable = ingenic_drm_bridge_atomic_disable, .atomic_check = ingenic_drm_bridge_atomic_check, .atomic_reset = drm_atomic_helper_bridge_reset, .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, - .atomic_get_input_bus_fmts = drm_atomic_helper_bridge_propagate_bus_fmt, + .atomic_get_input_bus_fmts = ingenic_drm_bridge_atomic_get_input_bus_fmts, }; static const struct drm_mode_config_funcs ingenic_drm_mode_config_funcs = { diff --git a/drivers/gpu/drm/ingenic/ingenic-dw-hdmi.c b/drivers/gpu/drm/ingenic/ingenic-dw-hdmi.c new file mode 100644 index 000000000000..72f8b44998a5 --- /dev/null +++ b/drivers/gpu/drm/ingenic/ingenic-dw-hdmi.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2011-2013 Freescale Semiconductor, Inc. + * Copyright (C) 2019, 2020 Paul Boddie <paul@boddie.org.uk> + * + * Derived from dw_hdmi-imx.c with i.MX portions removed. + */ + +#include <linux/module.h> +#include <linux/of_platform.h> +#include <linux/platform_device.h> + +#include <drm/bridge/dw_hdmi.h> +#include <drm/drm_of.h> +#include <drm/drm_print.h> + +static const struct dw_hdmi_mpll_config ingenic_mpll_cfg[] = { + { 45250000, { { 0x01e0, 0x0000 }, { 0x21e1, 0x0000 }, { 0x41e2, 0x0000 } } }, + { 92500000, { { 0x0140, 0x0005 }, { 0x2141, 0x0005 }, { 0x4142, 0x0005 } } }, + { 148500000, { { 0x00a0, 0x000a }, { 0x20a1, 0x000a }, { 0x40a2, 0x000a } } }, + { 216000000, { { 0x00a0, 0x000a }, { 0x2001, 0x000f }, { 0x4002, 0x000f } } }, + { ~0UL, { { 0x0000, 0x0000 }, { 0x0000, 0x0000 }, { 0x0000, 0x0000 } } } +}; + +static const struct dw_hdmi_curr_ctrl ingenic_cur_ctr[] = { + /*pixelclk bpp8 bpp10 bpp12 */ + { 54000000, { 0x091c, 0x091c, 0x06dc } }, + { 58400000, { 0x091c, 0x06dc, 0x06dc } }, + { 72000000, { 0x06dc, 0x06dc, 0x091c } }, + { 74250000, { 0x06dc, 0x0b5c, 0x091c } }, + { 118800000, { 0x091c, 0x091c, 0x06dc } }, + { 216000000, { 0x06dc, 0x0b5c, 0x091c } }, + { ~0UL, { 0x0000, 0x0000, 0x0000 } }, +}; + +/* + * Resistance term 133Ohm Cfg + * PREEMP config 0.00 + * TX/CK level 10 + */ +static const struct dw_hdmi_phy_config ingenic_phy_config[] = { + /*pixelclk symbol term vlev */ + { 216000000, 0x800d, 0x0005, 0x01ad}, + { ~0UL, 0x0000, 0x0000, 0x0000} +}; + +static enum drm_mode_status +ingenic_dw_hdmi_mode_valid(struct dw_hdmi *hdmi, void *data, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + if (mode->clock < 13500) + return MODE_CLOCK_LOW; + /* FIXME: Hardware is capable of 270MHz, but setup data is missing. */ + if (mode->clock > 216000) + return MODE_CLOCK_HIGH; + + return MODE_OK; +} + +static struct dw_hdmi_plat_data ingenic_dw_hdmi_plat_data = { + .mpll_cfg = ingenic_mpll_cfg, + .cur_ctr = ingenic_cur_ctr, + .phy_config = ingenic_phy_config, + .mode_valid = ingenic_dw_hdmi_mode_valid, + .output_port = 1, +}; + +static const struct of_device_id ingenic_dw_hdmi_dt_ids[] = { + { .compatible = "ingenic,jz4780-dw-hdmi" }, + { /* Sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, ingenic_dw_hdmi_dt_ids); + +static void ingenic_dw_hdmi_cleanup(void *data) +{ + struct dw_hdmi *hdmi = (struct dw_hdmi *)data; + + dw_hdmi_remove(hdmi); +} + +static int ingenic_dw_hdmi_probe(struct platform_device *pdev) +{ + struct dw_hdmi *hdmi; + + hdmi = dw_hdmi_probe(pdev, &ingenic_dw_hdmi_plat_data); + if (IS_ERR(hdmi)) + return PTR_ERR(hdmi); + + return devm_add_action_or_reset(&pdev->dev, ingenic_dw_hdmi_cleanup, hdmi); +} + +static struct platform_driver ingenic_dw_hdmi_driver = { + .probe = ingenic_dw_hdmi_probe, + .driver = { + .name = "dw-hdmi-ingenic", + .of_match_table = ingenic_dw_hdmi_dt_ids, + }, +}; +module_platform_driver(ingenic_dw_hdmi_driver); + +MODULE_DESCRIPTION("JZ4780 Specific DW-HDMI Driver Extension"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:dw-hdmi-ingenic"); diff --git a/drivers/gpu/drm/lima/lima_gem.c b/drivers/gpu/drm/lima/lima_gem.c index 55bb1ec3c4f7..0f1ca0b0db49 100644 --- a/drivers/gpu/drm/lima/lima_gem.c +++ b/drivers/gpu/drm/lima/lima_gem.c @@ -257,13 +257,11 @@ int lima_gem_get_info(struct drm_file *file, u32 handle, u32 *va, u64 *offset) static int lima_gem_sync_bo(struct lima_sched_task *task, struct lima_bo *bo, bool write, bool explicit) { - int err = 0; + int err; - if (!write) { - err = dma_resv_reserve_shared(lima_bo_resv(bo), 1); - if (err) - return err; - } + err = dma_resv_reserve_fences(lima_bo_resv(bo), 1); + if (err) + return err; /* explicit sync use user passed dep fence */ if (explicit) @@ -366,10 +364,9 @@ int lima_gem_submit(struct drm_file *file, struct lima_submit *submit) fence = lima_sched_context_queue_task(submit->task); for (i = 0; i < submit->nr_bos; i++) { - if (submit->bos[i].flags & LIMA_SUBMIT_BO_WRITE) - dma_resv_add_excl_fence(lima_bo_resv(bos[i]), fence); - else - dma_resv_add_shared_fence(lima_bo_resv(bos[i]), fence); + dma_resv_add_fence(lima_bo_resv(bos[i]), fence, + submit->bos[i].flags & LIMA_SUBMIT_BO_WRITE ? + DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ); } drm_gem_unlock_reservations((struct drm_gem_object **)bos, diff --git a/drivers/gpu/drm/mcde/mcde_dsi.c b/drivers/gpu/drm/mcde/mcde_dsi.c index 5651734ce977..960b49ea2ee5 100644 --- a/drivers/gpu/drm/mcde/mcde_dsi.c +++ b/drivers/gpu/drm/mcde/mcde_dsi.c @@ -19,7 +19,6 @@ #include <drm/drm_mipi_dsi.h> #include <drm/drm_modeset_helper_vtables.h> #include <drm/drm_of.h> -#include <drm/drm_panel.h> #include <drm/drm_print.h> #include <drm/drm_probe_helper.h> @@ -39,7 +38,6 @@ struct mcde_dsi { struct device *dev; struct mcde *mcde; struct drm_bridge bridge; - struct drm_panel *panel; struct drm_bridge *bridge_out; struct mipi_dsi_host dsi_host; struct mipi_dsi_device *mdsi; @@ -1073,9 +1071,7 @@ static int mcde_dsi_bind(struct device *dev, struct device *master, struct drm_device *drm = data; struct mcde *mcde = to_mcde(drm); struct mcde_dsi *d = dev_get_drvdata(dev); - struct device_node *child; - struct drm_panel *panel = NULL; - struct drm_bridge *bridge = NULL; + struct drm_bridge *bridge; if (!of_get_available_child_count(dev->of_node)) { dev_info(dev, "unused DSI interface\n"); @@ -1100,37 +1096,10 @@ static int mcde_dsi_bind(struct device *dev, struct device *master, return PTR_ERR(d->lp_clk); } - /* Look for a panel as a child to this node */ - for_each_available_child_of_node(dev->of_node, child) { - panel = of_drm_find_panel(child); - if (IS_ERR(panel)) { - dev_err(dev, "failed to find panel try bridge (%ld)\n", - PTR_ERR(panel)); - panel = NULL; - - bridge = of_drm_find_bridge(child); - if (!bridge) { - dev_err(dev, "failed to find bridge\n"); - return -EINVAL; - } - } - } - if (panel) { - bridge = drm_panel_bridge_add_typed(panel, - DRM_MODE_CONNECTOR_DSI); - if (IS_ERR(bridge)) { - dev_err(dev, "error adding panel bridge\n"); - return PTR_ERR(bridge); - } - dev_info(dev, "connected to panel\n"); - d->panel = panel; - } else if (bridge) { - /* TODO: AV8100 HDMI encoder goes here for example */ - dev_info(dev, "connected to non-panel bridge (unsupported)\n"); - return -ENODEV; - } else { - dev_err(dev, "no panel or bridge\n"); - return -ENODEV; + bridge = devm_drm_of_get_bridge(dev, dev->of_node, 0, 0); + if (IS_ERR(bridge)) { + dev_err(dev, "error to get bridge\n"); + return PTR_ERR(bridge); } d->bridge_out = bridge; @@ -1153,8 +1122,6 @@ static void mcde_dsi_unbind(struct device *dev, struct device *master, { struct mcde_dsi *d = dev_get_drvdata(dev); - if (d->panel) - drm_panel_bridge_remove(d->bridge_out); regmap_update_bits(d->prcmu, PRCM_DSI_SW_RESET, PRCM_DSI_SW_RESET_DSI0_SW_RESETN, 0); } diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index ccb0511b9cd5..bd3f5b485085 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -500,6 +500,18 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi) DRM_WARN("HFP + HBP less than d-phy, FPS will under 60Hz\n"); } + if ((dsi->mode_flags & MIPI_DSI_HS_PKT_END_ALIGNED) && + (dsi->lanes == 4)) { + horizontal_sync_active_byte = + roundup(horizontal_sync_active_byte, dsi->lanes) - 2; + horizontal_frontporch_byte = + roundup(horizontal_frontporch_byte, dsi->lanes) - 2; + horizontal_backporch_byte = + roundup(horizontal_backporch_byte, dsi->lanes) - 2; + horizontal_backporch_byte -= + (vm->hactive * dsi_tmp_buf_bpp + 2) % dsi->lanes; + } + writel(horizontal_sync_active_byte, dsi->regs + DSI_HSA_WC); writel(horizontal_backporch_byte, dsi->regs + DSI_HBP_WC); writel(horizontal_frontporch_byte, dsi->regs + DSI_HFP_WC); diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index edae79f41153..1b70938cfd2c 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -168,7 +168,7 @@ static const struct meson_drm_soc_attr meson_drm_soc_attrs[] = { }, .attrs = (const struct soc_device_attribute []) { { .soc_id = "GXL (S805*)", }, - { /* sentinel */ }, + { /* sentinel */ } } }, }; diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 02b9ae65a96a..01bbb5f2d462 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -848,7 +848,8 @@ int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout) op & MSM_PREP_NOSYNC ? 0 : timeout_to_jiffies(timeout); long ret; - ret = dma_resv_wait_timeout(obj->resv, write, true, remain); + ret = dma_resv_wait_timeout(obj->resv, dma_resv_usage_rw(write), + true, remain); if (ret == 0) return remain == 0 ? -EBUSY : -ETIMEDOUT; else if (ret < 0) diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index c6d60c8d286d..8d1eef914ba8 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -320,16 +320,14 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit) struct drm_gem_object *obj = &submit->bos[i].obj->base; bool write = submit->bos[i].flags & MSM_SUBMIT_BO_WRITE; - if (!write) { - /* NOTE: _reserve_shared() must happen before - * _add_shared_fence(), which makes this a slightly - * strange place to call it. OTOH this is a - * convenient can-fail point to hook it in. - */ - ret = dma_resv_reserve_shared(obj->resv, 1); - if (ret) - return ret; - } + /* NOTE: _reserve_shared() must happen before + * _add_shared_fence(), which makes this a slightly + * strange place to call it. OTOH this is a + * convenient can-fail point to hook it in. + */ + ret = dma_resv_reserve_fences(obj->resv, 1); + if (ret) + return ret; /* exclusive fences must be ordered */ if (no_implicit && !write) @@ -397,9 +395,11 @@ static void submit_attach_object_fences(struct msm_gem_submit *submit) struct drm_gem_object *obj = &submit->bos[i].obj->base; if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE) - dma_resv_add_excl_fence(obj->resv, submit->user_fence); + dma_resv_add_fence(obj->resv, submit->user_fence, + DMA_RESV_USAGE_WRITE); else if (submit->bos[i].flags & MSM_SUBMIT_BO_READ) - dma_resv_add_shared_fence(obj->resv, submit->user_fence); + dma_resv_add_fence(obj->resv, submit->user_fence, + DMA_RESV_USAGE_READ); } } diff --git a/drivers/gpu/drm/nouveau/dispnv50/atom.h b/drivers/gpu/drm/nouveau/dispnv50/atom.h index 3d82b3c67dec..93f8f4f64578 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/atom.h +++ b/drivers/gpu/drm/nouveau/dispnv50/atom.h @@ -160,14 +160,14 @@ nv50_head_atom_get(struct drm_atomic_state *state, struct drm_crtc *crtc) static inline struct drm_encoder * nv50_head_atom_get_encoder(struct nv50_head_atom *atom) { - struct drm_encoder *encoder = NULL; + struct drm_encoder *encoder; /* We only ever have a single encoder */ drm_for_each_encoder_mask(encoder, atom->state.crtc->dev, atom->state.encoder_mask) - break; + return encoder; - return encoder; + return NULL; } #define nv50_wndw_atom(p) container_of((p), struct nv50_wndw_atom, state) diff --git a/drivers/gpu/drm/nouveau/dispnv50/base917c.c b/drivers/gpu/drm/nouveau/dispnv50/base917c.c index a1baed4fe0e9..ca260509a4f1 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/base917c.c +++ b/drivers/gpu/drm/nouveau/dispnv50/base917c.c @@ -22,7 +22,7 @@ #include "base.h" #include "atom.h" -const u32 +static const u32 base917c_format[] = { DRM_FORMAT_C8, DRM_FORMAT_XRGB8888, diff --git a/drivers/gpu/drm/nouveau/dispnv50/crc.c b/drivers/gpu/drm/nouveau/dispnv50/crc.c index 29428e770f14..b834e8a9ae77 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/crc.c +++ b/drivers/gpu/drm/nouveau/dispnv50/crc.c @@ -390,9 +390,18 @@ void nv50_crc_atomic_check_outp(struct nv50_atom *atom) struct nv50_head_atom *armh = nv50_head_atom(old_crtc_state); struct nv50_head_atom *asyh = nv50_head_atom(new_crtc_state); struct nv50_outp_atom *outp_atom; - struct nouveau_encoder *outp = - nv50_real_outp(nv50_head_atom_get_encoder(armh)); - struct drm_encoder *encoder = &outp->base.base; + struct nouveau_encoder *outp; + struct drm_encoder *encoder, *enc; + + enc = nv50_head_atom_get_encoder(armh); + if (!enc) + continue; + + outp = nv50_real_outp(enc); + if (!outp) + continue; + + encoder = &outp->base.base; if (!asyh->clr.crc) continue; @@ -443,8 +452,16 @@ void nv50_crc_atomic_set(struct nv50_head *head, struct drm_device *dev = crtc->dev; struct nv50_crc *crc = &head->crc; const struct nv50_crc_func *func = nv50_disp(dev)->core->func->crc; - struct nouveau_encoder *outp = - nv50_real_outp(nv50_head_atom_get_encoder(asyh)); + struct nouveau_encoder *outp; + struct drm_encoder *encoder; + + encoder = nv50_head_atom_get_encoder(asyh); + if (!encoder) + return; + + outp = nv50_real_outp(encoder); + if (!outp) + return; func->set_src(head, outp->or, nv50_crc_source_type(outp, asyh->crc.src), &crc->ctx[crc->ctx_idx]); diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c index 0c1a2ea0ed04..8642b84ea20c 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c +++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c @@ -536,8 +536,6 @@ nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) struct nouveau_bo *nvbo; struct nv50_head_atom *asyh; struct nv50_wndw_ctxdma *ctxdma; - struct dma_resv_iter cursor; - struct dma_fence *fence; int ret; NV_ATOMIC(drm, "%s prepare: %p\n", plane->name, fb); @@ -560,13 +558,12 @@ nv50_wndw_prepare_fb(struct drm_plane *plane, struct drm_plane_state *state) asyw->image.handle[0] = ctxdma->object.handle; } - dma_resv_iter_begin(&cursor, nvbo->bo.base.resv, false); - dma_resv_for_each_fence_unlocked(&cursor, fence) { - /* TODO: We only use the first writer here */ - asyw->state.fence = dma_fence_get(fence); - break; - } - dma_resv_iter_end(&cursor); + ret = dma_resv_get_singleton(nvbo->bo.base.resv, + DMA_RESV_USAGE_WRITE, + &asyw->state.fence); + if (ret) + return ret; + asyw->image.offset[0] = nvbo->offset; if (wndw->func->prepare) { diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index fa73fe57f97b..05076e530e7d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -959,7 +959,14 @@ nouveau_bo_vm_cleanup(struct ttm_buffer_object *bo, { struct nouveau_drm *drm = nouveau_bdev(bo->bdev); struct drm_device *dev = drm->dev; - struct dma_fence *fence = dma_resv_excl_fence(bo->base.resv); + struct dma_fence *fence; + int ret; + + ret = dma_resv_get_singleton(bo->base.resv, DMA_RESV_USAGE_WRITE, + &fence); + if (ret) + dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_WRITE, + false, MAX_SCHEDULE_TIMEOUT); nv10_bo_put_tile_region(dev, *old_tile, fence); *old_tile = new_tile; @@ -1301,10 +1308,11 @@ nouveau_bo_fence(struct nouveau_bo *nvbo, struct nouveau_fence *fence, bool excl { struct dma_resv *resv = nvbo->bo.base.resv; - if (exclusive) - dma_resv_add_excl_fence(resv, &fence->base); - else if (fence) - dma_resv_add_shared_fence(resv, &fence->base); + if (!fence) + return; + + dma_resv_add_fence(resv, &fence->base, exclusive ? + DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ); } static void diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index a3a04e0d76ec..7f01dcf81fab 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -346,23 +346,25 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, struct dma_resv *resv = nvbo->bo.base.resv; int i, ret; - if (!exclusive) { - ret = dma_resv_reserve_shared(resv, 1); - if (ret) - return ret; - } + ret = dma_resv_reserve_fences(resv, 1); + if (ret) + return ret; - /* Waiting for the exclusive fence first causes performance regressions - * under some circumstances. So manually wait for the shared ones first. + /* Waiting for the writes first causes performance regressions + * under some circumstances. So manually wait for the reads first. */ for (i = 0; i < 2; ++i) { struct dma_resv_iter cursor; struct dma_fence *fence; - dma_resv_for_each_fence(&cursor, resv, exclusive, fence) { + dma_resv_for_each_fence(&cursor, resv, + dma_resv_usage_rw(exclusive), + fence) { + enum dma_resv_usage usage; struct nouveau_fence *f; - if (i == 0 && dma_resv_iter_is_exclusive(&cursor)) + usage = dma_resv_iter_usage(&cursor); + if (i == 0 && usage == DMA_RESV_USAGE_WRITE) continue; f = nouveau_local_fence(fence, chan->drm); diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 9416bee92141..fab542a758ff 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -962,7 +962,8 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data, return -ENOENT; nvbo = nouveau_gem_object(gem); - lret = dma_resv_wait_timeout(nvbo->bo.base.resv, write, true, + lret = dma_resv_wait_timeout(nvbo->bo.base.resv, + dma_resv_usage_rw(write), true, no_wait ? 0 : 30 * HZ); if (!lret) ret = -EBUSY; diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c index 60019d0532fc..347488685f74 100644 --- a/drivers/gpu/drm/nouveau/nouveau_prime.c +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -93,22 +93,7 @@ int nouveau_gem_prime_pin(struct drm_gem_object *obj) if (ret) return -EINVAL; - ret = ttm_bo_reserve(&nvbo->bo, false, false, NULL); - if (ret) - goto error; - - if (nvbo->bo.moving) - ret = dma_fence_wait(nvbo->bo.moving, true); - - ttm_bo_unreserve(&nvbo->bo); - if (ret) - goto error; - - return ret; - -error: - nouveau_bo_unpin(nvbo); - return ret; + return 0; } void nouveau_gem_prime_unpin(struct drm_gem_object *obj) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 88d262ba648c..62efbd0f3846 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2935,7 +2935,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func, /* switch mmio to cpu's native endianness */ if (!nvkm_device_endianness(device)) { nvdev_error(device, - "Couldn't switch GPU to CPUs endianess\n"); + "Couldn't switch GPU to CPUs endianness\n"); ret = -ENOSYS; goto done; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf108.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf108.c index 030640bb3dca..ab3760e804b8 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf108.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf108.c @@ -143,7 +143,7 @@ gf108_gr = { } }; -const struct gf100_gr_fwif +static const struct gf100_gr_fwif gf108_gr_fwif[] = { { -1, gf100_gr_load, &gf108_gr }, { -1, gf100_gr_nofw, &gf108_gr }, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c index 57199be082fd..c2b5cc5f97ed 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c @@ -135,10 +135,10 @@ nvkm_cstate_find_best(struct nvkm_clk *clk, struct nvkm_pstate *pstate, list_for_each_entry_from_reverse(cstate, &pstate->list, head) { if (nvkm_cstate_valid(clk, cstate, max_volt, clk->temp)) - break; + return cstate; } - return cstate; + return NULL; } static struct nvkm_cstate * @@ -169,6 +169,8 @@ nvkm_cstate_prog(struct nvkm_clk *clk, struct nvkm_pstate *pstate, int cstatei) if (!list_empty(&pstate->list)) { cstate = nvkm_cstate_get(clk, pstate, cstatei); cstate = nvkm_cstate_find_best(clk, pstate, cstate); + if (!cstate) + return -EINVAL; } else { cstate = &pstate->base; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c index 96aca0edfa3c..c51bac76174c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c @@ -313,7 +313,7 @@ nv50_instobj_dtor(struct nvkm_memory *memory) struct nv50_instobj *iobj = nv50_instobj(memory); struct nvkm_instmem *imem = &iobj->imem->base; struct nvkm_vma *bar; - void *map = map; + void *map; mutex_lock(&imem->mutex); if (likely(iobj->lru.next)) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c index e1772211b0a4..612310d5d481 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c @@ -216,6 +216,7 @@ gm20b_pmu = { .intr = gt215_pmu_intr, .recv = gm20b_pmu_recv, .initmsg = gm20b_pmu_initmsg, + .reset = gf100_pmu_reset, }; #if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c index 6bf7fc1bd1e3..1a6f9c3af5ec 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp102.c @@ -23,7 +23,7 @@ */ #include "priv.h" -static void +void gp102_pmu_reset(struct nvkm_pmu *pmu) { struct nvkm_device *device = pmu->subdev.device; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c index ba1583bb618b..94cfb1791af6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c @@ -83,6 +83,7 @@ gp10b_pmu = { .intr = gt215_pmu_intr, .recv = gm20b_pmu_recv, .initmsg = gm20b_pmu_initmsg, + .reset = gp102_pmu_reset, }; #if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC) diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h index bcaade758ff7..21abf31f4442 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/priv.h @@ -41,6 +41,7 @@ int gt215_pmu_send(struct nvkm_pmu *, u32[2], u32, u32, u32, u32); bool gf100_pmu_enabled(struct nvkm_pmu *); void gf100_pmu_reset(struct nvkm_pmu *); +void gp102_pmu_reset(struct nvkm_pmu *pmu); void gk110_pmu_pgob(struct nvkm_pmu *, bool); diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c index b0fa17409b66..cf571796fd26 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem.c +++ b/drivers/gpu/drm/omapdrm/omap_gem.c @@ -38,7 +38,7 @@ struct omap_gem_object { /** roll applied when mapping to DMM */ u32 roll; - /** protects dma_addr_cnt, block, pages, dma_addrs and vaddr */ + /** protects pin_cnt, block, pages, dma_addrs and vaddr */ struct mutex lock; /** @@ -50,24 +50,24 @@ struct omap_gem_object { * - buffers imported from dmabuf (with the OMAP_BO_MEM_DMABUF flag set) * if they are physically contiguous (when sgt->orig_nents == 1) * - * - buffers mapped through the TILER when dma_addr_cnt is not zero, in - * which case the DMA address points to the TILER aperture + * - buffers mapped through the TILER when pin_cnt is not zero, in which + * case the DMA address points to the TILER aperture * * Physically contiguous buffers have their DMA address equal to the * physical address as we don't remap those buffers through the TILER. * * Buffers mapped to the TILER have their DMA address pointing to the - * TILER aperture. As TILER mappings are refcounted (through - * dma_addr_cnt) the DMA address must be accessed through omap_gem_pin() - * to ensure that the mapping won't disappear unexpectedly. References - * must be released with omap_gem_unpin(). + * TILER aperture. As TILER mappings are refcounted (through pin_cnt) + * the DMA address must be accessed through omap_gem_pin() to ensure + * that the mapping won't disappear unexpectedly. References must be + * released with omap_gem_unpin(). */ dma_addr_t dma_addr; /** - * # of users of dma_addr + * # of users */ - refcount_t dma_addr_cnt; + refcount_t pin_cnt; /** * If the buffer has been imported from a dmabuf the OMAP_DB_DMABUF flag @@ -750,6 +750,46 @@ void omap_gem_dma_sync_buffer(struct drm_gem_object *obj, } } +static int omap_gem_pin_tiler(struct drm_gem_object *obj) +{ + struct omap_gem_object *omap_obj = to_omap_bo(obj); + u32 npages = obj->size >> PAGE_SHIFT; + enum tiler_fmt fmt = gem2fmt(omap_obj->flags); + struct tiler_block *block; + int ret; + + BUG_ON(omap_obj->block); + + if (omap_obj->flags & OMAP_BO_TILED_MASK) { + block = tiler_reserve_2d(fmt, omap_obj->width, omap_obj->height, + PAGE_SIZE); + } else { + block = tiler_reserve_1d(obj->size); + } + + if (IS_ERR(block)) { + ret = PTR_ERR(block); + dev_err(obj->dev->dev, "could not remap: %d (%d)\n", ret, fmt); + goto fail; + } + + /* TODO: enable async refill.. */ + ret = tiler_pin(block, omap_obj->pages, npages, omap_obj->roll, true); + if (ret) { + tiler_release(block); + dev_err(obj->dev->dev, "could not pin: %d\n", ret); + goto fail; + } + + omap_obj->dma_addr = tiler_ssptr(block); + omap_obj->block = block; + + DBG("got dma address: %pad", &omap_obj->dma_addr); + +fail: + return ret; +} + /** * omap_gem_pin() - Pin a GEM object in memory * @obj: the GEM object @@ -772,63 +812,30 @@ int omap_gem_pin(struct drm_gem_object *obj, dma_addr_t *dma_addr) mutex_lock(&omap_obj->lock); - if (!omap_gem_is_contiguous(omap_obj) && priv->has_dmm) { - if (refcount_read(&omap_obj->dma_addr_cnt) == 0) { - u32 npages = obj->size >> PAGE_SHIFT; - enum tiler_fmt fmt = gem2fmt(omap_obj->flags); - struct tiler_block *block; - - BUG_ON(omap_obj->block); + if (!omap_gem_is_contiguous(omap_obj)) { + if (refcount_read(&omap_obj->pin_cnt) == 0) { - refcount_set(&omap_obj->dma_addr_cnt, 1); + refcount_set(&omap_obj->pin_cnt, 1); ret = omap_gem_attach_pages(obj); if (ret) goto fail; - if (omap_obj->flags & OMAP_BO_TILED_MASK) { - block = tiler_reserve_2d(fmt, - omap_obj->width, - omap_obj->height, PAGE_SIZE); - } else { - block = tiler_reserve_1d(obj->size); - } - - if (IS_ERR(block)) { - ret = PTR_ERR(block); - dev_err(obj->dev->dev, - "could not remap: %d (%d)\n", ret, fmt); - goto fail; - } - - /* TODO: enable async refill.. */ - ret = tiler_pin(block, omap_obj->pages, npages, - omap_obj->roll, true); - if (ret) { - tiler_release(block); - dev_err(obj->dev->dev, - "could not pin: %d\n", ret); - goto fail; + if (omap_obj->flags & OMAP_BO_SCANOUT) { + if (priv->has_dmm) { + ret = omap_gem_pin_tiler(obj); + if (ret) + goto fail; + } } - - omap_obj->dma_addr = tiler_ssptr(block); - omap_obj->block = block; - - DBG("got dma address: %pad", &omap_obj->dma_addr); } else { - refcount_inc(&omap_obj->dma_addr_cnt); + refcount_inc(&omap_obj->pin_cnt); } - - if (dma_addr) - *dma_addr = omap_obj->dma_addr; - } else if (omap_gem_is_contiguous(omap_obj)) { - if (dma_addr) - *dma_addr = omap_obj->dma_addr; - } else { - ret = -EINVAL; - goto fail; } + if (dma_addr) + *dma_addr = omap_obj->dma_addr; + fail: mutex_unlock(&omap_obj->lock); @@ -847,27 +854,31 @@ static void omap_gem_unpin_locked(struct drm_gem_object *obj) struct omap_gem_object *omap_obj = to_omap_bo(obj); int ret; - if (omap_gem_is_contiguous(omap_obj) || !priv->has_dmm) + if (omap_gem_is_contiguous(omap_obj)) return; - if (refcount_dec_and_test(&omap_obj->dma_addr_cnt)) { + if (refcount_dec_and_test(&omap_obj->pin_cnt)) { if (omap_obj->sgt) { sg_free_table(omap_obj->sgt); kfree(omap_obj->sgt); omap_obj->sgt = NULL; } - ret = tiler_unpin(omap_obj->block); - if (ret) { - dev_err(obj->dev->dev, - "could not unpin pages: %d\n", ret); - } - ret = tiler_release(omap_obj->block); - if (ret) { - dev_err(obj->dev->dev, - "could not release unmap: %d\n", ret); + if (!(omap_obj->flags & OMAP_BO_SCANOUT)) + return; + if (priv->has_dmm) { + ret = tiler_unpin(omap_obj->block); + if (ret) { + dev_err(obj->dev->dev, + "could not unpin pages: %d\n", ret); + } + ret = tiler_release(omap_obj->block); + if (ret) { + dev_err(obj->dev->dev, + "could not release unmap: %d\n", ret); + } + omap_obj->dma_addr = 0; + omap_obj->block = NULL; } - omap_obj->dma_addr = 0; - omap_obj->block = NULL; } } @@ -900,7 +911,7 @@ int omap_gem_rotated_dma_addr(struct drm_gem_object *obj, u32 orient, mutex_lock(&omap_obj->lock); - if ((refcount_read(&omap_obj->dma_addr_cnt) > 0) && omap_obj->block && + if ((refcount_read(&omap_obj->pin_cnt) > 0) && omap_obj->block && (omap_obj->flags & OMAP_BO_TILED_MASK)) { *dma_addr = tiler_tsptr(omap_obj->block, orient, x, y); ret = 0; @@ -968,7 +979,8 @@ int omap_gem_put_pages(struct drm_gem_object *obj) return 0; } -struct sg_table *omap_gem_get_sg(struct drm_gem_object *obj) +struct sg_table *omap_gem_get_sg(struct drm_gem_object *obj, + enum dma_data_direction dir) { struct omap_gem_object *omap_obj = to_omap_bo(obj); dma_addr_t addr; @@ -993,28 +1005,44 @@ struct sg_table *omap_gem_get_sg(struct drm_gem_object *obj) goto err_unpin; } - if (omap_obj->flags & OMAP_BO_TILED_MASK) { - enum tiler_fmt fmt = gem2fmt(omap_obj->flags); + if (addr) { + if (omap_obj->flags & OMAP_BO_TILED_MASK) { + enum tiler_fmt fmt = gem2fmt(omap_obj->flags); - len = omap_obj->width << (int)fmt; - count = omap_obj->height; - stride = tiler_stride(fmt, 0); + len = omap_obj->width << (int)fmt; + count = omap_obj->height; + stride = tiler_stride(fmt, 0); + } else { + len = obj->size; + count = 1; + stride = 0; + } } else { - len = obj->size; - count = 1; - stride = 0; + count = obj->size >> PAGE_SHIFT; } ret = sg_alloc_table(sgt, count, GFP_KERNEL); if (ret) goto err_free; - for_each_sg(sgt->sgl, sg, count, i) { - sg_set_page(sg, phys_to_page(addr), len, offset_in_page(addr)); - sg_dma_address(sg) = addr; - sg_dma_len(sg) = len; + /* this must be after omap_gem_pin() to ensure we have pages attached */ + omap_gem_dma_sync_buffer(obj, dir); - addr += stride; + if (addr) { + for_each_sg(sgt->sgl, sg, count, i) { + sg_set_page(sg, phys_to_page(addr), len, + offset_in_page(addr)); + sg_dma_address(sg) = addr; + sg_dma_len(sg) = len; + + addr += stride; + } + } else { + for_each_sg(sgt->sgl, sg, count, i) { + sg_set_page(sg, omap_obj->pages[i], PAGE_SIZE, 0); + sg_dma_address(sg) = omap_obj->dma_addrs[i]; + sg_dma_len(sg) = PAGE_SIZE; + } } omap_obj->sgt = sgt; @@ -1124,7 +1152,7 @@ void omap_gem_describe(struct drm_gem_object *obj, struct seq_file *m) seq_printf(m, "%08x: %2d (%2d) %08llx %pad (%2d) %p %4d", omap_obj->flags, obj->name, kref_read(&obj->refcount), off, &omap_obj->dma_addr, - refcount_read(&omap_obj->dma_addr_cnt), + refcount_read(&omap_obj->pin_cnt), omap_obj->vaddr, omap_obj->roll); if (omap_obj->flags & OMAP_BO_TILED_MASK) { @@ -1187,7 +1215,7 @@ static void omap_gem_free_object(struct drm_gem_object *obj) mutex_lock(&omap_obj->lock); /* The object should not be pinned. */ - WARN_ON(refcount_read(&omap_obj->dma_addr_cnt) > 0); + WARN_ON(refcount_read(&omap_obj->pin_cnt) > 0); if (omap_obj->pages) { if (omap_obj->flags & OMAP_BO_MEM_DMABUF) diff --git a/drivers/gpu/drm/omapdrm/omap_gem.h b/drivers/gpu/drm/omapdrm/omap_gem.h index 19209e319663..4d4488939f6b 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem.h +++ b/drivers/gpu/drm/omapdrm/omap_gem.h @@ -82,7 +82,8 @@ u32 omap_gem_flags(struct drm_gem_object *obj); int omap_gem_rotated_dma_addr(struct drm_gem_object *obj, u32 orient, int x, int y, dma_addr_t *dma_addr); int omap_gem_tiled_stride(struct drm_gem_object *obj, u32 orient); -struct sg_table *omap_gem_get_sg(struct drm_gem_object *obj); +struct sg_table *omap_gem_get_sg(struct drm_gem_object *obj, + enum dma_data_direction dir); void omap_gem_put_sg(struct drm_gem_object *obj, struct sg_table *sgt); #endif /* __OMAPDRM_GEM_H__ */ diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c index ab3fc86e7256..393f82e26927 100644 --- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c +++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c @@ -23,13 +23,10 @@ static struct sg_table *omap_gem_map_dma_buf( { struct drm_gem_object *obj = attachment->dmabuf->priv; struct sg_table *sg; - sg = omap_gem_get_sg(obj); + sg = omap_gem_get_sg(obj, dir); if (IS_ERR(sg)) return sg; - /* this must be after omap_gem_pin() to ensure we have pages attached */ - omap_gem_dma_sync_buffer(obj, dir); - return sg; } diff --git a/drivers/gpu/drm/omapdrm/omap_overlay.c b/drivers/gpu/drm/omapdrm/omap_overlay.c index 10730c9b2752..b0bc9ad2ef73 100644 --- a/drivers/gpu/drm/omapdrm/omap_overlay.c +++ b/drivers/gpu/drm/omapdrm/omap_overlay.c @@ -86,7 +86,7 @@ int omap_overlay_assign(struct drm_atomic_state *s, struct drm_plane *plane, r_ovl = omap_plane_find_free_overlay(s->dev, overlay_map, caps, fourcc); if (!r_ovl) { - overlay_map[r_ovl->idx] = NULL; + overlay_map[ovl->idx] = NULL; *overlay = NULL; return -ENOMEM; } diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index ddf5f38e8731..cc51ddeb54fd 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -284,6 +284,15 @@ config DRM_PANEL_NEC_NL8048HL11 panel (found on the Zoom2/3/3630 SDP boards). To compile this driver as a module, choose M here. +config DRM_PANEL_NEWVISION_NV3052C + tristate "NewVision NV3052C RGB/SPI panel" + depends on OF && SPI + depends on BACKLIGHT_CLASS_DEVICE + select DRM_MIPI_DBI + help + Say Y here if you want to enable support for the panels built + around the NewVision NV3052C display controller. + config DRM_PANEL_NOVATEK_NT35510 tristate "Novatek NT35510 RGB panel driver" depends on OF diff --git a/drivers/gpu/drm/panel/Makefile b/drivers/gpu/drm/panel/Makefile index 5740911f637c..42a7ab54234b 100644 --- a/drivers/gpu/drm/panel/Makefile +++ b/drivers/gpu/drm/panel/Makefile @@ -26,6 +26,7 @@ obj-$(CONFIG_DRM_PANEL_LEADTEK_LTK500HD1829) += panel-leadtek-ltk500hd1829.o obj-$(CONFIG_DRM_PANEL_LG_LB035Q02) += panel-lg-lb035q02.o obj-$(CONFIG_DRM_PANEL_LG_LG4573) += panel-lg-lg4573.o obj-$(CONFIG_DRM_PANEL_NEC_NL8048HL11) += panel-nec-nl8048hl11.o +obj-$(CONFIG_DRM_PANEL_NEWVISION_NV3052C) += panel-newvision-nv3052c.o obj-$(CONFIG_DRM_PANEL_NOVATEK_NT35510) += panel-novatek-nt35510.o obj-$(CONFIG_DRM_PANEL_NOVATEK_NT35560) += panel-novatek-nt35560.o obj-$(CONFIG_DRM_PANEL_NOVATEK_NT35950) += panel-novatek-nt35950.o diff --git a/drivers/gpu/drm/panel/panel-abt-y030xx067a.c b/drivers/gpu/drm/panel/panel-abt-y030xx067a.c index ed626fdc08e8..1cc0f1d09684 100644 --- a/drivers/gpu/drm/panel/panel-abt-y030xx067a.c +++ b/drivers/gpu/drm/panel/panel-abt-y030xx067a.c @@ -140,7 +140,7 @@ static const struct reg_sequence y030xx067a_init_sequence[] = { { 0x03, REG03_VPOSITION(0x0a) }, { 0x04, REG04_HPOSITION1(0xd2) }, { 0x05, REG05_CLIP | REG05_NVM_VREFRESH | REG05_SLBRCHARGE(0x2) }, - { 0x06, REG06_XPSAVE | REG06_NT }, + { 0x06, REG06_NT }, { 0x07, 0 }, { 0x08, REG08_PANEL(0x1) | REG08_CLOCK_DIV(0x2) }, { 0x09, REG09_SUB_BRIGHT_R(0x20) }, @@ -183,8 +183,6 @@ static int y030xx067a_prepare(struct drm_panel *panel) goto err_disable_regulator; } - msleep(120); - return 0; err_disable_regulator: @@ -202,6 +200,29 @@ static int y030xx067a_unprepare(struct drm_panel *panel) return 0; } +static int y030xx067a_enable(struct drm_panel *panel) +{ + struct y030xx067a *priv = to_y030xx067a(panel); + + regmap_set_bits(priv->map, 0x06, REG06_XPSAVE); + + if (panel->backlight) { + /* Wait for the picture to be ready before enabling backlight */ + msleep(120); + } + + return 0; +} + +static int y030xx067a_disable(struct drm_panel *panel) +{ + struct y030xx067a *priv = to_y030xx067a(panel); + + regmap_clear_bits(priv->map, 0x06, REG06_XPSAVE); + + return 0; +} + static int y030xx067a_get_modes(struct drm_panel *panel, struct drm_connector *connector) { @@ -239,6 +260,8 @@ static int y030xx067a_get_modes(struct drm_panel *panel, static const struct drm_panel_funcs y030xx067a_funcs = { .prepare = y030xx067a_prepare, .unprepare = y030xx067a_unprepare, + .enable = y030xx067a_enable, + .disable = y030xx067a_disable, .get_modes = y030xx067a_get_modes, }; @@ -246,6 +269,7 @@ static const struct regmap_config y030xx067a_regmap_config = { .reg_bits = 8, .val_bits = 8, .max_register = 0x15, + .cache_type = REGCACHE_FLAT, }; static int y030xx067a_probe(struct spi_device *spi) diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c index f7bfcf63d48e..1732b4f56e38 100644 --- a/drivers/gpu/drm/panel/panel-edp.c +++ b/drivers/gpu/drm/panel/panel-edp.c @@ -1847,6 +1847,7 @@ static const struct panel_delay delay_100_500_e200 = { static const struct edp_panel_entry edp_panels[] = { EDP_PANEL_ENTRY('A', 'U', 'O', 0x405c, &auo_b116xak01.delay, "B116XAK01"), EDP_PANEL_ENTRY('A', 'U', 'O', 0x615c, &delay_200_500_e50, "B116XAN06.1"), + EDP_PANEL_ENTRY('A', 'U', 'O', 0x8594, &delay_200_500_e50, "B133UAN01.0"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x0786, &delay_200_500_p2e80, "NV116WHM-T01"), EDP_PANEL_ENTRY('B', 'O', 'E', 0x07d1, &boe_nv133fhm_n61.delay, "NV133FHM-N61"), @@ -1859,6 +1860,7 @@ static const struct edp_panel_entry edp_panels[] = { EDP_PANEL_ENTRY('K', 'D', 'B', 0x0624, &kingdisplay_kd116n21_30nv_a010.delay, "116N21-30NV-A010"), EDP_PANEL_ENTRY('K', 'D', 'B', 0x1120, &delay_200_500_e80_d50, "116N29-30NK-C007"), + EDP_PANEL_ENTRY('S', 'H', 'P', 0x1523, &sharp_lq140m1jw46.delay, "LQ140M1JW46"), EDP_PANEL_ENTRY('S', 'H', 'P', 0x154c, &delay_200_500_p2e100, "LQ116M1JW10"), EDP_PANEL_ENTRY('S', 'T', 'A', 0x0100, &delay_100_500_e200, "2081116HHD028001-51D"), diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c index a07ef26234e5..6826f4d4826a 100644 --- a/drivers/gpu/drm/panel/panel-ilitek-ili9341.c +++ b/drivers/gpu/drm/panel/panel-ilitek-ili9341.c @@ -612,8 +612,10 @@ static int ili9341_dbi_probe(struct spi_device *spi, struct gpio_desc *dc, int ret; vcc = devm_regulator_get_optional(dev, "vcc"); - if (IS_ERR(vcc)) + if (IS_ERR(vcc)) { dev_err(dev, "get optional vcc failed\n"); + vcc = NULL; + } dbidev = devm_drm_dev_alloc(dev, &ili9341_dbi_driver, struct mipi_dbi_dev, drm); diff --git a/drivers/gpu/drm/panel/panel-innolux-ej030na.c b/drivers/gpu/drm/panel/panel-innolux-ej030na.c index e3b1daa0cb72..b2b0ebc9e943 100644 --- a/drivers/gpu/drm/panel/panel-innolux-ej030na.c +++ b/drivers/gpu/drm/panel/panel-innolux-ej030na.c @@ -80,8 +80,6 @@ static const struct reg_sequence ej030na_init_sequence[] = { { 0x47, 0x08 }, { 0x48, 0x0f }, { 0x49, 0x0f }, - - { 0x2b, 0x01 }, }; static int ej030na_prepare(struct drm_panel *panel) @@ -109,8 +107,6 @@ static int ej030na_prepare(struct drm_panel *panel) goto err_disable_regulator; } - msleep(120); - return 0; err_disable_regulator: @@ -128,6 +124,31 @@ static int ej030na_unprepare(struct drm_panel *panel) return 0; } +static int ej030na_enable(struct drm_panel *panel) +{ + struct ej030na *priv = to_ej030na(panel); + + /* standby off */ + regmap_write(priv->map, 0x2b, 0x01); + + if (panel->backlight) { + /* Wait for the picture to be ready before enabling backlight */ + msleep(120); + } + + return 0; +} + +static int ej030na_disable(struct drm_panel *panel) +{ + struct ej030na *priv = to_ej030na(panel); + + /* standby on */ + regmap_write(priv->map, 0x2b, 0x00); + + return 0; +} + static int ej030na_get_modes(struct drm_panel *panel, struct drm_connector *connector) { @@ -165,6 +186,8 @@ static int ej030na_get_modes(struct drm_panel *panel, static const struct drm_panel_funcs ej030na_funcs = { .prepare = ej030na_prepare, .unprepare = ej030na_unprepare, + .enable = ej030na_enable, + .disable = ej030na_disable, .get_modes = ej030na_get_modes, }; diff --git a/drivers/gpu/drm/panel/panel-lvds.c b/drivers/gpu/drm/panel/panel-lvds.c index 27a1c9923b09..eca067e78579 100644 --- a/drivers/gpu/drm/panel/panel-lvds.c +++ b/drivers/gpu/drm/panel/panel-lvds.c @@ -30,9 +30,9 @@ struct panel_lvds { const char *label; unsigned int width; unsigned int height; - struct videomode video_mode; + struct drm_display_mode dmode; + u32 bus_flags; unsigned int bus_format; - bool data_mirror; struct regulator *supply; @@ -87,21 +87,18 @@ static int panel_lvds_get_modes(struct drm_panel *panel, struct panel_lvds *lvds = to_panel_lvds(panel); struct drm_display_mode *mode; - mode = drm_mode_create(connector->dev); + mode = drm_mode_duplicate(connector->dev, &lvds->dmode); if (!mode) return 0; - drm_display_mode_from_videomode(&lvds->video_mode, mode); mode->type |= DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; drm_mode_probed_add(connector, mode); - connector->display_info.width_mm = lvds->width; - connector->display_info.height_mm = lvds->height; + connector->display_info.width_mm = lvds->dmode.width_mm; + connector->display_info.height_mm = lvds->dmode.height_mm; drm_display_info_set_bus_formats(&connector->display_info, &lvds->bus_format, 1); - connector->display_info.bus_flags = lvds->data_mirror - ? DRM_BUS_FLAG_DATA_LSB_TO_MSB - : DRM_BUS_FLAG_DATA_MSB_TO_LSB; + connector->display_info.bus_flags = lvds->bus_flags; drm_connector_set_panel_orientation(connector, lvds->orientation); return 1; @@ -116,7 +113,6 @@ static const struct drm_panel_funcs panel_lvds_funcs = { static int panel_lvds_parse_dt(struct panel_lvds *lvds) { struct device_node *np = lvds->dev->of_node; - struct display_timing timing; int ret; ret = of_drm_get_panel_orientation(np, &lvds->orientation); @@ -125,23 +121,20 @@ static int panel_lvds_parse_dt(struct panel_lvds *lvds) return ret; } - ret = of_get_display_timing(np, "panel-timing", &timing); + ret = of_get_drm_panel_display_mode(np, &lvds->dmode, &lvds->bus_flags); if (ret < 0) { dev_err(lvds->dev, "%pOF: problems parsing panel-timing (%d)\n", np, ret); return ret; } - videomode_from_timing(&timing, &lvds->video_mode); - - ret = of_property_read_u32(np, "width-mm", &lvds->width); - if (ret < 0) { + if (lvds->dmode.width_mm == 0) { dev_err(lvds->dev, "%pOF: invalid or missing %s DT property\n", np, "width-mm"); return -ENODEV; } - ret = of_property_read_u32(np, "height-mm", &lvds->height); - if (ret < 0) { + + if (lvds->dmode.height_mm == 0) { dev_err(lvds->dev, "%pOF: invalid or missing %s DT property\n", np, "height-mm"); return -ENODEV; @@ -158,7 +151,9 @@ static int panel_lvds_parse_dt(struct panel_lvds *lvds) lvds->bus_format = ret; - lvds->data_mirror = of_property_read_bool(np, "data-mirror"); + lvds->bus_flags |= of_property_read_bool(np, "data-mirror") ? + DRM_BUS_FLAG_DATA_LSB_TO_MSB : + DRM_BUS_FLAG_DATA_MSB_TO_LSB; return 0; } diff --git a/drivers/gpu/drm/panel/panel-newvision-nv3052c.c b/drivers/gpu/drm/panel/panel-newvision-nv3052c.c new file mode 100644 index 000000000000..cf078f0d3cd3 --- /dev/null +++ b/drivers/gpu/drm/panel/panel-newvision-nv3052c.c @@ -0,0 +1,482 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NewVision NV3052C IPS LCD panel driver + * + * Copyright (C) 2020, Paul Cercueil <paul@crapouillou.net> + * Copyright (C) 2022, Christophe Branchereau <cbranchereau@gmail.com> + */ + +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/gpio/consumer.h> +#include <linux/media-bus-format.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/regulator/consumer.h> +#include <linux/spi/spi.h> +#include <video/mipi_display.h> +#include <drm/drm_mipi_dbi.h> +#include <drm/drm_modes.h> +#include <drm/drm_panel.h> + +struct nv3052c_panel_info { + const struct drm_display_mode *display_modes; + unsigned int num_modes; + u16 width_mm, height_mm; + u32 bus_format, bus_flags; +}; + +struct nv3052c { + struct device *dev; + struct drm_panel panel; + struct mipi_dbi dbi; + const struct nv3052c_panel_info *panel_info; + struct regulator *supply; + struct gpio_desc *reset_gpio; +}; + +struct nv3052c_reg { + u8 cmd; + u8 val; +}; + +static const struct nv3052c_reg nv3052c_panel_regs[] = { + { 0xff, 0x30 }, + { 0xff, 0x52 }, + { 0xff, 0x01 }, + { 0xe3, 0x00 }, + { 0x40, 0x00 }, + { 0x03, 0x40 }, + { 0x04, 0x00 }, + { 0x05, 0x03 }, + { 0x08, 0x00 }, + { 0x09, 0x07 }, + { 0x0a, 0x01 }, + { 0x0b, 0x32 }, + { 0x0c, 0x32 }, + { 0x0d, 0x0b }, + { 0x0e, 0x00 }, + { 0x23, 0xa0 }, + { 0x24, 0x0c }, + { 0x25, 0x06 }, + { 0x26, 0x14 }, + { 0x27, 0x14 }, + { 0x38, 0xcc }, + { 0x39, 0xd7 }, + { 0x3a, 0x4a }, + { 0x28, 0x40 }, + { 0x29, 0x01 }, + { 0x2a, 0xdf }, + { 0x49, 0x3c }, + { 0x91, 0x77 }, + { 0x92, 0x77 }, + { 0xa0, 0x55 }, + { 0xa1, 0x50 }, + { 0xa4, 0x9c }, + { 0xa7, 0x02 }, + { 0xa8, 0x01 }, + { 0xa9, 0x01 }, + { 0xaa, 0xfc }, + { 0xab, 0x28 }, + { 0xac, 0x06 }, + { 0xad, 0x06 }, + { 0xae, 0x06 }, + { 0xaf, 0x03 }, + { 0xb0, 0x08 }, + { 0xb1, 0x26 }, + { 0xb2, 0x28 }, + { 0xb3, 0x28 }, + { 0xb4, 0x33 }, + { 0xb5, 0x08 }, + { 0xb6, 0x26 }, + { 0xb7, 0x08 }, + { 0xb8, 0x26 }, + { 0xf0, 0x00 }, + { 0xf6, 0xc0 }, + { 0xff, 0x30 }, + { 0xff, 0x52 }, + { 0xff, 0x02 }, + { 0xb0, 0x0b }, + { 0xb1, 0x16 }, + { 0xb2, 0x17 }, + { 0xb3, 0x2c }, + { 0xb4, 0x32 }, + { 0xb5, 0x3b }, + { 0xb6, 0x29 }, + { 0xb7, 0x40 }, + { 0xb8, 0x0d }, + { 0xb9, 0x05 }, + { 0xba, 0x12 }, + { 0xbb, 0x10 }, + { 0xbc, 0x12 }, + { 0xbd, 0x15 }, + { 0xbe, 0x19 }, + { 0xbf, 0x0e }, + { 0xc0, 0x16 }, + { 0xc1, 0x0a }, + { 0xd0, 0x0c }, + { 0xd1, 0x17 }, + { 0xd2, 0x14 }, + { 0xd3, 0x2e }, + { 0xd4, 0x32 }, + { 0xd5, 0x3c }, + { 0xd6, 0x22 }, + { 0xd7, 0x3d }, + { 0xd8, 0x0d }, + { 0xd9, 0x07 }, + { 0xda, 0x13 }, + { 0xdb, 0x13 }, + { 0xdc, 0x11 }, + { 0xdd, 0x15 }, + { 0xde, 0x19 }, + { 0xdf, 0x10 }, + { 0xe0, 0x17 }, + { 0xe1, 0x0a }, + { 0xff, 0x30 }, + { 0xff, 0x52 }, + { 0xff, 0x03 }, + { 0x00, 0x2a }, + { 0x01, 0x2a }, + { 0x02, 0x2a }, + { 0x03, 0x2a }, + { 0x04, 0x61 }, + { 0x05, 0x80 }, + { 0x06, 0xc7 }, + { 0x07, 0x01 }, + { 0x08, 0x03 }, + { 0x09, 0x04 }, + { 0x70, 0x22 }, + { 0x71, 0x80 }, + { 0x30, 0x2a }, + { 0x31, 0x2a }, + { 0x32, 0x2a }, + { 0x33, 0x2a }, + { 0x34, 0x61 }, + { 0x35, 0xc5 }, + { 0x36, 0x80 }, + { 0x37, 0x23 }, + { 0x40, 0x03 }, + { 0x41, 0x04 }, + { 0x42, 0x05 }, + { 0x43, 0x06 }, + { 0x44, 0x11 }, + { 0x45, 0xe8 }, + { 0x46, 0xe9 }, + { 0x47, 0x11 }, + { 0x48, 0xea }, + { 0x49, 0xeb }, + { 0x50, 0x07 }, + { 0x51, 0x08 }, + { 0x52, 0x09 }, + { 0x53, 0x0a }, + { 0x54, 0x11 }, + { 0x55, 0xec }, + { 0x56, 0xed }, + { 0x57, 0x11 }, + { 0x58, 0xef }, + { 0x59, 0xf0 }, + { 0xb1, 0x01 }, + { 0xb4, 0x15 }, + { 0xb5, 0x16 }, + { 0xb6, 0x09 }, + { 0xb7, 0x0f }, + { 0xb8, 0x0d }, + { 0xb9, 0x0b }, + { 0xba, 0x00 }, + { 0xc7, 0x02 }, + { 0xca, 0x17 }, + { 0xcb, 0x18 }, + { 0xcc, 0x0a }, + { 0xcd, 0x10 }, + { 0xce, 0x0e }, + { 0xcf, 0x0c }, + { 0xd0, 0x00 }, + { 0x81, 0x00 }, + { 0x84, 0x15 }, + { 0x85, 0x16 }, + { 0x86, 0x10 }, + { 0x87, 0x0a }, + { 0x88, 0x0c }, + { 0x89, 0x0e }, + { 0x8a, 0x02 }, + { 0x97, 0x00 }, + { 0x9a, 0x17 }, + { 0x9b, 0x18 }, + { 0x9c, 0x0f }, + { 0x9d, 0x09 }, + { 0x9e, 0x0b }, + { 0x9f, 0x0d }, + { 0xa0, 0x01 }, + { 0xff, 0x30 }, + { 0xff, 0x52 }, + { 0xff, 0x02 }, + { 0x01, 0x01 }, + { 0x02, 0xda }, + { 0x03, 0xba }, + { 0x04, 0xa8 }, + { 0x05, 0x9a }, + { 0x06, 0x70 }, + { 0x07, 0xff }, + { 0x08, 0x91 }, + { 0x09, 0x90 }, + { 0x0a, 0xff }, + { 0x0b, 0x8f }, + { 0x0c, 0x60 }, + { 0x0d, 0x58 }, + { 0x0e, 0x48 }, + { 0x0f, 0x38 }, + { 0x10, 0x2b }, + { 0xff, 0x30 }, + { 0xff, 0x52 }, + { 0xff, 0x00 }, + { 0x36, 0x0a }, +}; + +static inline struct nv3052c *to_nv3052c(struct drm_panel *panel) +{ + return container_of(panel, struct nv3052c, panel); +} + +static int nv3052c_prepare(struct drm_panel *panel) +{ + struct nv3052c *priv = to_nv3052c(panel); + struct mipi_dbi *dbi = &priv->dbi; + unsigned int i; + int err; + + err = regulator_enable(priv->supply); + if (err) { + dev_err(priv->dev, "Failed to enable power supply: %d\n", err); + return err; + } + + /* Reset the chip */ + gpiod_set_value_cansleep(priv->reset_gpio, 1); + usleep_range(10, 1000); + gpiod_set_value_cansleep(priv->reset_gpio, 0); + usleep_range(5000, 20000); + + for (i = 0; i < ARRAY_SIZE(nv3052c_panel_regs); i++) { + err = mipi_dbi_command(dbi, nv3052c_panel_regs[i].cmd, + nv3052c_panel_regs[i].val); + + if (err) { + dev_err(priv->dev, "Unable to set register: %d\n", err); + goto err_disable_regulator; + } + } + + err = mipi_dbi_command(dbi, MIPI_DCS_EXIT_SLEEP_MODE); + if (err) { + dev_err(priv->dev, "Unable to exit sleep mode: %d\n", err); + goto err_disable_regulator; + } + + return 0; + +err_disable_regulator: + regulator_disable(priv->supply); + return err; +} + +static int nv3052c_unprepare(struct drm_panel *panel) +{ + struct nv3052c *priv = to_nv3052c(panel); + struct mipi_dbi *dbi = &priv->dbi; + int err; + + err = mipi_dbi_command(dbi, MIPI_DCS_ENTER_SLEEP_MODE); + if (err) + dev_err(priv->dev, "Unable to enter sleep mode: %d\n", err); + + gpiod_set_value_cansleep(priv->reset_gpio, 1); + regulator_disable(priv->supply); + + return 0; +} + +static int nv3052c_enable(struct drm_panel *panel) +{ + struct nv3052c *priv = to_nv3052c(panel); + struct mipi_dbi *dbi = &priv->dbi; + int err; + + err = mipi_dbi_command(dbi, MIPI_DCS_SET_DISPLAY_ON); + if (err) { + dev_err(priv->dev, "Unable to enable display: %d\n", err); + return err; + } + + if (panel->backlight) { + /* Wait for the picture to be ready before enabling backlight */ + msleep(120); + } + + return 0; +} + +static int nv3052c_disable(struct drm_panel *panel) +{ + struct nv3052c *priv = to_nv3052c(panel); + struct mipi_dbi *dbi = &priv->dbi; + int err; + + err = mipi_dbi_command(dbi, MIPI_DCS_SET_DISPLAY_OFF); + if (err) { + dev_err(priv->dev, "Unable to disable display: %d\n", err); + return err; + } + + return 0; +} + +static int nv3052c_get_modes(struct drm_panel *panel, + struct drm_connector *connector) +{ + struct nv3052c *priv = to_nv3052c(panel); + const struct nv3052c_panel_info *panel_info = priv->panel_info; + struct drm_display_mode *mode; + unsigned int i; + + for (i = 0; i < panel_info->num_modes; i++) { + mode = drm_mode_duplicate(connector->dev, + &panel_info->display_modes[i]); + if (!mode) + return -ENOMEM; + + drm_mode_set_name(mode); + + mode->type = DRM_MODE_TYPE_DRIVER; + if (panel_info->num_modes == 1) + mode->type |= DRM_MODE_TYPE_PREFERRED; + + drm_mode_probed_add(connector, mode); + } + + connector->display_info.bpc = 8; + connector->display_info.width_mm = panel_info->width_mm; + connector->display_info.height_mm = panel_info->height_mm; + + drm_display_info_set_bus_formats(&connector->display_info, + &panel_info->bus_format, 1); + connector->display_info.bus_flags = panel_info->bus_flags; + + return panel_info->num_modes; +} + +static const struct drm_panel_funcs nv3052c_funcs = { + .prepare = nv3052c_prepare, + .unprepare = nv3052c_unprepare, + .enable = nv3052c_enable, + .disable = nv3052c_disable, + .get_modes = nv3052c_get_modes, +}; + +static int nv3052c_probe(struct spi_device *spi) +{ + struct device *dev = &spi->dev; + struct nv3052c *priv; + int err; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->dev = dev; + + priv->panel_info = of_device_get_match_data(dev); + if (!priv->panel_info) + return -EINVAL; + + priv->supply = devm_regulator_get(dev, "power"); + if (IS_ERR(priv->supply)) + return dev_err_probe(dev, PTR_ERR(priv->supply), "Failed to get power supply\n"); + + priv->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(priv->reset_gpio)) + return dev_err_probe(dev, PTR_ERR(priv->reset_gpio), "Failed to get reset GPIO\n"); + + err = mipi_dbi_spi_init(spi, &priv->dbi, NULL); + if (err) + return dev_err_probe(dev, err, "MIPI DBI init failed\n"); + + priv->dbi.read_commands = NULL; + + spi_set_drvdata(spi, priv); + + drm_panel_init(&priv->panel, dev, &nv3052c_funcs, + DRM_MODE_CONNECTOR_DPI); + + err = drm_panel_of_backlight(&priv->panel); + if (err) + return dev_err_probe(dev, err, "Failed to attach backlight\n"); + + drm_panel_add(&priv->panel); + + return 0; +} + +static void nv3052c_remove(struct spi_device *spi) +{ + struct nv3052c *priv = spi_get_drvdata(spi); + + drm_panel_remove(&priv->panel); + drm_panel_disable(&priv->panel); + drm_panel_unprepare(&priv->panel); +} + +static const struct drm_display_mode ltk035c5444t_modes[] = { + { /* 60 Hz */ + .clock = 24000, + .hdisplay = 640, + .hsync_start = 640 + 96, + .hsync_end = 640 + 96 + 16, + .htotal = 640 + 96 + 16 + 48, + .vdisplay = 480, + .vsync_start = 480 + 5, + .vsync_end = 480 + 5 + 2, + .vtotal = 480 + 5 + 2 + 13, + .flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC, + }, + { /* 50 Hz */ + .clock = 18000, + .hdisplay = 640, + .hsync_start = 640 + 39, + .hsync_end = 640 + 39 + 2, + .htotal = 640 + 39 + 2 + 39, + .vdisplay = 480, + .vsync_start = 480 + 5, + .vsync_end = 480 + 5 + 2, + .vtotal = 480 + 5 + 2 + 13, + .flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC, + }, +}; + +static const struct nv3052c_panel_info ltk035c5444t_panel_info = { + .display_modes = ltk035c5444t_modes, + .num_modes = ARRAY_SIZE(ltk035c5444t_modes), + .width_mm = 77, + .height_mm = 64, + .bus_format = MEDIA_BUS_FMT_RGB888_1X24, + .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE, +}; + +static const struct of_device_id nv3052c_of_match[] = { + { .compatible = "leadtek,ltk035c5444t", .data = <k035c5444t_panel_info }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, nv3052c_of_match); + +static struct spi_driver nv3052c_driver = { + .driver = { + .name = "nv3052c", + .of_match_table = nv3052c_of_match, + }, + .probe = nv3052c_probe, + .remove = nv3052c_remove, +}; +module_spi_driver(nv3052c_driver); + +MODULE_AUTHOR("Paul Cercueil <paul@crapouillou.net>"); +MODULE_AUTHOR("Christophe Branchereau <cbranchereau@gmail.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/panel/panel-truly-nt35597.c b/drivers/gpu/drm/panel/panel-truly-nt35597.c index b24b92d93ea5..9ca5c7ff41d6 100644 --- a/drivers/gpu/drm/panel/panel-truly-nt35597.c +++ b/drivers/gpu/drm/panel/panel-truly-nt35597.c @@ -446,7 +446,7 @@ static int truly_nt35597_get_modes(struct drm_panel *panel, const struct nt35597_config *config; config = ctx->config; - mode = drm_mode_create(connector->dev); + mode = drm_mode_duplicate(connector->dev, config->dm); if (!mode) { dev_err(ctx->dev, "failed to create a new display mode\n"); return 0; @@ -454,7 +454,6 @@ static int truly_nt35597_get_modes(struct drm_panel *panel, connector->display_info.width_mm = config->width_mm; connector->display_info.height_mm = config->height_mm; - drm_mode_copy(mode, config->dm); mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; drm_mode_probed_add(connector, mode); diff --git a/drivers/gpu/drm/panel/panel-visionox-rm69299.c b/drivers/gpu/drm/panel/panel-visionox-rm69299.c index eb43503ec97b..db2443ac81d3 100644 --- a/drivers/gpu/drm/panel/panel-visionox-rm69299.c +++ b/drivers/gpu/drm/panel/panel-visionox-rm69299.c @@ -168,7 +168,8 @@ static int visionox_rm69299_get_modes(struct drm_panel *panel, struct visionox_rm69299 *ctx = panel_to_ctx(panel); struct drm_display_mode *mode; - mode = drm_mode_create(connector->dev); + mode = drm_mode_duplicate(connector->dev, + &visionox_rm69299_1080x2248_60hz); if (!mode) { dev_err(ctx->panel.dev, "failed to create a new display mode\n"); return 0; @@ -176,7 +177,6 @@ static int visionox_rm69299_get_modes(struct drm_panel *panel, connector->display_info.width_mm = 74; connector->display_info.height_mm = 131; - drm_mode_copy(mode, &visionox_rm69299_1080x2248_60hz); mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; drm_mode_probed_add(connector, mode); diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 94b6f0a19c83..7fcbc2a5b6cd 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -316,7 +316,8 @@ panfrost_ioctl_wait_bo(struct drm_device *dev, void *data, if (!gem_obj) return -ENOENT; - ret = dma_resv_wait_timeout(gem_obj->resv, true, true, timeout); + ret = dma_resv_wait_timeout(gem_obj->resv, DMA_RESV_USAGE_READ, + true, timeout); if (!ret) ret = timeout ? -ETIMEDOUT : -EBUSY; diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index a6925dbb6224..fda5871aebe3 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -247,6 +247,10 @@ static int panfrost_acquire_object_fences(struct drm_gem_object **bos, int i, ret; for (i = 0; i < bo_count; i++) { + ret = dma_resv_reserve_fences(bos[i]->resv, 1); + if (ret) + return ret; + /* panfrost always uses write mode in its current uapi */ ret = drm_sched_job_add_implicit_dependencies(job, bos[i], true); @@ -264,7 +268,7 @@ static void panfrost_attach_object_fences(struct drm_gem_object **bos, int i; for (i = 0; i < bo_count; i++) - dma_resv_add_excl_fence(bos[i]->resv, fence); + dma_resv_add_fence(bos[i]->resv, fence, DMA_RESV_USAGE_WRITE); } int panfrost_job_push(struct panfrost_job *job) diff --git a/drivers/gpu/drm/qxl/qxl_debugfs.c b/drivers/gpu/drm/qxl/qxl_debugfs.c index 6a36b0fd845c..2d9ed3b94574 100644 --- a/drivers/gpu/drm/qxl/qxl_debugfs.c +++ b/drivers/gpu/drm/qxl/qxl_debugfs.c @@ -61,7 +61,8 @@ qxl_debugfs_buffers_info(struct seq_file *m, void *data) struct dma_fence *fence; int rel = 0; - dma_resv_iter_begin(&cursor, bo->tbo.base.resv, true); + dma_resv_iter_begin(&cursor, bo->tbo.base.resv, + DMA_RESV_USAGE_BOOKKEEP); dma_resv_for_each_fence_unlocked(&cursor, fence) { if (dma_resv_iter_is_restarted(&cursor)) rel = 0; diff --git a/drivers/gpu/drm/qxl/qxl_kms.c b/drivers/gpu/drm/qxl/qxl_kms.c index 4dc5ad13f12c..a054e4a00fe8 100644 --- a/drivers/gpu/drm/qxl/qxl_kms.c +++ b/drivers/gpu/drm/qxl/qxl_kms.c @@ -165,7 +165,7 @@ int qxl_device_init(struct qxl_device *qdev, (int)qdev->surfaceram_size / 1024, (sb == 4) ? "64bit" : "32bit"); - qdev->rom = ioremap(qdev->rom_base, qdev->rom_size); + qdev->rom = ioremap_wc(qdev->rom_base, qdev->rom_size); if (!qdev->rom) { pr_err("Unable to ioremap ROM\n"); r = -ENOMEM; @@ -183,7 +183,7 @@ int qxl_device_init(struct qxl_device *qdev, goto rom_unmap; } - qdev->ram_header = ioremap(qdev->vram_base + + qdev->ram_header = ioremap_wc(qdev->vram_base + qdev->rom->ram_header_offset, sizeof(*qdev->ram_header)); if (!qdev->ram_header) { diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c index 469979cd0341..368d26da0d6a 100644 --- a/drivers/gpu/drm/qxl/qxl_release.c +++ b/drivers/gpu/drm/qxl/qxl_release.c @@ -200,7 +200,7 @@ static int qxl_release_validate_bo(struct qxl_bo *bo) return ret; } - ret = dma_resv_reserve_shared(bo->tbo.base.resv, 1); + ret = dma_resv_reserve_fences(bo->tbo.base.resv, 1); if (ret) return ret; @@ -429,7 +429,8 @@ void qxl_release_fence_buffer_objects(struct qxl_release *release) list_for_each_entry(entry, &release->bos, head) { bo = entry->bo; - dma_resv_add_shared_fence(bo->base.resv, &release->base); + dma_resv_add_fence(bo->base.resv, &release->base, + DMA_RESV_USAGE_READ); ttm_bo_move_to_lru_tail_unlocked(bo); dma_resv_unlock(bo->base.resv); } diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c index b2e33d5ba5d0..ee95001e6b5e 100644 --- a/drivers/gpu/drm/qxl/qxl_ttm.c +++ b/drivers/gpu/drm/qxl/qxl_ttm.c @@ -82,13 +82,13 @@ int qxl_ttm_io_mem_reserve(struct ttm_device *bdev, case TTM_PL_VRAM: mem->bus.is_iomem = true; mem->bus.offset = (mem->start << PAGE_SHIFT) + qdev->vram_base; - mem->bus.caching = ttm_cached; + mem->bus.caching = ttm_write_combined; break; case TTM_PL_PRIV: mem->bus.is_iomem = true; mem->bus.offset = (mem->start << PAGE_SHIFT) + qdev->surfaceram_base; - mem->bus.caching = ttm_cached; + mem->bus.caching = ttm_write_combined; break; default: return -EINVAL; @@ -113,7 +113,7 @@ static struct ttm_tt *qxl_ttm_tt_create(struct ttm_buffer_object *bo, ttm = kzalloc(sizeof(struct ttm_tt), GFP_KERNEL); if (ttm == NULL) return NULL; - if (ttm_tt_init(ttm, bo, page_flags, ttm_cached)) { + if (ttm_tt_init(ttm, bo, page_flags, ttm_cached, 0)) { kfree(ttm); return NULL; } @@ -222,41 +222,14 @@ void qxl_ttm_fini(struct qxl_device *qdev) DRM_INFO("qxl: ttm finalized\n"); } -#define QXL_DEBUGFS_MEM_TYPES 2 - -#if defined(CONFIG_DEBUG_FS) -static int qxl_mm_dump_table(struct seq_file *m, void *data) -{ - struct drm_info_node *node = (struct drm_info_node *)m->private; - struct ttm_resource_manager *man = (struct ttm_resource_manager *)node->info_ent->data; - struct drm_printer p = drm_seq_file_printer(m); - - ttm_resource_manager_debug(man, &p); - return 0; -} -#endif - void qxl_ttm_debugfs_init(struct qxl_device *qdev) { #if defined(CONFIG_DEBUG_FS) - static struct drm_info_list qxl_mem_types_list[QXL_DEBUGFS_MEM_TYPES]; - static char qxl_mem_types_names[QXL_DEBUGFS_MEM_TYPES][32]; - unsigned int i; - - for (i = 0; i < QXL_DEBUGFS_MEM_TYPES; i++) { - if (i == 0) - sprintf(qxl_mem_types_names[i], "qxl_mem_mm"); - else - sprintf(qxl_mem_types_names[i], "qxl_surf_mm"); - qxl_mem_types_list[i].name = qxl_mem_types_names[i]; - qxl_mem_types_list[i].show = &qxl_mm_dump_table; - qxl_mem_types_list[i].driver_features = 0; - if (i == 0) - qxl_mem_types_list[i].data = ttm_manager_type(&qdev->mman.bdev, TTM_PL_VRAM); - else - qxl_mem_types_list[i].data = ttm_manager_type(&qdev->mman.bdev, TTM_PL_PRIV); - - } - qxl_debugfs_add_files(qdev, qxl_mem_types_list, i); + ttm_resource_manager_create_debugfs(ttm_manager_type(&qdev->mman.bdev, + TTM_PL_VRAM), + qdev->ddev.primary->debugfs_root, "qxl_mem_mm"); + ttm_resource_manager_create_debugfs(ttm_manager_type(&qdev->mman.bdev, + TTM_PL_PRIV), + qdev->ddev.primary->debugfs_root, "qxl_surf_mm"); #endif } diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c index 9ed2b2700e0a..446f7bae54c4 100644 --- a/drivers/gpu/drm/radeon/radeon_cs.c +++ b/drivers/gpu/drm/radeon/radeon_cs.c @@ -535,6 +535,10 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *p, return r; radeon_sync_fence(&p->ib.sync, bo_va->last_pt_update); + + r = dma_resv_reserve_fences(bo->tbo.base.resv, 1); + if (r) + return r; } return radeon_vm_clear_invalids(rdev, vm); diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index b9a07677a71e..57ff2b723c87 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -533,7 +533,13 @@ static int radeon_crtc_page_flip_target(struct drm_crtc *crtc, DRM_ERROR("failed to pin new rbo buffer before flip\n"); goto cleanup; } - work->fence = dma_fence_get(dma_resv_excl_fence(new_rbo->tbo.base.resv)); + r = dma_resv_get_singleton(new_rbo->tbo.base.resv, DMA_RESV_USAGE_WRITE, + &work->fence); + if (r) { + radeon_bo_unreserve(new_rbo); + DRM_ERROR("failed to get new rbo buffer fences\n"); + goto cleanup; + } radeon_bo_get_tiling_flags(new_rbo, &tiling_flags, NULL); radeon_bo_unreserve(new_rbo); diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index f563284a7fac..8c01a7f0e027 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -162,7 +162,9 @@ static int radeon_gem_set_domain(struct drm_gem_object *gobj, } if (domain == RADEON_GEM_DOMAIN_CPU) { /* Asking for cpu access wait for object idle */ - r = dma_resv_wait_timeout(robj->tbo.base.resv, true, true, 30 * HZ); + r = dma_resv_wait_timeout(robj->tbo.base.resv, + DMA_RESV_USAGE_BOOKKEEP, + true, 30 * HZ); if (!r) r = -EBUSY; @@ -524,7 +526,7 @@ int radeon_gem_busy_ioctl(struct drm_device *dev, void *data, } robj = gem_to_radeon_bo(gobj); - r = dma_resv_test_signaled(robj->tbo.base.resv, true); + r = dma_resv_test_signaled(robj->tbo.base.resv, DMA_RESV_USAGE_READ); if (r == 0) r = -EBUSY; else @@ -553,7 +555,8 @@ int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data, } robj = gem_to_radeon_bo(gobj); - ret = dma_resv_wait_timeout(robj->tbo.base.resv, true, true, 30 * HZ); + ret = dma_resv_wait_timeout(robj->tbo.base.resv, DMA_RESV_USAGE_READ, + true, 30 * HZ); if (ret == 0) r = -EBUSY; else if (ret < 0) diff --git a/drivers/gpu/drm/radeon/radeon_mn.c b/drivers/gpu/drm/radeon/radeon_mn.c index 9fa88549c89e..29fe8423bd90 100644 --- a/drivers/gpu/drm/radeon/radeon_mn.c +++ b/drivers/gpu/drm/radeon/radeon_mn.c @@ -66,8 +66,8 @@ static bool radeon_mn_invalidate(struct mmu_interval_notifier *mn, return true; } - r = dma_resv_wait_timeout(bo->tbo.base.resv, true, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(bo->tbo.base.resv, DMA_RESV_USAGE_BOOKKEEP, + false, MAX_SCHEDULE_TIMEOUT); if (r <= 0) DRM_ERROR("(%ld) failed to wait for user bo\n", r); diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c index 91a72cd14304..6c4a6802ca96 100644 --- a/drivers/gpu/drm/radeon/radeon_object.c +++ b/drivers/gpu/drm/radeon/radeon_object.c @@ -219,7 +219,12 @@ int radeon_bo_create(struct radeon_device *rdev, int radeon_bo_kmap(struct radeon_bo *bo, void **ptr) { bool is_iomem; - int r; + long r; + + r = dma_resv_wait_timeout(bo->tbo.base.resv, DMA_RESV_USAGE_KERNEL, + false, MAX_SCHEDULE_TIMEOUT); + if (r < 0) + return r; if (bo->kptr) { if (ptr) { @@ -782,9 +787,15 @@ void radeon_bo_fence(struct radeon_bo *bo, struct radeon_fence *fence, bool shared) { struct dma_resv *resv = bo->tbo.base.resv; + int r; + + r = dma_resv_reserve_fences(resv, 1); + if (r) { + /* As last resort on OOM we block for the fence */ + dma_fence_wait(&fence->base, false); + return; + } - if (shared) - dma_resv_add_shared_fence(resv, &fence->base); - else - dma_resv_add_excl_fence(resv, &fence->base); + dma_resv_add_fence(resv, &fence->base, shared ? + DMA_RESV_USAGE_READ : DMA_RESV_USAGE_WRITE); } diff --git a/drivers/gpu/drm/radeon/radeon_prime.c b/drivers/gpu/drm/radeon/radeon_prime.c index 4a90807351e7..42a87948e28c 100644 --- a/drivers/gpu/drm/radeon/radeon_prime.c +++ b/drivers/gpu/drm/radeon/radeon_prime.c @@ -77,19 +77,9 @@ int radeon_gem_prime_pin(struct drm_gem_object *obj) /* pin buffer into GTT */ ret = radeon_bo_pin(bo, RADEON_GEM_DOMAIN_GTT, NULL); - if (unlikely(ret)) - goto error; - - if (bo->tbo.moving) { - ret = dma_fence_wait(bo->tbo.moving, false); - if (unlikely(ret)) { - radeon_bo_unpin(bo); - goto error; - } - } - - bo->prime_shared_count++; -error: + if (likely(ret == 0)) + bo->prime_shared_count++; + radeon_bo_unreserve(bo); return ret; } diff --git a/drivers/gpu/drm/radeon/radeon_sync.c b/drivers/gpu/drm/radeon/radeon_sync.c index b991ba1bcd51..49bbb2266c0f 100644 --- a/drivers/gpu/drm/radeon/radeon_sync.c +++ b/drivers/gpu/drm/radeon/radeon_sync.c @@ -96,7 +96,7 @@ int radeon_sync_resv(struct radeon_device *rdev, struct dma_fence *f; int r = 0; - dma_resv_for_each_fence(&cursor, resv, shared, f) { + dma_resv_for_each_fence(&cursor, resv, dma_resv_usage_rw(shared), f) { fence = to_radeon_fence(f); if (fence && fence->rdev == rdev) radeon_sync_fence(sync, fence); diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 44594d16611f..d33fec488713 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -781,17 +781,6 @@ void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size) #if defined(CONFIG_DEBUG_FS) -static int radeon_mm_vram_dump_table_show(struct seq_file *m, void *unused) -{ - struct radeon_device *rdev = (struct radeon_device *)m->private; - struct ttm_resource_manager *man = ttm_manager_type(&rdev->mman.bdev, - TTM_PL_VRAM); - struct drm_printer p = drm_seq_file_printer(m); - - ttm_resource_manager_debug(man, &p); - return 0; -} - static int radeon_ttm_page_pool_show(struct seq_file *m, void *data) { struct radeon_device *rdev = (struct radeon_device *)m->private; @@ -799,19 +788,6 @@ static int radeon_ttm_page_pool_show(struct seq_file *m, void *data) return ttm_pool_debugfs(&rdev->mman.bdev.pool, m); } -static int radeon_mm_gtt_dump_table_show(struct seq_file *m, void *unused) -{ - struct radeon_device *rdev = (struct radeon_device *)m->private; - struct ttm_resource_manager *man = ttm_manager_type(&rdev->mman.bdev, - TTM_PL_TT); - struct drm_printer p = drm_seq_file_printer(m); - - ttm_resource_manager_debug(man, &p); - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(radeon_mm_vram_dump_table); -DEFINE_SHOW_ATTRIBUTE(radeon_mm_gtt_dump_table); DEFINE_SHOW_ATTRIBUTE(radeon_ttm_page_pool); static int radeon_ttm_vram_open(struct inode *inode, struct file *filep) @@ -930,15 +906,15 @@ static void radeon_ttm_debugfs_init(struct radeon_device *rdev) debugfs_create_file("radeon_vram", 0444, root, rdev, &radeon_ttm_vram_fops); - debugfs_create_file("radeon_gtt", 0444, root, rdev, &radeon_ttm_gtt_fops); - - debugfs_create_file("radeon_vram_mm", 0444, root, rdev, - &radeon_mm_vram_dump_table_fops); - debugfs_create_file("radeon_gtt_mm", 0444, root, rdev, - &radeon_mm_gtt_dump_table_fops); debugfs_create_file("ttm_page_pool", 0444, root, rdev, &radeon_ttm_page_pool_fops); + ttm_resource_manager_create_debugfs(ttm_manager_type(&rdev->mman.bdev, + TTM_PL_VRAM), + root, "radeon_vram_mm"); + ttm_resource_manager_create_debugfs(ttm_manager_type(&rdev->mman.bdev, + TTM_PL_TT), + root, "radeon_gtt_mm"); #endif } diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index bc0f44299bb9..a2cda184b2b2 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -470,24 +470,16 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, int32_t *msg, msg_type, handle; unsigned img_size = 0; void *ptr; - long r; - int i; + int i, r; if (offset & 0x3F) { DRM_ERROR("UVD messages must be 64 byte aligned!\n"); return -EINVAL; } - r = dma_resv_wait_timeout(bo->tbo.base.resv, false, false, - MAX_SCHEDULE_TIMEOUT); - if (r <= 0) { - DRM_ERROR("Failed waiting for UVD message (%ld)!\n", r); - return r ? r : -ETIME; - } - r = radeon_bo_kmap(bo, &ptr); if (r) { - DRM_ERROR("Failed mapping the UVD message (%ld)!\n", r); + DRM_ERROR("Failed mapping the UVD message (%d)!\n", r); return r; } diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c index bb53016f3138..987cabbf1318 100644 --- a/drivers/gpu/drm/radeon/radeon_vm.c +++ b/drivers/gpu/drm/radeon/radeon_vm.c @@ -831,7 +831,7 @@ static int radeon_vm_update_ptes(struct radeon_device *rdev, int r; radeon_sync_resv(rdev, &ib->sync, pt->tbo.base.resv, true); - r = dma_resv_reserve_shared(pt->tbo.base.resv, 1); + r = dma_resv_reserve_fences(pt->tbo.base.resv, 1); if (r) return r; diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index b81fceb0b8a2..76fd2904c7c6 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -703,7 +703,10 @@ int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job, struct dma_fence *fence; int ret; - dma_resv_for_each_fence(&cursor, obj->resv, write, fence) { + dma_resv_assert_held(obj->resv); + + dma_resv_for_each_fence(&cursor, obj->resv, dma_resv_usage_rw(write), + fence) { /* Make sure to grab an additional ref on the added fence */ dma_fence_get(fence); ret = drm_sched_job_add_dependency(job, fence); diff --git a/drivers/gpu/drm/selftests/test-drm_buddy.c b/drivers/gpu/drm/selftests/test-drm_buddy.c index fa997f89522b..aca0c491040f 100644 --- a/drivers/gpu/drm/selftests/test-drm_buddy.c +++ b/drivers/gpu/drm/selftests/test-drm_buddy.c @@ -488,8 +488,10 @@ static int igt_buddy_alloc_smoke(void *arg) } order = drm_random_order(mm.max_order + 1, &prng); - if (!order) + if (!order) { + err = -ENOMEM; goto out_fini; + } for (i = 0; i <= mm.max_order; ++i) { struct drm_buddy_block *block; @@ -902,14 +904,13 @@ err_fini: static int igt_buddy_alloc_limit(void *arg) { - u64 end, size = U64_MAX, start = 0; + u64 size = U64_MAX, start = 0; struct drm_buddy_block *block; unsigned long flags = 0; LIST_HEAD(allocated); struct drm_buddy mm; int err; - size = end = round_down(size, 4096); err = drm_buddy_init(&mm, size, PAGE_SIZE); if (err) return err; @@ -921,7 +922,8 @@ static int igt_buddy_alloc_limit(void *arg) goto out_fini; } - err = drm_buddy_alloc_blocks(&mm, start, end, size, + size = mm.chunk_size << mm.max_order; + err = drm_buddy_alloc_blocks(&mm, start, size, size, PAGE_SIZE, &allocated, flags); if (unlikely(err)) diff --git a/drivers/gpu/drm/solomon/Kconfig b/drivers/gpu/drm/solomon/Kconfig index 5861c3ab7c45..e170716d976b 100644 --- a/drivers/gpu/drm/solomon/Kconfig +++ b/drivers/gpu/drm/solomon/Kconfig @@ -1,13 +1,13 @@ config DRM_SSD130X tristate "DRM support for Solomon SSD130x OLED displays" - depends on DRM + depends on DRM && MMU select BACKLIGHT_CLASS_DEVICE select DRM_GEM_SHMEM_HELPER select DRM_KMS_HELPER help - DRM driver for the SSD1305, SSD1306, SSD1307 and SSD1309 Solomon - OLED controllers. This is only for the core driver, a driver for - the appropriate bus transport in your chip also must be selected. + DRM driver for the SSD130x Solomon and SINO WEALTH SH110x OLED + controllers. This is only for the core driver, a driver for the + appropriate bus transport in your chip also must be selected. If M is selected the module will be called ssd130x. @@ -16,6 +16,16 @@ config DRM_SSD130X_I2C depends on DRM_SSD130X && I2C select REGMAP_I2C help - Say Y here if the SSD130x OLED display is connected via I2C bus. + Say Y here if the SSD130x or SH110x OLED display is connected via + I2C bus. If M is selected the module will be called ssd130x-i2c. + +config DRM_SSD130X_SPI + tristate "DRM support for Solomon SSD130X OLED displays (SPI bus)" + depends on DRM_SSD130X && SPI + select REGMAP + help + Say Y here if the SSD130x OLED display is connected via SPI bus. + + If M is selected the module will be called ssd130x-spi. diff --git a/drivers/gpu/drm/solomon/Makefile b/drivers/gpu/drm/solomon/Makefile index 4bfc5acb0447..b5fc792257d7 100644 --- a/drivers/gpu/drm/solomon/Makefile +++ b/drivers/gpu/drm/solomon/Makefile @@ -1,2 +1,3 @@ obj-$(CONFIG_DRM_SSD130X) += ssd130x.o obj-$(CONFIG_DRM_SSD130X_I2C) += ssd130x-i2c.o +obj-$(CONFIG_DRM_SSD130X_SPI) += ssd130x-spi.o diff --git a/drivers/gpu/drm/solomon/ssd130x-i2c.c b/drivers/gpu/drm/solomon/ssd130x-i2c.c index 3126aeda4ced..d6835ec71c39 100644 --- a/drivers/gpu/drm/solomon/ssd130x-i2c.c +++ b/drivers/gpu/drm/solomon/ssd130x-i2c.c @@ -53,48 +53,43 @@ static void ssd130x_i2c_shutdown(struct i2c_client *client) ssd130x_shutdown(ssd130x); } -static struct ssd130x_deviceinfo ssd130x_ssd1305_deviceinfo = { - .default_vcomh = 0x34, - .default_dclk_div = 1, - .default_dclk_frq = 7, -}; - -static struct ssd130x_deviceinfo ssd130x_ssd1306_deviceinfo = { - .default_vcomh = 0x20, - .default_dclk_div = 1, - .default_dclk_frq = 8, - .need_chargepump = 1, -}; - -static struct ssd130x_deviceinfo ssd130x_ssd1307_deviceinfo = { - .default_vcomh = 0x20, - .default_dclk_div = 2, - .default_dclk_frq = 12, - .need_pwm = 1, -}; - -static struct ssd130x_deviceinfo ssd130x_ssd1309_deviceinfo = { - .default_vcomh = 0x34, - .default_dclk_div = 1, - .default_dclk_frq = 10, -}; - static const struct of_device_id ssd130x_of_match[] = { { + .compatible = "sinowealth,sh1106", + .data = &ssd130x_variants[SH1106_ID], + }, + { + .compatible = "solomon,ssd1305", + .data = &ssd130x_variants[SSD1305_ID], + }, + { + .compatible = "solomon,ssd1306", + .data = &ssd130x_variants[SSD1306_ID], + }, + { + .compatible = "solomon,ssd1307", + .data = &ssd130x_variants[SSD1307_ID], + }, + { + .compatible = "solomon,ssd1309", + .data = &ssd130x_variants[SSD1309_ID], + }, + /* Deprecated but kept for backward compatibility */ + { .compatible = "solomon,ssd1305fb-i2c", - .data = &ssd130x_ssd1305_deviceinfo, + .data = &ssd130x_variants[SSD1305_ID], }, { .compatible = "solomon,ssd1306fb-i2c", - .data = &ssd130x_ssd1306_deviceinfo, + .data = &ssd130x_variants[SSD1306_ID], }, { .compatible = "solomon,ssd1307fb-i2c", - .data = &ssd130x_ssd1307_deviceinfo, + .data = &ssd130x_variants[SSD1307_ID], }, { .compatible = "solomon,ssd1309fb-i2c", - .data = &ssd130x_ssd1309_deviceinfo, + .data = &ssd130x_variants[SSD1309_ID], }, { /* sentinel */ } }; @@ -114,3 +109,4 @@ module_i2c_driver(ssd130x_i2c_driver); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_AUTHOR("Javier Martinez Canillas <javierm@redhat.com>"); MODULE_LICENSE("GPL v2"); +MODULE_IMPORT_NS(DRM_SSD130X); diff --git a/drivers/gpu/drm/solomon/ssd130x-spi.c b/drivers/gpu/drm/solomon/ssd130x-spi.c new file mode 100644 index 000000000000..43722adab1f8 --- /dev/null +++ b/drivers/gpu/drm/solomon/ssd130x-spi.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * DRM driver for Solomon SSD130X OLED displays (SPI bus) + * + * Copyright 2022 Red Hat Inc. + * Authors: Javier Martinez Canillas <javierm@redhat.com> + */ +#include <linux/spi/spi.h> +#include <linux/module.h> + +#include "ssd130x.h" + +#define DRIVER_NAME "ssd130x-spi" +#define DRIVER_DESC "DRM driver for Solomon SSD130X OLED displays (SPI)" + +struct ssd130x_spi_transport { + struct spi_device *spi; + struct gpio_desc *dc; +}; + +static const struct regmap_config ssd130x_spi_regmap_config = { + .reg_bits = 8, + .val_bits = 8, +}; + +/* + * The regmap bus .write handler, it is just a wrapper around spi_write() + * but toggling the Data/Command control pin (D/C#). Since for 4-wire SPI + * a D/C# pin is used, in contrast with I2C where a control byte is sent, + * prior to every data byte, that contains a bit with the D/C# value. + * + * These control bytes are considered registers by the ssd130x core driver + * and can be used by the ssd130x SPI driver to determine if the data sent + * is for a command register or for the Graphic Display Data RAM (GDDRAM). + */ +static int ssd130x_spi_write(void *context, const void *data, size_t count) +{ + struct ssd130x_spi_transport *t = context; + struct spi_device *spi = t->spi; + const u8 *reg = data; + + if (*reg == SSD130X_COMMAND) + gpiod_set_value_cansleep(t->dc, 0); + + if (*reg == SSD130X_DATA) + gpiod_set_value_cansleep(t->dc, 1); + + /* Remove control byte since is not used in a 4-wire SPI interface */ + return spi_write(spi, reg + 1, count - 1); +} + +/* The ssd130x driver does not read registers but regmap expects a .read */ +static int ssd130x_spi_read(void *context, const void *reg, size_t reg_size, + void *val, size_t val_size) +{ + return -EOPNOTSUPP; +} + +/* + * A custom bus is needed due the special write that toggles a D/C# pin, + * another option could be to just have a .reg_write() callback but that + * will prevent to do data writes in bulk. + * + * Once the regmap API is extended to support defining a bulk write handler + * in the struct regmap_config, this can be simplified and the bus dropped. + */ +static struct regmap_bus regmap_ssd130x_spi_bus = { + .write = ssd130x_spi_write, + .read = ssd130x_spi_read, +}; + +static int ssd130x_spi_probe(struct spi_device *spi) +{ + struct ssd130x_spi_transport *t; + struct ssd130x_device *ssd130x; + struct regmap *regmap; + struct gpio_desc *dc; + struct device *dev = &spi->dev; + + dc = devm_gpiod_get(dev, "dc", GPIOD_OUT_LOW); + if (IS_ERR(dc)) + return dev_err_probe(dev, PTR_ERR(dc), + "Failed to get dc gpio\n"); + + t = devm_kzalloc(dev, sizeof(*t), GFP_KERNEL); + if (!t) + return dev_err_probe(dev, -ENOMEM, + "Failed to allocate SPI transport data\n"); + + t->spi = spi; + t->dc = dc; + + regmap = devm_regmap_init(dev, ®map_ssd130x_spi_bus, t, + &ssd130x_spi_regmap_config); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); + + ssd130x = ssd130x_probe(dev, regmap); + if (IS_ERR(ssd130x)) + return PTR_ERR(ssd130x); + + spi_set_drvdata(spi, ssd130x); + + return 0; +} + +static void ssd130x_spi_remove(struct spi_device *spi) +{ + struct ssd130x_device *ssd130x = spi_get_drvdata(spi); + + ssd130x_remove(ssd130x); +} + +static void ssd130x_spi_shutdown(struct spi_device *spi) +{ + struct ssd130x_device *ssd130x = spi_get_drvdata(spi); + + ssd130x_shutdown(ssd130x); +} + +static const struct of_device_id ssd130x_of_match[] = { + { + .compatible = "sinowealth,sh1106", + .data = &ssd130x_variants[SH1106_ID], + }, + { + .compatible = "solomon,ssd1305", + .data = &ssd130x_variants[SSD1305_ID], + }, + { + .compatible = "solomon,ssd1306", + .data = &ssd130x_variants[SSD1306_ID], + }, + { + .compatible = "solomon,ssd1307", + .data = &ssd130x_variants[SSD1307_ID], + }, + { + .compatible = "solomon,ssd1309", + .data = &ssd130x_variants[SSD1309_ID], + }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, ssd130x_of_match); + +/* + * The SPI core always reports a MODALIAS uevent of the form "spi:<dev>", even + * if the device was registered via OF. This means that the module will not be + * auto loaded, unless it contains an alias that matches the MODALIAS reported. + * + * To workaround this issue, add a SPI device ID table. Even when this should + * not be needed for this driver to match the registered SPI devices. + */ +static const struct spi_device_id ssd130x_spi_table[] = { + { "sh1106", SH1106_ID }, + { "ssd1305", SSD1305_ID }, + { "ssd1306", SSD1306_ID }, + { "ssd1307", SSD1307_ID }, + { "ssd1309", SSD1309_ID }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(spi, ssd130x_spi_table); + +static struct spi_driver ssd130x_spi_driver = { + .driver = { + .name = DRIVER_NAME, + .of_match_table = ssd130x_of_match, + }, + .probe = ssd130x_spi_probe, + .remove = ssd130x_spi_remove, + .shutdown = ssd130x_spi_shutdown, +}; +module_spi_driver(ssd130x_spi_driver); + +MODULE_DESCRIPTION(DRIVER_DESC); +MODULE_AUTHOR("Javier Martinez Canillas <javierm@redhat.com>"); +MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS(DRM_SSD130X); diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c index ce4dc20412e0..ba2de93d00f0 100644 --- a/drivers/gpu/drm/solomon/ssd130x.c +++ b/drivers/gpu/drm/solomon/ssd130x.c @@ -39,16 +39,15 @@ #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 -#define SSD130X_DATA 0x40 -#define SSD130X_COMMAND 0x80 - +#define SSD130X_PAGE_COL_START_LOW 0x00 +#define SSD130X_PAGE_COL_START_HIGH 0x10 #define SSD130X_SET_ADDRESS_MODE 0x20 #define SSD130X_SET_COL_RANGE 0x21 #define SSD130X_SET_PAGE_RANGE 0x22 #define SSD130X_CONTRAST 0x81 #define SSD130X_SET_LOOKUP_TABLE 0x91 #define SSD130X_CHARGE_PUMP 0x8d -#define SSD130X_SEG_REMAP_ON 0xa1 +#define SSD130X_SET_SEG_REMAP 0xa0 #define SSD130X_DISPLAY_OFF 0xae #define SSD130X_SET_MULTIPLEX_RATIO 0xa8 #define SSD130X_DISPLAY_ON 0xaf @@ -61,7 +60,14 @@ #define SSD130X_SET_COM_PINS_CONFIG 0xda #define SSD130X_SET_VCOMH 0xdb -#define SSD130X_SET_COM_SCAN_DIR_MASK GENMASK(3, 2) +#define SSD130X_PAGE_COL_START_MASK GENMASK(3, 0) +#define SSD130X_PAGE_COL_START_HIGH_SET(val) FIELD_PREP(SSD130X_PAGE_COL_START_MASK, (val) >> 4) +#define SSD130X_PAGE_COL_START_LOW_SET(val) FIELD_PREP(SSD130X_PAGE_COL_START_MASK, (val)) +#define SSD130X_START_PAGE_ADDRESS_MASK GENMASK(2, 0) +#define SSD130X_START_PAGE_ADDRESS_SET(val) FIELD_PREP(SSD130X_START_PAGE_ADDRESS_MASK, (val)) +#define SSD130X_SET_SEG_REMAP_MASK GENMASK(0, 0) +#define SSD130X_SET_SEG_REMAP_SET(val) FIELD_PREP(SSD130X_SET_SEG_REMAP_MASK, (val)) +#define SSD130X_SET_COM_SCAN_DIR_MASK GENMASK(3, 3) #define SSD130X_SET_COM_SCAN_DIR_SET(val) FIELD_PREP(SSD130X_SET_COM_SCAN_DIR_MASK, (val)) #define SSD130X_SET_CLOCK_DIV_MASK GENMASK(3, 0) #define SSD130X_SET_CLOCK_DIV_SET(val) FIELD_PREP(SSD130X_SET_CLOCK_DIV_MASK, (val)) @@ -85,6 +91,38 @@ #define MAX_CONTRAST 255 +const struct ssd130x_deviceinfo ssd130x_variants[] = { + [SH1106_ID] = { + .default_vcomh = 0x40, + .default_dclk_div = 1, + .default_dclk_frq = 5, + .page_mode_only = 1, + }, + [SSD1305_ID] = { + .default_vcomh = 0x34, + .default_dclk_div = 1, + .default_dclk_frq = 7, + }, + [SSD1306_ID] = { + .default_vcomh = 0x20, + .default_dclk_div = 1, + .default_dclk_frq = 8, + .need_chargepump = 1, + }, + [SSD1307_ID] = { + .default_vcomh = 0x20, + .default_dclk_div = 2, + .default_dclk_frq = 12, + .need_pwm = 1, + }, + [SSD1309_ID] = { + .default_vcomh = 0x34, + .default_dclk_div = 1, + .default_dclk_frq = 10, + } +}; +EXPORT_SYMBOL_NS_GPL(ssd130x_variants, DRM_SSD130X); + static inline struct ssd130x_device *drm_to_ssd130x(struct drm_device *drm) { return container_of(drm, struct ssd130x_device, drm); @@ -128,6 +166,7 @@ out_end: return ret; } +/* Set address range for horizontal/vertical addressing modes */ static int ssd130x_set_col_range(struct ssd130x_device *ssd130x, u8 col_start, u8 cols) { @@ -164,6 +203,26 @@ static int ssd130x_set_page_range(struct ssd130x_device *ssd130x, return 0; } +/* Set page and column start address for page addressing mode */ +static int ssd130x_set_page_pos(struct ssd130x_device *ssd130x, + u8 page_start, u8 col_start) +{ + int ret; + u32 page, col_low, col_high; + + page = SSD130X_START_PAGE_ADDRESS | + SSD130X_START_PAGE_ADDRESS_SET(page_start); + col_low = SSD130X_PAGE_COL_START_LOW | + SSD130X_PAGE_COL_START_LOW_SET(col_start); + col_high = SSD130X_PAGE_COL_START_HIGH | + SSD130X_PAGE_COL_START_HIGH_SET(col_start); + ret = ssd130x_write_cmd(ssd130x, 3, page, col_low, col_high); + if (ret < 0) + return ret; + + return 0; +} + static int ssd130x_pwm_enable(struct ssd130x_device *ssd130x) { struct device *dev = ssd130x->dev; @@ -235,7 +294,7 @@ static void ssd130x_power_off(struct ssd130x_device *ssd130x) static int ssd130x_init(struct ssd130x_device *ssd130x) { - u32 precharge, dclk, com_invdir, compins, chargepump; + u32 precharge, dclk, com_invdir, compins, chargepump, seg_remap; int ret; /* Set initial contrast */ @@ -244,11 +303,11 @@ static int ssd130x_init(struct ssd130x_device *ssd130x) return ret; /* Set segment re-map */ - if (ssd130x->seg_remap) { - ret = ssd130x_write_cmd(ssd130x, 1, SSD130X_SEG_REMAP_ON); - if (ret < 0) - return ret; - } + seg_remap = (SSD130X_SET_SEG_REMAP | + SSD130X_SET_SEG_REMAP_SET(ssd130x->seg_remap)); + ret = ssd130x_write_cmd(ssd130x, 1, seg_remap); + if (ret < 0) + return ret; /* Set COM direction */ com_invdir = (SSD130X_SET_COM_SCAN_DIR | @@ -340,6 +399,11 @@ static int ssd130x_init(struct ssd130x_device *ssd130x) } } + /* Switch to page addressing mode */ + if (ssd130x->page_address_mode) + return ssd130x_write_cmd(ssd130x, 2, SSD130X_SET_ADDRESS_MODE, + SSD130X_SET_ADDRESS_MODE_PAGE); + /* Switch to horizontal addressing mode */ return ssd130x_write_cmd(ssd130x, 2, SSD130X_SET_ADDRESS_MODE, SSD130X_SET_ADDRESS_MODE_HORIZONTAL); @@ -353,11 +417,14 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x, u8 *buf, unsigned int width = drm_rect_width(rect); unsigned int height = drm_rect_height(rect); unsigned int line_length = DIV_ROUND_UP(width, 8); - unsigned int pages = DIV_ROUND_UP(y % 8 + height, 8); + unsigned int pages = DIV_ROUND_UP(height, 8); + struct drm_device *drm = &ssd130x->drm; u32 array_idx = 0; int ret, i, j, k; u8 *data_array = NULL; + drm_WARN_ONCE(drm, y % 8 != 0, "y must be aligned to screen page\n"); + data_array = kcalloc(width, pages, GFP_KERNEL); if (!data_array) return -ENOMEM; @@ -391,21 +458,24 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x, u8 *buf, * (5) A4 B4 C4 D4 E4 F4 G4 H4 */ - ret = ssd130x_set_col_range(ssd130x, ssd130x->col_offset + x, width); - if (ret < 0) - goto out_free; + if (!ssd130x->page_address_mode) { + /* Set address range for horizontal addressing mode */ + ret = ssd130x_set_col_range(ssd130x, ssd130x->col_offset + x, width); + if (ret < 0) + goto out_free; - ret = ssd130x_set_page_range(ssd130x, ssd130x->page_offset + y / 8, pages); - if (ret < 0) - goto out_free; + ret = ssd130x_set_page_range(ssd130x, ssd130x->page_offset + y / 8, pages); + if (ret < 0) + goto out_free; + } - for (i = y / 8; i < y / 8 + pages; i++) { + for (i = 0; i < pages; i++) { int m = 8; /* Last page may be partial */ - if (8 * (i + 1) > ssd130x->height) + if (8 * (y / 8 + i + 1) > ssd130x->height) m = ssd130x->height % 8; - for (j = x; j < x + width; j++) { + for (j = 0; j < width; j++) { u8 data = 0; for (k = 0; k < m; k++) { @@ -416,9 +486,29 @@ static int ssd130x_update_rect(struct ssd130x_device *ssd130x, u8 *buf, } data_array[array_idx++] = data; } + + /* + * In page addressing mode, the start address needs to be reset, + * and each page then needs to be written out separately. + */ + if (ssd130x->page_address_mode) { + ret = ssd130x_set_page_pos(ssd130x, + ssd130x->page_offset + i, + ssd130x->col_offset + x); + if (ret < 0) + goto out_free; + + ret = ssd130x_write_data(ssd130x, data_array, width); + if (ret < 0) + goto out_free; + + array_idx = 0; + } } - ret = ssd130x_write_data(ssd130x, data_array, width * pages); + /* Write out update in one go if we aren't using page addressing mode */ + if (!ssd130x->page_address_mode) + ret = ssd130x_write_data(ssd130x, data_array, width * pages); out_free: kfree(data_array); @@ -435,7 +525,8 @@ static void ssd130x_clear_screen(struct ssd130x_device *ssd130x) .y2 = ssd130x->height, }; - buf = kcalloc(ssd130x->width, ssd130x->height, GFP_KERNEL); + buf = kcalloc(DIV_ROUND_UP(ssd130x->width, 8), ssd130x->height, + GFP_KERNEL); if (!buf) return; @@ -449,14 +540,20 @@ static int ssd130x_fb_blit_rect(struct drm_framebuffer *fb, const struct iosys_m { struct ssd130x_device *ssd130x = drm_to_ssd130x(fb->dev); void *vmap = map->vaddr; /* TODO: Use mapping abstraction properly */ + unsigned int dst_pitch; int ret = 0; u8 *buf = NULL; - buf = kcalloc(fb->width, fb->height, GFP_KERNEL); + /* Align y to display page boundaries */ + rect->y1 = round_down(rect->y1, 8); + rect->y2 = min_t(unsigned int, round_up(rect->y2, 8), ssd130x->height); + + dst_pitch = DIV_ROUND_UP(drm_rect_width(rect), 8); + buf = kcalloc(dst_pitch, drm_rect_height(rect), GFP_KERNEL); if (!buf) return -ENOMEM; - drm_fb_xrgb8888_to_mono_reversed(buf, 0, vmap, fb, rect); + drm_fb_xrgb8888_to_mono(buf, dst_pitch, vmap, fb, rect); ssd130x_update_rect(ssd130x, buf, rect); @@ -794,6 +891,9 @@ struct ssd130x_device *ssd130x_probe(struct device *dev, struct regmap *regmap) ssd130x->regmap = regmap; ssd130x->device_info = device_get_match_data(dev); + if (ssd130x->device_info->page_mode_only) + ssd130x->page_address_mode = 1; + ssd130x_parse_properties(ssd130x); ret = ssd130x_get_resources(ssd130x); diff --git a/drivers/gpu/drm/solomon/ssd130x.h b/drivers/gpu/drm/solomon/ssd130x.h index cd21cdccb566..d14f78c2eb07 100644 --- a/drivers/gpu/drm/solomon/ssd130x.h +++ b/drivers/gpu/drm/solomon/ssd130x.h @@ -18,12 +18,25 @@ #include <linux/regmap.h> +#define SSD130X_DATA 0x40 +#define SSD130X_COMMAND 0x80 + +enum ssd130x_variants { + SH1106_ID, + SSD1305_ID, + SSD1306_ID, + SSD1307_ID, + SSD1309_ID, + NR_SSD130X_VARIANTS +}; + struct ssd130x_deviceinfo { u32 default_vcomh; u32 default_dclk_div; u32 default_dclk_frq; int need_pwm; int need_chargepump; + bool page_mode_only; }; struct ssd130x_device { @@ -38,6 +51,7 @@ struct ssd130x_device { const struct ssd130x_deviceinfo *device_info; + unsigned page_address_mode : 1; unsigned area_color_enable : 1; unsigned com_invdir : 1; unsigned com_lrremap : 1; @@ -69,6 +83,8 @@ struct ssd130x_device { u8 page_end; }; +extern const struct ssd130x_deviceinfo ssd130x_variants[]; + struct ssd130x_device *ssd130x_probe(struct device *dev, struct regmap *regmap); int ssd130x_remove(struct ssd130x_device *ssd130x); void ssd130x_shutdown(struct ssd130x_device *ssd130x); diff --git a/drivers/gpu/drm/sti/sti_gdp.c b/drivers/gpu/drm/sti/sti_gdp.c index 3db3768a3241..b58415f2e4d8 100644 --- a/drivers/gpu/drm/sti/sti_gdp.c +++ b/drivers/gpu/drm/sti/sti_gdp.c @@ -406,7 +406,7 @@ static struct sti_gdp_node_list *sti_gdp_get_free_nodes(struct sti_gdp *gdp) (hw_nvn != gdp->node_list[i].top_field_paddr)) return &gdp->node_list[i]; - /* in hazardious cases restart with the first node */ + /* in hazardous cases restart with the first node */ DRM_ERROR("inconsistent NVN for %s: 0x%08X\n", sti_plane_to_str(&gdp->plane), hw_nvn); diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c index f3ace11209dd..b3fbee7eac11 100644 --- a/drivers/gpu/drm/sti/sti_hdmi.c +++ b/drivers/gpu/drm/sti/sti_hdmi.c @@ -183,7 +183,7 @@ void hdmi_write(struct sti_hdmi *hdmi, u32 val, int offset) writel(val, hdmi->regs + offset); } -/** +/* * HDMI interrupt handler threaded * * @irq: irq number @@ -215,7 +215,7 @@ static irqreturn_t hdmi_irq_thread(int irq, void *arg) return IRQ_HANDLED; } -/** +/* * HDMI interrupt handler * * @irq: irq number @@ -237,7 +237,7 @@ static irqreturn_t hdmi_irq(int irq, void *arg) return IRQ_WAKE_THREAD; } -/** +/* * Set hdmi active area depending on the drm display mode selected * * @hdmi: pointer on the hdmi internal structure @@ -258,7 +258,7 @@ static void hdmi_active_area(struct sti_hdmi *hdmi) hdmi_write(hdmi, ymax, HDMI_ACTIVE_VID_YMAX); } -/** +/* * Overall hdmi configuration * * @hdmi: pointer on the hdmi internal structure @@ -336,7 +336,7 @@ static void hdmi_infoframe_reset(struct sti_hdmi *hdmi, hdmi_write(hdmi, 0x0, pack_offset + i); } -/** +/* * Helper to concatenate infoframe in 32 bits word * * @ptr: pointer on the hdmi internal structure @@ -353,7 +353,7 @@ static inline unsigned int hdmi_infoframe_subpack(const u8 *ptr, size_t size) return value; } -/** +/* * Helper to write info frame * * @hdmi: pointer on the hdmi internal structure @@ -423,7 +423,7 @@ static void hdmi_infoframe_write_infopack(struct sti_hdmi *hdmi, hdmi_write(hdmi, val, HDMI_SW_DI_CFG); } -/** +/* * Prepare and configure the AVI infoframe * * AVI infoframe are transmitted at least once per two video field and @@ -466,7 +466,7 @@ static int hdmi_avi_infoframe_config(struct sti_hdmi *hdmi) return 0; } -/** +/* * Prepare and configure the AUDIO infoframe * * AUDIO infoframe are transmitted once per frame and @@ -551,7 +551,7 @@ static int hdmi_vendor_infoframe_config(struct sti_hdmi *hdmi) #define HDMI_TIMEOUT_SWRESET 100 /*milliseconds */ -/** +/* * Software reset of the hdmi subsystem * * @hdmi: pointer on the hdmi internal structure @@ -785,7 +785,7 @@ static void sti_hdmi_disable(struct drm_bridge *bridge) cec_notifier_set_phys_addr(hdmi->notifier, CEC_PHYS_ADDR_INVALID); } -/** +/* * sti_hdmi_audio_get_non_coherent_n() - get N parameter for non-coherent * clocks. None-coherent clocks means that audio and TMDS clocks have not the * same source (drifts between clocks). In this case assumption is that CTS is @@ -892,7 +892,7 @@ static void sti_hdmi_pre_enable(struct drm_bridge *bridge) if (clk_prepare_enable(hdmi->clk_tmds)) DRM_ERROR("Failed to prepare/enable hdmi_tmds clk\n"); if (clk_prepare_enable(hdmi->clk_phy)) - DRM_ERROR("Failed to prepare/enable hdmi_rejec_pll clk\n"); + DRM_ERROR("Failed to prepare/enable hdmi_rejection_pll clk\n"); hdmi->enabled = true; diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c index 17cc050207f4..6bd45df8f5a7 100644 --- a/drivers/gpu/drm/stm/ltdc.c +++ b/drivers/gpu/drm/stm/ltdc.c @@ -869,8 +869,8 @@ static void ltdc_crtc_mode_set_nofb(struct drm_crtc *crtc) struct drm_device *ddev = crtc->dev; struct drm_connector_list_iter iter; struct drm_connector *connector = NULL; - struct drm_encoder *encoder = NULL; - struct drm_bridge *bridge = NULL; + struct drm_encoder *encoder = NULL, *en_iter; + struct drm_bridge *bridge = NULL, *br_iter; struct drm_display_mode *mode = &crtc->state->adjusted_mode; u32 hsync, vsync, accum_hbp, accum_vbp, accum_act_w, accum_act_h; u32 total_width, total_height; @@ -880,15 +880,19 @@ static void ltdc_crtc_mode_set_nofb(struct drm_crtc *crtc) int ret; /* get encoder from crtc */ - drm_for_each_encoder(encoder, ddev) - if (encoder->crtc == crtc) + drm_for_each_encoder(en_iter, ddev) + if (en_iter->crtc == crtc) { + encoder = en_iter; break; + } if (encoder) { /* get bridge from encoder */ - list_for_each_entry(bridge, &encoder->bridge_chain, chain_node) - if (bridge->encoder == encoder) + list_for_each_entry(br_iter, &encoder->bridge_chain, chain_node) + if (br_iter->encoder == encoder) { + bridge = br_iter; break; + } /* Get the connector from encoder */ drm_connector_list_iter_begin(ddev, &iter); diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c index 5e2b0175df36..2860e6bff8b7 100644 --- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c +++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c @@ -135,7 +135,7 @@ static int sun8i_hdmi_phy_config_a83t(struct dw_hdmi *hdmi, dw_hdmi_phy_gen2_txpwron(hdmi, 0); dw_hdmi_phy_gen2_pddq(hdmi, 1); - dw_hdmi_phy_reset(hdmi); + dw_hdmi_phy_gen2_reset(hdmi); dw_hdmi_phy_gen2_pddq(hdmi, 0); diff --git a/drivers/gpu/drm/tidss/tidss_dispc.c b/drivers/gpu/drm/tidss/tidss_dispc.c index 60b92df615aa..dae47853b728 100644 --- a/drivers/gpu/drm/tidss/tidss_dispc.c +++ b/drivers/gpu/drm/tidss/tidss_dispc.c @@ -2650,6 +2650,20 @@ static void dispc_init_errata(struct dispc_device *dispc) } } +static void dispc_softreset(struct dispc_device *dispc) +{ + u32 val; + int ret = 0; + + /* Soft reset */ + REG_FLD_MOD(dispc, DSS_SYSCONFIG, 1, 1, 1); + /* Wait for reset to complete */ + ret = readl_poll_timeout(dispc->base_common + DSS_SYSSTATUS, + val, val & 1, 100, 5000); + if (ret) + dev_warn(dispc->dev, "failed to reset dispc\n"); +} + int dispc_init(struct tidss_device *tidss) { struct device *dev = tidss->dev; @@ -2709,6 +2723,10 @@ int dispc_init(struct tidss_device *tidss) return r; } + /* K2G display controller does not support soft reset */ + if (feat->subrev != DISPC_K2G) + dispc_softreset(dispc); + for (i = 0; i < dispc->feat->num_vps; i++) { u32 gamma_size = dispc->feat->vp_feat.color.gamma_size; u32 *gamma_table; diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c index 29890d704cb4..853c6b443fff 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c @@ -433,7 +433,7 @@ static void tilcdc_crtc_set_mode(struct drm_crtc *crtc) set_scanout(crtc, fb); - crtc->hwmode = crtc->state->adjusted_mode; + drm_mode_copy(&crtc->hwmode, &crtc->state->adjusted_mode); tilcdc_crtc->hvtotal_us = tilcdc_mode_hvtotal(&crtc->hwmode); diff --git a/drivers/gpu/drm/tilcdc/tilcdc_external.c b/drivers/gpu/drm/tilcdc/tilcdc_external.c index 7594cf6e186e..3b86d002ef62 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_external.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_external.c @@ -60,11 +60,13 @@ struct drm_connector *tilcdc_encoder_find_connector(struct drm_device *ddev, int tilcdc_add_component_encoder(struct drm_device *ddev) { struct tilcdc_drm_private *priv = ddev->dev_private; - struct drm_encoder *encoder; + struct drm_encoder *encoder = NULL, *iter; - list_for_each_entry(encoder, &ddev->mode_config.encoder_list, head) - if (encoder->possible_crtcs & (1 << priv->crtc->index)) + list_for_each_entry(iter, &ddev->mode_config.encoder_list, head) + if (iter->possible_crtcs & (1 << priv->crtc->index)) { + encoder = iter; break; + } if (!encoder) { dev_err(ddev->dev, "%s: No suitable encoder found\n", __func__); diff --git a/drivers/gpu/drm/tiny/repaper.c b/drivers/gpu/drm/tiny/repaper.c index 37b6bb90e46e..a096fb8b83e9 100644 --- a/drivers/gpu/drm/tiny/repaper.c +++ b/drivers/gpu/drm/tiny/repaper.c @@ -540,7 +540,7 @@ static int repaper_fb_dirty(struct drm_framebuffer *fb) if (ret) goto out_free; - drm_fb_xrgb8888_to_mono_reversed(buf, 0, cma_obj->vaddr, fb, &clip); + drm_fb_xrgb8888_to_mono(buf, 0, cma_obj->vaddr, fb, &clip); drm_gem_fb_end_cpu_access(fb, DMA_FROM_DEVICE); diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c index 6ddc16f0fe2b..d27691f2e451 100644 --- a/drivers/gpu/drm/ttm/ttm_agp_backend.c +++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c @@ -134,7 +134,7 @@ struct ttm_tt *ttm_agp_tt_create(struct ttm_buffer_object *bo, agp_be->mem = NULL; agp_be->bridge = bridge; - if (ttm_tt_init(&agp_be->ttm, bo, page_flags, ttm_write_combined)) { + if (ttm_tt_init(&agp_be->ttm, bo, page_flags, ttm_write_combined, 0)) { kfree(agp_be); return NULL; } diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index db3dc7ef5382..75d308ec173d 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -69,107 +69,54 @@ static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo, } } -static inline void ttm_bo_move_to_pinned(struct ttm_buffer_object *bo) -{ - struct ttm_device *bdev = bo->bdev; - - list_move_tail(&bo->lru, &bdev->pinned); - - if (bdev->funcs->del_from_lru_notify) - bdev->funcs->del_from_lru_notify(bo); -} - -static inline void ttm_bo_del_from_lru(struct ttm_buffer_object *bo) -{ - struct ttm_device *bdev = bo->bdev; - - list_del_init(&bo->lru); - - if (bdev->funcs->del_from_lru_notify) - bdev->funcs->del_from_lru_notify(bo); -} - -static void ttm_bo_bulk_move_set_pos(struct ttm_lru_bulk_move_pos *pos, - struct ttm_buffer_object *bo) -{ - if (!pos->first) - pos->first = bo; - pos->last = bo; -} - -void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo, - struct ttm_resource *mem, - struct ttm_lru_bulk_move *bulk) +/** + * ttm_bo_move_to_lru_tail + * + * @bo: The buffer object. + * + * Move this BO to the tail of all lru lists used to lookup and reserve an + * object. This function must be called with struct ttm_global::lru_lock + * held, and is used to make a BO less likely to be considered for eviction. + */ +void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo) { - struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *man; - - if (!bo->deleted) - dma_resv_assert_held(bo->base.resv); - - if (bo->pin_count) { - ttm_bo_move_to_pinned(bo); - return; - } - - if (!mem) - return; - - man = ttm_manager_type(bdev, mem->mem_type); - list_move_tail(&bo->lru, &man->lru[bo->priority]); - - if (bdev->funcs->del_from_lru_notify) - bdev->funcs->del_from_lru_notify(bo); - - if (bulk && !bo->pin_count) { - switch (bo->resource->mem_type) { - case TTM_PL_TT: - ttm_bo_bulk_move_set_pos(&bulk->tt[bo->priority], bo); - break; + dma_resv_assert_held(bo->base.resv); - case TTM_PL_VRAM: - ttm_bo_bulk_move_set_pos(&bulk->vram[bo->priority], bo); - break; - } - } + if (bo->resource) + ttm_resource_move_to_lru_tail(bo->resource); } EXPORT_SYMBOL(ttm_bo_move_to_lru_tail); -void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk) +/** + * ttm_bo_set_bulk_move - update BOs bulk move object + * + * @bo: The buffer object. + * + * Update the BOs bulk move object, making sure that resources are added/removed + * as well. A bulk move allows to move many resource on the LRU at once, + * resulting in much less overhead of maintaining the LRU. + * The only requirement is that the resources stay together on the LRU and are + * never separated. This is enforces by setting the bulk_move structure on a BO. + * ttm_lru_bulk_move_tail() should be used to move all resources to the tail of + * their LRU list. + */ +void ttm_bo_set_bulk_move(struct ttm_buffer_object *bo, + struct ttm_lru_bulk_move *bulk) { - unsigned i; - - for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) { - struct ttm_lru_bulk_move_pos *pos = &bulk->tt[i]; - struct ttm_resource_manager *man; - - if (!pos->first) - continue; - - dma_resv_assert_held(pos->first->base.resv); - dma_resv_assert_held(pos->last->base.resv); - - man = ttm_manager_type(pos->first->bdev, TTM_PL_TT); - list_bulk_move_tail(&man->lru[i], &pos->first->lru, - &pos->last->lru); - } - - for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) { - struct ttm_lru_bulk_move_pos *pos = &bulk->vram[i]; - struct ttm_resource_manager *man; - - if (!pos->first) - continue; + dma_resv_assert_held(bo->base.resv); - dma_resv_assert_held(pos->first->base.resv); - dma_resv_assert_held(pos->last->base.resv); + if (bo->bulk_move == bulk) + return; - man = ttm_manager_type(pos->first->bdev, TTM_PL_VRAM); - list_bulk_move_tail(&man->lru[i], &pos->first->lru, - &pos->last->lru); - } + spin_lock(&bo->bdev->lru_lock); + if (bo->bulk_move && bo->resource) + ttm_lru_bulk_move_del(bo->bulk_move, bo->resource); + bo->bulk_move = bulk; + if (bo->bulk_move && bo->resource) + ttm_lru_bulk_move_add(bo->bulk_move, bo->resource); + spin_unlock(&bo->bdev->lru_lock); } -EXPORT_SYMBOL(ttm_bo_bulk_move_lru_tail); +EXPORT_SYMBOL(ttm_bo_set_bulk_move); static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, struct ttm_resource *mem, bool evict, @@ -204,6 +151,10 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, } } + ret = dma_resv_reserve_fences(bo->base.resv, 1); + if (ret) + goto out_err; + ret = bdev->funcs->move(bo, evict, ctx, mem, hop); if (ret) { if (ret == -EMULTIHOP) @@ -272,7 +223,7 @@ static void ttm_bo_flush_all_fences(struct ttm_buffer_object *bo) struct dma_resv_iter cursor; struct dma_fence *fence; - dma_resv_iter_begin(&cursor, resv, true); + dma_resv_iter_begin(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP); dma_resv_for_each_fence_unlocked(&cursor, fence) { if (!fence->ops->signaled) dma_fence_enable_sw_signaling(fence); @@ -301,7 +252,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, struct dma_resv *resv = &bo->base._resv; int ret; - if (dma_resv_test_signaled(resv, true)) + if (dma_resv_test_signaled(resv, DMA_RESV_USAGE_BOOKKEEP)) ret = 0; else ret = -EBUSY; @@ -313,7 +264,8 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, dma_resv_unlock(bo->base.resv); spin_unlock(&bo->bdev->lru_lock); - lret = dma_resv_wait_timeout(resv, true, interruptible, + lret = dma_resv_wait_timeout(resv, DMA_RESV_USAGE_BOOKKEEP, + interruptible, 30 * HZ); if (lret < 0) @@ -344,7 +296,6 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, return ret; } - ttm_bo_move_to_pinned(bo); list_del_init(&bo->ddestroy); spin_unlock(&bo->bdev->lru_lock); ttm_bo_cleanup_memtype_use(bo); @@ -409,6 +360,7 @@ static void ttm_bo_release(struct kref *kref) int ret; WARN_ON_ONCE(bo->pin_count); + WARN_ON_ONCE(bo->bulk_move); if (!bo->deleted) { ret = ttm_bo_individualize_resv(bo); @@ -416,7 +368,8 @@ static void ttm_bo_release(struct kref *kref) /* Last resort, if we fail to allocate memory for the * fences block for the BO to become idle */ - dma_resv_wait_timeout(bo->base.resv, true, false, + dma_resv_wait_timeout(bo->base.resv, + DMA_RESV_USAGE_BOOKKEEP, false, 30 * HZ); } @@ -427,7 +380,7 @@ static void ttm_bo_release(struct kref *kref) ttm_mem_io_free(bdev, bo->resource); } - if (!dma_resv_test_signaled(bo->base.resv, true) || + if (!dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP) || !dma_resv_trylock(bo->base.resv)) { /* The BO is not idle, resurrect it for delayed destroy */ ttm_bo_flush_all_fences(bo); @@ -445,7 +398,7 @@ static void ttm_bo_release(struct kref *kref) */ if (bo->pin_count) { bo->pin_count = 0; - ttm_bo_move_to_lru_tail(bo, bo->resource, NULL); + ttm_resource_move_to_lru_tail(bo->resource); } kref_init(&bo->kref); @@ -458,7 +411,6 @@ static void ttm_bo_release(struct kref *kref) } spin_lock(&bo->bdev->lru_lock); - ttm_bo_del_from_lru(bo); list_del(&bo->ddestroy); spin_unlock(&bo->bdev->lru_lock); @@ -466,7 +418,6 @@ static void ttm_bo_release(struct kref *kref) dma_resv_unlock(bo->base.resv); atomic_dec(&ttm_glob.bo_count); - dma_fence_put(bo->moving); bo->destroy(bo); } @@ -673,36 +624,29 @@ int ttm_mem_evict_first(struct ttm_device *bdev, struct ww_acquire_ctx *ticket) { struct ttm_buffer_object *bo = NULL, *busy_bo = NULL; + struct ttm_resource_cursor cursor; + struct ttm_resource *res; bool locked = false; - unsigned i; int ret; spin_lock(&bdev->lru_lock); - for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) { - list_for_each_entry(bo, &man->lru[i], lru) { - bool busy; - - if (!ttm_bo_evict_swapout_allowable(bo, ctx, place, - &locked, &busy)) { - if (busy && !busy_bo && ticket != - dma_resv_locking_ctx(bo->base.resv)) - busy_bo = bo; - continue; - } - - if (!ttm_bo_get_unless_zero(bo)) { - if (locked) - dma_resv_unlock(bo->base.resv); - continue; - } - break; + ttm_resource_manager_for_each_res(man, &cursor, res) { + bool busy; + + if (!ttm_bo_evict_swapout_allowable(res->bo, ctx, place, + &locked, &busy)) { + if (busy && !busy_bo && ticket != + dma_resv_locking_ctx(res->bo->base.resv)) + busy_bo = res->bo; + continue; } - /* If the inner loop terminated early, we have our candidate */ - if (&bo->lru != &man->lru[i]) + if (ttm_bo_get_unless_zero(res->bo)) { + bo = res->bo; break; - - bo = NULL; + } + if (locked) + dma_resv_unlock(res->bo->base.resv); } if (!bo) { @@ -734,10 +678,43 @@ int ttm_mem_evict_first(struct ttm_device *bdev, return ret; } +/** + * ttm_bo_pin - Pin the buffer object. + * @bo: The buffer object to pin + * + * Make sure the buffer is not evicted any more during memory pressure. + * @bo must be unpinned again by calling ttm_bo_unpin(). + */ +void ttm_bo_pin(struct ttm_buffer_object *bo) +{ + dma_resv_assert_held(bo->base.resv); + WARN_ON_ONCE(!kref_read(&bo->kref)); + if (!(bo->pin_count++) && bo->bulk_move && bo->resource) + ttm_lru_bulk_move_del(bo->bulk_move, bo->resource); +} +EXPORT_SYMBOL(ttm_bo_pin); + +/** + * ttm_bo_unpin - Unpin the buffer object. + * @bo: The buffer object to unpin + * + * Allows the buffer object to be evicted again during memory pressure. + */ +void ttm_bo_unpin(struct ttm_buffer_object *bo) +{ + dma_resv_assert_held(bo->base.resv); + WARN_ON_ONCE(!kref_read(&bo->kref)); + if (WARN_ON_ONCE(!bo->pin_count)) + return; + + if (!(--bo->pin_count) && bo->bulk_move && bo->resource) + ttm_lru_bulk_move_add(bo->bulk_move, bo->resource); +} +EXPORT_SYMBOL(ttm_bo_unpin); + /* - * Add the last move fence to the BO and reserve a new shared slot. We only use - * a shared slot to avoid unecessary sync and rely on the subsequent bo move to - * either stall or use an exclusive fence respectively set bo->moving. + * Add the last move fence to the BO as kernel dependency and reserve a new + * fence slot. */ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, struct ttm_resource_manager *man, @@ -760,17 +737,11 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, return ret; } - dma_resv_add_shared_fence(bo->base.resv, fence); - - ret = dma_resv_reserve_shared(bo->base.resv, 1); - if (unlikely(ret)) { - dma_fence_put(fence); - return ret; - } + dma_resv_add_fence(bo->base.resv, fence, DMA_RESV_USAGE_KERNEL); - dma_fence_put(bo->moving); - bo->moving = fence; - return 0; + ret = dma_resv_reserve_fences(bo->base.resv, 1); + dma_fence_put(fence); + return ret; } /* @@ -821,7 +792,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, bool type_found = false; int i, ret; - ret = dma_resv_reserve_shared(bo->base.resv, 1); + ret = dma_resv_reserve_fences(bo->base.resv, 1); if (unlikely(ret)) return ret; @@ -875,9 +846,6 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, } error: - if (bo->resource->mem_type == TTM_PL_SYSTEM && !bo->pin_count) - ttm_bo_move_to_lru_tail_unlocked(bo); - return ret; } EXPORT_SYMBOL(ttm_bo_mem_space); @@ -971,14 +939,13 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, bo->destroy = destroy ? destroy : ttm_bo_default_destroy; kref_init(&bo->kref); - INIT_LIST_HEAD(&bo->lru); INIT_LIST_HEAD(&bo->ddestroy); bo->bdev = bdev; bo->type = type; bo->page_alignment = page_alignment; - bo->moving = NULL; bo->pin_count = 0; bo->sg = sg; + bo->bulk_move = NULL; if (resv) { bo->base.resv = resv; dma_resv_assert_held(bo->base.resv); @@ -1021,8 +988,6 @@ int ttm_bo_init_reserved(struct ttm_device *bdev, return ret; } - ttm_bo_move_to_lru_tail_unlocked(bo); - return ret; } EXPORT_SYMBOL(ttm_bo_init_reserved); @@ -1072,14 +1037,14 @@ int ttm_bo_wait(struct ttm_buffer_object *bo, long timeout = 15 * HZ; if (no_wait) { - if (dma_resv_test_signaled(bo->base.resv, true)) + if (dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP)) return 0; else return -EBUSY; } - timeout = dma_resv_wait_timeout(bo->base.resv, true, interruptible, - timeout); + timeout = dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP, + interruptible, timeout); if (timeout < 0) return timeout; @@ -1123,7 +1088,6 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, return ret == -EBUSY ? -ENOSPC : ret; } - ttm_bo_move_to_pinned(bo); /* TODO: Cleanup the locking */ spin_unlock(&bo->bdev->lru_lock); diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 2b8caa1efaa3..1cbfb00c1d65 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -221,9 +221,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo, fbo->base = *bo; - ttm_bo_get(bo); - fbo->bo = bo; - /** * Fix up members that we shouldn't copy directly: * TODO: Explicit member copy would probably be better here. @@ -231,8 +228,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo, atomic_inc(&ttm_glob.bo_count); INIT_LIST_HEAD(&fbo->base.ddestroy); - INIT_LIST_HEAD(&fbo->base.lru); - fbo->base.moving = NULL; drm_vma_node_reset(&fbo->base.base.vma_node); kref_init(&fbo->base.kref); @@ -251,6 +246,15 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo, ret = dma_resv_trylock(&fbo->base.base._resv); WARN_ON(!ret); + ret = dma_resv_reserve_fences(&fbo->base.base._resv, 1); + if (ret) { + kfree(fbo); + return ret; + } + + ttm_bo_get(bo); + fbo->bo = bo; + ttm_bo_move_to_lru_tail_unlocked(&fbo->base); *new_obj = &fbo->base; @@ -495,14 +499,12 @@ static int ttm_bo_move_to_ghost(struct ttm_buffer_object *bo, * operation has completed. */ - dma_fence_put(bo->moving); - bo->moving = dma_fence_get(fence); - ret = ttm_buffer_object_transfer(bo, &ghost_obj); if (ret) return ret; - dma_resv_add_excl_fence(&ghost_obj->base._resv, fence); + dma_resv_add_fence(&ghost_obj->base._resv, fence, + DMA_RESV_USAGE_KERNEL); /** * If we're not moving to fixed memory, the TTM object @@ -540,9 +542,6 @@ static void ttm_bo_move_pipeline_evict(struct ttm_buffer_object *bo, spin_unlock(&from->move_lock); ttm_resource_free(bo, &bo->resource); - - dma_fence_put(bo->moving); - bo->moving = dma_fence_get(fence); } int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, @@ -556,7 +555,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type); int ret = 0; - dma_resv_add_excl_fence(bo->base.resv, fence); + dma_resv_add_fence(bo->base.resv, fence, DMA_RESV_USAGE_KERNEL); if (!evict) ret = ttm_bo_move_to_ghost(bo, fence, man->use_tt); else if (!from->use_tt && pipeline) @@ -573,6 +572,21 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, } EXPORT_SYMBOL(ttm_bo_move_accel_cleanup); +void ttm_bo_move_sync_cleanup(struct ttm_buffer_object *bo, + struct ttm_resource *new_mem) +{ + struct ttm_device *bdev = bo->bdev; + struct ttm_resource_manager *man = ttm_manager_type(bdev, new_mem->mem_type); + int ret; + + ret = ttm_bo_wait_free_node(bo, man->use_tt); + if (WARN_ON(ret)) + return; + + ttm_bo_assign_mem(bo, new_mem); +} +EXPORT_SYMBOL(ttm_bo_move_sync_cleanup); + /** * ttm_bo_pipeline_gutting - purge the contents of a bo * @bo: The buffer object diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 08ba083a80d2..5b324f245265 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -46,17 +46,13 @@ static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo, struct vm_fault *vmf) { - vm_fault_t ret = 0; - int err = 0; - - if (likely(!bo->moving)) - goto out_unlock; + long err = 0; /* * Quick non-stalling check for idle. */ - if (dma_fence_is_signaled(bo->moving)) - goto out_clear; + if (dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_KERNEL)) + return 0; /* * If possible, avoid waiting for GPU with mmap_lock @@ -64,34 +60,30 @@ static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo, * is the first attempt. */ if (fault_flag_allow_retry_first(vmf->flags)) { - ret = VM_FAULT_RETRY; if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) - goto out_unlock; + return VM_FAULT_RETRY; ttm_bo_get(bo); mmap_read_unlock(vmf->vma->vm_mm); - (void) dma_fence_wait(bo->moving, true); + (void)dma_resv_wait_timeout(bo->base.resv, + DMA_RESV_USAGE_KERNEL, true, + MAX_SCHEDULE_TIMEOUT); dma_resv_unlock(bo->base.resv); ttm_bo_put(bo); - goto out_unlock; + return VM_FAULT_RETRY; } /* * Ordinary wait. */ - err = dma_fence_wait(bo->moving, true); - if (unlikely(err != 0)) { - ret = (err != -ERESTARTSYS) ? VM_FAULT_SIGBUS : + err = dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_KERNEL, true, + MAX_SCHEDULE_TIMEOUT); + if (unlikely(err < 0)) { + return (err != -ERESTARTSYS) ? VM_FAULT_SIGBUS : VM_FAULT_NOPAGE; - goto out_unlock; } -out_clear: - dma_fence_put(bo->moving); - bo->moving = NULL; - -out_unlock: - return ret; + return 0; } static unsigned long ttm_bo_io_mem_pfn(struct ttm_buffer_object *bo, diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c index be24bb6cefd0..a0562ab386f5 100644 --- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/drivers/gpu/drm/ttm/ttm_device.c @@ -142,9 +142,10 @@ EXPORT_SYMBOL(ttm_global_swapout); int ttm_device_swapout(struct ttm_device *bdev, struct ttm_operation_ctx *ctx, gfp_t gfp_flags) { + struct ttm_resource_cursor cursor; struct ttm_resource_manager *man; - struct ttm_buffer_object *bo; - unsigned i, j; + struct ttm_resource *res; + unsigned i; int ret; spin_lock(&bdev->lru_lock); @@ -153,17 +154,16 @@ int ttm_device_swapout(struct ttm_device *bdev, struct ttm_operation_ctx *ctx, if (!man || !man->use_tt) continue; - for (j = 0; j < TTM_MAX_BO_PRIORITY; ++j) { - list_for_each_entry(bo, &man->lru[j], lru) { - uint32_t num_pages = PFN_UP(bo->base.size); - - ret = ttm_bo_swapout(bo, ctx, gfp_flags); - /* ttm_bo_swapout has dropped the lru_lock */ - if (!ret) - return num_pages; - if (ret != -EBUSY) - return ret; - } + ttm_resource_manager_for_each_res(man, &cursor, res) { + struct ttm_buffer_object *bo = res->bo; + uint32_t num_pages = PFN_UP(bo->base.size); + + ret = ttm_bo_swapout(bo, ctx, gfp_flags); + /* ttm_bo_swapout has dropped the lru_lock */ + if (!ret) + return num_pages; + if (ret != -EBUSY) + return ret; } } spin_unlock(&bdev->lru_lock); @@ -259,49 +259,45 @@ void ttm_device_fini(struct ttm_device *bdev) } EXPORT_SYMBOL(ttm_device_fini); -void ttm_device_clear_dma_mappings(struct ttm_device *bdev) +static void ttm_device_clear_lru_dma_mappings(struct ttm_device *bdev, + struct list_head *list) { - struct ttm_resource_manager *man; - struct ttm_buffer_object *bo; - unsigned int i, j; + struct ttm_resource *res; spin_lock(&bdev->lru_lock); - while (!list_empty(&bdev->pinned)) { - bo = list_first_entry(&bdev->pinned, struct ttm_buffer_object, lru); + while ((res = list_first_entry_or_null(list, typeof(*res), lru))) { + struct ttm_buffer_object *bo = res->bo; + /* Take ref against racing releases once lru_lock is unlocked */ - if (ttm_bo_get_unless_zero(bo)) { - list_del_init(&bo->lru); - spin_unlock(&bdev->lru_lock); + if (!ttm_bo_get_unless_zero(bo)) + continue; - if (bo->ttm) - ttm_tt_unpopulate(bo->bdev, bo->ttm); + list_del_init(&res->lru); + spin_unlock(&bdev->lru_lock); - ttm_bo_put(bo); - spin_lock(&bdev->lru_lock); - } + if (bo->ttm) + ttm_tt_unpopulate(bo->bdev, bo->ttm); + + ttm_bo_put(bo); + spin_lock(&bdev->lru_lock); } + spin_unlock(&bdev->lru_lock); +} + +void ttm_device_clear_dma_mappings(struct ttm_device *bdev) +{ + struct ttm_resource_manager *man; + unsigned int i, j; + + ttm_device_clear_lru_dma_mappings(bdev, &bdev->pinned); for (i = TTM_PL_SYSTEM; i < TTM_NUM_MEM_TYPES; ++i) { man = ttm_manager_type(bdev, i); if (!man || !man->use_tt) continue; - for (j = 0; j < TTM_MAX_BO_PRIORITY; ++j) { - while (!list_empty(&man->lru[j])) { - bo = list_first_entry(&man->lru[j], struct ttm_buffer_object, lru); - if (ttm_bo_get_unless_zero(bo)) { - list_del_init(&bo->lru); - spin_unlock(&bdev->lru_lock); - - if (bo->ttm) - ttm_tt_unpopulate(bo->bdev, bo->ttm); - - ttm_bo_put(bo); - spin_lock(&bdev->lru_lock); - } - } - } + for (j = 0; j < TTM_MAX_BO_PRIORITY; ++j) + ttm_device_clear_lru_dma_mappings(bdev, &man->lru[j]); } - spin_unlock(&bdev->lru_lock); } EXPORT_SYMBOL(ttm_device_clear_dma_mappings); diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c index 071c48d672c6..dbee34a058df 100644 --- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c +++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c @@ -90,6 +90,7 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket, list_for_each_entry(entry, list, head) { struct ttm_buffer_object *bo = entry->bo; + unsigned int num_fences; ret = ttm_bo_reserve(bo, intr, (ticket == NULL), ticket); if (ret == -EALREADY && dups) { @@ -100,12 +101,10 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket, continue; } + num_fences = max(entry->num_shared, 1u); if (!ret) { - if (!entry->num_shared) - continue; - - ret = dma_resv_reserve_shared(bo->base.resv, - entry->num_shared); + ret = dma_resv_reserve_fences(bo->base.resv, + num_fences); if (!ret) continue; } @@ -120,9 +119,9 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket, ret = ttm_bo_reserve_slowpath(bo, intr, ticket); } - if (!ret && entry->num_shared) - ret = dma_resv_reserve_shared(bo->base.resv, - entry->num_shared); + if (!ret) + ret = dma_resv_reserve_fences(bo->base.resv, + num_fences); if (unlikely(ret != 0)) { if (ticket) { @@ -155,10 +154,8 @@ void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket, list_for_each_entry(entry, list, head) { struct ttm_buffer_object *bo = entry->bo; - if (entry->num_shared) - dma_resv_add_shared_fence(bo->base.resv, fence); - else - dma_resv_add_excl_fence(bo->base.resv, fence); + dma_resv_add_fence(bo->base.resv, fence, entry->num_shared ? + DMA_RESV_USAGE_READ : DMA_RESV_USAGE_WRITE); ttm_bo_move_to_lru_tail_unlocked(bo); dma_resv_unlock(bo->base.resv); } diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c index 9a477f0fddee..65889b3caf50 100644 --- a/drivers/gpu/drm/ttm/ttm_resource.c +++ b/drivers/gpu/drm/ttm/ttm_resource.c @@ -30,12 +30,129 @@ #include <drm/ttm/ttm_bo_driver.h> /** + * ttm_lru_bulk_move_init - initialize a bulk move structure + * @bulk: the structure to init + * + * For now just memset the structure to zero. + */ +void ttm_lru_bulk_move_init(struct ttm_lru_bulk_move *bulk) +{ + memset(bulk, 0, sizeof(*bulk)); +} +EXPORT_SYMBOL(ttm_lru_bulk_move_init); + +/** + * ttm_lru_bulk_move_tail - bulk move range of resources to the LRU tail. + * + * @bulk: bulk move structure + * + * Bulk move BOs to the LRU tail, only valid to use when driver makes sure that + * resource order never changes. Should be called with &ttm_device.lru_lock held. + */ +void ttm_lru_bulk_move_tail(struct ttm_lru_bulk_move *bulk) +{ + unsigned i, j; + + for (i = 0; i < TTM_NUM_MEM_TYPES; ++i) { + for (j = 0; j < TTM_MAX_BO_PRIORITY; ++j) { + struct ttm_lru_bulk_move_pos *pos = &bulk->pos[i][j]; + struct ttm_resource_manager *man; + + if (!pos->first) + continue; + + lockdep_assert_held(&pos->first->bo->bdev->lru_lock); + dma_resv_assert_held(pos->first->bo->base.resv); + dma_resv_assert_held(pos->last->bo->base.resv); + + man = ttm_manager_type(pos->first->bo->bdev, i); + list_bulk_move_tail(&man->lru[j], &pos->first->lru, + &pos->last->lru); + } + } +} +EXPORT_SYMBOL(ttm_lru_bulk_move_tail); + +/* Return the bulk move pos object for this resource */ +static struct ttm_lru_bulk_move_pos * +ttm_lru_bulk_move_pos(struct ttm_lru_bulk_move *bulk, struct ttm_resource *res) +{ + return &bulk->pos[res->mem_type][res->bo->priority]; +} + +/* Move the resource to the tail of the bulk move range */ +static void ttm_lru_bulk_move_pos_tail(struct ttm_lru_bulk_move_pos *pos, + struct ttm_resource *res) +{ + if (pos->last != res) { + list_move(&res->lru, &pos->last->lru); + pos->last = res; + } +} + +/* Add the resource to a bulk_move cursor */ +void ttm_lru_bulk_move_add(struct ttm_lru_bulk_move *bulk, + struct ttm_resource *res) +{ + struct ttm_lru_bulk_move_pos *pos = ttm_lru_bulk_move_pos(bulk, res); + + if (!pos->first) { + pos->first = res; + pos->last = res; + } else { + ttm_lru_bulk_move_pos_tail(pos, res); + } +} + +/* Remove the resource from a bulk_move range */ +void ttm_lru_bulk_move_del(struct ttm_lru_bulk_move *bulk, + struct ttm_resource *res) +{ + struct ttm_lru_bulk_move_pos *pos = ttm_lru_bulk_move_pos(bulk, res); + + if (unlikely(pos->first == res && pos->last == res)) { + pos->first = NULL; + pos->last = NULL; + } else if (pos->first == res) { + pos->first = list_next_entry(res, lru); + } else if (pos->last == res) { + pos->last = list_prev_entry(res, lru); + } else { + list_move(&res->lru, &pos->last->lru); + } +} + +/* Move a resource to the LRU or bulk tail */ +void ttm_resource_move_to_lru_tail(struct ttm_resource *res) +{ + struct ttm_buffer_object *bo = res->bo; + struct ttm_device *bdev = bo->bdev; + + lockdep_assert_held(&bo->bdev->lru_lock); + + if (bo->pin_count) { + list_move_tail(&res->lru, &bdev->pinned); + + } else if (bo->bulk_move) { + struct ttm_lru_bulk_move_pos *pos = + ttm_lru_bulk_move_pos(bo->bulk_move, res); + + ttm_lru_bulk_move_pos_tail(pos, res); + } else { + struct ttm_resource_manager *man; + + man = ttm_manager_type(bdev, res->mem_type); + list_move_tail(&res->lru, &man->lru[bo->priority]); + } +} + +/** * ttm_resource_init - resource object constructure * @bo: buffer object this resources is allocated for * @place: placement of the resource * @res: the resource object to inistilize * - * Initialize a new resource object. Counterpart of &ttm_resource_fini. + * Initialize a new resource object. Counterpart of ttm_resource_fini(). */ void ttm_resource_init(struct ttm_buffer_object *bo, const struct ttm_place *place, @@ -52,10 +169,15 @@ void ttm_resource_init(struct ttm_buffer_object *bo, res->bus.is_iomem = false; res->bus.caching = ttm_cached; res->bo = bo; + INIT_LIST_HEAD(&res->lru); man = ttm_manager_type(bo->bdev, place->mem_type); spin_lock(&bo->bdev->lru_lock); - man->usage += bo->base.size; + man->usage += res->num_pages << PAGE_SHIFT; + if (bo->bulk_move) + ttm_lru_bulk_move_add(bo->bulk_move, res); + else + ttm_resource_move_to_lru_tail(res); spin_unlock(&bo->bdev->lru_lock); } EXPORT_SYMBOL(ttm_resource_init); @@ -66,15 +188,19 @@ EXPORT_SYMBOL(ttm_resource_init); * @res: the resource to clean up * * Should be used by resource manager backends to clean up the TTM resource - * objects before freeing the underlying structure. Counterpart of - * &ttm_resource_init + * objects before freeing the underlying structure. Makes sure the resource is + * removed from the LRU before destruction. + * Counterpart of ttm_resource_init(). */ void ttm_resource_fini(struct ttm_resource_manager *man, struct ttm_resource *res) { - spin_lock(&man->bdev->lru_lock); - man->usage -= res->bo->base.size; - spin_unlock(&man->bdev->lru_lock); + struct ttm_device *bdev = man->bdev; + + spin_lock(&bdev->lru_lock); + list_del_init(&res->lru); + man->usage -= res->num_pages << PAGE_SHIFT; + spin_unlock(&bdev->lru_lock); } EXPORT_SYMBOL(ttm_resource_fini); @@ -95,6 +221,12 @@ void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res) if (!*res) return; + if (bo->bulk_move) { + spin_lock(&bo->bdev->lru_lock); + ttm_lru_bulk_move_del(bo->bulk_move, *res); + spin_unlock(&bo->bdev->lru_lock); + } + man = ttm_manager_type(bo->bdev, (*res)->mem_type); man->func->free(man, *res); *res = NULL; @@ -273,6 +405,57 @@ void ttm_resource_manager_debug(struct ttm_resource_manager *man, } EXPORT_SYMBOL(ttm_resource_manager_debug); +/** + * ttm_resource_manager_first + * + * @man: resource manager to iterate over + * @cursor: cursor to record the position + * + * Returns the first resource from the resource manager. + */ +struct ttm_resource * +ttm_resource_manager_first(struct ttm_resource_manager *man, + struct ttm_resource_cursor *cursor) +{ + struct ttm_resource *res; + + lockdep_assert_held(&man->bdev->lru_lock); + + for (cursor->priority = 0; cursor->priority < TTM_MAX_BO_PRIORITY; + ++cursor->priority) + list_for_each_entry(res, &man->lru[cursor->priority], lru) + return res; + + return NULL; +} + +/** + * ttm_resource_manager_next + * + * @man: resource manager to iterate over + * @cursor: cursor to record the position + * @res: the current resource pointer + * + * Returns the next resource from the resource manager. + */ +struct ttm_resource * +ttm_resource_manager_next(struct ttm_resource_manager *man, + struct ttm_resource_cursor *cursor, + struct ttm_resource *res) +{ + lockdep_assert_held(&man->bdev->lru_lock); + + list_for_each_entry_continue(res, &man->lru[cursor->priority], lru) + return res; + + for (++cursor->priority; cursor->priority < TTM_MAX_BO_PRIORITY; + ++cursor->priority) + list_for_each_entry(res, &man->lru[cursor->priority], lru) + return res; + + return NULL; +} + static void ttm_kmap_iter_iomap_map_local(struct ttm_kmap_iter *iter, struct iosys_map *dmap, pgoff_t i) @@ -461,3 +644,37 @@ ttm_kmap_iter_linear_io_fini(struct ttm_kmap_iter_linear_io *iter_io, ttm_mem_io_free(bdev, mem); } + +#if defined(CONFIG_DEBUG_FS) + +static int ttm_resource_manager_show(struct seq_file *m, void *unused) +{ + struct ttm_resource_manager *man = + (struct ttm_resource_manager *)m->private; + struct drm_printer p = drm_seq_file_printer(m); + ttm_resource_manager_debug(man, &p); + return 0; +} +DEFINE_SHOW_ATTRIBUTE(ttm_resource_manager); + +#endif + +/** + * ttm_resource_manager_create_debugfs - Create debugfs entry for specified + * resource manager. + * @man: The TTM resource manager for which the debugfs stats file be creates + * @parent: debugfs directory in which the file will reside + * @name: The filename to create. + * + * This function setups up a debugfs file that can be used to look + * at debug statistics of the specified ttm_resource_manager. + */ +void ttm_resource_manager_create_debugfs(struct ttm_resource_manager *man, + struct dentry * parent, + const char *name) +{ +#if defined(CONFIG_DEBUG_FS) + debugfs_create_file(name, 0444, parent, man, &ttm_resource_manager_fops); +#endif +} +EXPORT_SYMBOL(ttm_resource_manager_create_debugfs); diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index d234aab800a0..1a66d9fc589a 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -134,9 +134,10 @@ void ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm) static void ttm_tt_init_fields(struct ttm_tt *ttm, struct ttm_buffer_object *bo, uint32_t page_flags, - enum ttm_caching caching) + enum ttm_caching caching, + unsigned long extra_pages) { - ttm->num_pages = PAGE_ALIGN(bo->base.size) >> PAGE_SHIFT; + ttm->num_pages = (PAGE_ALIGN(bo->base.size) >> PAGE_SHIFT) + extra_pages; ttm->caching = ttm_cached; ttm->page_flags = page_flags; ttm->dma_address = NULL; @@ -146,9 +147,10 @@ static void ttm_tt_init_fields(struct ttm_tt *ttm, } int ttm_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo, - uint32_t page_flags, enum ttm_caching caching) + uint32_t page_flags, enum ttm_caching caching, + unsigned long extra_pages) { - ttm_tt_init_fields(ttm, bo, page_flags, caching); + ttm_tt_init_fields(ttm, bo, page_flags, caching, extra_pages); if (ttm_tt_alloc_page_directory(ttm)) { pr_err("Failed allocating page table\n"); @@ -180,7 +182,7 @@ int ttm_sg_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo, { int ret; - ttm_tt_init_fields(ttm, bo, page_flags, caching); + ttm_tt_init_fields(ttm, bo, page_flags, caching, 0); if (page_flags & TTM_TT_FLAG_EXTERNAL) ret = ttm_sg_tt_alloc_page_directory(ttm); diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 92bc0faee84f..2352e9640922 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -259,16 +259,21 @@ v3d_lock_bo_reservations(struct v3d_job *job, return ret; for (i = 0; i < job->bo_count; i++) { + ret = dma_resv_reserve_fences(job->bo[i]->resv, 1); + if (ret) + goto fail; + ret = drm_sched_job_add_implicit_dependencies(&job->base, job->bo[i], true); - if (ret) { - drm_gem_unlock_reservations(job->bo, job->bo_count, - acquire_ctx); - return ret; - } + if (ret) + goto fail; } return 0; + +fail: + drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx); + return ret; } /** @@ -545,8 +550,8 @@ v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv, for (i = 0; i < job->bo_count; i++) { /* XXX: Use shared fences for read-only objects. */ - dma_resv_add_excl_fence(job->bo[i]->resv, - job->done_fence); + dma_resv_add_fence(job->bo[i]->resv, job->done_fence, + DMA_RESV_USAGE_WRITE); } drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx); diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index 783890e8d43a..59b20c8f132b 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -70,6 +70,7 @@ static const struct debugfs_reg32 crtc_regs[] = { static unsigned int vc4_crtc_get_cob_allocation(struct vc4_dev *vc4, unsigned int channel) { + struct vc4_hvs *hvs = vc4->hvs; u32 dispbase = HVS_READ(SCALER_DISPBASEX(channel)); /* Top/base are supposed to be 4-pixel aligned, but the * Raspberry Pi firmware fills the low bits (which are @@ -89,6 +90,7 @@ static bool vc4_crtc_get_scanout_position(struct drm_crtc *crtc, { struct drm_device *dev = crtc->dev; struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_hvs *hvs = vc4->hvs; struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); struct vc4_crtc_state *vc4_crtc_state = to_vc4_crtc_state(crtc->state); unsigned int cob_size; @@ -123,7 +125,7 @@ static bool vc4_crtc_get_scanout_position(struct drm_crtc *crtc, *vpos /= 2; /* Use hpos to correct for field offset in interlaced mode. */ - if (VC4_GET_FIELD(val, SCALER_DISPSTATX_FRAME_COUNT) % 2) + if (vc4_hvs_get_fifo_frame_count(hvs, vc4_crtc_state->assigned_channel) % 2) *hpos += mode->crtc_htotal / 2; } @@ -413,6 +415,7 @@ static void vc4_crtc_config_pv(struct drm_crtc *crtc, struct drm_encoder *encode static void require_hvs_enabled(struct drm_device *dev) { struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_hvs *hvs = vc4->hvs; WARN_ON_ONCE((HVS_READ(SCALER_DISPCTRL) & SCALER_DISPCTRL_ENABLE) != SCALER_DISPCTRL_ENABLE); @@ -426,6 +429,7 @@ static int vc4_crtc_disable(struct drm_crtc *crtc, struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder); struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); struct drm_device *dev = crtc->dev; + struct vc4_dev *vc4 = to_vc4_dev(dev); int ret; CRTC_WRITE(PV_V_CONTROL, @@ -455,7 +459,7 @@ static int vc4_crtc_disable(struct drm_crtc *crtc, vc4_encoder->post_crtc_disable(encoder, state); vc4_crtc_pixelvalve_reset(crtc); - vc4_hvs_stop_channel(dev, channel); + vc4_hvs_stop_channel(vc4->hvs, channel); if (vc4_encoder && vc4_encoder->post_crtc_powerdown) vc4_encoder->post_crtc_powerdown(encoder, state); @@ -481,6 +485,7 @@ static struct drm_encoder *vc4_crtc_get_encoder_by_type(struct drm_crtc *crtc, int vc4_crtc_disable_at_boot(struct drm_crtc *crtc) { struct drm_device *drm = crtc->dev; + struct vc4_dev *vc4 = to_vc4_dev(drm); struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); enum vc4_encoder_type encoder_type; const struct vc4_pv_data *pv_data; @@ -502,7 +507,7 @@ int vc4_crtc_disable_at_boot(struct drm_crtc *crtc) if (!(CRTC_READ(PV_V_CONTROL) & PV_VCONTROL_VIDEN)) return 0; - channel = vc4_hvs_get_fifo_from_output(drm, vc4_crtc->data->hvs_output); + channel = vc4_hvs_get_fifo_from_output(vc4->hvs, vc4_crtc->data->hvs_output); if (channel < 0) return 0; @@ -717,6 +722,7 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc) struct drm_crtc *crtc = &vc4_crtc->base; struct drm_device *dev = crtc->dev; struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_hvs *hvs = vc4->hvs; u32 chan = vc4_crtc->current_hvs_channel; unsigned long flags; @@ -735,7 +741,7 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc) * the CRTC and encoder already reconfigured, leading to * underruns. This can be seen when reconfiguring the CRTC. */ - vc4_hvs_unmask_underrun(dev, chan); + vc4_hvs_unmask_underrun(hvs, chan); } spin_unlock(&vc4_crtc->irq_lock); spin_unlock_irqrestore(&dev->event_lock, flags); diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h index 4329e09d357c..15e0c2ac3940 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.h +++ b/drivers/gpu/drm/vc4/vc4_drv.h @@ -574,8 +574,8 @@ to_vc4_crtc_state(struct drm_crtc_state *crtc_state) #define V3D_READ(offset) readl(vc4->v3d->regs + offset) #define V3D_WRITE(offset, val) writel(val, vc4->v3d->regs + offset) -#define HVS_READ(offset) readl(vc4->hvs->regs + offset) -#define HVS_WRITE(offset, val) writel(val, vc4->hvs->regs + offset) +#define HVS_READ(offset) readl(hvs->regs + offset) +#define HVS_WRITE(offset, val) writel(val, hvs->regs + offset) #define VC4_REG32(reg) { .name = #reg, .offset = reg } @@ -933,16 +933,17 @@ void vc4_irq_reset(struct drm_device *dev); /* vc4_hvs.c */ extern struct platform_driver vc4_hvs_driver; -void vc4_hvs_stop_channel(struct drm_device *dev, unsigned int output); -int vc4_hvs_get_fifo_from_output(struct drm_device *dev, unsigned int output); +void vc4_hvs_stop_channel(struct vc4_hvs *hvs, unsigned int output); +int vc4_hvs_get_fifo_from_output(struct vc4_hvs *hvs, unsigned int output); +u8 vc4_hvs_get_fifo_frame_count(struct vc4_hvs *hvs, unsigned int fifo); int vc4_hvs_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state); void vc4_hvs_atomic_begin(struct drm_crtc *crtc, struct drm_atomic_state *state); void vc4_hvs_atomic_enable(struct drm_crtc *crtc, struct drm_atomic_state *state); void vc4_hvs_atomic_disable(struct drm_crtc *crtc, struct drm_atomic_state *state); void vc4_hvs_atomic_flush(struct drm_crtc *crtc, struct drm_atomic_state *state); -void vc4_hvs_dump_state(struct drm_device *dev); -void vc4_hvs_unmask_underrun(struct drm_device *dev, int channel); -void vc4_hvs_mask_underrun(struct drm_device *dev, int channel); +void vc4_hvs_dump_state(struct vc4_hvs *hvs); +void vc4_hvs_unmask_underrun(struct vc4_hvs *hvs, int channel); +void vc4_hvs_mask_underrun(struct vc4_hvs *hvs, int channel); /* vc4_kms.c */ int vc4_kms_load(struct drm_device *dev); diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index 445d3bab89e0..9eaf304fc20d 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -485,6 +485,8 @@ again: * immediately move it to the to-be-rendered queue. */ if (exec->ct0ca != exec->ct0ea) { + trace_vc4_submit_cl(dev, false, exec->seqno, exec->ct0ca, + exec->ct0ea); submit_cl(dev, 0, exec->ct0ca, exec->ct0ea); } else { struct vc4_exec_info *next; @@ -519,6 +521,7 @@ vc4_submit_next_render_job(struct drm_device *dev) */ vc4_flush_texture_caches(dev); + trace_vc4_submit_cl(dev, true, exec->seqno, exec->ct1ca, exec->ct1ea); submit_cl(dev, 1, exec->ct1ca, exec->ct1ea); } @@ -543,7 +546,8 @@ vc4_update_bo_seqnos(struct vc4_exec_info *exec, uint64_t seqno) bo = to_vc4_bo(&exec->bo[i]->base); bo->seqno = seqno; - dma_resv_add_shared_fence(bo->base.base.resv, exec->fence); + dma_resv_add_fence(bo->base.base.resv, exec->fence, + DMA_RESV_USAGE_READ); } list_for_each_entry(bo, &exec->unref_list, unref_head) { @@ -554,7 +558,8 @@ vc4_update_bo_seqnos(struct vc4_exec_info *exec, uint64_t seqno) bo = to_vc4_bo(&exec->rcl_write_bo[i]->base); bo->write_seqno = seqno; - dma_resv_add_excl_fence(bo->base.base.resv, exec->fence); + dma_resv_add_fence(bo->base.base.resv, exec->fence, + DMA_RESV_USAGE_WRITE); } } @@ -641,7 +646,7 @@ retry: for (i = 0; i < exec->bo_count; i++) { bo = &exec->bo[i]->base; - ret = dma_resv_reserve_shared(bo->resv, 1); + ret = dma_resv_reserve_fences(bo->resv, 1); if (ret) { vc4_unlock_bo_reservations(dev, exec, acquire_ctx); return ret; @@ -1135,6 +1140,10 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data, struct dma_fence *in_fence; int ret = 0; + trace_vc4_submit_cl_ioctl(dev, args->bin_cl_size, + args->shader_rec_size, + args->bo_handle_count); + if (!vc4->v3d) { DRM_DEBUG("VC4_SUBMIT_CL with no VC4 V3D probed\n"); return -ENODEV; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 6c58b0fd13fb..e601b29e632b 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -99,9 +99,32 @@ #define HDMI_14_MAX_TMDS_CLK (340 * 1000 * 1000) -static bool vc4_hdmi_mode_needs_scrambling(const struct drm_display_mode *mode) +static const char * const output_format_str[] = { + [VC4_HDMI_OUTPUT_RGB] = "RGB", + [VC4_HDMI_OUTPUT_YUV420] = "YUV 4:2:0", + [VC4_HDMI_OUTPUT_YUV422] = "YUV 4:2:2", + [VC4_HDMI_OUTPUT_YUV444] = "YUV 4:4:4", +}; + +static const char *vc4_hdmi_output_fmt_str(enum vc4_hdmi_output_format fmt) { - return (mode->clock * 1000) > HDMI_14_MAX_TMDS_CLK; + if (fmt >= ARRAY_SIZE(output_format_str)) + return "invalid"; + + return output_format_str[fmt]; +} + +static unsigned long long +vc4_hdmi_encoder_compute_mode_clock(const struct drm_display_mode *mode, + unsigned int bpc, enum vc4_hdmi_output_format fmt); + +static bool vc4_hdmi_mode_needs_scrambling(const struct drm_display_mode *mode, + unsigned int bpc, + enum vc4_hdmi_output_format fmt) +{ + unsigned long long clock = vc4_hdmi_encoder_compute_mode_clock(mode, bpc, fmt); + + return clock > HDMI_14_MAX_TMDS_CLK; } static bool vc4_hdmi_is_full_range_rgb(struct vc4_hdmi *vc4_hdmi, @@ -266,7 +289,7 @@ static int vc4_hdmi_connector_get_modes(struct drm_connector *connector) struct drm_display_mode *mode; list_for_each_entry(mode, &connector->probed_modes, head) { - if (vc4_hdmi_mode_needs_scrambling(mode)) { + if (vc4_hdmi_mode_needs_scrambling(mode, 8, VC4_HDMI_OUTPUT_RGB)) { drm_warn_once(drm, "The core clock cannot reach frequencies high enough to support 4k @ 60Hz."); drm_warn_once(drm, "Please change your config.txt file to add hdmi_enable_4kp60."); } @@ -323,6 +346,7 @@ static void vc4_hdmi_connector_reset(struct drm_connector *connector) new_state->base.max_bpc = 8; new_state->base.max_requested_bpc = 8; + new_state->output_format = VC4_HDMI_OUTPUT_RGB; drm_atomic_helper_connector_tv_reset(connector); } @@ -337,7 +361,9 @@ vc4_hdmi_connector_duplicate_state(struct drm_connector *connector) if (!new_state) return NULL; - new_state->pixel_rate = vc4_state->pixel_rate; + new_state->tmds_char_rate = vc4_state->tmds_char_rate; + new_state->output_bpc = vc4_state->output_bpc; + new_state->output_format = vc4_state->output_format; __drm_atomic_helper_connector_duplicate_state(connector, &new_state->base); return &new_state->base; @@ -481,11 +507,38 @@ static void vc4_hdmi_write_infoframe(struct drm_encoder *encoder, DRM_ERROR("Failed to wait for infoframe to start: %d\n", ret); } +static void vc4_hdmi_avi_infoframe_colorspace(struct hdmi_avi_infoframe *frame, + enum vc4_hdmi_output_format fmt) +{ + switch (fmt) { + case VC4_HDMI_OUTPUT_RGB: + frame->colorspace = HDMI_COLORSPACE_RGB; + break; + + case VC4_HDMI_OUTPUT_YUV420: + frame->colorspace = HDMI_COLORSPACE_YUV420; + break; + + case VC4_HDMI_OUTPUT_YUV422: + frame->colorspace = HDMI_COLORSPACE_YUV422; + break; + + case VC4_HDMI_OUTPUT_YUV444: + frame->colorspace = HDMI_COLORSPACE_YUV444; + break; + + default: + break; + } +} + static void vc4_hdmi_set_avi_infoframe(struct drm_encoder *encoder) { struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); struct drm_connector *connector = &vc4_hdmi->connector; struct drm_connector_state *cstate = connector->state; + struct vc4_hdmi_connector_state *vc4_state = + conn_state_to_vc4_hdmi_conn_state(cstate); const struct drm_display_mode *mode = &vc4_hdmi->saved_adjusted_mode; union hdmi_infoframe frame; int ret; @@ -505,6 +558,7 @@ static void vc4_hdmi_set_avi_infoframe(struct drm_encoder *encoder) HDMI_QUANTIZATION_RANGE_FULL : HDMI_QUANTIZATION_RANGE_LIMITED); drm_hdmi_avi_infoframe_colorimetry(&frame.avi, cstate); + vc4_hdmi_avi_infoframe_colorspace(&frame.avi, vc4_state->output_format); drm_hdmi_avi_infoframe_bars(&frame.avi, cstate); vc4_hdmi_write_infoframe(encoder, &frame); @@ -607,7 +661,9 @@ static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder) if (!vc4_hdmi_supports_scrambling(encoder, mode)) return; - if (!vc4_hdmi_mode_needs_scrambling(mode)) + if (!vc4_hdmi_mode_needs_scrambling(mode, + vc4_hdmi->output_bpc, + vc4_hdmi->output_format)) return; drm_scdc_set_high_tmds_clock_ratio(vc4_hdmi->ddc, true); @@ -802,6 +858,39 @@ static const u16 vc5_hdmi_csc_full_rgb_to_limited_rgb[3][4] = { { 0x0000, 0x0000, 0x1b80, 0x0400 }, }; +/* + * Conversion between Full Range RGB and Full Range YUV422 using the + * BT.709 Colorspace + * + * + * [ 0.181906 0.611804 0.061758 16 ] + * [ -0.100268 -0.337232 0.437500 128 ] + * [ 0.437500 -0.397386 -0.040114 128 ] + * + * Matrix is signed 2p13 fixed point, with signed 9p6 offsets + */ +static const u16 vc5_hdmi_csc_full_rgb_to_limited_yuv422_bt709[3][4] = { + { 0x05d2, 0x1394, 0x01fa, 0x0400 }, + { 0xfccc, 0xf536, 0x0e00, 0x2000 }, + { 0x0e00, 0xf34a, 0xfeb8, 0x2000 }, +}; + +/* + * Conversion between Full Range RGB and Full Range YUV444 using the + * BT.709 Colorspace + * + * [ -0.100268 -0.337232 0.437500 128 ] + * [ 0.437500 -0.397386 -0.040114 128 ] + * [ 0.181906 0.611804 0.061758 16 ] + * + * Matrix is signed 2p13 fixed point, with signed 9p6 offsets + */ +static const u16 vc5_hdmi_csc_full_rgb_to_limited_yuv444_bt709[3][4] = { + { 0xfccc, 0xf536, 0x0e00, 0x2000 }, + { 0x0e00, 0xf34a, 0xfeb8, 0x2000 }, + { 0x05d2, 0x1394, 0x01fa, 0x0400 }, +}; + static void vc5_hdmi_set_csc_coeffs(struct vc4_hdmi *vc4_hdmi, const u16 coeffs[3][4]) { @@ -819,19 +908,53 @@ static void vc5_hdmi_csc_setup(struct vc4_hdmi *vc4_hdmi, struct drm_connector_state *state, const struct drm_display_mode *mode) { + struct vc4_hdmi_connector_state *vc4_state = + conn_state_to_vc4_hdmi_conn_state(state); unsigned long flags; + u32 if_cfg = 0; + u32 if_xbar = 0x543210; + u32 csc_chan_ctl = 0; u32 csc_ctl = VC5_MT_CP_CSC_CTL_ENABLE | VC4_SET_FIELD(VC4_HD_CSC_CTL_MODE_CUSTOM, VC5_MT_CP_CSC_CTL_MODE); spin_lock_irqsave(&vc4_hdmi->hw_lock, flags); - HDMI_WRITE(HDMI_VEC_INTERFACE_XBAR, 0x354021); + switch (vc4_state->output_format) { + case VC4_HDMI_OUTPUT_YUV444: + vc5_hdmi_set_csc_coeffs(vc4_hdmi, vc5_hdmi_csc_full_rgb_to_limited_yuv444_bt709); + break; - if (!vc4_hdmi_is_full_range_rgb(vc4_hdmi, mode)) - vc5_hdmi_set_csc_coeffs(vc4_hdmi, vc5_hdmi_csc_full_rgb_to_limited_rgb); - else - vc5_hdmi_set_csc_coeffs(vc4_hdmi, vc5_hdmi_csc_full_rgb_unity); + case VC4_HDMI_OUTPUT_YUV422: + csc_ctl |= VC4_SET_FIELD(VC5_MT_CP_CSC_CTL_FILTER_MODE_444_TO_422_STANDARD, + VC5_MT_CP_CSC_CTL_FILTER_MODE_444_TO_422) | + VC5_MT_CP_CSC_CTL_USE_444_TO_422 | + VC5_MT_CP_CSC_CTL_USE_RNG_SUPPRESSION; + + csc_chan_ctl |= VC4_SET_FIELD(VC5_MT_CP_CHANNEL_CTL_OUTPUT_REMAP_LEGACY_STYLE, + VC5_MT_CP_CHANNEL_CTL_OUTPUT_REMAP); + + if_cfg |= VC4_SET_FIELD(VC5_DVP_HT_VEC_INTERFACE_CFG_SEL_422_FORMAT_422_LEGACY, + VC5_DVP_HT_VEC_INTERFACE_CFG_SEL_422); + + vc5_hdmi_set_csc_coeffs(vc4_hdmi, vc5_hdmi_csc_full_rgb_to_limited_yuv422_bt709); + break; + + case VC4_HDMI_OUTPUT_RGB: + if_xbar = 0x354021; + if (!vc4_hdmi_is_full_range_rgb(vc4_hdmi, mode)) + vc5_hdmi_set_csc_coeffs(vc4_hdmi, vc5_hdmi_csc_full_rgb_to_limited_rgb); + else + vc5_hdmi_set_csc_coeffs(vc4_hdmi, vc5_hdmi_csc_full_rgb_unity); + break; + + default: + break; + } + + HDMI_WRITE(HDMI_VEC_INTERFACE_CFG, if_cfg); + HDMI_WRITE(HDMI_VEC_INTERFACE_XBAR, if_xbar); + HDMI_WRITE(HDMI_CSC_CHANNEL_CTL, csc_chan_ctl); HDMI_WRITE(HDMI_CSC_CTL, csc_ctl); spin_unlock_irqrestore(&vc4_hdmi->hw_lock, flags); @@ -892,6 +1015,8 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi, struct drm_connector_state *state, struct drm_display_mode *mode) { + const struct vc4_hdmi_connector_state *vc4_state = + conn_state_to_vc4_hdmi_conn_state(state); bool hsync_pos = mode->flags & DRM_MODE_FLAG_PHSYNC; bool vsync_pos = mode->flags & DRM_MODE_FLAG_PVSYNC; bool interlaced = mode->flags & DRM_MODE_FLAG_INTERLACE; @@ -939,7 +1064,7 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi, HDMI_WRITE(HDMI_VERTB0, vertb_even); HDMI_WRITE(HDMI_VERTB1, vertb); - switch (state->max_bpc) { + switch (vc4_state->output_bpc) { case 12: gcp = 6; gcp_en = true; @@ -955,6 +1080,15 @@ static void vc5_hdmi_set_timings(struct vc4_hdmi *vc4_hdmi, break; } + /* + * YCC422 is always 36-bit and not considered deep colour so + * doesn't signal in GCP. + */ + if (vc4_state->output_format == VC4_HDMI_OUTPUT_YUV422) { + gcp = 4; + gcp_en = false; + } + reg = HDMI_READ(HDMI_DEEP_COLOR_CONFIG_1); reg &= ~(VC5_HDMI_DEEP_COLOR_CONFIG_1_INIT_PACK_PHASE_MASK | VC5_HDMI_DEEP_COLOR_CONFIG_1_COLOR_DEPTH_MASK); @@ -1022,7 +1156,7 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder, struct vc4_hdmi_connector_state *vc4_conn_state = conn_state_to_vc4_hdmi_conn_state(conn_state); struct drm_display_mode *mode = &vc4_hdmi->saved_adjusted_mode; - unsigned long pixel_rate = vc4_conn_state->pixel_rate; + unsigned long tmds_char_rate = vc4_conn_state->tmds_char_rate; unsigned long bvb_rate, hsm_rate; unsigned long flags; int ret; @@ -1045,7 +1179,7 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder, * Additionally, the AXI clock needs to be at least 25% of * pixel clock, but HSM ends up being the limiting factor. */ - hsm_rate = max_t(unsigned long, 120000000, (pixel_rate / 100) * 101); + hsm_rate = max_t(unsigned long, 120000000, (tmds_char_rate / 100) * 101); ret = clk_set_min_rate(vc4_hdmi->hsm_clock, hsm_rate); if (ret) { DRM_ERROR("Failed to set HSM clock rate: %d\n", ret); @@ -1058,7 +1192,7 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder, goto out; } - ret = clk_set_rate(vc4_hdmi->pixel_clock, pixel_rate); + ret = clk_set_rate(vc4_hdmi->pixel_clock, tmds_char_rate); if (ret) { DRM_ERROR("Failed to set pixel clock rate: %d\n", ret); goto err_put_runtime_pm; @@ -1073,9 +1207,9 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder, vc4_hdmi_cec_update_clk_div(vc4_hdmi); - if (pixel_rate > 297000000) + if (tmds_char_rate > 297000000) bvb_rate = 300000000; - else if (pixel_rate > 148500000) + else if (tmds_char_rate > 148500000) bvb_rate = 150000000; else bvb_rate = 75000000; @@ -1232,13 +1366,234 @@ static void vc4_hdmi_encoder_atomic_mode_set(struct drm_encoder *encoder, struct drm_connector_state *conn_state) { struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); + struct vc4_hdmi_connector_state *vc4_state = + conn_state_to_vc4_hdmi_conn_state(conn_state); mutex_lock(&vc4_hdmi->mutex); drm_mode_copy(&vc4_hdmi->saved_adjusted_mode, &crtc_state->adjusted_mode); + vc4_hdmi->output_bpc = vc4_state->output_bpc; + vc4_hdmi->output_format = vc4_state->output_format; mutex_unlock(&vc4_hdmi->mutex); } +static bool +vc4_hdmi_sink_supports_format_bpc(const struct vc4_hdmi *vc4_hdmi, + const struct drm_display_info *info, + const struct drm_display_mode *mode, + unsigned int format, unsigned int bpc) +{ + struct drm_device *dev = vc4_hdmi->connector.dev; + u8 vic = drm_match_cea_mode(mode); + + if (vic == 1 && bpc != 8) { + drm_dbg(dev, "VIC1 requires a bpc of 8, got %u\n", bpc); + return false; + } + + if (!info->is_hdmi && + (format != VC4_HDMI_OUTPUT_RGB || bpc != 8)) { + drm_dbg(dev, "DVI Monitors require an RGB output at 8 bpc\n"); + return false; + } + + switch (format) { + case VC4_HDMI_OUTPUT_RGB: + drm_dbg(dev, "RGB Format, checking the constraints.\n"); + + if (!(info->color_formats & DRM_COLOR_FORMAT_RGB444)) + return false; + + if (bpc == 10 && !(info->edid_hdmi_rgb444_dc_modes & DRM_EDID_HDMI_DC_30)) { + drm_dbg(dev, "10 BPC but sink doesn't support Deep Color 30.\n"); + return false; + } + + if (bpc == 12 && !(info->edid_hdmi_rgb444_dc_modes & DRM_EDID_HDMI_DC_36)) { + drm_dbg(dev, "12 BPC but sink doesn't support Deep Color 36.\n"); + return false; + } + + drm_dbg(dev, "RGB format supported in that configuration.\n"); + + return true; + + case VC4_HDMI_OUTPUT_YUV422: + drm_dbg(dev, "YUV422 format, checking the constraints.\n"); + + if (!(info->color_formats & DRM_COLOR_FORMAT_YCBCR422)) { + drm_dbg(dev, "Sink doesn't support YUV422.\n"); + return false; + } + + if (bpc != 12) { + drm_dbg(dev, "YUV422 only supports 12 bpc.\n"); + return false; + } + + drm_dbg(dev, "YUV422 format supported in that configuration.\n"); + + return true; + + case VC4_HDMI_OUTPUT_YUV444: + drm_dbg(dev, "YUV444 format, checking the constraints.\n"); + + if (!(info->color_formats & DRM_COLOR_FORMAT_YCBCR444)) { + drm_dbg(dev, "Sink doesn't support YUV444.\n"); + return false; + } + + if (bpc == 10 && !(info->edid_hdmi_ycbcr444_dc_modes & DRM_EDID_HDMI_DC_30)) { + drm_dbg(dev, "10 BPC but sink doesn't support Deep Color 30.\n"); + return false; + } + + if (bpc == 12 && !(info->edid_hdmi_ycbcr444_dc_modes & DRM_EDID_HDMI_DC_36)) { + drm_dbg(dev, "12 BPC but sink doesn't support Deep Color 36.\n"); + return false; + } + + drm_dbg(dev, "YUV444 format supported in that configuration.\n"); + + return true; + } + + return false; +} + +static enum drm_mode_status +vc4_hdmi_encoder_clock_valid(const struct vc4_hdmi *vc4_hdmi, + unsigned long long clock) +{ + const struct drm_connector *connector = &vc4_hdmi->connector; + const struct drm_display_info *info = &connector->display_info; + + if (clock > vc4_hdmi->variant->max_pixel_clock) + return MODE_CLOCK_HIGH; + + if (vc4_hdmi->disable_4kp60 && clock > HDMI_14_MAX_TMDS_CLK) + return MODE_CLOCK_HIGH; + + if (info->max_tmds_clock && clock > (info->max_tmds_clock * 1000)) + return MODE_CLOCK_HIGH; + + return MODE_OK; +} + +static unsigned long long +vc4_hdmi_encoder_compute_mode_clock(const struct drm_display_mode *mode, + unsigned int bpc, + enum vc4_hdmi_output_format fmt) +{ + unsigned long long clock = mode->clock * 1000; + + if (mode->flags & DRM_MODE_FLAG_DBLCLK) + clock = clock * 2; + + if (fmt == VC4_HDMI_OUTPUT_YUV422) + bpc = 8; + + clock = clock * bpc; + do_div(clock, 8); + + return clock; +} + +static int +vc4_hdmi_encoder_compute_clock(const struct vc4_hdmi *vc4_hdmi, + struct vc4_hdmi_connector_state *vc4_state, + const struct drm_display_mode *mode, + unsigned int bpc, unsigned int fmt) +{ + unsigned long long clock; + + clock = vc4_hdmi_encoder_compute_mode_clock(mode, bpc, fmt); + if (vc4_hdmi_encoder_clock_valid(vc4_hdmi, clock) != MODE_OK) + return -EINVAL; + + vc4_state->tmds_char_rate = clock; + + return 0; +} + +static int +vc4_hdmi_encoder_compute_format(const struct vc4_hdmi *vc4_hdmi, + struct vc4_hdmi_connector_state *vc4_state, + const struct drm_display_mode *mode, + unsigned int bpc) +{ + struct drm_device *dev = vc4_hdmi->connector.dev; + const struct drm_connector *connector = &vc4_hdmi->connector; + const struct drm_display_info *info = &connector->display_info; + unsigned int format; + + drm_dbg(dev, "Trying with an RGB output\n"); + + format = VC4_HDMI_OUTPUT_RGB; + if (vc4_hdmi_sink_supports_format_bpc(vc4_hdmi, info, mode, format, bpc)) { + int ret; + + ret = vc4_hdmi_encoder_compute_clock(vc4_hdmi, vc4_state, + mode, bpc, format); + if (!ret) { + vc4_state->output_format = format; + return 0; + } + } + + drm_dbg(dev, "Failed, Trying with an YUV422 output\n"); + + format = VC4_HDMI_OUTPUT_YUV422; + if (vc4_hdmi_sink_supports_format_bpc(vc4_hdmi, info, mode, format, bpc)) { + int ret; + + ret = vc4_hdmi_encoder_compute_clock(vc4_hdmi, vc4_state, + mode, bpc, format); + if (!ret) { + vc4_state->output_format = format; + return 0; + } + } + + drm_dbg(dev, "Failed. No Format Supported for that bpc count.\n"); + + return -EINVAL; +} + +static int +vc4_hdmi_encoder_compute_config(const struct vc4_hdmi *vc4_hdmi, + struct vc4_hdmi_connector_state *vc4_state, + const struct drm_display_mode *mode) +{ + struct drm_device *dev = vc4_hdmi->connector.dev; + struct drm_connector_state *conn_state = &vc4_state->base; + unsigned int max_bpc = clamp_t(unsigned int, conn_state->max_bpc, 8, 12); + unsigned int bpc; + int ret; + + for (bpc = max_bpc; bpc >= 8; bpc -= 2) { + drm_dbg(dev, "Trying with a %d bpc output\n", bpc); + + ret = vc4_hdmi_encoder_compute_format(vc4_hdmi, vc4_state, + mode, bpc); + if (ret) + continue; + + vc4_state->output_bpc = bpc; + + drm_dbg(dev, + "Mode %ux%u @ %uHz: Found configuration: bpc: %u, fmt: %s, clock: %llu\n", + mode->hdisplay, mode->vdisplay, drm_mode_vrefresh(mode), + vc4_state->output_bpc, + vc4_hdmi_output_fmt_str(vc4_state->output_format), + vc4_state->tmds_char_rate); + + break; + } + + return ret; +} + #define WIFI_2_4GHz_CH1_MIN_FREQ 2400000000ULL #define WIFI_2_4GHz_CH1_MAX_FREQ 2422000000ULL @@ -1249,8 +1604,9 @@ static int vc4_hdmi_encoder_atomic_check(struct drm_encoder *encoder, struct vc4_hdmi_connector_state *vc4_state = conn_state_to_vc4_hdmi_conn_state(conn_state); struct drm_display_mode *mode = &crtc_state->adjusted_mode; struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); - unsigned long long pixel_rate = mode->clock * 1000; - unsigned long long tmds_rate; + unsigned long long tmds_char_rate = mode->clock * 1000; + unsigned long long tmds_bit_rate; + int ret; if (vc4_hdmi->variant->unsupported_odd_h_timings && !(mode->flags & DRM_MODE_FLAG_DBLCLK) && @@ -1264,32 +1620,17 @@ static int vc4_hdmi_encoder_atomic_check(struct drm_encoder *encoder, * bandwidth). Slightly lower the frequency to bring it out of * the WiFi range. */ - tmds_rate = pixel_rate * 10; + tmds_bit_rate = tmds_char_rate * 10; if (vc4_hdmi->disable_wifi_frequencies && - (tmds_rate >= WIFI_2_4GHz_CH1_MIN_FREQ && - tmds_rate <= WIFI_2_4GHz_CH1_MAX_FREQ)) { + (tmds_bit_rate >= WIFI_2_4GHz_CH1_MIN_FREQ && + tmds_bit_rate <= WIFI_2_4GHz_CH1_MAX_FREQ)) { mode->clock = 238560; - pixel_rate = mode->clock * 1000; + tmds_char_rate = mode->clock * 1000; } - if (conn_state->max_bpc == 12) { - pixel_rate = pixel_rate * 150; - do_div(pixel_rate, 100); - } else if (conn_state->max_bpc == 10) { - pixel_rate = pixel_rate * 125; - do_div(pixel_rate, 100); - } - - if (mode->flags & DRM_MODE_FLAG_DBLCLK) - pixel_rate = pixel_rate * 2; - - if (pixel_rate > vc4_hdmi->variant->max_pixel_clock) - return -EINVAL; - - if (vc4_hdmi->disable_4kp60 && (pixel_rate > HDMI_14_MAX_TMDS_CLK)) - return -EINVAL; - - vc4_state->pixel_rate = pixel_rate; + ret = vc4_hdmi_encoder_compute_config(vc4_hdmi, vc4_state, mode); + if (ret) + return ret; return 0; } @@ -1306,13 +1647,7 @@ vc4_hdmi_encoder_mode_valid(struct drm_encoder *encoder, (mode->hsync_end % 2) || (mode->htotal % 2))) return MODE_H_ILLEGAL; - if ((mode->clock * 1000) > vc4_hdmi->variant->max_pixel_clock) - return MODE_CLOCK_HIGH; - - if (vc4_hdmi->disable_4kp60 && vc4_hdmi_mode_needs_scrambling(mode)) - return MODE_CLOCK_HIGH; - - return MODE_OK; + return vc4_hdmi_encoder_clock_valid(vc4_hdmi, mode->clock * 1000); } static const struct drm_encoder_helper_funcs vc4_hdmi_encoder_helper_funcs = { @@ -2568,19 +2903,6 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) } /* - * If we boot without any cable connected to the HDMI connector, - * the firmware will skip the HSM initialization and leave it - * with a rate of 0, resulting in a bus lockup when we're - * accessing the registers even if it's enabled. - * - * Let's put a sensible default at runtime_resume so that we - * don't end up in this situation. - */ - ret = clk_set_min_rate(vc4_hdmi->hsm_clock, HSM_MIN_CLOCK_FREQ); - if (ret) - goto err_put_ddc; - - /* * We need to have the device powered up at this point to call * our reset hook and for the CEC init. */ diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h index 1076faeab616..015a4b7955a0 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.h +++ b/drivers/gpu/drm/vc4/vc4_hdmi.h @@ -121,6 +121,13 @@ struct vc4_hdmi_audio { bool streaming; }; +enum vc4_hdmi_output_format { + VC4_HDMI_OUTPUT_RGB, + VC4_HDMI_OUTPUT_YUV422, + VC4_HDMI_OUTPUT_YUV444, + VC4_HDMI_OUTPUT_YUV420, +}; + /* General HDMI hardware state. */ struct vc4_hdmi { struct vc4_hdmi_audio audio; @@ -220,6 +227,18 @@ struct vc4_hdmi { * the scrambler on? Protected by @mutex. */ bool scdc_enabled; + + /** + * @output_bpc: Copy of @vc4_connector_state.output_bpc for use + * outside of KMS hooks. Protected by @mutex. + */ + unsigned int output_bpc; + + /** + * @output_format: Copy of @vc4_connector_state.output_format + * for use outside of KMS hooks. Protected by @mutex. + */ + enum vc4_hdmi_output_format output_format; }; static inline struct vc4_hdmi * @@ -238,7 +257,9 @@ encoder_to_vc4_hdmi(struct drm_encoder *encoder) struct vc4_hdmi_connector_state { struct drm_connector_state base; - unsigned long long pixel_rate; + unsigned long long tmds_char_rate; + unsigned int output_bpc; + enum vc4_hdmi_output_format output_format; }; static inline struct vc4_hdmi_connector_state * diff --git a/drivers/gpu/drm/vc4/vc4_hdmi_phy.c b/drivers/gpu/drm/vc4/vc4_hdmi_phy.c index 62148f0dc284..ec24999bf96d 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi_phy.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi_phy.c @@ -365,7 +365,7 @@ void vc5_hdmi_phy_init(struct vc4_hdmi *vc4_hdmi, { const struct phy_lane_settings *chan0_settings, *chan1_settings, *chan2_settings, *clock_settings; const struct vc4_hdmi_variant *variant = vc4_hdmi->variant; - unsigned long long pixel_freq = conn_state->pixel_rate; + unsigned long long pixel_freq = conn_state->tmds_char_rate; unsigned long long vco_freq; unsigned char word_sel; unsigned long flags; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi_regs.h b/drivers/gpu/drm/vc4/vc4_hdmi_regs.h index fc971506bd4f..a040356b6bdc 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi_regs.h +++ b/drivers/gpu/drm/vc4/vc4_hdmi_regs.h @@ -54,6 +54,7 @@ enum vc4_hdmi_field { HDMI_CSC_24_23, HDMI_CSC_32_31, HDMI_CSC_34_33, + HDMI_CSC_CHANNEL_CTL, HDMI_CSC_CTL, /* @@ -119,6 +120,7 @@ enum vc4_hdmi_field { HDMI_TX_PHY_POWERDOWN_CTL, HDMI_TX_PHY_RESET_CTL, HDMI_TX_PHY_TMDS_CLK_WORD_SEL, + HDMI_VEC_INTERFACE_CFG, HDMI_VEC_INTERFACE_XBAR, HDMI_VERTA0, HDMI_VERTA1, @@ -244,6 +246,7 @@ static const struct vc4_hdmi_register __maybe_unused vc5_hdmi_hdmi0_fields[] = { VC4_HDMI_REG(HDMI_SCRAMBLER_CTL, 0x1c4), VC5_DVP_REG(HDMI_CLOCK_STOP, 0x0bc), + VC5_DVP_REG(HDMI_VEC_INTERFACE_CFG, 0x0ec), VC5_DVP_REG(HDMI_VEC_INTERFACE_XBAR, 0x0f0), VC5_PHY_REG(HDMI_TX_PHY_RESET_CTL, 0x000), @@ -289,6 +292,7 @@ static const struct vc4_hdmi_register __maybe_unused vc5_hdmi_hdmi0_fields[] = { VC5_CSC_REG(HDMI_CSC_24_23, 0x010), VC5_CSC_REG(HDMI_CSC_32_31, 0x014), VC5_CSC_REG(HDMI_CSC_34_33, 0x018), + VC5_CSC_REG(HDMI_CSC_CHANNEL_CTL, 0x02c), }; static const struct vc4_hdmi_register __maybe_unused vc5_hdmi_hdmi1_fields[] = { @@ -324,6 +328,7 @@ static const struct vc4_hdmi_register __maybe_unused vc5_hdmi_hdmi1_fields[] = { VC4_HDMI_REG(HDMI_SCRAMBLER_CTL, 0x1c4), VC5_DVP_REG(HDMI_CLOCK_STOP, 0x0bc), + VC5_DVP_REG(HDMI_VEC_INTERFACE_CFG, 0x0ec), VC5_DVP_REG(HDMI_VEC_INTERFACE_XBAR, 0x0f0), VC5_PHY_REG(HDMI_TX_PHY_RESET_CTL, 0x000), @@ -369,6 +374,7 @@ static const struct vc4_hdmi_register __maybe_unused vc5_hdmi_hdmi1_fields[] = { VC5_CSC_REG(HDMI_CSC_24_23, 0x010), VC5_CSC_REG(HDMI_CSC_32_31, 0x014), VC5_CSC_REG(HDMI_CSC_34_33, 0x018), + VC5_CSC_REG(HDMI_CSC_CHANNEL_CTL, 0x02c), }; static inline diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c index 604933e20e6a..2a58fc421cf6 100644 --- a/drivers/gpu/drm/vc4/vc4_hvs.c +++ b/drivers/gpu/drm/vc4/vc4_hvs.c @@ -64,22 +64,21 @@ static const struct debugfs_reg32 hvs_regs[] = { VC4_REG32(SCALER_OLEDCOEF2), }; -void vc4_hvs_dump_state(struct drm_device *dev) +void vc4_hvs_dump_state(struct vc4_hvs *hvs) { - struct vc4_dev *vc4 = to_vc4_dev(dev); - struct drm_printer p = drm_info_printer(&vc4->hvs->pdev->dev); + struct drm_printer p = drm_info_printer(&hvs->pdev->dev); int i; - drm_print_regset32(&p, &vc4->hvs->regset); + drm_print_regset32(&p, &hvs->regset); DRM_INFO("HVS ctx:\n"); for (i = 0; i < 64; i += 4) { DRM_INFO("0x%08x (%s): 0x%08x 0x%08x 0x%08x 0x%08x\n", i * 4, i < HVS_BOOTLOADER_DLIST_END ? "B" : "D", - readl((u32 __iomem *)vc4->hvs->dlist + i + 0), - readl((u32 __iomem *)vc4->hvs->dlist + i + 1), - readl((u32 __iomem *)vc4->hvs->dlist + i + 2), - readl((u32 __iomem *)vc4->hvs->dlist + i + 3)); + readl((u32 __iomem *)hvs->dlist + i + 0), + readl((u32 __iomem *)hvs->dlist + i + 1), + readl((u32 __iomem *)hvs->dlist + i + 2), + readl((u32 __iomem *)hvs->dlist + i + 3)); } } @@ -157,11 +156,10 @@ static int vc4_hvs_upload_linear_kernel(struct vc4_hvs *hvs, return 0; } -static void vc4_hvs_lut_load(struct drm_crtc *crtc) +static void vc4_hvs_lut_load(struct vc4_hvs *hvs, + struct vc4_crtc *vc4_crtc) { - struct drm_device *dev = crtc->dev; - struct vc4_dev *vc4 = to_vc4_dev(dev); - struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); + struct drm_crtc *crtc = &vc4_crtc->base; struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state); u32 i; @@ -181,11 +179,12 @@ static void vc4_hvs_lut_load(struct drm_crtc *crtc) HVS_WRITE(SCALER_GAMDATA, vc4_crtc->lut_b[i]); } -static void vc4_hvs_update_gamma_lut(struct drm_crtc *crtc) +static void vc4_hvs_update_gamma_lut(struct vc4_hvs *hvs, + struct vc4_crtc *vc4_crtc) { - struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); - struct drm_color_lut *lut = crtc->state->gamma_lut->data; - u32 length = drm_color_lut_size(crtc->state->gamma_lut); + struct drm_crtc_state *crtc_state = vc4_crtc->base.state; + struct drm_color_lut *lut = crtc_state->gamma_lut->data; + u32 length = drm_color_lut_size(crtc_state->gamma_lut); u32 i; for (i = 0; i < length; i++) { @@ -194,16 +193,37 @@ static void vc4_hvs_update_gamma_lut(struct drm_crtc *crtc) vc4_crtc->lut_b[i] = drm_color_lut_extract(lut[i].blue, 8); } - vc4_hvs_lut_load(crtc); + vc4_hvs_lut_load(hvs, vc4_crtc); } -int vc4_hvs_get_fifo_from_output(struct drm_device *dev, unsigned int output) +u8 vc4_hvs_get_fifo_frame_count(struct vc4_hvs *hvs, unsigned int fifo) +{ + u8 field = 0; + + switch (fifo) { + case 0: + field = VC4_GET_FIELD(HVS_READ(SCALER_DISPSTAT1), + SCALER_DISPSTAT1_FRCNT0); + break; + case 1: + field = VC4_GET_FIELD(HVS_READ(SCALER_DISPSTAT1), + SCALER_DISPSTAT1_FRCNT1); + break; + case 2: + field = VC4_GET_FIELD(HVS_READ(SCALER_DISPSTAT2), + SCALER_DISPSTAT2_FRCNT2); + break; + } + + return field; +} + +int vc4_hvs_get_fifo_from_output(struct vc4_hvs *hvs, unsigned int output) { - struct vc4_dev *vc4 = to_vc4_dev(dev); u32 reg; int ret; - if (!vc4->hvs->hvs5) + if (!hvs->hvs5) return output; switch (output) { @@ -250,9 +270,10 @@ int vc4_hvs_get_fifo_from_output(struct drm_device *dev, unsigned int output) } } -static int vc4_hvs_init_channel(struct vc4_dev *vc4, struct drm_crtc *crtc, +static int vc4_hvs_init_channel(struct vc4_hvs *hvs, struct drm_crtc *crtc, struct drm_display_mode *mode, bool oneshot) { + struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); struct vc4_crtc_state *vc4_crtc_state = to_vc4_crtc_state(crtc->state); unsigned int chan = vc4_crtc_state->assigned_channel; bool interlace = mode->flags & DRM_MODE_FLAG_INTERLACE; @@ -270,7 +291,7 @@ static int vc4_hvs_init_channel(struct vc4_dev *vc4, struct drm_crtc *crtc, */ dispctrl = SCALER_DISPCTRLX_ENABLE; - if (!vc4->hvs->hvs5) + if (!hvs->hvs5) dispctrl |= VC4_SET_FIELD(mode->hdisplay, SCALER_DISPCTRLX_WIDTH) | VC4_SET_FIELD(mode->vdisplay, @@ -291,21 +312,19 @@ static int vc4_hvs_init_channel(struct vc4_dev *vc4, struct drm_crtc *crtc, HVS_WRITE(SCALER_DISPBKGNDX(chan), dispbkgndx | SCALER_DISPBKGND_AUTOHS | - ((!vc4->hvs->hvs5) ? SCALER_DISPBKGND_GAMMA : 0) | + ((!hvs->hvs5) ? SCALER_DISPBKGND_GAMMA : 0) | (interlace ? SCALER_DISPBKGND_INTERLACE : 0)); /* Reload the LUT, since the SRAMs would have been disabled if * all CRTCs had SCALER_DISPBKGND_GAMMA unset at once. */ - vc4_hvs_lut_load(crtc); + vc4_hvs_lut_load(hvs, vc4_crtc); return 0; } -void vc4_hvs_stop_channel(struct drm_device *dev, unsigned int chan) +void vc4_hvs_stop_channel(struct vc4_hvs *hvs, unsigned int chan) { - struct vc4_dev *vc4 = to_vc4_dev(dev); - if (HVS_READ(SCALER_DISPCTRLX(chan)) & SCALER_DISPCTRLX_ENABLE) return; @@ -359,10 +378,20 @@ int vc4_hvs_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state) return 0; } -static void vc4_hvs_update_dlist(struct drm_crtc *crtc) +static void vc4_hvs_install_dlist(struct drm_crtc *crtc) { struct drm_device *dev = crtc->dev; struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_hvs *hvs = vc4->hvs; + struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state); + + HVS_WRITE(SCALER_DISPLISTX(vc4_state->assigned_channel), + vc4_state->mm.start); +} + +static void vc4_hvs_update_dlist(struct drm_crtc *crtc) +{ + struct drm_device *dev = crtc->dev; struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state); unsigned long flags; @@ -379,13 +408,7 @@ static void vc4_hvs_update_dlist(struct drm_crtc *crtc) crtc->state->event = NULL; } - HVS_WRITE(SCALER_DISPLISTX(vc4_state->assigned_channel), - vc4_state->mm.start); - spin_unlock_irqrestore(&dev->event_lock, flags); - } else { - HVS_WRITE(SCALER_DISPLISTX(vc4_state->assigned_channel), - vc4_state->mm.start); } spin_lock_irqsave(&vc4_crtc->irq_lock, flags); @@ -414,19 +437,21 @@ void vc4_hvs_atomic_enable(struct drm_crtc *crtc, struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); bool oneshot = vc4_crtc->feeds_txp; + vc4_hvs_install_dlist(crtc); vc4_hvs_update_dlist(crtc); - vc4_hvs_init_channel(vc4, crtc, mode, oneshot); + vc4_hvs_init_channel(vc4->hvs, crtc, mode, oneshot); } void vc4_hvs_atomic_disable(struct drm_crtc *crtc, struct drm_atomic_state *state) { struct drm_device *dev = crtc->dev; + struct vc4_dev *vc4 = to_vc4_dev(dev); struct drm_crtc_state *old_state = drm_atomic_get_old_crtc_state(state, crtc); struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(old_state); unsigned int chan = vc4_state->assigned_channel; - vc4_hvs_stop_channel(dev, chan); + vc4_hvs_stop_channel(vc4->hvs, chan); } void vc4_hvs_atomic_flush(struct drm_crtc *crtc, @@ -436,7 +461,10 @@ void vc4_hvs_atomic_flush(struct drm_crtc *crtc, crtc); struct drm_device *dev = crtc->dev; struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_hvs *hvs = vc4->hvs; + struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state); + unsigned int channel = vc4_state->assigned_channel; struct drm_plane *plane; struct vc4_plane_state *vc4_plane_state; bool debug_dump_regs = false; @@ -446,7 +474,7 @@ void vc4_hvs_atomic_flush(struct drm_crtc *crtc, if (debug_dump_regs) { DRM_INFO("CRTC %d HVS before:\n", drm_crtc_index(crtc)); - vc4_hvs_dump_state(dev); + vc4_hvs_dump_state(hvs); } /* Copy all the active planes' dlist contents to the hardware dlist. */ @@ -477,8 +505,8 @@ void vc4_hvs_atomic_flush(struct drm_crtc *crtc, /* This sets a black background color fill, as is the case * with other DRM drivers. */ - HVS_WRITE(SCALER_DISPBKGNDX(vc4_state->assigned_channel), - HVS_READ(SCALER_DISPBKGNDX(vc4_state->assigned_channel)) | + HVS_WRITE(SCALER_DISPBKGNDX(channel), + HVS_READ(SCALER_DISPBKGNDX(channel)) | SCALER_DISPBKGND_FILL); /* Only update DISPLIST if the CRTC was already running and is not @@ -488,14 +516,16 @@ void vc4_hvs_atomic_flush(struct drm_crtc *crtc, * If the CRTC is being disabled, there's no point in updating this * information. */ - if (crtc->state->active && old_state->active) + if (crtc->state->active && old_state->active) { + vc4_hvs_install_dlist(crtc); vc4_hvs_update_dlist(crtc); + } if (crtc->state->color_mgmt_changed) { - u32 dispbkgndx = HVS_READ(SCALER_DISPBKGNDX(vc4_state->assigned_channel)); + u32 dispbkgndx = HVS_READ(SCALER_DISPBKGNDX(channel)); if (crtc->state->gamma_lut) { - vc4_hvs_update_gamma_lut(crtc); + vc4_hvs_update_gamma_lut(hvs, vc4_crtc); dispbkgndx |= SCALER_DISPBKGND_GAMMA; } else { /* Unsetting DISPBKGND_GAMMA skips the gamma lut step @@ -504,18 +534,17 @@ void vc4_hvs_atomic_flush(struct drm_crtc *crtc, */ dispbkgndx &= ~SCALER_DISPBKGND_GAMMA; } - HVS_WRITE(SCALER_DISPBKGNDX(vc4_state->assigned_channel), dispbkgndx); + HVS_WRITE(SCALER_DISPBKGNDX(channel), dispbkgndx); } if (debug_dump_regs) { DRM_INFO("CRTC %d HVS after:\n", drm_crtc_index(crtc)); - vc4_hvs_dump_state(dev); + vc4_hvs_dump_state(hvs); } } -void vc4_hvs_mask_underrun(struct drm_device *dev, int channel) +void vc4_hvs_mask_underrun(struct vc4_hvs *hvs, int channel) { - struct vc4_dev *vc4 = to_vc4_dev(dev); u32 dispctrl = HVS_READ(SCALER_DISPCTRL); dispctrl &= ~SCALER_DISPCTRL_DSPEISLUR(channel); @@ -523,9 +552,8 @@ void vc4_hvs_mask_underrun(struct drm_device *dev, int channel) HVS_WRITE(SCALER_DISPCTRL, dispctrl); } -void vc4_hvs_unmask_underrun(struct drm_device *dev, int channel) +void vc4_hvs_unmask_underrun(struct vc4_hvs *hvs, int channel) { - struct vc4_dev *vc4 = to_vc4_dev(dev); u32 dispctrl = HVS_READ(SCALER_DISPCTRL); dispctrl |= SCALER_DISPCTRL_DSPEISLUR(channel); @@ -547,6 +575,7 @@ static irqreturn_t vc4_hvs_irq_handler(int irq, void *data) { struct drm_device *dev = data; struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_hvs *hvs = vc4->hvs; irqreturn_t irqret = IRQ_NONE; int channel; u32 control; @@ -559,7 +588,7 @@ static irqreturn_t vc4_hvs_irq_handler(int irq, void *data) /* Interrupt masking is not always honored, so check it here. */ if (status & SCALER_DISPSTAT_EUFLOW(channel) && control & SCALER_DISPCTRL_DSPEISLUR(channel)) { - vc4_hvs_mask_underrun(dev, channel); + vc4_hvs_mask_underrun(hvs, channel); vc4_hvs_report_underrun(dev); irqret = IRQ_HANDLED; @@ -582,6 +611,7 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data) struct vc4_hvs *hvs = NULL; int ret; u32 dispctrl; + u32 reg; hvs = devm_kzalloc(&pdev->dev, sizeof(*hvs), GFP_KERNEL); if (!hvs) @@ -653,6 +683,26 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data) vc4->hvs = hvs; + reg = HVS_READ(SCALER_DISPECTRL); + reg &= ~SCALER_DISPECTRL_DSP2_MUX_MASK; + HVS_WRITE(SCALER_DISPECTRL, + reg | VC4_SET_FIELD(0, SCALER_DISPECTRL_DSP2_MUX)); + + reg = HVS_READ(SCALER_DISPCTRL); + reg &= ~SCALER_DISPCTRL_DSP3_MUX_MASK; + HVS_WRITE(SCALER_DISPCTRL, + reg | VC4_SET_FIELD(3, SCALER_DISPCTRL_DSP3_MUX)); + + reg = HVS_READ(SCALER_DISPEOLN); + reg &= ~SCALER_DISPEOLN_DSP4_MUX_MASK; + HVS_WRITE(SCALER_DISPEOLN, + reg | VC4_SET_FIELD(3, SCALER_DISPEOLN_DSP4_MUX)); + + reg = HVS_READ(SCALER_DISPDITHER); + reg &= ~SCALER_DISPDITHER_DSP5_MUX_MASK; + HVS_WRITE(SCALER_DISPDITHER, + reg | VC4_SET_FIELD(3, SCALER_DISPDITHER_DSP5_MUX)); + dispctrl = HVS_READ(SCALER_DISPCTRL); dispctrl |= SCALER_DISPCTRL_ENABLE; @@ -660,10 +710,6 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data) SCALER_DISPCTRL_DISPEIRQ(1) | SCALER_DISPCTRL_DISPEIRQ(2); - /* Set DSP3 (PV1) to use HVS channel 2, which would otherwise - * be unused. - */ - dispctrl &= ~SCALER_DISPCTRL_DSP3_MUX_MASK; dispctrl &= ~(SCALER_DISPCTRL_DMAEIRQ | SCALER_DISPCTRL_SLVWREIRQ | SCALER_DISPCTRL_SLVRDEIRQ | @@ -677,7 +723,6 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data) SCALER_DISPCTRL_DSPEISLUR(1) | SCALER_DISPCTRL_DSPEISLUR(2) | SCALER_DISPCTRL_SCLEIRQ); - dispctrl |= VC4_SET_FIELD(2, SCALER_DISPCTRL_DSP3_MUX); HVS_WRITE(SCALER_DISPCTRL, dispctrl); diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c index 20fa8e34c20b..4342fb43e8c1 100644 --- a/drivers/gpu/drm/vc4/vc4_irq.c +++ b/drivers/gpu/drm/vc4/vc4_irq.c @@ -51,6 +51,7 @@ #include "vc4_drv.h" #include "vc4_regs.h" +#include "vc4_trace.h" #define V3D_DRIVER_IRQS (V3D_INT_OUTOMEM | \ V3D_INT_FLDONE | \ @@ -123,6 +124,8 @@ vc4_irq_finish_bin_job(struct drm_device *dev) if (!exec) return; + trace_vc4_bcl_end_irq(dev, exec->seqno); + vc4_move_job_to_render(dev, exec); next = vc4_first_bin_job(vc4); @@ -161,6 +164,8 @@ vc4_irq_finish_render_job(struct drm_device *dev) if (!exec) return; + trace_vc4_rcl_end_irq(dev, exec->seqno); + vc4->finished_seqno++; list_move_tail(&exec->head, &vc4->job_done_list); diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index 24de29bc1cda..c169bd72e53b 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -32,7 +32,8 @@ struct vc4_ctm_state { int fifo; }; -static struct vc4_ctm_state *to_vc4_ctm_state(struct drm_private_state *priv) +static struct vc4_ctm_state * +to_vc4_ctm_state(const struct drm_private_state *priv) { return container_of(priv, struct vc4_ctm_state, base); } @@ -49,7 +50,7 @@ struct vc4_hvs_state { }; static struct vc4_hvs_state * -to_vc4_hvs_state(struct drm_private_state *priv) +to_vc4_hvs_state(const struct drm_private_state *priv) { return container_of(priv, struct vc4_hvs_state, base); } @@ -61,7 +62,7 @@ struct vc4_load_tracker_state { }; static struct vc4_load_tracker_state * -to_vc4_load_tracker_state(struct drm_private_state *priv) +to_vc4_load_tracker_state(const struct drm_private_state *priv) { return container_of(priv, struct vc4_load_tracker_state, base); } @@ -157,6 +158,7 @@ static u16 vc4_ctm_s31_32_to_s0_9(u64 in) static void vc4_ctm_commit(struct vc4_dev *vc4, struct drm_atomic_state *state) { + struct vc4_hvs *hvs = vc4->hvs; struct vc4_ctm_state *ctm_state = to_vc4_ctm_state(vc4->ctm_manager.state); struct drm_color_ctm *ctm = ctm_state->ctm; @@ -230,6 +232,7 @@ vc4_hvs_get_global_state(struct drm_atomic_state *state) static void vc4_hvs_pv_muxing_commit(struct vc4_dev *vc4, struct drm_atomic_state *state) { + struct vc4_hvs *hvs = vc4->hvs; struct drm_crtc_state *crtc_state; struct drm_crtc *crtc; unsigned int i; @@ -270,6 +273,7 @@ static void vc4_hvs_pv_muxing_commit(struct vc4_dev *vc4, static void vc5_hvs_pv_muxing_commit(struct vc4_dev *vc4, struct drm_atomic_state *state) { + struct vc4_hvs *hvs = vc4->hvs; struct drm_crtc_state *crtc_state; struct drm_crtc *crtc; unsigned char mux; @@ -279,13 +283,18 @@ static void vc5_hvs_pv_muxing_commit(struct vc4_dev *vc4, for_each_new_crtc_in_state(state, crtc, crtc_state, i) { struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc_state); struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc); + unsigned int channel = vc4_state->assigned_channel; if (!vc4_state->update_muxing) continue; switch (vc4_crtc->data->hvs_output) { case 2: - mux = (vc4_state->assigned_channel == 2) ? 0 : 1; + drm_WARN_ON(&vc4->base, + VC4_GET_FIELD(HVS_READ(SCALER_DISPCTRL), + SCALER_DISPCTRL_DSP3_MUX) == channel); + + mux = (channel == 2) ? 0 : 1; reg = HVS_READ(SCALER_DISPECTRL); HVS_WRITE(SCALER_DISPECTRL, (reg & ~SCALER_DISPECTRL_DSP2_MUX_MASK) | @@ -293,10 +302,10 @@ static void vc5_hvs_pv_muxing_commit(struct vc4_dev *vc4, break; case 3: - if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED) + if (channel == VC4_HVS_CHANNEL_DISABLED) mux = 3; else - mux = vc4_state->assigned_channel; + mux = channel; reg = HVS_READ(SCALER_DISPCTRL); HVS_WRITE(SCALER_DISPCTRL, @@ -305,10 +314,10 @@ static void vc5_hvs_pv_muxing_commit(struct vc4_dev *vc4, break; case 4: - if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED) + if (channel == VC4_HVS_CHANNEL_DISABLED) mux = 3; else - mux = vc4_state->assigned_channel; + mux = channel; reg = HVS_READ(SCALER_DISPEOLN); HVS_WRITE(SCALER_DISPEOLN, @@ -318,10 +327,10 @@ static void vc5_hvs_pv_muxing_commit(struct vc4_dev *vc4, break; case 5: - if (vc4_state->assigned_channel == VC4_HVS_CHANNEL_DISABLED) + if (channel == VC4_HVS_CHANNEL_DISABLED) mux = 3; else - mux = vc4_state->assigned_channel; + mux = channel; reg = HVS_READ(SCALER_DISPDITHER); HVS_WRITE(SCALER_DISPDITHER, @@ -362,7 +371,7 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state) continue; vc4_crtc_state = to_vc4_crtc_state(new_crtc_state); - vc4_hvs_mask_underrun(dev, vc4_crtc_state->assigned_channel); + vc4_hvs_mask_underrun(hvs, vc4_crtc_state->assigned_channel); } for (channel = 0; channel < HVS_NUM_CHANNELS; channel++) { @@ -385,12 +394,20 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state) } if (vc4->hvs->hvs5) { + unsigned long state_rate = max(old_hvs_state->core_clock_rate, + new_hvs_state->core_clock_rate); unsigned long core_rate = max_t(unsigned long, - 500000000, - new_hvs_state->core_clock_rate); + 500000000, state_rate); + drm_dbg(dev, "Raising the core clock at %lu Hz\n", core_rate); + + /* + * Do a temporary request on the core clock during the + * modeset. + */ clk_set_min_rate(hvs->core_clk, core_rate); } + drm_atomic_helper_commit_modeset_disables(dev, state); vc4_ctm_commit(vc4, state); @@ -400,7 +417,8 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state) else vc4_hvs_pv_muxing_commit(vc4, state); - drm_atomic_helper_commit_planes(dev, state, 0); + drm_atomic_helper_commit_planes(dev, state, + DRM_PLANE_COMMIT_ACTIVE_ONLY); drm_atomic_helper_commit_modeset_enables(dev, state); @@ -416,7 +434,14 @@ static void vc4_atomic_commit_tail(struct drm_atomic_state *state) drm_dbg(dev, "Running the core clock at %lu Hz\n", new_hvs_state->core_clock_rate); + /* + * Request a clock rate based on the current HVS + * requirements. + */ clk_set_min_rate(hvs->core_clk, new_hvs_state->core_clock_rate); + + drm_dbg(dev, "Core clock actual rate: %lu Hz\n", + clk_get_rate(hvs->core_clk)); } } @@ -700,9 +725,26 @@ static void vc4_hvs_channels_destroy_state(struct drm_private_obj *obj, kfree(hvs_state); } +static void vc4_hvs_channels_print_state(struct drm_printer *p, + const struct drm_private_state *state) +{ + struct vc4_hvs_state *hvs_state = to_vc4_hvs_state(state); + unsigned int i; + + drm_printf(p, "HVS State\n"); + drm_printf(p, "\tCore Clock Rate: %lu\n", hvs_state->core_clock_rate); + + for (i = 0; i < HVS_NUM_CHANNELS; i++) { + drm_printf(p, "\tChannel %d\n", i); + drm_printf(p, "\t\tin use=%d\n", hvs_state->fifo_state[i].in_use); + drm_printf(p, "\t\tload=%lu\n", hvs_state->fifo_state[i].fifo_load); + } +} + static const struct drm_private_state_funcs vc4_hvs_state_funcs = { .atomic_duplicate_state = vc4_hvs_channels_duplicate_state, .atomic_destroy_state = vc4_hvs_channels_destroy_state, + .atomic_print_state = vc4_hvs_channels_print_state, }; static void vc4_hvs_channels_obj_fini(struct drm_device *dev, void *unused) @@ -783,9 +825,18 @@ static int vc4_pv_muxing_atomic_check(struct drm_device *dev, unsigned int matching_channels; unsigned int channel; + drm_dbg(dev, "%s: Trying to find a channel.\n", crtc->name); + /* Nothing to do here, let's skip it */ - if (old_crtc_state->enable == new_crtc_state->enable) + if (old_crtc_state->enable == new_crtc_state->enable) { + if (new_crtc_state->enable) + drm_dbg(dev, "%s: Already enabled, reusing channel %d.\n", + crtc->name, new_vc4_crtc_state->assigned_channel); + else + drm_dbg(dev, "%s: Disabled, ignoring.\n", crtc->name); + continue; + } /* Muxing will need to be modified, mark it as such */ new_vc4_crtc_state->update_muxing = true; @@ -793,6 +844,10 @@ static int vc4_pv_muxing_atomic_check(struct drm_device *dev, /* If we're disabling our CRTC, we put back our channel */ if (!new_crtc_state->enable) { channel = old_vc4_crtc_state->assigned_channel; + + drm_dbg(dev, "%s: Disabling, Freeing channel %d\n", + crtc->name, channel); + hvs_new_state->fifo_state[channel].in_use = false; new_vc4_crtc_state->assigned_channel = VC4_HVS_CHANNEL_DISABLED; continue; @@ -827,6 +882,8 @@ static int vc4_pv_muxing_atomic_check(struct drm_device *dev, return -EINVAL; channel = ffs(matching_channels) - 1; + + drm_dbg(dev, "Assigned HVS channel %d to CRTC %s\n", channel, crtc->name); new_vc4_crtc_state->assigned_channel = channel; unassigned_channels &= ~BIT(channel); hvs_new_state->fifo_state[channel].in_use = true; diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h index 33410718089e..a2b5cbbbc1b0 100644 --- a/drivers/gpu/drm/vc4/vc4_regs.h +++ b/drivers/gpu/drm/vc4/vc4_regs.h @@ -379,8 +379,6 @@ # define SCALER_DISPSTATX_MODE_EOF 3 # define SCALER_DISPSTATX_FULL BIT(29) # define SCALER_DISPSTATX_EMPTY BIT(28) -# define SCALER_DISPSTATX_FRAME_COUNT_MASK VC4_MASK(17, 12) -# define SCALER_DISPSTATX_FRAME_COUNT_SHIFT 12 # define SCALER_DISPSTATX_LINE_MASK VC4_MASK(11, 0) # define SCALER_DISPSTATX_LINE_SHIFT 0 @@ -403,9 +401,15 @@ (x) * (SCALER_DISPBKGND1 - \ SCALER_DISPBKGND0)) #define SCALER_DISPSTAT1 0x00000058 +# define SCALER_DISPSTAT1_FRCNT0_MASK VC4_MASK(23, 18) +# define SCALER_DISPSTAT1_FRCNT0_SHIFT 18 +# define SCALER_DISPSTAT1_FRCNT1_MASK VC4_MASK(17, 12) +# define SCALER_DISPSTAT1_FRCNT1_SHIFT 12 + #define SCALER_DISPSTATX(x) (SCALER_DISPSTAT0 + \ (x) * (SCALER_DISPSTAT1 - \ SCALER_DISPSTAT0)) + #define SCALER_DISPBASE1 0x0000005c #define SCALER_DISPBASEX(x) (SCALER_DISPBASE0 + \ (x) * (SCALER_DISPBASE1 - \ @@ -415,7 +419,11 @@ (x) * (SCALER_DISPCTRL1 - \ SCALER_DISPCTRL0)) #define SCALER_DISPBKGND2 0x00000064 + #define SCALER_DISPSTAT2 0x00000068 +# define SCALER_DISPSTAT2_FRCNT2_MASK VC4_MASK(17, 12) +# define SCALER_DISPSTAT2_FRCNT2_SHIFT 12 + #define SCALER_DISPBASE2 0x0000006c #define SCALER_DISPALPHA2 0x00000070 #define SCALER_GAMADDR 0x00000078 @@ -774,11 +782,27 @@ enum { # define VC4_HD_CSC_CTL_RGB2YCC BIT(1) # define VC4_HD_CSC_CTL_ENABLE BIT(0) +# define VC5_MT_CP_CSC_CTL_USE_444_TO_422 BIT(6) +# define VC5_MT_CP_CSC_CTL_FILTER_MODE_444_TO_422_MASK \ + VC4_MASK(5, 4) +# define VC5_MT_CP_CSC_CTL_FILTER_MODE_444_TO_422_STANDARD \ + 3 +# define VC5_MT_CP_CSC_CTL_USE_RNG_SUPPRESSION BIT(3) # define VC5_MT_CP_CSC_CTL_ENABLE BIT(2) # define VC5_MT_CP_CSC_CTL_MODE_MASK VC4_MASK(1, 0) +# define VC5_MT_CP_CHANNEL_CTL_OUTPUT_REMAP_MASK \ + VC4_MASK(7, 6) +# define VC5_MT_CP_CHANNEL_CTL_OUTPUT_REMAP_LEGACY_STYLE \ + 2 + # define VC4_DVP_HT_CLOCK_STOP_PIXEL BIT(1) +# define VC5_DVP_HT_VEC_INTERFACE_CFG_SEL_422_MASK \ + VC4_MASK(3, 2) +# define VC5_DVP_HT_VEC_INTERFACE_CFG_SEL_422_FORMAT_422_LEGACY \ + 2 + /* HVS display list information. */ #define HVS_BOOTLOADER_DLIST_END 32 diff --git a/drivers/gpu/drm/vc4/vc4_trace.h b/drivers/gpu/drm/vc4/vc4_trace.h index 1cccde0b09a7..7f4c49e7e011 100644 --- a/drivers/gpu/drm/vc4/vc4_trace.h +++ b/drivers/gpu/drm/vc4/vc4_trace.h @@ -52,6 +52,101 @@ TRACE_EVENT(vc4_wait_for_seqno_end, __entry->dev, __entry->seqno) ); +TRACE_EVENT(vc4_submit_cl_ioctl, + TP_PROTO(struct drm_device *dev, u32 bin_cl_size, u32 shader_rec_size, u32 bo_count), + TP_ARGS(dev, bin_cl_size, shader_rec_size, bo_count), + + TP_STRUCT__entry( + __field(u32, dev) + __field(u32, bin_cl_size) + __field(u32, shader_rec_size) + __field(u32, bo_count) + ), + + TP_fast_assign( + __entry->dev = dev->primary->index; + __entry->bin_cl_size = bin_cl_size; + __entry->shader_rec_size = shader_rec_size; + __entry->bo_count = bo_count; + ), + + TP_printk("dev=%u, bin_cl_size=%u, shader_rec_size=%u, bo_count=%u", + __entry->dev, + __entry->bin_cl_size, + __entry->shader_rec_size, + __entry->bo_count) +); + +TRACE_EVENT(vc4_submit_cl, + TP_PROTO(struct drm_device *dev, bool is_render, + uint64_t seqno, + u32 ctnqba, u32 ctnqea), + TP_ARGS(dev, is_render, seqno, ctnqba, ctnqea), + + TP_STRUCT__entry( + __field(u32, dev) + __field(bool, is_render) + __field(u64, seqno) + __field(u32, ctnqba) + __field(u32, ctnqea) + ), + + TP_fast_assign( + __entry->dev = dev->primary->index; + __entry->is_render = is_render; + __entry->seqno = seqno; + __entry->ctnqba = ctnqba; + __entry->ctnqea = ctnqea; + ), + + TP_printk("dev=%u, %s, seqno=%llu, 0x%08x..0x%08x", + __entry->dev, + __entry->is_render ? "RCL" : "BCL", + __entry->seqno, + __entry->ctnqba, + __entry->ctnqea) +); + +TRACE_EVENT(vc4_bcl_end_irq, + TP_PROTO(struct drm_device *dev, + uint64_t seqno), + TP_ARGS(dev, seqno), + + TP_STRUCT__entry( + __field(u32, dev) + __field(u64, seqno) + ), + + TP_fast_assign( + __entry->dev = dev->primary->index; + __entry->seqno = seqno; + ), + + TP_printk("dev=%u, seqno=%llu", + __entry->dev, + __entry->seqno) +); + +TRACE_EVENT(vc4_rcl_end_irq, + TP_PROTO(struct drm_device *dev, + uint64_t seqno), + TP_ARGS(dev, seqno), + + TP_STRUCT__entry( + __field(u32, dev) + __field(u64, seqno) + ), + + TP_fast_assign( + __entry->dev = dev->primary->index; + __entry->seqno = seqno; + ), + + TP_printk("dev=%u, seqno=%llu", + __entry->dev, + __entry->seqno) +); + #endif /* _VC4_TRACE_H_ */ /* This part must be outside protection */ diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c index 9809ca3e2945..82beb8c159f2 100644 --- a/drivers/gpu/drm/vc4/vc4_txp.c +++ b/drivers/gpu/drm/vc4/vc4_txp.c @@ -298,12 +298,18 @@ static void vc4_txp_connector_atomic_commit(struct drm_connector *conn, if (WARN_ON(i == ARRAY_SIZE(drm_fmts))) return; - ctrl = TXP_GO | TXP_VSTART_AT_EOF | TXP_EI | + ctrl = TXP_GO | TXP_EI | VC4_SET_FIELD(0xf, TXP_BYTE_ENABLE) | VC4_SET_FIELD(txp_fmts[i], TXP_FORMAT); if (fb->format->has_alpha) ctrl |= TXP_ALPHA_ENABLE; + else + /* + * If TXP_ALPHA_ENABLE isn't set and TXP_ALPHA_INVERT is, the + * hardware will force the output padding to be 0xff. + */ + ctrl |= TXP_ALPHA_INVERT; gem = drm_fb_cma_get_gem_obj(fb, 0); TXP_WRITE(TXP_DST_PTR, gem->paddr + fb->offsets[0]); diff --git a/drivers/gpu/drm/vgem/vgem_fence.c b/drivers/gpu/drm/vgem/vgem_fence.c index bd6f75285fd9..c2a879734d40 100644 --- a/drivers/gpu/drm/vgem/vgem_fence.c +++ b/drivers/gpu/drm/vgem/vgem_fence.c @@ -130,6 +130,7 @@ int vgem_fence_attach_ioctl(struct drm_device *dev, struct vgem_file *vfile = file->driver_priv; struct dma_resv *resv; struct drm_gem_object *obj; + enum dma_resv_usage usage; struct dma_fence *fence; int ret; @@ -151,18 +152,18 @@ int vgem_fence_attach_ioctl(struct drm_device *dev, /* Check for a conflicting fence */ resv = obj->resv; - if (!dma_resv_test_signaled(resv, arg->flags & VGEM_FENCE_WRITE)) { + usage = dma_resv_usage_rw(arg->flags & VGEM_FENCE_WRITE); + if (!dma_resv_test_signaled(resv, usage)) { ret = -EBUSY; goto err_fence; } /* Expose the fence via the dma-buf */ - ret = 0; dma_resv_lock(resv, NULL); - if (arg->flags & VGEM_FENCE_WRITE) - dma_resv_add_excl_fence(resv, fence); - else if ((ret = dma_resv_reserve_shared(resv, 1)) == 0) - dma_resv_add_shared_fence(resv, fence); + ret = dma_resv_reserve_fences(resv, 1); + if (!ret) + dma_resv_add_fence(resv, fence, arg->flags & VGEM_FENCE_WRITE ? + DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ); dma_resv_unlock(resv); /* Record the fence in our idr for later signaling */ diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index 5b00310ac4cd..f73352e7b832 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -179,6 +179,8 @@ static int virtio_gpu_conn_get_modes(struct drm_connector *connector) DRM_DEBUG("add mode: %dx%d\n", width, height); mode = drm_cvt_mode(connector->dev, width, height, 60, false, false, false); + if (!mode) + return count; mode->type |= DRM_MODE_TYPE_PREFERRED; drm_mode_probed_add(connector, mode); count++; diff --git a/drivers/gpu/drm/virtio/virtgpu_gem.c b/drivers/gpu/drm/virtio/virtgpu_gem.c index 48d3c9955f0d..580a78809836 100644 --- a/drivers/gpu/drm/virtio/virtgpu_gem.c +++ b/drivers/gpu/drm/virtio/virtgpu_gem.c @@ -214,6 +214,7 @@ void virtio_gpu_array_add_obj(struct virtio_gpu_object_array *objs, int virtio_gpu_array_lock_resv(struct virtio_gpu_object_array *objs) { + unsigned int i; int ret; if (objs->nents == 1) { @@ -222,6 +223,14 @@ int virtio_gpu_array_lock_resv(struct virtio_gpu_object_array *objs) ret = drm_gem_lock_reservations(objs->objs, objs->nents, &objs->ticket); } + if (ret) + return ret; + + for (i = 0; i < objs->nents; ++i) { + ret = dma_resv_reserve_fences(objs->objs[i]->resv, 1); + if (ret) + return ret; + } return ret; } @@ -241,7 +250,8 @@ void virtio_gpu_array_add_fence(struct virtio_gpu_object_array *objs, int i; for (i = 0; i < objs->nents; i++) - dma_resv_add_excl_fence(objs->objs[i]->resv, fence); + dma_resv_add_fence(objs->objs[i]->resv, fence, + DMA_RESV_USAGE_WRITE); } void virtio_gpu_array_put_free(struct virtio_gpu_object_array *objs) diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index c708bab555c6..f8d83358d2a0 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -518,9 +518,10 @@ static int virtio_gpu_wait_ioctl(struct drm_device *dev, void *data, return -ENOENT; if (args->flags & VIRTGPU_WAIT_NOWAIT) { - ret = dma_resv_test_signaled(obj->resv, true); + ret = dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ); } else { - ret = dma_resv_wait_timeout(obj->resv, true, true, timeout); + ret = dma_resv_wait_timeout(obj->resv, DMA_RESV_USAGE_READ, + true, timeout); } if (ret == 0) ret = -EBUSY; @@ -609,8 +610,7 @@ static int verify_blob(struct virtio_gpu_device *vgdev, if (!vgdev->has_resource_blob) return -EINVAL; - if ((rc_blob->blob_flags & ~VIRTGPU_BLOB_FLAG_USE_MASK) || - !rc_blob->blob_flags) + if (rc_blob->blob_flags & ~VIRTGPU_BLOB_FLAG_USE_MASK) return -EINVAL; if (rc_blob->blob_flags & VIRTGPU_BLOB_FLAG_USE_CROSS_DEVICE) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 31aecc46624b..408ede1f967f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -528,8 +528,8 @@ static int vmw_user_bo_synccpu_grab(struct vmw_buffer_object *vmw_bo, if (flags & drm_vmw_synccpu_allow_cs) { long lret; - lret = dma_resv_wait_timeout(bo->base.resv, true, true, - nonblock ? 0 : + lret = dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_READ, + true, nonblock ? 0 : MAX_SCHEDULE_TIMEOUT); if (!lret) return -EBUSY; @@ -747,16 +747,23 @@ void vmw_bo_fence_single(struct ttm_buffer_object *bo, struct vmw_fence_obj *fence) { struct ttm_device *bdev = bo->bdev; - struct vmw_private *dev_priv = container_of(bdev, struct vmw_private, bdev); + int ret; - if (fence == NULL) { + if (fence == NULL) vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL); - dma_resv_add_excl_fence(bo->base.resv, &fence->base); - dma_fence_put(&fence->base); - } else - dma_resv_add_excl_fence(bo->base.resv, &fence->base); + else + dma_fence_get(&fence->base); + + ret = dma_resv_reserve_fences(bo->base.resv, 1); + if (!ret) + dma_resv_add_fence(bo->base.resv, &fence->base, + DMA_RESV_USAGE_KERNEL); + else + /* Last resort fallback when we are OOM */ + dma_fence_wait(&fence->base, false); + dma_fence_put(&fence->base); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c index a3bfbb6c3e14..162dfeb1cc5a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c @@ -528,7 +528,7 @@ int vmw_cmd_send_fence(struct vmw_private *dev_priv, uint32_t *seqno) *seqno = atomic_add_return(1, &dev_priv->marker_seq); } while (*seqno == 0); - if (!(vmw_fifo_caps(dev_priv) & SVGA_FIFO_CAP_FENCE)) { + if (!vmw_has_fences(dev_priv)) { /* * Don't request hardware to send a fence. The @@ -675,11 +675,14 @@ int vmw_cmd_emit_dummy_query(struct vmw_private *dev_priv, */ bool vmw_cmd_supported(struct vmw_private *vmw) { - if ((vmw->capabilities & (SVGA_CAP_COMMAND_BUFFERS | - SVGA_CAP_CMD_BUFFERS_2)) != 0) - return true; + bool has_cmdbufs = + (vmw->capabilities & (SVGA_CAP_COMMAND_BUFFERS | + SVGA_CAP_CMD_BUFFERS_2)) != 0; + if (vmw_is_svga_v3(vmw)) + return (has_cmdbufs && + (vmw->capabilities & SVGA_CAP_GBOBJECTS) != 0); /* * We have FIFO cmd's */ - return vmw->fifo_mem != NULL; + return has_cmdbufs || vmw->fifo_mem != NULL; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 26eb5478394a..ffd975c14136 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR MIT /************************************************************************** * - * Copyright 2009-2016 VMware, Inc., Palo Alto, CA., USA + * Copyright 2009-2022 VMware, Inc., Palo Alto, CA., USA * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the @@ -848,12 +848,16 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) dev_priv->capabilities = vmw_read(dev_priv, SVGA_REG_CAPABILITIES); - + vmw_print_bitmap(&dev_priv->drm, "Capabilities", + dev_priv->capabilities, + cap1_names, ARRAY_SIZE(cap1_names)); if (dev_priv->capabilities & SVGA_CAP_CAP2_REGISTER) { dev_priv->capabilities2 = vmw_read(dev_priv, SVGA_REG_CAP2); + vmw_print_bitmap(&dev_priv->drm, "Capabilities2", + dev_priv->capabilities2, + cap2_names, ARRAY_SIZE(cap2_names)); } - ret = vmw_dma_select_mode(dev_priv); if (unlikely(ret != 0)) { drm_info(&dev_priv->drm, @@ -939,14 +943,6 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) "MOB limits: max mob size = %u kB, max mob pages = %u\n", dev_priv->max_mob_size / 1024, dev_priv->max_mob_pages); - vmw_print_bitmap(&dev_priv->drm, "Capabilities", - dev_priv->capabilities, - cap1_names, ARRAY_SIZE(cap1_names)); - if (dev_priv->capabilities & SVGA_CAP_CAP2_REGISTER) - vmw_print_bitmap(&dev_priv->drm, "Capabilities2", - dev_priv->capabilities2, - cap2_names, ARRAY_SIZE(cap2_names)); - ret = vmw_dma_masks(dev_priv); if (unlikely(ret != 0)) goto out_err0; @@ -984,7 +980,7 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) } if (dev_priv->capabilities & SVGA_CAP_IRQMASK) { - ret = vmw_irq_install(&dev_priv->drm, pdev->irq); + ret = vmw_irq_install(dev_priv); if (ret != 0) { drm_err(&dev_priv->drm, "Failed installing irq: %d\n", ret); @@ -1389,6 +1385,23 @@ static void vmw_remove(struct pci_dev *pdev) vmw_driver_unload(dev); } +static void vmw_debugfs_resource_managers_init(struct vmw_private *vmw) +{ + struct drm_minor *minor = vmw->drm.primary; + struct dentry *root = minor->debugfs_root; + + ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, TTM_PL_SYSTEM), + root, "system_ttm"); + ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, TTM_PL_VRAM), + root, "vram_ttm"); + ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_GMR), + root, "gmr_ttm"); + ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_MOB), + root, "mob_ttm"); + ttm_resource_manager_create_debugfs(ttm_manager_type(&vmw->bdev, VMW_PL_SYSTEM), + root, "system_mob_ttm"); +} + static unsigned long vmw_get_unmapped_area(struct file *file, unsigned long uaddr, unsigned long len, unsigned long pgoff, @@ -1636,6 +1649,7 @@ static int vmw_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto out_unload; vmw_debugfs_gem_init(vmw); + vmw_debugfs_resource_managers_init(vmw); return 0; out_unload: diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index ea3ecdda561d..be19aa6e1f13 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 OR MIT */ /************************************************************************** * - * Copyright 2009-2021 VMware, Inc., Palo Alto, CA., USA + * Copyright 2009-2022 VMware, Inc., Palo Alto, CA., USA * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the @@ -66,6 +66,11 @@ #define VMWGFX_PCI_ID_SVGA3 0x0406 /* + * This has to match get_count_order(SVGA_IRQFLAG_MAX) + */ +#define VMWGFX_MAX_NUM_IRQS 6 + +/* * Perhaps we should have sysfs entries for these. */ #define VMWGFX_NUM_GB_CONTEXT 256 @@ -101,6 +106,7 @@ struct vmw_fpriv { * struct vmw_buffer_object - TTM buffer object with vmwgfx additions * @base: The TTM buffer object * @res_tree: RB tree of resources using this buffer object as a backing MOB + * @base_mapped_count: ttm BO mapping count; used by KMS atomic helpers. * @cpu_writers: Number of synccpu write grabs. Protected by reservation when * increased. May be decreased without reservation. * @dx_query_ctx: DX context if this buffer object is used as a DX query MOB @@ -111,6 +117,9 @@ struct vmw_fpriv { struct vmw_buffer_object { struct ttm_buffer_object base; struct rb_root res_tree; + /* For KMS atomic helpers: ttm bo mapping count */ + atomic_t base_mapped_count; + atomic_t cpu_writers; /* Not ref-counted. Protected by binding_mutex */ struct vmw_resource *dx_query_ctx; @@ -528,6 +537,8 @@ struct vmw_private { bool has_mob; spinlock_t hw_lock; bool assume_16bpp; + u32 irqs[VMWGFX_MAX_NUM_IRQS]; + u32 num_irq_vectors; enum vmw_sm_type sm_type; @@ -1154,7 +1165,7 @@ bool vmw_cmd_describe(const void *buf, u32 *size, char const **cmd); * IRQs and wating - vmwgfx_irq.c */ -extern int vmw_irq_install(struct drm_device *dev, int irq); +extern int vmw_irq_install(struct vmw_private *dev_priv); extern void vmw_irq_uninstall(struct drm_device *dev); extern bool vmw_seqno_passed(struct vmw_private *dev_priv, uint32_t seqno); @@ -1679,4 +1690,12 @@ static inline void vmw_irq_status_write(struct vmw_private *vmw, outl(status, vmw->io_start + SVGA_IRQSTATUS_PORT); } +static inline bool vmw_has_fences(struct vmw_private *vmw) +{ + if ((vmw->capabilities & (SVGA_CAP_COMMAND_BUFFERS | + SVGA_CAP_CMD_BUFFERS_2)) != 0) + return true; + return (vmw_fifo_caps(vmw) & SVGA_FIFO_CAP_FENCE) != 0; +} + #endif diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c index 8ee34576c7d0..adf17c740656 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c @@ -483,7 +483,7 @@ static int vmw_fb_kms_detach(struct vmw_fb_par *par, static int vmw_fb_kms_framebuffer(struct fb_info *info) { - struct drm_mode_fb_cmd2 mode_cmd; + struct drm_mode_fb_cmd2 mode_cmd = {0}; struct vmw_fb_par *par = info->par; struct fb_var_screeninfo *var = &info->var; struct drm_framebuffer *cur_fb; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 59d6a2dd4c2e..66cc35dc223e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -82,6 +82,22 @@ fman_from_fence(struct vmw_fence_obj *fence) return container_of(fence->base.lock, struct vmw_fence_manager, lock); } +static u32 vmw_fence_goal_read(struct vmw_private *vmw) +{ + if ((vmw->capabilities2 & SVGA_CAP2_EXTRA_REGS) != 0) + return vmw_read(vmw, SVGA_REG_FENCE_GOAL); + else + return vmw_fifo_mem_read(vmw, SVGA_FIFO_FENCE_GOAL); +} + +static void vmw_fence_goal_write(struct vmw_private *vmw, u32 value) +{ + if ((vmw->capabilities2 & SVGA_CAP2_EXTRA_REGS) != 0) + vmw_write(vmw, SVGA_REG_FENCE_GOAL, value); + else + vmw_fifo_mem_write(vmw, SVGA_FIFO_FENCE_GOAL, value); +} + /* * Note on fencing subsystem usage of irqs: * Typically the vmw_fences_update function is called @@ -392,7 +408,7 @@ static bool vmw_fence_goal_new_locked(struct vmw_fence_manager *fman, if (likely(!fman->seqno_valid)) return false; - goal_seqno = vmw_fifo_mem_read(fman->dev_priv, SVGA_FIFO_FENCE_GOAL); + goal_seqno = vmw_fence_goal_read(fman->dev_priv); if (likely(passed_seqno - goal_seqno >= VMW_FENCE_WRAP)) return false; @@ -400,9 +416,8 @@ static bool vmw_fence_goal_new_locked(struct vmw_fence_manager *fman, list_for_each_entry(fence, &fman->fence_list, head) { if (!list_empty(&fence->seq_passed_actions)) { fman->seqno_valid = true; - vmw_fifo_mem_write(fman->dev_priv, - SVGA_FIFO_FENCE_GOAL, - fence->base.seqno); + vmw_fence_goal_write(fman->dev_priv, + fence->base.seqno); break; } } @@ -434,13 +449,12 @@ static bool vmw_fence_goal_check_locked(struct vmw_fence_obj *fence) if (dma_fence_is_signaled_locked(&fence->base)) return false; - goal_seqno = vmw_fifo_mem_read(fman->dev_priv, SVGA_FIFO_FENCE_GOAL); + goal_seqno = vmw_fence_goal_read(fman->dev_priv); if (likely(fman->seqno_valid && goal_seqno - fence->base.seqno < VMW_FENCE_WRAP)) return false; - vmw_fifo_mem_write(fman->dev_priv, SVGA_FIFO_FENCE_GOAL, - fence->base.seqno); + vmw_fence_goal_write(fman->dev_priv, fence->base.seqno); fman->seqno_valid = true; return true; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c index 471da2b4c177..a1da5678c731 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR MIT /************************************************************************** * - * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA + * Copyright 2009-2022 VMware, Inc., Palo Alto, CA., USA * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the @@ -27,9 +27,11 @@ #include "vmwgfx_drv.h" #include "vmwgfx_devcaps.h" -#include <drm/vmwgfx_drm.h> #include "vmwgfx_kms.h" +#include <drm/vmwgfx_drm.h> +#include <linux/pci.h> + int vmw_getparam_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { @@ -62,17 +64,15 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data, break; case DRM_VMW_PARAM_FIFO_HW_VERSION: { - if ((dev_priv->capabilities & SVGA_CAP_GBOBJECTS)) { + if ((dev_priv->capabilities & SVGA_CAP_GBOBJECTS)) param->value = SVGA3D_HWVERSION_WS8_B1; - break; - } - - param->value = - vmw_fifo_mem_read(dev_priv, - ((vmw_fifo_caps(dev_priv) & - SVGA_FIFO_CAP_3D_HWVERSION_REVISED) ? - SVGA_FIFO_3D_HWVERSION_REVISED : - SVGA_FIFO_3D_HWVERSION)); + else + param->value = vmw_fifo_mem_read( + dev_priv, + ((vmw_fifo_caps(dev_priv) & + SVGA_FIFO_CAP_3D_HWVERSION_REVISED) ? + SVGA_FIFO_3D_HWVERSION_REVISED : + SVGA_FIFO_3D_HWVERSION)); break; } case DRM_VMW_PARAM_MAX_SURF_MEMORY: @@ -108,6 +108,9 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data, case DRM_VMW_PARAM_GL43: param->value = has_gl43_context(dev_priv); break; + case DRM_VMW_PARAM_DEVICE_ID: + param->value = to_pci_dev(dev_priv->drm.dev)->device; + break; default: return -EINVAL; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c index c5191de365ca..086e69a130d4 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c @@ -32,6 +32,14 @@ #define VMW_FENCE_WRAP (1 << 24) +static u32 vmw_irqflag_fence_goal(struct vmw_private *vmw) +{ + if ((vmw->capabilities2 & SVGA_CAP2_EXTRA_REGS) != 0) + return SVGA_IRQFLAG_REG_FENCE_GOAL; + else + return SVGA_IRQFLAG_FENCE_GOAL; +} + /** * vmw_thread_fn - Deferred (process context) irq handler * @@ -96,7 +104,7 @@ static irqreturn_t vmw_irq_handler(int irq, void *arg) wake_up_all(&dev_priv->fifo_queue); if ((masked_status & (SVGA_IRQFLAG_ANY_FENCE | - SVGA_IRQFLAG_FENCE_GOAL)) && + vmw_irqflag_fence_goal(dev_priv))) && !test_and_set_bit(VMW_IRQTHREAD_FENCE, dev_priv->irqthread_pending)) ret = IRQ_WAKE_THREAD; @@ -137,8 +145,7 @@ bool vmw_seqno_passed(struct vmw_private *dev_priv, if (likely(dev_priv->last_read_seqno - seqno < VMW_FENCE_WRAP)) return true; - if (!(vmw_fifo_caps(dev_priv) & SVGA_FIFO_CAP_FENCE) && - vmw_fifo_idle(dev_priv, seqno)) + if (!vmw_has_fences(dev_priv) && vmw_fifo_idle(dev_priv, seqno)) return true; /** @@ -160,6 +167,7 @@ int vmw_fallback_wait(struct vmw_private *dev_priv, unsigned long timeout) { struct vmw_fifo_state *fifo_state = dev_priv->fifo; + bool fifo_down = false; uint32_t count = 0; uint32_t signal_seq; @@ -176,12 +184,14 @@ int vmw_fallback_wait(struct vmw_private *dev_priv, */ if (fifo_idle) { - down_read(&fifo_state->rwsem); if (dev_priv->cman) { ret = vmw_cmdbuf_idle(dev_priv->cman, interruptible, 10*HZ); if (ret) goto out_err; + } else if (fifo_state) { + down_read(&fifo_state->rwsem); + fifo_down = true; } } @@ -218,12 +228,12 @@ int vmw_fallback_wait(struct vmw_private *dev_priv, } } finish_wait(&dev_priv->fence_queue, &__wait); - if (ret == 0 && fifo_idle) + if (ret == 0 && fifo_idle && fifo_state) vmw_fence_write(dev_priv, signal_seq); wake_up_all(&dev_priv->fence_queue); out_err: - if (fifo_idle) + if (fifo_down) up_read(&fifo_state->rwsem); return ret; @@ -266,13 +276,13 @@ void vmw_seqno_waiter_remove(struct vmw_private *dev_priv) void vmw_goal_waiter_add(struct vmw_private *dev_priv) { - vmw_generic_waiter_add(dev_priv, SVGA_IRQFLAG_FENCE_GOAL, + vmw_generic_waiter_add(dev_priv, vmw_irqflag_fence_goal(dev_priv), &dev_priv->goal_queue_waiters); } void vmw_goal_waiter_remove(struct vmw_private *dev_priv) { - vmw_generic_waiter_remove(dev_priv, SVGA_IRQFLAG_FENCE_GOAL, + vmw_generic_waiter_remove(dev_priv, vmw_irqflag_fence_goal(dev_priv), &dev_priv->goal_queue_waiters); } @@ -290,6 +300,7 @@ void vmw_irq_uninstall(struct drm_device *dev) struct vmw_private *dev_priv = vmw_priv(dev); struct pci_dev *pdev = to_pci_dev(dev->dev); uint32_t status; + u32 i; if (!(dev_priv->capabilities & SVGA_CAP_IRQMASK)) return; @@ -299,20 +310,62 @@ void vmw_irq_uninstall(struct drm_device *dev) status = vmw_irq_status_read(dev_priv); vmw_irq_status_write(dev_priv, status); - free_irq(pdev->irq, dev); + for (i = 0; i < dev_priv->num_irq_vectors; ++i) + free_irq(dev_priv->irqs[i], dev); + + pci_free_irq_vectors(pdev); + dev_priv->num_irq_vectors = 0; } /** * vmw_irq_install - Install the irq handlers * - * @dev: Pointer to the drm device. - * @irq: The irq number. + * @dev_priv: Pointer to the vmw_private device. * Return: Zero if successful. Negative number otherwise. */ -int vmw_irq_install(struct drm_device *dev, int irq) +int vmw_irq_install(struct vmw_private *dev_priv) { + struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + struct drm_device *dev = &dev_priv->drm; + int ret; + int nvec; + int i = 0; + + BUILD_BUG_ON((SVGA_IRQFLAG_MAX >> VMWGFX_MAX_NUM_IRQS) != 1); + BUG_ON(VMWGFX_MAX_NUM_IRQS != get_count_order(SVGA_IRQFLAG_MAX)); + + nvec = pci_alloc_irq_vectors(pdev, 1, VMWGFX_MAX_NUM_IRQS, + PCI_IRQ_ALL_TYPES); + + if (nvec <= 0) { + drm_err(&dev_priv->drm, + "IRQ's are unavailable, nvec: %d\n", nvec); + ret = nvec; + goto done; + } + vmw_irq_preinstall(dev); - return request_threaded_irq(irq, vmw_irq_handler, vmw_thread_fn, - IRQF_SHARED, VMWGFX_DRIVER_NAME, dev); + for (i = 0; i < nvec; ++i) { + ret = pci_irq_vector(pdev, i); + if (ret < 0) { + drm_err(&dev_priv->drm, + "failed getting irq vector: %d\n", ret); + goto done; + } + dev_priv->irqs[i] = ret; + + ret = request_threaded_irq(dev_priv->irqs[i], vmw_irq_handler, vmw_thread_fn, + IRQF_SHARED, VMWGFX_DRIVER_NAME, dev); + if (ret != 0) { + drm_err(&dev_priv->drm, + "Failed installing irq(%d): %d\n", + dev_priv->irqs[i], ret); + goto done; + } + } + +done: + dev_priv->num_irq_vectors = i; + return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index bbd2f4ec08ec..693028c31b6b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR MIT /************************************************************************** * - * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA + * Copyright 2009-2022 VMware, Inc., Palo Alto, CA., USA * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the @@ -41,7 +41,7 @@ void vmw_du_cleanup(struct vmw_display_unit *du) struct vmw_private *dev_priv = vmw_priv(du->primary.dev); drm_plane_cleanup(&du->primary); if (vmw_cmd_supported(dev_priv)) - drm_plane_cleanup(&du->cursor); + drm_plane_cleanup(&du->cursor.base); drm_connector_unregister(&du->connector); drm_crtc_cleanup(&du->crtc); @@ -53,23 +53,43 @@ void vmw_du_cleanup(struct vmw_display_unit *du) * Display Unit Cursor functions */ -static int vmw_cursor_update_image(struct vmw_private *dev_priv, - u32 *image, u32 width, u32 height, - u32 hotspotX, u32 hotspotY) +static void vmw_cursor_update_mob(struct vmw_private *dev_priv, + struct ttm_buffer_object *bo, + struct ttm_bo_kmap_obj *map, + u32 *image, u32 width, u32 height, + u32 hotspotX, u32 hotspotY); + +struct vmw_svga_fifo_cmd_define_cursor { + u32 cmd; + SVGAFifoCmdDefineAlphaCursor cursor; +}; + +static void vmw_cursor_update_image(struct vmw_private *dev_priv, + struct ttm_buffer_object *cm_bo, + struct ttm_bo_kmap_obj *cm_map, + u32 *image, u32 width, u32 height, + u32 hotspotX, u32 hotspotY) { - struct { - u32 cmd; - SVGAFifoCmdDefineAlphaCursor cursor; - } *cmd; - u32 image_size = width * height * 4; - u32 cmd_size = sizeof(*cmd) + image_size; + struct vmw_svga_fifo_cmd_define_cursor *cmd; + const u32 image_size = width * height * sizeof(*image); + const u32 cmd_size = sizeof(*cmd) + image_size; - if (!image) - return -EINVAL; + if (cm_bo != NULL) { + vmw_cursor_update_mob(dev_priv, cm_bo, cm_map, image, + width, height, + hotspotX, hotspotY); + return; + } + /* Try to reserve fifocmd space and swallow any failures; + such reservations cannot be left unconsumed for long + under the risk of clogging other fifocmd users, so + we treat reservations separtely from the way we treat + other fallible KMS-atomic resources at prepare_fb */ cmd = VMW_CMD_RESERVE(dev_priv, cmd_size); + if (unlikely(cmd == NULL)) - return -ENOMEM; + return; memset(cmd, 0, sizeof(*cmd)); @@ -83,55 +103,158 @@ static int vmw_cursor_update_image(struct vmw_private *dev_priv, cmd->cursor.hotspotY = hotspotY; vmw_cmd_commit_flush(dev_priv, cmd_size); - - return 0; } -static int vmw_cursor_update_bo(struct vmw_private *dev_priv, - struct vmw_buffer_object *bo, - u32 width, u32 height, - u32 hotspotX, u32 hotspotY) -{ - struct ttm_bo_kmap_obj map; - unsigned long kmap_offset; - unsigned long kmap_num; - void *virtual; +/** + * vmw_cursor_update_mob - Update cursor vis CursorMob mechanism + * + * @dev_priv: device to work with + * @bo: BO for the MOB + * @map: kmap obj for the BO + * @image: cursor source data to fill the MOB with + * @width: source data width + * @height: source data height + * @hotspotX: cursor hotspot x + * @hotspotY: cursor hotspot Y + */ +static void vmw_cursor_update_mob(struct vmw_private *dev_priv, + struct ttm_buffer_object *bo, + struct ttm_bo_kmap_obj *map, + u32 *image, u32 width, u32 height, + u32 hotspotX, u32 hotspotY) +{ + SVGAGBCursorHeader *header; + SVGAGBAlphaCursorHeader *alpha_header; + const u32 image_size = width * height * sizeof(*image); bool dummy; - int ret; - kmap_offset = 0; - kmap_num = PFN_UP(width*height*4); + BUG_ON(!image); - ret = ttm_bo_reserve(&bo->base, true, false, NULL); - if (unlikely(ret != 0)) { - DRM_ERROR("reserve failed\n"); - return -EINVAL; + header = (SVGAGBCursorHeader *)ttm_kmap_obj_virtual(map, &dummy); + alpha_header = &header->header.alphaHeader; + + header->type = SVGA_ALPHA_CURSOR; + header->sizeInBytes = image_size; + + alpha_header->hotspotX = hotspotX; + alpha_header->hotspotY = hotspotY; + alpha_header->width = width; + alpha_header->height = height; + + memcpy(header + 1, image, image_size); + + vmw_write(dev_priv, SVGA_REG_CURSOR_MOBID, bo->resource->start); +} + +void vmw_du_destroy_cursor_mob_array(struct vmw_cursor_plane *vcp) +{ + size_t i; + + for (i = 0; i < ARRAY_SIZE(vcp->cursor_mob); i++) { + if (vcp->cursor_mob[i] != NULL) { + ttm_bo_unpin(vcp->cursor_mob[i]); + ttm_bo_put(vcp->cursor_mob[i]); + kfree(vcp->cursor_mob[i]); + vcp->cursor_mob[i] = NULL; + } } +} - ret = ttm_bo_kmap(&bo->base, kmap_offset, kmap_num, &map); - if (unlikely(ret != 0)) - goto err_unreserve; +#define CURSOR_MOB_SIZE(dimension) \ + ((dimension) * (dimension) * sizeof(u32) + sizeof(SVGAGBCursorHeader)) - virtual = ttm_kmap_obj_virtual(&map, &dummy); - ret = vmw_cursor_update_image(dev_priv, virtual, width, height, - hotspotX, hotspotY); +int vmw_du_create_cursor_mob_array(struct vmw_cursor_plane *cursor) +{ + struct vmw_private *dev_priv = cursor->base.dev->dev_private; + uint32_t cursor_max_dim, mob_max_size; + int ret = 0; + size_t i; - ttm_bo_kunmap(&map); -err_unreserve: - ttm_bo_unreserve(&bo->base); + if (!dev_priv->has_mob || (dev_priv->capabilities2 & SVGA_CAP2_CURSOR_MOB) == 0) + return -ENOSYS; + + mob_max_size = vmw_read(dev_priv, SVGA_REG_MOB_MAX_SIZE); + cursor_max_dim = vmw_read(dev_priv, SVGA_REG_CURSOR_MAX_DIMENSION); + + if (CURSOR_MOB_SIZE(cursor_max_dim) > mob_max_size) + cursor_max_dim = 64; /* Mandatorily-supported cursor dimension */ + + for (i = 0; i < ARRAY_SIZE(cursor->cursor_mob); i++) { + struct ttm_buffer_object **const bo = &cursor->cursor_mob[i]; + + ret = vmw_bo_create_kernel(dev_priv, + CURSOR_MOB_SIZE(cursor_max_dim), + &vmw_mob_placement, bo); + + if (ret != 0) + goto teardown; + + if ((*bo)->resource->mem_type != VMW_PL_MOB) { + DRM_ERROR("Obtained buffer object is not a MOB.\n"); + ret = -ENOSYS; + goto teardown; + } + + /* Fence the mob creation so we are guarateed to have the mob */ + ret = ttm_bo_reserve(*bo, false, false, NULL); + + if (ret != 0) + goto teardown; + + vmw_bo_fence_single(*bo, NULL); + + ttm_bo_unreserve(*bo); + + drm_info(&dev_priv->drm, "Using CursorMob mobid %lu, max dimension %u\n", + (*bo)->resource->start, cursor_max_dim); + } + + return 0; + +teardown: + vmw_du_destroy_cursor_mob_array(cursor); return ret; } +#undef CURSOR_MOB_SIZE + +static void vmw_cursor_update_bo(struct vmw_private *dev_priv, + struct ttm_buffer_object *cm_bo, + struct ttm_bo_kmap_obj *cm_map, + struct vmw_buffer_object *bo, + u32 width, u32 height, + u32 hotspotX, u32 hotspotY) +{ + void *virtual; + bool dummy; + + virtual = ttm_kmap_obj_virtual(&bo->map, &dummy); + if (virtual) { + vmw_cursor_update_image(dev_priv, cm_bo, cm_map, virtual, + width, height, + hotspotX, hotspotY); + atomic_dec(&bo->base_mapped_count); + } +} + static void vmw_cursor_update_position(struct vmw_private *dev_priv, bool show, int x, int y) { + const uint32_t svga_cursor_on = show ? SVGA_CURSOR_ON_SHOW + : SVGA_CURSOR_ON_HIDE; uint32_t count; spin_lock(&dev_priv->cursor_lock); - if (vmw_is_cursor_bypass3_enabled(dev_priv)) { - vmw_fifo_mem_write(dev_priv, SVGA_FIFO_CURSOR_ON, show ? 1 : 0); + if (dev_priv->capabilities2 & SVGA_CAP2_EXTRA_REGS) { + vmw_write(dev_priv, SVGA_REG_CURSOR4_X, x); + vmw_write(dev_priv, SVGA_REG_CURSOR4_Y, y); + vmw_write(dev_priv, SVGA_REG_CURSOR4_SCREEN_ID, SVGA3D_INVALID_ID); + vmw_write(dev_priv, SVGA_REG_CURSOR4_ON, svga_cursor_on); + vmw_write(dev_priv, SVGA_REG_CURSOR4_SUBMIT, TRUE); + } else if (vmw_is_cursor_bypass3_enabled(dev_priv)) { + vmw_fifo_mem_write(dev_priv, SVGA_FIFO_CURSOR_ON, svga_cursor_on); vmw_fifo_mem_write(dev_priv, SVGA_FIFO_CURSOR_X, x); vmw_fifo_mem_write(dev_priv, SVGA_FIFO_CURSOR_Y, y); count = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_CURSOR_COUNT); @@ -139,7 +262,7 @@ static void vmw_cursor_update_position(struct vmw_private *dev_priv, } else { vmw_write(dev_priv, SVGA_REG_CURSOR_X, x); vmw_write(dev_priv, SVGA_REG_CURSOR_Y, y); - vmw_write(dev_priv, SVGA_REG_CURSOR_ON, show ? 1 : 0); + vmw_write(dev_priv, SVGA_REG_CURSOR_ON, svga_cursor_on); } spin_unlock(&dev_priv->cursor_lock); } @@ -269,7 +392,7 @@ void vmw_kms_cursor_post_execbuf(struct vmw_private *dev_priv) continue; du->cursor_age = du->cursor_surface->snooper.age; - vmw_cursor_update_image(dev_priv, + vmw_cursor_update_image(dev_priv, NULL, NULL, du->cursor_surface->snooper.image, 64, 64, du->hotspot_x + du->core_hotspot_x, @@ -283,7 +406,7 @@ void vmw_kms_cursor_post_execbuf(struct vmw_private *dev_priv) void vmw_du_cursor_plane_destroy(struct drm_plane *plane) { vmw_cursor_update_position(plane->dev->dev_private, false, 0, 0); - + vmw_du_destroy_cursor_mob_array(vmw_plane_to_vcp(plane)); drm_plane_cleanup(plane); } @@ -321,7 +444,7 @@ void vmw_du_plane_unpin_surf(struct vmw_plane_state *vps, /** - * vmw_du_plane_cleanup_fb - Unpins the cursor + * vmw_du_plane_cleanup_fb - Unpins the plane surface * * @plane: display plane * @old_state: Contains the FB to clean up @@ -341,6 +464,55 @@ vmw_du_plane_cleanup_fb(struct drm_plane *plane, /** + * vmw_du_cursor_plane_cleanup_fb - Unpins the plane surface + * + * @plane: cursor plane + * @old_state: contains the state to clean up + * + * Unmaps all cursor bo mappings and unpins the cursor surface + * + * Returns 0 on success + */ +void +vmw_du_cursor_plane_cleanup_fb(struct drm_plane *plane, + struct drm_plane_state *old_state) +{ + struct vmw_plane_state *vps = vmw_plane_state_to_vps(old_state); + bool dummy; + + if (vps->bo != NULL && ttm_kmap_obj_virtual(&vps->bo->map, &dummy) != NULL) { + const int ret = ttm_bo_reserve(&vps->bo->base, true, false, NULL); + + if (likely(ret == 0)) { + if (atomic_read(&vps->bo->base_mapped_count) == 0) + ttm_bo_kunmap(&vps->bo->map); + ttm_bo_unreserve(&vps->bo->base); + } + } + + if (vps->cm_bo != NULL && ttm_kmap_obj_virtual(&vps->cm_map, &dummy) != NULL) { + const int ret = ttm_bo_reserve(vps->cm_bo, true, false, NULL); + + if (likely(ret == 0)) { + ttm_bo_kunmap(&vps->cm_map); + ttm_bo_unreserve(vps->cm_bo); + } + } + + vmw_du_plane_unpin_surf(vps, false); + + if (vps->surf) { + vmw_surface_unreference(&vps->surf); + vps->surf = NULL; + } + + if (vps->bo) { + vmw_bo_unreference(&vps->bo); + vps->bo = NULL; + } +} + +/** * vmw_du_cursor_plane_prepare_fb - Readies the cursor by referencing it * * @plane: display plane @@ -353,14 +525,21 @@ vmw_du_cursor_plane_prepare_fb(struct drm_plane *plane, struct drm_plane_state *new_state) { struct drm_framebuffer *fb = new_state->fb; + struct vmw_cursor_plane *vcp = vmw_plane_to_vcp(plane); struct vmw_plane_state *vps = vmw_plane_state_to_vps(new_state); + struct ttm_buffer_object *cm_bo = NULL; + bool dummy; + int ret = 0; - - if (vps->surf) + if (vps->surf) { vmw_surface_unreference(&vps->surf); + vps->surf = NULL; + } - if (vps->bo) + if (vps->bo) { vmw_bo_unreference(&vps->bo); + vps->bo = NULL; + } if (fb) { if (vmw_framebuffer_to_vfb(fb)->bo) { @@ -372,7 +551,90 @@ vmw_du_cursor_plane_prepare_fb(struct drm_plane *plane, } } + vps->cm_bo = NULL; + + if (vps->surf == NULL && vps->bo != NULL) { + const u32 size = new_state->crtc_w * new_state->crtc_h * sizeof(u32); + + /* Not using vmw_bo_map_and_cache() helper here as we need to reserve + the ttm_buffer_object first which wmw_bo_map_and_cache() omits. */ + ret = ttm_bo_reserve(&vps->bo->base, true, false, NULL); + + if (unlikely(ret != 0)) + return -ENOMEM; + + ret = ttm_bo_kmap(&vps->bo->base, 0, PFN_UP(size), &vps->bo->map); + + if (likely(ret == 0)) + atomic_inc(&vps->bo->base_mapped_count); + + ttm_bo_unreserve(&vps->bo->base); + + if (unlikely(ret != 0)) + return -ENOMEM; + } + + if (vps->surf || vps->bo) { + unsigned cursor_mob_idx = vps->cursor_mob_idx; + + /* Lazily set up cursor MOBs just once -- no reattempts. */ + if (cursor_mob_idx == 0 && vcp->cursor_mob[0] == NULL) + if (vmw_du_create_cursor_mob_array(vcp) != 0) + vps->cursor_mob_idx = cursor_mob_idx = -1U; + + if (cursor_mob_idx < ARRAY_SIZE(vcp->cursor_mob)) { + const u32 size = sizeof(SVGAGBCursorHeader) + + new_state->crtc_w * new_state->crtc_h * sizeof(u32); + + cm_bo = vcp->cursor_mob[cursor_mob_idx]; + + if (cm_bo->resource->num_pages * PAGE_SIZE < size) { + ret = -EINVAL; + goto error_bo_unmap; + } + + ret = ttm_bo_reserve(cm_bo, false, false, NULL); + + if (unlikely(ret != 0)) { + ret = -ENOMEM; + goto error_bo_unmap; + } + + ret = ttm_bo_kmap(cm_bo, 0, PFN_UP(size), &vps->cm_map); + + /* + * We just want to try to get mob bind to finish + * so that the first write to SVGA_REG_CURSOR_MOBID + * is done with a buffer that the device has already + * seen + */ + (void) ttm_bo_wait(cm_bo, false, false); + + ttm_bo_unreserve(cm_bo); + + if (unlikely(ret != 0)) { + ret = -ENOMEM; + goto error_bo_unmap; + } + + vps->cursor_mob_idx = cursor_mob_idx ^ 1; + vps->cm_bo = cm_bo; + } + } + return 0; + +error_bo_unmap: + if (vps->bo != NULL && ttm_kmap_obj_virtual(&vps->bo->map, &dummy) != NULL) { + const int ret = ttm_bo_reserve(&vps->bo->base, true, false, NULL); + if (likely(ret == 0)) { + atomic_dec(&vps->bo->base_mapped_count); + ttm_bo_kunmap(&vps->bo->map); + ttm_bo_unreserve(&vps->bo->base); + } + } + + return ret; } @@ -389,8 +651,6 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane, struct vmw_display_unit *du = vmw_crtc_to_du(crtc); struct vmw_plane_state *vps = vmw_plane_state_to_vps(new_state); s32 hotspot_x, hotspot_y; - int ret = 0; - hotspot_x = du->hotspot_x; hotspot_y = du->hotspot_y; @@ -406,33 +666,31 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane, if (vps->surf) { du->cursor_age = du->cursor_surface->snooper.age; - ret = vmw_cursor_update_image(dev_priv, - vps->surf->snooper.image, - 64, 64, hotspot_x, - hotspot_y); + vmw_cursor_update_image(dev_priv, vps->cm_bo, &vps->cm_map, + vps->surf->snooper.image, + new_state->crtc_w, + new_state->crtc_h, + hotspot_x, hotspot_y); } else if (vps->bo) { - ret = vmw_cursor_update_bo(dev_priv, vps->bo, - new_state->crtc_w, - new_state->crtc_h, - hotspot_x, hotspot_y); + vmw_cursor_update_bo(dev_priv, vps->cm_bo, &vps->cm_map, + vps->bo, + new_state->crtc_w, + new_state->crtc_h, + hotspot_x, hotspot_y); } else { vmw_cursor_update_position(dev_priv, false, 0, 0); return; } - if (!ret) { - du->cursor_x = new_state->crtc_x + du->set_gui_x; - du->cursor_y = new_state->crtc_y + du->set_gui_y; + du->cursor_x = new_state->crtc_x + du->set_gui_x; + du->cursor_y = new_state->crtc_y + du->set_gui_y; - vmw_cursor_update_position(dev_priv, true, - du->cursor_x + hotspot_x, - du->cursor_y + hotspot_y); + vmw_cursor_update_position(dev_priv, true, + du->cursor_x + hotspot_x, + du->cursor_y + hotspot_y); - du->core_hotspot_x = hotspot_x - du->hotspot_x; - du->core_hotspot_y = hotspot_y - du->hotspot_y; - } else { - DRM_ERROR("Failed to update cursor image\n"); - } + du->core_hotspot_x = hotspot_x - du->hotspot_x; + du->core_hotspot_y = hotspot_y - du->hotspot_y; } @@ -518,7 +776,7 @@ int vmw_du_cursor_plane_atomic_check(struct drm_plane *plane, if (new_state->crtc_w != 64 || new_state->crtc_h != 64) { DRM_ERROR("Invalid cursor dimensions (%d, %d)\n", new_state->crtc_w, new_state->crtc_h); - ret = -EINVAL; + return -EINVAL; } if (!vmw_framebuffer_to_vfb(fb)->bo) @@ -526,10 +784,10 @@ int vmw_du_cursor_plane_atomic_check(struct drm_plane *plane, if (surface && !surface->snooper.image) { DRM_ERROR("surface not suitable for cursor\n"); - ret = -EINVAL; + return -EINVAL; } - return ret; + return 0; } @@ -712,7 +970,6 @@ void vmw_du_plane_reset(struct drm_plane *plane) { struct vmw_plane_state *vps; - if (plane->state) vmw_du_plane_destroy_state(plane, plane->state); @@ -914,6 +1171,15 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv, * Sanity checks. */ + if (!drm_any_plane_has_format(&dev_priv->drm, + mode_cmd->pixel_format, + mode_cmd->modifier[0])) { + drm_dbg(&dev_priv->drm, + "unsupported pixel format %p4cc / modifier 0x%llx\n", + &mode_cmd->pixel_format, mode_cmd->modifier[0]); + return -EINVAL; + } + /* Surface must be marked as a scanout. */ if (unlikely(!surface->metadata.scanout)) return -EINVAL; @@ -1236,20 +1502,13 @@ static int vmw_kms_new_framebuffer_bo(struct vmw_private *dev_priv, return -EINVAL; } - /* Limited framebuffer color depth support for screen objects */ - if (dev_priv->active_display_unit == vmw_du_screen_object) { - switch (mode_cmd->pixel_format) { - case DRM_FORMAT_XRGB8888: - case DRM_FORMAT_ARGB8888: - break; - case DRM_FORMAT_XRGB1555: - case DRM_FORMAT_RGB565: - break; - default: - DRM_ERROR("Invalid pixel format: %p4cc\n", - &mode_cmd->pixel_format); - return -EINVAL; - } + if (!drm_any_plane_has_format(&dev_priv->drm, + mode_cmd->pixel_format, + mode_cmd->modifier[0])) { + drm_dbg(&dev_priv->drm, + "unsupported pixel format %p4cc / modifier 0x%llx\n", + &mode_cmd->pixel_format, mode_cmd->modifier[0]); + return -EINVAL; } vfbd = kzalloc(sizeof(*vfbd), GFP_KERNEL); @@ -1344,7 +1603,6 @@ vmw_kms_new_framebuffer(struct vmw_private *dev_priv, ret = vmw_kms_new_framebuffer_surface(dev_priv, surface, &vfb, mode_cmd, is_bo_proxy); - /* * vmw_create_bo_proxy() adds a reference that is no longer * needed @@ -1385,13 +1643,16 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev, ret = vmw_user_lookup_handle(dev_priv, file_priv, mode_cmd->handles[0], &surface, &bo); - if (ret) + if (ret) { + DRM_ERROR("Invalid buffer object handle %u (0x%x).\n", + mode_cmd->handles[0], mode_cmd->handles[0]); goto err_out; + } if (!bo && !vmw_kms_srf_ok(dev_priv, mode_cmd->width, mode_cmd->height)) { - DRM_ERROR("Surface size cannot exceed %dx%d", + DRM_ERROR("Surface size cannot exceed %dx%d\n", dev_priv->texture_max_width, dev_priv->texture_max_height); goto err_out; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h index 4d36e8507380..1d1c8b82c898 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 OR MIT */ /************************************************************************** * - * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA + * Copyright 2009-2022 VMware, Inc., Palo Alto, CA., USA * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the @@ -247,7 +247,6 @@ struct vmw_framebuffer_bo { static const uint32_t __maybe_unused vmw_primary_plane_formats[] = { DRM_FORMAT_XRGB1555, DRM_FORMAT_RGB565, - DRM_FORMAT_RGB888, DRM_FORMAT_XRGB8888, DRM_FORMAT_ARGB8888, }; @@ -261,6 +260,7 @@ static const uint32_t __maybe_unused vmw_cursor_plane_formats[] = { #define vmw_plane_state_to_vps(x) container_of(x, struct vmw_plane_state, base) #define vmw_connector_state_to_vcs(x) \ container_of(x, struct vmw_connector_state, base) +#define vmw_plane_to_vcp(x) container_of(x, struct vmw_cursor_plane, base) /** * Derived class for crtc state object @@ -293,6 +293,14 @@ struct vmw_plane_state { /* For CPU Blit */ unsigned int cpp; + + /* CursorMob flipping index; -1 if cursor mobs not used */ + unsigned int cursor_mob_idx; + /* Currently-active CursorMob */ + struct ttm_buffer_object *cm_bo; + /* CursorMob kmap_obj; expected valid at cursor_plane_atomic_update + IFF currently-active CursorMob above is valid */ + struct ttm_bo_kmap_obj cm_map; }; @@ -326,6 +334,17 @@ struct vmw_connector_state { }; /** + * Derived class for cursor plane object + * + * @base DRM plane object + * @cursor_mob array of two MOBs for CursorMob flipping + */ +struct vmw_cursor_plane { + struct drm_plane base; + struct ttm_buffer_object *cursor_mob[2]; +}; + +/** * Base class display unit. * * Since the SVGA hw doesn't have a concept of a crtc, encoder or connector @@ -337,7 +356,7 @@ struct vmw_display_unit { struct drm_encoder encoder; struct drm_connector connector; struct drm_plane primary; - struct drm_plane cursor; + struct vmw_cursor_plane cursor; struct vmw_surface *cursor_surface; struct vmw_buffer_object *cursor_bo; @@ -452,6 +471,8 @@ void vmw_kms_create_implicit_placement_property(struct vmw_private *dev_priv); /* Universal Plane Helpers */ void vmw_du_primary_plane_destroy(struct drm_plane *plane); void vmw_du_cursor_plane_destroy(struct drm_plane *plane); +int vmw_du_create_cursor_mob_array(struct vmw_cursor_plane *vcp); +void vmw_du_destroy_cursor_mob_array(struct vmw_cursor_plane *vcp); /* Atomic Helpers */ int vmw_du_primary_plane_atomic_check(struct drm_plane *plane, @@ -462,6 +483,8 @@ void vmw_du_cursor_plane_atomic_update(struct drm_plane *plane, struct drm_atomic_state *state); int vmw_du_cursor_plane_prepare_fb(struct drm_plane *plane, struct drm_plane_state *new_state); +void vmw_du_cursor_plane_cleanup_fb(struct drm_plane *plane, + struct drm_plane_state *old_state); void vmw_du_plane_cleanup_fb(struct drm_plane *plane, struct drm_plane_state *old_state); void vmw_du_plane_reset(struct drm_plane *plane); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c index fb58a71c458f..e4347faccee0 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR MIT /************************************************************************** * - * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA + * Copyright 2009-2022 VMware, Inc., Palo Alto, CA., USA * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the @@ -338,7 +338,7 @@ drm_plane_helper_funcs vmw_ldu_cursor_plane_helper_funcs = { .atomic_check = vmw_du_cursor_plane_atomic_check, .atomic_update = vmw_du_cursor_plane_atomic_update, .prepare_fb = vmw_du_cursor_plane_prepare_fb, - .cleanup_fb = vmw_du_plane_cleanup_fb, + .cleanup_fb = vmw_du_cursor_plane_cleanup_fb, }; static const struct @@ -363,7 +363,8 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit) struct drm_device *dev = &dev_priv->drm; struct drm_connector *connector; struct drm_encoder *encoder; - struct drm_plane *primary, *cursor; + struct drm_plane *primary; + struct vmw_cursor_plane *cursor; struct drm_crtc *crtc; int ret; @@ -392,7 +393,7 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit) ldu->base.is_implicit = true; /* Initialize primary plane */ - ret = drm_universal_plane_init(dev, &ldu->base.primary, + ret = drm_universal_plane_init(dev, primary, 0, &vmw_ldu_plane_funcs, vmw_primary_plane_formats, ARRAY_SIZE(vmw_primary_plane_formats), @@ -409,7 +410,7 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit) */ if (vmw_cmd_supported(dev_priv)) { /* Initialize cursor plane */ - ret = drm_universal_plane_init(dev, &ldu->base.cursor, + ret = drm_universal_plane_init(dev, &cursor->base, 0, &vmw_ldu_cursor_funcs, vmw_cursor_plane_formats, ARRAY_SIZE(vmw_cursor_plane_formats), @@ -420,7 +421,7 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit) goto err_free; } - drm_plane_helper_add(cursor, &vmw_ldu_cursor_plane_helper_funcs); + drm_plane_helper_add(&cursor->base, &vmw_ldu_cursor_plane_helper_funcs); } ret = drm_connector_init(dev, connector, &vmw_legacy_connector_funcs, @@ -450,9 +451,8 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit) goto err_free_encoder; } - ret = drm_crtc_init_with_planes( - dev, crtc, &ldu->base.primary, - vmw_cmd_supported(dev_priv) ? &ldu->base.cursor : NULL, + ret = drm_crtc_init_with_planes(dev, crtc, primary, + vmw_cmd_supported(dev_priv) ? &cursor->base : NULL, &vmw_legacy_crtc_funcs, NULL); if (ret) { DRM_ERROR("Failed to initialize CRTC\n"); @@ -492,6 +492,8 @@ int vmw_kms_ldu_init_display(struct vmw_private *dev_priv) { struct drm_device *dev = &dev_priv->drm; int i, ret; + int num_display_units = (dev_priv->capabilities & SVGA_CAP_MULTIMON) ? + VMWGFX_NUM_DISPLAY_UNITS : 1; if (unlikely(dev_priv->ldu_priv)) { return -EINVAL; @@ -506,21 +508,17 @@ int vmw_kms_ldu_init_display(struct vmw_private *dev_priv) dev_priv->ldu_priv->last_num_active = 0; dev_priv->ldu_priv->fb = NULL; - /* for old hardware without multimon only enable one display */ - if (dev_priv->capabilities & SVGA_CAP_MULTIMON) - ret = drm_vblank_init(dev, VMWGFX_NUM_DISPLAY_UNITS); - else - ret = drm_vblank_init(dev, 1); + ret = drm_vblank_init(dev, num_display_units); if (ret != 0) goto err_free; vmw_kms_create_implicit_placement_property(dev_priv); - if (dev_priv->capabilities & SVGA_CAP_MULTIMON) - for (i = 0; i < VMWGFX_NUM_DISPLAY_UNITS; ++i) - vmw_ldu_init(dev_priv, i); - else - vmw_ldu_init(dev_priv, 0); + for (i = 0; i < num_display_units; ++i) { + ret = vmw_ldu_init(dev_priv, i); + if (ret != 0) + goto err_free; + } dev_priv->active_display_unit = vmw_du_legacy; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 708899ba2102..a7d62a4eb47b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -859,22 +859,21 @@ void vmw_query_move_notify(struct ttm_buffer_object *bo, struct ttm_device *bdev = bo->bdev; struct vmw_private *dev_priv; - dev_priv = container_of(bdev, struct vmw_private, bdev); mutex_lock(&dev_priv->binding_mutex); - dx_query_mob = container_of(bo, struct vmw_buffer_object, base); - if (!dx_query_mob || !dx_query_mob->dx_query_ctx) { - mutex_unlock(&dev_priv->binding_mutex); - return; - } - /* If BO is being moved from MOB to system memory */ if (new_mem->mem_type == TTM_PL_SYSTEM && old_mem->mem_type == VMW_PL_MOB) { struct vmw_fence_obj *fence; + dx_query_mob = container_of(bo, struct vmw_buffer_object, base); + if (!dx_query_mob || !dx_query_mob->dx_query_ctx) { + mutex_unlock(&dev_priv->binding_mutex); + return; + } + (void) vmw_query_readback_all(dx_query_mob); mutex_unlock(&dev_priv->binding_mutex); @@ -888,7 +887,6 @@ void vmw_query_move_notify(struct ttm_buffer_object *bo, (void) ttm_bo_wait(bo, false, false); } else mutex_unlock(&dev_priv->binding_mutex); - } /** @@ -1163,10 +1161,6 @@ int vmw_resources_clean(struct vmw_buffer_object *vbo, pgoff_t start, *num_prefault = __KERNEL_DIV_ROUND_UP(last_cleaned - res_start, PAGE_SIZE); vmw_bo_fence_single(bo, NULL); - if (bo->moving) - dma_fence_put(bo->moving); - bo->moving = dma_fence_get - (dma_resv_excl_fence(bo->base.resv)); } return 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index 3004c7a719e9..c89ad3a2d141 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR MIT /************************************************************************** * - * Copyright 2011-2015 VMware, Inc., Palo Alto, CA., USA + * Copyright 2011-2022 VMware, Inc., Palo Alto, CA., USA * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the @@ -804,7 +804,7 @@ drm_plane_helper_funcs vmw_sou_cursor_plane_helper_funcs = { .atomic_check = vmw_du_cursor_plane_atomic_check, .atomic_update = vmw_du_cursor_plane_atomic_update, .prepare_fb = vmw_du_cursor_plane_prepare_fb, - .cleanup_fb = vmw_du_plane_cleanup_fb, + .cleanup_fb = vmw_du_cursor_plane_cleanup_fb, }; static const struct @@ -832,7 +832,8 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit) struct drm_device *dev = &dev_priv->drm; struct drm_connector *connector; struct drm_encoder *encoder; - struct drm_plane *primary, *cursor; + struct drm_plane *primary; + struct vmw_cursor_plane *cursor; struct drm_crtc *crtc; int ret; @@ -859,7 +860,7 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit) sou->base.is_implicit = false; /* Initialize primary plane */ - ret = drm_universal_plane_init(dev, &sou->base.primary, + ret = drm_universal_plane_init(dev, primary, 0, &vmw_sou_plane_funcs, vmw_primary_plane_formats, ARRAY_SIZE(vmw_primary_plane_formats), @@ -873,7 +874,7 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit) drm_plane_enable_fb_damage_clips(primary); /* Initialize cursor plane */ - ret = drm_universal_plane_init(dev, &sou->base.cursor, + ret = drm_universal_plane_init(dev, &cursor->base, 0, &vmw_sou_cursor_funcs, vmw_cursor_plane_formats, ARRAY_SIZE(vmw_cursor_plane_formats), @@ -884,7 +885,7 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit) goto err_free; } - drm_plane_helper_add(cursor, &vmw_sou_cursor_plane_helper_funcs); + drm_plane_helper_add(&cursor->base, &vmw_sou_cursor_plane_helper_funcs); ret = drm_connector_init(dev, connector, &vmw_sou_connector_funcs, DRM_MODE_CONNECTOR_VIRTUAL); @@ -913,8 +914,8 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit) goto err_free_encoder; } - ret = drm_crtc_init_with_planes(dev, crtc, &sou->base.primary, - &sou->base.cursor, + ret = drm_crtc_init_with_planes(dev, crtc, primary, + &cursor->base, &vmw_screen_object_crtc_funcs, NULL); if (ret) { DRM_ERROR("Failed to initialize CRTC\n"); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index ae9a6044d448..eb014b97d156 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR MIT /****************************************************************************** * - * COPYRIGHT (C) 2014-2015 VMware, Inc., Palo Alto, CA., USA + * COPYRIGHT (C) 2014-2022 VMware, Inc., Palo Alto, CA., USA * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the @@ -138,6 +138,11 @@ static void vmw_stdu_destroy(struct vmw_screen_target_display_unit *stdu); * Screen Target Display Unit CRTC Functions *****************************************************************************/ +static bool vmw_stdu_use_cpu_blit(const struct vmw_private *vmw) +{ + return !(vmw->capabilities & SVGA_CAP_3D) || vmw->vram_size < (32 * 1024 * 1024); +} + /** * vmw_stdu_crtc_destroy - cleans up the STDU @@ -689,7 +694,7 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv, container_of(vfb, struct vmw_framebuffer_bo, base)->buffer; struct vmw_stdu_dirty ddirty; int ret; - bool cpu_blit = !(dev_priv->capabilities & SVGA_CAP_3D); + bool cpu_blit = vmw_stdu_use_cpu_blit(dev_priv); DECLARE_VAL_CONTEXT(val_ctx, NULL, 0); /* @@ -1164,7 +1169,7 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane, * so cache these mappings */ if (vps->content_fb_type == SEPARATE_BO && - !(dev_priv->capabilities & SVGA_CAP_3D)) + vmw_stdu_use_cpu_blit(dev_priv)) vps->cpp = new_fb->pitches[0] / new_fb->width; return 0; @@ -1368,7 +1373,7 @@ static int vmw_stdu_plane_update_bo(struct vmw_private *dev_priv, bo_update.base.vfb = vfb; bo_update.base.out_fence = out_fence; bo_update.base.mutex = NULL; - bo_update.base.cpu_blit = !(dev_priv->capabilities & SVGA_CAP_3D); + bo_update.base.cpu_blit = vmw_stdu_use_cpu_blit(dev_priv); bo_update.base.intr = false; /* @@ -1685,7 +1690,7 @@ drm_plane_helper_funcs vmw_stdu_cursor_plane_helper_funcs = { .atomic_check = vmw_du_cursor_plane_atomic_check, .atomic_update = vmw_du_cursor_plane_atomic_update, .prepare_fb = vmw_du_cursor_plane_prepare_fb, - .cleanup_fb = vmw_du_plane_cleanup_fb, + .cleanup_fb = vmw_du_cursor_plane_cleanup_fb, }; static const struct @@ -1723,11 +1728,11 @@ static int vmw_stdu_init(struct vmw_private *dev_priv, unsigned unit) struct drm_device *dev = &dev_priv->drm; struct drm_connector *connector; struct drm_encoder *encoder; - struct drm_plane *primary, *cursor; + struct drm_plane *primary; + struct vmw_cursor_plane *cursor; struct drm_crtc *crtc; int ret; - stdu = kzalloc(sizeof(*stdu), GFP_KERNEL); if (!stdu) return -ENOMEM; @@ -1759,7 +1764,7 @@ static int vmw_stdu_init(struct vmw_private *dev_priv, unsigned unit) drm_plane_enable_fb_damage_clips(primary); /* Initialize cursor plane */ - ret = drm_universal_plane_init(dev, cursor, + ret = drm_universal_plane_init(dev, &cursor->base, 0, &vmw_stdu_cursor_funcs, vmw_cursor_plane_formats, ARRAY_SIZE(vmw_cursor_plane_formats), @@ -1770,7 +1775,7 @@ static int vmw_stdu_init(struct vmw_private *dev_priv, unsigned unit) goto err_free; } - drm_plane_helper_add(cursor, &vmw_stdu_cursor_plane_helper_funcs); + drm_plane_helper_add(&cursor->base, &vmw_stdu_cursor_plane_helper_funcs); ret = drm_connector_init(dev, connector, &vmw_stdu_connector_funcs, DRM_MODE_CONNECTOR_VIRTUAL); @@ -1799,8 +1804,8 @@ static int vmw_stdu_init(struct vmw_private *dev_priv, unsigned unit) goto err_free_encoder; } - ret = drm_crtc_init_with_planes(dev, crtc, &stdu->base.primary, - &stdu->base.cursor, + ret = drm_crtc_init_with_planes(dev, crtc, primary, + &cursor->base, &vmw_stdu_crtc_funcs, NULL); if (ret) { DRM_ERROR("Failed to initialize CRTC\n"); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index b84ecc6d6611..4e3938e62c08 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -517,7 +517,7 @@ static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo, ttm_cached); else ret = ttm_tt_init(&vmw_be->dma_ttm, bo, page_flags, - ttm_cached); + ttm_cached, 0); if (unlikely(ret != 0)) goto out_no_init; diff --git a/drivers/gpu/ipu-v3/ipu-di.c b/drivers/gpu/ipu-v3/ipu-di.c index 666223c6bec4..0a34e0ab4fe6 100644 --- a/drivers/gpu/ipu-v3/ipu-di.c +++ b/drivers/gpu/ipu-v3/ipu-di.c @@ -447,8 +447,9 @@ static void ipu_di_config_clock(struct ipu_di *di, error = rate / (sig->mode.pixelclock / 1000); - dev_dbg(di->ipu->dev, " IPU clock can give %lu with divider %u, error %d.%u%%\n", - rate, div, (signed)(error - 1000) / 10, error % 10); + dev_dbg(di->ipu->dev, " IPU clock can give %lu with divider %u, error %c%d.%d%%\n", + rate, div, error < 1000 ? '-' : '+', + abs(error - 1000) / 10, abs(error - 1000) % 10); /* Allow a 1% error */ if (error < 1010 && error >= 990) { diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 26d269ba947c..85a2142c9384 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -380,7 +380,7 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel) * execute: * * (a) In the "normal (i.e., not resuming from hibernation)" path, - * the full barrier in smp_store_mb() guarantees that the store + * the full barrier in virt_store_mb() guarantees that the store * is propagated to all CPUs before the add_channel_work work * is queued. In turn, add_channel_work is queued before the * channel's ring buffer is allocated/initialized and the @@ -392,14 +392,14 @@ void vmbus_channel_map_relid(struct vmbus_channel *channel) * recv_int_page before retrieving the channel pointer from the * array of channels. * - * (b) In the "resuming from hibernation" path, the smp_store_mb() + * (b) In the "resuming from hibernation" path, the virt_store_mb() * guarantees that the store is propagated to all CPUs before * the VMBus connection is marked as ready for the resume event * (cf. check_ready_for_resume_event()). The interrupt handler * of the VMBus driver and vmbus_chan_sched() can not run before * vmbus_bus_resume() has completed execution (cf. resume_noirq). */ - smp_store_mb( + virt_store_mb( vmbus_connection.channels[channel->offermsg.child_relid], channel); } diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 439f99b8b5de..3248b48f37f6 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/kthread.h> #include <linux/completion.h> +#include <linux/count_zeros.h> #include <linux/memory_hotplug.h> #include <linux/memory.h> #include <linux/notifier.h> @@ -1130,6 +1131,7 @@ static void post_status(struct hv_dynmem_device *dm) struct dm_status status; unsigned long now = jiffies; unsigned long last_post = last_post_time; + unsigned long num_pages_avail, num_pages_committed; if (pressure_report_delay > 0) { --pressure_report_delay; @@ -1154,16 +1156,21 @@ static void post_status(struct hv_dynmem_device *dm) * num_pages_onlined) as committed to the host, otherwise it can try * asking us to balloon them out. */ - status.num_avail = si_mem_available(); - status.num_committed = vm_memory_committed() + + num_pages_avail = si_mem_available(); + num_pages_committed = vm_memory_committed() + dm->num_pages_ballooned + (dm->num_pages_added > dm->num_pages_onlined ? dm->num_pages_added - dm->num_pages_onlined : 0) + compute_balloon_floor(); - trace_balloon_status(status.num_avail, status.num_committed, + trace_balloon_status(num_pages_avail, num_pages_committed, vm_memory_committed(), dm->num_pages_ballooned, dm->num_pages_added, dm->num_pages_onlined); + + /* Convert numbers of pages into numbers of HV_HYP_PAGEs. */ + status.num_avail = num_pages_avail * NR_HV_HYP_PAGES_IN_PAGE; + status.num_committed = num_pages_committed * NR_HV_HYP_PAGES_IN_PAGE; + /* * If our transaction ID is no longer current, just don't * send the status. This can happen if we were interrupted @@ -1653,6 +1660,38 @@ static void disable_page_reporting(void) } } +static int ballooning_enabled(void) +{ + /* + * Disable ballooning if the page size is not 4k (HV_HYP_PAGE_SIZE), + * since currently it's unclear to us whether an unballoon request can + * make sure all page ranges are guest page size aligned. + */ + if (PAGE_SIZE != HV_HYP_PAGE_SIZE) { + pr_info("Ballooning disabled because page size is not 4096 bytes\n"); + return 0; + } + + return 1; +} + +static int hot_add_enabled(void) +{ + /* + * Disable hot add on ARM64, because we currently rely on + * memory_add_physaddr_to_nid() to get a node id of a hot add range, + * however ARM64's memory_add_physaddr_to_nid() always return 0 and + * DM_MEM_HOT_ADD_REQUEST doesn't have the NUMA node information for + * add_memory(). + */ + if (IS_ENABLED(CONFIG_ARM64)) { + pr_info("Memory hot add disabled on ARM64\n"); + return 0; + } + + return 1; +} + static int balloon_connect_vsp(struct hv_device *dev) { struct dm_version_request version_req; @@ -1724,8 +1763,8 @@ static int balloon_connect_vsp(struct hv_device *dev) * currently still requires the bits to be set, so we have to add code * to fail the host's hot-add and balloon up/down requests, if any. */ - cap_msg.caps.cap_bits.balloon = 1; - cap_msg.caps.cap_bits.hot_add = 1; + cap_msg.caps.cap_bits.balloon = ballooning_enabled(); + cap_msg.caps.cap_bits.hot_add = hot_add_enabled(); /* * Specify our alignment requirements as it relates diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index c1dd21d0d7ef..ae68298c0dca 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -20,6 +20,7 @@ #include <linux/panic_notifier.h> #include <linux/ptrace.h> #include <linux/slab.h> +#include <linux/dma-map-ops.h> #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> @@ -218,6 +219,16 @@ bool hv_query_ext_cap(u64 cap_query) } EXPORT_SYMBOL_GPL(hv_query_ext_cap); +void hv_setup_dma_ops(struct device *dev, bool coherent) +{ + /* + * Hyper-V does not offer a vIOMMU in the guest + * VM, so pass 0/NULL for the IOMMU settings + */ + arch_setup_dma_ops(dev, 0, 0, NULL, coherent); +} +EXPORT_SYMBOL_GPL(hv_setup_dma_ops); + bool hv_is_hibernation_supported(void) { return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4); diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 71efacb90965..3d215d9dec43 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -439,7 +439,16 @@ int hv_ringbuffer_read(struct vmbus_channel *channel, static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi) { u32 priv_read_loc = rbi->priv_read_index; - u32 write_loc = READ_ONCE(rbi->ring_buffer->write_index); + u32 write_loc; + + /* + * The Hyper-V host writes the packet data, then uses + * store_release() to update the write_index. Use load_acquire() + * here to prevent loads of the packet data from being re-ordered + * before the read of the write_index and potentially getting + * stale data. + */ + write_loc = virt_load_acquire(&rbi->ring_buffer->write_index); if (write_loc >= priv_read_loc) return write_loc - priv_read_loc; diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 60ee8b329f9e..14de17087864 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -77,8 +77,8 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val, /* * Hyper-V should be notified only once about a panic. If we will be - * doing hyperv_report_panic_msg() later with kmsg data, don't do - * the notification here. + * doing hv_kmsg_dump() with kmsg data later, don't do the notification + * here. */ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE && hyperv_report_reg()) { @@ -100,8 +100,8 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val, /* * Hyper-V should be notified only once about a panic. If we will be - * doing hyperv_report_panic_msg() later with kmsg data, don't do - * the notification here. + * doing hv_kmsg_dump() with kmsg data later, don't do the notification + * here. */ if (hyperv_report_reg()) hyperv_report_panic(regs, val, true); @@ -921,6 +921,21 @@ static int vmbus_probe(struct device *child_device) } /* + * vmbus_dma_configure -- Configure DMA coherence for VMbus device + */ +static int vmbus_dma_configure(struct device *child_device) +{ + /* + * On ARM64, propagate the DMA coherence setting from the top level + * VMbus ACPI device to the child VMbus device being added here. + * On x86/x64 coherence is assumed and these calls have no effect. + */ + hv_setup_dma_ops(child_device, + device_get_dma_attr(&hv_acpi_dev->dev) == DEV_DMA_COHERENT); + return 0; +} + +/* * vmbus_remove - Remove a vmbus device */ static void vmbus_remove(struct device *child_device) @@ -1040,6 +1055,7 @@ static struct bus_type hv_bus = { .remove = vmbus_remove, .probe = vmbus_probe, .uevent = vmbus_uevent, + .dma_configure = vmbus_dma_configure, .dev_groups = vmbus_dev_groups, .drv_groups = vmbus_drv_groups, .bus_groups = vmbus_bus_groups, @@ -1546,14 +1562,20 @@ static int vmbus_bus_init(void) if (ret) goto err_connect; + if (hv_is_isolation_supported()) + sysctl_record_panic_msg = 0; + /* * Only register if the crash MSRs are available */ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { u64 hyperv_crash_ctl; /* - * Sysctl registration is not fatal, since by default - * reporting is enabled. + * Panic message recording (sysctl_record_panic_msg) + * is enabled by default in non-isolated guests and + * disabled by default in isolated guests; the panic + * message recording won't be available in isolated + * guests should the following registration fail. */ hv_ctl_table_hdr = register_sysctl_table(hv_root_table); if (!hv_ctl_table_hdr) @@ -2097,6 +2119,10 @@ int vmbus_device_register(struct hv_device *child_device_obj) child_device_obj->device.parent = &hv_acpi_dev->dev; child_device_obj->device.release = vmbus_device_release; + child_device_obj->device.dma_parms = &child_device_obj->dma_parms; + child_device_obj->device.dma_mask = &child_device_obj->dma_mask; + dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64)); + /* * Register with the LDM. This will kick off the driver/device * binding...which will eventually call vmbus_match() and vmbus_probe() @@ -2122,9 +2148,6 @@ int vmbus_device_register(struct hv_device *child_device_obj) } hv_debug_add_dev_dir(child_device_obj); - child_device_obj->device.dma_parms = &child_device_obj->dma_parms; - child_device_obj->device.dma_mask = &child_device_obj->dma_mask; - dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64)); return 0; err_kset_unregister: @@ -2428,6 +2451,21 @@ static int vmbus_acpi_add(struct acpi_device *device) hv_acpi_dev = device; + /* + * Older versions of Hyper-V for ARM64 fail to include the _CCA + * method on the top level VMbus device in the DSDT. But devices + * are hardware coherent in all current Hyper-V use cases, so fix + * up the ACPI device to behave as if _CCA is present and indicates + * hardware coherence. + */ + ACPI_COMPANION_SET(&device->dev, device); + if (IS_ENABLED(CONFIG_ACPI_CCA_REQUIRED) && + device_get_dma_attr(&device->dev) == DEV_DMA_NOT_SUPPORTED) { + pr_info("No ACPI _CCA found; assuming coherent device I/O\n"); + device->flags.cca_seen = true; + device->flags.coherent_dma = true; + } + result = acpi_walk_resources(device->handle, METHOD_NAME__CRS, vmbus_walk_resources, NULL); @@ -2780,10 +2818,15 @@ static void __exit vmbus_exit(void) if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) { kmsg_dump_unregister(&hv_kmsg_dumper); unregister_die_notifier(&hyperv_die_block); - atomic_notifier_chain_unregister(&panic_notifier_list, - &hyperv_panic_block); } + /* + * The panic notifier is always registered, hence we should + * also unconditionally unregister it here as well. + */ + atomic_notifier_chain_unregister(&panic_notifier_list, + &hyperv_panic_block); + free_page((unsigned long)hv_panic_page); unregister_sysctl_table(hv_ctl_table_hdr); hv_ctl_table_hdr = NULL; diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 35f0d5e7533d..1c107d6d03b9 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -2824,6 +2824,7 @@ static int cm_dreq_handler(struct cm_work *work) switch (cm_id_priv->id.state) { case IB_CM_REP_SENT: case IB_CM_DREQ_SENT: + case IB_CM_MRA_REP_RCVD: ib_cancel_mad(cm_id_priv->msg); break; case IB_CM_ESTABLISHED: @@ -2831,8 +2832,6 @@ static int cm_dreq_handler(struct cm_work *work) cm_id_priv->id.lap_state == IB_CM_MRA_LAP_RCVD) ib_cancel_mad(cm_id_priv->msg); break; - case IB_CM_MRA_REP_RCVD: - break; case IB_CM_TIMEWAIT: atomic_long_inc(&work->port->counters[CM_RECV_DUPLICATES] [CM_DREQ_COUNTER]); diff --git a/drivers/infiniband/core/umem_dmabuf.c b/drivers/infiniband/core/umem_dmabuf.c index f0760741f281..fce80a4a5147 100644 --- a/drivers/infiniband/core/umem_dmabuf.c +++ b/drivers/infiniband/core/umem_dmabuf.c @@ -16,7 +16,6 @@ int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf) { struct sg_table *sgt; struct scatterlist *sg; - struct dma_fence *fence; unsigned long start, end, cur = 0; unsigned int nmap = 0; int i; @@ -68,11 +67,9 @@ wait_fence: * may be not up-to-date. Wait for the exporter to finish * the migration. */ - fence = dma_resv_excl_fence(umem_dmabuf->attach->dmabuf->resv); - if (fence) - return dma_fence_wait(fence, false); - - return 0; + return dma_resv_wait_timeout(umem_dmabuf->attach->dmabuf->resv, + DMA_RESV_USAGE_KERNEL, + false, MAX_SCHEDULE_TIMEOUT); } EXPORT_SYMBOL(ib_umem_dmabuf_map_pages); diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index 876cc78a22cc..7333646021bb 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -80,6 +80,9 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler) unsigned long flags; struct list_head del_list; + /* Prevent freeing of mm until we are completely finished. */ + mmgrab(handler->mn.mm); + /* Unregister first so we don't get any more notifications. */ mmu_notifier_unregister(&handler->mn, handler->mn.mm); @@ -102,6 +105,9 @@ void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler) do_remove(handler, &del_list); + /* Now the mm may be freed. */ + mmdrop(handler->mn.mm); + kfree(handler); } diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 956f8e875daa..32ef67e9a6a7 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -574,8 +574,10 @@ static void __cache_work_func(struct mlx5_cache_ent *ent) spin_lock_irq(&ent->lock); if (ent->disabled) goto out; - if (need_delay) + if (need_delay) { queue_delayed_work(cache->wq, &ent->dwork, 300 * HZ); + goto out; + } remove_cache_mr_locked(ent); queue_adjust_cache_locked(ent); } @@ -625,6 +627,7 @@ static void mlx5_mr_cache_free(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { struct mlx5_cache_ent *ent = mr->cache_ent; + WRITE_ONCE(dev->cache.last_add, jiffies); spin_lock_irq(&ent->lock); list_add_tail(&mr->list, &ent->head); ent->available_mrs++; diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index ae50b56e8913..8ef112f883a7 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -3190,7 +3190,11 @@ serr_no_r_lock: spin_lock_irqsave(&sqp->s_lock, flags); rvt_send_complete(sqp, wqe, send_status); if (sqp->ibqp.qp_type == IB_QPT_RC) { - int lastwqe = rvt_error_qp(sqp, IB_WC_WR_FLUSH_ERR); + int lastwqe; + + spin_lock(&sqp->r_lock); + lastwqe = rvt_error_qp(sqp, IB_WC_WR_FLUSH_ERR); + spin_unlock(&sqp->r_lock); sqp->s_flags &= ~RVT_S_BUSY; spin_unlock_irqrestore(&sqp->s_lock, flags); diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 4aab631ef517..d9cf2820c02e 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1661,7 +1661,7 @@ static struct iommu_device *omap_iommu_probe_device(struct device *dev) num_iommus = of_property_count_elems_of_size(dev->of_node, "iommus", sizeof(phandle)); if (num_iommus < 0) - return 0; + return ERR_PTR(-ENODEV); arch_data = kcalloc(num_iommus + 1, sizeof(*arch_data), GFP_KERNEL); if (!arch_data) diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 680d2fcf2686..15edb9a6fcae 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -433,6 +433,7 @@ config QCOM_PDC config QCOM_MPM tristate "QCOM MPM" depends on ARCH_QCOM + depends on MAILBOX select IRQ_DOMAIN_HIERARCHY help MSM Power Manager driver to manage and configure wakeup diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index cd772973114a..a0fc764ec9dc 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3011,18 +3011,12 @@ static int __init allocate_lpi_tables(void) return 0; } -static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set) +static u64 read_vpend_dirty_clear(void __iomem *vlpi_base) { u32 count = 1000000; /* 1s! */ bool clean; u64 val; - val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER); - val &= ~GICR_VPENDBASER_Valid; - val &= ~clr; - val |= set; - gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); - do { val = gicr_read_vpendbaser(vlpi_base + GICR_VPENDBASER); clean = !(val & GICR_VPENDBASER_Dirty); @@ -3033,10 +3027,26 @@ static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set) } } while (!clean && count); - if (unlikely(val & GICR_VPENDBASER_Dirty)) { + if (unlikely(!clean)) pr_err_ratelimited("ITS virtual pending table not cleaning\n"); + + return val; +} + +static u64 its_clear_vpend_valid(void __iomem *vlpi_base, u64 clr, u64 set) +{ + u64 val; + + /* Make sure we wait until the RD is done with the initial scan */ + val = read_vpend_dirty_clear(vlpi_base); + val &= ~GICR_VPENDBASER_Valid; + val &= ~clr; + val |= set; + gicr_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + + val = read_vpend_dirty_clear(vlpi_base); + if (unlikely(val & GICR_VPENDBASER_Dirty)) val |= GICR_VPENDBASER_PendingLast; - } return val; } diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 0efe1a9a9f3b..b252d5534547 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -206,11 +206,11 @@ static inline void __iomem *gic_dist_base(struct irq_data *d) } } -static void gic_do_wait_for_rwp(void __iomem *base) +static void gic_do_wait_for_rwp(void __iomem *base, u32 bit) { u32 count = 1000000; /* 1s! */ - while (readl_relaxed(base + GICD_CTLR) & GICD_CTLR_RWP) { + while (readl_relaxed(base + GICD_CTLR) & bit) { count--; if (!count) { pr_err_ratelimited("RWP timeout, gone fishing\n"); @@ -224,13 +224,13 @@ static void gic_do_wait_for_rwp(void __iomem *base) /* Wait for completion of a distributor change */ static void gic_dist_wait_for_rwp(void) { - gic_do_wait_for_rwp(gic_data.dist_base); + gic_do_wait_for_rwp(gic_data.dist_base, GICD_CTLR_RWP); } /* Wait for completion of a redistributor change */ static void gic_redist_wait_for_rwp(void) { - gic_do_wait_for_rwp(gic_data_rdist_rd_base()); + gic_do_wait_for_rwp(gic_data_rdist_rd_base(), GICR_CTLR_RWP); } #ifdef CONFIG_ARM64 @@ -1466,6 +1466,12 @@ static int gic_irq_domain_translate(struct irq_domain *d, if(fwspec->param_count != 2) return -EINVAL; + if (fwspec->param[0] < 16) { + pr_err(FW_BUG "Illegal GSI%d translation request\n", + fwspec->param[0]); + return -EINVAL; + } + *hwirq = fwspec->param[0]; *type = fwspec->param[1]; diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 58ba835bee1f..09c710ecc387 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -1123,6 +1123,12 @@ static int gic_irq_domain_translate(struct irq_domain *d, if(fwspec->param_count != 2) return -EINVAL; + if (fwspec->param[0] < 16) { + pr_err(FW_BUG "Illegal GSI%d translation request\n", + fwspec->param[0]); + return -EINVAL; + } + *hwirq = fwspec->param[0]; *type = fwspec->param[1]; diff --git a/drivers/irqchip/irq-qcom-mpm.c b/drivers/irqchip/irq-qcom-mpm.c index eea5a753618c..d30614661eea 100644 --- a/drivers/irqchip/irq-qcom-mpm.c +++ b/drivers/irqchip/irq-qcom-mpm.c @@ -375,7 +375,7 @@ static int qcom_mpm_init(struct device_node *np, struct device_node *parent) raw_spin_lock_init(&priv->lock); priv->base = devm_platform_ioremap_resource(pdev, 0); - if (!priv->base) + if (IS_ERR(priv->base)) return PTR_ERR(priv->base); for (i = 0; i < priv->reg_stride; i++) { diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c index e90adfa57950..9b3ba2df71c7 100644 --- a/drivers/message/fusion/mptbase.c +++ b/drivers/message/fusion/mptbase.c @@ -6658,13 +6658,13 @@ static int mpt_summary_proc_show(struct seq_file *m, void *v) static int mpt_version_proc_show(struct seq_file *m, void *v) { u8 cb_idx; - int scsi, fc, sas, lan, ctl, targ, dmp; + int scsi, fc, sas, lan, ctl, targ; char *drvname; seq_printf(m, "%s-%s\n", "mptlinux", MPT_LINUX_VERSION_COMMON); seq_printf(m, " Fusion MPT base driver\n"); - scsi = fc = sas = lan = ctl = targ = dmp = 0; + scsi = fc = sas = lan = ctl = targ = 0; for (cb_idx = MPT_MAX_PROTOCOL_DRIVERS-1; cb_idx; cb_idx--) { drvname = NULL; if (MptCallbacks[cb_idx]) { diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c index e008d82e4ba3..a13506dd8119 100644 --- a/drivers/misc/habanalabs/common/memory.c +++ b/drivers/misc/habanalabs/common/memory.c @@ -111,10 +111,10 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args, if (contiguous) { if (is_power_of_2(page_size)) - paddr = (u64) (uintptr_t) gen_pool_dma_alloc_align(vm->dram_pg_pool, - total_size, NULL, page_size); + paddr = (uintptr_t) gen_pool_dma_alloc_align(vm->dram_pg_pool, + total_size, NULL, page_size); else - paddr = (u64) (uintptr_t) gen_pool_alloc(vm->dram_pg_pool, total_size); + paddr = gen_pool_alloc(vm->dram_pg_pool, total_size); if (!paddr) { dev_err(hdev->dev, "failed to allocate %llu contiguous pages with total size of %llu\n", @@ -150,12 +150,12 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args, for (i = 0 ; i < num_pgs ; i++) { if (is_power_of_2(page_size)) phys_pg_pack->pages[i] = - (u64) gen_pool_dma_alloc_align(vm->dram_pg_pool, - page_size, NULL, - page_size); + (uintptr_t)gen_pool_dma_alloc_align(vm->dram_pg_pool, + page_size, NULL, + page_size); else - phys_pg_pack->pages[i] = (u64) gen_pool_alloc(vm->dram_pg_pool, - page_size); + phys_pg_pack->pages[i] = gen_pool_alloc(vm->dram_pg_pool, + page_size); if (!phys_pg_pack->pages[i]) { dev_err(hdev->dev, "Failed to allocate device memory (out of memory)\n"); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 4e67c1403cc9..506dc900f5c7 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -993,7 +993,7 @@ static int mmc_blk_reset(struct mmc_blk_data *md, struct mmc_host *host, return -EEXIST; md->reset_done |= type; - err = mmc_hw_reset(host); + err = mmc_hw_reset(host->card); /* Ensure we switch back to the correct partition */ if (err) { struct mmc_blk_data *main_md = @@ -1880,6 +1880,31 @@ static inline bool mmc_blk_rq_error(struct mmc_blk_request *brq) brq->data.error || brq->cmd.resp[0] & CMD_ERRORS; } +static int mmc_spi_err_check(struct mmc_card *card) +{ + u32 status = 0; + int err; + + /* + * SPI does not have a TRAN state we have to wait on, instead the + * card is ready again when it no longer holds the line LOW. + * We still have to ensure two things here before we know the write + * was successful: + * 1. The card has not disconnected during busy and we actually read our + * own pull-up, thinking it was still connected, so ensure it + * still responds. + * 2. Check for any error bits, in particular R1_SPI_IDLE to catch a + * just reconnected card after being disconnected during busy. + */ + err = __mmc_send_status(card, &status, 0); + if (err) + return err; + /* All R1 and R2 bits of SPI are errors in our case */ + if (status) + return -EIO; + return 0; +} + static int mmc_blk_busy_cb(void *cb_data, bool *busy) { struct mmc_blk_busy_data *data = cb_data; @@ -1903,9 +1928,16 @@ static int mmc_blk_card_busy(struct mmc_card *card, struct request *req) struct mmc_blk_busy_data cb_data; int err; - if (mmc_host_is_spi(card->host) || rq_data_dir(req) == READ) + if (rq_data_dir(req) == READ) return 0; + if (mmc_host_is_spi(card->host)) { + err = mmc_spi_err_check(card); + if (err) + mqrq->brq.data.bytes_xfered = 0; + return err; + } + cb_data.card = card; cb_data.status = 0; err = __mmc_poll_for_busy(card->host, 0, MMC_BLK_TIMEOUT_MS, @@ -2350,6 +2382,8 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, struct mmc_blk_data *md; int devidx, ret; char cap_str[10]; + bool cache_enabled = false; + bool fua_enabled = false; devidx = ida_simple_get(&mmc_blk_ida, 0, max_devices, GFP_KERNEL); if (devidx < 0) { @@ -2429,13 +2463,17 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, md->flags |= MMC_BLK_CMD23; } - if (mmc_card_mmc(card) && - md->flags & MMC_BLK_CMD23 && + if (md->flags & MMC_BLK_CMD23 && ((card->ext_csd.rel_param & EXT_CSD_WR_REL_PARAM_EN) || card->ext_csd.rel_sectors)) { md->flags |= MMC_BLK_REL_WR; - blk_queue_write_cache(md->queue.queue, true, true); + fua_enabled = true; + cache_enabled = true; } + if (mmc_cache_enabled(card->host)) + cache_enabled = true; + + blk_queue_write_cache(md->queue.queue, cache_enabled, fua_enabled); string_get_size((u64)size, 512, STRING_UNITS_2, cap_str, sizeof(cap_str)); diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 368f10405e13..c6ae16d40766 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -1995,7 +1995,7 @@ static void mmc_hw_reset_for_init(struct mmc_host *host) /** * mmc_hw_reset - reset the card in hardware - * @host: MMC host to which the card is attached + * @card: card to be reset * * Hard reset the card. This function is only for upper layers, like the * block layer or card drivers. You cannot use it in host drivers (struct @@ -2003,8 +2003,9 @@ static void mmc_hw_reset_for_init(struct mmc_host *host) * * Return: 0 on success, -errno on failure */ -int mmc_hw_reset(struct mmc_host *host) +int mmc_hw_reset(struct mmc_card *card) { + struct mmc_host *host = card->host; int ret; ret = host->bus_ops->hw_reset(host); diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c index e6a2fd2c6d5c..8d9bceeff986 100644 --- a/drivers/mmc/core/mmc_test.c +++ b/drivers/mmc/core/mmc_test.c @@ -2325,10 +2325,9 @@ static int mmc_test_profile_sglen_r_nonblock_perf(struct mmc_test_card *test) static int mmc_test_reset(struct mmc_test_card *test) { struct mmc_card *card = test->card; - struct mmc_host *host = card->host; int err; - err = mmc_hw_reset(host); + err = mmc_hw_reset(card); if (!err) { /* * Reset will re-enable the card's command queue, but tests diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c index 9c13f2c31365..4566d7fc9055 100644 --- a/drivers/mmc/host/mmci_stm32_sdmmc.c +++ b/drivers/mmc/host/mmci_stm32_sdmmc.c @@ -62,8 +62,8 @@ static int sdmmc_idma_validate_data(struct mmci_host *host, * excepted the last element which has no constraint on idmasize */ for_each_sg(data->sg, sg, data->sg_len - 1, i) { - if (!IS_ALIGNED(data->sg->offset, sizeof(u32)) || - !IS_ALIGNED(data->sg->length, SDMMC_IDMA_BURST)) { + if (!IS_ALIGNED(sg->offset, sizeof(u32)) || + !IS_ALIGNED(sg->length, SDMMC_IDMA_BURST)) { dev_err(mmc_dev(host->mmc), "unaligned scatterlist: ofst:%x length:%d\n", data->sg->offset, data->sg->length); @@ -71,7 +71,7 @@ static int sdmmc_idma_validate_data(struct mmci_host *host, } } - if (!IS_ALIGNED(data->sg->offset, sizeof(u32))) { + if (!IS_ALIGNED(sg->offset, sizeof(u32))) { dev_err(mmc_dev(host->mmc), "unaligned last scatterlist: ofst:%x length:%d\n", data->sg->offset, data->sg->length); diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index 2797a9c0f17d..ddb5ca2f559e 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -144,9 +144,9 @@ static unsigned int renesas_sdhi_clk_update(struct tmio_mmc_host *host, return clk_get_rate(priv->clk); if (priv->clkh) { + /* HS400 with 4TAP needs different clock settings */ bool use_4tap = priv->quirks && priv->quirks->hs400_4taps; - bool need_slow_clkh = (host->mmc->ios.timing == MMC_TIMING_UHS_SDR104) || - (host->mmc->ios.timing == MMC_TIMING_MMC_HS400); + bool need_slow_clkh = host->mmc->ios.timing == MMC_TIMING_MMC_HS400; clkh_shift = use_4tap && need_slow_clkh ? 1 : 2; ref_clk = priv->clkh; } @@ -396,10 +396,10 @@ static void renesas_sdhi_hs400_complete(struct mmc_host *mmc) SH_MOBILE_SDHI_SCC_TMPPORT2_HS400OSEL) | sd_scc_read32(host, priv, SH_MOBILE_SDHI_SCC_TMPPORT2)); - /* Set the sampling clock selection range of HS400 mode */ sd_scc_write32(host, priv, SH_MOBILE_SDHI_SCC_DTCNTL, SH_MOBILE_SDHI_SCC_DTCNTL_TAPEN | - 0x4 << SH_MOBILE_SDHI_SCC_DTCNTL_TAPNUM_SHIFT); + sd_scc_read32(host, priv, + SH_MOBILE_SDHI_SCC_DTCNTL)); /* Avoid bad TAP */ if (bad_taps & BIT(priv->tap_set)) { diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c index 666cee4c7f7c..08e838400b52 100644 --- a/drivers/mmc/host/sdhci-xenon.c +++ b/drivers/mmc/host/sdhci-xenon.c @@ -241,16 +241,6 @@ static void xenon_voltage_switch(struct sdhci_host *host) { /* Wait for 5ms after set 1.8V signal enable bit */ usleep_range(5000, 5500); - - /* - * For some reason the controller's Host Control2 register reports - * the bit representing 1.8V signaling as 0 when read after it was - * written as 1. Subsequent read reports 1. - * - * Since this may cause some issues, do an empty read of the Host - * Control2 register here to circumvent this. - */ - sdhci_readw(host, SDHCI_HOST_CONTROL2); } static unsigned int xenon_get_max_clock(struct sdhci_host *host) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 1c28495875cf..874fad0a5cf8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3253,6 +3253,7 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp) } qidx = bp->tc_to_qidx[j]; ring->queue_id = bp->q_info[qidx].queue_id; + spin_lock_init(&txr->xdp_tx_lock); if (i < bp->tx_nr_rings_xdp) continue; if (i % bp->tx_nr_rings_per_tc == (bp->tx_nr_rings_per_tc - 1)) @@ -10338,6 +10339,12 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) if (irq_re_init) udp_tunnel_nic_reset_ntf(bp->dev); + if (bp->tx_nr_rings_xdp < num_possible_cpus()) { + if (!static_key_enabled(&bnxt_xdp_locking_key)) + static_branch_enable(&bnxt_xdp_locking_key); + } else if (static_key_enabled(&bnxt_xdp_locking_key)) { + static_branch_disable(&bnxt_xdp_locking_key); + } set_bit(BNXT_STATE_OPEN, &bp->state); bnxt_enable_int(bp); /* Enable TX queues */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 61aa3e8c5952..98453a78cbd0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -593,7 +593,8 @@ struct nqe_cn { #define BNXT_MAX_MTU 9500 #define BNXT_MAX_PAGE_MODE_MTU \ ((unsigned int)PAGE_SIZE - VLAN_ETH_HLEN - NET_IP_ALIGN - \ - XDP_PACKET_HEADROOM) + XDP_PACKET_HEADROOM - \ + SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info))) #define BNXT_MIN_PKT_SIZE 52 @@ -800,6 +801,8 @@ struct bnxt_tx_ring_info { u32 dev_state; struct bnxt_ring_struct tx_ring_struct; + /* Synchronize simultaneous xdp_xmit on same ring */ + spinlock_t xdp_tx_lock; }; #define BNXT_LEGACY_COAL_CMPL_PARAMS \ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 52fad0fdeacf..03b1d6c04504 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -20,6 +20,8 @@ #include "bnxt.h" #include "bnxt_xdp.h" +DEFINE_STATIC_KEY_FALSE(bnxt_xdp_locking_key); + struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, struct bnxt_tx_ring_info *txr, dma_addr_t mapping, u32 len) @@ -227,11 +229,16 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames, ring = smp_processor_id() % bp->tx_nr_rings_xdp; txr = &bp->tx_ring[ring]; + if (READ_ONCE(txr->dev_state) == BNXT_DEV_STATE_CLOSING) + return -EINVAL; + + if (static_branch_unlikely(&bnxt_xdp_locking_key)) + spin_lock(&txr->xdp_tx_lock); + for (i = 0; i < num_frames; i++) { struct xdp_frame *xdp = frames[i]; - if (!txr || !bnxt_tx_avail(bp, txr) || - !(bp->bnapi[ring]->flags & BNXT_NAPI_FLAG_XDP)) + if (!bnxt_tx_avail(bp, txr)) break; mapping = dma_map_single(&pdev->dev, xdp->data, xdp->len, @@ -250,6 +257,9 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames, bnxt_db_write(bp, &txr->tx_db, txr->tx_prod); } + if (static_branch_unlikely(&bnxt_xdp_locking_key)) + spin_unlock(&txr->xdp_tx_lock); + return nxmit; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h index 0df40c3beb05..067bb5e821f5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h @@ -10,6 +10,8 @@ #ifndef BNXT_XDP_H #define BNXT_XDP_H +DECLARE_STATIC_KEY_FALSE(bnxt_xdp_locking_key); + struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, struct bnxt_tx_ring_info *txr, dma_addr_t mapping, u32 len); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c index 5f5f8c53c4a0..c8cb541572ff 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c @@ -167,7 +167,7 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev) base = of_iomap(node, 0); if (!base) { err = -ENOMEM; - goto err_close; + goto err_put; } err = fsl_mc_allocate_irqs(mc_dev); @@ -210,6 +210,8 @@ err_free_mc_irq: fsl_mc_free_irqs(mc_dev); err_unmap: iounmap(base); +err_put: + of_node_put(node); err_close: dprtc_close(mc_dev->mc_io, 0, mc_dev->mc_handle); err_free_mcp: diff --git a/drivers/net/ethernet/fungible/funcore/fun_dev.c b/drivers/net/ethernet/fungible/funcore/fun_dev.c index 5d7aef73df61..fb5120d90f26 100644 --- a/drivers/net/ethernet/fungible/funcore/fun_dev.c +++ b/drivers/net/ethernet/fungible/funcore/fun_dev.c @@ -586,8 +586,8 @@ static int fun_get_dev_limits(struct fun_dev *fdev) /* Calculate the max QID based on SQ/CQ/doorbell counts. * SQ/CQ doorbells alternate. */ - num_dbs = (pci_resource_len(pdev, 0) - NVME_REG_DBS) / - (fdev->db_stride * 4); + num_dbs = (pci_resource_len(pdev, 0) - NVME_REG_DBS) >> + (2 + NVME_CAP_STRIDE(fdev->cap_reg)); fdev->max_qid = min3(cq_count, sq_count, num_dbs / 2) - 1; fdev->kern_end_qid = fdev->max_qid + 1; return 0; diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index d4f1874df7d0..8ed3c9ab7ff7 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -301,7 +301,6 @@ enum ice_vsi_state { ICE_VSI_NETDEV_REGISTERED, ICE_VSI_UMAC_FLTR_CHANGED, ICE_VSI_MMAC_FLTR_CHANGED, - ICE_VSI_VLAN_FLTR_CHANGED, ICE_VSI_PROMISC_CHANGED, ICE_VSI_STATE_NBITS /* must be last */ }; @@ -672,7 +671,7 @@ static inline struct ice_pf *ice_netdev_to_pf(struct net_device *netdev) static inline bool ice_is_xdp_ena_vsi(struct ice_vsi *vsi) { - return !!vsi->xdp_prog; + return !!READ_ONCE(vsi->xdp_prog); } static inline void ice_set_ring_xdp(struct ice_tx_ring *ring) diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c index af57eb114966..85a94483c2ed 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.c +++ b/drivers/net/ethernet/intel/ice/ice_fltr.c @@ -58,7 +58,16 @@ int ice_fltr_set_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, u8 promisc_mask) { - return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, false); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error setting promisc mode on VSI %i (rc=%d)\n", + vsi->vsi_num, result); + + return result; } /** @@ -73,7 +82,16 @@ int ice_fltr_clear_vlan_vsi_promisc(struct ice_hw *hw, struct ice_vsi *vsi, u8 promisc_mask) { - return ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vlan_vsi_promisc(hw, vsi->idx, promisc_mask, true); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error clearing promisc mode on VSI %i (rc=%d)\n", + vsi->vsi_num, result); + + return result; } /** @@ -87,7 +105,16 @@ int ice_fltr_clear_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid) { - return ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + struct ice_pf *pf = hw->back; + int result; + + result = ice_clear_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error clearing promisc mode on VSI %i for VID %u (rc=%d)\n", + ice_get_hw_vsi_num(hw, vsi_handle), vid, result); + + return result; } /** @@ -101,7 +128,16 @@ int ice_fltr_set_vsi_promisc(struct ice_hw *hw, u16 vsi_handle, u8 promisc_mask, u16 vid) { - return ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + struct ice_pf *pf = hw->back; + int result; + + result = ice_set_vsi_promisc(hw, vsi_handle, promisc_mask, vid); + if (result) + dev_err(ice_pf_to_dev(pf), + "Error setting promisc mode on VSI %i for VID %u (rc=%d)\n", + ice_get_hw_vsi_num(hw, vsi_handle), vid, result); + + return result; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index b897926f817d..2774cbd5b12a 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1480,6 +1480,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->tx_tstamps = &pf->ptp.port.tx; ring->dev = dev; ring->count = vsi->num_tx_desc; + ring->txq_teid = ICE_INVAL_TEID; if (dvm_ena) ring->flags |= ICE_TX_FLAGS_RING_VLAN_L2TAG2; else @@ -2983,6 +2984,8 @@ int ice_vsi_release(struct ice_vsi *vsi) } } + if (ice_is_vsi_dflt_vsi(pf->first_sw, vsi)) + ice_clear_dflt_vsi(pf->first_sw); ice_fltr_remove_all(vsi); ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index b588d7995631..d768925785ca 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -243,8 +243,7 @@ static int ice_add_mac_to_unsync_list(struct net_device *netdev, const u8 *addr) static bool ice_vsi_fltr_changed(struct ice_vsi *vsi) { return test_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state) || - test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state) || - test_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); + test_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); } /** @@ -260,10 +259,15 @@ static int ice_set_promisc(struct ice_vsi *vsi, u8 promisc_m) if (vsi->type != ICE_VSI_PF) return 0; - if (ice_vsi_has_non_zero_vlans(vsi)) - status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); - else - status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); + if (ice_vsi_has_non_zero_vlans(vsi)) { + promisc_m |= (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX); + status = ice_fltr_set_vlan_vsi_promisc(&vsi->back->hw, vsi, + promisc_m); + } else { + status = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + promisc_m, 0); + } + return status; } @@ -280,10 +284,15 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) if (vsi->type != ICE_VSI_PF) return 0; - if (ice_vsi_has_non_zero_vlans(vsi)) - status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, promisc_m); - else - status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, promisc_m, 0); + if (ice_vsi_has_non_zero_vlans(vsi)) { + promisc_m |= (ICE_PROMISC_VLAN_RX | ICE_PROMISC_VLAN_TX); + status = ice_fltr_clear_vlan_vsi_promisc(&vsi->back->hw, vsi, + promisc_m); + } else { + status = ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + promisc_m, 0); + } + return status; } @@ -302,7 +311,6 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; u32 changed_flags = 0; - u8 promisc_m; int err; if (!vsi->netdev) @@ -320,7 +328,6 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) if (ice_vsi_fltr_changed(vsi)) { clear_bit(ICE_VSI_UMAC_FLTR_CHANGED, vsi->state); clear_bit(ICE_VSI_MMAC_FLTR_CHANGED, vsi->state); - clear_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); /* grab the netdev's addr_list_lock */ netif_addr_lock_bh(netdev); @@ -369,29 +376,15 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi) /* check for changes in promiscuous modes */ if (changed_flags & IFF_ALLMULTI) { if (vsi->current_netdev_flags & IFF_ALLMULTI) { - if (ice_vsi_has_non_zero_vlans(vsi)) - promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_MCAST_PROMISC_BITS; - - err = ice_set_promisc(vsi, promisc_m); + err = ice_set_promisc(vsi, ICE_MCAST_PROMISC_BITS); if (err) { - netdev_err(netdev, "Error setting Multicast promiscuous mode on VSI %i\n", - vsi->vsi_num); vsi->current_netdev_flags &= ~IFF_ALLMULTI; goto out_promisc; } } else { /* !(vsi->current_netdev_flags & IFF_ALLMULTI) */ - if (ice_vsi_has_non_zero_vlans(vsi)) - promisc_m = ICE_MCAST_VLAN_PROMISC_BITS; - else - promisc_m = ICE_MCAST_PROMISC_BITS; - - err = ice_clear_promisc(vsi, promisc_m); + err = ice_clear_promisc(vsi, ICE_MCAST_PROMISC_BITS); if (err) { - netdev_err(netdev, "Error clearing Multicast promiscuous mode on VSI %i\n", - vsi->vsi_num); vsi->current_netdev_flags |= IFF_ALLMULTI; goto out_promisc; } @@ -2569,7 +2562,7 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) spin_lock_init(&xdp_ring->tx_lock); for (j = 0; j < xdp_ring->count; j++) { tx_desc = ICE_TX_DESC(xdp_ring, j); - tx_desc->cmd_type_offset_bsz = cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE); + tx_desc->cmd_type_offset_bsz = 0; } } @@ -2765,8 +2758,10 @@ free_qmap: ice_for_each_xdp_txq(vsi, i) if (vsi->xdp_rings[i]) { - if (vsi->xdp_rings[i]->desc) + if (vsi->xdp_rings[i]->desc) { + synchronize_rcu(); ice_free_tx_ring(vsi->xdp_rings[i]); + } kfree_rcu(vsi->xdp_rings[i], rcu); vsi->xdp_rings[i] = NULL; } @@ -3488,6 +3483,20 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) if (!vid) return 0; + while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) + usleep_range(1000, 2000); + + /* Add multicast promisc rule for the VLAN ID to be added if + * all-multicast is currently enabled. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) { + ret = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, + vid); + if (ret) + goto finish; + } + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); /* Add a switch rule for this VLAN ID so its corresponding VLAN tagged @@ -3495,8 +3504,23 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) */ vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0); ret = vlan_ops->add_vlan(vsi, &vlan); - if (!ret) - set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); + if (ret) + goto finish; + + /* If all-multicast is currently enabled and this VLAN ID is only one + * besides VLAN-0 we have to update look-up type of multicast promisc + * rule for VLAN-0 from ICE_SW_LKUP_PROMISC to ICE_SW_LKUP_PROMISC_VLAN. + */ + if ((vsi->current_netdev_flags & IFF_ALLMULTI) && + ice_vsi_num_non_zero_vlans(vsi) == 1) { + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_PROMISC_BITS, 0); + ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, 0); + } + +finish: + clear_bit(ICE_CFG_BUSY, vsi->state); return ret; } @@ -3522,6 +3546,9 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) if (!vid) return 0; + while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) + usleep_range(1000, 2000); + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); /* Make sure VLAN delete is successful before updating VLAN @@ -3530,10 +3557,33 @@ ice_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) vlan = ICE_VLAN(be16_to_cpu(proto), vid, 0); ret = vlan_ops->del_vlan(vsi, &vlan); if (ret) - return ret; + goto finish; - set_bit(ICE_VSI_VLAN_FLTR_CHANGED, vsi->state); - return 0; + /* Remove multicast promisc rule for the removed VLAN ID if + * all-multicast is enabled. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, vid); + + if (!ice_vsi_has_non_zero_vlans(vsi)) { + /* Update look-up type of multicast promisc rule for VLAN 0 + * from ICE_SW_LKUP_PROMISC_VLAN to ICE_SW_LKUP_PROMISC when + * all-multicast is enabled and VLAN 0 is the only VLAN rule. + */ + if (vsi->current_netdev_flags & IFF_ALLMULTI) { + ice_fltr_clear_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_VLAN_PROMISC_BITS, + 0); + ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, + ICE_MCAST_PROMISC_BITS, 0); + } + } + +finish: + clear_bit(ICE_CFG_BUSY, vsi->state); + + return ret; } /** @@ -5475,16 +5525,19 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) /* Add filter for new MAC. If filter exists, return success */ err = ice_fltr_add_mac(vsi, mac, ICE_FWD_TO_VSI); - if (err == -EEXIST) + if (err == -EEXIST) { /* Although this MAC filter is already present in hardware it's * possible in some cases (e.g. bonding) that dev_addr was * modified outside of the driver and needs to be restored back * to this value. */ netdev_dbg(netdev, "filter for MAC %pM already exists\n", mac); - else if (err) + + return 0; + } else if (err) { /* error if the new filter addition failed */ err = -EADDRNOTAVAIL; + } err_update_filters: if (err) { diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 3f1a63815bac..69ff4b929772 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -1358,9 +1358,9 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) goto error_param; } - /* Skip queue if not enabled */ if (!test_bit(vf_q_id, vf->txq_ena)) - continue; + dev_dbg(ice_pf_to_dev(vsi->back), "Queue %u on VSI %u is not enabled, but stopping it anyway\n", + vf_q_id, vsi->vsi_num); ice_fill_txq_meta(vsi, ring, &txq_meta); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index dfbcaf08520e..866ee4df9671 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -41,8 +41,10 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx) { ice_clean_tx_ring(vsi->tx_rings[q_idx]); - if (ice_is_xdp_ena_vsi(vsi)) + if (ice_is_xdp_ena_vsi(vsi)) { + synchronize_rcu(); ice_clean_tx_ring(vsi->xdp_rings[q_idx]); + } ice_clean_rx_ring(vsi->rx_rings[q_idx]); } @@ -918,7 +920,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, struct ice_vsi *vsi = np->vsi; struct ice_tx_ring *ring; - if (test_bit(ICE_DOWN, vsi->state)) + if (test_bit(ICE_VSI_DOWN, vsi->state)) return -ENETDOWN; if (!ice_is_xdp_ena_vsi(vsi)) diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 5f9ab1842d49..c18801490649 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2751,7 +2751,7 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, } ret = of_get_mac_address(pnp, ppd.mac_addr); - if (ret) + if (ret == -EPROBE_DEFER) return ret; mv643xx_eth_property(pnp, "tx-queue-size", ppd.tx_queue_size); diff --git a/drivers/net/ethernet/micrel/Kconfig b/drivers/net/ethernet/micrel/Kconfig index 93df3049cdc0..830363bafcce 100644 --- a/drivers/net/ethernet/micrel/Kconfig +++ b/drivers/net/ethernet/micrel/Kconfig @@ -28,6 +28,7 @@ config KS8842 config KS8851 tristate "Micrel KS8851 SPI" depends on SPI + depends on PTP_1588_CLOCK_OPTIONAL select MII select CRC32 select EEPROM_93CX6 @@ -39,6 +40,7 @@ config KS8851 config KS8851_MLL tristate "Micrel KS8851 MLL" depends on HAS_IOMEM + depends on PTP_1588_CLOCK_OPTIONAL select MII select CRC32 select EEPROM_93CX6 diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 50ac3ee2577a..21d2645885ce 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -2903,11 +2903,9 @@ static netdev_tx_t myri10ge_sw_tso(struct sk_buff *skb, status = myri10ge_xmit(curr, dev); if (status != 0) { dev_kfree_skb_any(curr); - if (segs != NULL) { - curr = segs; - segs = next; + skb_list_walk_safe(next, curr, next) { curr->next = NULL; - dev_kfree_skb_any(segs); + dev_kfree_skb_any(curr); } goto drop; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index e3edca187ddf..5250d1d1e49c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -489,7 +489,7 @@ struct split_type_defs { #define STATIC_DEBUG_LINE_DWORDS 9 -#define NUM_COMMON_GLOBAL_PARAMS 11 +#define NUM_COMMON_GLOBAL_PARAMS 10 #define MAX_RECURSION_DEPTH 10 diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index b242000a77fd..b7cc36589f59 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -748,6 +748,9 @@ qede_build_skb(struct qede_rx_queue *rxq, buf = page_address(bd->data) + bd->page_offset; skb = build_skb(buf, rxq->rx_buf_seg_size); + if (unlikely(!skb)) + return NULL; + skb_reserve(skb, pad); skb_put(skb, len); diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index f9064532beb6..377df8b7f015 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -786,6 +786,85 @@ void efx_remove_channels(struct efx_nic *efx) kfree(efx->xdp_tx_queues); } +static int efx_set_xdp_tx_queue(struct efx_nic *efx, int xdp_queue_number, + struct efx_tx_queue *tx_queue) +{ + if (xdp_queue_number >= efx->xdp_tx_queue_count) + return -EINVAL; + + netif_dbg(efx, drv, efx->net_dev, + "Channel %u TXQ %u is XDP %u, HW %u\n", + tx_queue->channel->channel, tx_queue->label, + xdp_queue_number, tx_queue->queue); + efx->xdp_tx_queues[xdp_queue_number] = tx_queue; + return 0; +} + +static void efx_set_xdp_channels(struct efx_nic *efx) +{ + struct efx_tx_queue *tx_queue; + struct efx_channel *channel; + unsigned int next_queue = 0; + int xdp_queue_number = 0; + int rc; + + /* We need to mark which channels really have RX and TX + * queues, and adjust the TX queue numbers if we have separate + * RX-only and TX-only channels. + */ + efx_for_each_channel(channel, efx) { + if (channel->channel < efx->tx_channel_offset) + continue; + + if (efx_channel_is_xdp_tx(channel)) { + efx_for_each_channel_tx_queue(tx_queue, channel) { + tx_queue->queue = next_queue++; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, + tx_queue); + if (rc == 0) + xdp_queue_number++; + } + } else { + efx_for_each_channel_tx_queue(tx_queue, channel) { + tx_queue->queue = next_queue++; + netif_dbg(efx, drv, efx->net_dev, + "Channel %u TXQ %u is HW %u\n", + channel->channel, tx_queue->label, + tx_queue->queue); + } + + /* If XDP is borrowing queues from net stack, it must + * use the queue with no csum offload, which is the + * first one of the channel + * (note: tx_queue_by_type is not initialized yet) + */ + if (efx->xdp_txq_queues_mode == + EFX_XDP_TX_QUEUES_BORROWED) { + tx_queue = &channel->tx_queue[0]; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, + tx_queue); + if (rc == 0) + xdp_queue_number++; + } + } + } + WARN_ON(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DEDICATED && + xdp_queue_number != efx->xdp_tx_queue_count); + WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED && + xdp_queue_number > efx->xdp_tx_queue_count); + + /* If we have more CPUs than assigned XDP TX queues, assign the already + * existing queues to the exceeding CPUs + */ + next_queue = 0; + while (xdp_queue_number < efx->xdp_tx_queue_count) { + tx_queue = efx->xdp_tx_queues[next_queue++]; + rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); + if (rc == 0) + xdp_queue_number++; + } +} + int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries) { struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel; @@ -857,6 +936,7 @@ int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries) efx_init_napi_channel(efx->channel[i]); } + efx_set_xdp_channels(efx); out: /* Destroy unused channel structures */ for (i = 0; i < efx->n_channels; i++) { @@ -889,26 +969,9 @@ rollback: goto out; } -static inline int -efx_set_xdp_tx_queue(struct efx_nic *efx, int xdp_queue_number, - struct efx_tx_queue *tx_queue) -{ - if (xdp_queue_number >= efx->xdp_tx_queue_count) - return -EINVAL; - - netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n", - tx_queue->channel->channel, tx_queue->label, - xdp_queue_number, tx_queue->queue); - efx->xdp_tx_queues[xdp_queue_number] = tx_queue; - return 0; -} - int efx_set_channels(struct efx_nic *efx) { - struct efx_tx_queue *tx_queue; struct efx_channel *channel; - unsigned int next_queue = 0; - int xdp_queue_number; int rc; efx->tx_channel_offset = @@ -926,61 +989,14 @@ int efx_set_channels(struct efx_nic *efx) return -ENOMEM; } - /* We need to mark which channels really have RX and TX - * queues, and adjust the TX queue numbers if we have separate - * RX-only and TX-only channels. - */ - xdp_queue_number = 0; efx_for_each_channel(channel, efx) { if (channel->channel < efx->n_rx_channels) channel->rx_queue.core_index = channel->channel; else channel->rx_queue.core_index = -1; - - if (channel->channel >= efx->tx_channel_offset) { - if (efx_channel_is_xdp_tx(channel)) { - efx_for_each_channel_tx_queue(tx_queue, channel) { - tx_queue->queue = next_queue++; - rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); - if (rc == 0) - xdp_queue_number++; - } - } else { - efx_for_each_channel_tx_queue(tx_queue, channel) { - tx_queue->queue = next_queue++; - netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is HW %u\n", - channel->channel, tx_queue->label, - tx_queue->queue); - } - - /* If XDP is borrowing queues from net stack, it must use the queue - * with no csum offload, which is the first one of the channel - * (note: channel->tx_queue_by_type is not initialized yet) - */ - if (efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_BORROWED) { - tx_queue = &channel->tx_queue[0]; - rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); - if (rc == 0) - xdp_queue_number++; - } - } - } } - WARN_ON(efx->xdp_txq_queues_mode == EFX_XDP_TX_QUEUES_DEDICATED && - xdp_queue_number != efx->xdp_tx_queue_count); - WARN_ON(efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED && - xdp_queue_number > efx->xdp_tx_queue_count); - /* If we have more CPUs than assigned XDP TX queues, assign the already - * existing queues to the exceeding CPUs - */ - next_queue = 0; - while (xdp_queue_number < efx->xdp_tx_queue_count) { - tx_queue = efx->xdp_tx_queues[next_queue++]; - rc = efx_set_xdp_tx_queue(efx, xdp_queue_number, tx_queue); - if (rc == 0) - xdp_queue_number++; - } + efx_set_xdp_channels(efx); rc = netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels); if (rc) @@ -1124,7 +1140,7 @@ void efx_start_channels(struct efx_nic *efx) struct efx_rx_queue *rx_queue; struct efx_channel *channel; - efx_for_each_channel(channel, efx) { + efx_for_each_channel_rev(channel, efx) { efx_for_each_channel_tx_queue(tx_queue, channel) { efx_init_tx_queue(tx_queue); atomic_inc(&efx->active_queues); diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 1b22c7be0088..fa8b9aacca11 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -150,6 +150,9 @@ static void efx_fini_rx_recycle_ring(struct efx_rx_queue *rx_queue) struct efx_nic *efx = rx_queue->efx; int i; + if (unlikely(!rx_queue->page_ring)) + return; + /* Unmap and release the pages in the recycle ring. Remove the ring. */ for (i = 0; i <= rx_queue->page_ptr_mask; i++) { struct page *page = rx_queue->page_ring[i]; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index d16e031e95f4..6983799e1c05 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -443,6 +443,9 @@ int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs, if (unlikely(!tx_queue)) return -EINVAL; + if (!tx_queue->initialised) + return -EINVAL; + if (efx->xdp_txq_queues_mode != EFX_XDP_TX_QUEUES_DEDICATED) HARD_TX_LOCK(efx->net_dev, tx_queue->core_txq, cpu); diff --git a/drivers/net/ethernet/sfc/tx_common.c b/drivers/net/ethernet/sfc/tx_common.c index d530cde2b864..9bc8281b7f5b 100644 --- a/drivers/net/ethernet/sfc/tx_common.c +++ b/drivers/net/ethernet/sfc/tx_common.c @@ -101,6 +101,8 @@ void efx_fini_tx_queue(struct efx_tx_queue *tx_queue) netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev, "shutting down TX queue %d\n", tx_queue->queue); + tx_queue->initialised = false; + if (!tx_queue->buffer) return; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index ecf759ee1c9f..017dbbda0c1c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -205,7 +205,7 @@ static const struct pci_device_id loongson_dwmac_id_table[] = { }; MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table); -struct pci_driver loongson_dwmac_driver = { +static struct pci_driver loongson_dwmac_driver = { .name = "dwmac-loongson-pci", .id_table = loongson_dwmac_id_table, .probe = loongson_dwmac_probe, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 5d29f336315b..11e1055e8260 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -431,8 +431,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) plat->phylink_node = np; /* Get max speed of operation from device tree */ - if (of_property_read_u32(np, "max-speed", &plat->max_speed)) - plat->max_speed = -1; + of_property_read_u32(np, "max-speed", &plat->max_speed); plat->bus_id = of_alias_get_id(np, "ethernet"); if (plat->bus_id < 0) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 0f9c88dd1a4a..d5c1e5c4a508 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -433,8 +433,6 @@ struct axienet_local { struct net_device *ndev; struct device *dev; - struct device_node *phy_node; - struct phylink *phylink; struct phylink_config phylink_config; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index c7eb05e4a6bf..d6fc3f7acdf0 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -2064,25 +2064,33 @@ static int axienet_probe(struct platform_device *pdev) if (ret) goto cleanup_clk; - lp->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); - if (lp->phy_node) { - ret = axienet_mdio_setup(lp); - if (ret) - dev_warn(&pdev->dev, - "error registering MDIO bus: %d\n", ret); - } + ret = axienet_mdio_setup(lp); + if (ret) + dev_warn(&pdev->dev, + "error registering MDIO bus: %d\n", ret); + if (lp->phy_mode == PHY_INTERFACE_MODE_SGMII || lp->phy_mode == PHY_INTERFACE_MODE_1000BASEX) { - if (!lp->phy_node) { - dev_err(&pdev->dev, "phy-handle required for 1000BaseX/SGMII\n"); + np = of_parse_phandle(pdev->dev.of_node, "pcs-handle", 0); + if (!np) { + /* Deprecated: Always use "pcs-handle" for pcs_phy. + * Falling back to "phy-handle" here is only for + * backward compatibility with old device trees. + */ + np = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); + } + if (!np) { + dev_err(&pdev->dev, "pcs-handle (preferred) or phy-handle required for 1000BaseX/SGMII\n"); ret = -EINVAL; goto cleanup_mdio; } - lp->pcs_phy = of_mdio_find_device(lp->phy_node); + lp->pcs_phy = of_mdio_find_device(np); if (!lp->pcs_phy) { ret = -EPROBE_DEFER; + of_node_put(np); goto cleanup_mdio; } + of_node_put(np); lp->pcs.ops = &axienet_pcs_ops; lp->pcs.poll = true; } @@ -2125,8 +2133,6 @@ cleanup_mdio: put_device(&lp->pcs_phy->dev); if (lp->mii_bus) axienet_mdio_teardown(lp); - of_node_put(lp->phy_node); - cleanup_clk: clk_bulk_disable_unprepare(XAE_NUM_MISC_CLOCKS, lp->misc_clks); clk_disable_unprepare(lp->axi_clk); @@ -2155,9 +2161,6 @@ static int axienet_remove(struct platform_device *pdev) clk_bulk_disable_unprepare(XAE_NUM_MISC_CLOCKS, lp->misc_clks); clk_disable_unprepare(lp->axi_clk); - of_node_put(lp->phy_node); - lp->phy_node = NULL; - free_netdev(ndev); return 0; diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c index baf7afac7857..53846c6b56ca 100644 --- a/drivers/net/mctp/mctp-i2c.c +++ b/drivers/net/mctp/mctp-i2c.c @@ -553,7 +553,7 @@ static int mctp_i2c_header_create(struct sk_buff *skb, struct net_device *dev, hdr->source_slave = ((llsrc << 1) & 0xff) | 0x01; mhdr->ver = 0x01; - return 0; + return sizeof(struct mctp_i2c_hdr); } static int mctp_i2c_tx_thread(void *data) diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index c483ba67c21f..582969751b4c 100644 --- a/drivers/net/mdio/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c @@ -102,6 +102,9 @@ static int mscc_miim_read(struct mii_bus *bus, int mii_id, int regnum) u32 val; int ret; + if (regnum & MII_ADDR_C45) + return -EOPNOTSUPP; + ret = mscc_miim_wait_pending(bus); if (ret) goto out; @@ -145,6 +148,9 @@ static int mscc_miim_write(struct mii_bus *bus, int mii_id, struct mscc_miim_dev *miim = bus->priv; int ret; + if (regnum & MII_ADDR_C45) + return -EOPNOTSUPP; + ret = mscc_miim_wait_pending(bus); if (ret < 0) goto out; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 19b11e896460..fc53b71dc872 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -99,15 +99,6 @@ #define PTP_TIMESTAMP_EN_PDREQ_ BIT(2) #define PTP_TIMESTAMP_EN_PDRES_ BIT(3) -#define PTP_RX_LATENCY_1000 0x0224 -#define PTP_TX_LATENCY_1000 0x0225 - -#define PTP_RX_LATENCY_100 0x0222 -#define PTP_TX_LATENCY_100 0x0223 - -#define PTP_RX_LATENCY_10 0x0220 -#define PTP_TX_LATENCY_10 0x0221 - #define PTP_TX_PARSE_L2_ADDR_EN 0x0284 #define PTP_RX_PARSE_L2_ADDR_EN 0x0244 @@ -268,15 +259,6 @@ struct lan8814_ptp_rx_ts { u16 seq_id; }; -struct kszphy_latencies { - u16 rx_10; - u16 tx_10; - u16 rx_100; - u16 tx_100; - u16 rx_1000; - u16 tx_1000; -}; - struct kszphy_ptp_priv { struct mii_timestamper mii_ts; struct phy_device *phydev; @@ -296,7 +278,6 @@ struct kszphy_ptp_priv { struct kszphy_priv { struct kszphy_ptp_priv ptp_priv; - struct kszphy_latencies latencies; const struct kszphy_type *type; int led_mode; bool rmii_ref_clk_sel; @@ -304,14 +285,6 @@ struct kszphy_priv { u64 stats[ARRAY_SIZE(kszphy_hw_stats)]; }; -static struct kszphy_latencies lan8814_latencies = { - .rx_10 = 0x22AA, - .tx_10 = 0x2E4A, - .rx_100 = 0x092A, - .tx_100 = 0x02C1, - .rx_1000 = 0x01AD, - .tx_1000 = 0x00C9, -}; static const struct kszphy_type ksz8021_type = { .led_mode_reg = MII_KSZPHY_CTRL_2, .has_broadcast_disable = true, @@ -2618,55 +2591,6 @@ static int lan8814_ptp_probe_once(struct phy_device *phydev) return 0; } -static int lan8814_read_status(struct phy_device *phydev) -{ - struct kszphy_priv *priv = phydev->priv; - struct kszphy_latencies *latencies = &priv->latencies; - int err; - int regval; - - err = genphy_read_status(phydev); - if (err) - return err; - - switch (phydev->speed) { - case SPEED_1000: - lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_1000, - latencies->rx_1000); - lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_1000, - latencies->tx_1000); - break; - case SPEED_100: - lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_100, - latencies->rx_100); - lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_100, - latencies->tx_100); - break; - case SPEED_10: - lanphy_write_page_reg(phydev, 5, PTP_RX_LATENCY_10, - latencies->rx_10); - lanphy_write_page_reg(phydev, 5, PTP_TX_LATENCY_10, - latencies->tx_10); - break; - default: - break; - } - - /* Make sure the PHY is not broken. Read idle error count, - * and reset the PHY if it is maxed out. - */ - regval = phy_read(phydev, MII_STAT1000); - if ((regval & 0xFF) == 0xFF) { - phy_init_hw(phydev); - phydev->link = 0; - if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev)) - phydev->drv->config_intr(phydev); - return genphy_config_aneg(phydev); - } - - return 0; -} - static int lan8814_config_init(struct phy_device *phydev) { int val; @@ -2690,30 +2614,8 @@ static int lan8814_config_init(struct phy_device *phydev) return 0; } -static void lan8814_parse_latency(struct phy_device *phydev) -{ - const struct device_node *np = phydev->mdio.dev.of_node; - struct kszphy_priv *priv = phydev->priv; - struct kszphy_latencies *latency = &priv->latencies; - u32 val; - - if (!of_property_read_u32(np, "lan8814,latency_rx_10", &val)) - latency->rx_10 = val; - if (!of_property_read_u32(np, "lan8814,latency_tx_10", &val)) - latency->tx_10 = val; - if (!of_property_read_u32(np, "lan8814,latency_rx_100", &val)) - latency->rx_100 = val; - if (!of_property_read_u32(np, "lan8814,latency_tx_100", &val)) - latency->tx_100 = val; - if (!of_property_read_u32(np, "lan8814,latency_rx_1000", &val)) - latency->rx_1000 = val; - if (!of_property_read_u32(np, "lan8814,latency_tx_1000", &val)) - latency->tx_1000 = val; -} - static int lan8814_probe(struct phy_device *phydev) { - const struct device_node *np = phydev->mdio.dev.of_node; struct kszphy_priv *priv; u16 addr; int err; @@ -2724,13 +2626,10 @@ static int lan8814_probe(struct phy_device *phydev) priv->led_mode = -1; - priv->latencies = lan8814_latencies; - phydev->priv = priv; if (!IS_ENABLED(CONFIG_PTP_1588_CLOCK) || - !IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING) || - of_property_read_bool(np, "lan8814,ignore-ts")) + !IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING)) return 0; /* Strap-in value for PHY address, below register read gives starting @@ -2746,7 +2645,6 @@ static int lan8814_probe(struct phy_device *phydev) return err; } - lan8814_parse_latency(phydev); lan8814_ptp_init(phydev); return 0; @@ -2928,7 +2826,7 @@ static struct phy_driver ksphy_driver[] = { .config_init = lan8814_config_init, .probe = lan8814_probe, .soft_reset = genphy_soft_reset, - .read_status = lan8814_read_status, + .read_status = ksz9031_read_status, .get_sset_count = kszphy_get_sset_count, .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 88396ff99f03..6865d32270e5 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -469,7 +469,7 @@ static void sl_tx_timeout(struct net_device *dev, unsigned int txqueue) spin_lock(&sl->lock); if (netif_queue_stopped(dev)) { - if (!netif_running(dev)) + if (!netif_running(dev) || !sl->tty) goto out; /* May be we must check transmitter timeout here ? diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c index ea06d10e1c21..ca409d450a29 100644 --- a/drivers/net/usb/aqc111.c +++ b/drivers/net/usb/aqc111.c @@ -1102,10 +1102,15 @@ static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb) if (start_of_descs != desc_offset) goto err; - /* self check desc_offset from header*/ - if (desc_offset >= skb_len) + /* self check desc_offset from header and make sure that the + * bounds of the metadata array are inside the SKB + */ + if (pkt_count * 2 + desc_offset >= skb_len) goto err; + /* Packets must not overlap the metadata array */ + skb_trim(skb, desc_offset); + if (pkt_count == 0) goto err; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 85e362461d71..cfc30ce4c6e1 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1265,6 +1265,7 @@ static int vrf_prepare_mac_header(struct sk_buff *skb, eth = (struct ethhdr *)skb->data; skb_reset_mac_header(skb); + skb_reset_mac_len(skb); /* we set the ethernet destination and the source addresses to the * address of the VRF device. @@ -1294,9 +1295,9 @@ static int vrf_prepare_mac_header(struct sk_buff *skb, */ static int vrf_add_mac_header_if_unset(struct sk_buff *skb, struct net_device *vrf_dev, - u16 proto) + u16 proto, struct net_device *orig_dev) { - if (skb_mac_header_was_set(skb)) + if (skb_mac_header_was_set(skb) && dev_has_header(orig_dev)) return 0; return vrf_prepare_mac_header(skb, vrf_dev, proto); @@ -1402,6 +1403,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, /* if packet is NDISC then keep the ingress interface */ if (!is_ndisc) { + struct net_device *orig_dev = skb->dev; + vrf_rx_stats(vrf_dev, skb->len); skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; @@ -1410,7 +1413,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, int err; err = vrf_add_mac_header_if_unset(skb, vrf_dev, - ETH_P_IPV6); + ETH_P_IPV6, + orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); @@ -1440,6 +1444,8 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev, static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, struct sk_buff *skb) { + struct net_device *orig_dev = skb->dev; + skb->dev = vrf_dev; skb->skb_iif = vrf_dev->ifindex; IPCB(skb)->flags |= IPSKB_L3SLAVE; @@ -1460,7 +1466,8 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev, if (!list_empty(&vrf_dev->ptype_all)) { int err; - err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP); + err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP, + orig_dev); if (likely(!err)) { skb_push(skb, skb->mac_len); dev_queue_xmit_nit(skb, vrf_dev); diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c index 63e1c2d783c5..73693c66cef1 100644 --- a/drivers/net/wireless/ath/ath10k/sdio.c +++ b/drivers/net/wireless/ath/ath10k/sdio.c @@ -1633,7 +1633,7 @@ static void ath10k_sdio_hif_power_down(struct ath10k *ar) return; } - ret = mmc_hw_reset(ar_sdio->func->card->host); + ret = mmc_hw_reset(ar_sdio->func->card); if (ret) ath10k_warn(ar, "unable to reset sdio: %d\n", ret); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index ba3c159111d3..55285cad527f 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -4165,7 +4165,7 @@ static int brcmf_sdio_bus_reset(struct device *dev) /* reset the adapter */ sdio_claim_host(sdiodev->func1); - mmc_hw_reset(sdiodev->func1->card->host); + mmc_hw_reset(sdiodev->func1->card); sdio_release_host(sdiodev->func1); brcmf_bus_change_state(sdiodev->bus_if, BRCMF_BUS_DOWN); diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c index bde9e4bbfffe..4f3238d2a171 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.c +++ b/drivers/net/wireless/marvell/mwifiex/sdio.c @@ -2639,7 +2639,7 @@ static void mwifiex_sdio_card_reset_work(struct mwifiex_adapter *adapter) /* Run a HW reset of the SDIO interface. */ sdio_claim_host(func); - ret = mmc_hw_reset(func->card->host); + ret = mmc_hw_reset(func->card); sdio_release_host(func); switch (ret) { diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c index 72fc41ac83c0..9140b0163474 100644 --- a/drivers/net/wireless/ti/wlcore/sdio.c +++ b/drivers/net/wireless/ti/wlcore/sdio.c @@ -146,7 +146,7 @@ static int wl12xx_sdio_power_on(struct wl12xx_sdio_glue *glue) * To guarantee that the SDIO card is power cycled, as required to make * the FW programming to succeed, let's do a brute force HW reset. */ - mmc_hw_reset(card->host); + mmc_hw_reset(card); sdio_enable_func(func); sdio_release_host(func); diff --git a/drivers/of/platform.c b/drivers/of/platform.c index a16b74f32aa9..176ed71d20c0 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -507,7 +507,6 @@ int of_platform_default_populate(struct device_node *root, } EXPORT_SYMBOL_GPL(of_platform_default_populate); -#ifndef CONFIG_PPC static const struct of_device_id reserved_mem_matches[] = { { .compatible = "qcom,rmtfs-mem" }, { .compatible = "qcom,cmd-db" }, @@ -527,26 +526,73 @@ static int __init of_platform_default_populate_init(void) if (!of_have_populated_dt()) return -ENODEV; - /* - * Handle certain compatibles explicitly, since we don't want to create - * platform_devices for every node in /reserved-memory with a - * "compatible", - */ - for_each_matching_node(node, reserved_mem_matches) - of_platform_device_create(node, NULL, NULL); + if (IS_ENABLED(CONFIG_PPC)) { + struct device_node *boot_display = NULL; + struct platform_device *dev; + int ret; + + /* Check if we have a MacOS display without a node spec */ + if (of_get_property(of_chosen, "linux,bootx-noscreen", NULL)) { + /* + * The old code tried to work out which node was the MacOS + * display based on the address. I'm dropping that since the + * lack of a node spec only happens with old BootX versions + * (users can update) and with this code, they'll still get + * a display (just not the palette hacks). + */ + dev = platform_device_alloc("bootx-noscreen", 0); + if (WARN_ON(!dev)) + return -ENOMEM; + ret = platform_device_add(dev); + if (WARN_ON(ret)) { + platform_device_put(dev); + return ret; + } + } - node = of_find_node_by_path("/firmware"); - if (node) { - of_platform_populate(node, NULL, NULL, NULL); - of_node_put(node); - } + /* + * For OF framebuffers, first create the device for the boot display, + * then for the other framebuffers. Only fail for the boot display; + * ignore errors for the rest. + */ + for_each_node_by_type(node, "display") { + if (!of_get_property(node, "linux,opened", NULL) || + !of_get_property(node, "linux,boot-display", NULL)) + continue; + dev = of_platform_device_create(node, "of-display", NULL); + if (WARN_ON(!dev)) + return -ENOMEM; + boot_display = node; + break; + } + for_each_node_by_type(node, "display") { + if (!of_get_property(node, "linux,opened", NULL) || node == boot_display) + continue; + of_platform_device_create(node, "of-display", NULL); + } - node = of_get_compatible_child(of_chosen, "simple-framebuffer"); - of_platform_device_create(node, NULL, NULL); - of_node_put(node); + } else { + /* + * Handle certain compatibles explicitly, since we don't want to create + * platform_devices for every node in /reserved-memory with a + * "compatible", + */ + for_each_matching_node(node, reserved_mem_matches) + of_platform_device_create(node, NULL, NULL); + + node = of_find_node_by_path("/firmware"); + if (node) { + of_platform_populate(node, NULL, NULL, NULL); + of_node_put(node); + } - /* Populate everything else. */ - of_platform_default_populate(NULL, NULL, NULL); + node = of_get_compatible_child(of_chosen, "simple-framebuffer"); + of_platform_device_create(node, NULL, NULL); + of_node_put(node); + + /* Populate everything else. */ + of_platform_default_populate(NULL, NULL, NULL); + } return 0; } @@ -558,7 +604,6 @@ static int __init of_platform_sync_state_init(void) return 0; } late_initcall_sync(of_platform_sync_state_init); -#endif int of_platform_device_destroy(struct device *dev, void *data) { diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 558b35aba610..d270a204324e 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -3407,6 +3407,15 @@ static int hv_pci_probe(struct hv_device *hdev, hbus->bridge->domain_nr = dom; #ifdef CONFIG_X86 hbus->sysdata.domain = dom; +#elif defined(CONFIG_ARM64) + /* + * Set the PCI bus parent to be the corresponding VMbus + * device. Then the VMbus device will be assigned as the + * ACPI companion in pcibios_root_bridge_prepare() and + * pci_dma_configure() will propagate device coherence + * information to devices created on the bus. + */ + hbus->sysdata.parent = hdev->device.parent; #endif hbus->hdev = hdev; diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index afdcb91601d2..1e2d69453771 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -187,7 +187,7 @@ source "drivers/perf/hisilicon/Kconfig" config MARVELL_CN10K_DDR_PMU tristate "Enable MARVELL CN10K DRAM Subsystem(DSS) PMU Support" - depends on ARM64 || (COMPILE_TEST && 64BIT) + depends on ARCH_THUNDER || (COMPILE_TEST && 64BIT) help Enable perf support for Marvell DDR Performance monitoring event on CN10K platform. diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c index 94ebc1ecace7..b1b2a55de77f 100644 --- a/drivers/perf/fsl_imx8_ddr_perf.c +++ b/drivers/perf/fsl_imx8_ddr_perf.c @@ -29,7 +29,7 @@ #define CNTL_OVER_MASK 0xFFFFFFFE #define CNTL_CSV_SHIFT 24 -#define CNTL_CSV_MASK (0xFF << CNTL_CSV_SHIFT) +#define CNTL_CSV_MASK (0xFFU << CNTL_CSV_SHIFT) #define EVENT_CYCLES_ID 0 #define EVENT_CYCLES_COUNTER 0 diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c index 7640491aab12..30234c261b05 100644 --- a/drivers/perf/qcom_l2_pmu.c +++ b/drivers/perf/qcom_l2_pmu.c @@ -736,7 +736,7 @@ static struct cluster_pmu *l2_cache_associate_cpu_with_cluster( { u64 mpidr; int cpu_cluster_id; - struct cluster_pmu *cluster = NULL; + struct cluster_pmu *cluster; /* * This assumes that the cluster_id is in MPIDR[aff1] for @@ -758,10 +758,10 @@ static struct cluster_pmu *l2_cache_associate_cpu_with_cluster( cluster->cluster_id); cpumask_set_cpu(cpu, &cluster->cluster_cpus); *per_cpu_ptr(l2cache_pmu->pmu_cluster, cpu) = cluster; - break; + return cluster; } - return cluster; + return NULL; } static int l2cache_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) diff --git a/drivers/regulator/atc260x-regulator.c b/drivers/regulator/atc260x-regulator.c index 05147d2c3842..485e58b264c0 100644 --- a/drivers/regulator/atc260x-regulator.c +++ b/drivers/regulator/atc260x-regulator.c @@ -292,6 +292,7 @@ enum atc2603c_reg_ids { .bypass_mask = BIT(5), \ .active_discharge_reg = ATC2603C_PMU_SWITCH_CTL, \ .active_discharge_mask = BIT(1), \ + .active_discharge_on = BIT(1), \ .owner = THIS_MODULE, \ } diff --git a/drivers/regulator/rtq2134-regulator.c b/drivers/regulator/rtq2134-regulator.c index f21e3f8b21f2..8e13dea354a2 100644 --- a/drivers/regulator/rtq2134-regulator.c +++ b/drivers/regulator/rtq2134-regulator.c @@ -285,6 +285,7 @@ static const unsigned int rtq2134_buck_ramp_delay_table[] = { .enable_mask = RTQ2134_VOUTEN_MASK, \ .active_discharge_reg = RTQ2134_REG_BUCK##_id##_CFG0, \ .active_discharge_mask = RTQ2134_ACTDISCHG_MASK, \ + .active_discharge_on = RTQ2134_ACTDISCHG_MASK, \ .ramp_reg = RTQ2134_REG_BUCK##_id##_RSPCFG, \ .ramp_mask = RTQ2134_RSPUP_MASK, \ .ramp_delay_table = rtq2134_buck_ramp_delay_table, \ diff --git a/drivers/regulator/wm8994-regulator.c b/drivers/regulator/wm8994-regulator.c index cadea0344486..40befdd9dfa9 100644 --- a/drivers/regulator/wm8994-regulator.c +++ b/drivers/regulator/wm8994-regulator.c @@ -82,6 +82,35 @@ static const struct regulator_desc wm8994_ldo_desc[] = { .min_uV = 2400000, .uV_step = 100000, .enable_time = 3000, + .off_on_delay = 36000, + .owner = THIS_MODULE, + }, + { + .name = "LDO2", + .id = 2, + .type = REGULATOR_VOLTAGE, + .n_voltages = WM8994_LDO2_MAX_SELECTOR + 1, + .vsel_reg = WM8994_LDO_2, + .vsel_mask = WM8994_LDO2_VSEL_MASK, + .ops = &wm8994_ldo2_ops, + .enable_time = 3000, + .off_on_delay = 36000, + .owner = THIS_MODULE, + }, +}; + +static const struct regulator_desc wm8958_ldo_desc[] = { + { + .name = "LDO1", + .id = 1, + .type = REGULATOR_VOLTAGE, + .n_voltages = WM8994_LDO1_MAX_SELECTOR + 1, + .vsel_reg = WM8994_LDO_1, + .vsel_mask = WM8994_LDO1_VSEL_MASK, + .ops = &wm8994_ldo1_ops, + .min_uV = 2400000, + .uV_step = 100000, + .enable_time = 3000, .owner = THIS_MODULE, }, { @@ -172,9 +201,16 @@ static int wm8994_ldo_probe(struct platform_device *pdev) * regulator core and we need not worry about it on the * error path. */ - ldo->regulator = devm_regulator_register(&pdev->dev, - &wm8994_ldo_desc[id], - &config); + if (ldo->wm8994->type == WM8994) { + ldo->regulator = devm_regulator_register(&pdev->dev, + &wm8994_ldo_desc[id], + &config); + } else { + ldo->regulator = devm_regulator_register(&pdev->dev, + &wm8958_ldo_desc[id], + &config); + } + if (IS_ERR(ldo->regulator)) { ret = PTR_ERR(ldo->regulator); dev_err(wm8994->dev, "Failed to register LDO%d: %d\n", diff --git a/drivers/scsi/aha152x.c b/drivers/scsi/aha152x.c index 5f554a3a0f62..caeebfb67149 100644 --- a/drivers/scsi/aha152x.c +++ b/drivers/scsi/aha152x.c @@ -317,14 +317,18 @@ enum { }; struct aha152x_cmd_priv { - struct scsi_pointer scsi_pointer; + char *ptr; + int this_residual; + struct scatterlist *buffer; + int status; + int message; + int sent_command; + int phase; }; -static struct scsi_pointer *aha152x_scsi_pointer(struct scsi_cmnd *cmd) +static struct aha152x_cmd_priv *aha152x_priv(struct scsi_cmnd *cmd) { - struct aha152x_cmd_priv *acmd = scsi_cmd_priv(cmd); - - return &acmd->scsi_pointer; + return scsi_cmd_priv(cmd); } MODULE_AUTHOR("Jürgen Fischer"); @@ -890,17 +894,16 @@ void aha152x_release(struct Scsi_Host *shpnt) static int setup_expected_interrupts(struct Scsi_Host *shpnt) { if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); - scsi_pointer->phase |= 1 << 16; + acp->phase |= 1 << 16; - if (scsi_pointer->phase & selecting) { + if (acp->phase & selecting) { SETPORT(SSTAT1, SELTO); SETPORT(SIMODE0, ENSELDO | (DISCONNECTED_SC ? ENSELDI : 0)); SETPORT(SIMODE1, ENSELTIMO); } else { - SETPORT(SIMODE0, (scsi_pointer->phase & spiordy) ? ENSPIORDY : 0); + SETPORT(SIMODE0, (acp->phase & spiordy) ? ENSPIORDY : 0); SETPORT(SIMODE1, ENPHASEMIS | ENSCSIRST | ENSCSIPERR | ENBUSFREE); } } else if(STATE==seldi) { @@ -924,17 +927,16 @@ static int setup_expected_interrupts(struct Scsi_Host *shpnt) static int aha152x_internal_queue(struct scsi_cmnd *SCpnt, struct completion *complete, int phase) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(SCpnt); + struct aha152x_cmd_priv *acp = aha152x_priv(SCpnt); struct Scsi_Host *shpnt = SCpnt->device->host; unsigned long flags; - scsi_pointer->phase = not_issued | phase; - scsi_pointer->Status = 0x1; /* Ilegal status by SCSI standard */ - scsi_pointer->Message = 0; - scsi_pointer->have_data_in = 0; - scsi_pointer->sent_command = 0; + acp->phase = not_issued | phase; + acp->status = 0x1; /* Illegal status by SCSI standard */ + acp->message = 0; + acp->sent_command = 0; - if (scsi_pointer->phase & (resetting | check_condition)) { + if (acp->phase & (resetting | check_condition)) { if (!SCpnt->host_scribble || SCSEM(SCpnt) || SCNEXT(SCpnt)) { scmd_printk(KERN_ERR, SCpnt, "cannot reuse command\n"); return FAILED; @@ -957,15 +959,15 @@ static int aha152x_internal_queue(struct scsi_cmnd *SCpnt, SCp.phase : current state of the command */ if ((phase & resetting) || !scsi_sglist(SCpnt)) { - scsi_pointer->ptr = NULL; - scsi_pointer->this_residual = 0; + acp->ptr = NULL; + acp->this_residual = 0; scsi_set_resid(SCpnt, 0); - scsi_pointer->buffer = NULL; + acp->buffer = NULL; } else { scsi_set_resid(SCpnt, scsi_bufflen(SCpnt)); - scsi_pointer->buffer = scsi_sglist(SCpnt); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = scsi_sglist(SCpnt); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } DO_LOCK(flags); @@ -1015,7 +1017,7 @@ static void reset_done(struct scsi_cmnd *SCpnt) static void aha152x_scsi_done(struct scsi_cmnd *SCpnt) { - if (aha152x_scsi_pointer(SCpnt)->phase & resetting) + if (aha152x_priv(SCpnt)->phase & resetting) reset_done(SCpnt); else scsi_done(SCpnt); @@ -1101,7 +1103,7 @@ static int aha152x_device_reset(struct scsi_cmnd * SCpnt) DO_LOCK(flags); - if (aha152x_scsi_pointer(SCpnt)->phase & resetted) { + if (aha152x_priv(SCpnt)->phase & resetted) { HOSTDATA(shpnt)->commands--; if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); @@ -1395,31 +1397,30 @@ static void busfree_run(struct Scsi_Host *shpnt) SETPORT(SSTAT1, CLRBUSFREE); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); #if defined(AHA152X_STAT) action++; #endif - scsi_pointer->phase &= ~syncneg; + acp->phase &= ~syncneg; - if (scsi_pointer->phase & completed) { + if (acp->phase & completed) { /* target sent COMMAND COMPLETE */ - done(shpnt, scsi_pointer->Status, DID_OK); + done(shpnt, acp->status, DID_OK); - } else if (scsi_pointer->phase & aborted) { - done(shpnt, scsi_pointer->Status, DID_ABORT); + } else if (acp->phase & aborted) { + done(shpnt, acp->status, DID_ABORT); - } else if (scsi_pointer->phase & resetted) { - done(shpnt, scsi_pointer->Status, DID_RESET); + } else if (acp->phase & resetted) { + done(shpnt, acp->status, DID_RESET); - } else if (scsi_pointer->phase & disconnected) { + } else if (acp->phase & disconnected) { /* target sent DISCONNECT */ #if defined(AHA152X_STAT) HOSTDATA(shpnt)->disconnections++; #endif append_SC(&DISCONNECTED_SC, CURRENT_SC); - scsi_pointer->phase |= 1 << 16; + acp->phase |= 1 << 16; CURRENT_SC = NULL; } else { @@ -1438,24 +1439,23 @@ static void busfree_run(struct Scsi_Host *shpnt) action++; #endif - if (aha152x_scsi_pointer(DONE_SC)->phase & check_condition) { + if (aha152x_priv(DONE_SC)->phase & check_condition) { struct scsi_cmnd *cmd = HOSTDATA(shpnt)->done_SC; struct aha152x_scdata *sc = SCDATA(cmd); scsi_eh_restore_cmnd(cmd, &sc->ses); - aha152x_scsi_pointer(cmd)->Status = SAM_STAT_CHECK_CONDITION; + aha152x_priv(cmd)->status = SAM_STAT_CHECK_CONDITION; HOSTDATA(shpnt)->commands--; if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); /* turn led off */ - } else if (aha152x_scsi_pointer(DONE_SC)->Status == - SAM_STAT_CHECK_CONDITION) { + } else if (aha152x_priv(DONE_SC)->status == SAM_STAT_CHECK_CONDITION) { #if defined(AHA152X_STAT) HOSTDATA(shpnt)->busfree_with_check_condition++; #endif - if(!(aha152x_scsi_pointer(DONE_SC)->phase & not_issued)) { + if (!(aha152x_priv(DONE_SC)->phase & not_issued)) { struct aha152x_scdata *sc; struct scsi_cmnd *ptr = DONE_SC; DONE_SC=NULL; @@ -1480,7 +1480,7 @@ static void busfree_run(struct Scsi_Host *shpnt) if (!HOSTDATA(shpnt)->commands) SETPORT(PORTA, 0); /* turn led off */ - if (!(aha152x_scsi_pointer(ptr)->phase & resetting)) { + if (!(aha152x_priv(ptr)->phase & resetting)) { kfree(ptr->host_scribble); ptr->host_scribble=NULL; } @@ -1503,13 +1503,12 @@ static void busfree_run(struct Scsi_Host *shpnt) DO_UNLOCK(flags); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); #if defined(AHA152X_STAT) action++; #endif - scsi_pointer->phase |= selecting; + acp->phase |= selecting; /* clear selection timeout */ SETPORT(SSTAT1, SELTO); @@ -1537,13 +1536,13 @@ static void busfree_run(struct Scsi_Host *shpnt) */ static void seldo_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); SETPORT(SCSISIG, 0); SETPORT(SSTAT1, CLRBUSFREE); SETPORT(SSTAT1, CLRPHASECHG); - scsi_pointer->phase &= ~(selecting | not_issued); + acp->phase &= ~(selecting | not_issued); SETPORT(SCSISEQ, 0); @@ -1558,12 +1557,12 @@ static void seldo_run(struct Scsi_Host *shpnt) ADDMSGO(IDENTIFY(RECONNECT, CURRENT_SC->device->lun)); - if (scsi_pointer->phase & aborting) { + if (acp->phase & aborting) { ADDMSGO(ABORT); - } else if (scsi_pointer->phase & resetting) { + } else if (acp->phase & resetting) { ADDMSGO(BUS_DEVICE_RESET); } else if (SYNCNEG==0 && SYNCHRONOUS) { - scsi_pointer->phase |= syncneg; + acp->phase |= syncneg; MSGOLEN += spi_populate_sync_msg(&MSGO(MSGOLEN), 50, 8); SYNCNEG=1; /* negotiation in progress */ } @@ -1578,7 +1577,7 @@ static void seldo_run(struct Scsi_Host *shpnt) */ static void selto_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp; SETPORT(SCSISEQ, 0); SETPORT(SSTAT1, CLRSELTIMO); @@ -1586,9 +1585,10 @@ static void selto_run(struct Scsi_Host *shpnt) if (!CURRENT_SC) return; - scsi_pointer->phase &= ~selecting; + acp = aha152x_priv(CURRENT_SC); + acp->phase &= ~selecting; - if (scsi_pointer->phase & aborted) + if (acp->phase & aborted) done(shpnt, SAM_STAT_GOOD, DID_ABORT); else if (TESTLO(SSTAT0, SELINGO)) done(shpnt, SAM_STAT_GOOD, DID_BUS_BUSY); @@ -1616,10 +1616,9 @@ static void seldi_run(struct Scsi_Host *shpnt) SETPORT(SSTAT1, CLRPHASECHG); if(CURRENT_SC) { - struct scsi_pointer *scsi_pointer = - aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); - if (!(scsi_pointer->phase & not_issued)) + if (!(acp->phase & not_issued)) scmd_printk(KERN_ERR, CURRENT_SC, "command should not have been issued yet\n"); @@ -1676,7 +1675,7 @@ static void seldi_run(struct Scsi_Host *shpnt) static void msgi_run(struct Scsi_Host *shpnt) { for(;;) { - struct scsi_pointer *scsi_pointer; + struct aha152x_cmd_priv *acp; int sstat1 = GETPORT(SSTAT1); if(sstat1 & (PHASECHG|PHASEMIS|BUSFREE) || !(sstat1 & REQINIT)) @@ -1714,9 +1713,9 @@ static void msgi_run(struct Scsi_Host *shpnt) continue; } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - scsi_pointer->Message = MSGI(0); - scsi_pointer->phase &= ~disconnected; + acp = aha152x_priv(CURRENT_SC); + acp->message = MSGI(0); + acp->phase &= ~disconnected; MSGILEN=0; @@ -1724,8 +1723,8 @@ static void msgi_run(struct Scsi_Host *shpnt) continue; } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - scsi_pointer->Message = MSGI(0); + acp = aha152x_priv(CURRENT_SC); + acp->message = MSGI(0); switch (MSGI(0)) { case DISCONNECT: @@ -1733,11 +1732,11 @@ static void msgi_run(struct Scsi_Host *shpnt) scmd_printk(KERN_WARNING, CURRENT_SC, "target was not allowed to disconnect\n"); - scsi_pointer->phase |= disconnected; + acp->phase |= disconnected; break; case COMMAND_COMPLETE: - scsi_pointer->phase |= completed; + acp->phase |= completed; break; case MESSAGE_REJECT: @@ -1867,11 +1866,9 @@ static void msgi_end(struct Scsi_Host *shpnt) */ static void msgo_init(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - if(MSGOLEN==0) { - if ((scsi_pointer->phase & syncneg) && SYNCNEG==2 && - SYNCRATE==0) { + if ((aha152x_priv(CURRENT_SC)->phase & syncneg) && + SYNCNEG == 2 && SYNCRATE == 0) { ADDMSGO(IDENTIFY(RECONNECT, CURRENT_SC->device->lun)); } else { scmd_printk(KERN_INFO, CURRENT_SC, @@ -1888,7 +1885,7 @@ static void msgo_init(struct Scsi_Host *shpnt) */ static void msgo_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); while(MSGO_I<MSGOLEN) { if (TESTLO(SSTAT0, SPIORDY)) @@ -1901,13 +1898,13 @@ static void msgo_run(struct Scsi_Host *shpnt) if (MSGO(MSGO_I) & IDENTIFY_BASE) - scsi_pointer->phase |= identified; + acp->phase |= identified; if (MSGO(MSGO_I)==ABORT) - scsi_pointer->phase |= aborted; + acp->phase |= aborted; if (MSGO(MSGO_I)==BUS_DEVICE_RESET) - scsi_pointer->phase |= resetted; + acp->phase |= resetted; SETPORT(SCSIDAT, MSGO(MSGO_I++)); } @@ -1936,7 +1933,7 @@ static void msgo_end(struct Scsi_Host *shpnt) */ static void cmd_init(struct Scsi_Host *shpnt) { - if (aha152x_scsi_pointer(CURRENT_SC)->sent_command) { + if (aha152x_priv(CURRENT_SC)->sent_command) { scmd_printk(KERN_ERR, CURRENT_SC, "command already sent\n"); done(shpnt, SAM_STAT_GOOD, DID_ERROR); @@ -1967,7 +1964,7 @@ static void cmd_end(struct Scsi_Host *shpnt) "command sent incompletely (%d/%d)\n", CMD_I, CURRENT_SC->cmd_len); else - aha152x_scsi_pointer(CURRENT_SC)->sent_command++; + aha152x_priv(CURRENT_SC)->sent_command++; } /* @@ -1979,7 +1976,7 @@ static void status_run(struct Scsi_Host *shpnt) if (TESTLO(SSTAT0, SPIORDY)) return; - aha152x_scsi_pointer(CURRENT_SC)->Status = GETPORT(SCSIDAT); + aha152x_priv(CURRENT_SC)->status = GETPORT(SCSIDAT); } @@ -2003,7 +2000,7 @@ static void datai_init(struct Scsi_Host *shpnt) static void datai_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer; + struct aha152x_cmd_priv *acp; unsigned long the_time; int fifodata, data_count; @@ -2041,36 +2038,35 @@ static void datai_run(struct Scsi_Host *shpnt) fifodata = GETPORT(FIFOSTAT); } - scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); - if (scsi_pointer->this_residual > 0) { - while (fifodata > 0 && scsi_pointer->this_residual > 0) { - data_count = fifodata > scsi_pointer->this_residual ? - scsi_pointer->this_residual : - fifodata; + acp = aha152x_priv(CURRENT_SC); + if (acp->this_residual > 0) { + while (fifodata > 0 && acp->this_residual > 0) { + data_count = fifodata > acp->this_residual ? + acp->this_residual : fifodata; fifodata -= data_count; if (data_count & 1) { SETPORT(DMACNTRL0, ENDMA|_8BIT); - *scsi_pointer->ptr++ = GETPORT(DATAPORT); - scsi_pointer->this_residual--; + *acp->ptr++ = GETPORT(DATAPORT); + acp->this_residual--; DATA_LEN++; SETPORT(DMACNTRL0, ENDMA); } if (data_count > 1) { data_count >>= 1; - insw(DATAPORT, scsi_pointer->ptr, data_count); - scsi_pointer->ptr += 2 * data_count; - scsi_pointer->this_residual -= 2 * data_count; + insw(DATAPORT, acp->ptr, data_count); + acp->ptr += 2 * data_count; + acp->this_residual -= 2 * data_count; DATA_LEN += 2 * data_count; } - if (scsi_pointer->this_residual == 0 && - !sg_is_last(scsi_pointer->buffer)) { + if (acp->this_residual == 0 && + !sg_is_last(acp->buffer)) { /* advance to next buffer */ - scsi_pointer->buffer = sg_next(scsi_pointer->buffer); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = sg_next(acp->buffer); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } } } else if (fifodata > 0) { @@ -2138,15 +2134,15 @@ static void datao_init(struct Scsi_Host *shpnt) static void datao_run(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); unsigned long the_time; int data_count; /* until phase changes or all data sent */ - while (TESTLO(DMASTAT, INTSTAT) && scsi_pointer->this_residual > 0) { + while (TESTLO(DMASTAT, INTSTAT) && acp->this_residual > 0) { data_count = 128; - if (data_count > scsi_pointer->this_residual) - data_count = scsi_pointer->this_residual; + if (data_count > acp->this_residual) + data_count = acp->this_residual; if(TESTLO(DMASTAT, DFIFOEMP)) { scmd_printk(KERN_ERR, CURRENT_SC, @@ -2157,26 +2153,25 @@ static void datao_run(struct Scsi_Host *shpnt) if(data_count & 1) { SETPORT(DMACNTRL0,WRITE_READ|ENDMA|_8BIT); - SETPORT(DATAPORT, *scsi_pointer->ptr++); - scsi_pointer->this_residual--; + SETPORT(DATAPORT, *acp->ptr++); + acp->this_residual--; CMD_INC_RESID(CURRENT_SC, -1); SETPORT(DMACNTRL0,WRITE_READ|ENDMA); } if(data_count > 1) { data_count >>= 1; - outsw(DATAPORT, scsi_pointer->ptr, data_count); - scsi_pointer->ptr += 2 * data_count; - scsi_pointer->this_residual -= 2 * data_count; + outsw(DATAPORT, acp->ptr, data_count); + acp->ptr += 2 * data_count; + acp->this_residual -= 2 * data_count; CMD_INC_RESID(CURRENT_SC, -2 * data_count); } - if (scsi_pointer->this_residual == 0 && - !sg_is_last(scsi_pointer->buffer)) { + if (acp->this_residual == 0 && !sg_is_last(acp->buffer)) { /* advance to next buffer */ - scsi_pointer->buffer = sg_next(scsi_pointer->buffer); - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer); - scsi_pointer->this_residual = scsi_pointer->buffer->length; + acp->buffer = sg_next(acp->buffer); + acp->ptr = SG_ADDRESS(acp->buffer); + acp->this_residual = acp->buffer->length; } the_time=jiffies + 100*HZ; @@ -2192,7 +2187,7 @@ static void datao_run(struct Scsi_Host *shpnt) static void datao_end(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); + struct aha152x_cmd_priv *acp = aha152x_priv(CURRENT_SC); if(TESTLO(DMASTAT, DFIFOEMP)) { u32 datao_cnt = GETSTCNT(); @@ -2211,10 +2206,9 @@ static void datao_end(struct Scsi_Host *shpnt) sg = sg_next(sg); } - scsi_pointer->buffer = sg; - scsi_pointer->ptr = SG_ADDRESS(scsi_pointer->buffer) + done; - scsi_pointer->this_residual = scsi_pointer->buffer->length - - done; + acp->buffer = sg; + acp->ptr = SG_ADDRESS(acp->buffer) + done; + acp->this_residual = acp->buffer->length - done; } SETPORT(SXFRCTL0, CH1|CLRCH1|CLRSTCNT); @@ -2229,7 +2223,6 @@ static void datao_end(struct Scsi_Host *shpnt) */ static int update_state(struct Scsi_Host *shpnt) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(CURRENT_SC); int dataphase=0; unsigned int stat0 = GETPORT(SSTAT0); unsigned int stat1 = GETPORT(SSTAT1); @@ -2244,7 +2237,7 @@ static int update_state(struct Scsi_Host *shpnt) } else if (stat0 & SELDI && PREVSTATE == busfree) { STATE=seldi; } else if (stat0 & SELDO && CURRENT_SC && - (scsi_pointer->phase & selecting)) { + (aha152x_priv(CURRENT_SC)->phase & selecting)) { STATE=seldo; } else if(stat1 & SELTO) { STATE=selto; @@ -2376,8 +2369,7 @@ static void is_complete(struct Scsi_Host *shpnt) SETPORT(SXFRCTL0, CH1); SETPORT(DMACNTRL0, 0); if(CURRENT_SC) - aha152x_scsi_pointer(CURRENT_SC)->phase &= - ~spiordy; + aha152x_priv(CURRENT_SC)->phase &= ~spiordy; } /* @@ -2399,8 +2391,7 @@ static void is_complete(struct Scsi_Host *shpnt) SETPORT(DMACNTRL0, 0); SETPORT(SXFRCTL0, CH1|SPIOEN); if(CURRENT_SC) - aha152x_scsi_pointer(CURRENT_SC)->phase |= - spiordy; + aha152x_priv(CURRENT_SC)->phase |= spiordy; } /* @@ -2490,7 +2481,7 @@ static void disp_enintr(struct Scsi_Host *shpnt) */ static void show_command(struct scsi_cmnd *ptr) { - const int phase = aha152x_scsi_pointer(ptr)->phase; + const int phase = aha152x_priv(ptr)->phase; scsi_print_command(ptr); scmd_printk(KERN_DEBUG, ptr, @@ -2538,8 +2529,8 @@ static void show_queues(struct Scsi_Host *shpnt) static void get_command(struct seq_file *m, struct scsi_cmnd * ptr) { - struct scsi_pointer *scsi_pointer = aha152x_scsi_pointer(ptr); - const int phase = scsi_pointer->phase; + struct aha152x_cmd_priv *acp = aha152x_priv(ptr); + const int phase = acp->phase; int i; seq_printf(m, "%p: target=%d; lun=%d; cmnd=( ", @@ -2549,8 +2540,8 @@ static void get_command(struct seq_file *m, struct scsi_cmnd * ptr) seq_printf(m, "0x%02x ", ptr->cmnd[i]); seq_printf(m, "); resid=%d; residual=%d; buffers=%d; phase |", - scsi_get_resid(ptr), scsi_pointer->this_residual, - sg_nents(scsi_pointer->buffer) - 1); + scsi_get_resid(ptr), acp->this_residual, + sg_nents(acp->buffer) - 1); if (phase & not_issued) seq_puts(m, "not issued|"); diff --git a/drivers/scsi/aic7xxx/aic79xx_osm.h b/drivers/scsi/aic7xxx/aic79xx_osm.h index 679a4fd13874..793fe19993a9 100644 --- a/drivers/scsi/aic7xxx/aic79xx_osm.h +++ b/drivers/scsi/aic7xxx/aic79xx_osm.h @@ -420,8 +420,6 @@ ahd_unlock(struct ahd_softc *ahd, unsigned long *flags) /* config registers for header type 0 devices */ #define PCIR_MAPS 0x10 -#define PCIR_SUBVEND_0 0x2c -#define PCIR_SUBDEV_0 0x2e /****************************** PCI-X definitions *****************************/ #define PCIXR_COMMAND 0x96 diff --git a/drivers/scsi/aic7xxx/aic79xx_pci.c b/drivers/scsi/aic7xxx/aic79xx_pci.c index 2f0bdb9225a4..5fad41b1ab58 100644 --- a/drivers/scsi/aic7xxx/aic79xx_pci.c +++ b/drivers/scsi/aic7xxx/aic79xx_pci.c @@ -260,8 +260,8 @@ ahd_find_pci_device(ahd_dev_softc_t pci) vendor = ahd_pci_read_config(pci, PCIR_DEVVENDOR, /*bytes*/2); device = ahd_pci_read_config(pci, PCIR_DEVICE, /*bytes*/2); - subvendor = ahd_pci_read_config(pci, PCIR_SUBVEND_0, /*bytes*/2); - subdevice = ahd_pci_read_config(pci, PCIR_SUBDEV_0, /*bytes*/2); + subvendor = ahd_pci_read_config(pci, PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); + subdevice = ahd_pci_read_config(pci, PCI_SUBSYSTEM_ID, /*bytes*/2); full_id = ahd_compose_id(device, vendor, subdevice, @@ -298,7 +298,7 @@ ahd_pci_config(struct ahd_softc *ahd, const struct ahd_pci_identity *entry) * Record if this is an HP board. */ subvendor = ahd_pci_read_config(ahd->dev_softc, - PCIR_SUBVEND_0, /*bytes*/2); + PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); if (subvendor == SUBID_HP) ahd->flags |= AHD_HP_BOARD; diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.h b/drivers/scsi/aic7xxx/aic7xxx_osm.h index 4782a304e93c..51d9f4de0734 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_osm.h +++ b/drivers/scsi/aic7xxx/aic7xxx_osm.h @@ -433,8 +433,6 @@ ahc_unlock(struct ahc_softc *ahc, unsigned long *flags) /* config registers for header type 0 devices */ #define PCIR_MAPS 0x10 -#define PCIR_SUBVEND_0 0x2c -#define PCIR_SUBDEV_0 0x2e typedef enum { diff --git a/drivers/scsi/aic7xxx/aic7xxx_pci.c b/drivers/scsi/aic7xxx/aic7xxx_pci.c index dab3a6d12c4d..2d4c85426dc3 100644 --- a/drivers/scsi/aic7xxx/aic7xxx_pci.c +++ b/drivers/scsi/aic7xxx/aic7xxx_pci.c @@ -673,8 +673,8 @@ ahc_find_pci_device(ahc_dev_softc_t pci) vendor = ahc_pci_read_config(pci, PCIR_DEVVENDOR, /*bytes*/2); device = ahc_pci_read_config(pci, PCIR_DEVICE, /*bytes*/2); - subvendor = ahc_pci_read_config(pci, PCIR_SUBVEND_0, /*bytes*/2); - subdevice = ahc_pci_read_config(pci, PCIR_SUBDEV_0, /*bytes*/2); + subvendor = ahc_pci_read_config(pci, PCI_SUBSYSTEM_VENDOR_ID, /*bytes*/2); + subdevice = ahc_pci_read_config(pci, PCI_SUBSYSTEM_ID, /*bytes*/2); full_id = ahc_compose_id(device, vendor, subdevice, subvendor); /* diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c index 0103f811cc25..776544385598 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c +++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c @@ -1169,7 +1169,7 @@ static void bnx2fc_process_ofld_cmpl(struct bnx2fc_hba *hba, ofld_kcqe->fcoe_conn_context_id); interface = tgt->port->priv; if (hba != interface->hba) { - printk(KERN_ERR PFX "ERROR:ofld_cmpl: HBA mis-match\n"); + printk(KERN_ERR PFX "ERROR:ofld_cmpl: HBA mismatch\n"); goto ofld_cmpl_err; } /* @@ -1226,12 +1226,12 @@ static void bnx2fc_process_enable_conn_cmpl(struct bnx2fc_hba *hba, * and enable */ if (tgt->context_id != context_id) { - printk(KERN_ERR PFX "context id mis-match\n"); + printk(KERN_ERR PFX "context id mismatch\n"); return; } interface = tgt->port->priv; if (hba != interface->hba) { - printk(KERN_ERR PFX "bnx2fc-enbl_cmpl: HBA mis-match\n"); + printk(KERN_ERR PFX "bnx2fc-enbl_cmpl: HBA mismatch\n"); goto enbl_cmpl_err; } if (!ofld_kcqe->completion_status) diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c index 5521469ce678..7fe7f53a41c0 100644 --- a/drivers/scsi/bnx2i/bnx2i_hwi.c +++ b/drivers/scsi/bnx2i/bnx2i_hwi.c @@ -2398,7 +2398,7 @@ static void bnx2i_process_conn_destroy_cmpl(struct bnx2i_hba *hba, } if (hba != ep->hba) { - printk(KERN_ALERT "conn destroy- error hba mis-match\n"); + printk(KERN_ALERT "conn destroy- error hba mismatch\n"); return; } @@ -2432,7 +2432,7 @@ static void bnx2i_process_ofld_cmpl(struct bnx2i_hba *hba, } if (hba != ep->hba) { - printk(KERN_ALERT "ofld_cmpl: error hba mis-match\n"); + printk(KERN_ALERT "ofld_cmpl: error hba mismatch\n"); return; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 461ef8a76c4c..4bda2f6cb352 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -442,7 +442,6 @@ void hisi_sas_task_deliver(struct hisi_hba *hisi_hba, case SAS_PROTOCOL_INTERNAL_ABORT: hisi_sas_task_prep_abort(hisi_hba, slot); break; - fallthrough; default: return; } diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c index 80238e6a3c98..eee1a24f7e15 100644 --- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c +++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c @@ -36,7 +36,7 @@ #define IBMVSCSIS_VERSION "v0.2" -#define INITIAL_SRP_LIMIT 800 +#define INITIAL_SRP_LIMIT 1024 #define DEFAULT_MAX_SECTORS 256 #define MAX_TXU 1024 * 1024 diff --git a/drivers/scsi/isci/host.c b/drivers/scsi/isci/host.c index d690d9cf7eb1..35589b6af90d 100644 --- a/drivers/scsi/isci/host.c +++ b/drivers/scsi/isci/host.c @@ -413,7 +413,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) dev_warn(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received " "event 0x%x for io request object " - "that doesnt exist.\n", + "that doesn't exist.\n", __func__, ihost, ent); @@ -428,7 +428,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) dev_warn(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received " "event 0x%x for remote device object " - "that doesnt exist.\n", + "that doesn't exist.\n", __func__, ihost, ent); @@ -462,7 +462,7 @@ static void sci_controller_event_completion(struct isci_host *ihost, u32 ent) } else dev_err(&ihost->pdev->dev, "%s: SCIC Controller 0x%p received event 0x%x " - "for remote device object 0x%0x that doesnt " + "for remote device object 0x%0x that doesn't " "exist.\n", __func__, ihost, diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index d09926e6c8a8..cf4211c6500d 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -3045,7 +3045,6 @@ iscsi_conn_setup(struct iscsi_cls_session *cls_session, int dd_size, if (!cls_conn) return NULL; conn = cls_conn->dd_data; - memset(conn, 0, sizeof(*conn) + dd_size); conn->dd_data = cls_conn->dd_data + sizeof(*conn); conn->session = session; diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index f0cf8ffdc5f3..0025760230e5 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -897,6 +897,11 @@ enum lpfc_irq_chann_mode { NHT_MODE, }; +enum lpfc_hba_bit_flags { + FABRIC_COMANDS_BLOCKED, + HBA_PCI_ERR, +}; + struct lpfc_hba { /* SCSI interface function jump table entries */ struct lpfc_io_buf * (*lpfc_get_scsi_buf) @@ -1043,7 +1048,6 @@ struct lpfc_hba { * Firmware supports Forced Link Speed * capability */ -#define HBA_PCI_ERR 0x80000 /* The PCI slot is offline */ #define HBA_FLOGI_ISSUED 0x100000 /* FLOGI was issued */ #define HBA_SHORT_CMF 0x200000 /* shorter CMF timer routine */ #define HBA_CGN_DAY_WRAP 0x400000 /* HBA Congestion info day wraps */ @@ -1350,7 +1354,6 @@ struct lpfc_hba { atomic_t fabric_iocb_count; struct timer_list fabric_block_timer; unsigned long bit_flags; -#define FABRIC_COMANDS_BLOCKED 0 atomic_t num_rsrc_err; atomic_t num_cmd_success; unsigned long last_rsrc_error_time; diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h index 96408cd6c4c8..9897a1aa387b 100644 --- a/drivers/scsi/lpfc/lpfc_crtn.h +++ b/drivers/scsi/lpfc/lpfc_crtn.h @@ -670,3 +670,6 @@ struct lpfc_vmid *lpfc_get_vmid_from_hashtable(struct lpfc_vport *vport, uint32_t hash, uint8_t *buf); void lpfc_vmid_vport_cleanup(struct lpfc_vport *vport); int lpfc_issue_els_qfpa(struct lpfc_vport *vport); + +void lpfc_sli_rpi_release(struct lpfc_vport *vport, + struct lpfc_nodelist *ndlp); diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 0144da30e3db..2b877dff5ed4 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -109,8 +109,8 @@ lpfc_rport_invalid(struct fc_rport *rport) ndlp = rdata->pnode; if (!rdata->pnode) { - pr_err("**** %s: NULL ndlp on rport x%px SID x%x\n", - __func__, rport, rport->scsi_target_id); + pr_info("**** %s: NULL ndlp on rport x%px SID x%x\n", + __func__, rport, rport->scsi_target_id); return -EINVAL; } @@ -169,9 +169,10 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, "3181 dev_loss_callbk x%06x, rport x%px flg x%x " - "load_flag x%x refcnt %d\n", + "load_flag x%x refcnt %d state %d xpt x%x\n", ndlp->nlp_DID, ndlp->rport, ndlp->nlp_flag, - vport->load_flag, kref_read(&ndlp->kref)); + vport->load_flag, kref_read(&ndlp->kref), + ndlp->nlp_state, ndlp->fc4_xpt_flags); /* Don't schedule a worker thread event if the vport is going down. * The teardown process cleans up the node via lpfc_drop_node. @@ -181,6 +182,11 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) ndlp->rport = NULL; ndlp->fc4_xpt_flags &= ~SCSI_XPT_REGD; + /* clear the NLP_XPT_REGD if the node is not registered + * with nvme-fc + */ + if (ndlp->fc4_xpt_flags == NLP_XPT_REGD) + ndlp->fc4_xpt_flags &= ~NLP_XPT_REGD; /* Remove the node reference from remote_port_add now. * The driver will not call remote_port_delete. @@ -225,18 +231,36 @@ lpfc_dev_loss_tmo_callbk(struct fc_rport *rport) ndlp->rport = NULL; spin_unlock_irqrestore(&ndlp->lock, iflags); - /* We need to hold the node by incrementing the reference - * count until this queued work is done - */ - evtp->evt_arg1 = lpfc_nlp_get(ndlp); + if (phba->worker_thread) { + /* We need to hold the node by incrementing the reference + * count until this queued work is done + */ + evtp->evt_arg1 = lpfc_nlp_get(ndlp); + + spin_lock_irqsave(&phba->hbalock, iflags); + if (evtp->evt_arg1) { + evtp->evt = LPFC_EVT_DEV_LOSS; + list_add_tail(&evtp->evt_listp, &phba->work_list); + lpfc_worker_wake_up(phba); + } + spin_unlock_irqrestore(&phba->hbalock, iflags); + } else { + lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE, + "3188 worker thread is stopped %s x%06x, " + " rport x%px flg x%x load_flag x%x refcnt " + "%d\n", __func__, ndlp->nlp_DID, + ndlp->rport, ndlp->nlp_flag, + vport->load_flag, kref_read(&ndlp->kref)); + if (!(ndlp->fc4_xpt_flags & NVME_XPT_REGD)) { + spin_lock_irqsave(&ndlp->lock, iflags); + /* Node is in dev loss. No further transaction. */ + ndlp->nlp_flag &= ~NLP_IN_DEV_LOSS; + spin_unlock_irqrestore(&ndlp->lock, iflags); + lpfc_disc_state_machine(vport, ndlp, NULL, + NLP_EVT_DEVICE_RM); + } - spin_lock_irqsave(&phba->hbalock, iflags); - if (evtp->evt_arg1) { - evtp->evt = LPFC_EVT_DEV_LOSS; - list_add_tail(&evtp->evt_listp, &phba->work_list); - lpfc_worker_wake_up(phba); } - spin_unlock_irqrestore(&phba->hbalock, iflags); return; } @@ -503,11 +527,12 @@ lpfc_dev_loss_tmo_handler(struct lpfc_nodelist *ndlp) lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, "0203 Devloss timeout on " "WWPN %02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x " - "NPort x%06x Data: x%x x%x x%x\n", + "NPort x%06x Data: x%x x%x x%x refcnt %d\n", *name, *(name+1), *(name+2), *(name+3), *(name+4), *(name+5), *(name+6), *(name+7), ndlp->nlp_DID, ndlp->nlp_flag, - ndlp->nlp_state, ndlp->nlp_rpi); + ndlp->nlp_state, ndlp->nlp_rpi, + kref_read(&ndlp->kref)); } else { lpfc_printf_vlog(vport, KERN_INFO, LOG_TRACE_EVENT, "0204 Devloss timeout on " @@ -755,18 +780,22 @@ lpfc_work_list_done(struct lpfc_hba *phba) int free_evt; int fcf_inuse; uint32_t nlp_did; + bool hba_pci_err; spin_lock_irq(&phba->hbalock); while (!list_empty(&phba->work_list)) { list_remove_head((&phba->work_list), evtp, typeof(*evtp), evt_listp); spin_unlock_irq(&phba->hbalock); + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); free_evt = 1; switch (evtp->evt) { case LPFC_EVT_ELS_RETRY: ndlp = (struct lpfc_nodelist *) (evtp->evt_arg1); - lpfc_els_retry_delay_handler(ndlp); - free_evt = 0; /* evt is part of ndlp */ + if (!hba_pci_err) { + lpfc_els_retry_delay_handler(ndlp); + free_evt = 0; /* evt is part of ndlp */ + } /* decrement the node reference count held * for this queued work */ @@ -788,8 +817,10 @@ lpfc_work_list_done(struct lpfc_hba *phba) break; case LPFC_EVT_RECOVER_PORT: ndlp = (struct lpfc_nodelist *)(evtp->evt_arg1); - lpfc_sli_abts_recover_port(ndlp->vport, ndlp); - free_evt = 0; + if (!hba_pci_err) { + lpfc_sli_abts_recover_port(ndlp->vport, ndlp); + free_evt = 0; + } /* decrement the node reference count held for * this queued work */ @@ -859,14 +890,18 @@ lpfc_work_done(struct lpfc_hba *phba) struct lpfc_vport **vports; struct lpfc_vport *vport; int i; + bool hba_pci_err; + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); spin_lock_irq(&phba->hbalock); ha_copy = phba->work_ha; phba->work_ha = 0; spin_unlock_irq(&phba->hbalock); + if (hba_pci_err) + ha_copy = 0; /* First, try to post the next mailbox command to SLI4 device */ - if (phba->pci_dev_grp == LPFC_PCI_DEV_OC) + if (phba->pci_dev_grp == LPFC_PCI_DEV_OC && !hba_pci_err) lpfc_sli4_post_async_mbox(phba); if (ha_copy & HA_ERATT) { @@ -886,7 +921,7 @@ lpfc_work_done(struct lpfc_hba *phba) lpfc_handle_latt(phba); /* Handle VMID Events */ - if (lpfc_is_vmid_enabled(phba)) { + if (lpfc_is_vmid_enabled(phba) && !hba_pci_err) { if (phba->pport->work_port_events & WORKER_CHECK_VMID_ISSUE_QFPA) { lpfc_check_vmid_qfpa_issue(phba); @@ -936,6 +971,8 @@ lpfc_work_done(struct lpfc_hba *phba) work_port_events = vport->work_port_events; vport->work_port_events &= ~work_port_events; spin_unlock_irq(&vport->work_port_lock); + if (hba_pci_err) + continue; if (work_port_events & WORKER_DISC_TMO) lpfc_disc_timeout_handler(vport); if (work_port_events & WORKER_ELS_TMO) @@ -1173,12 +1210,14 @@ lpfc_linkdown(struct lpfc_hba *phba) struct lpfc_vport **vports; LPFC_MBOXQ_t *mb; int i; + int offline; if (phba->link_state == LPFC_LINK_DOWN) return 0; /* Block all SCSI stack I/Os */ lpfc_scsi_dev_block(phba); + offline = pci_channel_offline(phba->pcidev); phba->defer_flogi_acc_flag = false; @@ -1219,7 +1258,7 @@ lpfc_linkdown(struct lpfc_hba *phba) lpfc_destroy_vport_work_array(phba, vports); /* Clean up any SLI3 firmware default rpi's */ - if (phba->sli_rev > LPFC_SLI_REV3) + if (phba->sli_rev > LPFC_SLI_REV3 || offline) goto skip_unreg_did; mb = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); @@ -4712,6 +4751,11 @@ lpfc_nlp_unreg_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) spin_lock_irqsave(&ndlp->lock, iflags); if (!(ndlp->fc4_xpt_flags & NLP_XPT_REGD)) { spin_unlock_irqrestore(&ndlp->lock, iflags); + lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, + "0999 %s Not regd: ndlp x%px rport x%px DID " + "x%x FLG x%x XPT x%x\n", + __func__, ndlp, ndlp->rport, ndlp->nlp_DID, + ndlp->nlp_flag, ndlp->fc4_xpt_flags); return; } @@ -4722,6 +4766,13 @@ lpfc_nlp_unreg_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->fc4_xpt_flags & SCSI_XPT_REGD) { vport->phba->nport_event_cnt++; lpfc_unregister_remote_port(ndlp); + } else if (!ndlp->rport) { + lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI, + "1999 %s NDLP in devloss x%px DID x%x FLG x%x" + " XPT x%x refcnt %d\n", + __func__, ndlp, ndlp->nlp_DID, ndlp->nlp_flag, + ndlp->fc4_xpt_flags, + kref_read(&ndlp->kref)); } if (ndlp->fc4_xpt_flags & NVME_XPT_REGD) { @@ -5371,6 +5422,7 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->nlp_flag &= ~NLP_UNREG_INP; mempool_free(mbox, phba->mbox_mem_pool); acc_plogi = 1; + lpfc_nlp_put(ndlp); } } else { lpfc_printf_vlog(vport, KERN_INFO, @@ -6097,12 +6149,34 @@ lpfc_disc_flush_list(struct lpfc_vport *vport) } } +/* + * lpfc_notify_xport_npr - notifies xport of node disappearance + * @vport: Pointer to Virtual Port object. + * + * Transitions all ndlps to NPR state. When lpfc_nlp_set_state + * calls lpfc_nlp_state_cleanup, the ndlp->rport is unregistered + * and transport notified that the node is gone. + * Return Code: + * none + */ +static void +lpfc_notify_xport_npr(struct lpfc_vport *vport) +{ + struct lpfc_nodelist *ndlp, *next_ndlp; + + list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, + nlp_listp) { + lpfc_nlp_set_state(vport, ndlp, NLP_STE_NPR_NODE); + } +} void lpfc_cleanup_discovery_resources(struct lpfc_vport *vport) { lpfc_els_flush_rscn(vport); lpfc_els_flush_cmd(vport); lpfc_disc_flush_list(vport); + if (pci_channel_offline(vport->phba->pcidev)) + lpfc_notify_xport_npr(vport); } /*****************************************************************************/ diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index eed6464bd880..461d333b1b3a 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -95,6 +95,7 @@ static void lpfc_sli4_oas_verify(struct lpfc_hba *phba); static uint16_t lpfc_find_cpu_handle(struct lpfc_hba *, uint16_t, int); static void lpfc_setup_bg(struct lpfc_hba *, struct Scsi_Host *); static int lpfc_sli4_cgn_parm_chg_evt(struct lpfc_hba *); +static void lpfc_sli4_prep_dev_for_reset(struct lpfc_hba *phba); static struct scsi_transport_template *lpfc_transport_template = NULL; static struct scsi_transport_template *lpfc_vport_transport_template = NULL; @@ -1642,7 +1643,7 @@ lpfc_sli4_offline_eratt(struct lpfc_hba *phba) { spin_lock_irq(&phba->hbalock); if (phba->link_state == LPFC_HBA_ERROR && - phba->hba_flag & HBA_PCI_ERR) { + test_bit(HBA_PCI_ERR, &phba->bit_flags)) { spin_unlock_irq(&phba->hbalock); return; } @@ -1985,6 +1986,7 @@ lpfc_handle_eratt_s4(struct lpfc_hba *phba) if (pci_channel_offline(phba->pcidev)) { lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "3166 pci channel is offline\n"); + lpfc_sli_flush_io_rings(phba); return; } @@ -2973,6 +2975,22 @@ lpfc_cleanup(struct lpfc_vport *vport) NLP_EVT_DEVICE_RM); } + /* This is a special case flush to return all + * IOs before entering this loop. There are + * two points in the code where a flush is + * avoided if the FC_UNLOADING flag is set. + * one is in the multipool destroy, + * (this prevents a crash) and the other is + * in the nvme abort handler, ( also prevents + * a crash). Both of these exceptions are + * cases where the slot is still accessible. + * The flush here is only when the pci slot + * is offline. + */ + if (vport->load_flag & FC_UNLOADING && + pci_channel_offline(phba->pcidev)) + lpfc_sli_flush_io_rings(vport->phba); + /* At this point, ALL ndlp's should be gone * because of the previous NLP_EVT_DEVICE_RM. * Lets wait for this to happen, if needed. @@ -2985,7 +3003,7 @@ lpfc_cleanup(struct lpfc_vport *vport) list_for_each_entry_safe(ndlp, next_ndlp, &vport->fc_nodes, nlp_listp) { lpfc_printf_vlog(ndlp->vport, KERN_ERR, - LOG_TRACE_EVENT, + LOG_DISCOVERY, "0282 did:x%x ndlp:x%px " "refcnt:%d xflags x%x nflag x%x\n", ndlp->nlp_DID, (void *)ndlp, @@ -3682,7 +3700,8 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) struct lpfc_vport **vports; struct Scsi_Host *shost; int i; - int offline = 0; + int offline; + bool hba_pci_err; if (vport->fc_flag & FC_OFFLINE_MODE) return; @@ -3692,6 +3711,7 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) lpfc_linkdown(phba); offline = pci_channel_offline(phba->pcidev); + hba_pci_err = test_bit(HBA_PCI_ERR, &phba->bit_flags); /* Issue an unreg_login to all nodes on all vports */ vports = lpfc_create_vport_work_array(phba); @@ -3715,11 +3735,14 @@ lpfc_offline_prep(struct lpfc_hba *phba, int mbx_action) ndlp->nlp_flag &= ~NLP_NPR_ADISC; spin_unlock_irq(&ndlp->lock); - if (offline) { + if (offline || hba_pci_err) { spin_lock_irq(&ndlp->lock); ndlp->nlp_flag &= ~(NLP_UNREG_INP | NLP_RPI_REGISTERED); spin_unlock_irq(&ndlp->lock); + if (phba->sli_rev == LPFC_SLI_REV4) + lpfc_sli_rpi_release(vports[i], + ndlp); } else { lpfc_unreg_rpi(vports[i], ndlp); } @@ -13354,8 +13377,9 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba) /* Abort all iocbs associated with the hba */ lpfc_sli_hba_iocb_abort(phba); - /* Wait for completion of device XRI exchange busy */ - lpfc_sli4_xri_exchange_busy_wait(phba); + if (!pci_channel_offline(phba->pcidev)) + /* Wait for completion of device XRI exchange busy */ + lpfc_sli4_xri_exchange_busy_wait(phba); /* per-phba callback de-registration for hotplug event */ if (phba->pport) @@ -13374,15 +13398,12 @@ lpfc_sli4_hba_unset(struct lpfc_hba *phba) /* Disable FW logging to host memory */ lpfc_ras_stop_fwlog(phba); - /* Unset the queues shared with the hardware then release all - * allocated resources. - */ - lpfc_sli4_queue_unset(phba); - lpfc_sli4_queue_destroy(phba); - /* Reset SLI4 HBA FCoE function */ lpfc_pci_function_reset(phba); + /* release all queue allocated resources. */ + lpfc_sli4_queue_destroy(phba); + /* Free RAS DMA memory */ if (phba->ras_fwlog.ras_enabled) lpfc_sli4_ras_dma_free(phba); @@ -14262,6 +14283,7 @@ lpfc_sli_prep_dev_for_perm_failure(struct lpfc_hba *phba) "2711 PCI channel permanent disable for failure\n"); /* Block all SCSI devices' I/Os on the host */ lpfc_scsi_dev_block(phba); + lpfc_sli4_prep_dev_for_reset(phba); /* stop all timers */ lpfc_stop_hba_timers(phba); @@ -15057,24 +15079,28 @@ lpfc_sli4_prep_dev_for_recover(struct lpfc_hba *phba) static void lpfc_sli4_prep_dev_for_reset(struct lpfc_hba *phba) { - lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, - "2826 PCI channel disable preparing for reset\n"); + int offline = pci_channel_offline(phba->pcidev); + + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "2826 PCI channel disable preparing for reset offline" + " %d\n", offline); /* Block any management I/Os to the device */ lpfc_block_mgmt_io(phba, LPFC_MBX_NO_WAIT); - /* Block all SCSI devices' I/Os on the host */ - lpfc_scsi_dev_block(phba); + /* HBA_PCI_ERR was set in io_error_detect */ + lpfc_offline_prep(phba, LPFC_MBX_NO_WAIT); /* Flush all driver's outstanding I/Os as we are to reset */ lpfc_sli_flush_io_rings(phba); + lpfc_offline(phba); /* stop all timers */ lpfc_stop_hba_timers(phba); + lpfc_sli4_queue_destroy(phba); /* Disable interrupt and pci device */ lpfc_sli4_disable_intr(phba); - lpfc_sli4_queue_destroy(phba); pci_disable_device(phba->pcidev); } @@ -15123,6 +15149,7 @@ lpfc_io_error_detected_s4(struct pci_dev *pdev, pci_channel_state_t state) { struct Scsi_Host *shost = pci_get_drvdata(pdev); struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba; + bool hba_pci_err; switch (state) { case pci_channel_io_normal: @@ -15130,17 +15157,24 @@ lpfc_io_error_detected_s4(struct pci_dev *pdev, pci_channel_state_t state) lpfc_sli4_prep_dev_for_recover(phba); return PCI_ERS_RESULT_CAN_RECOVER; case pci_channel_io_frozen: - phba->hba_flag |= HBA_PCI_ERR; + hba_pci_err = test_and_set_bit(HBA_PCI_ERR, &phba->bit_flags); /* Fatal error, prepare for slot reset */ - lpfc_sli4_prep_dev_for_reset(phba); + if (!hba_pci_err) + lpfc_sli4_prep_dev_for_reset(phba); + else + lpfc_printf_log(phba, KERN_ERR, LOG_INIT, + "2832 Already handling PCI error " + "state: x%x\n", state); return PCI_ERS_RESULT_NEED_RESET; case pci_channel_io_perm_failure: - phba->hba_flag |= HBA_PCI_ERR; + set_bit(HBA_PCI_ERR, &phba->bit_flags); /* Permanent failure, prepare for device down */ lpfc_sli4_prep_dev_for_perm_failure(phba); return PCI_ERS_RESULT_DISCONNECT; default: - phba->hba_flag |= HBA_PCI_ERR; + hba_pci_err = test_and_set_bit(HBA_PCI_ERR, &phba->bit_flags); + if (!hba_pci_err) + lpfc_sli4_prep_dev_for_reset(phba); /* Unknown state, prepare and request slot reset */ lpfc_printf_log(phba, KERN_ERR, LOG_TRACE_EVENT, "2825 Unknown PCI error state: x%x\n", state); @@ -15174,17 +15208,21 @@ lpfc_io_slot_reset_s4(struct pci_dev *pdev) struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba; struct lpfc_sli *psli = &phba->sli; uint32_t intr_mode; + bool hba_pci_err; dev_printk(KERN_INFO, &pdev->dev, "recovering from a slot reset.\n"); if (pci_enable_device_mem(pdev)) { printk(KERN_ERR "lpfc: Cannot re-enable " - "PCI device after reset.\n"); + "PCI device after reset.\n"); return PCI_ERS_RESULT_DISCONNECT; } pci_restore_state(pdev); - phba->hba_flag &= ~HBA_PCI_ERR; + hba_pci_err = test_and_clear_bit(HBA_PCI_ERR, &phba->bit_flags); + if (!hba_pci_err) + dev_info(&pdev->dev, + "hba_pci_err was not set, recovering slot reset.\n"); /* * As the new kernel behavior of pci_restore_state() API call clears * device saved_state flag, need to save the restored state again. @@ -15198,6 +15236,8 @@ lpfc_io_slot_reset_s4(struct pci_dev *pdev) psli->sli_flag &= ~LPFC_SLI_ACTIVE; spin_unlock_irq(&phba->hbalock); + /* Init cpu_map array */ + lpfc_cpu_map_array_init(phba); /* Configure and enable interrupt */ intr_mode = lpfc_sli4_enable_intr(phba, phba->intr_mode); if (intr_mode == LPFC_INTR_ERROR) { @@ -15239,8 +15279,6 @@ lpfc_io_resume_s4(struct pci_dev *pdev) */ if (!(phba->sli.sli_flag & LPFC_SLI_ACTIVE)) { /* Perform device reset */ - lpfc_offline_prep(phba, LPFC_MBX_WAIT); - lpfc_offline(phba); lpfc_sli_brdrestart(phba); /* Bring the device back online */ lpfc_online(phba); diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index 1213a299f9aa..8d26f207ebd2 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -93,6 +93,11 @@ lpfc_nvme_create_queue(struct nvme_fc_local_port *pnvme_lport, lport = (struct lpfc_nvme_lport *)pnvme_lport->private; vport = lport->vport; + + if (!vport || vport->load_flag & FC_UNLOADING || + vport->phba->hba_flag & HBA_IOQ_FLUSH) + return -ENODEV; + qhandle = kzalloc(sizeof(struct lpfc_nvme_qhandle), GFP_KERNEL); if (qhandle == NULL) return -ENOMEM; @@ -267,7 +272,8 @@ lpfc_nvme_handle_lsreq(struct lpfc_hba *phba, return -EINVAL; remoteport = lpfc_rport->remoteport; - if (!vport->localport) + if (!vport->localport || + vport->phba->hba_flag & HBA_IOQ_FLUSH) return -EINVAL; lport = vport->localport->private; @@ -559,6 +565,8 @@ __lpfc_nvme_ls_req(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, ndlp->nlp_DID, ntype, nstate); return -ENODEV; } + if (vport->phba->hba_flag & HBA_IOQ_FLUSH) + return -ENODEV; if (!vport->phba->sli4_hba.nvmels_wq) return -ENOMEM; @@ -662,7 +670,8 @@ lpfc_nvme_ls_req(struct nvme_fc_local_port *pnvme_lport, return -EINVAL; vport = lport->vport; - if (vport->load_flag & FC_UNLOADING) + if (vport->load_flag & FC_UNLOADING || + vport->phba->hba_flag & HBA_IOQ_FLUSH) return -ENODEV; atomic_inc(&lport->fc4NvmeLsRequests); @@ -1516,7 +1525,8 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport, phba = vport->phba; - if (unlikely(vport->load_flag & FC_UNLOADING)) { + if ((unlikely(vport->load_flag & FC_UNLOADING)) || + phba->hba_flag & HBA_IOQ_FLUSH) { lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR, "6124 Fail IO, Driver unload\n"); atomic_inc(&lport->xmt_fcp_err); @@ -2169,8 +2179,7 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport, abts_nvme = 0; for (i = 0; i < phba->cfg_hdw_queue; i++) { qp = &phba->sli4_hba.hdwq[i]; - if (!vport || !vport->localport || - !qp || !qp->io_wq) + if (!vport->localport || !qp || !qp->io_wq) return; pring = qp->io_wq->pring; @@ -2180,8 +2189,9 @@ lpfc_nvme_lport_unreg_wait(struct lpfc_vport *vport, abts_scsi += qp->abts_scsi_io_bufs; abts_nvme += qp->abts_nvme_io_bufs; } - if (!vport || !vport->localport || - vport->phba->hba_flag & HBA_PCI_ERR) + if (!vport->localport || + test_bit(HBA_PCI_ERR, &vport->phba->bit_flags) || + vport->load_flag & FC_UNLOADING) return; lpfc_printf_vlog(vport, KERN_ERR, LOG_TRACE_EVENT, @@ -2541,8 +2551,7 @@ lpfc_nvme_unregister_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) * return values is ignored. The upcall is a courtesy to the * transport. */ - if (vport->load_flag & FC_UNLOADING || - unlikely(vport->phba->hba_flag & HBA_PCI_ERR)) + if (vport->load_flag & FC_UNLOADING) (void)nvme_fc_set_remoteport_devloss(remoteport, 0); ret = nvme_fc_unregister_remoteport(remoteport); diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c index 3c132604fd91..ba9dbb51b75f 100644 --- a/drivers/scsi/lpfc/lpfc_scsi.c +++ b/drivers/scsi/lpfc/lpfc_scsi.c @@ -5929,13 +5929,15 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd) } lpfc_cmd->waitq = &waitq; - if (phba->sli_rev == LPFC_SLI_REV4) + if (phba->sli_rev == LPFC_SLI_REV4) { spin_unlock(&pring_s4->ring_lock); - else + ret_val = lpfc_sli4_issue_abort_iotag(phba, iocb, + lpfc_sli_abort_fcp_cmpl); + } else { pring = &phba->sli.sli3_ring[LPFC_FCP_RING]; - - ret_val = lpfc_sli_issue_abort_iotag(phba, pring, iocb, - lpfc_sli_abort_fcp_cmpl); + ret_val = lpfc_sli_issue_abort_iotag(phba, pring, iocb, + lpfc_sli_abort_fcp_cmpl); + } /* Make sure HBA is alive */ lpfc_issue_hb_tmo(phba); diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 20d40957a385..bda2a7ba4e77 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -2828,6 +2828,12 @@ __lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) ndlp->nlp_flag &= ~NLP_UNREG_INP; } +void +lpfc_sli_rpi_release(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp) +{ + __lpfc_sli_rpi_release(vport, ndlp); +} + /** * lpfc_sli_def_mbox_cmpl - Default mailbox completion handler * @phba: Pointer to HBA context object. @@ -3715,7 +3721,15 @@ lpfc_sli_process_sol_iocb(struct lpfc_hba *phba, struct lpfc_sli_ring *pring, unsigned long iflag; u32 ulp_command, ulp_status, ulp_word4, ulp_context, iotag; + if (phba->sli_rev == LPFC_SLI_REV4) + spin_lock_irqsave(&pring->ring_lock, iflag); + else + spin_lock_irqsave(&phba->hbalock, iflag); cmdiocbp = lpfc_sli_iocbq_lookup(phba, pring, saveq); + if (phba->sli_rev == LPFC_SLI_REV4) + spin_unlock_irqrestore(&pring->ring_lock, iflag); + else + spin_unlock_irqrestore(&phba->hbalock, iflag); ulp_command = get_job_cmnd(phba, saveq); ulp_status = get_job_ulpstatus(phba, saveq); @@ -4052,10 +4066,8 @@ lpfc_sli_handle_fast_ring_event(struct lpfc_hba *phba, break; } - spin_unlock_irqrestore(&phba->hbalock, iflag); cmdiocbq = lpfc_sli_iocbq_lookup(phba, pring, &rspiocbq); - spin_lock_irqsave(&phba->hbalock, iflag); if (unlikely(!cmdiocbq)) break; if (cmdiocbq->cmd_flag & LPFC_DRIVER_ABORTED) @@ -4536,42 +4548,62 @@ lpfc_sli_handle_slow_ring_event_s4(struct lpfc_hba *phba, void lpfc_sli_abort_iocb_ring(struct lpfc_hba *phba, struct lpfc_sli_ring *pring) { - LIST_HEAD(completions); + LIST_HEAD(tx_completions); + LIST_HEAD(txcmplq_completions); struct lpfc_iocbq *iocb, *next_iocb; + int offline; if (pring->ringno == LPFC_ELS_RING) { lpfc_fabric_abort_hba(phba); } + offline = pci_channel_offline(phba->pcidev); /* Error everything on txq and txcmplq * First do the txq. */ if (phba->sli_rev >= LPFC_SLI_REV4) { spin_lock_irq(&pring->ring_lock); - list_splice_init(&pring->txq, &completions); + list_splice_init(&pring->txq, &tx_completions); pring->txq_cnt = 0; - spin_unlock_irq(&pring->ring_lock); - spin_lock_irq(&phba->hbalock); - /* Next issue ABTS for everything on the txcmplq */ - list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list) - lpfc_sli_issue_abort_iotag(phba, pring, iocb, NULL); - spin_unlock_irq(&phba->hbalock); + if (offline) { + list_splice_init(&pring->txcmplq, + &txcmplq_completions); + } else { + /* Next issue ABTS for everything on the txcmplq */ + list_for_each_entry_safe(iocb, next_iocb, + &pring->txcmplq, list) + lpfc_sli_issue_abort_iotag(phba, pring, + iocb, NULL); + } + spin_unlock_irq(&pring->ring_lock); } else { spin_lock_irq(&phba->hbalock); - list_splice_init(&pring->txq, &completions); + list_splice_init(&pring->txq, &tx_completions); pring->txq_cnt = 0; - /* Next issue ABTS for everything on the txcmplq */ - list_for_each_entry_safe(iocb, next_iocb, &pring->txcmplq, list) - lpfc_sli_issue_abort_iotag(phba, pring, iocb, NULL); + if (offline) { + list_splice_init(&pring->txcmplq, &txcmplq_completions); + } else { + /* Next issue ABTS for everything on the txcmplq */ + list_for_each_entry_safe(iocb, next_iocb, + &pring->txcmplq, list) + lpfc_sli_issue_abort_iotag(phba, pring, + iocb, NULL); + } spin_unlock_irq(&phba->hbalock); } - /* Make sure HBA is alive */ - lpfc_issue_hb_tmo(phba); + if (offline) { + /* Cancel all the IOCBs from the completions list */ + lpfc_sli_cancel_iocbs(phba, &txcmplq_completions, + IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED); + } else { + /* Make sure HBA is alive */ + lpfc_issue_hb_tmo(phba); + } /* Cancel all the IOCBs from the completions list */ - lpfc_sli_cancel_iocbs(phba, &completions, IOSTAT_LOCAL_REJECT, + lpfc_sli_cancel_iocbs(phba, &tx_completions, IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED); } @@ -4624,11 +4656,6 @@ lpfc_sli_flush_io_rings(struct lpfc_hba *phba) struct lpfc_iocbq *piocb, *next_iocb; spin_lock_irq(&phba->hbalock); - if (phba->hba_flag & HBA_IOQ_FLUSH || - !phba->sli4_hba.hdwq) { - spin_unlock_irq(&phba->hbalock); - return; - } /* Indicate the I/O queues are flushed */ phba->hba_flag |= HBA_IOQ_FLUSH; spin_unlock_irq(&phba->hbalock); @@ -10997,6 +11024,10 @@ lpfc_sli_issue_iocb(struct lpfc_hba *phba, uint32_t ring_number, unsigned long iflags; int rc; + /* If the PCI channel is in offline state, do not post iocbs. */ + if (unlikely(pci_channel_offline(phba->pcidev))) + return IOCB_ERROR; + if (phba->sli_rev == LPFC_SLI_REV4) { lpfc_sli_prep_wqe(phba, piocb); diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h index e52f37e5d896..a4d3259b8c52 100644 --- a/drivers/scsi/lpfc/lpfc_version.h +++ b/drivers/scsi/lpfc/lpfc_version.h @@ -20,7 +20,7 @@ * included with this package. * *******************************************************************/ -#define LPFC_DRIVER_VERSION "14.2.0.0" +#define LPFC_DRIVER_VERSION "14.2.0.1" #define LPFC_DRIVER_NAME "lpfc" /* Used for SLI 2/3 */ diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h index 611871ef15b5..4919ea54b827 100644 --- a/drivers/scsi/megaraid/megaraid_sas.h +++ b/drivers/scsi/megaraid/megaraid_sas.h @@ -2560,6 +2560,9 @@ struct megasas_instance_template { #define MEGASAS_IS_LOGICAL(sdev) \ ((sdev->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1) +#define MEGASAS_IS_LUN_VALID(sdev) \ + (((sdev)->lun == 0) ? 1 : 0) + #define MEGASAS_DEV_INDEX(scp) \ (((scp->device->channel % 2) * MEGASAS_MAX_DEV_PER_CHANNEL) + \ scp->device->id) diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 8bf72dbc33b7..db6793608447 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -2126,6 +2126,9 @@ static int megasas_slave_alloc(struct scsi_device *sdev) goto scan_target; } return -ENXIO; + } else if (!MEGASAS_IS_LUN_VALID(sdev)) { + sdev_printk(KERN_INFO, sdev, "%s: invalid LUN\n", __func__); + return -ENXIO; } scan_target: @@ -2156,6 +2159,10 @@ static void megasas_slave_destroy(struct scsi_device *sdev) instance = megasas_lookup_instance(sdev->host->host_no); if (MEGASAS_IS_LOGICAL(sdev)) { + if (!MEGASAS_IS_LUN_VALID(sdev)) { + sdev_printk(KERN_INFO, sdev, "%s: invalid LUN\n", __func__); + return; + } ld_tgt_id = MEGASAS_TARGET_ID(sdev); instance->ld_tgtid_status[ld_tgt_id] = LD_TARGET_ID_DELETED; if (megasas_dbg_lvl & LD_PD_DEBUG) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index b57f1803371e..538d2c0cd971 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -5716,13 +5716,12 @@ _base_release_memory_pools(struct MPT3SAS_ADAPTER *ioc) /** * mpt3sas_check_same_4gb_region - checks whether all reply queues in a set are * having same upper 32bits in their base memory address. - * @reply_pool_start_address: Base address of a reply queue set + * @start_address: Base address of a reply queue set * @pool_sz: Size of single Reply Descriptor Post Queues pool size * * Return: 1 if reply queues in a set have a same upper 32bits in their base * memory address, else 0. */ - static int mpt3sas_check_same_4gb_region(dma_addr_t start_address, u32 pool_sz) { diff --git a/drivers/scsi/mpt3sas/mpt3sas_config.c b/drivers/scsi/mpt3sas/mpt3sas_config.c index 0563078227de..a8dd14c91efd 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_config.c +++ b/drivers/scsi/mpt3sas/mpt3sas_config.c @@ -394,10 +394,13 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t retry_count++; if (ioc->config_cmds.smid == smid) mpt3sas_base_free_smid(ioc, smid); - if ((ioc->shost_recovery) || (ioc->config_cmds.status & - MPT3_CMD_RESET) || ioc->pci_error_recovery) + if (ioc->config_cmds.status & MPT3_CMD_RESET) goto retry_config; - issue_host_reset = 1; + if (ioc->shost_recovery || ioc->pci_error_recovery) { + issue_host_reset = 0; + r = -EFAULT; + } else + issue_host_reset = 1; goto free_mem; } diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 00792767c620..7e476f50935b 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -11035,6 +11035,7 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, { struct _sas_port *mpt3sas_port, *next; unsigned long flags; + int port_id; /* remove sibling ports attached to this expander */ list_for_each_entry_safe(mpt3sas_port, next, @@ -11055,6 +11056,8 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, mpt3sas_port->hba_port); } + port_id = sas_expander->port->port_id; + mpt3sas_transport_port_remove(ioc, sas_expander->sas_address, sas_expander->sas_address_parent, sas_expander->port); @@ -11062,7 +11065,7 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc, "expander_remove: handle(0x%04x), sas_addr(0x%016llx), port:%d\n", sas_expander->handle, (unsigned long long) sas_expander->sas_address, - sas_expander->port->port_id); + port_id); spin_lock_irqsave(&ioc->sas_node_lock, flags); list_del(&sas_expander->list); diff --git a/drivers/scsi/mvsas/mv_init.c b/drivers/scsi/mvsas/mv_init.c index 7ac63eb5ccd3..2fde496fff5f 100644 --- a/drivers/scsi/mvsas/mv_init.c +++ b/drivers/scsi/mvsas/mv_init.c @@ -647,6 +647,7 @@ static struct pci_device_id mvs_pci_table[] = { { PCI_VDEVICE(ARECA, PCI_DEVICE_ID_ARECA_1300), chip_1300 }, { PCI_VDEVICE(ARECA, PCI_DEVICE_ID_ARECA_1320), chip_1320 }, { PCI_VDEVICE(ADAPTEC2, 0x0450), chip_6440 }, + { PCI_VDEVICE(TTI, 0x2640), chip_6440 }, { PCI_VDEVICE(TTI, 0x2710), chip_9480 }, { PCI_VDEVICE(TTI, 0x2720), chip_9480 }, { PCI_VDEVICE(TTI, 0x2721), chip_9480 }, diff --git a/drivers/scsi/pcmcia/sym53c500_cs.c b/drivers/scsi/pcmcia/sym53c500_cs.c index c4a838635893..5d7dfefd6f6c 100644 --- a/drivers/scsi/pcmcia/sym53c500_cs.c +++ b/drivers/scsi/pcmcia/sym53c500_cs.c @@ -192,10 +192,11 @@ struct sym53c500_data { int fast_pio; }; -static struct scsi_pointer *sym53c500_scsi_pointer(struct scsi_cmnd *cmd) -{ - return scsi_cmd_priv(cmd); -} +struct sym53c500_cmd_priv { + int status; + int message; + int phase; +}; enum Phase { idle, @@ -356,7 +357,7 @@ SYM53C500_intr(int irq, void *dev_id) struct sym53c500_data *data = (struct sym53c500_data *)dev->hostdata; struct scsi_cmnd *curSC = data->current_SC; - struct scsi_pointer *scsi_pointer = sym53c500_scsi_pointer(curSC); + struct sym53c500_cmd_priv *scp = scsi_cmd_priv(curSC); int fast_pio = data->fast_pio; spin_lock_irqsave(dev->host_lock, flags); @@ -403,12 +404,11 @@ SYM53C500_intr(int irq, void *dev_id) if (int_reg & 0x20) { /* Disconnect */ DEB(printk("SYM53C500: disconnect intr received\n")); - if (scsi_pointer->phase != message_in) { /* Unexpected disconnect */ + if (scp->phase != message_in) { /* Unexpected disconnect */ curSC->result = DID_NO_CONNECT << 16; } else { /* Command complete, return status and message */ - curSC->result = (scsi_pointer->Status & 0xff) | - ((scsi_pointer->Message & 0xff) << 8) | - (DID_OK << 16); + curSC->result = (scp->status & 0xff) | + ((scp->message & 0xff) << 8) | (DID_OK << 16); } goto idle_out; } @@ -419,7 +419,7 @@ SYM53C500_intr(int irq, void *dev_id) struct scatterlist *sg; int i; - scsi_pointer->phase = data_out; + scp->phase = data_out; VDEB(printk("SYM53C500: Data-Out phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); LOAD_DMA_COUNT(port_base, scsi_bufflen(curSC)); /* Max transfer size */ @@ -438,7 +438,7 @@ SYM53C500_intr(int irq, void *dev_id) struct scatterlist *sg; int i; - scsi_pointer->phase = data_in; + scp->phase = data_in; VDEB(printk("SYM53C500: Data-In phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); LOAD_DMA_COUNT(port_base, scsi_bufflen(curSC)); /* Max transfer size */ @@ -453,12 +453,12 @@ SYM53C500_intr(int irq, void *dev_id) break; case 0x02: /* COMMAND */ - scsi_pointer->phase = command_ph; + scp->phase = command_ph; printk("SYM53C500: Warning: Unknown interrupt occurred in command phase!\n"); break; case 0x03: /* STATUS */ - scsi_pointer->phase = status_ph; + scp->phase = status_ph; VDEB(printk("SYM53C500: Status phase\n")); outb(FLUSH_FIFO, port_base + CMD_REG); outb(INIT_CMD_COMPLETE, port_base + CMD_REG); @@ -471,24 +471,22 @@ SYM53C500_intr(int irq, void *dev_id) case 0x06: /* MESSAGE-OUT */ DEB(printk("SYM53C500: Message-Out phase\n")); - scsi_pointer->phase = message_out; + scp->phase = message_out; outb(SET_ATN, port_base + CMD_REG); /* Reject the message */ outb(MSG_ACCEPT, port_base + CMD_REG); break; case 0x07: /* MESSAGE-IN */ VDEB(printk("SYM53C500: Message-In phase\n")); - scsi_pointer->phase = message_in; + scp->phase = message_in; - scsi_pointer->Status = inb(port_base + SCSI_FIFO); - scsi_pointer->Message = inb(port_base + SCSI_FIFO); + scp->status = inb(port_base + SCSI_FIFO); + scp->message = inb(port_base + SCSI_FIFO); VDEB(printk("SCSI FIFO size=%d\n", inb(port_base + FIFO_FLAGS) & 0x1f)); - DEB(printk("Status = %02x Message = %02x\n", - scsi_pointer->Status, scsi_pointer->Message)); + DEB(printk("Status = %02x Message = %02x\n", scp->status, scp->message)); - if (scsi_pointer->Message == SAVE_POINTERS || - scsi_pointer->Message == DISCONNECT) { + if (scp->message == SAVE_POINTERS || scp->message == DISCONNECT) { outb(SET_ATN, port_base + CMD_REG); /* Reject message */ DEB(printk("Discarding SAVE_POINTERS message\n")); } @@ -500,7 +498,7 @@ out: return IRQ_HANDLED; idle_out: - scsi_pointer->phase = idle; + scp->phase = idle; scsi_done(curSC); goto out; } @@ -548,7 +546,7 @@ SYM53C500_info(struct Scsi_Host *SChost) static int SYM53C500_queue_lck(struct scsi_cmnd *SCpnt) { - struct scsi_pointer *scsi_pointer = sym53c500_scsi_pointer(SCpnt); + struct sym53c500_cmd_priv *scp = scsi_cmd_priv(SCpnt); int i; int port_base = SCpnt->device->host->io_port; struct sym53c500_data *data = @@ -565,9 +563,9 @@ static int SYM53C500_queue_lck(struct scsi_cmnd *SCpnt) VDEB(printk("\n")); data->current_SC = SCpnt; - scsi_pointer->phase = command_ph; - scsi_pointer->Status = 0; - scsi_pointer->Message = 0; + scp->phase = command_ph; + scp->status = 0; + scp->message = 0; /* We are locked here already by the mid layer */ REG0(port_base); @@ -682,7 +680,7 @@ static struct scsi_host_template sym53c500_driver_template = { .this_id = 7, .sg_tablesize = 32, .shost_groups = SYM53C500_shost_groups, - .cmd_size = sizeof(struct scsi_pointer), + .cmd_size = sizeof(struct sym53c500_cmd_priv), }; static int SYM53C500_config_check(struct pcmcia_device *p_dev, void *priv_data) diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c index 928532180d32..fd674ed1febe 100644 --- a/drivers/scsi/pmcraid.c +++ b/drivers/scsi/pmcraid.c @@ -3182,124 +3182,6 @@ static int pmcraid_build_ioadl( } /** - * pmcraid_free_sglist - Frees an allocated SG buffer list - * @sglist: scatter/gather list pointer - * - * Free a DMA'able memory previously allocated with pmcraid_alloc_sglist - * - * Return value: - * none - */ -static void pmcraid_free_sglist(struct pmcraid_sglist *sglist) -{ - sgl_free_order(sglist->scatterlist, sglist->order); - kfree(sglist); -} - -/** - * pmcraid_alloc_sglist - Allocates memory for a SG list - * @buflen: buffer length - * - * Allocates a DMA'able buffer in chunks and assembles a scatter/gather - * list. - * - * Return value - * pointer to sglist / NULL on failure - */ -static struct pmcraid_sglist *pmcraid_alloc_sglist(int buflen) -{ - struct pmcraid_sglist *sglist; - int sg_size; - int order; - - sg_size = buflen / (PMCRAID_MAX_IOADLS - 1); - order = (sg_size > 0) ? get_order(sg_size) : 0; - - /* Allocate a scatter/gather list for the DMA */ - sglist = kzalloc(sizeof(struct pmcraid_sglist), GFP_KERNEL); - if (sglist == NULL) - return NULL; - - sglist->order = order; - sgl_alloc_order(buflen, order, false, GFP_KERNEL | __GFP_ZERO, - &sglist->num_sg); - - return sglist; -} - -/** - * pmcraid_copy_sglist - Copy user buffer to kernel buffer's SG list - * @sglist: scatter/gather list pointer - * @buffer: buffer pointer - * @len: buffer length - * @direction: data transfer direction - * - * Copy a user buffer into a buffer allocated by pmcraid_alloc_sglist - * - * Return value: - * 0 on success / other on failure - */ -static int pmcraid_copy_sglist( - struct pmcraid_sglist *sglist, - void __user *buffer, - u32 len, - int direction -) -{ - struct scatterlist *sg; - void *kaddr; - int bsize_elem; - int i; - int rc = 0; - - /* Determine the actual number of bytes per element */ - bsize_elem = PAGE_SIZE * (1 << sglist->order); - - sg = sglist->scatterlist; - - for (i = 0; i < (len / bsize_elem); i++, sg = sg_next(sg), buffer += bsize_elem) { - struct page *page = sg_page(sg); - - kaddr = kmap(page); - if (direction == DMA_TO_DEVICE) - rc = copy_from_user(kaddr, buffer, bsize_elem); - else - rc = copy_to_user(buffer, kaddr, bsize_elem); - - kunmap(page); - - if (rc) { - pmcraid_err("failed to copy user data into sg list\n"); - return -EFAULT; - } - - sg->length = bsize_elem; - } - - if (len % bsize_elem) { - struct page *page = sg_page(sg); - - kaddr = kmap(page); - - if (direction == DMA_TO_DEVICE) - rc = copy_from_user(kaddr, buffer, len % bsize_elem); - else - rc = copy_to_user(buffer, kaddr, len % bsize_elem); - - kunmap(page); - - sg->length = len % bsize_elem; - } - - if (rc) { - pmcraid_err("failed to copy user data into sg list\n"); - rc = -EFAULT; - } - - return rc; -} - -/** * pmcraid_queuecommand_lck - Queue a mid-layer request * @scsi_cmd: scsi command struct * @@ -3454,365 +3336,6 @@ static int pmcraid_chr_fasync(int fd, struct file *filep, int mode) return rc; } - -/** - * pmcraid_build_passthrough_ioadls - builds SG elements for passthrough - * commands sent over IOCTL interface - * - * @cmd : pointer to struct pmcraid_cmd - * @buflen : length of the request buffer - * @direction : data transfer direction - * - * Return value - * 0 on success, non-zero error code on failure - */ -static int pmcraid_build_passthrough_ioadls( - struct pmcraid_cmd *cmd, - int buflen, - int direction -) -{ - struct pmcraid_sglist *sglist = NULL; - struct scatterlist *sg = NULL; - struct pmcraid_ioarcb *ioarcb = &cmd->ioa_cb->ioarcb; - struct pmcraid_ioadl_desc *ioadl; - int i; - - sglist = pmcraid_alloc_sglist(buflen); - - if (!sglist) { - pmcraid_err("can't allocate memory for passthrough SGls\n"); - return -ENOMEM; - } - - sglist->num_dma_sg = dma_map_sg(&cmd->drv_inst->pdev->dev, - sglist->scatterlist, - sglist->num_sg, direction); - - if (!sglist->num_dma_sg || sglist->num_dma_sg > PMCRAID_MAX_IOADLS) { - dev_err(&cmd->drv_inst->pdev->dev, - "Failed to map passthrough buffer!\n"); - pmcraid_free_sglist(sglist); - return -EIO; - } - - cmd->sglist = sglist; - ioarcb->request_flags0 |= NO_LINK_DESCS; - - ioadl = pmcraid_init_ioadls(cmd, sglist->num_dma_sg); - - /* Initialize IOADL descriptor addresses */ - for_each_sg(sglist->scatterlist, sg, sglist->num_dma_sg, i) { - ioadl[i].data_len = cpu_to_le32(sg_dma_len(sg)); - ioadl[i].address = cpu_to_le64(sg_dma_address(sg)); - ioadl[i].flags = 0; - } - - /* setup the last descriptor */ - ioadl[i - 1].flags = IOADL_FLAGS_LAST_DESC; - - return 0; -} - - -/** - * pmcraid_release_passthrough_ioadls - release passthrough ioadls - * - * @cmd: pointer to struct pmcraid_cmd for which ioadls were allocated - * @buflen: size of the request buffer - * @direction: data transfer direction - * - * Return value - * 0 on success, non-zero error code on failure - */ -static void pmcraid_release_passthrough_ioadls( - struct pmcraid_cmd *cmd, - int buflen, - int direction -) -{ - struct pmcraid_sglist *sglist = cmd->sglist; - - if (buflen > 0) { - dma_unmap_sg(&cmd->drv_inst->pdev->dev, - sglist->scatterlist, - sglist->num_sg, - direction); - pmcraid_free_sglist(sglist); - cmd->sglist = NULL; - } -} - -/** - * pmcraid_ioctl_passthrough - handling passthrough IOCTL commands - * - * @pinstance: pointer to adapter instance structure - * @ioctl_cmd: ioctl code - * @buflen: unused - * @arg: pointer to pmcraid_passthrough_buffer user buffer - * - * Return value - * 0 on success, non-zero error code on failure - */ -static long pmcraid_ioctl_passthrough( - struct pmcraid_instance *pinstance, - unsigned int ioctl_cmd, - unsigned int buflen, - void __user *arg -) -{ - struct pmcraid_passthrough_ioctl_buffer *buffer; - struct pmcraid_ioarcb *ioarcb; - struct pmcraid_cmd *cmd; - struct pmcraid_cmd *cancel_cmd; - void __user *request_buffer; - unsigned long request_offset; - unsigned long lock_flags; - void __user *ioasa; - u32 ioasc; - int request_size; - int buffer_size; - u8 direction; - int rc = 0; - - /* If IOA reset is in progress, wait 10 secs for reset to complete */ - if (pinstance->ioa_reset_in_progress) { - rc = wait_event_interruptible_timeout( - pinstance->reset_wait_q, - !pinstance->ioa_reset_in_progress, - msecs_to_jiffies(10000)); - - if (!rc) - return -ETIMEDOUT; - else if (rc < 0) - return -ERESTARTSYS; - } - - /* If adapter is not in operational state, return error */ - if (pinstance->ioa_state != IOA_STATE_OPERATIONAL) { - pmcraid_err("IOA is not operational\n"); - return -ENOTTY; - } - - buffer_size = sizeof(struct pmcraid_passthrough_ioctl_buffer); - buffer = kmalloc(buffer_size, GFP_KERNEL); - - if (!buffer) { - pmcraid_err("no memory for passthrough buffer\n"); - return -ENOMEM; - } - - request_offset = - offsetof(struct pmcraid_passthrough_ioctl_buffer, request_buffer); - - request_buffer = arg + request_offset; - - rc = copy_from_user(buffer, arg, - sizeof(struct pmcraid_passthrough_ioctl_buffer)); - - ioasa = arg + offsetof(struct pmcraid_passthrough_ioctl_buffer, ioasa); - - if (rc) { - pmcraid_err("ioctl: can't copy passthrough buffer\n"); - rc = -EFAULT; - goto out_free_buffer; - } - - request_size = le32_to_cpu(buffer->ioarcb.data_transfer_length); - - if (buffer->ioarcb.request_flags0 & TRANSFER_DIR_WRITE) { - direction = DMA_TO_DEVICE; - } else { - direction = DMA_FROM_DEVICE; - } - - if (request_size < 0) { - rc = -EINVAL; - goto out_free_buffer; - } - - /* check if we have any additional command parameters */ - if (le16_to_cpu(buffer->ioarcb.add_cmd_param_length) - > PMCRAID_ADD_CMD_PARAM_LEN) { - rc = -EINVAL; - goto out_free_buffer; - } - - cmd = pmcraid_get_free_cmd(pinstance); - - if (!cmd) { - pmcraid_err("free command block is not available\n"); - rc = -ENOMEM; - goto out_free_buffer; - } - - cmd->scsi_cmd = NULL; - ioarcb = &(cmd->ioa_cb->ioarcb); - - /* Copy the user-provided IOARCB stuff field by field */ - ioarcb->resource_handle = buffer->ioarcb.resource_handle; - ioarcb->data_transfer_length = buffer->ioarcb.data_transfer_length; - ioarcb->cmd_timeout = buffer->ioarcb.cmd_timeout; - ioarcb->request_type = buffer->ioarcb.request_type; - ioarcb->request_flags0 = buffer->ioarcb.request_flags0; - ioarcb->request_flags1 = buffer->ioarcb.request_flags1; - memcpy(ioarcb->cdb, buffer->ioarcb.cdb, PMCRAID_MAX_CDB_LEN); - - if (buffer->ioarcb.add_cmd_param_length) { - ioarcb->add_cmd_param_length = - buffer->ioarcb.add_cmd_param_length; - ioarcb->add_cmd_param_offset = - buffer->ioarcb.add_cmd_param_offset; - memcpy(ioarcb->add_data.u.add_cmd_params, - buffer->ioarcb.add_data.u.add_cmd_params, - le16_to_cpu(buffer->ioarcb.add_cmd_param_length)); - } - - /* set hrrq number where the IOA should respond to. Note that all cmds - * generated internally uses hrrq_id 0, exception to this is the cmd - * block of scsi_cmd which is re-used (e.g. cancel/abort), which uses - * hrrq_id assigned here in queuecommand - */ - ioarcb->hrrq_id = atomic_add_return(1, &(pinstance->last_message_id)) % - pinstance->num_hrrq; - - if (request_size) { - rc = pmcraid_build_passthrough_ioadls(cmd, - request_size, - direction); - if (rc) { - pmcraid_err("couldn't build passthrough ioadls\n"); - goto out_free_cmd; - } - } - - /* If data is being written into the device, copy the data from user - * buffers - */ - if (direction == DMA_TO_DEVICE && request_size > 0) { - rc = pmcraid_copy_sglist(cmd->sglist, - request_buffer, - request_size, - direction); - if (rc) { - pmcraid_err("failed to copy user buffer\n"); - goto out_free_sglist; - } - } - - /* passthrough ioctl is a blocking command so, put the user to sleep - * until timeout. Note that a timeout value of 0 means, do timeout. - */ - cmd->cmd_done = pmcraid_internal_done; - init_completion(&cmd->wait_for_completion); - cmd->completion_req = 1; - - pmcraid_info("command(%d) (CDB[0] = %x) for %x\n", - le32_to_cpu(cmd->ioa_cb->ioarcb.response_handle) >> 2, - cmd->ioa_cb->ioarcb.cdb[0], - le32_to_cpu(cmd->ioa_cb->ioarcb.resource_handle)); - - spin_lock_irqsave(pinstance->host->host_lock, lock_flags); - _pmcraid_fire_command(cmd); - spin_unlock_irqrestore(pinstance->host->host_lock, lock_flags); - - /* NOTE ! Remove the below line once abort_task is implemented - * in firmware. This line disables ioctl command timeout handling logic - * similar to IO command timeout handling, making ioctl commands to wait - * until the command completion regardless of timeout value specified in - * ioarcb - */ - buffer->ioarcb.cmd_timeout = 0; - - /* If command timeout is specified put caller to wait till that time, - * otherwise it would be blocking wait. If command gets timed out, it - * will be aborted. - */ - if (buffer->ioarcb.cmd_timeout == 0) { - wait_for_completion(&cmd->wait_for_completion); - } else if (!wait_for_completion_timeout( - &cmd->wait_for_completion, - msecs_to_jiffies(le16_to_cpu(buffer->ioarcb.cmd_timeout) * 1000))) { - - pmcraid_info("aborting cmd %d (CDB[0] = %x) due to timeout\n", - le32_to_cpu(cmd->ioa_cb->ioarcb.response_handle) >> 2, - cmd->ioa_cb->ioarcb.cdb[0]); - - spin_lock_irqsave(pinstance->host->host_lock, lock_flags); - cancel_cmd = pmcraid_abort_cmd(cmd); - spin_unlock_irqrestore(pinstance->host->host_lock, lock_flags); - - if (cancel_cmd) { - wait_for_completion(&cancel_cmd->wait_for_completion); - ioasc = le32_to_cpu(cancel_cmd->ioa_cb->ioasa.ioasc); - pmcraid_return_cmd(cancel_cmd); - - /* if abort task couldn't find the command i.e it got - * completed prior to aborting, return good completion. - * if command got aborted successfully or there was IOA - * reset due to abort task itself getting timedout then - * return -ETIMEDOUT - */ - if (ioasc == PMCRAID_IOASC_IOA_WAS_RESET || - PMCRAID_IOASC_SENSE_KEY(ioasc) == 0x00) { - if (ioasc != PMCRAID_IOASC_GC_IOARCB_NOTFOUND) - rc = -ETIMEDOUT; - goto out_handle_response; - } - } - - /* no command block for abort task or abort task failed to abort - * the IOARCB, then wait for 150 more seconds and initiate reset - * sequence after timeout - */ - if (!wait_for_completion_timeout( - &cmd->wait_for_completion, - msecs_to_jiffies(150 * 1000))) { - pmcraid_reset_bringup(cmd->drv_inst); - rc = -ETIMEDOUT; - } - } - -out_handle_response: - /* copy entire IOASA buffer and return IOCTL success. - * If copying IOASA to user-buffer fails, return - * EFAULT - */ - if (copy_to_user(ioasa, &cmd->ioa_cb->ioasa, - sizeof(struct pmcraid_ioasa))) { - pmcraid_err("failed to copy ioasa buffer to user\n"); - rc = -EFAULT; - } - - /* If the data transfer was from device, copy the data onto user - * buffers - */ - else if (direction == DMA_FROM_DEVICE && request_size > 0) { - rc = pmcraid_copy_sglist(cmd->sglist, - request_buffer, - request_size, - direction); - if (rc) { - pmcraid_err("failed to copy user buffer\n"); - rc = -EFAULT; - } - } - -out_free_sglist: - pmcraid_release_passthrough_ioadls(cmd, request_size, direction); - -out_free_cmd: - pmcraid_return_cmd(cmd); - -out_free_buffer: - kfree(buffer); - - return rc; -} - - - - /** * pmcraid_ioctl_driver - ioctl handler for commands handled by driver itself * @@ -3922,20 +3445,6 @@ static long pmcraid_chr_ioctl( switch (_IOC_TYPE(cmd)) { - case PMCRAID_PASSTHROUGH_IOCTL: - /* If ioctl code is to download microcode, we need to block - * mid-layer requests. - */ - if (cmd == PMCRAID_IOCTL_DOWNLOAD_MICROCODE) - scsi_block_requests(pinstance->host); - - retval = pmcraid_ioctl_passthrough(pinstance, cmd, - hdr->buffer_length, argp); - - if (cmd == PMCRAID_IOCTL_DOWNLOAD_MICROCODE) - scsi_unblock_requests(pinstance->host); - break; - case PMCRAID_DRIVER_IOCTL: arg += sizeof(struct pmcraid_ioctl_header); retval = pmcraid_ioctl_driver(pinstance, cmd, diff --git a/drivers/scsi/pmcraid.h b/drivers/scsi/pmcraid.h index bbb75318f1e7..9f59930e8b4f 100644 --- a/drivers/scsi/pmcraid.h +++ b/drivers/scsi/pmcraid.h @@ -1023,40 +1023,15 @@ struct pmcraid_ioctl_header { #define PMCRAID_IOCTL_SIGNATURE "PMCRAID" /* - * pmcraid_passthrough_ioctl_buffer - structure given as argument to - * passthrough(or firmware handled) IOCTL commands. Note that ioarcb requires - * 32-byte alignment so, it is necessary to pack this structure to avoid any - * holes between ioctl_header and passthrough buffer - * - * .ioactl_header : ioctl header - * .ioarcb : filled-up ioarcb buffer, driver always reads this buffer - * .ioasa : buffer for ioasa, driver fills this with IOASA from firmware - * .request_buffer: The I/O buffer (flat), driver reads/writes to this based on - * the transfer directions passed in ioarcb.flags0. Contents - * of this buffer are valid only when ioarcb.data_transfer_len - * is not zero. - */ -struct pmcraid_passthrough_ioctl_buffer { - struct pmcraid_ioctl_header ioctl_header; - struct pmcraid_ioarcb ioarcb; - struct pmcraid_ioasa ioasa; - u8 request_buffer[]; -} __attribute__ ((packed, aligned(PMCRAID_IOARCB_ALIGNMENT))); - -/* * keys to differentiate between driver handled IOCTLs and passthrough * IOCTLs passed to IOA. driver determines the ioctl type using macro * _IOC_TYPE */ #define PMCRAID_DRIVER_IOCTL 'D' -#define PMCRAID_PASSTHROUGH_IOCTL 'F' #define DRV_IOCTL(n, size) \ _IOC(_IOC_READ|_IOC_WRITE, PMCRAID_DRIVER_IOCTL, (n), (size)) -#define FMW_IOCTL(n, size) \ - _IOC(_IOC_READ|_IOC_WRITE, PMCRAID_PASSTHROUGH_IOCTL, (n), (size)) - /* * _ARGSIZE: macro that gives size of the argument type passed to an IOCTL cmd. * This is to facilitate applications avoiding un-necessary memory allocations. @@ -1069,12 +1044,4 @@ struct pmcraid_passthrough_ioctl_buffer { #define PMCRAID_IOCTL_RESET_ADAPTER \ DRV_IOCTL(5, sizeof(struct pmcraid_ioctl_header)) -/* passthrough/firmware handled commands */ -#define PMCRAID_IOCTL_PASSTHROUGH_COMMAND \ - FMW_IOCTL(1, sizeof(struct pmcraid_passthrough_ioctl_buffer)) - -#define PMCRAID_IOCTL_DOWNLOAD_MICROCODE \ - FMW_IOCTL(2, sizeof(struct pmcraid_passthrough_ioctl_buffer)) - - #endif /* _PMCRAID_H */ diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index c607755cce00..ff78ef702f22 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -7519,12 +7519,13 @@ static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num) struct sdebug_defer *sd_dp; sqp = sdebug_q_arr + queue_num; - qc_idx = find_first_bit(sqp->in_use_bm, sdebug_max_queue); - if (qc_idx >= sdebug_max_queue) - return 0; spin_lock_irqsave(&sqp->qc_lock, iflags); + qc_idx = find_first_bit(sqp->in_use_bm, sdebug_max_queue); + if (qc_idx >= sdebug_max_queue) + goto unlock; + for (first = true; first || qc_idx + 1 < sdebug_max_queue; ) { if (first) { first = false; @@ -7589,6 +7590,7 @@ static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num) break; } +unlock: spin_unlock_irqrestore(&sqp->qc_lock, iflags); if (num_entries > 0) diff --git a/drivers/scsi/scsi_logging.c b/drivers/scsi/scsi_logging.c index ff89de86545d..b02af340c2d3 100644 --- a/drivers/scsi/scsi_logging.c +++ b/drivers/scsi/scsi_logging.c @@ -30,7 +30,7 @@ static inline const char *scmd_name(const struct scsi_cmnd *scmd) { struct request *rq = scsi_cmd_to_rq((struct scsi_cmnd *)scmd); - if (!rq->q->disk) + if (!rq->q || !rq->q->disk) return NULL; return rq->q->disk->disk_name; } diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index f4e6c68ac99e..2ef78083f1ef 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -223,6 +223,8 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, int ret; struct sbitmap sb_backup; + depth = min_t(unsigned int, depth, scsi_device_max_queue_depth(sdev)); + /* * realloc if new shift is calculated, which is caused by setting * up one new default queue depth after calling ->slave_configure @@ -245,6 +247,9 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, scsi_device_max_queue_depth(sdev), new_shift, GFP_KERNEL, sdev->request_queue->node, false, true); + if (!ret) + sbitmap_resize(&sdev->budget_map, depth); + if (need_free) { if (ret) sdev->budget_map = sb_backup; diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 226a50944c00..dc6872e352bd 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1384,10 +1384,6 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev) if (IS_ENABLED(CONFIG_BLK_DEV_BSG)) { sdev->bsg_dev = scsi_bsg_register_queue(sdev); if (IS_ERR(sdev->bsg_dev)) { - /* - * We're treating error on bsg register as non-fatal, so - * pretend nothing went wrong. - */ error = PTR_ERR(sdev->bsg_dev); sdev_printk(KERN_INFO, sdev, "Failed to register bsg queue, errno=%d\n", diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index a390679cf458..dc6e55761fd1 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3216,6 +3216,7 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_block_limits(sdkp); sd_read_block_characteristics(sdkp); sd_zbc_read_zones(sdkp, buffer); + sd_read_cpr(sdkp); } sd_print_capacity(sdkp, old_capacity); @@ -3225,7 +3226,6 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_app_tag_own(sdkp, buffer); sd_read_write_same(sdkp, buffer); sd_read_security(sdkp, buffer); - sd_read_cpr(sdkp); } /* @@ -3475,6 +3475,7 @@ static int sd_probe(struct device *dev) error = device_add_disk(dev, gd, NULL); if (error) { put_device(&sdkp->disk_dev); + blk_cleanup_disk(gd); goto out; } diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 5ba9df334968..cbd92891a762 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -535,7 +535,7 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, scsi_autopm_get_device(sdev); - if (ret != CDROMCLOSETRAY && ret != CDROMEJECT) { + if (cmd != CDROMCLOSETRAY && cmd != CDROMEJECT) { ret = cdrom_ioctl(&cd->cdi, bdev, mode, cmd, arg); if (ret != -ENOSYS) goto put; diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c index 0d2e950d0865..586c0e567ff9 100644 --- a/drivers/scsi/ufs/ufs-qcom.c +++ b/drivers/scsi/ufs/ufs-qcom.c @@ -957,18 +957,6 @@ static const struct reset_control_ops ufs_qcom_reset_ops = { .deassert = ufs_qcom_reset_deassert, }; -#define ANDROID_BOOT_DEV_MAX 30 -static char android_boot_dev[ANDROID_BOOT_DEV_MAX]; - -#ifndef MODULE -static int __init get_android_boot_dev(char *str) -{ - strlcpy(android_boot_dev, str, ANDROID_BOOT_DEV_MAX); - return 1; -} -__setup("androidboot.bootdevice=", get_android_boot_dev); -#endif - /** * ufs_qcom_init - bind phy with controller * @hba: host controller instance @@ -988,9 +976,6 @@ static int ufs_qcom_init(struct ufs_hba *hba) struct resource *res; struct ufs_clk_info *clki; - if (strlen(android_boot_dev) && strcmp(android_boot_dev, dev_name(dev))) - return -ENODEV; - host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL); if (!host) { err = -ENOMEM; diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c index f76692053ca1..e892b9feffb1 100644 --- a/drivers/scsi/ufs/ufshcd-pci.c +++ b/drivers/scsi/ufs/ufshcd-pci.c @@ -428,6 +428,12 @@ static int ufs_intel_adl_init(struct ufs_hba *hba) return ufs_intel_common_init(hba); } +static int ufs_intel_mtl_init(struct ufs_hba *hba) +{ + hba->caps |= UFSHCD_CAP_CRYPTO | UFSHCD_CAP_WB_EN; + return ufs_intel_common_init(hba); +} + static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = { .name = "intel-pci", .init = ufs_intel_common_init, @@ -465,6 +471,16 @@ static struct ufs_hba_variant_ops ufs_intel_adl_hba_vops = { .device_reset = ufs_intel_device_reset, }; +static struct ufs_hba_variant_ops ufs_intel_mtl_hba_vops = { + .name = "intel-pci", + .init = ufs_intel_mtl_init, + .exit = ufs_intel_common_exit, + .hce_enable_notify = ufs_intel_hce_enable_notify, + .link_startup_notify = ufs_intel_link_startup_notify, + .resume = ufs_intel_resume, + .device_reset = ufs_intel_device_reset, +}; + #ifdef CONFIG_PM_SLEEP static int ufshcd_pci_restore(struct device *dev) { @@ -579,6 +595,7 @@ static const struct pci_device_id ufshcd_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x98FA), (kernel_ulong_t)&ufs_intel_lkf_hba_vops }, { PCI_VDEVICE(INTEL, 0x51FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops }, { PCI_VDEVICE(INTEL, 0x54FF), (kernel_ulong_t)&ufs_intel_adl_hba_vops }, + { PCI_VDEVICE(INTEL, 0x7E47), (kernel_ulong_t)&ufs_intel_mtl_hba_vops }, { } /* terminate list */ }; diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index 88c20f3608c2..94f545be183a 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -820,8 +820,6 @@ struct ufs_hba { enum ufs_pm_level rpm_lvl; /* Desired UFS power management level during system PM */ enum ufs_pm_level spm_lvl; - struct device_attribute rpm_lvl_attr; - struct device_attribute spm_lvl_attr; int pm_op_in_progress; /* Auto-Hibernate Idle Timer register value */ diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index b2bec19022cd..81099b68bbfb 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -867,12 +867,6 @@ static struct ufshpb_region *ufshpb_victim_lru_info(struct ufshpb_lu *hpb) struct ufshpb_region *rgn, *victim_rgn = NULL; list_for_each_entry(rgn, &lru_info->lh_lru_rgn, list_lru_rgn) { - if (!rgn) { - dev_err(&hpb->sdev_ufs_lu->sdev_dev, - "%s: no region allocated\n", - __func__); - return NULL; - } if (ufshpb_check_srgns_issue_state(hpb, rgn)) continue; @@ -888,6 +882,11 @@ static struct ufshpb_region *ufshpb_victim_lru_info(struct ufshpb_lu *hpb) break; } + if (!victim_rgn) + dev_err(&hpb->sdev_ufs_lu->sdev_dev, + "%s: no region allocated\n", + __func__); + return victim_rgn; } diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 0e6110da69e7..578c4b6d0f7d 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -988,7 +988,7 @@ static struct virtio_driver virtio_scsi_driver = { .remove = virtscsi_remove, }; -static int __init init(void) +static int __init virtio_scsi_init(void) { int ret = -ENOMEM; @@ -1020,14 +1020,14 @@ error: return ret; } -static void __exit fini(void) +static void __exit virtio_scsi_fini(void) { unregister_virtio_driver(&virtio_scsi_driver); mempool_destroy(virtscsi_cmd_pool); kmem_cache_destroy(virtscsi_cmd_cache); } -module_init(init); -module_exit(fini); +module_init(virtio_scsi_init); +module_exit(virtio_scsi_fini); MODULE_DEVICE_TABLE(virtio, id_table); MODULE_DESCRIPTION("Virtio SCSI HBA driver"); diff --git a/drivers/scsi/zorro7xx.c b/drivers/scsi/zorro7xx.c index 27b9e2baab1a..7acf9193a9e8 100644 --- a/drivers/scsi/zorro7xx.c +++ b/drivers/scsi/zorro7xx.c @@ -159,6 +159,8 @@ static void zorro7xx_remove_one(struct zorro_dev *z) scsi_remove_host(host); NCR_700_release(host); + if (host->base > 0x01000000) + iounmap(hostdata->base); kfree(hostdata); free_irq(host->irq, host); zorro_release_device(z); diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 86c76211b3d3..cad2d55dcd3d 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -1205,7 +1205,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem, addr = op->addr.val; len = op->data.nbytes; - if (bcm_qspi_bspi_ver_three(qspi) == true) { + if (has_bspi(qspi) && bcm_qspi_bspi_ver_three(qspi) == true) { /* * The address coming into this function is a raw flash offset. * But for BSPI <= V3, we need to convert it to a remapped BSPI @@ -1224,7 +1224,7 @@ static int bcm_qspi_exec_mem_op(struct spi_mem *mem, len < 4) mspi_read = true; - if (mspi_read) + if (!has_bspi(qspi) || mspi_read) return bcm_qspi_mspi_exec_mem_op(spi, op); ret = bcm_qspi_bspi_set_mode(qspi, op, 0); diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index b0c9f62ccefb..616ada891974 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -19,6 +19,7 @@ #include <linux/iopoll.h> #include <linux/jiffies.h> #include <linux/kernel.h> +#include <linux/log2.h> #include <linux/module.h> #include <linux/of_device.h> #include <linux/of.h> @@ -102,12 +103,6 @@ struct cqspi_driver_platdata { #define CQSPI_TIMEOUT_MS 500 #define CQSPI_READ_TIMEOUT_MS 10 -/* Instruction type */ -#define CQSPI_INST_TYPE_SINGLE 0 -#define CQSPI_INST_TYPE_DUAL 1 -#define CQSPI_INST_TYPE_QUAD 2 -#define CQSPI_INST_TYPE_OCTAL 3 - #define CQSPI_DUMMY_CLKS_PER_BYTE 8 #define CQSPI_DUMMY_BYTES_MAX 4 #define CQSPI_DUMMY_CLKS_MAX 31 @@ -376,10 +371,6 @@ static unsigned int cqspi_calc_dummy(const struct spi_mem_op *op, bool dtr) static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, const struct spi_mem_op *op) { - f_pdata->inst_width = CQSPI_INST_TYPE_SINGLE; - f_pdata->addr_width = CQSPI_INST_TYPE_SINGLE; - f_pdata->data_width = CQSPI_INST_TYPE_SINGLE; - /* * For an op to be DTR, cmd phase along with every other non-empty * phase should have dtr field set to 1. If an op phase has zero @@ -389,32 +380,23 @@ static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, (!op->addr.nbytes || op->addr.dtr) && (!op->data.nbytes || op->data.dtr); - switch (op->data.buswidth) { - case 0: - break; - case 1: - f_pdata->data_width = CQSPI_INST_TYPE_SINGLE; - break; - case 2: - f_pdata->data_width = CQSPI_INST_TYPE_DUAL; - break; - case 4: - f_pdata->data_width = CQSPI_INST_TYPE_QUAD; - break; - case 8: - f_pdata->data_width = CQSPI_INST_TYPE_OCTAL; - break; - default: - return -EINVAL; - } + f_pdata->inst_width = 0; + if (op->cmd.buswidth) + f_pdata->inst_width = ilog2(op->cmd.buswidth); + + f_pdata->addr_width = 0; + if (op->addr.buswidth) + f_pdata->addr_width = ilog2(op->addr.buswidth); + + f_pdata->data_width = 0; + if (op->data.buswidth) + f_pdata->data_width = ilog2(op->data.buswidth); /* Right now we only support 8-8-8 DTR mode. */ if (f_pdata->dtr) { switch (op->cmd.buswidth) { case 0: - break; case 8: - f_pdata->inst_width = CQSPI_INST_TYPE_OCTAL; break; default: return -EINVAL; @@ -422,9 +404,7 @@ static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, switch (op->addr.buswidth) { case 0: - break; case 8: - f_pdata->addr_width = CQSPI_INST_TYPE_OCTAL; break; default: return -EINVAL; @@ -432,9 +412,7 @@ static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata, switch (op->data.buswidth) { case 0: - break; case 8: - f_pdata->data_width = CQSPI_INST_TYPE_OCTAL; break; default: return -EINVAL; diff --git a/drivers/spi/spi-mxic.c b/drivers/spi/spi-mxic.c index 55c092069301..65be8e085ab8 100644 --- a/drivers/spi/spi-mxic.c +++ b/drivers/spi/spi-mxic.c @@ -813,6 +813,7 @@ static int mxic_spi_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "spi_register_master failed\n"); pm_runtime_disable(&pdev->dev); + mxic_spi_mem_ecc_remove(mxic); } return ret; diff --git a/drivers/spi/spi-rpc-if.c b/drivers/spi/spi-rpc-if.c index fe82f3575df4..24ec1c83f379 100644 --- a/drivers/spi/spi-rpc-if.c +++ b/drivers/spi/spi-rpc-if.c @@ -158,14 +158,18 @@ static int rpcif_spi_probe(struct platform_device *pdev) error = rpcif_hw_init(rpc, false); if (error) - return error; + goto out_disable_rpm; error = spi_register_controller(ctlr); if (error) { dev_err(&pdev->dev, "spi_register_controller failed\n"); - rpcif_disable_rpm(rpc); + goto out_disable_rpm; } + return 0; + +out_disable_rpm: + rpcif_disable_rpm(rpc); return error; } diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index c4dd1200fe99..2e6d6bbeb784 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1130,11 +1130,15 @@ static int __spi_unmap_msg(struct spi_controller *ctlr, struct spi_message *msg) if (ctlr->dma_tx) tx_dev = ctlr->dma_tx->device->dev; + else if (ctlr->dma_map_dev) + tx_dev = ctlr->dma_map_dev; else tx_dev = ctlr->dev.parent; if (ctlr->dma_rx) rx_dev = ctlr->dma_rx->device->dev; + else if (ctlr->dma_map_dev) + rx_dev = ctlr->dma_map_dev; else rx_dev = ctlr->dev.parent; @@ -2406,7 +2410,8 @@ static int acpi_spi_add_resource(struct acpi_resource *ares, void *data) } else { struct acpi_device *adev; - if (acpi_bus_get_device(parent_handle, &adev)) + adev = acpi_fetch_acpi_dev(parent_handle); + if (!adev) return -ENODEV; ctlr = acpi_spi_find_controller_by_adev(adev); diff --git a/drivers/staging/r8188eu/core/rtw_br_ext.c b/drivers/staging/r8188eu/core/rtw_br_ext.c index d68611ef22f8..f056204c0fdb 100644 --- a/drivers/staging/r8188eu/core/rtw_br_ext.c +++ b/drivers/staging/r8188eu/core/rtw_br_ext.c @@ -70,7 +70,7 @@ static int __nat25_add_pppoe_tag(struct sk_buff *skb, struct pppoe_tag *tag) struct pppoe_hdr *ph = (struct pppoe_hdr *)(skb->data + ETH_HLEN); int data_len; - data_len = tag->tag_len + TAG_HDR_LEN; + data_len = be16_to_cpu(tag->tag_len) + TAG_HDR_LEN; if (skb_tailroom(skb) < data_len) return -1; diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 95d4ca50a605..fd7267baa707 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -1821,6 +1821,7 @@ static struct page *tcmu_try_get_data_page(struct tcmu_dev *udev, uint32_t dpi) mutex_lock(&udev->cmdr_lock); page = xa_load(&udev->data_pages, dpi); if (likely(page)) { + get_page(page); mutex_unlock(&udev->cmdr_lock); return page; } @@ -1877,6 +1878,7 @@ static vm_fault_t tcmu_vma_fault(struct vm_fault *vmf) /* For the vmalloc()ed cmd area pages */ addr = (void *)(unsigned long)info->mem[mi].addr + offset; page = vmalloc_to_page(addr); + get_page(page); } else { uint32_t dpi; @@ -1887,7 +1889,6 @@ static vm_fault_t tcmu_vma_fault(struct vm_fault *vmf) return VM_FAULT_SIGBUS; } - get_page(page); vmf->page = page; return 0; } diff --git a/drivers/tty/serial/mpc52xx_uart.c b/drivers/tty/serial/mpc52xx_uart.c index 8a6958377764..3acc0f185762 100644 --- a/drivers/tty/serial/mpc52xx_uart.c +++ b/drivers/tty/serial/mpc52xx_uart.c @@ -436,31 +436,31 @@ static void mpc512x_psc_fifo_init(struct uart_port *port) out_be32(&FIFO_512x(port)->rximr, MPC512x_PSC_FIFO_ALARM); } -static int mpc512x_psc_raw_rx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_raw_rx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_512x(port)->rxsr) & MPC512x_PSC_FIFO_EMPTY); } -static int mpc512x_psc_raw_tx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_raw_tx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_512x(port)->txsr) & MPC512x_PSC_FIFO_FULL); } -static int mpc512x_psc_rx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_rx_rdy(struct uart_port *port) { return in_be32(&FIFO_512x(port)->rxsr) & in_be32(&FIFO_512x(port)->rximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc512x_psc_tx_rdy(struct uart_port *port) +static unsigned int mpc512x_psc_tx_rdy(struct uart_port *port) { return in_be32(&FIFO_512x(port)->txsr) & in_be32(&FIFO_512x(port)->tximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc512x_psc_tx_empty(struct uart_port *port) +static unsigned int mpc512x_psc_tx_empty(struct uart_port *port) { return in_be32(&FIFO_512x(port)->txsr) & MPC512x_PSC_FIFO_EMPTY; @@ -780,29 +780,29 @@ static void mpc5125_psc_fifo_init(struct uart_port *port) out_be32(&FIFO_5125(port)->rximr, MPC512x_PSC_FIFO_ALARM); } -static int mpc5125_psc_raw_rx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_raw_rx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_5125(port)->rxsr) & MPC512x_PSC_FIFO_EMPTY); } -static int mpc5125_psc_raw_tx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_raw_tx_rdy(struct uart_port *port) { return !(in_be32(&FIFO_5125(port)->txsr) & MPC512x_PSC_FIFO_FULL); } -static int mpc5125_psc_rx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_rx_rdy(struct uart_port *port) { return in_be32(&FIFO_5125(port)->rxsr) & in_be32(&FIFO_5125(port)->rximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc5125_psc_tx_rdy(struct uart_port *port) +static unsigned int mpc5125_psc_tx_rdy(struct uart_port *port) { return in_be32(&FIFO_5125(port)->txsr) & in_be32(&FIFO_5125(port)->tximr) & MPC512x_PSC_FIFO_ALARM; } -static int mpc5125_psc_tx_empty(struct uart_port *port) +static unsigned int mpc5125_psc_tx_empty(struct uart_port *port) { return in_be32(&FIFO_5125(port)->txsr) & MPC512x_PSC_FIFO_EMPTY; } diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 2f4fb09f1e89..79001301b383 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -163,6 +163,7 @@ struct mlx5_vdpa_net { u32 cur_num_vqs; struct notifier_block nb; struct vdpa_callback config_cb; + struct mlx5_vdpa_wq_ent cvq_ent; }; static void free_resources(struct mlx5_vdpa_net *ndev); @@ -1658,6 +1659,12 @@ static void mlx5_cvq_kick_handler(struct work_struct *work) mvdev = wqent->mvdev; ndev = to_mlx5_vdpa_ndev(mvdev); cvq = &mvdev->cvq; + + mutex_lock(&ndev->reslock); + + if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) + goto out; + if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ))) goto out; @@ -1696,9 +1703,13 @@ static void mlx5_cvq_kick_handler(struct work_struct *work) if (vringh_need_notify_iotlb(&cvq->vring)) vringh_notify(&cvq->vring); + + queue_work(mvdev->wq, &wqent->work); + break; } + out: - kfree(wqent); + mutex_unlock(&ndev->reslock); } static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) @@ -1706,7 +1717,6 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); struct mlx5_vdpa_virtqueue *mvq; - struct mlx5_vdpa_wq_ent *wqent; if (!is_index_valid(mvdev, idx)) return; @@ -1715,13 +1725,7 @@ static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx) if (!mvdev->wq || !mvdev->cvq.ready) return; - wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC); - if (!wqent) - return; - - wqent->mvdev = mvdev; - INIT_WORK(&wqent->work, mlx5_cvq_kick_handler); - queue_work(mvdev->wq, &wqent->work); + queue_work(mvdev->wq, &ndev->cvq_ent.work); return; } @@ -2180,7 +2184,7 @@ static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb goto err_mr; if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) - return 0; + goto err_mr; restore_channels_info(ndev); err = setup_driver(mvdev); @@ -2195,12 +2199,14 @@ err_mr: return err; } +/* reslock must be held for this function */ static int setup_driver(struct mlx5_vdpa_dev *mvdev) { struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); int err; - mutex_lock(&ndev->reslock); + WARN_ON(!mutex_is_locked(&ndev->reslock)); + if (ndev->setup) { mlx5_vdpa_warn(mvdev, "setup driver called for already setup driver\n"); err = 0; @@ -2230,7 +2236,6 @@ static int setup_driver(struct mlx5_vdpa_dev *mvdev) goto err_fwd; } ndev->setup = true; - mutex_unlock(&ndev->reslock); return 0; @@ -2241,23 +2246,23 @@ err_tir: err_rqt: teardown_virtqueues(ndev); out: - mutex_unlock(&ndev->reslock); return err; } +/* reslock must be held for this function */ static void teardown_driver(struct mlx5_vdpa_net *ndev) { - mutex_lock(&ndev->reslock); + + WARN_ON(!mutex_is_locked(&ndev->reslock)); + if (!ndev->setup) - goto out; + return; remove_fwd_to_tir(ndev); destroy_tir(ndev); destroy_rqt(ndev); teardown_virtqueues(ndev); ndev->setup = false; -out: - mutex_unlock(&ndev->reslock); } static void clear_vqs_ready(struct mlx5_vdpa_net *ndev) @@ -2278,6 +2283,8 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) print_status(mvdev, status, true); + mutex_lock(&ndev->reslock); + if ((status ^ ndev->mvdev.status) & VIRTIO_CONFIG_S_DRIVER_OK) { if (status & VIRTIO_CONFIG_S_DRIVER_OK) { err = setup_driver(mvdev); @@ -2287,16 +2294,19 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) } } else { mlx5_vdpa_warn(mvdev, "did not expect DRIVER_OK to be cleared\n"); - return; + goto err_clear; } } ndev->mvdev.status = status; + mutex_unlock(&ndev->reslock); return; err_setup: mlx5_vdpa_destroy_mr(&ndev->mvdev); ndev->mvdev.status |= VIRTIO_CONFIG_S_FAILED; +err_clear: + mutex_unlock(&ndev->reslock); } static int mlx5_vdpa_reset(struct vdpa_device *vdev) @@ -2306,6 +2316,8 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) print_status(mvdev, 0, true); mlx5_vdpa_info(mvdev, "performing device reset\n"); + + mutex_lock(&ndev->reslock); teardown_driver(ndev); clear_vqs_ready(ndev); mlx5_vdpa_destroy_mr(&ndev->mvdev); @@ -2318,6 +2330,7 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev) if (mlx5_vdpa_create_mr(mvdev, NULL)) mlx5_vdpa_warn(mvdev, "create MR failed\n"); } + mutex_unlock(&ndev->reslock); return 0; } @@ -2353,19 +2366,24 @@ static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev) static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); bool change_map; int err; + mutex_lock(&ndev->reslock); + err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map); if (err) { mlx5_vdpa_warn(mvdev, "set map failed(%d)\n", err); - return err; + goto err; } if (change_map) - return mlx5_vdpa_change_map(mvdev, iotlb); + err = mlx5_vdpa_change_map(mvdev, iotlb); - return 0; +err: + mutex_unlock(&ndev->reslock); + return err; } static void mlx5_vdpa_free(struct vdpa_device *vdev) @@ -2740,6 +2758,8 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, if (err) goto err_mr; + ndev->cvq_ent.mvdev = mvdev; + INIT_WORK(&ndev->cvq_ent.work, mlx5_cvq_kick_handler); mvdev->wq = create_singlethread_workqueue("mlx5_vdpa_wq"); if (!mvdev->wq) { err = -ENOMEM; diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index 93b8d84c34cf..f2a6b81e45c4 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -66,13 +66,6 @@ config FB_DDC select I2C_ALGOBIT select I2C -config FB_BOOT_VESA_SUPPORT - bool - depends on FB - help - If true, at least one selected framebuffer driver can take advantage - of VESA video modes set at an early boot stage via the vga= parameter. - config FB_CFB_FILLRECT tristate depends on FB @@ -627,7 +620,7 @@ config FB_VESA select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT - select FB_BOOT_VESA_SUPPORT + select SYSFB help This is the frame buffer device driver for generic VESA 2.0 compliant graphic cards. The older VESA 1.2 cards are not supported. @@ -641,6 +634,7 @@ config FB_EFI select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT + select SYSFB help This is the EFI frame buffer device driver. If the firmware on your platform is EFI 1.10 or UEFI 2.0, select Y to add support for @@ -1051,7 +1045,7 @@ config FB_INTEL select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT - select FB_BOOT_VESA_SUPPORT if FB_INTEL = y + select BOOT_VESA_SUPPORT if FB_INTEL = y depends on !DRM_I915 help This driver supports the on-board graphics built in to the Intel @@ -1378,7 +1372,7 @@ config FB_SIS select FB_CFB_FILLRECT select FB_CFB_COPYAREA select FB_CFB_IMAGEBLIT - select FB_BOOT_VESA_SUPPORT if FB_SIS = y + select BOOT_VESA_SUPPORT if FB_SIS = y select FB_SIS_300 if !FB_SIS_315 help This is the frame buffer device driver for the SiS 300, 315, 330 diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index 842c66b3e33d..6aaf6d0abf39 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -59,7 +59,6 @@ static vm_fault_t fb_deferred_io_fault(struct vm_fault *vmf) printk(KERN_ERR "no mapping available\n"); BUG_ON(!page->mapping); - INIT_LIST_HEAD(&page->lru); page->index = vmf->pgoff; vmf->page = page; @@ -213,6 +212,8 @@ static void fb_deferred_io_work(struct work_struct *work) void fb_deferred_io_init(struct fb_info *info) { struct fb_deferred_io *fbdefio = info->fbdefio; + struct page *page; + unsigned int i; BUG_ON(!fbdefio); mutex_init(&fbdefio->lock); @@ -220,6 +221,12 @@ void fb_deferred_io_init(struct fb_info *info) INIT_LIST_HEAD(&fbdefio->pagelist); if (fbdefio->delay == 0) /* set a default of 1 s */ fbdefio->delay = HZ; + + /* initialize all the page lists one time */ + for (i = 0; i < info->fix.smem_len; i += PAGE_SIZE) { + page = fb_deferred_io_page(info, i); + INIT_LIST_HEAD(&page->lru); + } } EXPORT_SYMBOL_GPL(fb_deferred_io_init); diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 2fc1b80a26ad..c4e91715ef00 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -86,10 +86,6 @@ * - fbcon state itself is protected by the console_lock, and the code does a * pretty good job at making sure that lock is held everywhere it's needed. * - * - access to the registered_fb array is entirely unprotected. This should use - * proper object lifetime handling, i.e. get/put_fb_info. This also means - * switching from indices to proper pointers for fb_info everywhere. - * * - fbcon doesn't bother with fb_lock/unlock at all. This is buggy, since it * means concurrent access to the same fbdev from both fbcon and userspace * will blow up. To fix this all fbcon calls from fbmem.c need to be moved out @@ -107,9 +103,23 @@ enum { static struct fbcon_display fb_display[MAX_NR_CONSOLES]; +struct fb_info *fbcon_registered_fb[FB_MAX]; +int fbcon_num_registered_fb; + +#define fbcon_for_each_registered_fb(i) \ + for (i = 0; WARN_CONSOLE_UNLOCKED(), i < FB_MAX; i++) \ + if (!fbcon_registered_fb[i]) {} else + static signed char con2fb_map[MAX_NR_CONSOLES]; static signed char con2fb_map_boot[MAX_NR_CONSOLES]; +static struct fb_info *fbcon_info_from_console(int console) +{ + WARN_CONSOLE_UNLOCKED(); + + return fbcon_registered_fb[con2fb_map[console]]; +} + static int logo_lines; /* logo_shown is an index to vc_cons when >= 0; otherwise follows FBCON_LOGO enums. */ @@ -163,39 +173,19 @@ static int fbcon_cursor_noblink; * Interface used by the world */ -static const char *fbcon_startup(void); -static void fbcon_init(struct vc_data *vc, int init); -static void fbcon_deinit(struct vc_data *vc); -static void fbcon_clear(struct vc_data *vc, int sy, int sx, int height, - int width); -static void fbcon_putc(struct vc_data *vc, int c, int ypos, int xpos); -static void fbcon_putcs(struct vc_data *vc, const unsigned short *s, - int count, int ypos, int xpos); static void fbcon_clear_margins(struct vc_data *vc, int bottom_only); -static void fbcon_cursor(struct vc_data *vc, int mode); -static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, - int height, int width); -static int fbcon_switch(struct vc_data *vc); -static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch); static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table); /* * Internal routines */ -static __inline__ void ywrap_up(struct vc_data *vc, int count); -static __inline__ void ywrap_down(struct vc_data *vc, int count); -static __inline__ void ypan_up(struct vc_data *vc, int count); -static __inline__ void ypan_down(struct vc_data *vc, int count); -static void fbcon_bmove_rec(struct vc_data *vc, struct fbcon_display *p, int sy, int sx, - int dy, int dx, int height, int width, u_int y_break); static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, int unit); static void fbcon_redraw_move(struct vc_data *vc, struct fbcon_display *p, int line, int count, int dy); static void fbcon_modechanged(struct fb_info *info); static void fbcon_set_all_vcs(struct fb_info *info); -static void fbcon_start(void); -static void fbcon_exit(void); + static struct device *fbcon_device; #ifdef CONFIG_FRAMEBUFFER_CONSOLE_ROTATION @@ -218,7 +208,7 @@ static void fbcon_rotate(struct fb_info *info, u32 rotate) if (!ops || ops->currcon == -1) return; - fb_info = registered_fb[con2fb_map[ops->currcon]]; + fb_info = fbcon_info_from_console(ops->currcon); if (info == fb_info) { struct fbcon_display *p = &fb_display[ops->currcon]; @@ -245,7 +235,7 @@ static void fbcon_rotate_all(struct fb_info *info, u32 rotate) for (i = first_fb_vc; i <= last_fb_vc; i++) { vc = vc_cons[i].d; if (!vc || vc->vc_mode != KD_TEXT || - registered_fb[con2fb_map[i]] != info) + fbcon_info_from_console(i) != info) continue; p = &fb_display[vc->vc_num]; @@ -357,8 +347,8 @@ static int get_color(struct vc_data *vc, struct fb_info *info, static void fb_flashcursor(struct work_struct *work) { - struct fb_info *info = container_of(work, struct fb_info, queue); - struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_ops *ops = container_of(work, struct fbcon_ops, cursor_work.work); + struct fb_info *info; struct vc_data *vc = NULL; int c; int mode; @@ -371,11 +361,14 @@ static void fb_flashcursor(struct work_struct *work) if (ret == 0) return; - if (ops && ops->currcon != -1) + /* protected by console_lock */ + info = ops->info; + + if (ops->currcon != -1) vc = vc_cons[ops->currcon].d; if (!vc || !con_is_visible(vc) || - registered_fb[con2fb_map[vc->vc_num]] != info || + fbcon_info_from_console(vc->vc_num) != info || vc->vc_deccm != 1) { console_unlock(); return; @@ -387,42 +380,25 @@ static void fb_flashcursor(struct work_struct *work) ops->cursor(vc, info, mode, get_color(vc, info, c, 1), get_color(vc, info, c, 0)); console_unlock(); -} -static void cursor_timer_handler(struct timer_list *t) -{ - struct fbcon_ops *ops = from_timer(ops, t, cursor_timer); - struct fb_info *info = ops->info; - - queue_work(system_power_efficient_wq, &info->queue); - mod_timer(&ops->cursor_timer, jiffies + ops->cur_blink_jiffies); + queue_delayed_work(system_power_efficient_wq, &ops->cursor_work, + ops->cur_blink_jiffies); } -static void fbcon_add_cursor_timer(struct fb_info *info) +static void fbcon_add_cursor_work(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; - if ((!info->queue.func || info->queue.func == fb_flashcursor) && - !(ops->flags & FBCON_FLAGS_CURSOR_TIMER) && - !fbcon_cursor_noblink) { - if (!info->queue.func) - INIT_WORK(&info->queue, fb_flashcursor); - - timer_setup(&ops->cursor_timer, cursor_timer_handler, 0); - mod_timer(&ops->cursor_timer, jiffies + ops->cur_blink_jiffies); - ops->flags |= FBCON_FLAGS_CURSOR_TIMER; - } + if (!fbcon_cursor_noblink) + queue_delayed_work(system_power_efficient_wq, &ops->cursor_work, + ops->cur_blink_jiffies); } -static void fbcon_del_cursor_timer(struct fb_info *info) +static void fbcon_del_cursor_work(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; - if (info->queue.func == fb_flashcursor && - ops->flags & FBCON_FLAGS_CURSOR_TIMER) { - del_timer_sync(&ops->cursor_timer); - ops->flags &= ~FBCON_FLAGS_CURSOR_TIMER; - } + cancel_delayed_work_sync(&ops->cursor_work); } #ifndef MODULE @@ -540,7 +516,7 @@ static int do_fbcon_takeover(int show_logo) { int err, i; - if (!num_registered_fb) + if (!fbcon_num_registered_fb) return -ENODEV; if (!show_logo) @@ -602,7 +578,7 @@ static void fbcon_prepare_logo(struct vc_data *vc, struct fb_info *info, save = kmalloc(array3_size(logo_lines, new_cols, 2), GFP_KERNEL); if (save) { - int i = cols < new_cols ? cols : new_cols; + int i = min(cols, new_cols); scr_memsetw(save, erase, array3_size(logo_lines, new_cols, 2)); r = q - step; for (cnt = 0; cnt < logo_lines; cnt++, r += i) @@ -703,87 +679,95 @@ static int fbcon_invalid_charcount(struct fb_info *info, unsigned charcount) #endif /* CONFIG_MISC_TILEBLITTING */ - -static int con2fb_acquire_newinfo(struct vc_data *vc, struct fb_info *info, - int unit, int oldidx) +static void fbcon_release(struct fb_info *info) { - struct fbcon_ops *ops = NULL; - int err = 0; + lock_fb_info(info); + if (info->fbops->fb_release) + info->fbops->fb_release(info, 0); + unlock_fb_info(info); - if (!try_module_get(info->fbops->owner)) - err = -ENODEV; + module_put(info->fbops->owner); - if (!err && info->fbops->fb_open && - info->fbops->fb_open(info, 0)) - err = -ENODEV; + if (info->fbcon_par) { + struct fbcon_ops *ops = info->fbcon_par; - if (!err) { - ops = kzalloc(sizeof(struct fbcon_ops), GFP_KERNEL); - if (!ops) - err = -ENOMEM; + fbcon_del_cursor_work(info); + kfree(ops->cursor_state.mask); + kfree(ops->cursor_data); + kfree(ops->cursor_src); + kfree(ops->fontbuffer); + kfree(info->fbcon_par); + info->fbcon_par = NULL; } +} - if (!err) { - ops->cur_blink_jiffies = HZ / 5; - ops->info = info; - info->fbcon_par = ops; +static int fbcon_open(struct fb_info *info) +{ + struct fbcon_ops *ops; - if (vc) - set_blitting_type(vc, info); - } + if (!try_module_get(info->fbops->owner)) + return -ENODEV; - if (err) { - con2fb_map[unit] = oldidx; + lock_fb_info(info); + if (info->fbops->fb_open && + info->fbops->fb_open(info, 0)) { + unlock_fb_info(info); module_put(info->fbops->owner); + return -ENODEV; + } + unlock_fb_info(info); + + ops = kzalloc(sizeof(struct fbcon_ops), GFP_KERNEL); + if (!ops) { + fbcon_release(info); + return -ENOMEM; } + INIT_DELAYED_WORK(&ops->cursor_work, fb_flashcursor); + ops->info = info; + info->fbcon_par = ops; + ops->cur_blink_jiffies = HZ / 5; + + return 0; +} + +static int con2fb_acquire_newinfo(struct vc_data *vc, struct fb_info *info, + int unit) +{ + int err; + + err = fbcon_open(info); + if (err) + return err; + + if (vc) + set_blitting_type(vc, info); + return err; } -static int con2fb_release_oldinfo(struct vc_data *vc, struct fb_info *oldinfo, - struct fb_info *newinfo, int unit, - int oldidx, int found) +static void con2fb_release_oldinfo(struct vc_data *vc, struct fb_info *oldinfo, + struct fb_info *newinfo) { - struct fbcon_ops *ops = oldinfo->fbcon_par; - int err = 0, ret; + int ret; - if (oldinfo->fbops->fb_release && - oldinfo->fbops->fb_release(oldinfo, 0)) { - con2fb_map[unit] = oldidx; - if (!found && newinfo->fbops->fb_release) - newinfo->fbops->fb_release(newinfo, 0); - if (!found) - module_put(newinfo->fbops->owner); - err = -ENODEV; - } + fbcon_release(oldinfo); - if (!err) { - fbcon_del_cursor_timer(oldinfo); - kfree(ops->cursor_state.mask); - kfree(ops->cursor_data); - kfree(ops->cursor_src); - kfree(ops->fontbuffer); - kfree(oldinfo->fbcon_par); - oldinfo->fbcon_par = NULL; - module_put(oldinfo->fbops->owner); - /* - If oldinfo and newinfo are driving the same hardware, - the fb_release() method of oldinfo may attempt to - restore the hardware state. This will leave the - newinfo in an undefined state. Thus, a call to - fb_set_par() may be needed for the newinfo. - */ - if (newinfo && newinfo->fbops->fb_set_par) { - ret = newinfo->fbops->fb_set_par(newinfo); + /* + If oldinfo and newinfo are driving the same hardware, + the fb_release() method of oldinfo may attempt to + restore the hardware state. This will leave the + newinfo in an undefined state. Thus, a call to + fb_set_par() may be needed for the newinfo. + */ + if (newinfo && newinfo->fbops->fb_set_par) { + ret = newinfo->fbops->fb_set_par(newinfo); - if (ret) - printk(KERN_ERR "con2fb_release_oldinfo: " - "detected unhandled fb_set_par error, " - "error code %d\n", ret); - } + if (ret) + printk(KERN_ERR "con2fb_release_oldinfo: " + "detected unhandled fb_set_par error, " + "error code %d\n", ret); } - - return err; } static void con2fb_init_display(struct vc_data *vc, struct fb_info *info, @@ -794,7 +778,7 @@ static void con2fb_init_display(struct vc_data *vc, struct fb_info *info, ops->currcon = fg_console; - if (info->fbops->fb_set_par && !(ops->flags & FBCON_FLAGS_INIT)) { + if (info->fbops->fb_set_par && !ops->initialized) { ret = info->fbops->fb_set_par(info); if (ret) @@ -803,14 +787,14 @@ static void con2fb_init_display(struct vc_data *vc, struct fb_info *info, "error code %d\n", ret); } - ops->flags |= FBCON_FLAGS_INIT; + ops->initialized = true; ops->graphics = 0; fbcon_set_disp(info, &info->var, unit); if (show_logo) { struct vc_data *fg_vc = vc_cons[fg_console].d; struct fb_info *fg_info = - registered_fb[con2fb_map[fg_console]]; + fbcon_info_from_console(fg_console); fbcon_prepare_logo(fg_vc, fg_info, fg_vc->vc_cols, fg_vc->vc_rows, fg_vc->vc_cols, @@ -835,9 +819,9 @@ static int set_con2fb_map(int unit, int newidx, int user) { struct vc_data *vc = vc_cons[unit].d; int oldidx = con2fb_map[unit]; - struct fb_info *info = registered_fb[newidx]; + struct fb_info *info = fbcon_registered_fb[newidx]; struct fb_info *oldinfo = NULL; - int found, err = 0; + int found, err = 0, show_logo; WARN_CONSOLE_UNLOCKED(); @@ -853,31 +837,30 @@ static int set_con2fb_map(int unit, int newidx, int user) } if (oldidx != -1) - oldinfo = registered_fb[oldidx]; + oldinfo = fbcon_registered_fb[oldidx]; found = search_fb_in_map(newidx); - con2fb_map[unit] = newidx; - if (!err && !found) - err = con2fb_acquire_newinfo(vc, info, unit, oldidx); + if (!err && !found) { + err = con2fb_acquire_newinfo(vc, info, unit); + if (!err) + con2fb_map[unit] = newidx; + } /* * If old fb is not mapped to any of the consoles, * fbcon should release it. */ if (!err && oldinfo && !search_fb_in_map(oldidx)) - err = con2fb_release_oldinfo(vc, oldinfo, info, unit, oldidx, - found); + con2fb_release_oldinfo(vc, oldinfo, info); - if (!err) { - int show_logo = (fg_console == 0 && !user && - logo_shown != FBCON_LOGO_DONTSHOW); + show_logo = (fg_console == 0 && !user && + logo_shown != FBCON_LOGO_DONTSHOW); - if (!found) - fbcon_add_cursor_timer(info); - con2fb_map_boot[unit] = newidx; - con2fb_init_display(vc, info, unit, show_logo); - } + if (!found) + fbcon_add_cursor_work(info); + con2fb_map_boot[unit] = newidx; + con2fb_init_display(vc, info, unit, show_logo); if (!search_fb_in_map(info_idx)) info_idx = newidx; @@ -938,7 +921,6 @@ static const char *fbcon_startup(void) struct fbcon_display *p = &fb_display[fg_console]; struct vc_data *vc = vc_cons[fg_console].d; const struct font_desc *font = NULL; - struct module *owner; struct fb_info *info = NULL; struct fbcon_ops *ops; int rows, cols; @@ -947,36 +929,23 @@ static const char *fbcon_startup(void) * If num_registered_fb is zero, this is a call for the dummy part. * The frame buffer devices weren't initialized yet. */ - if (!num_registered_fb || info_idx == -1) + if (!fbcon_num_registered_fb || info_idx == -1) return display_desc; /* * Instead of blindly using registered_fb[0], we use info_idx, set by - * fb_console_init(); + * fbcon_fb_registered(); */ - info = registered_fb[info_idx]; + info = fbcon_registered_fb[info_idx]; if (!info) return NULL; - owner = info->fbops->owner; - if (!try_module_get(owner)) - return NULL; - if (info->fbops->fb_open && info->fbops->fb_open(info, 0)) { - module_put(owner); + if (fbcon_open(info)) return NULL; - } - - ops = kzalloc(sizeof(struct fbcon_ops), GFP_KERNEL); - if (!ops) { - module_put(owner); - return NULL; - } + ops = info->fbcon_par; ops->currcon = -1; ops->graphics = 1; ops->cur_rotate = -1; - ops->cur_blink_jiffies = HZ / 5; - ops->info = info; - info->fbcon_par = ops; p->con_rotate = initial_rotation; if (p->con_rotate == -1) @@ -1013,7 +982,7 @@ static const char *fbcon_startup(void) info->var.yres, info->var.bits_per_pixel); - fbcon_add_cursor_timer(info); + fbcon_add_cursor_work(info); return display_desc; } @@ -1033,7 +1002,7 @@ static void fbcon_init(struct vc_data *vc, int init) if (con2fb_map[vc->vc_num] == -1) con2fb_map[vc->vc_num] = info_idx; - info = registered_fb[con2fb_map[vc->vc_num]]; + info = fbcon_info_from_console(vc->vc_num); if (logo_shown < 0 && console_loglevel <= CONSOLE_LOGLEVEL_QUIET) logo_shown = FBCON_LOGO_DONTSHOW; @@ -1046,7 +1015,7 @@ static void fbcon_init(struct vc_data *vc, int init) return; if (!info->fbcon_par) - con2fb_acquire_newinfo(vc, info, vc->vc_num, -1); + con2fb_acquire_newinfo(vc, info, vc->vc_num); /* If we are not the first console on this fb, copy the font from that console */ @@ -1120,8 +1089,7 @@ static void fbcon_init(struct vc_data *vc, int init) * We need to do it in fbcon_init() to prevent screen corruption. */ if (con_is_visible(vc) && vc->vc_mode == KD_TEXT) { - if (info->fbops->fb_set_par && - !(ops->flags & FBCON_FLAGS_INIT)) { + if (info->fbops->fb_set_par && !ops->initialized) { ret = info->fbops->fb_set_par(info); if (ret) @@ -1130,7 +1098,7 @@ static void fbcon_init(struct vc_data *vc, int init) "error code %d\n", ret); } - ops->flags |= FBCON_FLAGS_INIT; + ops->initialized = true; } ops->graphics = 0; @@ -1175,6 +1143,27 @@ static void fbcon_free_font(struct fbcon_display *p, bool freefont) static void set_vc_hi_font(struct vc_data *vc, bool set); +static void fbcon_release_all(void) +{ + struct fb_info *info; + int i, j, mapped; + + fbcon_for_each_registered_fb(i) { + mapped = 0; + info = fbcon_registered_fb[i]; + + for (j = first_fb_vc; j <= last_fb_vc; j++) { + if (con2fb_map[j] == i) { + mapped = 1; + con2fb_map[j] = -1; + } + } + + if (mapped) + fbcon_release(info); + } +} + static void fbcon_deinit(struct vc_data *vc) { struct fbcon_display *p = &fb_display[vc->vc_num]; @@ -1188,7 +1177,7 @@ static void fbcon_deinit(struct vc_data *vc) if (idx == -1) goto finished; - info = registered_fb[idx]; + info = fbcon_registered_fb[idx]; if (!info) goto finished; @@ -1201,9 +1190,9 @@ static void fbcon_deinit(struct vc_data *vc) goto finished; if (con_is_visible(vc)) - fbcon_del_cursor_timer(info); + fbcon_del_cursor_work(info); - ops->flags &= ~FBCON_FLAGS_INIT; + ops->initialized = false; finished: fbcon_free_font(p, free_font); @@ -1214,7 +1203,7 @@ finished: set_vc_hi_font(vc, false); if (!con_is_bound(&fb_con)) - fbcon_exit(); + fbcon_release_all(); if (vc->vc_num == logo_shown) logo_shown = FBCON_LOGO_CANSHOW; @@ -1250,7 +1239,7 @@ finished: static void fbcon_clear(struct vc_data *vc, int sy, int sx, int height, int width) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; @@ -1288,7 +1277,7 @@ static void fbcon_clear(struct vc_data *vc, int sy, int sx, int height, static void fbcon_putcs(struct vc_data *vc, const unsigned short *s, int count, int ypos, int xpos) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_display *p = &fb_display[vc->vc_num]; struct fbcon_ops *ops = info->fbcon_par; @@ -1308,7 +1297,7 @@ static void fbcon_putc(struct vc_data *vc, int c, int ypos, int xpos) static void fbcon_clear_margins(struct vc_data *vc, int bottom_only) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; if (!fbcon_is_inactive(vc, info)) @@ -1317,7 +1306,7 @@ static void fbcon_clear_margins(struct vc_data *vc, int bottom_only) static void fbcon_cursor(struct vc_data *vc, int mode) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; int c = scr_readw((u16 *) vc->vc_pos); @@ -1327,9 +1316,9 @@ static void fbcon_cursor(struct vc_data *vc, int mode) return; if (vc->vc_cursor_type & CUR_SW) - fbcon_del_cursor_timer(info); + fbcon_del_cursor_work(info); else - fbcon_add_cursor_timer(info); + fbcon_add_cursor_work(info); ops->cursor_flash = (mode == CM_ERASE) ? 0 : 1; @@ -1411,7 +1400,7 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, static __inline__ void ywrap_up(struct vc_data *vc, int count) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; @@ -1430,7 +1419,7 @@ static __inline__ void ywrap_up(struct vc_data *vc, int count) static __inline__ void ywrap_down(struct vc_data *vc, int count) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; @@ -1449,7 +1438,7 @@ static __inline__ void ywrap_down(struct vc_data *vc, int count) static __inline__ void ypan_up(struct vc_data *vc, int count) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_display *p = &fb_display[vc->vc_num]; struct fbcon_ops *ops = info->fbcon_par; @@ -1473,7 +1462,7 @@ static __inline__ void ypan_up(struct vc_data *vc, int count) static __inline__ void ypan_up_redraw(struct vc_data *vc, int t, int count) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; @@ -1497,7 +1486,7 @@ static __inline__ void ypan_up_redraw(struct vc_data *vc, int t, int count) static __inline__ void ypan_down(struct vc_data *vc, int count) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_display *p = &fb_display[vc->vc_num]; struct fbcon_ops *ops = info->fbcon_par; @@ -1521,7 +1510,7 @@ static __inline__ void ypan_down(struct vc_data *vc, int count) static __inline__ void ypan_down_redraw(struct vc_data *vc, int t, int count) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; @@ -1682,10 +1671,75 @@ static void fbcon_redraw(struct vc_data *vc, struct fbcon_display *p, } } +static void fbcon_bmove_rec(struct vc_data *vc, struct fbcon_display *p, int sy, int sx, + int dy, int dx, int height, int width, u_int y_break) +{ + struct fb_info *info = fbcon_info_from_console(vc->vc_num); + struct fbcon_ops *ops = info->fbcon_par; + u_int b; + + if (sy < y_break && sy + height > y_break) { + b = y_break - sy; + if (dy < sy) { /* Avoid trashing self */ + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, + y_break); + fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, + height - b, width, y_break); + } else { + fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, + height - b, width, y_break); + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, + y_break); + } + return; + } + + if (dy < y_break && dy + height > y_break) { + b = y_break - dy; + if (dy < sy) { /* Avoid trashing self */ + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, + y_break); + fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, + height - b, width, y_break); + } else { + fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, + height - b, width, y_break); + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, + y_break); + } + return; + } + ops->bmove(vc, info, real_y(p, sy), sx, real_y(p, dy), dx, + height, width); +} + +static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, + int height, int width) +{ + struct fb_info *info = fbcon_info_from_console(vc->vc_num); + struct fbcon_display *p = &fb_display[vc->vc_num]; + + if (fbcon_is_inactive(vc, info)) + return; + + if (!width || !height) + return; + + /* Split blits that cross physical y_wrap case. + * Pathological case involves 4 blits, better to use recursive + * code rather than unrolled case + * + * Recursive invocations don't need to erase the cursor over and + * over again, so we use fbcon_bmove_rec() + */ + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, height, width, + p->vrows - p->yscroll); +} + static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b, enum con_scroll dir, unsigned int count) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_display *p = &fb_display[vc->vc_num]; int scroll_partial = info->flags & FBINFO_PARTIAL_PAN_OK; @@ -1882,71 +1936,6 @@ static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b, } -static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, - int height, int width) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_display *p = &fb_display[vc->vc_num]; - - if (fbcon_is_inactive(vc, info)) - return; - - if (!width || !height) - return; - - /* Split blits that cross physical y_wrap case. - * Pathological case involves 4 blits, better to use recursive - * code rather than unrolled case - * - * Recursive invocations don't need to erase the cursor over and - * over again, so we use fbcon_bmove_rec() - */ - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, height, width, - p->vrows - p->yscroll); -} - -static void fbcon_bmove_rec(struct vc_data *vc, struct fbcon_display *p, int sy, int sx, - int dy, int dx, int height, int width, u_int y_break) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_ops *ops = info->fbcon_par; - u_int b; - - if (sy < y_break && sy + height > y_break) { - b = y_break - sy; - if (dy < sy) { /* Avoid trashing self */ - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, - y_break); - fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, - height - b, width, y_break); - } else { - fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, - height - b, width, y_break); - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, - y_break); - } - return; - } - - if (dy < y_break && dy + height > y_break) { - b = y_break - dy; - if (dy < sy) { /* Avoid trashing self */ - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, - y_break); - fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, - height - b, width, y_break); - } else { - fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, - height - b, width, y_break); - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, - y_break); - } - return; - } - ops->bmove(vc, info, real_y(p, sy), sx, real_y(p, dy), dx, - height, width); -} - static void updatescrollmode_accel(struct fbcon_display *p, struct fb_info *info, struct vc_data *vc) @@ -2015,7 +2004,7 @@ static void updatescrollmode(struct fbcon_display *p, static int fbcon_resize(struct vc_data *vc, unsigned int width, unsigned int height, unsigned int user) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; struct fb_var_screeninfo var = info->var; @@ -2084,7 +2073,7 @@ static int fbcon_switch(struct vc_data *vc) struct fb_var_screeninfo var; int i, ret, prev_console; - info = registered_fb[con2fb_map[vc->vc_num]]; + info = fbcon_info_from_console(vc->vc_num); ops = info->fbcon_par; if (logo_shown >= 0) { @@ -2098,7 +2087,7 @@ static int fbcon_switch(struct vc_data *vc) prev_console = ops->currcon; if (prev_console != -1) - old_info = registered_fb[con2fb_map[prev_console]]; + old_info = fbcon_info_from_console(prev_console); /* * FIXME: If we have multiple fbdev's loaded, we need to * update all info->currcon. Perhaps, we can place this @@ -2107,9 +2096,9 @@ static int fbcon_switch(struct vc_data *vc) * * info->currcon = vc->vc_num; */ - for_each_registered_fb(i) { - if (registered_fb[i]->fbcon_par) { - struct fbcon_ops *o = registered_fb[i]->fbcon_par; + fbcon_for_each_registered_fb(i) { + if (fbcon_registered_fb[i]->fbcon_par) { + struct fbcon_ops *o = fbcon_registered_fb[i]->fbcon_par; o->currcon = vc->vc_num; } @@ -2139,14 +2128,14 @@ static int fbcon_switch(struct vc_data *vc) } if (old_info != info) - fbcon_del_cursor_timer(old_info); + fbcon_del_cursor_work(old_info); } if (fbcon_is_inactive(vc, info) || ops->blank_state != FB_BLANK_UNBLANK) - fbcon_del_cursor_timer(info); + fbcon_del_cursor_work(info); else - fbcon_add_cursor_timer(info); + fbcon_add_cursor_work(info); set_blitting_type(vc, info); ops->cursor_reset = 1; @@ -2221,7 +2210,7 @@ static void fbcon_generic_blank(struct vc_data *vc, struct fb_info *info, static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; if (mode_switch) { @@ -2254,16 +2243,16 @@ static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch) if (mode_switch || fbcon_is_inactive(vc, info) || ops->blank_state != FB_BLANK_UNBLANK) - fbcon_del_cursor_timer(info); + fbcon_del_cursor_work(info); else - fbcon_add_cursor_timer(info); + fbcon_add_cursor_work(info); return 0; } static int fbcon_debug_enter(struct vc_data *vc) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; ops->save_graphics = ops->graphics; @@ -2276,7 +2265,7 @@ static int fbcon_debug_enter(struct vc_data *vc) static int fbcon_debug_leave(struct vc_data *vc) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; ops->graphics = ops->save_graphics; @@ -2412,7 +2401,7 @@ static void set_vc_hi_font(struct vc_data *vc, bool set) static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, const u8 * data, int userfont) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; int resize; @@ -2466,7 +2455,7 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, static int fbcon_set_font(struct vc_data *vc, struct console_font *font, unsigned int flags) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); unsigned charcount = font->charcount; int w = font->width; int h = font->height; @@ -2530,7 +2519,7 @@ static int fbcon_set_font(struct vc_data *vc, struct console_font *font, static int fbcon_set_def_font(struct vc_data *vc, struct console_font *font, char *name) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); const struct font_desc *f; if (!name) @@ -2554,7 +2543,7 @@ static struct fb_cmap palette_cmap = { static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table) { - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fb_info *info = fbcon_info_from_console(vc->vc_num); int i, j, k, depth; u8 val; @@ -2670,7 +2659,7 @@ static void fbcon_modechanged(struct fb_info *info) return; vc = vc_cons[ops->currcon].d; if (vc->vc_mode != KD_TEXT || - registered_fb[con2fb_map[ops->currcon]] != info) + fbcon_info_from_console(ops->currcon) != info) return; p = &fb_display[vc->vc_num]; @@ -2710,7 +2699,7 @@ static void fbcon_set_all_vcs(struct fb_info *info) for (i = first_fb_vc; i <= last_fb_vc; i++) { vc = vc_cons[i].d; if (!vc || vc->vc_mode != KD_TEXT || - registered_fb[con2fb_map[i]] != info) + fbcon_info_from_console(i) != info) continue; if (con_is_visible(vc)) { @@ -2754,7 +2743,7 @@ int fbcon_mode_deleted(struct fb_info *info, j = con2fb_map[i]; if (j == -1) continue; - fb_info = registered_fb[j]; + fb_info = fbcon_registered_fb[j]; if (fb_info != info) continue; p = &fb_display[i]; @@ -2783,16 +2772,17 @@ static void fbcon_unbind(void) static inline void fbcon_unbind(void) {} #endif /* CONFIG_VT_HW_CONSOLE_BINDING */ -/* called with console_lock held */ void fbcon_fb_unbind(struct fb_info *info) { - int i, new_idx = -1, ret = 0; + int i, new_idx = -1; int idx = info->node; - WARN_CONSOLE_UNLOCKED(); + console_lock(); - if (!fbcon_has_console_bind) + if (!fbcon_has_console_bind) { + console_unlock(); return; + } for (i = first_fb_vc; i <= last_fb_vc; i++) { if (con2fb_map[i] != idx && @@ -2808,7 +2798,7 @@ void fbcon_fb_unbind(struct fb_info *info) set_con2fb_map(i, new_idx, 0); } } else { - struct fb_info *info = registered_fb[idx]; + struct fb_info *info = fbcon_registered_fb[idx]; /* This is sort of like set_con2fb_map, except it maps * the consoles to no device and then releases the @@ -2820,29 +2810,30 @@ void fbcon_fb_unbind(struct fb_info *info) if (con2fb_map[i] == idx) { con2fb_map[i] = -1; if (!search_fb_in_map(idx)) { - ret = con2fb_release_oldinfo(vc_cons[i].d, - info, NULL, i, - idx, 0); - if (ret) { - con2fb_map[i] = idx; - return; - } + con2fb_release_oldinfo(vc_cons[i].d, + info, NULL); } } } fbcon_unbind(); } + + console_unlock(); } -/* called with console_lock held */ void fbcon_fb_unregistered(struct fb_info *info) { int i, idx; - WARN_CONSOLE_UNLOCKED(); + console_lock(); - if (deferred_takeover) + fbcon_registered_fb[info->node] = NULL; + fbcon_num_registered_fb--; + + if (deferred_takeover) { + console_unlock(); return; + } idx = info->node; for (i = first_fb_vc; i <= last_fb_vc; i++) { @@ -2853,7 +2844,7 @@ void fbcon_fb_unregistered(struct fb_info *info) if (idx == info_idx) { info_idx = -1; - for_each_registered_fb(i) { + fbcon_for_each_registered_fb(i) { info_idx = i; break; } @@ -2869,8 +2860,9 @@ void fbcon_fb_unregistered(struct fb_info *info) if (primary_device == idx) primary_device = -1; - if (!num_registered_fb) + if (!fbcon_num_registered_fb) do_unregister_con_driver(&fb_con); + console_unlock(); } void fbcon_remap_all(struct fb_info *info) @@ -2928,13 +2920,21 @@ static inline void fbcon_select_primary(struct fb_info *info) } #endif /* CONFIG_FRAMEBUFFER_DETECT_PRIMARY */ +static bool lockless_register_fb; +module_param_named_unsafe(lockless_register_fb, lockless_register_fb, bool, 0400); +MODULE_PARM_DESC(lockless_register_fb, + "Lockless framebuffer registration for debugging [default=off]"); + /* called with console_lock held */ -int fbcon_fb_registered(struct fb_info *info) +static int do_fb_registered(struct fb_info *info) { int ret = 0, i, idx; WARN_CONSOLE_UNLOCKED(); + fbcon_registered_fb[info->node] = info; + fbcon_num_registered_fb++; + idx = info->node; fbcon_select_primary(info); @@ -2963,6 +2963,25 @@ int fbcon_fb_registered(struct fb_info *info) return ret; } +int fbcon_fb_registered(struct fb_info *info) +{ + int ret; + + if (!lockless_register_fb) + console_lock(); + else + atomic_inc(&ignore_console_lock_warning); + + ret = do_fb_registered(info); + + if (!lockless_register_fb) + console_unlock(); + else + atomic_dec(&ignore_console_lock_warning); + + return ret; +} + void fbcon_fb_blanked(struct fb_info *info, int blank) { struct fbcon_ops *ops = info->fbcon_par; @@ -2973,7 +2992,7 @@ void fbcon_fb_blanked(struct fb_info *info, int blank) vc = vc_cons[ops->currcon].d; if (vc->vc_mode != KD_TEXT || - registered_fb[con2fb_map[ops->currcon]] != info) + fbcon_info_from_console(ops->currcon) != info) return; if (con_is_visible(vc)) { @@ -2993,7 +3012,7 @@ void fbcon_new_modelist(struct fb_info *info) const struct fb_videomode *mode; for (i = first_fb_vc; i <= last_fb_vc; i++) { - if (registered_fb[con2fb_map[i]] != info) + if (fbcon_info_from_console(i) != info) continue; if (!fb_display[i].mode) continue; @@ -3048,9 +3067,9 @@ int fbcon_set_con2fb_map_ioctl(void __user *argp) return -EINVAL; if (con2fb.framebuffer >= FB_MAX) return -EINVAL; - if (!registered_fb[con2fb.framebuffer]) + if (!fbcon_registered_fb[con2fb.framebuffer]) request_module("fb%d", con2fb.framebuffer); - if (!registered_fb[con2fb.framebuffer]) { + if (!fbcon_registered_fb[con2fb.framebuffer]) { return -EINVAL; } @@ -3117,10 +3136,10 @@ static ssize_t store_rotate(struct device *device, console_lock(); idx = con2fb_map[fg_console]; - if (idx == -1 || registered_fb[idx] == NULL) + if (idx == -1 || fbcon_registered_fb[idx] == NULL) goto err; - info = registered_fb[idx]; + info = fbcon_registered_fb[idx]; rotate = simple_strtoul(buf, last, 0); fbcon_rotate(info, rotate); err: @@ -3139,10 +3158,10 @@ static ssize_t store_rotate_all(struct device *device, console_lock(); idx = con2fb_map[fg_console]; - if (idx == -1 || registered_fb[idx] == NULL) + if (idx == -1 || fbcon_registered_fb[idx] == NULL) goto err; - info = registered_fb[idx]; + info = fbcon_registered_fb[idx]; rotate = simple_strtoul(buf, last, 0); fbcon_rotate_all(info, rotate); err: @@ -3159,14 +3178,14 @@ static ssize_t show_rotate(struct device *device, console_lock(); idx = con2fb_map[fg_console]; - if (idx == -1 || registered_fb[idx] == NULL) + if (idx == -1 || fbcon_registered_fb[idx] == NULL) goto err; - info = registered_fb[idx]; + info = fbcon_registered_fb[idx]; rotate = fbcon_get_rotate(info); err: console_unlock(); - return snprintf(buf, PAGE_SIZE, "%d\n", rotate); + return sysfs_emit(buf, "%d\n", rotate); } static ssize_t show_cursor_blink(struct device *device, @@ -3179,19 +3198,19 @@ static ssize_t show_cursor_blink(struct device *device, console_lock(); idx = con2fb_map[fg_console]; - if (idx == -1 || registered_fb[idx] == NULL) + if (idx == -1 || fbcon_registered_fb[idx] == NULL) goto err; - info = registered_fb[idx]; + info = fbcon_registered_fb[idx]; ops = info->fbcon_par; if (!ops) goto err; - blink = (ops->flags & FBCON_FLAGS_CURSOR_TIMER) ? 1 : 0; + blink = delayed_work_pending(&ops->cursor_work); err: console_unlock(); - return snprintf(buf, PAGE_SIZE, "%d\n", blink); + return sysfs_emit(buf, "%d\n", blink); } static ssize_t store_cursor_blink(struct device *device, @@ -3205,10 +3224,10 @@ static ssize_t store_cursor_blink(struct device *device, console_lock(); idx = con2fb_map[fg_console]; - if (idx == -1 || registered_fb[idx] == NULL) + if (idx == -1 || fbcon_registered_fb[idx] == NULL) goto err; - info = registered_fb[idx]; + info = fbcon_registered_fb[idx]; if (!info->fbcon_par) goto err; @@ -3217,10 +3236,10 @@ static ssize_t store_cursor_blink(struct device *device, if (blink) { fbcon_cursor_noblink = 0; - fbcon_add_cursor_timer(info); + fbcon_add_cursor_work(info); } else { fbcon_cursor_noblink = 1; - fbcon_del_cursor_timer(info); + fbcon_del_cursor_work(info); } err: @@ -3265,8 +3284,11 @@ static void fbcon_register_existing_fbs(struct work_struct *work) console_lock(); - for_each_registered_fb(i) - fbcon_fb_registered(registered_fb[i]); + deferred_takeover = false; + logo_shown = FBCON_LOGO_DONTSHOW; + + fbcon_for_each_registered_fb(i) + do_fb_registered(fbcon_registered_fb[i]); console_unlock(); } @@ -3282,8 +3304,6 @@ static int fbcon_output_notifier(struct notifier_block *nb, pr_info("fbcon: Taking over console\n"); dummycon_unregister_output_notifier(&fbcon_output_nb); - deferred_takeover = false; - logo_shown = FBCON_LOGO_DONTSHOW; /* We may get called in atomic context */ schedule_work(&fbcon_deferred_takeover_work); @@ -3306,67 +3326,6 @@ static void fbcon_start(void) return; } #endif - - if (num_registered_fb) { - int i; - - for_each_registered_fb(i) { - info_idx = i; - break; - } - - do_fbcon_takeover(0); - } -} - -static void fbcon_exit(void) -{ - struct fb_info *info; - int i, j, mapped; - -#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER - if (deferred_takeover) { - dummycon_unregister_output_notifier(&fbcon_output_nb); - deferred_takeover = false; - } -#endif - - for_each_registered_fb(i) { - int pending = 0; - - mapped = 0; - info = registered_fb[i]; - - if (info->queue.func) - pending = cancel_work_sync(&info->queue); - pr_debug("fbcon: %s pending work\n", (pending ? "canceled" : "no")); - - for (j = first_fb_vc; j <= last_fb_vc; j++) { - if (con2fb_map[j] == i) { - mapped = 1; - con2fb_map[j] = -1; - } - } - - if (mapped) { - if (info->fbops->fb_release) - info->fbops->fb_release(info, 0); - module_put(info->fbops->owner); - - if (info->fbcon_par) { - struct fbcon_ops *ops = info->fbcon_par; - - fbcon_del_cursor_timer(info); - kfree(ops->cursor_src); - kfree(ops->cursor_state.mask); - kfree(info->fbcon_par); - info->fbcon_par = NULL; - } - - if (info->queue.func == fb_flashcursor) - info->queue.func = NULL; - } - } } void __init fb_console_init(void) @@ -3408,10 +3367,19 @@ static void __exit fbcon_deinit_device(void) void __exit fb_console_exit(void) { +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER + console_lock(); + if (deferred_takeover) + dummycon_unregister_output_notifier(&fbcon_output_nb); + console_unlock(); + + cancel_work_sync(&fbcon_deferred_takeover_work); +#endif + console_lock(); fbcon_deinit_device(); device_destroy(fb_class, MKDEV(0, 0)); - fbcon_exit(); + do_unregister_con_driver(&fb_con); console_unlock(); } diff --git a/drivers/video/fbdev/core/fbcon.h b/drivers/video/fbdev/core/fbcon.h index 969d41ecede5..0eaf54a21151 100644 --- a/drivers/video/fbdev/core/fbcon.h +++ b/drivers/video/fbdev/core/fbcon.h @@ -14,12 +14,10 @@ #include <linux/types.h> #include <linux/vt_buffer.h> #include <linux/vt_kern.h> +#include <linux/workqueue.h> #include <asm/io.h> -#define FBCON_FLAGS_INIT 1 -#define FBCON_FLAGS_CURSOR_TIMER 2 - /* * This is the interface between the low-level console driver and the * low-level frame buffer device @@ -68,7 +66,7 @@ struct fbcon_ops { int (*update_start)(struct fb_info *info); int (*rotate_font)(struct fb_info *info, struct vc_data *vc); struct fb_var_screeninfo var; /* copy of the current fb_var_screeninfo */ - struct timer_list cursor_timer; /* Cursor timer */ + struct delayed_work cursor_work; /* Cursor timer */ struct fb_cursor cursor_state; struct fbcon_display *p; struct fb_info *info; @@ -79,7 +77,7 @@ struct fbcon_ops { int blank_state; int graphics; int save_graphics; /* for debug enter/leave */ - int flags; + bool initialized; int rotate; int cur_rotate; char *cursor_data; diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 34d6bb1bf82e..84427470367b 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1577,9 +1577,14 @@ static void do_remove_conflicting_framebuffers(struct apertures_struct *a, * allocate the memory range. * * If it's not a platform device, at least print a warning. A - * fix would add code to remove the device from the system. + * fix would add code to remove the device from the system. For + * framebuffers without any Linux device, print a warning as + * well. */ - if (dev_is_platform(device)) { + if (!device) { + pr_warn("fb%d: no device set\n", i); + do_unregister_framebuffer(registered_fb[i]); + } else if (dev_is_platform(device)) { registered_fb[i]->forced_out = true; platform_device_unregister(to_platform_device(device)); } else { @@ -1590,14 +1595,9 @@ static void do_remove_conflicting_framebuffers(struct apertures_struct *a, } } -static bool lockless_register_fb; -module_param_named_unsafe(lockless_register_fb, lockless_register_fb, bool, 0400); -MODULE_PARM_DESC(lockless_register_fb, - "Lockless framebuffer registration for debugging [default=off]"); - static int do_register_framebuffer(struct fb_info *fb_info) { - int i, ret; + int i; struct fb_videomode mode; if (fb_check_foreignness(fb_info)) @@ -1666,19 +1666,7 @@ static int do_register_framebuffer(struct fb_info *fb_info) } #endif - if (!lockless_register_fb) - console_lock(); - else - atomic_inc(&ignore_console_lock_warning); - lock_fb_info(fb_info); - ret = fbcon_fb_registered(fb_info); - unlock_fb_info(fb_info); - - if (!lockless_register_fb) - console_unlock(); - else - atomic_dec(&ignore_console_lock_warning); - return ret; + return fbcon_fb_registered(fb_info); } static void unbind_console(struct fb_info *fb_info) @@ -1688,11 +1676,7 @@ static void unbind_console(struct fb_info *fb_info) if (WARN_ON(i < 0 || i >= FB_MAX || registered_fb[i] != fb_info)) return; - console_lock(); - lock_fb_info(fb_info); fbcon_fb_unbind(fb_info); - unlock_fb_info(fb_info); - console_unlock(); } static void unlink_framebuffer(struct fb_info *fb_info) @@ -1735,9 +1719,7 @@ static void do_unregister_framebuffer(struct fb_info *fb_info) fb_notifier_call_chain(FB_EVENT_FB_UNREGISTERED, &event); } #endif - console_lock(); fbcon_fb_unregistered(fb_info); - console_unlock(); /* this may free fb info */ put_fb_info(fb_info); diff --git a/drivers/video/fbdev/core/fbsysfs.c b/drivers/video/fbdev/core/fbsysfs.c index 26892940c213..8c1ee9ecec3d 100644 --- a/drivers/video/fbdev/core/fbsysfs.c +++ b/drivers/video/fbdev/core/fbsysfs.c @@ -91,9 +91,11 @@ static int activate(struct fb_info *fb_info, struct fb_var_screeninfo *var) var->activate |= FB_ACTIVATE_FORCE; console_lock(); + lock_fb_info(fb_info); err = fb_set_var(fb_info, var); if (!err) fbcon_update_vcs(fb_info, var->activate & FB_ACTIVATE_ALL); + unlock_fb_info(fb_info); console_unlock(); if (err) return err; diff --git a/drivers/video/fbdev/offb.c b/drivers/video/fbdev/offb.c index afdb6aa48add..b1acb1ebebe9 100644 --- a/drivers/video/fbdev/offb.c +++ b/drivers/video/fbdev/offb.c @@ -386,10 +386,10 @@ static void offb_init_palette_hacks(struct fb_info *info, struct device_node *dp FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_STATIC_PSEUDOCOLOR; } -static void __init offb_init_fb(const char *name, - int width, int height, int depth, - int pitch, unsigned long address, - int foreign_endian, struct device_node *dp) +static void offb_init_fb(struct platform_device *parent, const char *name, + int width, int height, int depth, + int pitch, unsigned long address, + int foreign_endian, struct device_node *dp) { unsigned long res_size = pitch * height; struct offb_par *par = &default_par; @@ -410,12 +410,13 @@ static void __init offb_init_fb(const char *name, return; } - info = framebuffer_alloc(sizeof(u32) * 16, NULL); + info = framebuffer_alloc(sizeof(u32) * 16, &parent->dev); if (!info) { release_mem_region(res_start, res_size); return; } + platform_set_drvdata(parent, info); fix = &info->fix; var = &info->var; @@ -535,7 +536,8 @@ out_aper: } -static void __init offb_init_nodriver(struct device_node *dp, int no_real_node) +static void offb_init_nodriver(struct platform_device *parent, struct device_node *dp, + int no_real_node) { unsigned int len; int i, width = 640, height = 480, depth = 8, pitch = 640; @@ -650,46 +652,76 @@ static void __init offb_init_nodriver(struct device_node *dp, int no_real_node) /* kludge for valkyrie */ if (of_node_name_eq(dp, "valkyrie")) address += 0x1000; - offb_init_fb(no_real_node ? "bootx" : NULL, + offb_init_fb(parent, no_real_node ? "bootx" : NULL, width, height, depth, pitch, address, foreign_endian, no_real_node ? NULL : dp); } } -static int __init offb_init(void) +static int offb_remove(struct platform_device *pdev) { - struct device_node *dp = NULL, *boot_disp = NULL; + struct fb_info *info = platform_get_drvdata(pdev); - if (fb_get_options("offb", NULL)) - return -ENODEV; + if (info) + unregister_framebuffer(info); - /* Check if we have a MacOS display without a node spec */ - if (of_get_property(of_chosen, "linux,bootx-noscreen", NULL) != NULL) { - /* The old code tried to work out which node was the MacOS - * display based on the address. I'm dropping that since the - * lack of a node spec only happens with old BootX versions - * (users can update) and with this code, they'll still get - * a display (just not the palette hacks). - */ - offb_init_nodriver(of_chosen, 1); - } + return 0; +} - for_each_node_by_type(dp, "display") { - if (of_get_property(dp, "linux,opened", NULL) && - of_get_property(dp, "linux,boot-display", NULL)) { - boot_disp = dp; - offb_init_nodriver(dp, 0); - } - } - for_each_node_by_type(dp, "display") { - if (of_get_property(dp, "linux,opened", NULL) && - dp != boot_disp) - offb_init_nodriver(dp, 0); - } +static int offb_probe_bootx_noscreen(struct platform_device *pdev) +{ + offb_init_nodriver(pdev, of_chosen, 1); return 0; } +static struct platform_driver offb_driver_bootx_noscreen = { + .driver = { + .name = "bootx-noscreen", + }, + .probe = offb_probe_bootx_noscreen, + .remove = offb_remove, +}; + +static int offb_probe_display(struct platform_device *pdev) +{ + offb_init_nodriver(pdev, pdev->dev.of_node, 0); + + return 0; +} +static const struct of_device_id offb_of_match_display[] = { + { .compatible = "display", }, + { }, +}; +MODULE_DEVICE_TABLE(of, offb_of_match_display); + +static struct platform_driver offb_driver_display = { + .driver = { + .name = "of-display", + .of_match_table = offb_of_match_display, + }, + .probe = offb_probe_display, + .remove = offb_remove, +}; + +static int __init offb_init(void) +{ + if (fb_get_options("offb", NULL)) + return -ENODEV; + + platform_driver_register(&offb_driver_bootx_noscreen); + platform_driver_register(&offb_driver_display); + + return 0; +} module_init(offb_init); + +static void __exit offb_exit(void) +{ + platform_driver_unregister(&offb_driver_display); + platform_driver_unregister(&offb_driver_bootx_noscreen); +} +module_exit(offb_exit); + MODULE_LICENSE("GPL"); diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 75c8d560bbd3..22f15f444f75 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -526,9 +526,8 @@ int virtio_device_restore(struct virtio_device *dev) goto err; } - /* If restore didn't do it, mark device DRIVER_OK ourselves. */ - if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK)) - virtio_device_ready(dev); + /* Finally, tell the device we're all set */ + virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK); virtio_config_enable(dev); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 0399cf8e3c32..151e9da5da2d 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -118,7 +118,7 @@ struct btrfs_bio_ctrl { */ struct extent_changeset { /* How many bytes are set/cleared in this operation */ - unsigned int bytes_changed; + u64 bytes_changed; /* Changed ranges */ struct ulist range_changed; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 9f455c96c974..380054c94e4b 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2957,8 +2957,9 @@ out: return ret; } -static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) +static int btrfs_punch_hole(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; struct extent_state *cached_state = NULL; @@ -2990,6 +2991,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) goto out_only_mutex; } + ret = file_modified(file); + if (ret) + goto out_only_mutex; + lockstart = round_up(offset, btrfs_inode_sectorsize(BTRFS_I(inode))); lockend = round_down(offset + len, btrfs_inode_sectorsize(BTRFS_I(inode))) - 1; @@ -3430,7 +3435,7 @@ static long btrfs_fallocate(struct file *file, int mode, return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) - return btrfs_punch_hole(inode, offset, len); + return btrfs_punch_hole(file, offset, len); /* * Only trigger disk allocation, don't trigger qgroup reserve @@ -3452,6 +3457,10 @@ static long btrfs_fallocate(struct file *file, int mode, goto out; } + ret = file_modified(file); + if (ret) + goto out; + /* * TODO: Move these two operations after we have checked * accurate reserved space, or fallocate can still fail but diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6bfc4343c98d..17d5557f98ec 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1128,7 +1128,6 @@ static noinline int cow_file_range(struct btrfs_inode *inode, int ret = 0; if (btrfs_is_free_space_inode(inode)) { - WARN_ON_ONCE(1); ret = -EINVAL; goto out_unlock; } @@ -4488,6 +4487,13 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) dest->root_key.objectid); return -EPERM; } + if (atomic_read(&dest->nr_swapfiles)) { + spin_unlock(&dest->root_item_lock); + btrfs_warn(fs_info, + "attempt to delete subvolume %llu with active swapfile", + root->root_key.objectid); + return -EPERM; + } root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags | BTRFS_ROOT_SUBVOL_DEAD); @@ -11107,8 +11113,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file, * set. We use this counter to prevent snapshots. We must increment it * before walking the extents because we don't want a concurrent * snapshot to run after we've already checked the extents. + * + * It is possible that subvolume is marked for deletion but still not + * removed yet. To prevent this race, we check the root status before + * activating the swapfile. */ + spin_lock(&root->root_item_lock); + if (btrfs_root_dead(root)) { + spin_unlock(&root->root_item_lock); + + btrfs_exclop_finish(fs_info); + btrfs_warn(fs_info, + "cannot activate swapfile because subvolume %llu is being deleted", + root->root_key.objectid); + return -EPERM; + } atomic_inc(&root->nr_swapfiles); + spin_unlock(&root->root_item_lock); isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 238cee5b5254..f46e71061942 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1239,7 +1239,7 @@ static u32 get_extent_max_capacity(const struct extent_map *em) } static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, - bool locked) + u32 extent_thresh, u64 newer_than, bool locked) { struct extent_map *next; bool ret = false; @@ -1249,11 +1249,12 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, return false; /* - * We want to check if the next extent can be merged with the current - * one, which can be an extent created in a past generation, so we pass - * a minimum generation of 0 to defrag_lookup_extent(). + * Here we need to pass @newer_then when checking the next extent, or + * we will hit a case we mark current extent for defrag, but the next + * one will not be a target. + * This will just cause extra IO without really reducing the fragments. */ - next = defrag_lookup_extent(inode, em->start + em->len, 0, locked); + next = defrag_lookup_extent(inode, em->start + em->len, newer_than, locked); /* No more em or hole */ if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE) goto out; @@ -1265,6 +1266,13 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, */ if (next->len >= get_extent_max_capacity(em)) goto out; + /* Skip older extent */ + if (next->generation < newer_than) + goto out; + /* Also check extent size */ + if (next->len >= extent_thresh) + goto out; + ret = true; out: free_extent_map(next); @@ -1470,7 +1478,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode, goto next; next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em, - locked); + extent_thresh, newer_than, locked); if (!next_mergeable) { struct defrag_target_range *last; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 1be7cb2f955f..2cfbc74a3b4e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1896,23 +1896,18 @@ static void update_dev_time(const char *device_path) path_put(&path); } -static int btrfs_rm_dev_item(struct btrfs_device *device) +static int btrfs_rm_dev_item(struct btrfs_trans_handle *trans, + struct btrfs_device *device) { struct btrfs_root *root = device->fs_info->chunk_root; int ret; struct btrfs_path *path; struct btrfs_key key; - struct btrfs_trans_handle *trans; path = btrfs_alloc_path(); if (!path) return -ENOMEM; - trans = btrfs_start_transaction(root, 0); - if (IS_ERR(trans)) { - btrfs_free_path(path); - return PTR_ERR(trans); - } key.objectid = BTRFS_DEV_ITEMS_OBJECTID; key.type = BTRFS_DEV_ITEM_KEY; key.offset = device->devid; @@ -1923,21 +1918,12 @@ static int btrfs_rm_dev_item(struct btrfs_device *device) if (ret) { if (ret > 0) ret = -ENOENT; - btrfs_abort_transaction(trans, ret); - btrfs_end_transaction(trans); goto out; } ret = btrfs_del_item(trans, root, path); - if (ret) { - btrfs_abort_transaction(trans, ret); - btrfs_end_transaction(trans); - } - out: btrfs_free_path(path); - if (!ret) - ret = btrfs_commit_transaction(trans); return ret; } @@ -2078,6 +2064,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, struct btrfs_dev_lookup_args *args, struct block_device **bdev, fmode_t *mode) { + struct btrfs_trans_handle *trans; struct btrfs_device *device; struct btrfs_fs_devices *cur_devices; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; @@ -2098,7 +2085,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, ret = btrfs_check_raid_min_devices(fs_info, num_devices - 1); if (ret) - goto out; + return ret; device = btrfs_find_device(fs_info->fs_devices, args); if (!device) { @@ -2106,27 +2093,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, ret = BTRFS_ERROR_DEV_MISSING_NOT_FOUND; else ret = -ENOENT; - goto out; + return ret; } if (btrfs_pinned_by_swapfile(fs_info, device)) { btrfs_warn_in_rcu(fs_info, "cannot remove device %s (devid %llu) due to active swapfile", rcu_str_deref(device->name), device->devid); - ret = -ETXTBSY; - goto out; + return -ETXTBSY; } - if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { - ret = BTRFS_ERROR_DEV_TGT_REPLACE; - goto out; - } + if (test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) + return BTRFS_ERROR_DEV_TGT_REPLACE; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && - fs_info->fs_devices->rw_devices == 1) { - ret = BTRFS_ERROR_DEV_ONLY_WRITABLE; - goto out; - } + fs_info->fs_devices->rw_devices == 1) + return BTRFS_ERROR_DEV_ONLY_WRITABLE; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { mutex_lock(&fs_info->chunk_mutex); @@ -2139,14 +2121,22 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, if (ret) goto error_undo; - /* - * TODO: the superblock still includes this device in its num_devices - * counter although write_all_supers() is not locked out. This - * could give a filesystem state which requires a degraded mount. - */ - ret = btrfs_rm_dev_item(device); - if (ret) + trans = btrfs_start_transaction(fs_info->chunk_root, 0); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); goto error_undo; + } + + ret = btrfs_rm_dev_item(trans, device); + if (ret) { + /* Any error in dev item removal is critical */ + btrfs_crit(fs_info, + "failed to remove device item for devid %llu: %d", + device->devid, ret); + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + return ret; + } clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); btrfs_scrub_cancel_dev(device); @@ -2229,7 +2219,8 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, free_fs_devices(cur_devices); } -out: + ret = btrfs_commit_transaction(trans); + return ret; error_undo: @@ -2240,7 +2231,7 @@ error_undo: device->fs_devices->rw_devices++; mutex_unlock(&fs_info->chunk_mutex); } - goto out; + return ret; } void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index b7b5fac1c779..1b1b310c3c51 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1801,7 +1801,6 @@ struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info, map = em->map_lookup; /* We only support single profile for now */ - ASSERT(map->num_stripes == 1); device = map->stripes[0].dev; free_extent_map(em); @@ -1976,18 +1975,16 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group) bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags) { + struct btrfs_fs_info *fs_info = fs_devices->fs_info; struct btrfs_device *device; bool ret = false; - if (!btrfs_is_zoned(fs_devices->fs_info)) + if (!btrfs_is_zoned(fs_info)) return true; - /* Non-single profiles are not supported yet */ - ASSERT((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0); - /* Check if there is a device with active zones left */ - mutex_lock(&fs_devices->device_list_mutex); - list_for_each_entry(device, &fs_devices->devices, dev_list) { + mutex_lock(&fs_info->chunk_mutex); + list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) { struct btrfs_zoned_device_info *zinfo = device->zone_info; if (!device->bdev) @@ -1999,7 +1996,7 @@ bool btrfs_can_activate_zone(struct btrfs_fs_devices *fs_devices, u64 flags) break; } } - mutex_unlock(&fs_devices->device_list_mutex); + mutex_unlock(&fs_info->chunk_mutex); return ret; } diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 15a5c5db038b..c0542bdcd06b 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -153,5 +153,5 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ #define SMB3_PRODUCT_BUILD 35 -#define CIFS_VERSION "2.35" +#define CIFS_VERSION "2.36" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index ee3b7c15e884..54155eb4faac 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -453,9 +453,7 @@ static int reconnect_target_unlocked(struct TCP_Server_Info *server, struct dfs_ return rc; } -static int -reconnect_dfs_server(struct TCP_Server_Info *server, - bool mark_smb_session) +static int reconnect_dfs_server(struct TCP_Server_Info *server) { int rc = 0; const char *refpath = server->current_fullpath + 1; @@ -479,7 +477,12 @@ reconnect_dfs_server(struct TCP_Server_Info *server, if (!cifs_tcp_ses_needs_reconnect(server, num_targets)) return 0; - cifs_mark_tcp_ses_conns_for_reconnect(server, mark_smb_session); + /* + * Unconditionally mark all sessions & tcons for reconnect as we might be connecting to a + * different server or share during failover. It could be improved by adding some logic to + * only do that in case it connects to a different server or share, though. + */ + cifs_mark_tcp_ses_conns_for_reconnect(server, true); cifs_abort_connection(server); @@ -537,7 +540,7 @@ int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) } spin_unlock(&cifs_tcp_ses_lock); - return reconnect_dfs_server(server, mark_smb_session); + return reconnect_dfs_server(server); } #else int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) @@ -4465,7 +4468,7 @@ static int tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tco */ if (rc && server->current_fullpath != server->origin_fullpath) { server->current_fullpath = server->origin_fullpath; - cifs_reconnect(tcon->ses->server, true); + cifs_signal_cifsd_for_reconnect(server, true); } dfs_cache_free_tgts(tl); diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index ebe236b9d9f5..235aa1b395eb 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -896,7 +896,7 @@ map_and_check_smb_error(struct mid_q_entry *mid, bool logErr) if (class == ERRSRV && code == ERRbaduid) { cifs_dbg(FYI, "Server returned 0x%x, reconnecting session...\n", code); - cifs_reconnect(mid->server, false); + cifs_signal_cifsd_for_reconnect(mid->server, false); } } diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index c653beb735b8..3fe47a88f47d 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -150,16 +150,18 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) struct smb2_transform_hdr *thdr = (struct smb2_transform_hdr *)buf; struct cifs_ses *ses = NULL; + struct cifs_ses *iter; /* decrypt frame now that it is completely read in */ spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(ses, &srvr->smb_ses_list, smb_ses_list) { - if (ses->Suid == le64_to_cpu(thdr->SessionId)) + list_for_each_entry(iter, &srvr->smb_ses_list, smb_ses_list) { + if (iter->Suid == le64_to_cpu(thdr->SessionId)) { + ses = iter; break; + } } spin_unlock(&cifs_tcp_ses_lock); - if (list_entry_is_head(ses, &srvr->smb_ses_list, - smb_ses_list)) { + if (!ses) { cifs_dbg(VFS, "no decryption - session id not found\n"); return 1; } diff --git a/fs/file_table.c b/fs/file_table.c index 7d2e692b66a9..ada8fe814db9 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -412,6 +412,7 @@ void __fput_sync(struct file *file) } EXPORT_SYMBOL(fput); +EXPORT_SYMBOL(__fput_sync); void __init files_init(void) { diff --git a/fs/io-wq.h b/fs/io-wq.h index dbecd27656c7..04d374e65e54 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -155,6 +155,7 @@ struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack) struct io_wq_work { struct io_wq_work_node list; unsigned flags; + int fd; }; static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) diff --git a/fs/io_uring.c b/fs/io_uring.c index a8413f006417..659f8ecba5b7 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -63,7 +63,6 @@ #include <net/sock.h> #include <net/af_unix.h> #include <net/scm.h> -#include <net/busy_poll.h> #include <linux/anon_inodes.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> @@ -112,8 +111,7 @@ IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS) #define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ - REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \ - REQ_F_ASYNC_DATA) + REQ_F_POLLED | REQ_F_CREDS | REQ_F_ASYNC_DATA) #define IO_TCTX_REFS_CACHE_NR (1U << 10) @@ -412,11 +410,6 @@ struct io_ring_ctx { struct list_head sqd_list; unsigned long check_cq_overflow; -#ifdef CONFIG_NET_RX_BUSY_POLL - /* used to track busy poll napi_id */ - struct list_head napi_list; - spinlock_t napi_lock; /* napi_list lock */ -#endif struct { unsigned cached_cq_tail; @@ -500,7 +493,6 @@ struct io_uring_task { const struct io_ring_ctx *last; struct io_wq *io_wq; struct percpu_counter inflight; - atomic_t inflight_tracked; atomic_t in_idle; spinlock_t task_lock; @@ -592,7 +584,8 @@ struct io_rw { /* NOTE: kiocb has the file as the first member, so don't do it here */ struct kiocb kiocb; u64 addr; - u64 len; + u32 len; + u32 flags; }; struct io_connect { @@ -654,10 +647,10 @@ struct io_epoll { struct io_splice { struct file *file_out; - struct file *file_in; loff_t off_out; loff_t off_in; u64 len; + int splice_fd_in; unsigned int flags; }; @@ -1182,8 +1175,11 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, struct io_uring_rsrc_update2 *up, unsigned nr_args); static void io_clean_op(struct io_kiocb *req); -static struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed); +static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, + unsigned issue_flags); +static inline struct file *io_file_get_normal(struct io_kiocb *req, int fd); +static void io_drop_inflight_file(struct io_kiocb *req); +static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags); static void __io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); @@ -1313,13 +1309,20 @@ static void io_rsrc_refs_refill(struct io_ring_ctx *ctx) } static inline void io_req_set_rsrc_node(struct io_kiocb *req, - struct io_ring_ctx *ctx) + struct io_ring_ctx *ctx, + unsigned int issue_flags) { if (!req->fixed_rsrc_refs) { req->fixed_rsrc_refs = &ctx->rsrc_node->refs; - ctx->rsrc_cached_refs--; - if (unlikely(ctx->rsrc_cached_refs < 0)) - io_rsrc_refs_refill(ctx); + + if (!(issue_flags & IO_URING_F_UNLOCKED)) { + lockdep_assert_held(&ctx->uring_lock); + ctx->rsrc_cached_refs--; + if (unlikely(ctx->rsrc_cached_refs < 0)) + io_rsrc_refs_refill(ctx); + } else { + percpu_ref_get(req->fixed_rsrc_refs); + } } } @@ -1424,29 +1427,9 @@ static bool io_match_task(struct io_kiocb *head, struct task_struct *task, bool cancel_all) __must_hold(&req->ctx->timeout_lock) { - struct io_kiocb *req; - if (task && head->task != task) return false; - if (cancel_all) - return true; - - io_for_each_link(req, head) { - if (req->flags & REQ_F_INFLIGHT) - return true; - } - return false; -} - -static bool io_match_linked(struct io_kiocb *head) -{ - struct io_kiocb *req; - - io_for_each_link(req, head) { - if (req->flags & REQ_F_INFLIGHT) - return true; - } - return false; + return cancel_all; } /* @@ -1456,24 +1439,9 @@ static bool io_match_linked(struct io_kiocb *head) static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, bool cancel_all) { - bool matched; - if (task && head->task != task) return false; - if (cancel_all) - return true; - - if (head->flags & REQ_F_LINK_TIMEOUT) { - struct io_ring_ctx *ctx = head->ctx; - - /* protect against races with linked timeouts */ - spin_lock_irq(&ctx->timeout_lock); - matched = io_match_linked(head); - spin_unlock_irq(&ctx->timeout_lock); - } else { - matched = io_match_linked(head); - } - return matched; + return cancel_all; } static inline bool req_has_async_data(struct io_kiocb *req) @@ -1595,10 +1563,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_WQ_LIST(&ctx->locked_free_list); INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); INIT_WQ_LIST(&ctx->submit_state.compl_reqs); -#ifdef CONFIG_NET_RX_BUSY_POLL - INIT_LIST_HEAD(&ctx->napi_list); - spin_lock_init(&ctx->napi_lock); -#endif return ctx; err: kfree(ctx->dummy_ubuf); @@ -1636,14 +1600,6 @@ static inline bool io_req_ffs_set(struct io_kiocb *req) return req->flags & REQ_F_FIXED_FILE; } -static inline void io_req_track_inflight(struct io_kiocb *req) -{ - if (!(req->flags & REQ_F_INFLIGHT)) { - req->flags |= REQ_F_INFLIGHT; - atomic_inc(¤t->io_uring->inflight_tracked); - } -} - static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req) { if (WARN_ON_ONCE(!req->link)) @@ -1687,14 +1643,6 @@ static void io_prep_async_work(struct io_kiocb *req) if (def->unbound_nonreg_file) req->work.flags |= IO_WQ_WORK_UNBOUND; } - - switch (req->opcode) { - case IORING_OP_SPLICE: - case IORING_OP_TEE: - if (!S_ISREG(file_inode(req->splice.file_in)->i_mode)) - req->work.flags |= IO_WQ_WORK_UNBOUND; - break; - } } static void io_prep_async_link(struct io_kiocb *req) @@ -1788,12 +1736,11 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx) __must_hold(&ctx->completion_lock) { u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + struct io_kiocb *req, *tmp; spin_lock_irq(&ctx->timeout_lock); - while (!list_empty(&ctx->timeout_list)) { + list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { u32 events_needed, events_got; - struct io_kiocb *req = list_first_entry(&ctx->timeout_list, - struct io_kiocb, timeout.list); if (io_is_timeout_noseq(req)) break; @@ -1810,7 +1757,6 @@ static __cold void io_flush_timeouts(struct io_ring_ctx *ctx) if (events_got < events_needed) break; - list_del_init(&req->timeout.list); io_kill_timeout(req, 0); } ctx->cq_last_tm_flush = seq; @@ -2562,6 +2508,8 @@ static void io_req_task_work_add(struct io_kiocb *req, bool priority) WARN_ON_ONCE(!tctx); + io_drop_inflight_file(req); + spin_lock_irqsave(&tctx->task_lock, flags); if (priority) wq_list_add_tail(&req->io_task_work.node, &tctx->prior_task_list); @@ -3186,42 +3134,11 @@ static inline bool io_file_supports_nowait(struct io_kiocb *req) static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw.kiocb; - struct file *file = req->file; unsigned ioprio; int ret; - if (!io_req_ffs_set(req)) - req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; - kiocb->ki_pos = READ_ONCE(sqe->off); - kiocb->ki_flags = iocb_flags(file); - ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); - if (unlikely(ret)) - return ret; - - /* - * If the file is marked O_NONBLOCK, still allow retry for it if it - * supports async. Otherwise it's impossible to use O_NONBLOCK files - * reliably. If not, or it IOCB_NOWAIT is set, don't retry. - */ - if ((kiocb->ki_flags & IOCB_NOWAIT) || - ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) - req->flags |= REQ_F_NOWAIT; - - if (ctx->flags & IORING_SETUP_IOPOLL) { - if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) - return -EOPNOTSUPP; - - kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; - kiocb->ki_complete = io_complete_rw_iopoll; - req->iopoll_completed = 0; - } else { - if (kiocb->ki_flags & IOCB_HIPRI) - return -EINVAL; - kiocb->ki_complete = io_complete_rw; - } ioprio = READ_ONCE(sqe->ioprio); if (ioprio) { @@ -3237,6 +3154,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->imu = NULL; req->rw.addr = READ_ONCE(sqe->addr); req->rw.len = READ_ONCE(sqe->len); + req->rw.flags = READ_ONCE(sqe->rw_flags); req->buf_index = READ_ONCE(sqe->buf_index); return 0; } @@ -3367,7 +3285,8 @@ static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter return 0; } -static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) +static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter, + unsigned int issue_flags) { struct io_mapped_ubuf *imu = req->imu; u16 index, buf_index = req->buf_index; @@ -3377,7 +3296,7 @@ static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) if (unlikely(buf_index >= ctx->nr_user_bufs)) return -EFAULT; - io_req_set_rsrc_node(req, ctx); + io_req_set_rsrc_node(req, ctx, issue_flags); index = array_index_nospec(buf_index, ctx->nr_user_bufs); imu = READ_ONCE(ctx->user_bufs[index]); req->imu = imu; @@ -3539,7 +3458,7 @@ static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req, ssize_t ret; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { - ret = io_import_fixed(req, rw, iter); + ret = io_import_fixed(req, rw, iter, issue_flags); if (ret) return ERR_PTR(ret); return NULL; @@ -3740,13 +3659,6 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) return 0; } -static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (unlikely(!(req->file->f_mode & FMODE_READ))) - return -EBADF; - return io_prep_rw(req, sqe); -} - /* * This is our waitqueue callback handler, registered through __folio_lock_async() * when we initially tried to do the IO with the iocb armed our waitqueue. @@ -3834,6 +3746,49 @@ static bool need_read_all(struct io_kiocb *req) S_ISBLK(file_inode(req->file)->i_mode); } +static int io_rw_init_file(struct io_kiocb *req, fmode_t mode) +{ + struct kiocb *kiocb = &req->rw.kiocb; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = req->file; + int ret; + + if (unlikely(!file || !(file->f_mode & mode))) + return -EBADF; + + if (!io_req_ffs_set(req)) + req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; + + kiocb->ki_flags = iocb_flags(file); + ret = kiocb_set_rw_flags(kiocb, req->rw.flags); + if (unlikely(ret)) + return ret; + + /* + * If the file is marked O_NONBLOCK, still allow retry for it if it + * supports async. Otherwise it's impossible to use O_NONBLOCK files + * reliably. If not, or it IOCB_NOWAIT is set, don't retry. + */ + if ((kiocb->ki_flags & IOCB_NOWAIT) || + ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) + req->flags |= REQ_F_NOWAIT; + + if (ctx->flags & IORING_SETUP_IOPOLL) { + if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) + return -EOPNOTSUPP; + + kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; + kiocb->ki_complete = io_complete_rw_iopoll; + req->iopoll_completed = 0; + } else { + if (kiocb->ki_flags & IOCB_HIPRI) + return -EINVAL; + kiocb->ki_complete = io_complete_rw; + } + + return 0; +} + static int io_read(struct io_kiocb *req, unsigned int issue_flags) { struct io_rw_state __s, *s = &__s; @@ -3869,6 +3824,9 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; } + ret = io_rw_init_file(req, FMODE_READ); + if (unlikely(ret)) + return ret; req->result = iov_iter_count(&s->iter); if (force_nonblock) { @@ -3972,13 +3930,6 @@ out_free: return 0; } -static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) -{ - if (unlikely(!(req->file->f_mode & FMODE_WRITE))) - return -EBADF; - return io_prep_rw(req, sqe); -} - static int io_write(struct io_kiocb *req, unsigned int issue_flags) { struct io_rw_state __s, *s = &__s; @@ -3999,6 +3950,9 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; } + ret = io_rw_init_file(req, FMODE_WRITE); + if (unlikely(ret)) + return ret; req->result = iov_iter_count(&s->iter); if (force_nonblock) { @@ -4369,18 +4323,11 @@ static int __io_splice_prep(struct io_kiocb *req, if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - sp->file_in = NULL; sp->len = READ_ONCE(sqe->len); sp->flags = READ_ONCE(sqe->splice_flags); - if (unlikely(sp->flags & ~valid_flags)) return -EINVAL; - - sp->file_in = io_file_get(req->ctx, req, READ_ONCE(sqe->splice_fd_in), - (sp->flags & SPLICE_F_FD_IN_FIXED)); - if (!sp->file_in) - return -EBADF; - req->flags |= REQ_F_NEED_CLEANUP; + sp->splice_fd_in = READ_ONCE(sqe->splice_fd_in); return 0; } @@ -4395,20 +4342,29 @@ static int io_tee_prep(struct io_kiocb *req, static int io_tee(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; - struct file *in = sp->file_in; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; + struct file *in; long ret = 0; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; + + if (sp->flags & SPLICE_F_FD_IN_FIXED) + in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED); + else + in = io_file_get_normal(req, sp->splice_fd_in); + if (!in) { + ret = -EBADF; + goto done; + } + if (sp->len) ret = do_tee(in, out, sp->len, flags); if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) io_put_file(in); - req->flags &= ~REQ_F_NEED_CLEANUP; - +done: if (ret != sp->len) req_set_fail(req); io_req_complete(req, ret); @@ -4427,15 +4383,24 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) static int io_splice(struct io_kiocb *req, unsigned int issue_flags) { struct io_splice *sp = &req->splice; - struct file *in = sp->file_in; struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; loff_t *poff_in, *poff_out; + struct file *in; long ret = 0; if (issue_flags & IO_URING_F_NONBLOCK) return -EAGAIN; + if (sp->flags & SPLICE_F_FD_IN_FIXED) + in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED); + else + in = io_file_get_normal(req, sp->splice_fd_in); + if (!in) { + ret = -EBADF; + goto done; + } + poff_in = (sp->off_in == -1) ? NULL : &sp->off_in; poff_out = (sp->off_out == -1) ? NULL : &sp->off_out; @@ -4444,8 +4409,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags) if (!(sp->flags & SPLICE_F_FD_IN_FIXED)) io_put_file(in); - req->flags &= ~REQ_F_NEED_CLEANUP; - +done: if (ret != sp->len) req_set_fail(req); io_req_complete(req, ret); @@ -4513,9 +4477,6 @@ static int io_fsync_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; - if (!req->file) - return -EBADF; - if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index || @@ -5757,108 +5718,6 @@ IO_NETOP_FN(send); IO_NETOP_FN(recv); #endif /* CONFIG_NET */ -#ifdef CONFIG_NET_RX_BUSY_POLL - -#define NAPI_TIMEOUT (60 * SEC_CONVERSION) - -struct napi_entry { - struct list_head list; - unsigned int napi_id; - unsigned long timeout; -}; - -/* - * Add busy poll NAPI ID from sk. - */ -static void io_add_napi(struct file *file, struct io_ring_ctx *ctx) -{ - unsigned int napi_id; - struct socket *sock; - struct sock *sk; - struct napi_entry *ne; - - if (!net_busy_loop_on()) - return; - - sock = sock_from_file(file); - if (!sock) - return; - - sk = sock->sk; - if (!sk) - return; - - napi_id = READ_ONCE(sk->sk_napi_id); - - /* Non-NAPI IDs can be rejected */ - if (napi_id < MIN_NAPI_ID) - return; - - spin_lock(&ctx->napi_lock); - list_for_each_entry(ne, &ctx->napi_list, list) { - if (ne->napi_id == napi_id) { - ne->timeout = jiffies + NAPI_TIMEOUT; - goto out; - } - } - - ne = kmalloc(sizeof(*ne), GFP_NOWAIT); - if (!ne) - goto out; - - ne->napi_id = napi_id; - ne->timeout = jiffies + NAPI_TIMEOUT; - list_add_tail(&ne->list, &ctx->napi_list); -out: - spin_unlock(&ctx->napi_lock); -} - -static inline void io_check_napi_entry_timeout(struct napi_entry *ne) -{ - if (time_after(jiffies, ne->timeout)) { - list_del(&ne->list); - kfree(ne); - } -} - -/* - * Busy poll if globally on and supporting sockets found - */ -static bool io_napi_busy_loop(struct list_head *napi_list) -{ - struct napi_entry *ne, *n; - - list_for_each_entry_safe(ne, n, napi_list, list) { - napi_busy_loop(ne->napi_id, NULL, NULL, true, - BUSY_POLL_BUDGET); - io_check_napi_entry_timeout(ne); - } - return !list_empty(napi_list); -} - -static void io_free_napi_list(struct io_ring_ctx *ctx) -{ - spin_lock(&ctx->napi_lock); - while (!list_empty(&ctx->napi_list)) { - struct napi_entry *ne = - list_first_entry(&ctx->napi_list, struct napi_entry, - list); - - list_del(&ne->list); - kfree(ne); - } - spin_unlock(&ctx->napi_lock); -} -#else -static inline void io_add_napi(struct file *file, struct io_ring_ctx *ctx) -{ -} - -static inline void io_free_napi_list(struct io_ring_ctx *ctx) -{ -} -#endif /* CONFIG_NET_RX_BUSY_POLL */ - struct io_poll_table { struct poll_table_struct pt; struct io_kiocb *req; @@ -5972,7 +5831,7 @@ static void io_poll_remove_entries(struct io_kiocb *req) * either spurious wakeup or multishot CQE is served. 0 when it's done with * the request, then the mask is stored in req->result. */ -static int io_poll_check_events(struct io_kiocb *req) +static int io_poll_check_events(struct io_kiocb *req, bool locked) { struct io_ring_ctx *ctx = req->ctx; struct io_poll_iocb *poll = io_poll_get_single(req); @@ -5994,7 +5853,10 @@ static int io_poll_check_events(struct io_kiocb *req) if (!req->result) { struct poll_table_struct pt = { ._key = req->cflags }; - req->result = vfs_poll(req->file, &pt) & req->cflags; + if (unlikely(!io_assign_file(req, IO_URING_F_UNLOCKED))) + req->result = -EBADF; + else + req->result = vfs_poll(req->file, &pt) & req->cflags; } /* multishot, just fill an CQE and proceed */ @@ -6010,7 +5872,6 @@ static int io_poll_check_events(struct io_kiocb *req) if (unlikely(!filled)) return -ECANCELED; io_cqring_ev_posted(ctx); - io_add_napi(req->file, ctx); } else if (req->result) { return 0; } @@ -6029,7 +5890,7 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_poll_check_events(req); + ret = io_poll_check_events(req, *locked); if (ret > 0) return; @@ -6054,7 +5915,7 @@ static void io_apoll_task_func(struct io_kiocb *req, bool *locked) struct io_ring_ctx *ctx = req->ctx; int ret; - ret = io_poll_check_events(req); + ret = io_poll_check_events(req, *locked); if (ret > 0) return; @@ -6261,7 +6122,6 @@ static int __io_arm_poll_handler(struct io_kiocb *req, __io_poll_execute(req, mask, poll->events); return 0; } - io_add_napi(req->file, req->ctx); /* * Release ownership. If someone tried to queue a tw while it was @@ -6766,6 +6626,7 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0) return -EINVAL; + INIT_LIST_HEAD(&req->timeout.list); data->mode = io_translate_timeout_mode(flags); hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode); @@ -6992,11 +6853,10 @@ static int io_req_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) case IORING_OP_READV: case IORING_OP_READ_FIXED: case IORING_OP_READ: - return io_read_prep(req, sqe); case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: case IORING_OP_WRITE: - return io_write_prep(req, sqe); + return io_prep_rw(req, sqe); case IORING_OP_POLL_ADD: return io_poll_add_prep(req, sqe); case IORING_OP_POLL_REMOVE: @@ -7179,11 +7039,6 @@ static void io_clean_op(struct io_kiocb *req) kfree(io->free_iov); break; } - case IORING_OP_SPLICE: - case IORING_OP_TEE: - if (!(req->splice.flags & SPLICE_F_FD_IN_FIXED)) - io_put_file(req->splice.file_in); - break; case IORING_OP_OPENAT: case IORING_OP_OPENAT2: if (req->open.filename) @@ -7218,11 +7073,6 @@ static void io_clean_op(struct io_kiocb *req) kfree(req->apoll); req->apoll = NULL; } - if (req->flags & REQ_F_INFLIGHT) { - struct io_uring_task *tctx = req->task->io_uring; - - atomic_dec(&tctx->inflight_tracked); - } if (req->flags & REQ_F_CREDS) put_cred(req->creds); if (req->flags & REQ_F_ASYNC_DATA) { @@ -7232,6 +7082,23 @@ static void io_clean_op(struct io_kiocb *req) req->flags &= ~IO_REQ_CLEAN_FLAGS; } +static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags) +{ + if (req->file || !io_op_defs[req->opcode].needs_file) + return true; + + if (req->flags & REQ_F_FIXED_FILE) + req->file = io_file_get_fixed(req, req->work.fd, issue_flags); + else + req->file = io_file_get_normal(req, req->work.fd); + if (req->file) + return true; + + req_set_fail(req); + req->result = -EBADF; + return false; +} + static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) { const struct cred *creds = NULL; @@ -7242,6 +7109,8 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) if (!io_op_defs[req->opcode].audit_skip) audit_uring_entry(req->opcode); + if (unlikely(!io_assign_file(req, issue_flags))) + return -EBADF; switch (req->opcode) { case IORING_OP_NOP: @@ -7386,10 +7255,11 @@ static struct io_wq_work *io_wq_free_work(struct io_wq_work *work) static void io_wq_submit_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); + const struct io_op_def *def = &io_op_defs[req->opcode]; unsigned int issue_flags = IO_URING_F_UNLOCKED; bool needs_poll = false; struct io_kiocb *timeout; - int ret = 0; + int ret = 0, err = -ECANCELED; /* one will be dropped by ->io_free_work() after returning to io-wq */ if (!(req->flags & REQ_F_REFCOUNT)) @@ -7401,14 +7271,18 @@ static void io_wq_submit_work(struct io_wq_work *work) if (timeout) io_queue_linked_timeout(timeout); + if (!io_assign_file(req, issue_flags)) { + err = -EBADF; + work->flags |= IO_WQ_WORK_CANCEL; + } + /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ if (work->flags & IO_WQ_WORK_CANCEL) { - io_req_task_queue_fail(req, -ECANCELED); + io_req_task_queue_fail(req, err); return; } if (req->flags & REQ_F_FORCE_ASYNC) { - const struct io_op_def *def = &io_op_defs[req->opcode]; bool opcode_poll = def->pollin || def->pollout; if (opcode_poll && file_can_poll(req->file)) { @@ -7465,46 +7339,56 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file file_slot->file_ptr = file_ptr; } -static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) +static inline struct file *io_file_get_fixed(struct io_kiocb *req, int fd, + unsigned int issue_flags) { - struct file *file; + struct io_ring_ctx *ctx = req->ctx; + struct file *file = NULL; unsigned long file_ptr; + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_lock(&ctx->uring_lock); + if (unlikely((unsigned int)fd >= ctx->nr_user_files)) - return NULL; + goto out; fd = array_index_nospec(fd, ctx->nr_user_files); file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; file = (struct file *) (file_ptr & FFS_MASK); file_ptr &= ~FFS_MASK; /* mask in overlapping REQ_F and FFS bits */ req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT); - io_req_set_rsrc_node(req, ctx); + io_req_set_rsrc_node(req, ctx, 0); +out: + if (issue_flags & IO_URING_F_UNLOCKED) + mutex_unlock(&ctx->uring_lock); return file; } -static struct file *io_file_get_normal(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) +/* + * Drop the file for requeue operations. Only used of req->file is the + * io_uring descriptor itself. + */ +static void io_drop_inflight_file(struct io_kiocb *req) +{ + if (unlikely(req->flags & REQ_F_INFLIGHT)) { + fput(req->file); + req->file = NULL; + req->flags &= ~REQ_F_INFLIGHT; + } +} + +static struct file *io_file_get_normal(struct io_kiocb *req, int fd) { struct file *file = fget(fd); - trace_io_uring_file_get(ctx, req, req->user_data, fd); + trace_io_uring_file_get(req->ctx, req, req->user_data, fd); /* we don't allow fixed io_uring files */ - if (file && unlikely(file->f_op == &io_uring_fops)) - io_req_track_inflight(req); + if (file && file->f_op == &io_uring_fops) + req->flags |= REQ_F_INFLIGHT; return file; } -static inline struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed) -{ - if (fixed) - return io_file_get_fixed(ctx, req, fd); - else - return io_file_get_normal(ctx, req, fd); -} - static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) { struct io_kiocb *prev = req->timeout.prev; @@ -7744,6 +7628,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (io_op_defs[opcode].needs_file) { struct io_submit_state *state = &ctx->submit_state; + req->work.fd = READ_ONCE(sqe->fd); + /* * Plug now if we have more than 2 IO left after this, and the * target is potentially a read/write to block based storage. @@ -7753,11 +7639,6 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, state->need_plug = false; blk_start_plug_nr_ios(&state->plug, state->submit_nr); } - - req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), - (sqe_flags & IOSQE_FIXED_FILE)); - if (unlikely(!req->file)) - return -EBADF; } personality = READ_ONCE(sqe->personality); @@ -8032,13 +7913,7 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) !(ctx->flags & IORING_SETUP_R_DISABLED)) ret = io_submit_sqes(ctx, to_submit); mutex_unlock(&ctx->uring_lock); -#ifdef CONFIG_NET_RX_BUSY_POLL - spin_lock(&ctx->napi_lock); - if (!list_empty(&ctx->napi_list) && - io_napi_busy_loop(&ctx->napi_list)) - ++ret; - spin_unlock(&ctx->napi_lock); -#endif + if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait)) wake_up(&ctx->sqo_sq_wait); if (creds) @@ -8176,9 +8051,6 @@ struct io_wait_queue { struct io_ring_ctx *ctx; unsigned cq_tail; unsigned nr_timeouts; -#ifdef CONFIG_NET_RX_BUSY_POLL - unsigned busy_poll_to; -#endif }; static inline bool io_should_wake(struct io_wait_queue *iowq) @@ -8240,87 +8112,6 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, return 1; } -#ifdef CONFIG_NET_RX_BUSY_POLL -static void io_adjust_busy_loop_timeout(struct timespec64 *ts, - struct io_wait_queue *iowq) -{ - unsigned busy_poll_to = READ_ONCE(sysctl_net_busy_poll); - struct timespec64 pollto = ns_to_timespec64(1000 * (s64)busy_poll_to); - - if (timespec64_compare(ts, &pollto) > 0) { - *ts = timespec64_sub(*ts, pollto); - iowq->busy_poll_to = busy_poll_to; - } else { - u64 to = timespec64_to_ns(ts); - - do_div(to, 1000); - iowq->busy_poll_to = to; - ts->tv_sec = 0; - ts->tv_nsec = 0; - } -} - -static inline bool io_busy_loop_timeout(unsigned long start_time, - unsigned long bp_usec) -{ - if (bp_usec) { - unsigned long end_time = start_time + bp_usec; - unsigned long now = busy_loop_current_time(); - - return time_after(now, end_time); - } - return true; -} - -static bool io_busy_loop_end(void *p, unsigned long start_time) -{ - struct io_wait_queue *iowq = p; - - return signal_pending(current) || - io_should_wake(iowq) || - io_busy_loop_timeout(start_time, iowq->busy_poll_to); -} - -static void io_blocking_napi_busy_loop(struct list_head *napi_list, - struct io_wait_queue *iowq) -{ - unsigned long start_time = - list_is_singular(napi_list) ? 0 : - busy_loop_current_time(); - - do { - if (list_is_singular(napi_list)) { - struct napi_entry *ne = - list_first_entry(napi_list, - struct napi_entry, list); - - napi_busy_loop(ne->napi_id, io_busy_loop_end, iowq, - true, BUSY_POLL_BUDGET); - io_check_napi_entry_timeout(ne); - break; - } - } while (io_napi_busy_loop(napi_list) && - !io_busy_loop_end(iowq, start_time)); -} - -static void io_putback_napi_list(struct io_ring_ctx *ctx, - struct list_head *napi_list) -{ - struct napi_entry *cne, *lne; - - spin_lock(&ctx->napi_lock); - list_for_each_entry(cne, &ctx->napi_list, list) - list_for_each_entry(lne, napi_list, list) - if (cne->napi_id == lne->napi_id) { - list_del(&lne->list); - kfree(lne); - break; - } - list_splice(napi_list, &ctx->napi_list); - spin_unlock(&ctx->napi_lock); -} -#endif /* CONFIG_NET_RX_BUSY_POLL */ - /* * Wait until events become available, if we don't already have some. The * application must reap them itself, as they reside on the shared cq ring. @@ -8333,9 +8124,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, struct io_rings *rings = ctx->rings; ktime_t timeout = KTIME_MAX; int ret; -#ifdef CONFIG_NET_RX_BUSY_POLL - LIST_HEAD(local_napi_list); -#endif do { io_cqring_overflow_flush(ctx); @@ -8358,29 +8146,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return ret; } -#ifdef CONFIG_NET_RX_BUSY_POLL - iowq.busy_poll_to = 0; - if (!(ctx->flags & IORING_SETUP_SQPOLL)) { - spin_lock(&ctx->napi_lock); - list_splice_init(&ctx->napi_list, &local_napi_list); - spin_unlock(&ctx->napi_lock); - } -#endif if (uts) { struct timespec64 ts; if (get_timespec64(&ts, uts)) return -EFAULT; -#ifdef CONFIG_NET_RX_BUSY_POLL - if (!list_empty(&local_napi_list)) - io_adjust_busy_loop_timeout(&ts, &iowq); -#endif timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); } -#ifdef CONFIG_NET_RX_BUSY_POLL - else if (!list_empty(&local_napi_list)) - iowq.busy_poll_to = READ_ONCE(sysctl_net_busy_poll); -#endif init_waitqueue_func_entry(&iowq.wq, io_wake_function); iowq.wq.private = current; @@ -8390,12 +8162,6 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, iowq.cq_tail = READ_ONCE(ctx->rings->cq.head) + min_events; trace_io_uring_cqring_wait(ctx, min_events); -#ifdef CONFIG_NET_RX_BUSY_POLL - if (iowq.busy_poll_to) - io_blocking_napi_busy_loop(&local_napi_list, &iowq); - if (!list_empty(&local_napi_list)) - io_putback_napi_list(ctx, &local_napi_list); -#endif do { /* if we can't even flush overflow, don't wait for more */ if (!io_cqring_overflow_flush(ctx)) { @@ -8864,8 +8630,12 @@ static int __io_sqe_files_scm(struct io_ring_ctx *ctx, int nr, int offset) refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb_queue_head(&sk->sk_receive_queue, skb); - for (i = 0; i < nr_files; i++) - fput(fpl->fp[i]); + for (i = 0; i < nr; i++) { + struct file *file = io_file_from_index(ctx, i + offset); + + if (file) + fput(file); + } } else { kfree_skb(skb); free_uid(fpl->user); @@ -9156,13 +8926,15 @@ static int io_sqe_file_register(struct io_ring_ctx *ctx, struct file *file, static int io_queue_rsrc_removal(struct io_rsrc_data *data, unsigned idx, struct io_rsrc_node *node, void *rsrc) { + u64 *tag_slot = io_get_tag_slot(data, idx); struct io_rsrc_put *prsrc; prsrc = kzalloc(sizeof(*prsrc), GFP_KERNEL); if (!prsrc) return -ENOMEM; - prsrc->tag = *io_get_tag_slot(data, idx); + prsrc->tag = *tag_slot; + *tag_slot = 0; prsrc->rsrc = rsrc; list_add(&prsrc->list, &node->rsrc_list); return 0; @@ -9231,7 +9003,7 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; struct io_fixed_file *file_slot; struct file *file; - int ret, i; + int ret; io_ring_submit_lock(ctx, needs_lock); ret = -ENXIO; @@ -9244,8 +9016,8 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) if (ret) goto out; - i = array_index_nospec(offset, ctx->nr_user_files); - file_slot = io_fixed_file_slot(&ctx->file_table, i); + offset = array_index_nospec(offset, ctx->nr_user_files); + file_slot = io_fixed_file_slot(&ctx->file_table, offset); ret = -EBADF; if (!file_slot->file_ptr) goto out; @@ -9301,8 +9073,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (file_slot->file_ptr) { file = (struct file *)(file_slot->file_ptr & FFS_MASK); - err = io_queue_rsrc_removal(data, up->offset + done, - ctx->rsrc_node, file); + err = io_queue_rsrc_removal(data, i, ctx->rsrc_node, file); if (err) break; file_slot->file_ptr = 0; @@ -9327,7 +9098,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - *io_get_tag_slot(data, up->offset + done) = tag; + *io_get_tag_slot(data, i) = tag; io_fixed_file_set(file_slot, file); err = io_sqe_file_register(ctx, file, i); if (err) { @@ -9411,7 +9182,6 @@ static __cold int io_uring_alloc_task_context(struct task_struct *task, xa_init(&tctx->xa); init_waitqueue_head(&tctx->wait); atomic_set(&tctx->in_idle, 0); - atomic_set(&tctx->inflight_tracked, 0); task->io_uring = tctx; spin_lock_init(&tctx->task_lock); INIT_WQ_LIST(&tctx->task_list); @@ -9986,7 +9756,7 @@ static int __io_sqe_buffers_update(struct io_ring_ctx *ctx, i = array_index_nospec(offset, ctx->nr_user_bufs); if (ctx->user_bufs[i] != ctx->dummy_ubuf) { - err = io_queue_rsrc_removal(ctx->buf_data, offset, + err = io_queue_rsrc_removal(ctx->buf_data, i, ctx->rsrc_node, ctx->user_bufs[i]); if (unlikely(err)) { io_buffer_unmap(ctx, &imu); @@ -10181,7 +9951,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) io_req_caches_free(ctx); if (ctx->hash_map) io_wq_put_hash(ctx->hash_map); - io_free_napi_list(ctx); kfree(ctx->cancel_hash); kfree(ctx->dummy_ubuf); kfree(ctx->io_buffers); @@ -10604,7 +10373,7 @@ static __cold void io_uring_clean_tctx(struct io_uring_task *tctx) static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) { if (tracked) - return atomic_read(&tctx->inflight_tracked); + return 0; return percpu_counter_sum(&tctx->inflight); } @@ -11707,7 +11476,15 @@ static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx, if (len > cpumask_size()) len = cpumask_size(); - if (copy_from_user(new_mask, arg, len)) { + if (in_compat_syscall()) { + ret = compat_get_bitmap(cpumask_bits(new_mask), + (const compat_ulong_t __user *)arg, + len * 8 /* CHAR_BIT */); + } else { + ret = copy_from_user(new_mask, arg, len); + } + + if (ret) { free_cpumask_var(new_mask); return -EFAULT; } diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 47a53b3362b6..14a72224b657 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -4,10 +4,6 @@ config NFS_FS depends on INET && FILE_LOCKING && MULTIUSER select LOCKD select SUNRPC - select CRYPTO - select CRYPTO_HASH - select XXHASH - select CRYPTO_XXHASH select NFS_ACL_SUPPORT if NFS_V3_ACL help Choose Y here if you want to access files residing on other diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index bac4cf1a308e..c6b263b5faf1 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -39,7 +39,7 @@ #include <linux/sched.h> #include <linux/kmemleak.h> #include <linux/xattr.h> -#include <linux/xxhash.h> +#include <linux/hash.h> #include "delegation.h" #include "iostat.h" @@ -350,10 +350,7 @@ out: * of directory cookies. Content is addressed by the value of the * cookie index of the first readdir entry in a page. * - * The xxhash algorithm is chosen because it is fast, and is supposed - * to result in a decent flat distribution of hashes. - * - * We then select only the first 18 bits to avoid issues with excessive + * We select only the first 18 bits to avoid issues with excessive * memory use for the page cache XArray. 18 bits should allow the caching * of 262144 pages of sequences of readdir entries. Since each page holds * 127 readdir entries for a typical 64-bit system, that works out to a @@ -363,7 +360,7 @@ static pgoff_t nfs_readdir_page_cookie_hash(u64 cookie) { if (cookie == 0) return 0; - return xxhash(&cookie, sizeof(cookie), 0) & NFS_READDIR_COOKIE_MASK; + return hash_64(cookie, 18); } static bool nfs_readdir_page_validate(struct page *page, u64 last_cookie, @@ -1991,16 +1988,6 @@ const struct dentry_operations nfs4_dentry_operations = { }; EXPORT_SYMBOL_GPL(nfs4_dentry_operations); -static fmode_t flags_to_mode(int flags) -{ - fmode_t res = (__force fmode_t)flags & FMODE_EXEC; - if ((flags & O_ACCMODE) != O_WRONLY) - res |= FMODE_READ; - if ((flags & O_ACCMODE) != O_RDONLY) - res |= FMODE_WRITE; - return res; -} - static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags, struct file *filp) { return alloc_nfs_open_context(dentry, flags_to_mode(open_flags), filp); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 7eb3b08d702f..b4e46b0ffa2d 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1180,7 +1180,6 @@ int nfs_open(struct inode *inode, struct file *filp) nfs_fscache_open_file(inode, filp); return 0; } -EXPORT_SYMBOL_GPL(nfs_open); /* * This function is called whenever some part of NFS notices that diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 57b0497105c8..7eefa16ed381 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -42,6 +42,16 @@ static inline bool nfs_lookup_is_soft_revalidate(const struct dentry *dentry) return true; } +static inline fmode_t flags_to_mode(int flags) +{ + fmode_t res = (__force fmode_t)flags & FMODE_EXEC; + if ((flags & O_ACCMODE) != O_WRONLY) + res |= FMODE_READ; + if ((flags & O_ACCMODE) != O_RDONLY) + res |= FMODE_WRITE; + return res; +} + /* * Note: RFC 1813 doesn't limit the number of auth flavors that * a server can return, so make something up. diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index ad3405c64b9e..e7b34f7e0614 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -997,7 +997,7 @@ int __init nfs4_xattr_cache_init(void) nfs4_xattr_cache_cachep = kmem_cache_create("nfs4_xattr_cache_cache", sizeof(struct nfs4_xattr_cache), 0, - (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT), + (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD), nfs4_xattr_cache_init_once); if (nfs4_xattr_cache_cachep == NULL) return -ENOMEM; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index d258933cf8c8..7b861e4f0533 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -32,6 +32,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) struct dentry *parent = NULL; struct inode *dir; unsigned openflags = filp->f_flags; + fmode_t f_mode; struct iattr attr; int err; @@ -50,8 +51,9 @@ nfs4_file_open(struct inode *inode, struct file *filp) if (err) return err; + f_mode = filp->f_mode; if ((openflags & O_ACCMODE) == 3) - return nfs_open(inode, filp); + f_mode |= flags_to_mode(openflags); /* We can't create new files here */ openflags &= ~(O_CREAT|O_EXCL); @@ -59,7 +61,7 @@ nfs4_file_open(struct inode *inode, struct file *filp) parent = dget_parent(dentry); dir = d_inode(parent); - ctx = alloc_nfs_open_context(file_dentry(filp), filp->f_mode, filp); + ctx = alloc_nfs_open_context(file_dentry(filp), f_mode, filp); err = PTR_ERR(ctx); if (IS_ERR(ctx)) goto out; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e3f5b380cefe..16106f805ffa 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -9615,6 +9615,8 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout) nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0); task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return ERR_CAST(task); status = rpc_wait_for_completion_task(task); if (status != 0) diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 5fa11e1aca4c..6f325e10056c 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -347,6 +347,7 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir, data = kzalloc(sizeof(*data), GFP_KERNEL); if (data == NULL) return ERR_PTR(-ENOMEM); + task_setup_data.task = &data->task; task_setup_data.callback_data = data; data->cred = get_current_cred(); diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index 42dcf96881b6..a12ac0356c69 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -703,19 +703,6 @@ int sysfs_change_owner(struct kobject *kobj, kuid_t kuid, kgid_t kgid) ktype = get_ktype(kobj); if (ktype) { - struct attribute **kattr; - - /* - * Change owner of the default attributes associated with the - * ktype of @kobj. - */ - for (kattr = ktype->default_attrs; kattr && *kattr; kattr++) { - error = sysfs_file_change_owner(kobj, (*kattr)->name, - kuid, kgid); - if (error) - return error; - } - /* * Change owner of the default groups associated with the * ktype of @kobj. diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 3f7f01f03869..c4b78c21d793 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -509,7 +509,6 @@ extern int unregister_acpi_notifier(struct notifier_block *); * External Functions */ -int acpi_bus_get_device(acpi_handle handle, struct acpi_device **device); struct acpi_device *acpi_fetch_acpi_dev(acpi_handle handle); acpi_status acpi_bus_get_status_handle(acpi_handle handle, unsigned long long *sta); diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index c08758b6b364..c05d2ce9b6cd 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -269,6 +269,7 @@ bool hv_isolation_type_snp(void); u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size); void hyperv_cleanup(void); bool hv_query_ext_cap(u64 cap_query); +void hv_setup_dma_ops(struct device *dev, bool coherent); void *hv_map_memory(void *addr, unsigned long size); void hv_unmap_memory(void *addr); #else /* CONFIG_HYPERV */ diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index fd7feb5c7894..eee6f7763a39 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -565,10 +565,14 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ do { \ unsigned long _sz = huge_page_size(h); \ - if (_sz == PMD_SIZE) \ - tlb_flush_pmd_range(tlb, address, _sz); \ - else if (_sz == PUD_SIZE) \ + if (_sz >= P4D_SIZE) \ + tlb_flush_p4d_range(tlb, address, _sz); \ + else if (_sz >= PUD_SIZE) \ tlb_flush_pud_range(tlb, address, _sz); \ + else if (_sz >= PMD_SIZE) \ + tlb_flush_pmd_range(tlb, address, _sz); \ + else \ + tlb_flush_pte_range(tlb, address, _sz); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) diff --git a/include/drm/bridge/dw_hdmi.h b/include/drm/bridge/dw_hdmi.h index 2a1f85f9a8a3..f668e75fbabe 100644 --- a/include/drm/bridge/dw_hdmi.h +++ b/include/drm/bridge/dw_hdmi.h @@ -143,6 +143,11 @@ struct dw_hdmi_plat_data { const struct drm_display_info *info, const struct drm_display_mode *mode); + /* Platform-specific audio enable/disable (optional) */ + void (*enable_audio)(struct dw_hdmi *hdmi, int channel, + int width, int rate, int non_pcm); + void (*disable_audio)(struct dw_hdmi *hdmi); + /* Vendor PHY support */ const struct dw_hdmi_phy_ops *phy_ops; const char *phy_name; @@ -173,6 +178,8 @@ void dw_hdmi_setup_rx_sense(struct dw_hdmi *hdmi, bool hpd, bool rx_sense); int dw_hdmi_set_plugged_cb(struct dw_hdmi *hdmi, hdmi_codec_plugged_cb fn, struct device *codec_dev); +void dw_hdmi_set_sample_non_pcm(struct dw_hdmi *hdmi, unsigned int non_pcm); +void dw_hdmi_set_sample_width(struct dw_hdmi *hdmi, unsigned int width); void dw_hdmi_set_sample_rate(struct dw_hdmi *hdmi, unsigned int rate); void dw_hdmi_set_channel_count(struct dw_hdmi *hdmi, unsigned int cnt); void dw_hdmi_set_channel_status(struct dw_hdmi *hdmi, u8 *channel_status); @@ -187,9 +194,11 @@ void dw_hdmi_phy_i2c_set_addr(struct dw_hdmi *hdmi, u8 address); void dw_hdmi_phy_i2c_write(struct dw_hdmi *hdmi, unsigned short data, unsigned char addr); +void dw_hdmi_phy_gen1_reset(struct dw_hdmi *hdmi); + void dw_hdmi_phy_gen2_pddq(struct dw_hdmi *hdmi, u8 enable); void dw_hdmi_phy_gen2_txpwron(struct dw_hdmi *hdmi, u8 enable); -void dw_hdmi_phy_reset(struct dw_hdmi *hdmi); +void dw_hdmi_phy_gen2_reset(struct dw_hdmi *hdmi); enum drm_connector_status dw_hdmi_phy_read_hpd(struct dw_hdmi *hdmi, void *data); diff --git a/include/drm/dp/drm_dp_helper.h b/include/drm/dp/drm_dp_helper.h index 1eccd9741943..91af98e6617c 100644 --- a/include/drm/dp/drm_dp_helper.h +++ b/include/drm/dp/drm_dp_helper.h @@ -2053,6 +2053,7 @@ struct drm_dp_aux { bool is_remote; }; +int drm_dp_dpcd_probe(struct drm_dp_aux *aux, unsigned int offset); ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, void *buffer, size_t size); ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset, diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h index 1701c2128a5c..0777725085df 100644 --- a/include/drm/drm_atomic.h +++ b/include/drm/drm_atomic.h @@ -227,6 +227,18 @@ struct drm_private_state_funcs { */ void (*atomic_destroy_state)(struct drm_private_obj *obj, struct drm_private_state *state); + + /** + * @atomic_print_state: + * + * If driver subclasses &struct drm_private_state, it should implement + * this optional hook for printing additional driver specific state. + * + * Do not call this directly, use drm_atomic_private_obj_print_state() + * instead. + */ + void (*atomic_print_state)(struct drm_printer *p, + const struct drm_private_state *state); }; /** @@ -311,14 +323,21 @@ struct drm_private_obj { /** * struct drm_private_state - base struct for driver private object state - * @state: backpointer to global drm_atomic_state * - * Currently only contains a backpointer to the overall atomic update, but in - * the future also might hold synchronization information similar to e.g. - * &drm_crtc.commit. + * Currently only contains a backpointer to the overall atomic update, + * and the relevant private object but in the future also might hold + * synchronization information similar to e.g. &drm_crtc.commit. */ struct drm_private_state { + /** + * @state: backpointer to global drm_atomic_state + */ struct drm_atomic_state *state; + + /** + * @obj: backpointer to the private object + */ + struct drm_private_obj *obj; }; struct __drm_private_objs_state { diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h index 144c495b99c4..b7e170584000 100644 --- a/include/drm/drm_edid.h +++ b/include/drm/drm_edid.h @@ -372,8 +372,8 @@ struct drm_connector; struct drm_connector_state; struct drm_display_mode; -int drm_edid_to_sad(struct edid *edid, struct cea_sad **sads); -int drm_edid_to_speaker_allocation(struct edid *edid, u8 **sadb); +int drm_edid_to_sad(const struct edid *edid, struct cea_sad **sads); +int drm_edid_to_speaker_allocation(const struct edid *edid, u8 **sadb); int drm_av_sync_delay(struct drm_connector *connector, const struct drm_display_mode *mode); @@ -569,8 +569,8 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid); int drm_add_override_edid_modes(struct drm_connector *connector); u8 drm_match_cea_mode(const struct drm_display_mode *to_match); -bool drm_detect_hdmi_monitor(struct edid *edid); -bool drm_detect_monitor_audio(struct edid *edid); +bool drm_detect_hdmi_monitor(const struct edid *edid); +bool drm_detect_monitor_audio(const struct edid *edid); enum hdmi_quantization_range drm_default_rgb_quant_range(const struct drm_display_mode *mode); int drm_add_modes_noedid(struct drm_connector *connector, @@ -578,11 +578,11 @@ int drm_add_modes_noedid(struct drm_connector *connector, void drm_set_preferred_mode(struct drm_connector *connector, int hpref, int vpref); -int drm_edid_header_is_valid(const u8 *raw_edid); +int drm_edid_header_is_valid(const void *edid); bool drm_edid_block_valid(u8 *raw_edid, int block, bool print_bad_edid, bool *edid_corrupt); bool drm_edid_is_valid(struct edid *edid); -void drm_edid_get_monitor_name(struct edid *edid, char *name, +void drm_edid_get_monitor_name(const struct edid *edid, char *name, int buflen); struct drm_display_mode *drm_mode_find_dmt(struct drm_device *dev, int hsize, int vsize, int fresh, diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h index a3acb7ac3550..e0a73a1e2df7 100644 --- a/include/drm/drm_file.h +++ b/include/drm/drm_file.h @@ -248,7 +248,7 @@ struct drm_file { */ struct drm_master *master; - /** @master_lock: Serializes @master. */ + /** @master_lookup_lock: Serializes @master. */ spinlock_t master_lookup_lock; /** @pid: Process that opened this file. */ diff --git a/include/drm/drm_format_helper.h b/include/drm/drm_format_helper.h index 0b0937c0b2f6..55145eca0782 100644 --- a/include/drm/drm_format_helper.h +++ b/include/drm/drm_format_helper.h @@ -43,8 +43,7 @@ int drm_fb_blit_toio(void __iomem *dst, unsigned int dst_pitch, uint32_t dst_for const void *vmap, const struct drm_framebuffer *fb, const struct drm_rect *rect); -void drm_fb_xrgb8888_to_mono_reversed(void *dst, unsigned int dst_pitch, const void *src, - const struct drm_framebuffer *fb, - const struct drm_rect *clip); +void drm_fb_xrgb8888_to_mono(void *dst, unsigned int dst_pitch, const void *src, + const struct drm_framebuffer *fb, const struct drm_rect *clip); #endif /* __LINUX_DRM_FORMAT_HELPER_H */ diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h index e2941cee14b6..9d7c61a122dc 100644 --- a/include/drm/drm_gem.h +++ b/include/drm/drm_gem.h @@ -407,11 +407,6 @@ int drm_gem_lock_reservations(struct drm_gem_object **objs, int count, struct ww_acquire_ctx *acquire_ctx); void drm_gem_unlock_reservations(struct drm_gem_object **objs, int count, struct ww_acquire_ctx *acquire_ctx); -int drm_gem_fence_array_add(struct xarray *fence_array, - struct dma_fence *fence); -int drm_gem_fence_array_add_implicit(struct xarray *fence_array, - struct drm_gem_object *obj, - bool write); int drm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev, u32 handle, u64 *offset); diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h index 147e51b6d241..51e09a1a106a 100644 --- a/include/drm/drm_mipi_dsi.h +++ b/include/drm/drm_mipi_dsi.h @@ -137,6 +137,8 @@ struct mipi_dsi_host *of_find_mipi_dsi_host_by_node(struct device_node *node); #define MIPI_DSI_CLOCK_NON_CONTINUOUS BIT(10) /* transmit data in low power */ #define MIPI_DSI_MODE_LPM BIT(11) +/* transmit data ending at the same time for all lanes within one hsync */ +#define MIPI_DSI_HS_PKT_END_ALIGNED BIT(12) enum mipi_dsi_pixel_format { MIPI_DSI_FMT_RGB888, diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h index 2fa6b2c33b3f..a80ae9639e96 100644 --- a/include/drm/drm_modes.h +++ b/include/drm/drm_modes.h @@ -492,6 +492,8 @@ void drm_mode_set_crtcinfo(struct drm_display_mode *p, int adjust_flags); void drm_mode_copy(struct drm_display_mode *dst, const struct drm_display_mode *src); +void drm_mode_init(struct drm_display_mode *dst, + const struct drm_display_mode *src); struct drm_display_mode *drm_mode_duplicate(struct drm_device *dev, const struct drm_display_mode *mode); bool drm_mode_match(const struct drm_display_mode *mode1, diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index fdfa9f37ce05..fafa70ac1337 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -1384,7 +1384,7 @@ struct drm_mode_config_helper_funcs { * starting to commit the update to the hardware. * * After the atomic update is committed to the hardware this hook needs - * to call drm_atomic_helper_commit_hw_done(). Then wait for the upate + * to call drm_atomic_helper_commit_hw_done(). Then wait for the update * to be executed by the hardware, for example using * drm_atomic_helper_wait_for_vblanks() or * drm_atomic_helper_wait_for_flip_done(), and then clean up the old diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index 944f83ef9f2e..0fca8f38bee4 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -270,6 +270,7 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f); * @sched: the scheduler instance on which this job is scheduled. * @s_fence: contains the fences for the scheduling of job. * @finish_cb: the callback for the finished fence. + * @work: Helper to reschdeule job kill to different context. * @id: a unique id assigned to each job scheduled on the scheduler. * @karma: increment on every hang caused by this job. If this exceeds the hang * limit of the scheduler then the job is marked guilty and will not diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 155b19ee12fb..2d524f8b0802 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -55,8 +55,6 @@ struct ttm_placement; struct ttm_place; -struct ttm_lru_bulk_move; - /** * enum ttm_bo_type * @@ -94,10 +92,8 @@ struct ttm_tt; * @ttm: TTM structure holding system pages. * @evicted: Whether the object was evicted without user-space knowing. * @deleted: True if the object is only a zombie and already deleted. - * @lru: List head for the lru list. * @ddestroy: List head for the delayed destroy list. * @swap: List head for swap LRU list. - * @moving: Fence set when BO is moving * @offset: The current GPU offset, which can have different meanings * depending on the memory type. For SYSTEM type memory, it should be 0. * @cur_placement: Hint of current placement. @@ -138,19 +134,18 @@ struct ttm_buffer_object { struct ttm_resource *resource; struct ttm_tt *ttm; bool deleted; + struct ttm_lru_bulk_move *bulk_move; /** * Members protected by the bdev::lru_lock. */ - struct list_head lru; struct list_head ddestroy; /** * Members protected by a bo reservation. */ - struct dma_fence *moving; unsigned priority; unsigned pin_count; @@ -291,30 +286,9 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, */ void ttm_bo_put(struct ttm_buffer_object *bo); -/** - * ttm_bo_move_to_lru_tail - * - * @bo: The buffer object. - * @mem: Resource object. - * @bulk: optional bulk move structure to remember BO positions - * - * Move this BO to the tail of all lru lists used to lookup and reserve an - * object. This function must be called with struct ttm_global::lru_lock - * held, and is used to make a BO less likely to be considered for eviction. - */ -void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo, - struct ttm_resource *mem, - struct ttm_lru_bulk_move *bulk); - -/** - * ttm_bo_bulk_move_lru_tail - * - * @bulk: bulk move structure - * - * Bulk move BOs to the LRU tail, only valid to use when driver makes sure that - * BO order never changes. Should be called with ttm_global::lru_lock held. - */ -void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk); +void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo); +void ttm_bo_set_bulk_move(struct ttm_buffer_object *bo, + struct ttm_lru_bulk_move *bulk); /** * ttm_bo_lock_delayed_workqueue @@ -540,34 +514,8 @@ ssize_t ttm_bo_io(struct ttm_device *bdev, struct file *filp, int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, gfp_t gfp_flags); -/** - * ttm_bo_pin - Pin the buffer object. - * @bo: The buffer object to pin - * - * Make sure the buffer is not evicted any more during memory pressure. - */ -static inline void ttm_bo_pin(struct ttm_buffer_object *bo) -{ - dma_resv_assert_held(bo->base.resv); - WARN_ON_ONCE(!kref_read(&bo->kref)); - ++bo->pin_count; -} - -/** - * ttm_bo_unpin - Unpin the buffer object. - * @bo: The buffer object to unpin - * - * Allows the buffer object to be evicted again during memory pressure. - */ -static inline void ttm_bo_unpin(struct ttm_buffer_object *bo) -{ - dma_resv_assert_held(bo->base.resv); - WARN_ON_ONCE(!kref_read(&bo->kref)); - if (bo->pin_count) - --bo->pin_count; - else - WARN_ON_ONCE(true); -} +void ttm_bo_pin(struct ttm_buffer_object *bo); +void ttm_bo_unpin(struct ttm_buffer_object *bo); int ttm_mem_evict_first(struct ttm_device *bdev, struct ttm_resource_manager *man, diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 5f087575194b..897b88f0bd59 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -45,33 +45,6 @@ #include "ttm_tt.h" #include "ttm_pool.h" -/** - * struct ttm_lru_bulk_move_pos - * - * @first: first BO in the bulk move range - * @last: last BO in the bulk move range - * - * Positions for a lru bulk move. - */ -struct ttm_lru_bulk_move_pos { - struct ttm_buffer_object *first; - struct ttm_buffer_object *last; -}; - -/** - * struct ttm_lru_bulk_move - * - * @tt: first/last lru entry for BOs in the TT domain - * @vram: first/last lru entry for BOs in the VRAM domain - * @swap: first/last lru entry for BOs on the swap list - * - * Helper structure for bulk moves on the LRU list. - */ -struct ttm_lru_bulk_move { - struct ttm_lru_bulk_move_pos tt[TTM_MAX_BO_PRIORITY]; - struct ttm_lru_bulk_move_pos vram[TTM_MAX_BO_PRIORITY]; -}; - /* * ttm_bo.c */ @@ -182,7 +155,7 @@ static inline void ttm_bo_move_to_lru_tail_unlocked(struct ttm_buffer_object *bo) { spin_lock(&bo->bdev->lru_lock); - ttm_bo_move_to_lru_tail(bo, bo->resource, NULL); + ttm_bo_move_to_lru_tail(bo); spin_unlock(&bo->bdev->lru_lock); } @@ -272,7 +245,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, struct ttm_resource *new_mem); /** - * ttm_bo_move_accel_cleanup. + * ttm_bo_move_sync_cleanup. * * @bo: A pointer to a struct ttm_buffer_object. * @new_mem: struct ttm_resource indicating where to move. @@ -280,13 +253,8 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, * Special case of ttm_bo_move_accel_cleanup where the bo is guaranteed * by the caller to be idle. Typically used after memcpy buffer moves. */ -static inline void ttm_bo_move_sync_cleanup(struct ttm_buffer_object *bo, - struct ttm_resource *new_mem) -{ - int ret = ttm_bo_move_accel_cleanup(bo, NULL, true, false, new_mem); - - WARN_ON(ret); -} +void ttm_bo_move_sync_cleanup(struct ttm_buffer_object *bo, + struct ttm_resource *new_mem); /** * ttm_bo_pipeline_gutting. diff --git a/include/drm/ttm/ttm_device.h b/include/drm/ttm/ttm_device.h index 0a4ddec78d8f..95b3c04b1ab9 100644 --- a/include/drm/ttm/ttm_device.h +++ b/include/drm/ttm/ttm_device.h @@ -30,8 +30,6 @@ #include <drm/ttm/ttm_resource.h> #include <drm/ttm/ttm_pool.h> -#define TTM_NUM_MEM_TYPES 8 - struct ttm_device; struct ttm_placement; struct ttm_buffer_object; @@ -201,15 +199,6 @@ struct ttm_device_funcs { void *buf, int len, int write); /** - * struct ttm_bo_driver member del_from_lru_notify - * - * @bo: the buffer object deleted from lru - * - * notify driver that a BO was deleted from LRU. - */ - void (*del_from_lru_notify)(struct ttm_buffer_object *bo); - - /** * Notify the driver that we're about to release a BO * * @bo: BO that is about to be released diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h index 0f1d55262c68..441653693970 100644 --- a/include/drm/ttm/ttm_resource.h +++ b/include/drm/ttm/ttm_resource.h @@ -26,14 +26,17 @@ #define _TTM_RESOURCE_H_ #include <linux/types.h> +#include <linux/list.h> #include <linux/mutex.h> #include <linux/iosys-map.h> #include <linux/dma-fence.h> + #include <drm/drm_print.h> #include <drm/ttm/ttm_caching.h> #include <drm/ttm/ttm_kmap_iter.h> #define TTM_MAX_BO_PRIORITY 4U +#define TTM_NUM_MEM_TYPES 8 struct ttm_device; struct ttm_resource_manager; @@ -178,6 +181,47 @@ struct ttm_resource { uint32_t placement; struct ttm_bus_placement bus; struct ttm_buffer_object *bo; + + /** + * @lru: Least recently used list, see &ttm_resource_manager.lru + */ + struct list_head lru; +}; + +/** + * struct ttm_resource_cursor + * + * @priority: the current priority + * + * Cursor to iterate over the resources in a manager. + */ +struct ttm_resource_cursor { + unsigned int priority; +}; + +/** + * struct ttm_lru_bulk_move_pos + * + * @first: first res in the bulk move range + * @last: last res in the bulk move range + * + * Range of resources for a lru bulk move. + */ +struct ttm_lru_bulk_move_pos { + struct ttm_resource *first; + struct ttm_resource *last; +}; + +/** + * struct ttm_lru_bulk_move + * + * @pos: first/last lru entry for resources in the each domain/priority + * + * Container for the current bulk move state. Should be used with + * ttm_lru_bulk_move_init() and ttm_bo_set_bulk_move(). + */ +struct ttm_lru_bulk_move { + struct ttm_lru_bulk_move_pos pos[TTM_NUM_MEM_TYPES][TTM_MAX_BO_PRIORITY]; }; /** @@ -266,6 +310,15 @@ ttm_resource_manager_cleanup(struct ttm_resource_manager *man) man->move = NULL; } +void ttm_lru_bulk_move_init(struct ttm_lru_bulk_move *bulk); +void ttm_lru_bulk_move_add(struct ttm_lru_bulk_move *bulk, + struct ttm_resource *res); +void ttm_lru_bulk_move_del(struct ttm_lru_bulk_move *bulk, + struct ttm_resource *res); +void ttm_lru_bulk_move_tail(struct ttm_lru_bulk_move *bulk); + +void ttm_resource_move_to_lru_tail(struct ttm_resource *res); + void ttm_resource_init(struct ttm_buffer_object *bo, const struct ttm_place *place, struct ttm_resource *res); @@ -292,6 +345,26 @@ uint64_t ttm_resource_manager_usage(struct ttm_resource_manager *man); void ttm_resource_manager_debug(struct ttm_resource_manager *man, struct drm_printer *p); +struct ttm_resource * +ttm_resource_manager_first(struct ttm_resource_manager *man, + struct ttm_resource_cursor *cursor); +struct ttm_resource * +ttm_resource_manager_next(struct ttm_resource_manager *man, + struct ttm_resource_cursor *cursor, + struct ttm_resource *res); + +/** + * ttm_resource_manager_for_each_res - iterate over all resources + * @man: the resource manager + * @cursor: struct ttm_resource_cursor for the current position + * @res: the current resource + * + * Iterate over all the evictable resources in a resource manager. + */ +#define ttm_resource_manager_for_each_res(man, cursor, res) \ + for (res = ttm_resource_manager_first(man, cursor); res; \ + res = ttm_resource_manager_next(man, cursor, res)) + struct ttm_kmap_iter * ttm_kmap_iter_iomap_init(struct ttm_kmap_iter_iomap *iter_io, struct io_mapping *iomap, @@ -308,4 +381,8 @@ ttm_kmap_iter_linear_io_init(struct ttm_kmap_iter_linear_io *iter_io, void ttm_kmap_iter_linear_io_fini(struct ttm_kmap_iter_linear_io *iter_io, struct ttm_device *bdev, struct ttm_resource *mem); + +void ttm_resource_manager_create_debugfs(struct ttm_resource_manager *man, + struct dentry * parent, + const char *name); #endif diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h index f20832139815..17a0310e8aaa 100644 --- a/include/drm/ttm/ttm_tt.h +++ b/include/drm/ttm/ttm_tt.h @@ -140,6 +140,7 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc); * @bo: The buffer object we create the ttm for. * @page_flags: Page flags as identified by TTM_TT_FLAG_XX flags. * @caching: the desired caching state of the pages + * @extra_pages: Extra pages needed for the driver. * * Create a struct ttm_tt to back data with system memory pages. * No pages are actually allocated. @@ -147,7 +148,8 @@ int ttm_tt_create(struct ttm_buffer_object *bo, bool zero_alloc); * NULL: Out of memory. */ int ttm_tt_init(struct ttm_tt *ttm, struct ttm_buffer_object *bo, - uint32_t page_flags, enum ttm_caching caching); + uint32_t page_flags, enum ttm_caching caching, + unsigned long extra_pages); int ttm_sg_tt_init(struct ttm_tt *ttm_dma, struct ttm_buffer_object *bo, uint32_t page_flags, enum ttm_caching caching); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c1fc4af47f69..3a9d2d7cc6b7 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -570,9 +570,11 @@ static inline u32 type_flag(u32 type) return type & ~BPF_BASE_TYPE_MASK; } +/* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog) { - return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type; + return prog->type == BPF_PROG_TYPE_EXT ? + prog->aux->dst_prog->type : prog->type; } #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 2097760e8e95..71731796c8c3 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -393,27 +393,30 @@ struct dma_buf { * e.g. exposed in `Implicit Fence Poll Support`_ must follow the * below rules. * - * - Drivers must add a shared fence through dma_resv_add_shared_fence() - * for anything the userspace API considers a read access. This highly - * depends upon the API and window system. + * - Drivers must add a read fence through dma_resv_add_fence() with the + * DMA_RESV_USAGE_READ flag for anything the userspace API considers a + * read access. This highly depends upon the API and window system. * - * - Similarly drivers must set the exclusive fence through - * dma_resv_add_excl_fence() for anything the userspace API considers - * write access. + * - Similarly drivers must add a write fence through + * dma_resv_add_fence() with the DMA_RESV_USAGE_WRITE flag for + * anything the userspace API considers write access. * - * - Drivers may just always set the exclusive fence, since that only + * - Drivers may just always add a write fence, since that only * causes unecessarily synchronization, but no correctness issues. * * - Some drivers only expose a synchronous userspace API with no * pipelining across drivers. These do not set any fences for their * access. An example here is v4l. * + * - Driver should use dma_resv_usage_rw() when retrieving fences as + * dependency for implicit synchronization. + * * DYNAMIC IMPORTER RULES: * * Dynamic importers, see dma_buf_attachment_is_dynamic(), have * additional constraints on how they set up fences: * - * - Dynamic importers must obey the exclusive fence and wait for it to + * - Dynamic importers must obey the write fences and wait for them to * signal before allowing access to the buffer's underlying storage * through the device. * @@ -423,10 +426,9 @@ struct dma_buf { * * IMPORTANT: * - * All drivers must obey the struct dma_resv rules, specifically the - * rules for updating fences, see &dma_resv.fence_excl and - * &dma_resv.fence. If these dependency rules are broken access tracking - * can be lost resulting in use after free issues. + * All drivers and memory management related functions must obey the + * struct dma_resv rules, specifically the rules for updating and + * obeying fences. See enum dma_resv_usage for further descriptions. */ struct dma_resv *resv; diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index fec374f69e12..ec7f25def392 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -61,6 +61,21 @@ to_dma_fence_array(struct dma_fence *fence) return container_of(fence, struct dma_fence_array, base); } +/** + * dma_fence_array_for_each - iterate over all fences in array + * @fence: current fence + * @index: index into the array + * @head: potential dma_fence_array object + * + * Test if @array is a dma_fence_array object and if yes iterate over all fences + * in the array. If not just iterate over the fence in @array itself. + * + * For a deep dive iterator see dma_fence_unwrap_for_each(). + */ +#define dma_fence_array_for_each(fence, index, head) \ + for (index = 0, fence = dma_fence_array_first(head); fence; \ + ++(index), fence = dma_fence_array_next(head, index)) + struct dma_fence_array *dma_fence_array_create(int num_fences, struct dma_fence **fences, u64 context, unsigned seqno, @@ -68,4 +83,8 @@ struct dma_fence_array *dma_fence_array_create(int num_fences, bool dma_fence_match_context(struct dma_fence *fence, u64 context); +struct dma_fence *dma_fence_array_first(struct dma_fence *head); +struct dma_fence *dma_fence_array_next(struct dma_fence *head, + unsigned int index); + #endif /* __LINUX_DMA_FENCE_ARRAY_H */ diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 10d51bcdf7b7..4bdf0b96da28 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -112,6 +112,8 @@ static inline void dma_fence_chain_free(struct dma_fence_chain *chain) * * Iterate over all fences in the chain. We keep a reference to the current * fence while inside the loop which must be dropped when breaking out. + * + * For a deep dive iterator see dma_fence_unwrap_for_each(). */ #define dma_fence_chain_for_each(iter, head) \ for (iter = dma_fence_get(head); iter; \ diff --git a/include/linux/dma-fence-unwrap.h b/include/linux/dma-fence-unwrap.h new file mode 100644 index 000000000000..77e335a1bcac --- /dev/null +++ b/include/linux/dma-fence-unwrap.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * fence-chain: chain fences together in a timeline + * + * Copyright (C) 2022 Advanced Micro Devices, Inc. + * Authors: + * Christian König <christian.koenig@amd.com> + */ + +#ifndef __LINUX_DMA_FENCE_UNWRAP_H +#define __LINUX_DMA_FENCE_UNWRAP_H + +#include <linux/dma-fence-chain.h> +#include <linux/dma-fence-array.h> + +/** + * struct dma_fence_unwrap - cursor into the container structure + * + * Should be used with dma_fence_unwrap_for_each() iterator macro. + */ +struct dma_fence_unwrap { + /** + * @chain: potential dma_fence_chain, but can be other fence as well + */ + struct dma_fence *chain; + /** + * @array: potential dma_fence_array, but can be other fence as well + */ + struct dma_fence *array; + /** + * @index: last returned index if @array is really a dma_fence_array + */ + unsigned int index; +}; + +/* Internal helper to start new array iteration, don't use directly */ +static inline struct dma_fence * +__dma_fence_unwrap_array(struct dma_fence_unwrap * cursor) +{ + cursor->array = dma_fence_chain_contained(cursor->chain); + cursor->index = 0; + return dma_fence_array_first(cursor->array); +} + +/** + * dma_fence_unwrap_first - return the first fence from fence containers + * @head: the entrypoint into the containers + * @cursor: current position inside the containers + * + * Unwraps potential dma_fence_chain/dma_fence_array containers and return the + * first fence. + */ +static inline struct dma_fence * +dma_fence_unwrap_first(struct dma_fence *head, struct dma_fence_unwrap *cursor) +{ + cursor->chain = dma_fence_get(head); + return __dma_fence_unwrap_array(cursor); +} + +/** + * dma_fence_unwrap_next - return the next fence from a fence containers + * @cursor: current position inside the containers + * + * Continue unwrapping the dma_fence_chain/dma_fence_array containers and return + * the next fence from them. + */ +static inline struct dma_fence * +dma_fence_unwrap_next(struct dma_fence_unwrap *cursor) +{ + struct dma_fence *tmp; + + ++cursor->index; + tmp = dma_fence_array_next(cursor->array, cursor->index); + if (tmp) + return tmp; + + cursor->chain = dma_fence_chain_walk(cursor->chain); + return __dma_fence_unwrap_array(cursor); +} + +/** + * dma_fence_unwrap_for_each - iterate over all fences in containers + * @fence: current fence + * @cursor: current position inside the containers + * @head: starting point for the iterator + * + * Unwrap dma_fence_chain and dma_fence_array containers and deep dive into all + * potential fences in them. If @head is just a normal fence only that one is + * returned. + */ +#define dma_fence_unwrap_for_each(fence, cursor, head) \ + for (fence = dma_fence_unwrap_first(head, cursor); fence; \ + fence = dma_fence_unwrap_next(cursor)) + +#endif diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index afdfdfac729f..c8ccbc94d5d2 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -47,24 +47,89 @@ extern struct ww_class reservation_ww_class; +struct dma_resv_list; + /** - * struct dma_resv_list - a list of shared fences - * @rcu: for internal use - * @shared_count: table of shared fences - * @shared_max: for growing shared fence table - * @shared: shared fence table + * enum dma_resv_usage - how the fences from a dma_resv obj are used + * + * This enum describes the different use cases for a dma_resv object and + * controls which fences are returned when queried. + * + * An important fact is that there is the order KERNEL<WRITE<READ<BOOKKEEP and + * when the dma_resv object is asked for fences for one use case the fences + * for the lower use case are returned as well. + * + * For example when asking for WRITE fences then the KERNEL fences are returned + * as well. Similar when asked for READ fences then both WRITE and KERNEL + * fences are returned as well. */ -struct dma_resv_list { - struct rcu_head rcu; - u32 shared_count, shared_max; - struct dma_fence __rcu *shared[]; +enum dma_resv_usage { + /** + * @DMA_RESV_USAGE_KERNEL: For in kernel memory management only. + * + * This should only be used for things like copying or clearing memory + * with a DMA hardware engine for the purpose of kernel memory + * management. + * + * Drivers *always* must wait for those fences before accessing the + * resource protected by the dma_resv object. The only exception for + * that is when the resource is known to be locked down in place by + * pinning it previously. + */ + DMA_RESV_USAGE_KERNEL, + + /** + * @DMA_RESV_USAGE_WRITE: Implicit write synchronization. + * + * This should only be used for userspace command submissions which add + * an implicit write dependency. + */ + DMA_RESV_USAGE_WRITE, + + /** + * @DMA_RESV_USAGE_READ: Implicit read synchronization. + * + * This should only be used for userspace command submissions which add + * an implicit read dependency. + */ + DMA_RESV_USAGE_READ, + + /** + * @DMA_RESV_USAGE_BOOKKEEP: No implicit sync. + * + * This should be used by submissions which don't want to participate in + * implicit synchronization. + * + * The most common case are preemption fences as well as page table + * updates and their TLB flushes. + */ + DMA_RESV_USAGE_BOOKKEEP }; /** + * dma_resv_usage_rw - helper for implicit sync + * @write: true if we create a new implicit sync write + * + * This returns the implicit synchronization usage for write or read accesses, + * see enum dma_resv_usage and &dma_buf.resv. + */ +static inline enum dma_resv_usage dma_resv_usage_rw(bool write) +{ + /* This looks confusing at first sight, but is indeed correct. + * + * The rational is that new write operations needs to wait for the + * existing read and write operations to finish. + * But a new read operation only needs to wait for the existing write + * operations to finish. + */ + return write ? DMA_RESV_USAGE_READ : DMA_RESV_USAGE_WRITE; +} + +/** * struct dma_resv - a reservation object manages fences for a buffer * - * There are multiple uses for this, with sometimes slightly different rules in - * how the fence slots are used. + * This is a container for dma_fence objects which needs to handle multiple use + * cases. * * One use is to synchronize cross-driver access to a struct dma_buf, either for * dynamic buffer management or just to handle implicit synchronization between @@ -91,62 +156,16 @@ struct dma_resv { struct ww_mutex lock; /** - * @seq: + * @fences: * - * Sequence count for managing RCU read-side synchronization, allows - * read-only access to @fence_excl and @fence while ensuring we take a - * consistent snapshot. - */ - seqcount_ww_mutex_t seq; - - /** - * @fence_excl: - * - * The exclusive fence, if there is one currently. + * Array of fences which where added to the dma_resv object * - * There are two ways to update this fence: - * - * - First by calling dma_resv_add_excl_fence(), which replaces all - * fences attached to the reservation object. To guarantee that no - * fences are lost, this new fence must signal only after all previous - * fences, both shared and exclusive, have signalled. In some cases it - * is convenient to achieve that by attaching a struct dma_fence_array - * with all the new and old fences. - * - * - Alternatively the fence can be set directly, which leaves the - * shared fences unchanged. To guarantee that no fences are lost, this - * new fence must signal only after the previous exclusive fence has - * signalled. Since the shared fences are staying intact, it is not - * necessary to maintain any ordering against those. If semantically - * only a new access is added without actually treating the previous - * one as a dependency the exclusive fences can be strung together - * using struct dma_fence_chain. - * - * Note that actual semantics of what an exclusive or shared fence mean - * is defined by the user, for reservation objects shared across drivers - * see &dma_buf.resv. - */ - struct dma_fence __rcu *fence_excl; - - /** - * @fence: - * - * List of current shared fences. - * - * There are no ordering constraints of shared fences against the - * exclusive fence slot. If a waiter needs to wait for all access, it - * has to wait for both sets of fences to signal. - * - * A new fence is added by calling dma_resv_add_shared_fence(). Since - * this often needs to be done past the point of no return in command + * A new fence is added by calling dma_resv_add_fence(). Since this + * often needs to be done past the point of no return in command * submission it cannot fail, and therefore sufficient slots need to be - * reserved by calling dma_resv_reserve_shared(). - * - * Note that actual semantics of what an exclusive or shared fence mean - * is defined by the user, for reservation objects shared across drivers - * see &dma_buf.resv. + * reserved by calling dma_resv_reserve_fences(). */ - struct dma_resv_list __rcu *fence; + struct dma_resv_list __rcu *fences; }; /** @@ -165,14 +184,14 @@ struct dma_resv_iter { /** @obj: The dma_resv object we iterate over */ struct dma_resv *obj; - /** @all_fences: If all fences should be returned */ - bool all_fences; + /** @usage: Return fences with this usage or lower. */ + enum dma_resv_usage usage; /** @fence: the currently handled fence */ struct dma_fence *fence; - /** @seq: sequence number to check for modifications */ - unsigned int seq; + /** @fence_usage: the usage of the current fence */ + enum dma_resv_usage fence_usage; /** @index: index into the shared fences */ unsigned int index; @@ -180,8 +199,8 @@ struct dma_resv_iter { /** @fences: the shared fences; private, *MUST* not dereference */ struct dma_resv_list *fences; - /** @shared_count: number of shared fences */ - unsigned int shared_count; + /** @num_fences: number of fences */ + unsigned int num_fences; /** @is_restarted: true if this is the first returned fence */ bool is_restarted; @@ -196,14 +215,14 @@ struct dma_fence *dma_resv_iter_next(struct dma_resv_iter *cursor); * dma_resv_iter_begin - initialize a dma_resv_iter object * @cursor: The dma_resv_iter object to initialize * @obj: The dma_resv object which we want to iterate over - * @all_fences: If all fences should be returned or just the exclusive one + * @usage: controls which fences to include, see enum dma_resv_usage. */ static inline void dma_resv_iter_begin(struct dma_resv_iter *cursor, struct dma_resv *obj, - bool all_fences) + enum dma_resv_usage usage) { cursor->obj = obj; - cursor->all_fences = all_fences; + cursor->usage = usage; cursor->fence = NULL; } @@ -220,14 +239,15 @@ static inline void dma_resv_iter_end(struct dma_resv_iter *cursor) } /** - * dma_resv_iter_is_exclusive - test if the current fence is the exclusive one + * dma_resv_iter_usage - Return the usage of the current fence * @cursor: the cursor of the current position * - * Returns true if the currently returned fence is the exclusive one. + * Returns the usage of the currently processed fence. */ -static inline bool dma_resv_iter_is_exclusive(struct dma_resv_iter *cursor) +static inline enum dma_resv_usage +dma_resv_iter_usage(struct dma_resv_iter *cursor) { - return cursor->index == 0; + return cursor->fence_usage; } /** @@ -264,7 +284,7 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) * dma_resv_for_each_fence - fence iterator * @cursor: a struct dma_resv_iter pointer * @obj: a dma_resv object pointer - * @all_fences: true if all fences should be returned + * @usage: controls which fences to return * @fence: the current fence * * Iterate over the fences in a struct dma_resv object while holding the @@ -273,8 +293,8 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) * valid as long as the lock is held and so no extra reference to the fence is * taken. */ -#define dma_resv_for_each_fence(cursor, obj, all_fences, fence) \ - for (dma_resv_iter_begin(cursor, obj, all_fences), \ +#define dma_resv_for_each_fence(cursor, obj, usage, fence) \ + for (dma_resv_iter_begin(cursor, obj, usage), \ fence = dma_resv_iter_first(cursor); fence; \ fence = dma_resv_iter_next(cursor)) @@ -282,9 +302,9 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base) #ifdef CONFIG_DEBUG_MUTEXES -void dma_resv_reset_shared_max(struct dma_resv *obj); +void dma_resv_reset_max_fences(struct dma_resv *obj); #else -static inline void dma_resv_reset_shared_max(struct dma_resv *obj) {} +static inline void dma_resv_reset_max_fences(struct dma_resv *obj) {} #endif /** @@ -430,51 +450,26 @@ static inline struct ww_acquire_ctx *dma_resv_locking_ctx(struct dma_resv *obj) */ static inline void dma_resv_unlock(struct dma_resv *obj) { - dma_resv_reset_shared_max(obj); + dma_resv_reset_max_fences(obj); ww_mutex_unlock(&obj->lock); } -/** - * dma_resv_excl_fence - return the object's exclusive fence - * @obj: the reservation object - * - * Returns the exclusive fence (if any). Caller must either hold the objects - * through dma_resv_lock() or the RCU read side lock through rcu_read_lock(), - * or one of the variants of each - * - * RETURNS - * The exclusive fence or NULL - */ -static inline struct dma_fence * -dma_resv_excl_fence(struct dma_resv *obj) -{ - return rcu_dereference_check(obj->fence_excl, dma_resv_held(obj)); -} - -/** - * dma_resv_shared_list - get the reservation object's shared fence list - * @obj: the reservation object - * - * Returns the shared fence list. Caller must either hold the objects - * through dma_resv_lock() or the RCU read side lock through rcu_read_lock(), - * or one of the variants of each - */ -static inline struct dma_resv_list *dma_resv_shared_list(struct dma_resv *obj) -{ - return rcu_dereference_check(obj->fence, dma_resv_held(obj)); -} - void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); -int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences); -void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence); -void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); -int dma_resv_get_fences(struct dma_resv *obj, bool write, +int dma_resv_reserve_fences(struct dma_resv *obj, unsigned int num_fences); +void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence, + enum dma_resv_usage usage); +void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context, + struct dma_fence *fence, + enum dma_resv_usage usage); +int dma_resv_get_fences(struct dma_resv *obj, enum dma_resv_usage usage, unsigned int *num_fences, struct dma_fence ***fences); +int dma_resv_get_singleton(struct dma_resv *obj, enum dma_resv_usage usage, + struct dma_fence **fence); int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src); -long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, - unsigned long timeout); -bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all); +long dma_resv_wait_timeout(struct dma_resv *obj, enum dma_resv_usage usage, + bool intr, unsigned long timeout); +bool dma_resv_test_signaled(struct dma_resv *obj, enum dma_resv_usage usage); void dma_resv_describe(struct dma_resv *obj, struct seq_file *seq); #endif /* _LINUX_RESERVATION_H */ diff --git a/include/linux/efi.h b/include/linux/efi.h index ccd4d3f91c98..0cbbc4103632 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1329,10 +1329,6 @@ static inline struct efi_mokvar_table_entry *efi_mokvar_entry_find( } #endif -#ifdef CONFIG_SYSFB extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); -#else -static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { } -#endif #endif /* _LINUX_EFI_H */ diff --git a/include/linux/fb.h b/include/linux/fb.h index 9a77ab615c36..f95da1af9ff6 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -450,7 +450,6 @@ struct fb_info { struct fb_var_screeninfo var; /* Current var */ struct fb_fix_screeninfo fix; /* Current fix */ struct fb_monspecs monspecs; /* Current Monitor specs */ - struct work_struct queue; /* Framebuffer event queue */ struct fb_pixmap pixmap; /* Image hardware mapper */ struct fb_pixmap sprite; /* Cursor hardware mapper */ struct fb_cmap cmap; /* Current cmap */ diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 761f8f1885c7..3e3d36fc2109 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -613,9 +613,11 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, #ifdef CONFIG_NUMA struct page *alloc_pages(gfp_t gfp, unsigned int order); struct folio *folio_alloc(gfp_t gfp, unsigned order); -extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, +struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); +struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr, bool hugepage); #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages_vma(gfp_mask, order, vma, addr, true) #else @@ -627,8 +629,10 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define alloc_pages_vma(gfp_mask, order, vma, addr, false)\ +#define alloc_pages_vma(gfp_mask, order, vma, addr, hugepage) \ alloc_pages(gfp_mask, order) +#define vma_alloc_folio(gfp, order, vma, addr, hugepage) \ + folio_alloc(gfp, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 98c93510640e..874aabd270c9 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -222,6 +222,15 @@ struct gpio_irq_chip { bool per_parent_data; /** + * @initialized: + * + * Flag to track GPIO chip irq member's initialization. + * This flag will make sure GPIO chip irq members are not used + * before they are initialized. + */ + bool initialized; + + /** * @init_hw: optional routine to initialize hardware before * an IRQ chip will be added. This is quite useful when * a particular driver wants to clear IRQ related registers diff --git a/include/linux/kobject.h b/include/linux/kobject.h index c7b47399b36a..57fb972fea05 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -120,7 +120,6 @@ extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; - struct attribute **default_attrs; /* use default_groups instead */ const struct attribute_group **default_groups; const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); const void *(*namespace)(struct kobject *kobj); diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 6d635e8306d6..975e33b793a7 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -44,9 +44,9 @@ static inline void local_lock_debug_init(local_lock_t *l) } #else /* CONFIG_DEBUG_LOCK_ALLOC */ # define LOCAL_LOCK_DEBUG_INIT(lockname) -# define local_lock_acquire(__ll) do { typecheck(local_lock_t *, __ll); } while (0) -# define local_lock_release(__ll) do { typecheck(local_lock_t *, __ll); } while (0) -# define local_lock_debug_init(__ll) do { typecheck(local_lock_t *, __ll); } while (0) +static inline void local_lock_acquire(local_lock_t *l) { } +static inline void local_lock_release(local_lock_t *l) { } +static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ #define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h index 71101d1ec825..de5c64bbdb72 100644 --- a/include/linux/mmc/core.h +++ b/include/linux/mmc/core.h @@ -175,7 +175,7 @@ void mmc_wait_for_req(struct mmc_host *host, struct mmc_request *mrq); int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, int retries); -int mmc_hw_reset(struct mmc_host *host); +int mmc_hw_reset(struct mmc_card *card); int mmc_sw_reset(struct mmc_host *host); void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 962b14d403e8..46ffab808f03 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1397,13 +1397,16 @@ static inline unsigned long *section_to_usemap(struct mem_section *ms) static inline struct mem_section *__nr_to_section(unsigned long nr) { + unsigned long root = SECTION_NR_TO_ROOT(nr); + + if (unlikely(root >= NR_SECTION_ROOTS)) + return NULL; + #ifdef CONFIG_SPARSEMEM_EXTREME - if (!mem_section) + if (!mem_section || !mem_section[root]) return NULL; #endif - if (!mem_section[SECTION_NR_TO_ROOT(nr)]) - return NULL; - return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; + return &mem_section[root][nr & SECTION_ROOT_MASK]; } extern size_t mem_section_usage_size(void); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 49ba486aea5f..2863e5a69c6a 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1694,6 +1694,7 @@ struct nfs_unlinkdata { struct nfs_renamedata { struct nfs_renameargs args; struct nfs_renameres res; + struct rpc_task task; const struct cred *cred; struct inode *old_dir; struct dentry *old_dentry; diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 37ded6b8fee6..3926e9027947 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -17,7 +17,6 @@ #include <linux/kcsan-checks.h> #include <linux/lockdep.h> #include <linux/mutex.h> -#include <linux/ww_mutex.h> #include <linux/preempt.h> #include <linux/spinlock.h> @@ -164,7 +163,7 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) * static initializer or init function. This enables lockdep to validate * that the write side critical section is properly serialized. * - * LOCKNAME: raw_spinlock, spinlock, rwlock, mutex, or ww_mutex. + * LOCKNAME: raw_spinlock, spinlock, rwlock or mutex */ /* @@ -184,7 +183,6 @@ static inline void seqcount_lockdep_reader_access(const seqcount_t *s) #define seqcount_spinlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, spinlock) #define seqcount_rwlock_init(s, lock) seqcount_LOCKNAME_init(s, lock, rwlock) #define seqcount_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, mutex) -#define seqcount_ww_mutex_init(s, lock) seqcount_LOCKNAME_init(s, lock, ww_mutex) /* * SEQCOUNT_LOCKNAME() - Instantiate seqcount_LOCKNAME_t and helpers @@ -277,7 +275,6 @@ SEQCOUNT_LOCKNAME(raw_spinlock, raw_spinlock_t, false, s->lock, raw_s SEQCOUNT_LOCKNAME(spinlock, spinlock_t, __SEQ_RT, s->lock, spin, spin_lock(s->lock)) SEQCOUNT_LOCKNAME(rwlock, rwlock_t, __SEQ_RT, s->lock, read, read_lock(s->lock)) SEQCOUNT_LOCKNAME(mutex, struct mutex, true, s->lock, mutex, mutex_lock(s->lock)) -SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base, ww_mutex, ww_mutex_lock(s->lock, NULL)) /* * SEQCNT_LOCKNAME_ZERO - static initializer for seqcount_LOCKNAME_t @@ -304,8 +301,7 @@ SEQCOUNT_LOCKNAME(ww_mutex, struct ww_mutex, true, &s->lock->base, ww_mu __seqprop_case((s), raw_spinlock, prop), \ __seqprop_case((s), spinlock, prop), \ __seqprop_case((s), rwlock, prop), \ - __seqprop_case((s), mutex, prop), \ - __seqprop_case((s), ww_mutex, prop)) + __seqprop_case((s), mutex, prop)) #define seqprop_ptr(s) __seqprop(s, ptr) #define seqprop_sequence(s) __seqprop(s, sequence) diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 3e56a9751c06..df53bed9d71f 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -180,13 +180,13 @@ extern int static_call_text_reserved(void *start, void *end); extern long __static_call_return0(void); -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ .type = 1, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -196,6 +196,14 @@ extern long __static_call_return0(void); }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + .type = 1, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) + #define static_call_cond(name) (void)__static_call(name) #define EXPORT_STATIC_CALL(name) \ @@ -217,12 +225,12 @@ extern long __static_call_return0(void); static inline int static_call_init(void) { return 0; } -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -231,6 +239,12 @@ static inline int static_call_init(void) { return 0; } }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) #define static_call_cond(name) (void)__static_call(name) @@ -248,10 +262,7 @@ static inline int static_call_text_reserved(void *start, void *end) return 0; } -static inline long __static_call_return0(void) -{ - return 0; -} +extern long __static_call_return0(void); #define EXPORT_STATIC_CALL(name) \ EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ @@ -281,11 +292,14 @@ static inline long __static_call_return0(void) .func = _func_init, \ } +#define DEFINE_STATIC_CALL(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, _func) + #define DEFINE_STATIC_CALL_NULL(name, _func) \ - DECLARE_STATIC_CALL(name, _func); \ - struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = NULL, \ - } + __DEFINE_STATIC_CALL(name, _func, NULL) + +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, __static_call_return0) static inline void __static_call_nop(void) { } @@ -327,10 +341,4 @@ static inline int static_call_text_reserved(void *start, void *end) #endif /* CONFIG_HAVE_STATIC_CALL */ -#define DEFINE_STATIC_CALL(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, _func) - -#define DEFINE_STATIC_CALL_RET0(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, __static_call_return0) - #endif /* _LINUX_STATIC_CALL_H */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 45a9530d3839..522bbf937957 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -144,7 +144,7 @@ struct rpc_xprt_ops { unsigned short (*get_srcport)(struct rpc_xprt *xprt); int (*buf_alloc)(struct rpc_task *task); void (*buf_free)(struct rpc_task *task); - void (*prepare_request)(struct rpc_rqst *req); + int (*prepare_request)(struct rpc_rqst *req); int (*send_request)(struct rpc_rqst *req); void (*wait_for_reply_request)(struct rpc_task *task); void (*timer)(struct rpc_xprt *xprt, struct rpc_task *task); @@ -358,10 +358,9 @@ int xprt_reserve_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req); -void xprt_request_prepare(struct rpc_rqst *req); bool xprt_prepare_transmit(struct rpc_task *task); void xprt_request_enqueue_transmit(struct rpc_task *task); -void xprt_request_enqueue_receive(struct rpc_task *task); +int xprt_request_enqueue_receive(struct rpc_task *task); void xprt_request_wait_receive(struct rpc_task *task); void xprt_request_dequeue_xprt(struct rpc_task *task); bool xprt_request_need_retransmit(struct rpc_task *task); diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index dafdc7f48c01..b341dd62aa4d 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -23,8 +23,6 @@ struct virtio_shm_region { * any of @get/@set, @get_status/@set_status, or @get_features/ * @finalize_features are NOT safe to be called from an atomic * context. - * @enable_cbs: enable the callbacks - * vdev: the virtio_device * @get: read the value of a configuration field * vdev: the virtio_device * offset: the offset of the configuration field @@ -78,7 +76,6 @@ struct virtio_shm_region { */ typedef void vq_callback_t(struct virtqueue *); struct virtio_config_ops { - void (*enable_cbs)(struct virtio_device *vdev); void (*get)(struct virtio_device *vdev, unsigned offset, void *buf, unsigned len); void (*set)(struct virtio_device *vdev, unsigned offset, @@ -233,9 +230,6 @@ void virtio_device_ready(struct virtio_device *dev) { unsigned status = dev->config->get_status(dev); - if (dev->config->enable_cbs) - dev->config->enable_cbs(dev); - BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK); } diff --git a/include/net/mctp.h b/include/net/mctp.h index d37268fe6825..82800d521c3d 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -36,8 +36,6 @@ struct mctp_hdr { #define MCTP_HDR_TAG_SHIFT 0 #define MCTP_HDR_TAG_MASK GENMASK(2, 0) -#define MCTP_HEADER_MAXLEN 4 - #define MCTP_INITIAL_DEFAULT_NET 1 static inline bool mctp_address_unicast(mctp_eid_t eid) diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 0f34f13ebd55..5337acfe1e9c 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -1004,7 +1004,6 @@ DEFINE_RPC_XPRT_LIFETIME_EVENT(connect); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_auto); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_done); DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_force); -DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_cleanup); DEFINE_RPC_XPRT_LIFETIME_EVENT(destroy); DECLARE_EVENT_CLASS(rpc_xprt_event, diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 8277644c1144..26549c86a91f 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -1,6 +1,6 @@ /************************************************************************** * - * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA + * Copyright © 2009-2022 VMware, Inc., Palo Alto, CA., USA * All Rights Reserved. * * Permission is hereby granted, free of charge, to any person obtaining a @@ -92,6 +92,12 @@ extern "C" { * * DRM_VMW_PARAM_SM5 * SM5 support is enabled. + * + * DRM_VMW_PARAM_GL43 + * SM5.1+GL4.3 support is enabled. + * + * DRM_VMW_PARAM_DEVICE_ID + * PCI ID of the underlying SVGA device. */ #define DRM_VMW_PARAM_NUM_STREAMS 0 @@ -111,6 +117,7 @@ extern "C" { #define DRM_VMW_PARAM_SM4_1 14 #define DRM_VMW_PARAM_SM5 15 #define DRM_VMW_PARAM_GL43 16 +#define DRM_VMW_PARAM_DEVICE_ID 17 /** * enum drm_vmw_handle_type - handle type for ref ioctls diff --git a/kernel/Makefile b/kernel/Makefile index 471d71935e90..847a82bfe0e3 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -114,7 +114,8 @@ obj-$(CONFIG_CPU_PM) += cpu_pm.o obj-$(CONFIG_BPF) += bpf/ obj-$(CONFIG_KCSAN) += kcsan/ obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o -obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call.o +obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o +obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o obj-$(CONFIG_CFI_CLANG) += cfi.o obj-$(CONFIG_PERF_EVENTS) += events/ diff --git a/kernel/entry/common.c b/kernel/entry/common.c index e57a224d6b79..93c3b86e781c 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -392,7 +392,7 @@ DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched); DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched); void dynamic_irqentry_exit_cond_resched(void) { - if (!static_key_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) + if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched)) return; raw_irqentry_exit_cond_resched(); } diff --git a/kernel/events/core.c b/kernel/events/core.c index cfde994ce61c..23bb19716ad3 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -574,8 +574,7 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx, enum event_type_t event_type); static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task); + enum event_type_t event_type); static void update_context_time(struct perf_event_context *ctx); static u64 perf_event_time(struct perf_event *event); @@ -781,7 +780,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, static inline void update_cgrp_time_from_event(struct perf_event *event) { struct perf_cgroup_info *info; - struct perf_cgroup *cgrp; /* * ensure we access cgroup data only when needed and @@ -790,21 +788,19 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) if (!is_cgroup_event(event)) return; - cgrp = perf_cgroup_from_task(current, event->ctx); + info = this_cpu_ptr(event->cgrp->info); /* * Do not update time when cgroup is not active */ - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) { - info = this_cpu_ptr(event->cgrp->info); + if (info->active) __update_cgrp_time(info, perf_clock(), true); - } } static inline void -perf_cgroup_set_timestamp(struct task_struct *task, - struct perf_event_context *ctx) +perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx) { - struct perf_cgroup *cgrp; + struct perf_event_context *ctx = &cpuctx->ctx; + struct perf_cgroup *cgrp = cpuctx->cgrp; struct perf_cgroup_info *info; struct cgroup_subsys_state *css; @@ -813,10 +809,10 @@ perf_cgroup_set_timestamp(struct task_struct *task, * ensure we do not access cgroup data * unless we have the cgroup pinned (css_get) */ - if (!task || !ctx->nr_cgroups) + if (!cgrp) return; - cgrp = perf_cgroup_from_task(task, ctx); + WARN_ON_ONCE(!ctx->nr_cgroups); for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); @@ -828,17 +824,12 @@ perf_cgroup_set_timestamp(struct task_struct *task, static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list); -#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */ -#define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */ - /* * reschedule events based on the cgroup constraint of task. - * - * mode SWOUT : schedule out everything - * mode SWIN : schedule in based on cgroup for next */ -static void perf_cgroup_switch(struct task_struct *task, int mode) +static void perf_cgroup_switch(struct task_struct *task) { + struct perf_cgroup *cgrp; struct perf_cpu_context *cpuctx, *tmp; struct list_head *list; unsigned long flags; @@ -849,35 +840,31 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) */ local_irq_save(flags); + cgrp = perf_cgroup_from_task(task, NULL); + list = this_cpu_ptr(&cgrp_cpuctx_list); list_for_each_entry_safe(cpuctx, tmp, list, cgrp_cpuctx_entry) { WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0); + if (READ_ONCE(cpuctx->cgrp) == cgrp) + continue; perf_ctx_lock(cpuctx, cpuctx->task_ctx); perf_pmu_disable(cpuctx->ctx.pmu); - if (mode & PERF_CGROUP_SWOUT) { - cpu_ctx_sched_out(cpuctx, EVENT_ALL); - /* - * must not be done before ctxswout due - * to event_filter_match() in event_sched_out() - */ - cpuctx->cgrp = NULL; - } + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + /* + * must not be done before ctxswout due + * to update_cgrp_time_from_cpuctx() in + * ctx_sched_out() + */ + cpuctx->cgrp = cgrp; + /* + * set cgrp before ctxsw in to allow + * perf_cgroup_set_timestamp() in ctx_sched_in() + * to not have to pass task around + */ + cpu_ctx_sched_in(cpuctx, EVENT_ALL); - if (mode & PERF_CGROUP_SWIN) { - WARN_ON_ONCE(cpuctx->cgrp); - /* - * set cgrp before ctxsw in to allow - * event_filter_match() to not have to pass - * task around - * we pass the cpuctx->ctx to perf_cgroup_from_task() - * because cgorup events are only per-cpu - */ - cpuctx->cgrp = perf_cgroup_from_task(task, - &cpuctx->ctx); - cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); - } perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); } @@ -885,58 +872,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) local_irq_restore(flags); } -static inline void perf_cgroup_sched_out(struct task_struct *task, - struct task_struct *next) -{ - struct perf_cgroup *cgrp1; - struct perf_cgroup *cgrp2 = NULL; - - rcu_read_lock(); - /* - * we come here when we know perf_cgroup_events > 0 - * we do not need to pass the ctx here because we know - * we are holding the rcu lock - */ - cgrp1 = perf_cgroup_from_task(task, NULL); - cgrp2 = perf_cgroup_from_task(next, NULL); - - /* - * only schedule out current cgroup events if we know - * that we are switching to a different cgroup. Otherwise, - * do no touch the cgroup events. - */ - if (cgrp1 != cgrp2) - perf_cgroup_switch(task, PERF_CGROUP_SWOUT); - - rcu_read_unlock(); -} - -static inline void perf_cgroup_sched_in(struct task_struct *prev, - struct task_struct *task) -{ - struct perf_cgroup *cgrp1; - struct perf_cgroup *cgrp2 = NULL; - - rcu_read_lock(); - /* - * we come here when we know perf_cgroup_events > 0 - * we do not need to pass the ctx here because we know - * we are holding the rcu lock - */ - cgrp1 = perf_cgroup_from_task(task, NULL); - cgrp2 = perf_cgroup_from_task(prev, NULL); - - /* - * only need to schedule in cgroup events if we are changing - * cgroup during ctxsw. Cgroup events were not scheduled - * out of ctxsw out if that was not the case. - */ - if (cgrp1 != cgrp2) - perf_cgroup_switch(task, PERF_CGROUP_SWIN); - - rcu_read_unlock(); -} - static int perf_cgroup_ensure_storage(struct perf_event *event, struct cgroup_subsys_state *css) { @@ -1032,22 +967,10 @@ perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ct */ cpuctx = container_of(ctx, struct perf_cpu_context, ctx); - /* - * Since setting cpuctx->cgrp is conditional on the current @cgrp - * matching the event's cgroup, we must do this for every new event, - * because if the first would mismatch, the second would not try again - * and we would leave cpuctx->cgrp unset. - */ - if (ctx->is_active && !cpuctx->cgrp) { - struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx); - - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) - cpuctx->cgrp = cgrp; - } - if (ctx->nr_cgroups++) return; + cpuctx->cgrp = perf_cgroup_from_task(current, ctx); list_add(&cpuctx->cgrp_cpuctx_entry, per_cpu_ptr(&cgrp_cpuctx_list, event->cpu)); } @@ -1069,9 +992,7 @@ perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *c if (--ctx->nr_cgroups) return; - if (ctx->is_active && cpuctx->cgrp) - cpuctx->cgrp = NULL; - + cpuctx->cgrp = NULL; list_del(&cpuctx->cgrp_cpuctx_entry); } @@ -1100,16 +1021,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, { } -static inline void perf_cgroup_sched_out(struct task_struct *task, - struct task_struct *next) -{ -} - -static inline void perf_cgroup_sched_in(struct task_struct *prev, - struct task_struct *task) -{ -} - static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, struct perf_event_attr *attr, struct perf_event *group_leader) @@ -1118,13 +1029,7 @@ static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event, } static inline void -perf_cgroup_set_timestamp(struct task_struct *task, - struct perf_event_context *ctx) -{ -} - -static inline void -perf_cgroup_switch(struct task_struct *task, struct task_struct *next) +perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx) { } @@ -1147,6 +1052,10 @@ static inline void perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx) { } + +static void perf_cgroup_switch(struct task_struct *task) +{ +} #endif /* @@ -2713,8 +2622,7 @@ static void ctx_sched_out(struct perf_event_context *ctx, static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task); + enum event_type_t event_type); static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, @@ -2730,15 +2638,14 @@ static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, } static void perf_event_sched_in(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx, - struct task_struct *task) + struct perf_event_context *ctx) { - cpu_ctx_sched_in(cpuctx, EVENT_PINNED, task); + cpu_ctx_sched_in(cpuctx, EVENT_PINNED); if (ctx) - ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task); - cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task); + ctx_sched_in(ctx, cpuctx, EVENT_PINNED); + cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE); if (ctx) - ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); + ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE); } /* @@ -2788,7 +2695,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, else if (ctx_event_type & EVENT_PINNED) cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - perf_event_sched_in(cpuctx, task_ctx, current); + perf_event_sched_in(cpuctx, task_ctx); perf_pmu_enable(cpuctx->ctx.pmu); } @@ -3011,7 +2918,7 @@ static void __perf_event_enable(struct perf_event *event, return; if (!event_filter_match(event)) { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); return; } @@ -3020,7 +2927,7 @@ static void __perf_event_enable(struct perf_event *event, * then don't put it on unless the group is on. */ if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); return; } @@ -3668,7 +3575,7 @@ void __perf_event_task_sched_out(struct task_struct *task, * cgroup event are system-wide mode only */ if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_out(task, next); + perf_cgroup_switch(next); } /* @@ -3865,8 +3772,7 @@ ctx_flexible_sched_in(struct perf_event_context *ctx, static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task) + enum event_type_t event_type) { int is_active = ctx->is_active; @@ -3878,7 +3784,7 @@ ctx_sched_in(struct perf_event_context *ctx, if (is_active ^ EVENT_TIME) { /* start ctx time */ __update_context_time(ctx, false); - perf_cgroup_set_timestamp(task, ctx); + perf_cgroup_set_timestamp(cpuctx); /* * CPU-release for the below ->is_active store, * see __load_acquire() in perf_event_time_now() @@ -3909,12 +3815,11 @@ ctx_sched_in(struct perf_event_context *ctx, } static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, - enum event_type_t event_type, - struct task_struct *task) + enum event_type_t event_type) { struct perf_event_context *ctx = &cpuctx->ctx; - ctx_sched_in(ctx, cpuctx, event_type, task); + ctx_sched_in(ctx, cpuctx, event_type); } static void perf_event_context_sched_in(struct perf_event_context *ctx, @@ -3956,7 +3861,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, */ if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree)) cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - perf_event_sched_in(cpuctx, ctx, task); + perf_event_sched_in(cpuctx, ctx); if (cpuctx->sched_cb_usage && pmu->sched_task) pmu->sched_task(cpuctx->task_ctx, true); @@ -3984,16 +3889,6 @@ void __perf_event_task_sched_in(struct task_struct *prev, struct perf_event_context *ctx; int ctxn; - /* - * If cgroup events exist on this CPU, then we need to check if we have - * to switch in PMU state; cgroup event are system-wide mode only. - * - * Since cgroup events are CPU events, we must schedule these in before - * we schedule in the task events. - */ - if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_in(prev, task); - for_each_task_context_nr(ctxn) { ctx = task->perf_event_ctxp[ctxn]; if (likely(!ctx)) @@ -4267,7 +4162,7 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx) if (cpu_event) rotate_ctx(&cpuctx->ctx, cpu_event); - perf_event_sched_in(cpuctx, task_ctx, current); + perf_event_sched_in(cpuctx, task_ctx); perf_pmu_enable(cpuctx->ctx.pmu); perf_ctx_unlock(cpuctx, cpuctx->task_ctx); @@ -4339,7 +4234,7 @@ static void perf_event_enable_on_exec(int ctxn) clone_ctx = unclone_ctx(ctx); ctx_resched(cpuctx, ctx, event_type); } else { - ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + ctx_sched_in(ctx, cpuctx, EVENT_TIME); } perf_ctx_unlock(cpuctx, ctx); @@ -11635,6 +11530,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, event->state = PERF_EVENT_STATE_INACTIVE; + if (parent_event) + event->event_caps = parent_event->event_caps; + if (event->attr.sigtrap) atomic_set(&event->event_limit, 1); @@ -13562,7 +13460,7 @@ static int __perf_cgroup_move(void *info) { struct task_struct *task = info; rcu_read_lock(); - perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN); + perf_cgroup_switch(task); rcu_read_unlock(); return 0; } diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index c264cbeab71c..b5379c0e6d6d 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -3,6 +3,7 @@ #define _FUTEX_H #include <linux/futex.h> +#include <linux/rtmutex.h> #include <linux/sched/wake_q.h> #ifdef CONFIG_PREEMPT_RT diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d575b4914925..51efaabac3e4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5752,6 +5752,8 @@ static inline struct task_struct *pick_task(struct rq *rq) extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi); +static void queue_core_balance(struct rq *rq); + static struct task_struct * pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { @@ -5801,7 +5803,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } rq->core_pick = NULL; - return next; + goto out; } put_prev_task_balance(rq, prev, rf); @@ -5851,7 +5853,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) */ WARN_ON_ONCE(fi_before); task_vruntime_update(rq, next, false); - goto done; + goto out_set_next; } } @@ -5970,8 +5972,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) resched_curr(rq_i); } -done: +out_set_next: set_next_task(rq, next); +out: + if (rq->core->core_forceidle_count && next == rq->idle) + queue_core_balance(rq); + return next; } @@ -6000,7 +6006,7 @@ static bool try_steal_cookie(int this, int that) if (p == src->core_pick || p == src->curr) goto next; - if (!cpumask_test_cpu(this, &p->cpus_mask)) + if (!is_cpu_allowed(p, this)) goto next; if (p->core_occupation > dst->idle->core_occupation) @@ -6066,7 +6072,7 @@ static void sched_core_balance(struct rq *rq) static DEFINE_PER_CPU(struct callback_head, core_balance_head); -void queue_core_balance(struct rq *rq) +static void queue_core_balance(struct rq *rq) { if (!sched_core_enabled(rq)) return; diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8f8b5020e76a..ecb0d7052877 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -434,7 +434,6 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir { update_idle_core(rq); schedstat_inc(rq->sched_goidle); - queue_core_balance(rq); } #ifdef CONFIG_SMP diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 58263f90c559..8dccb34eb190 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1232,8 +1232,6 @@ static inline bool sched_group_cookie_match(struct rq *rq, return false; } -extern void queue_core_balance(struct rq *rq); - static inline bool sched_core_enqueued(struct task_struct *p) { return !RB_EMPTY_NODE(&p->core_node); @@ -1267,10 +1265,6 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq) return &rq->__lock; } -static inline void queue_core_balance(struct rq *rq) -{ -} - static inline bool sched_cpu_cookie_match(struct rq *rq, struct task_struct *p) { return true; diff --git a/kernel/static_call.c b/kernel/static_call.c index f2b8baea35d2..e9c3e69f3837 100644 --- a/kernel/static_call.c +++ b/kernel/static_call.c @@ -1,549 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/init.h> #include <linux/static_call.h> -#include <linux/bug.h> -#include <linux/smp.h> -#include <linux/sort.h> -#include <linux/slab.h> -#include <linux/module.h> -#include <linux/cpu.h> -#include <linux/processor.h> -#include <asm/sections.h> - -extern struct static_call_site __start_static_call_sites[], - __stop_static_call_sites[]; -extern struct static_call_tramp_key __start_static_call_tramp_key[], - __stop_static_call_tramp_key[]; - -static bool static_call_initialized; - -/* mutex to protect key modules/sites */ -static DEFINE_MUTEX(static_call_mutex); - -static void static_call_lock(void) -{ - mutex_lock(&static_call_mutex); -} - -static void static_call_unlock(void) -{ - mutex_unlock(&static_call_mutex); -} - -static inline void *static_call_addr(struct static_call_site *site) -{ - return (void *)((long)site->addr + (long)&site->addr); -} - -static inline unsigned long __static_call_key(const struct static_call_site *site) -{ - return (long)site->key + (long)&site->key; -} - -static inline struct static_call_key *static_call_key(const struct static_call_site *site) -{ - return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); -} - -/* These assume the key is word-aligned. */ -static inline bool static_call_is_init(struct static_call_site *site) -{ - return __static_call_key(site) & STATIC_CALL_SITE_INIT; -} - -static inline bool static_call_is_tail(struct static_call_site *site) -{ - return __static_call_key(site) & STATIC_CALL_SITE_TAIL; -} - -static inline void static_call_set_init(struct static_call_site *site) -{ - site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - - (long)&site->key; -} - -static int static_call_site_cmp(const void *_a, const void *_b) -{ - const struct static_call_site *a = _a; - const struct static_call_site *b = _b; - const struct static_call_key *key_a = static_call_key(a); - const struct static_call_key *key_b = static_call_key(b); - - if (key_a < key_b) - return -1; - - if (key_a > key_b) - return 1; - - return 0; -} - -static void static_call_site_swap(void *_a, void *_b, int size) -{ - long delta = (unsigned long)_a - (unsigned long)_b; - struct static_call_site *a = _a; - struct static_call_site *b = _b; - struct static_call_site tmp = *a; - - a->addr = b->addr - delta; - a->key = b->key - delta; - - b->addr = tmp.addr + delta; - b->key = tmp.key + delta; -} - -static inline void static_call_sort_entries(struct static_call_site *start, - struct static_call_site *stop) -{ - sort(start, stop - start, sizeof(struct static_call_site), - static_call_site_cmp, static_call_site_swap); -} - -static inline bool static_call_key_has_mods(struct static_call_key *key) -{ - return !(key->type & 1); -} - -static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) -{ - if (!static_call_key_has_mods(key)) - return NULL; - - return key->mods; -} - -static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) -{ - if (static_call_key_has_mods(key)) - return NULL; - - return (struct static_call_site *)(key->type & ~1); -} - -void __static_call_update(struct static_call_key *key, void *tramp, void *func) -{ - struct static_call_site *site, *stop; - struct static_call_mod *site_mod, first; - - cpus_read_lock(); - static_call_lock(); - - if (key->func == func) - goto done; - - key->func = func; - - arch_static_call_transform(NULL, tramp, func, false); - - /* - * If uninitialized, we'll not update the callsites, but they still - * point to the trampoline and we just patched that. - */ - if (WARN_ON_ONCE(!static_call_initialized)) - goto done; - - first = (struct static_call_mod){ - .next = static_call_key_next(key), - .mod = NULL, - .sites = static_call_key_sites(key), - }; - - for (site_mod = &first; site_mod; site_mod = site_mod->next) { - bool init = system_state < SYSTEM_RUNNING; - struct module *mod = site_mod->mod; - - if (!site_mod->sites) { - /* - * This can happen if the static call key is defined in - * a module which doesn't use it. - * - * It also happens in the has_mods case, where the - * 'first' entry has no sites associated with it. - */ - continue; - } - - stop = __stop_static_call_sites; - - if (mod) { -#ifdef CONFIG_MODULES - stop = mod->static_call_sites + - mod->num_static_call_sites; - init = mod->state == MODULE_STATE_COMING; -#endif - } - - for (site = site_mod->sites; - site < stop && static_call_key(site) == key; site++) { - void *site_addr = static_call_addr(site); - - if (!init && static_call_is_init(site)) - continue; - - if (!kernel_text_address((unsigned long)site_addr)) { - /* - * This skips patching built-in __exit, which - * is part of init_section_contains() but is - * not part of kernel_text_address(). - * - * Skipping built-in __exit is fine since it - * will never be executed. - */ - WARN_ONCE(!static_call_is_init(site), - "can't patch static call site at %pS", - site_addr); - continue; - } - - arch_static_call_transform(site_addr, NULL, func, - static_call_is_tail(site)); - } - } - -done: - static_call_unlock(); - cpus_read_unlock(); -} -EXPORT_SYMBOL_GPL(__static_call_update); - -static int __static_call_init(struct module *mod, - struct static_call_site *start, - struct static_call_site *stop) -{ - struct static_call_site *site; - struct static_call_key *key, *prev_key = NULL; - struct static_call_mod *site_mod; - - if (start == stop) - return 0; - - static_call_sort_entries(start, stop); - - for (site = start; site < stop; site++) { - void *site_addr = static_call_addr(site); - - if ((mod && within_module_init((unsigned long)site_addr, mod)) || - (!mod && init_section_contains(site_addr, 1))) - static_call_set_init(site); - - key = static_call_key(site); - if (key != prev_key) { - prev_key = key; - - /* - * For vmlinux (!mod) avoid the allocation by storing - * the sites pointer in the key itself. Also see - * __static_call_update()'s @first. - * - * This allows architectures (eg. x86) to call - * static_call_init() before memory allocation works. - */ - if (!mod) { - key->sites = site; - key->type |= 1; - goto do_transform; - } - - site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); - if (!site_mod) - return -ENOMEM; - - /* - * When the key has a direct sites pointer, extract - * that into an explicit struct static_call_mod, so we - * can have a list of modules. - */ - if (static_call_key_sites(key)) { - site_mod->mod = NULL; - site_mod->next = NULL; - site_mod->sites = static_call_key_sites(key); - - key->mods = site_mod; - - site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); - if (!site_mod) - return -ENOMEM; - } - - site_mod->mod = mod; - site_mod->sites = site; - site_mod->next = static_call_key_next(key); - key->mods = site_mod; - } - -do_transform: - arch_static_call_transform(site_addr, NULL, key->func, - static_call_is_tail(site)); - } - - return 0; -} - -static int addr_conflict(struct static_call_site *site, void *start, void *end) -{ - unsigned long addr = (unsigned long)static_call_addr(site); - - if (addr <= (unsigned long)end && - addr + CALL_INSN_SIZE > (unsigned long)start) - return 1; - - return 0; -} - -static int __static_call_text_reserved(struct static_call_site *iter_start, - struct static_call_site *iter_stop, - void *start, void *end, bool init) -{ - struct static_call_site *iter = iter_start; - - while (iter < iter_stop) { - if (init || !static_call_is_init(iter)) { - if (addr_conflict(iter, start, end)) - return 1; - } - iter++; - } - - return 0; -} - -#ifdef CONFIG_MODULES - -static int __static_call_mod_text_reserved(void *start, void *end) -{ - struct module *mod; - int ret; - - preempt_disable(); - mod = __module_text_address((unsigned long)start); - WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); - if (!try_module_get(mod)) - mod = NULL; - preempt_enable(); - - if (!mod) - return 0; - - ret = __static_call_text_reserved(mod->static_call_sites, - mod->static_call_sites + mod->num_static_call_sites, - start, end, mod->state == MODULE_STATE_COMING); - - module_put(mod); - - return ret; -} - -static unsigned long tramp_key_lookup(unsigned long addr) -{ - struct static_call_tramp_key *start = __start_static_call_tramp_key; - struct static_call_tramp_key *stop = __stop_static_call_tramp_key; - struct static_call_tramp_key *tramp_key; - - for (tramp_key = start; tramp_key != stop; tramp_key++) { - unsigned long tramp; - - tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; - if (tramp == addr) - return (long)tramp_key->key + (long)&tramp_key->key; - } - - return 0; -} - -static int static_call_add_module(struct module *mod) -{ - struct static_call_site *start = mod->static_call_sites; - struct static_call_site *stop = start + mod->num_static_call_sites; - struct static_call_site *site; - - for (site = start; site != stop; site++) { - unsigned long s_key = __static_call_key(site); - unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; - unsigned long key; - - /* - * Is the key is exported, 'addr' points to the key, which - * means modules are allowed to call static_call_update() on - * it. - * - * Otherwise, the key isn't exported, and 'addr' points to the - * trampoline so we need to lookup the key. - * - * We go through this dance to prevent crazy modules from - * abusing sensitive static calls. - */ - if (!kernel_text_address(addr)) - continue; - - key = tramp_key_lookup(addr); - if (!key) { - pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", - static_call_addr(site)); - return -EINVAL; - } - - key |= s_key & STATIC_CALL_SITE_FLAGS; - site->key = key - (long)&site->key; - } - - return __static_call_init(mod, start, stop); -} - -static void static_call_del_module(struct module *mod) -{ - struct static_call_site *start = mod->static_call_sites; - struct static_call_site *stop = mod->static_call_sites + - mod->num_static_call_sites; - struct static_call_key *key, *prev_key = NULL; - struct static_call_mod *site_mod, **prev; - struct static_call_site *site; - - for (site = start; site < stop; site++) { - key = static_call_key(site); - if (key == prev_key) - continue; - - prev_key = key; - - for (prev = &key->mods, site_mod = key->mods; - site_mod && site_mod->mod != mod; - prev = &site_mod->next, site_mod = site_mod->next) - ; - - if (!site_mod) - continue; - - *prev = site_mod->next; - kfree(site_mod); - } -} - -static int static_call_module_notify(struct notifier_block *nb, - unsigned long val, void *data) -{ - struct module *mod = data; - int ret = 0; - - cpus_read_lock(); - static_call_lock(); - - switch (val) { - case MODULE_STATE_COMING: - ret = static_call_add_module(mod); - if (ret) { - WARN(1, "Failed to allocate memory for static calls"); - static_call_del_module(mod); - } - break; - case MODULE_STATE_GOING: - static_call_del_module(mod); - break; - } - - static_call_unlock(); - cpus_read_unlock(); - - return notifier_from_errno(ret); -} - -static struct notifier_block static_call_module_nb = { - .notifier_call = static_call_module_notify, -}; - -#else - -static inline int __static_call_mod_text_reserved(void *start, void *end) -{ - return 0; -} - -#endif /* CONFIG_MODULES */ - -int static_call_text_reserved(void *start, void *end) -{ - bool init = system_state < SYSTEM_RUNNING; - int ret = __static_call_text_reserved(__start_static_call_sites, - __stop_static_call_sites, start, end, init); - - if (ret) - return ret; - - return __static_call_mod_text_reserved(start, end); -} - -int __init static_call_init(void) -{ - int ret; - - if (static_call_initialized) - return 0; - - cpus_read_lock(); - static_call_lock(); - ret = __static_call_init(NULL, __start_static_call_sites, - __stop_static_call_sites); - static_call_unlock(); - cpus_read_unlock(); - - if (ret) { - pr_err("Failed to allocate memory for static_call!\n"); - BUG(); - } - - static_call_initialized = true; - -#ifdef CONFIG_MODULES - register_module_notifier(&static_call_module_nb); -#endif - return 0; -} -early_initcall(static_call_init); long __static_call_return0(void) { return 0; } EXPORT_SYMBOL_GPL(__static_call_return0); - -#ifdef CONFIG_STATIC_CALL_SELFTEST - -static int func_a(int x) -{ - return x+1; -} - -static int func_b(int x) -{ - return x+2; -} - -DEFINE_STATIC_CALL(sc_selftest, func_a); - -static struct static_call_data { - int (*func)(int); - int val; - int expect; -} static_call_data [] __initdata = { - { NULL, 2, 3 }, - { func_b, 2, 4 }, - { func_a, 2, 3 } -}; - -static int __init test_static_call_init(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { - struct static_call_data *scd = &static_call_data[i]; - - if (scd->func) - static_call_update(sc_selftest, scd->func); - - WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); - } - - return 0; -} -early_initcall(test_static_call_init); - -#endif /* CONFIG_STATIC_CALL_SELFTEST */ diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c new file mode 100644 index 000000000000..dc5665b62814 --- /dev/null +++ b/kernel/static_call_inline.c @@ -0,0 +1,543 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/init.h> +#include <linux/static_call.h> +#include <linux/bug.h> +#include <linux/smp.h> +#include <linux/sort.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/cpu.h> +#include <linux/processor.h> +#include <asm/sections.h> + +extern struct static_call_site __start_static_call_sites[], + __stop_static_call_sites[]; +extern struct static_call_tramp_key __start_static_call_tramp_key[], + __stop_static_call_tramp_key[]; + +static bool static_call_initialized; + +/* mutex to protect key modules/sites */ +static DEFINE_MUTEX(static_call_mutex); + +static void static_call_lock(void) +{ + mutex_lock(&static_call_mutex); +} + +static void static_call_unlock(void) +{ + mutex_unlock(&static_call_mutex); +} + +static inline void *static_call_addr(struct static_call_site *site) +{ + return (void *)((long)site->addr + (long)&site->addr); +} + +static inline unsigned long __static_call_key(const struct static_call_site *site) +{ + return (long)site->key + (long)&site->key; +} + +static inline struct static_call_key *static_call_key(const struct static_call_site *site) +{ + return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); +} + +/* These assume the key is word-aligned. */ +static inline bool static_call_is_init(struct static_call_site *site) +{ + return __static_call_key(site) & STATIC_CALL_SITE_INIT; +} + +static inline bool static_call_is_tail(struct static_call_site *site) +{ + return __static_call_key(site) & STATIC_CALL_SITE_TAIL; +} + +static inline void static_call_set_init(struct static_call_site *site) +{ + site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - + (long)&site->key; +} + +static int static_call_site_cmp(const void *_a, const void *_b) +{ + const struct static_call_site *a = _a; + const struct static_call_site *b = _b; + const struct static_call_key *key_a = static_call_key(a); + const struct static_call_key *key_b = static_call_key(b); + + if (key_a < key_b) + return -1; + + if (key_a > key_b) + return 1; + + return 0; +} + +static void static_call_site_swap(void *_a, void *_b, int size) +{ + long delta = (unsigned long)_a - (unsigned long)_b; + struct static_call_site *a = _a; + struct static_call_site *b = _b; + struct static_call_site tmp = *a; + + a->addr = b->addr - delta; + a->key = b->key - delta; + + b->addr = tmp.addr + delta; + b->key = tmp.key + delta; +} + +static inline void static_call_sort_entries(struct static_call_site *start, + struct static_call_site *stop) +{ + sort(start, stop - start, sizeof(struct static_call_site), + static_call_site_cmp, static_call_site_swap); +} + +static inline bool static_call_key_has_mods(struct static_call_key *key) +{ + return !(key->type & 1); +} + +static inline struct static_call_mod *static_call_key_next(struct static_call_key *key) +{ + if (!static_call_key_has_mods(key)) + return NULL; + + return key->mods; +} + +static inline struct static_call_site *static_call_key_sites(struct static_call_key *key) +{ + if (static_call_key_has_mods(key)) + return NULL; + + return (struct static_call_site *)(key->type & ~1); +} + +void __static_call_update(struct static_call_key *key, void *tramp, void *func) +{ + struct static_call_site *site, *stop; + struct static_call_mod *site_mod, first; + + cpus_read_lock(); + static_call_lock(); + + if (key->func == func) + goto done; + + key->func = func; + + arch_static_call_transform(NULL, tramp, func, false); + + /* + * If uninitialized, we'll not update the callsites, but they still + * point to the trampoline and we just patched that. + */ + if (WARN_ON_ONCE(!static_call_initialized)) + goto done; + + first = (struct static_call_mod){ + .next = static_call_key_next(key), + .mod = NULL, + .sites = static_call_key_sites(key), + }; + + for (site_mod = &first; site_mod; site_mod = site_mod->next) { + bool init = system_state < SYSTEM_RUNNING; + struct module *mod = site_mod->mod; + + if (!site_mod->sites) { + /* + * This can happen if the static call key is defined in + * a module which doesn't use it. + * + * It also happens in the has_mods case, where the + * 'first' entry has no sites associated with it. + */ + continue; + } + + stop = __stop_static_call_sites; + + if (mod) { +#ifdef CONFIG_MODULES + stop = mod->static_call_sites + + mod->num_static_call_sites; + init = mod->state == MODULE_STATE_COMING; +#endif + } + + for (site = site_mod->sites; + site < stop && static_call_key(site) == key; site++) { + void *site_addr = static_call_addr(site); + + if (!init && static_call_is_init(site)) + continue; + + if (!kernel_text_address((unsigned long)site_addr)) { + /* + * This skips patching built-in __exit, which + * is part of init_section_contains() but is + * not part of kernel_text_address(). + * + * Skipping built-in __exit is fine since it + * will never be executed. + */ + WARN_ONCE(!static_call_is_init(site), + "can't patch static call site at %pS", + site_addr); + continue; + } + + arch_static_call_transform(site_addr, NULL, func, + static_call_is_tail(site)); + } + } + +done: + static_call_unlock(); + cpus_read_unlock(); +} +EXPORT_SYMBOL_GPL(__static_call_update); + +static int __static_call_init(struct module *mod, + struct static_call_site *start, + struct static_call_site *stop) +{ + struct static_call_site *site; + struct static_call_key *key, *prev_key = NULL; + struct static_call_mod *site_mod; + + if (start == stop) + return 0; + + static_call_sort_entries(start, stop); + + for (site = start; site < stop; site++) { + void *site_addr = static_call_addr(site); + + if ((mod && within_module_init((unsigned long)site_addr, mod)) || + (!mod && init_section_contains(site_addr, 1))) + static_call_set_init(site); + + key = static_call_key(site); + if (key != prev_key) { + prev_key = key; + + /* + * For vmlinux (!mod) avoid the allocation by storing + * the sites pointer in the key itself. Also see + * __static_call_update()'s @first. + * + * This allows architectures (eg. x86) to call + * static_call_init() before memory allocation works. + */ + if (!mod) { + key->sites = site; + key->type |= 1; + goto do_transform; + } + + site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); + if (!site_mod) + return -ENOMEM; + + /* + * When the key has a direct sites pointer, extract + * that into an explicit struct static_call_mod, so we + * can have a list of modules. + */ + if (static_call_key_sites(key)) { + site_mod->mod = NULL; + site_mod->next = NULL; + site_mod->sites = static_call_key_sites(key); + + key->mods = site_mod; + + site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL); + if (!site_mod) + return -ENOMEM; + } + + site_mod->mod = mod; + site_mod->sites = site; + site_mod->next = static_call_key_next(key); + key->mods = site_mod; + } + +do_transform: + arch_static_call_transform(site_addr, NULL, key->func, + static_call_is_tail(site)); + } + + return 0; +} + +static int addr_conflict(struct static_call_site *site, void *start, void *end) +{ + unsigned long addr = (unsigned long)static_call_addr(site); + + if (addr <= (unsigned long)end && + addr + CALL_INSN_SIZE > (unsigned long)start) + return 1; + + return 0; +} + +static int __static_call_text_reserved(struct static_call_site *iter_start, + struct static_call_site *iter_stop, + void *start, void *end, bool init) +{ + struct static_call_site *iter = iter_start; + + while (iter < iter_stop) { + if (init || !static_call_is_init(iter)) { + if (addr_conflict(iter, start, end)) + return 1; + } + iter++; + } + + return 0; +} + +#ifdef CONFIG_MODULES + +static int __static_call_mod_text_reserved(void *start, void *end) +{ + struct module *mod; + int ret; + + preempt_disable(); + mod = __module_text_address((unsigned long)start); + WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); + if (!try_module_get(mod)) + mod = NULL; + preempt_enable(); + + if (!mod) + return 0; + + ret = __static_call_text_reserved(mod->static_call_sites, + mod->static_call_sites + mod->num_static_call_sites, + start, end, mod->state == MODULE_STATE_COMING); + + module_put(mod); + + return ret; +} + +static unsigned long tramp_key_lookup(unsigned long addr) +{ + struct static_call_tramp_key *start = __start_static_call_tramp_key; + struct static_call_tramp_key *stop = __stop_static_call_tramp_key; + struct static_call_tramp_key *tramp_key; + + for (tramp_key = start; tramp_key != stop; tramp_key++) { + unsigned long tramp; + + tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp; + if (tramp == addr) + return (long)tramp_key->key + (long)&tramp_key->key; + } + + return 0; +} + +static int static_call_add_module(struct module *mod) +{ + struct static_call_site *start = mod->static_call_sites; + struct static_call_site *stop = start + mod->num_static_call_sites; + struct static_call_site *site; + + for (site = start; site != stop; site++) { + unsigned long s_key = __static_call_key(site); + unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; + unsigned long key; + + /* + * Is the key is exported, 'addr' points to the key, which + * means modules are allowed to call static_call_update() on + * it. + * + * Otherwise, the key isn't exported, and 'addr' points to the + * trampoline so we need to lookup the key. + * + * We go through this dance to prevent crazy modules from + * abusing sensitive static calls. + */ + if (!kernel_text_address(addr)) + continue; + + key = tramp_key_lookup(addr); + if (!key) { + pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n", + static_call_addr(site)); + return -EINVAL; + } + + key |= s_key & STATIC_CALL_SITE_FLAGS; + site->key = key - (long)&site->key; + } + + return __static_call_init(mod, start, stop); +} + +static void static_call_del_module(struct module *mod) +{ + struct static_call_site *start = mod->static_call_sites; + struct static_call_site *stop = mod->static_call_sites + + mod->num_static_call_sites; + struct static_call_key *key, *prev_key = NULL; + struct static_call_mod *site_mod, **prev; + struct static_call_site *site; + + for (site = start; site < stop; site++) { + key = static_call_key(site); + if (key == prev_key) + continue; + + prev_key = key; + + for (prev = &key->mods, site_mod = key->mods; + site_mod && site_mod->mod != mod; + prev = &site_mod->next, site_mod = site_mod->next) + ; + + if (!site_mod) + continue; + + *prev = site_mod->next; + kfree(site_mod); + } +} + +static int static_call_module_notify(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct module *mod = data; + int ret = 0; + + cpus_read_lock(); + static_call_lock(); + + switch (val) { + case MODULE_STATE_COMING: + ret = static_call_add_module(mod); + if (ret) { + WARN(1, "Failed to allocate memory for static calls"); + static_call_del_module(mod); + } + break; + case MODULE_STATE_GOING: + static_call_del_module(mod); + break; + } + + static_call_unlock(); + cpus_read_unlock(); + + return notifier_from_errno(ret); +} + +static struct notifier_block static_call_module_nb = { + .notifier_call = static_call_module_notify, +}; + +#else + +static inline int __static_call_mod_text_reserved(void *start, void *end) +{ + return 0; +} + +#endif /* CONFIG_MODULES */ + +int static_call_text_reserved(void *start, void *end) +{ + bool init = system_state < SYSTEM_RUNNING; + int ret = __static_call_text_reserved(__start_static_call_sites, + __stop_static_call_sites, start, end, init); + + if (ret) + return ret; + + return __static_call_mod_text_reserved(start, end); +} + +int __init static_call_init(void) +{ + int ret; + + if (static_call_initialized) + return 0; + + cpus_read_lock(); + static_call_lock(); + ret = __static_call_init(NULL, __start_static_call_sites, + __stop_static_call_sites); + static_call_unlock(); + cpus_read_unlock(); + + if (ret) { + pr_err("Failed to allocate memory for static_call!\n"); + BUG(); + } + + static_call_initialized = true; + +#ifdef CONFIG_MODULES + register_module_notifier(&static_call_module_nb); +#endif + return 0; +} +early_initcall(static_call_init); + +#ifdef CONFIG_STATIC_CALL_SELFTEST + +static int func_a(int x) +{ + return x+1; +} + +static int func_b(int x) +{ + return x+2; +} + +DEFINE_STATIC_CALL(sc_selftest, func_a); + +static struct static_call_data { + int (*func)(int); + int val; + int expect; +} static_call_data [] __initdata = { + { NULL, 2, 3 }, + { func_b, 2, 4 }, + { func_a, 2, 3 } +}; + +static int __init test_static_call_init(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) { + struct static_call_data *scd = &static_call_data[i]; + + if (scd->func) + static_call_update(sc_selftest, scd->func); + + WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect); + } + + return 0; +} +early_initcall(test_static_call_init); + +#endif /* CONFIG_STATIC_CALL_SELFTEST */ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7fa2ebc07f60..d8553f46caa2 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2349,11 +2349,11 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip, } static int -kprobe_multi_resolve_syms(const void *usyms, u32 cnt, +kprobe_multi_resolve_syms(const void __user *usyms, u32 cnt, unsigned long *addrs) { unsigned long addr, size; - const char **syms; + const char __user **syms; int err = -ENOMEM; unsigned int i; char *func; diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index ab463a4d2b23..b56833700d23 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -65,7 +65,7 @@ static void rethook_free_rcu(struct rcu_head *head) */ void rethook_free(struct rethook *rh) { - rcu_assign_pointer(rh->handler, NULL); + WRITE_ONCE(rh->handler, NULL); call_rcu(&rh->rcu, rethook_free_rcu); } diff --git a/lib/kobject.c b/lib/kobject.c index 56fa037501b5..5f0e71ab292c 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -54,32 +54,6 @@ void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) kobj->ktype->get_ownership(kobj, uid, gid); } -/* - * populate_dir - populate directory with attributes. - * @kobj: object we're working on. - * - * Most subsystems have a set of default attributes that are associated - * with an object that registers with them. This is a helper called during - * object registration that loops through the default attributes of the - * subsystem and creates attributes files for them in sysfs. - */ -static int populate_dir(struct kobject *kobj) -{ - const struct kobj_type *t = get_ktype(kobj); - struct attribute *attr; - int error = 0; - int i; - - if (t && t->default_attrs) { - for (i = 0; (attr = t->default_attrs[i]) != NULL; i++) { - error = sysfs_create_file(kobj, attr); - if (error) - break; - } - } - return error; -} - static int create_dir(struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); @@ -90,12 +64,6 @@ static int create_dir(struct kobject *kobj) if (error) return error; - error = populate_dir(kobj); - if (error) { - sysfs_remove_dir(kobj); - return error; - } - if (ktype) { error = sysfs_create_groups(kobj, ktype->default_groups); if (error) { diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 926f4823d5ea..fd1728d94bab 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -271,8 +271,12 @@ static FORCE_INLINE int LZ4_decompress_generic( ip += length; op += length; - /* Necessarily EOF, due to parsing restrictions */ - if (!partialDecoding || (cpy == oend)) + /* Necessarily EOF when !partialDecoding. + * When partialDecoding, it is EOF if we've either + * filled the output buffer or + * can't proceed with reading an offset for following match. + */ + if (!partialDecoding || (cpy == oend) || (ip >= (iend - 2))) break; } else { /* may overwrite up to WILDCOPYLENGTH beyond cpy */ diff --git a/mm/highmem.c b/mm/highmem.c index 0cc0c4da7ed9..1a692997fac4 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -624,7 +624,7 @@ void __kmap_local_sched_out(void) /* With debug all even slots are unmapped and act as guard */ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { - WARN_ON_ONCE(!pte_none(pteval)); + WARN_ON_ONCE(pte_val(pteval) != 0); continue; } if (WARN_ON_ONCE(pte_none(pteval))) @@ -661,7 +661,7 @@ void __kmap_local_sched_in(void) /* With debug all even slots are unmapped and act as guard */ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { - WARN_ON_ONCE(!pte_none(pteval)); + WARN_ON_ONCE(pte_val(pteval) != 0); continue; } if (WARN_ON_ONCE(pte_none(pteval))) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2fe38212e07c..c468fee595ff 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2145,15 +2145,14 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * pmd against. Otherwise we can end up replacing wrong folio. */ VM_BUG_ON(freeze && !folio); - if (folio) { - VM_WARN_ON_ONCE(!folio_test_locked(folio)); - if (folio != page_folio(pmd_page(*pmd))) - goto out; - } + VM_WARN_ON_ONCE(folio && !folio_test_locked(folio)); if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || - is_pmd_migration_entry(*pmd)) + is_pmd_migration_entry(*pmd)) { + if (folio && folio != page_folio(pmd_page(*pmd))) + goto out; __split_huge_pmd_locked(vma, pmd, range.start, freeze); + } out: spin_unlock(ptl); diff --git a/mm/list_lru.c b/mm/list_lru.c index c669d87001a6..ba76428ceece 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -395,12 +395,6 @@ static void memcg_reparent_list_lru_node(struct list_lru *lru, int nid, struct list_lru_one *src, *dst; /* - * If there is no lru entry in this nlru, we can skip it immediately. - */ - if (!READ_ONCE(nlru->nr_items)) - return; - - /* * Since list_lru_{add,del} may be called under an IRQ-safe lock, * we have to use IRQ-safe primitives here to avoid deadlock. */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index a2516d31db6c..8c74107a2b15 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1191,8 +1191,10 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, */ static struct page *new_page(struct page *page, unsigned long start) { + struct folio *dst, *src = page_folio(page); struct vm_area_struct *vma; unsigned long address; + gfp_t gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL; vma = find_vma(current->mm, start); while (vma) { @@ -1202,24 +1204,19 @@ static struct page *new_page(struct page *page, unsigned long start) vma = vma->vm_next; } - if (PageHuge(page)) { - return alloc_huge_page_vma(page_hstate(compound_head(page)), + if (folio_test_hugetlb(src)) + return alloc_huge_page_vma(page_hstate(&src->page), vma, address); - } else if (PageTransHuge(page)) { - struct page *thp; - thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, - HPAGE_PMD_ORDER); - if (!thp) - return NULL; - prep_transhuge_page(thp); - return thp; - } + if (folio_test_large(src)) + gfp = GFP_TRANSHUGE; + /* - * if !vma, alloc_page_vma() will use task or system default policy + * if !vma, vma_alloc_folio() will use task or system default policy */ - return alloc_page_vma(GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL, - vma, address); + dst = vma_alloc_folio(gfp, folio_order(src), vma, address, + folio_test_large(src)); + return &dst->page; } #else @@ -2227,6 +2224,19 @@ out: } EXPORT_SYMBOL(alloc_pages_vma); +struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, + unsigned long addr, bool hugepage) +{ + struct folio *folio; + + folio = (struct folio *)alloc_pages_vma(gfp, order, vma, addr, + hugepage); + if (folio && order > 1) + prep_transhuge_page(&folio->page); + + return folio; +} + /** * alloc_pages - Allocate pages. * @gfp: GFP flags. @@ -2733,6 +2743,7 @@ alloc_new: mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; + atomic_set(&mpol_new->refcnt, 1); goto restart; } diff --git a/mm/migrate.c b/mm/migrate.c index de175e2fdba5..6c31ee1e1c9b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1520,10 +1520,11 @@ out: struct page *alloc_migration_target(struct page *page, unsigned long private) { + struct folio *folio = page_folio(page); struct migration_target_control *mtc; gfp_t gfp_mask; unsigned int order = 0; - struct page *new_page = NULL; + struct folio *new_folio = NULL; int nid; int zidx; @@ -1531,34 +1532,31 @@ struct page *alloc_migration_target(struct page *page, unsigned long private) gfp_mask = mtc->gfp_mask; nid = mtc->nid; if (nid == NUMA_NO_NODE) - nid = page_to_nid(page); + nid = folio_nid(folio); - if (PageHuge(page)) { - struct hstate *h = page_hstate(compound_head(page)); + if (folio_test_hugetlb(folio)) { + struct hstate *h = page_hstate(&folio->page); gfp_mask = htlb_modify_alloc_mask(h, gfp_mask); return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask); } - if (PageTransHuge(page)) { + if (folio_test_large(folio)) { /* * clear __GFP_RECLAIM to make the migration callback * consistent with regular THP allocations. */ gfp_mask &= ~__GFP_RECLAIM; gfp_mask |= GFP_TRANSHUGE; - order = HPAGE_PMD_ORDER; + order = folio_order(folio); } - zidx = zone_idx(page_zone(page)); + zidx = zone_idx(folio_zone(folio)); if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE) gfp_mask |= __GFP_HIGHMEM; - new_page = __alloc_pages(gfp_mask, order, nid, mtc->nmask); - - if (new_page && PageTransHuge(new_page)) - prep_transhuge_page(new_page); + new_folio = __folio_alloc(gfp_mask, order, nid, mtc->nmask); - return new_page; + return &new_folio->page; } #ifdef CONFIG_NUMA @@ -1999,32 +1997,20 @@ static struct page *alloc_misplaced_dst_page(struct page *page, unsigned long data) { int nid = (int) data; - struct page *newpage; - - newpage = __alloc_pages_node(nid, - (GFP_HIGHUSER_MOVABLE | - __GFP_THISNODE | __GFP_NOMEMALLOC | - __GFP_NORETRY | __GFP_NOWARN) & - ~__GFP_RECLAIM, 0); - - return newpage; -} - -static struct page *alloc_misplaced_dst_page_thp(struct page *page, - unsigned long data) -{ - int nid = (int) data; - struct page *newpage; - - newpage = alloc_pages_node(nid, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), - HPAGE_PMD_ORDER); - if (!newpage) - goto out; - - prep_transhuge_page(newpage); + int order = compound_order(page); + gfp_t gfp = __GFP_THISNODE; + struct folio *new; + + if (order > 0) + gfp |= GFP_TRANSHUGE_LIGHT; + else { + gfp |= GFP_HIGHUSER_MOVABLE | __GFP_NOMEMALLOC | __GFP_NORETRY | + __GFP_NOWARN; + gfp &= ~__GFP_RECLAIM; + } + new = __folio_alloc_node(gfp, order, nid); -out: - return newpage; + return &new->page; } static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) @@ -2082,23 +2068,9 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int nr_remaining; unsigned int nr_succeeded; LIST_HEAD(migratepages); - new_page_t *new; - bool compound; int nr_pages = thp_nr_pages(page); /* - * PTE mapped THP or HugeTLB page can't reach here so the page could - * be either base page or THP. And it must be head page if it is - * THP. - */ - compound = PageTransHuge(page); - - if (compound) - new = alloc_misplaced_dst_page_thp; - else - new = alloc_misplaced_dst_page; - - /* * Don't migrate file pages that are mapped in multiple processes * with execute permissions as they are probably shared libraries. */ @@ -2118,9 +2090,9 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, goto out; list_add(&page->lru, &migratepages); - nr_remaining = migrate_pages(&migratepages, *new, NULL, node, - MIGRATE_ASYNC, MR_NUMA_MISPLACED, - &nr_succeeded); + nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, + NULL, node, MIGRATE_ASYNC, + MR_NUMA_MISPLACED, &nr_succeeded); if (nr_remaining) { if (!list_empty(&migratepages)) { list_del(&page->lru); diff --git a/mm/mremap.c b/mm/mremap.c index 9d76da79594d..303d3290b938 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -486,6 +486,9 @@ unsigned long move_page_tables(struct vm_area_struct *vma, pmd_t *old_pmd, *new_pmd; pud_t *old_pud, *new_pud; + if (!len) + return 0; + old_end = old_addr + len; flush_cache_range(vma, old_addr, old_end); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2db95780e003..6e5b4488a0c5 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -128,7 +128,7 @@ static DEFINE_MUTEX(pcp_batch_high_lock); struct pagesets { local_lock_t lock; }; -static DEFINE_PER_CPU(struct pagesets, pagesets) __maybe_unused = { +static DEFINE_PER_CPU(struct pagesets, pagesets) = { .lock = INIT_LOCAL_LOCK(lock), }; diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 1187f9c1ec5b..14a5cda73dee 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -163,7 +163,8 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) return not_found(pvmw); if (unlikely(is_vm_hugetlb_page(vma))) { - unsigned long size = pvmw->nr_pages * PAGE_SIZE; + struct hstate *hstate = hstate_vma(vma); + unsigned long size = huge_page_size(hstate); /* The only possible mapping was handled on last iteration */ if (pvmw->pte) return not_found(pvmw); @@ -173,8 +174,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (!pvmw->pte) return false; - pvmw->ptl = huge_pte_lockptr(size_to_hstate(size), mm, - pvmw->pte); + pvmw->ptl = huge_pte_lockptr(hstate, mm, pvmw->pte); spin_lock(pvmw->ptl); if (!check_pte(pvmw)) return not_found(pvmw); diff --git a/net/core/filter.c b/net/core/filter.c index a7044e98765e..64470a727ef7 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7016,24 +7016,33 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (!th->ack || th->rst || th->syn) return -ENOENT; + if (unlikely(iph_len < sizeof(struct iphdr))) + return -EINVAL; + if (tcp_synq_no_recent_overflow(sk)) return -ENOENT; cookie = ntohl(th->ack_seq) - 1; - switch (sk->sk_family) { - case AF_INET: - if (unlikely(iph_len < sizeof(struct iphdr))) + /* Both struct iphdr and struct ipv6hdr have the version field at the + * same offset so we can cast to the shorter header (struct iphdr). + */ + switch (((struct iphdr *)iph)->version) { + case 4: + if (sk->sk_family == AF_INET6 && ipv6_only_sock(sk)) return -EINVAL; ret = __cookie_v4_check((struct iphdr *)iph, th, cookie); break; #if IS_BUILTIN(CONFIG_IPV6) - case AF_INET6: + case 6: if (unlikely(iph_len < sizeof(struct ipv6hdr))) return -EINVAL; + if (sk->sk_family != AF_INET6) + return -EINVAL; + ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie); break; #endif /* CONFIG_IPV6 */ diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 10bde7c6db44..30b523fa4ad2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5276,11 +5276,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_cloned(to)) return false; - /* The page pool signature of struct page will eventually figure out - * which pages can be recycled or not but for now let's prohibit slab - * allocated and page_pool allocated SKBs from being coalesced. + /* In general, avoid mixing slab allocated and page_pool allocated + * pages within the same SKB. However when @to is not pp_recycle and + * @from is cloned, we can transition frag pages from page_pool to + * reference counted. + * + * On the other hand, don't allow coalescing two pp_recycle SKBs if + * @from is cloned, in case the SKB is using page_pool fragment + * references (PP_FLAG_PAGE_FRAG). Since we only take full page + * references for cloned SKBs at the moment that would result in + * inconsistent reference counts. */ - if (to->pp_recycle != from->pp_recycle) + if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from))) return false; if (len <= skb_tailroom(to)) { diff --git a/net/dsa/master.c b/net/dsa/master.c index 991c2930d631..2851e44c4cf0 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -335,11 +335,24 @@ static const struct attribute_group dsa_group = { .attrs = dsa_slave_attrs, }; +static void dsa_master_reset_mtu(struct net_device *dev) +{ + int err; + + err = dev_set_mtu(dev, ETH_DATA_LEN); + if (err) + netdev_dbg(dev, + "Unable to reset MTU to exclude DSA overheads\n"); +} + int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { + const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops; struct dsa_switch *ds = cpu_dp->ds; struct device_link *consumer_link; - int ret; + int mtu, ret; + + mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops); /* The DSA master must use SET_NETDEV_DEV for this to work. */ consumer_link = device_link_add(ds->dev, dev->dev.parent, @@ -349,6 +362,15 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) "Failed to create a device link to DSA switch %s\n", dev_name(ds->dev)); + /* The switch driver may not implement ->port_change_mtu(), case in + * which dsa_slave_change_mtu() will not update the master MTU either, + * so we need to do that here. + */ + ret = dev_set_mtu(dev, mtu); + if (ret) + netdev_warn(dev, "error %d setting MTU to %d to include DSA overhead\n", + ret, mtu); + /* If we use a tagging format that doesn't have an ethertype * field, make sure that all packets from this point on get * sent to the tag format's receive function. @@ -384,6 +406,7 @@ void dsa_master_teardown(struct net_device *dev) sysfs_remove_group(&dev->dev.kobj, &dsa_group); dsa_netdev_ops_set(dev, NULL); dsa_master_ethtool_teardown(dev); + dsa_master_reset_mtu(dev); dsa_master_set_promiscuity(dev, -1); dev->dsa_ptr = NULL; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index cc8e84ef2ae4..ccb62038f6a4 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -889,8 +889,13 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, } if (cfg->fc_oif || cfg->fc_gw_family) { - struct fib_nh *nh = fib_info_nh(fi, 0); + struct fib_nh *nh; + + /* cannot match on nexthop object attributes */ + if (fi->nh) + return 1; + nh = fib_info_nh(fi, 0); if (cfg->fc_encap) { if (fib_encap_match(net, cfg->fc_encap_type, cfg->fc_encap, nh, cfg, extack)) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index a9775c830194..4e74bc61a3db 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1653,7 +1653,6 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, mifi_t mifi; struct net *net = sock_net(sk); struct mr_table *mrt; - bool do_wrmifwhole; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_ICMPV6) @@ -1761,6 +1760,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval, #ifdef CONFIG_IPV6_PIMSM_V2 case MRT6_PIM: { + bool do_wrmifwhole; int v; if (optlen != sizeof(v)) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2fa10e60cccd..169e9df6d172 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4484,7 +4484,7 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) struct inet6_dev *idev; int type; - if (netif_is_l3_master(skb->dev) && + if (netif_is_l3_master(skb->dev) || dst->dev == net->loopback_dev) idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); else diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index f0702d920d8d..e22b0cbb2f35 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -93,13 +93,13 @@ out_release: static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name); - const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr); int rc, addrlen = msg->msg_namelen; struct sock *sk = sock->sk; struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct mctp_skb_cb *cb; struct mctp_route *rt; - struct sk_buff *skb; + struct sk_buff *skb = NULL; + int hlen; if (addr) { const u8 tagbits = MCTP_TAG_MASK | MCTP_TAG_OWNER | @@ -129,6 +129,34 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (addr->smctp_network == MCTP_NET_ANY) addr->smctp_network = mctp_default_net(sock_net(sk)); + /* direct addressing */ + if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) { + DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, + extaddr, msg->msg_name); + struct net_device *dev; + + rc = -EINVAL; + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), extaddr->smctp_ifindex); + /* check for correct halen */ + if (dev && extaddr->smctp_halen == dev->addr_len) { + hlen = LL_RESERVED_SPACE(dev) + sizeof(struct mctp_hdr); + rc = 0; + } + rcu_read_unlock(); + if (rc) + goto err_free; + rt = NULL; + } else { + rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, + addr->smctp_addr.s_addr); + if (!rt) { + rc = -EHOSTUNREACH; + goto err_free; + } + hlen = LL_RESERVED_SPACE(rt->dev->dev) + sizeof(struct mctp_hdr); + } + skb = sock_alloc_send_skb(sk, hlen + 1 + len, msg->msg_flags & MSG_DONTWAIT, &rc); if (!skb) @@ -147,8 +175,8 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) cb = __mctp_cb(skb); cb->net = addr->smctp_network; - /* direct addressing */ - if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) { + if (!rt) { + /* fill extended address in cb */ DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, extaddr, msg->msg_name); @@ -159,17 +187,9 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) } cb->ifindex = extaddr->smctp_ifindex; + /* smctp_halen is checked above */ cb->halen = extaddr->smctp_halen; memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen); - - rt = NULL; - } else { - rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, - addr->smctp_addr.s_addr); - if (!rt) { - rc = -EHOSTUNREACH; - goto err_free; - } } rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr, diff --git a/net/mctp/route.c b/net/mctp/route.c index d5e7db83fe9d..3b24b8d18b5b 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -503,6 +503,11 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) if (cb->ifindex) { /* direct route; use the hwaddr we stashed in sendmsg */ + if (cb->halen != skb->dev->addr_len) { + /* sanity check, sendmsg should have already caught this */ + kfree_skb(skb); + return -EMSGSIZE; + } daddr = cb->haddr; } else { /* If lookup fails let the device handle daddr==NULL */ @@ -512,7 +517,7 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) rc = dev_hard_header(skb, skb->dev, ntohs(skb->protocol), daddr, skb->dev->dev_addr, skb->len); - if (rc) { + if (rc < 0) { kfree_skb(skb); return -EHOSTUNREACH; } @@ -756,7 +761,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, { const unsigned int hlen = sizeof(struct mctp_hdr); struct mctp_hdr *hdr, *hdr2; - unsigned int pos, size; + unsigned int pos, size, headroom; struct sk_buff *skb2; int rc; u8 seq; @@ -770,6 +775,9 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, return -EMSGSIZE; } + /* keep same headroom as the original skb */ + headroom = skb_headroom(skb); + /* we've got the header */ skb_pull(skb, hlen); @@ -777,7 +785,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, /* size of message payload */ size = min(mtu - hlen, skb->len - pos); - skb2 = alloc_skb(MCTP_HEADER_MAXLEN + hlen + size, GFP_KERNEL); + skb2 = alloc_skb(headroom + hlen + size, GFP_KERNEL); if (!skb2) { rc = -ENOMEM; break; @@ -793,7 +801,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, skb_set_owner_w(skb2, skb->sk); /* establish packet */ - skb_reserve(skb2, MCTP_HEADER_MAXLEN); + skb_reserve(skb2, headroom); skb_reset_network_header(skb2); skb_put(skb2, hlen + size); skb2->transport_header = skb2->network_header + hlen; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5ddfdb2adaf1..128ee3b300d6 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5526,7 +5526,7 @@ int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, int err, i, k; for (i = 0; i < set->num_exprs; i++) { - expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL); + expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL_ACCOUNT); if (!expr) goto err_expr; diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 38caa66632b4..f590ee1c8a1b 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -290,7 +290,7 @@ static bool nft_bitwise_reduce(struct nft_regs_track *track, if (!track->regs[priv->sreg].selector) return false; - bitwise = nft_expr_priv(expr); + bitwise = nft_expr_priv(track->regs[priv->dreg].selector); if (track->regs[priv->sreg].selector == track->regs[priv->dreg].selector && track->regs[priv->sreg].num_reg == 0 && track->regs[priv->dreg].bitwise && @@ -442,7 +442,7 @@ static bool nft_bitwise_fast_reduce(struct nft_regs_track *track, if (!track->regs[priv->sreg].selector) return false; - bitwise = nft_expr_priv(expr); + bitwise = nft_expr_priv(track->regs[priv->dreg].selector); if (track->regs[priv->sreg].selector == track->regs[priv->dreg].selector && track->regs[priv->dreg].bitwise && track->regs[priv->dreg].bitwise->ops == expr->ops && diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index 9de1462e4ac4..d657f999a11b 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -77,7 +77,7 @@ static int nft_connlimit_do_init(const struct nft_ctx *ctx, invert = true; } - priv->list = kmalloc(sizeof(*priv->list), GFP_KERNEL); + priv->list = kmalloc(sizeof(*priv->list), GFP_KERNEL_ACCOUNT); if (!priv->list) return -ENOMEM; diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index da9083605a61..f4d3573e8782 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -62,7 +62,7 @@ static int nft_counter_do_init(const struct nlattr * const tb[], struct nft_counter __percpu *cpu_stats; struct nft_counter *this_cpu; - cpu_stats = alloc_percpu(struct nft_counter); + cpu_stats = alloc_percpu_gfp(struct nft_counter, GFP_KERNEL_ACCOUNT); if (cpu_stats == NULL) return -ENOMEM; diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c index 43d0d4aadb1f..bb15a55dad5c 100644 --- a/net/netfilter/nft_last.c +++ b/net/netfilter/nft_last.c @@ -30,7 +30,7 @@ static int nft_last_init(const struct nft_ctx *ctx, const struct nft_expr *expr, u64 last_jiffies; int err; - last = kzalloc(sizeof(*last), GFP_KERNEL); + last = kzalloc(sizeof(*last), GFP_KERNEL_ACCOUNT); if (!last) return -ENOMEM; diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index d4a6cf3cd697..04ea8b9bf202 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -90,7 +90,7 @@ static int nft_limit_init(struct nft_limit_priv *priv, priv->rate); } - priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL); + priv->limit = kmalloc(sizeof(*priv->limit), GFP_KERNEL_ACCOUNT); if (!priv->limit) return -ENOMEM; diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index d7db57ed3bc1..e6b0df68feea 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -90,7 +90,7 @@ static int nft_quota_do_init(const struct nlattr * const tb[], return -EOPNOTSUPP; } - priv->consumed = kmalloc(sizeof(*priv->consumed), GFP_KERNEL); + priv->consumed = kmalloc(sizeof(*priv->consumed), GFP_KERNEL_ACCOUNT); if (!priv->consumed) return -ENOMEM; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 7056cb1b8ba0..1b5d73079dc9 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1051,7 +1051,7 @@ static int clone(struct datapath *dp, struct sk_buff *skb, int rem = nla_len(attr); bool dont_clone_flow_key; - /* The first action is always 'OVS_CLONE_ATTR_ARG'. */ + /* The first action is always 'OVS_CLONE_ATTR_EXEC'. */ clone_arg = nla_data(attr); dont_clone_flow_key = nla_get_u32(clone_arg); actions = nla_next(clone_arg, &rem); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index cc282a58b75b..7176156d3844 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2317,6 +2317,62 @@ static struct sw_flow_actions *nla_alloc_flow_actions(int size) return sfa; } +static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len); + +static void ovs_nla_free_check_pkt_len_action(const struct nlattr *action) +{ + const struct nlattr *a; + int rem; + + nla_for_each_nested(a, action, rem) { + switch (nla_type(a)) { + case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL: + case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER: + ovs_nla_free_nested_actions(nla_data(a), nla_len(a)); + break; + } + } +} + +static void ovs_nla_free_clone_action(const struct nlattr *action) +{ + const struct nlattr *a = nla_data(action); + int rem = nla_len(action); + + switch (nla_type(a)) { + case OVS_CLONE_ATTR_EXEC: + /* The real list of actions follows this attribute. */ + a = nla_next(a, &rem); + ovs_nla_free_nested_actions(a, rem); + break; + } +} + +static void ovs_nla_free_dec_ttl_action(const struct nlattr *action) +{ + const struct nlattr *a = nla_data(action); + + switch (nla_type(a)) { + case OVS_DEC_TTL_ATTR_ACTION: + ovs_nla_free_nested_actions(nla_data(a), nla_len(a)); + break; + } +} + +static void ovs_nla_free_sample_action(const struct nlattr *action) +{ + const struct nlattr *a = nla_data(action); + int rem = nla_len(action); + + switch (nla_type(a)) { + case OVS_SAMPLE_ATTR_ARG: + /* The real list of actions follows this attribute. */ + a = nla_next(a, &rem); + ovs_nla_free_nested_actions(a, rem); + break; + } +} + static void ovs_nla_free_set_action(const struct nlattr *a) { const struct nlattr *ovs_key = nla_data(a); @@ -2330,25 +2386,54 @@ static void ovs_nla_free_set_action(const struct nlattr *a) } } -void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len) { const struct nlattr *a; int rem; - if (!sf_acts) + /* Whenever new actions are added, the need to update this + * function should be considered. + */ + BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 23); + + if (!actions) return; - nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) { + nla_for_each_attr(a, actions, len, rem) { switch (nla_type(a)) { - case OVS_ACTION_ATTR_SET: - ovs_nla_free_set_action(a); + case OVS_ACTION_ATTR_CHECK_PKT_LEN: + ovs_nla_free_check_pkt_len_action(a); + break; + + case OVS_ACTION_ATTR_CLONE: + ovs_nla_free_clone_action(a); break; + case OVS_ACTION_ATTR_CT: ovs_ct_free_action(a); break; + + case OVS_ACTION_ATTR_DEC_TTL: + ovs_nla_free_dec_ttl_action(a); + break; + + case OVS_ACTION_ATTR_SAMPLE: + ovs_nla_free_sample_action(a); + break; + + case OVS_ACTION_ATTR_SET: + ovs_nla_free_set_action(a); + break; } } +} + +void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) +{ + if (!sf_acts) + return; + ovs_nla_free_nested_actions(sf_acts->actions, sf_acts->actions_len); kfree(sf_acts); } @@ -3458,7 +3543,9 @@ static int clone_action_to_attr(const struct nlattr *attr, if (!start) return -EMSGSIZE; - err = ovs_nla_put_actions(nla_data(attr), rem, skb); + /* Skipping the OVS_CLONE_ATTR_EXEC that is always the first attribute. */ + attr = nla_next(nla_data(attr), &rem); + err = ovs_nla_put_actions(attr, rem, skb); if (err) nla_nest_cancel(skb, start); diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index 25bbc4cc8b13..f15d6942da45 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -113,8 +113,8 @@ static __net_exit void rxrpc_exit_net(struct net *net) struct rxrpc_net *rxnet = rxrpc_net(net); rxnet->live = false; - del_timer_sync(&rxnet->peer_keepalive_timer); cancel_work_sync(&rxnet->peer_keepalive_work); + del_timer_sync(&rxnet->peer_keepalive_timer); rxrpc_destroy_all_calls(rxnet); rxrpc_destroy_all_connections(rxnet); rxrpc_destroy_all_peers(rxnet); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index a18609f608fb..e213aaf45d67 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -914,6 +914,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) ctx->asoc->base.sk->sk_err = -error; return; } + ctx->asoc->stats.octrlchunks++; break; case SCTP_CID_ABORT: @@ -938,7 +939,10 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx) case SCTP_CID_HEARTBEAT: if (chunk->pmtu_probe) { - sctp_packet_singleton(ctx->transport, chunk, ctx->gfp); + error = sctp_packet_singleton(ctx->transport, + chunk, ctx->gfp); + if (!error) + ctx->asoc->stats.octrlchunks++; break; } fallthrough; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8bf2af8546d2..af0174d7ce5a 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1127,6 +1127,8 @@ struct rpc_task *rpc_run_task(const struct rpc_task_setup *task_setup_data) struct rpc_task *task; task = rpc_new_task(task_setup_data); + if (IS_ERR(task)) + return task; if (!RPC_IS_ASYNC(task)) task->tk_flags |= RPC_TASK_CRED_NOREF; @@ -1227,6 +1229,11 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req) * Create an rpc_task to send the data */ task = rpc_new_task(&task_setup_data); + if (IS_ERR(task)) { + xprt_free_bc_request(req); + return task; + } + xprt_init_bc_request(req, task); task->tk_action = call_bc_encode; @@ -1858,6 +1865,9 @@ call_encode(struct rpc_task *task) xprt_request_dequeue_xprt(task); /* Encode here so that rpcsec_gss can use correct sequence number. */ rpc_xdr_encode(task); + /* Add task to reply queue before transmission to avoid races */ + if (task->tk_status == 0 && rpc_reply_expected(task)) + task->tk_status = xprt_request_enqueue_receive(task); /* Did the encode result in an error condition? */ if (task->tk_status != 0) { /* Was the error nonfatal? */ @@ -1881,9 +1891,6 @@ call_encode(struct rpc_task *task) return; } - /* Add task to reply queue before transmission to avoid races */ - if (rpc_reply_expected(task)) - xprt_request_enqueue_receive(task); xprt_request_enqueue_transmit(task); out: task->tk_action = call_transmit; @@ -2200,6 +2207,7 @@ call_transmit_status(struct rpc_task *task) * socket just returned a connection error, * then hold onto the transport lock. */ + case -ENOMEM: case -ENOBUFS: rpc_delay(task, HZ>>2); fallthrough; @@ -2283,6 +2291,7 @@ call_bc_transmit_status(struct rpc_task *task) case -ENOTCONN: case -EPIPE: break; + case -ENOMEM: case -ENOBUFS: rpc_delay(task, HZ>>2); fallthrough; @@ -2365,6 +2374,11 @@ call_status(struct rpc_task *task) case -EPIPE: case -EAGAIN: break; + case -ENFILE: + case -ENOBUFS: + case -ENOMEM: + rpc_delay(task, HZ>>2); + break; case -EIO: /* shutdown or soft timeout */ goto out_exit; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index b258b87a3ec2..7f70c1e608b7 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -1128,6 +1128,11 @@ struct rpc_task *rpc_new_task(const struct rpc_task_setup *setup_data) if (task == NULL) { task = rpc_alloc_task(); + if (task == NULL) { + rpc_release_calldata(setup_data->callback_ops, + setup_data->callback_data); + return ERR_PTR(-ENOMEM); + } flags = RPC_TASK_DYNAMIC; } diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c index 05b38bf68316..71ba4cf513bc 100644 --- a/net/sunrpc/socklib.c +++ b/net/sunrpc/socklib.c @@ -221,12 +221,6 @@ static int xprt_send_kvec(struct socket *sock, struct msghdr *msg, static int xprt_send_pagedata(struct socket *sock, struct msghdr *msg, struct xdr_buf *xdr, size_t base) { - int err; - - err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); - if (err < 0) - return err; - iov_iter_bvec(&msg->msg_iter, WRITE, xdr->bvec, xdr_buf_pagecount(xdr), xdr->page_len + xdr->page_base); return xprt_sendmsg(sock, msg, base + xdr->page_base); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 478f857cdaed..cc35ec433400 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -579,15 +579,18 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) if (svc_xprt_is_dead(xprt)) goto out_notconn; + err = xdr_alloc_bvec(xdr, GFP_KERNEL); + if (err < 0) + goto out_unlock; + err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent); - xdr_free_bvec(xdr); if (err == -ECONNREFUSED) { /* ICMP error on earlier request. */ err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent); - xdr_free_bvec(xdr); } + xdr_free_bvec(xdr); trace_svcsock_udp_send(xprt, err); - +out_unlock: mutex_unlock(&xprt->xpt_mutex); if (err < 0) return err; @@ -1096,7 +1099,9 @@ static int svc_tcp_sendmsg(struct socket *sock, struct xdr_buf *xdr, int ret; *sentp = 0; - xdr_alloc_bvec(xdr, GFP_KERNEL); + ret = xdr_alloc_bvec(xdr, GFP_KERNEL); + if (ret < 0) + return ret; ret = kernel_sendmsg(sock, &msg, &rm, 1, rm.iov_len); if (ret < 0) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 515501f79290..86d62cffba0d 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -69,10 +69,11 @@ /* * Local functions */ -static void xprt_init(struct rpc_xprt *xprt, struct net *net); +static void xprt_init(struct rpc_xprt *xprt, struct net *net); static __be32 xprt_alloc_xid(struct rpc_xprt *xprt); -static void xprt_destroy(struct rpc_xprt *xprt); -static void xprt_request_init(struct rpc_task *task); +static void xprt_destroy(struct rpc_xprt *xprt); +static void xprt_request_init(struct rpc_task *task); +static int xprt_request_prepare(struct rpc_rqst *req); static DEFINE_SPINLOCK(xprt_list_lock); static LIST_HEAD(xprt_list); @@ -929,12 +930,7 @@ void xprt_connect(struct rpc_task *task) if (!xprt_lock_write(xprt, task)) return; - if (test_and_clear_bit(XPRT_CLOSE_WAIT, &xprt->state)) { - trace_xprt_disconnect_cleanup(xprt); - xprt->ops->close(xprt); - } - - if (!xprt_connected(xprt)) { + if (!xprt_connected(xprt) && !test_bit(XPRT_CLOSE_WAIT, &xprt->state)) { task->tk_rqstp->rq_connect_cookie = xprt->connect_cookie; rpc_sleep_on_timeout(&xprt->pending, task, NULL, xprt_request_timeout(task->tk_rqstp)); @@ -1143,16 +1139,19 @@ xprt_request_need_enqueue_receive(struct rpc_task *task, struct rpc_rqst *req) * @task: RPC task * */ -void +int xprt_request_enqueue_receive(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; struct rpc_xprt *xprt = req->rq_xprt; + int ret; if (!xprt_request_need_enqueue_receive(task, req)) - return; + return 0; - xprt_request_prepare(task->tk_rqstp); + ret = xprt_request_prepare(task->tk_rqstp); + if (ret) + return ret; spin_lock(&xprt->queue_lock); /* Update the softirq receive buffer */ @@ -1166,6 +1165,7 @@ xprt_request_enqueue_receive(struct rpc_task *task) /* Turn off autodisconnect */ del_singleshot_timer_sync(&xprt->timer); + return 0; } /** @@ -1452,14 +1452,16 @@ xprt_request_dequeue_xprt(struct rpc_task *task) * * Calls into the transport layer to do whatever is needed to prepare * the request for transmission or receive. + * Returns error, or zero. */ -void +static int xprt_request_prepare(struct rpc_rqst *req) { struct rpc_xprt *xprt = req->rq_xprt; if (xprt->ops->prepare_request) - xprt->ops->prepare_request(req); + return xprt->ops->prepare_request(req); + return 0; } /** diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 78af7518f263..8ab64ea46870 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -822,12 +822,17 @@ static int xs_stream_nospace(struct rpc_rqst *req, bool vm_wait) return ret; } -static void +static int xs_stream_prepare_request(struct rpc_rqst *req) { + gfp_t gfp = rpc_task_gfp_mask(); + int ret; + + ret = xdr_alloc_bvec(&req->rq_snd_buf, gfp); + if (ret < 0) + return ret; xdr_free_bvec(&req->rq_rcv_buf); - req->rq_task->tk_status = xdr_alloc_bvec( - &req->rq_rcv_buf, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + return xdr_alloc_bvec(&req->rq_rcv_buf, gfp); } /* @@ -879,7 +884,7 @@ static int xs_local_send_request(struct rpc_rqst *req) /* Close the stream if the previous transmission was incomplete */ if (xs_send_request_was_aborted(transport, req)) { - xs_close(xprt); + xprt_force_disconnect(xprt); return -ENOTCONN; } @@ -915,7 +920,7 @@ static int xs_local_send_request(struct rpc_rqst *req) -status); fallthrough; case -EPIPE: - xs_close(xprt); + xprt_force_disconnect(xprt); status = -ENOTCONN; } @@ -956,6 +961,9 @@ static int xs_udp_send_request(struct rpc_rqst *req) if (!xprt_request_get_cong(xprt, req)) return -EBADSLT; + status = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); + if (status < 0) + return status; req->rq_xtime = ktime_get(); status = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, 0, &sent); @@ -1185,6 +1193,16 @@ static void xs_reset_transport(struct sock_xprt *transport) if (sk == NULL) return; + /* + * Make sure we're calling this in a context from which it is safe + * to call __fput_sync(). In practice that means rpciod and the + * system workqueue. + */ + if (!(current->flags & PF_WQ_WORKER)) { + WARN_ON_ONCE(1); + set_bit(XPRT_CLOSE_WAIT, &xprt->state); + return; + } if (atomic_read(&transport->xprt.swapper)) sk_clear_memalloc(sk); @@ -1208,7 +1226,7 @@ static void xs_reset_transport(struct sock_xprt *transport) mutex_unlock(&transport->recv_mutex); trace_rpc_socket_close(xprt, sock); - fput(filp); + __fput_sync(filp); xprt_disconnect_done(xprt); } @@ -2544,6 +2562,9 @@ static int bc_sendto(struct rpc_rqst *req) int err; req->rq_xtime = ktime_get(); + err = xdr_alloc_bvec(xdr, rpc_task_gfp_mask()); + if (err < 0) + return err; err = xprt_sock_sendmsg(transport->sock, &msg, xdr, 0, marker, &sent); xdr_free_bvec(xdr); if (err < 0 || sent != (xdr->len + sizeof(marker))) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 0024a692f0f8..a8976ef95528 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1496,7 +1496,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, if (prot->version == TLS_1_3_VERSION || prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305) memcpy(iv + iv_offset, tls_ctx->rx.iv, - crypto_aead_ivsize(ctx->aead_recv)); + prot->iv_size + prot->salt_size); else memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size); diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 9afcc6467a09..e09d6908a21d 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -75,6 +75,7 @@ #define ARM_CPU_PART_CORTEX_A77 0xD0D #define ARM_CPU_PART_NEOVERSE_V1 0xD40 #define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 @@ -130,6 +131,7 @@ #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) #define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) #define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 91af2850b505..7678af364793 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -828,8 +828,10 @@ codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped) s->map_cnt = %zu; \n\ s->map_skel_sz = sizeof(*s->maps); \n\ s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ - if (!s->maps) \n\ + if (!s->maps) { \n\ + err = -ENOMEM; \n\ goto err; \n\ + } \n\ ", map_cnt ); @@ -870,8 +872,10 @@ codegen_progs_skeleton(struct bpf_object *obj, size_t prog_cnt, bool populate_li s->prog_cnt = %zu; \n\ s->prog_skel_sz = sizeof(*s->progs); \n\ s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ - if (!s->progs) \n\ + if (!s->progs) { \n\ + err = -ENOMEM; \n\ goto err; \n\ + } \n\ ", prog_cnt ); @@ -1182,10 +1186,13 @@ static int do_skeleton(int argc, char **argv) %1$s__create_skeleton(struct %1$s *obj) \n\ { \n\ struct bpf_object_skeleton *s; \n\ + int err; \n\ \n\ s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ - if (!s) \n\ + if (!s) { \n\ + err = -ENOMEM; \n\ goto err; \n\ + } \n\ \n\ s->sz = sizeof(*s); \n\ s->name = \"%1$s\"; \n\ @@ -1206,7 +1213,7 @@ static int do_skeleton(int argc, char **argv) return 0; \n\ err: \n\ bpf_object__destroy_skeleton(s); \n\ - return -ENOMEM; \n\ + return err; \n\ } \n\ \n\ static inline const void *%2$s__elf_bytes(size_t *sz) \n\ @@ -1466,12 +1473,12 @@ static int do_subskeleton(int argc, char **argv) \n\ obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ if (!obj) { \n\ - errno = ENOMEM; \n\ + err = -ENOMEM; \n\ goto err; \n\ } \n\ s = (struct bpf_object_subskeleton *)calloc(1, sizeof(*s));\n\ if (!s) { \n\ - errno = ENOMEM; \n\ + err = -ENOMEM; \n\ goto err; \n\ } \n\ s->sz = sizeof(*s); \n\ @@ -1483,7 +1490,7 @@ static int do_subskeleton(int argc, char **argv) s->var_cnt = %2$d; \n\ s->vars = (struct bpf_var_skeleton *)calloc(%2$d, sizeof(*s->vars));\n\ if (!s->vars) { \n\ - errno = ENOMEM; \n\ + err = -ENOMEM; \n\ goto err; \n\ } \n\ ", @@ -1538,6 +1545,7 @@ static int do_subskeleton(int argc, char **argv) return obj; \n\ err: \n\ %1$s__destroy(obj); \n\ + errno = -err; \n\ return NULL; \n\ } \n\ \n\ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 1480910c792e..de66e1cc0734 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -217,9 +217,16 @@ strip-libs = $(filter-out -l%,$(1)) PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null) PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS)) PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) -PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` +PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null) FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) +ifeq ($(CC_NO_CLANG), 0) + PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS)) + PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS)) + PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS)) + FLAGS_PERL_EMBED += -Wno-compound-token-split-by-macro +endif + $(OUTPUT)test-libperl.bin: $(BUILD) $(FLAGS_PERL_EMBED) diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index c998860d7bbc..5d99e7c242a2 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -150,4 +150,11 @@ /* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) + +/* Get the config size */ +#define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) + +/* Get the count of all virtqueues */ +#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) + #endif diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 6de5085e3e5a..bd0c2c828940 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1155,6 +1155,17 @@ static void annotate_call_site(struct objtool_file *file, : arch_nop_insn(insn->len)); insn->type = sibling ? INSN_RETURN : INSN_NOP; + + if (sibling) { + /* + * We've replaced the tail-call JMP insn by two new + * insn: RET; INT3, except we only have a single struct + * insn here. Mark it retpoline_safe to avoid the SLS + * warning, instead of adding another insn. + */ + insn->retpoline_safe = true; + } + return; } @@ -1239,11 +1250,20 @@ static bool same_function(struct instruction *insn1, struct instruction *insn2) return insn1->func->pfunc == insn2->func->pfunc; } -static bool is_first_func_insn(struct instruction *insn) +static bool is_first_func_insn(struct objtool_file *file, struct instruction *insn) { - return insn->offset == insn->func->offset || - (insn->type == INSN_ENDBR && - insn->offset == insn->func->offset + insn->len); + if (insn->offset == insn->func->offset) + return true; + + if (ibt) { + struct instruction *prev = prev_insn_same_sym(file, insn); + + if (prev && prev->type == INSN_ENDBR && + insn->offset == insn->func->offset + prev->len) + return true; + } + + return false; } /* @@ -1327,7 +1347,7 @@ static int add_jump_destinations(struct objtool_file *file) insn->jump_dest->func->pfunc = insn->func; } else if (!same_function(insn, insn->jump_dest) && - is_first_func_insn(insn->jump_dest)) { + is_first_func_insn(file, insn->jump_dest)) { /* internal sibling call (without reloc) */ add_call_dest(file, insn, insn->jump_dest->func, true); } diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index 9c330cdfa973..71ebdf8125de 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -83,7 +83,7 @@ linkperf:perf-buildid-list[1], linkperf:perf-c2c[1], linkperf:perf-config[1], linkperf:perf-data[1], linkperf:perf-diff[1], linkperf:perf-evlist[1], linkperf:perf-ftrace[1], linkperf:perf-help[1], linkperf:perf-inject[1], -linkperf:perf-intel-pt[1], linkperf:perf-kallsyms[1], +linkperf:perf-intel-pt[1], linkperf:perf-iostat[1], linkperf:perf-kallsyms[1], linkperf:perf-kmem[1], linkperf:perf-kvm[1], linkperf:perf-lock[1], linkperf:perf-mem[1], linkperf:perf-probe[1], linkperf:perf-sched[1], linkperf:perf-script[1], linkperf:perf-test[1], diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 96ad944ca6a8..f3bf9297bcc0 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -272,6 +272,9 @@ ifdef PYTHON_CONFIG PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null) FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) + ifeq ($(CC_NO_CLANG), 0) + PYTHON_EMBED_CCOPTS := $(filter-out -ffat-lto-objects, $(PYTHON_EMBED_CCOPTS)) + endif endif FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) @@ -790,6 +793,9 @@ else LDFLAGS += $(PERL_EMBED_LDFLAGS) EXTLIBS += $(PERL_EMBED_LIBADD) CFLAGS += -DHAVE_LIBPERL_SUPPORT + ifeq ($(CC_NO_CLANG), 0) + CFLAGS += -Wno-compound-token-split-by-macro + endif $(call detected,CONFIG_LIBPERL) endif endif diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 86e2e926aa0e..af4d63af8072 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -239,6 +239,12 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, arm_spe_set_timestamp(itr, arm_spe_evsel); } + /* + * Set this only so that perf report knows that SPE generates memory info. It has no effect + * on the opening of the event or the SPE data produced. + */ + evsel__set_sample_bit(arm_spe_evsel, DATA_SRC); + /* Add dummy event to keep tracking */ err = parse_events(evlist, "dummy:u", NULL); if (err) diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 134612bde0cb..4256dc5d6236 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -222,13 +222,20 @@ static void init_fdmaps(struct worker *w, int pct) static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i, j; int ret = 0; + int nrcpus; + size_t size; if (!noaffinity) pthread_attr_init(&thread_attr); + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < nthreads; i++) { struct worker *w = &worker[i]; @@ -252,22 +259,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) init_fdmaps(w, 50); if (!noaffinity) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } attrp = &thread_attr; } ret = pthread_create(&w->thread, attrp, workerfn, (void *)(struct worker *) w); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); if (!noaffinity) pthread_attr_destroy(&thread_attr); diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index 37de970c9743..2728b0140853 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -291,9 +291,11 @@ static void print_summary(void) static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i, j; int ret = 0, events = EPOLLIN; + int nrcpus; + size_t size; if (oneshot) events |= EPOLLONESHOT; @@ -306,6 +308,11 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) if (!noaffinity) pthread_attr_init(&thread_attr); + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < nthreads; i++) { struct worker *w = &worker[i]; @@ -341,22 +348,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) } if (!noaffinity) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } attrp = &thread_attr; } ret = pthread_create(&w->thread, attrp, workerfn, (void *)(struct worker *) w); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); if (!noaffinity) pthread_attr_destroy(&thread_attr); diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index dbcecec4eeda..f05db4cf983d 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -122,12 +122,14 @@ static void print_summary(void) int bench_futex_hash(int argc, const char **argv) { int ret = 0; - cpu_set_t cpuset; + cpu_set_t *cpuset; struct sigaction act; unsigned int i; pthread_attr_t thread_attr; struct worker *worker = NULL; struct perf_cpu_map *cpu; + int nrcpus; + size_t size; argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0); if (argc) { @@ -170,25 +172,35 @@ int bench_futex_hash(int argc, const char **argv) threads_starting = params.nthreads; pthread_attr_init(&thread_attr); gettimeofday(&bench__start, NULL); + + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < params.nthreads; i++) { worker[i].tid = i; worker[i].futex = calloc(params.nfutexes, sizeof(*worker[i].futex)); if (!worker[i].futex) goto errmem; - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); - + } ret = pthread_create(&worker[i].thread, &thread_attr, workerfn, (void *)(struct worker *) &worker[i]); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); pthread_attr_destroy(&thread_attr); pthread_mutex_lock(&thread_lock); diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 6fc9a3d55c1f..0abb3f7ee24f 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -120,11 +120,17 @@ static void *workerfn(void *arg) static void create_threads(struct worker *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < params.nthreads; i++) { worker[i].tid = i; @@ -135,15 +141,20 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr, } else worker[i].futex = &global_futex; - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) + if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } int bench_futex_lock_pi(int argc, const char **argv) diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index 2f59d5d1c509..b6faabfafb8e 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -123,22 +123,33 @@ static void *workerfn(void *arg __maybe_unused) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void toggle_done(int sig __maybe_unused, diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index 861deb934745..e47f46a3a47e 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -144,22 +144,33 @@ static void *blocked_workerfn(void *arg __maybe_unused) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void print_run(struct thread_data *waking_worker, unsigned int run_num) diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index cfda48bef1d7..201a3555f09a 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -97,22 +97,32 @@ static void print_summary(void) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; - + size_t size; + int nrcpus = perf_cpu_map__nr(cpu); threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void toggle_done(int sig __maybe_unused, diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 2f6b67189b42..0170cb0819d6 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -55,6 +55,7 @@ struct cmd_struct { }; static struct cmd_struct commands[] = { + { "archive", NULL, 0 }, { "buildid-cache", cmd_buildid_cache, 0 }, { "buildid-list", cmd_buildid_list, 0 }, { "config", cmd_config, 0 }, @@ -62,6 +63,7 @@ static struct cmd_struct commands[] = { { "diff", cmd_diff, 0 }, { "evlist", cmd_evlist, 0 }, { "help", cmd_help, 0 }, + { "iostat", NULL, 0 }, { "kallsyms", cmd_kallsyms, 0 }, { "list", cmd_list, 0 }, { "record", cmd_record, 0 }, @@ -360,6 +362,8 @@ static void handle_internal_command(int argc, const char **argv) for (i = 0; i < ARRAY_SIZE(commands); i++) { struct cmd_struct *p = commands+i; + if (p->fn == NULL) + continue; if (strcmp(p->cmd, cmd)) continue; exit(run_builtin(p, argc, argv)); @@ -434,7 +438,7 @@ void pthread__unblock_sigwinch(void) static int libperf_print(enum libperf_print_level level, const char *fmt, va_list ap) { - return eprintf(level, verbose, fmt, ap); + return veprintf(level, verbose, fmt, ap); } int main(int argc, const char **argv) diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 2dab2d262060..afdca7f2959f 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -122,7 +122,7 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thr } err = unwind__get_entries(unwind_entry, &cnt, thread, - &sample, MAX_STACK); + &sample, MAX_STACK, false); if (err) pr_debug("unwind failed\n"); else if (cnt != MAX_STACK) { diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index d12d0ad81801..cc6df49a65a1 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -47,6 +47,17 @@ } \ } +static int test__tsc_is_supported(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + if (!TSC_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture\n"); + return TEST_SKIP; + } + + return TEST_OK; +} + /** * test__perf_time_to_tsc - test converting perf time to TSC. * @@ -70,7 +81,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su struct perf_cpu_map *cpus = NULL; struct evlist *evlist = NULL; struct evsel *evsel = NULL; - int err = -1, ret, i; + int err = TEST_FAIL, ret, i; const char *comm1, *comm2; struct perf_tsc_conversion tc; struct perf_event_mmap_page *pc; @@ -79,10 +90,6 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su u64 test_time, comm1_time = 0, comm2_time = 0; struct mmap *md; - if (!TSC_IS_SUPPORTED) { - pr_debug("Test not supported on this architecture"); - return TEST_SKIP; - } threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); @@ -124,8 +131,8 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su ret = perf_read_tsc_conversion(pc, &tc); if (ret) { if (ret == -EOPNOTSUPP) { - fprintf(stderr, " (not supported)"); - return 0; + pr_debug("perf_read_tsc_conversion is not supported in current kernel\n"); + err = TEST_SKIP; } goto out_err; } @@ -191,7 +198,7 @@ next_event: test_tsc >= comm2_tsc) goto out_err; - err = 0; + err = TEST_OK; out_err: evlist__delete(evlist); @@ -200,4 +207,15 @@ out_err: return err; } -DEFINE_SUITE("Convert perf time to TSC", perf_time_to_tsc); +static struct test_case time_to_tsc_tests[] = { + TEST_CASE_REASON("TSC support", tsc_is_supported, + "This architecture does not support"), + TEST_CASE_REASON("Perf time to TSC", perf_time_to_tsc, + "perf_read_tsc_conversion is not supported"), + { .name = NULL, } +}; + +struct test_suite suite__perf_time_to_tsc = { + .desc = "Convert perf time to TSC", + .test_cases = time_to_tsc_tests, +}; diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index e4c641b240df..82cc396ef516 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2047,6 +2047,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) objdump_process.argv = objdump_argv; objdump_process.out = -1; objdump_process.err = -1; + objdump_process.no_stderr = 1; if (start_command(&objdump_process)) { pr_err("Failure starting to run %s\n", command); err = -1; diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c index 2242a885fbd7..4940be4a0569 100644 --- a/tools/perf/util/arm64-frame-pointer-unwind-support.c +++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c @@ -53,7 +53,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0; } - ret = unwind__get_entries(add_entry, &entries, thread, sample, 2); + ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true); sample->user_regs = old_regs; if (ret || entries.length != 2) diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b80048546451..95391236f5f6 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2987,7 +2987,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread, return 0; return unwind__get_entries(unwind_entry, cursor, - thread, sample, max_stack); + thread, sample, max_stack, false); } int thread__resolve_callchain(struct thread *thread, diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 3b8dfe603e50..45a30040ec8d 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -2095,6 +2095,7 @@ prefetch_event(char *buf, u64 head, size_t mmap_size, bool needs_swap, union perf_event *error) { union perf_event *event; + u16 event_size; /* * Ensure we have enough space remaining to read @@ -2107,15 +2108,23 @@ prefetch_event(char *buf, u64 head, size_t mmap_size, if (needs_swap) perf_event_header__bswap(&event->header); - if (head + event->header.size <= mmap_size) + event_size = event->header.size; + if (head + event_size <= mmap_size) return event; /* We're not fetching the event so swap back again */ if (needs_swap) perf_event_header__bswap(&event->header); - pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:" - " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size); + /* Check if the event fits into the next mmapped buf. */ + if (event_size <= mmap_size - head % page_size) { + /* Remap buf and fetch again. */ + return NULL; + } + + /* Invalid input. Event size should never exceed mmap_size. */ + pr_debug("%s: head=%#" PRIx64 " event->header.size=%#x, mmap_size=%#zx:" + " fuzzed or compressed perf.data?\n", __func__, head, event_size, mmap_size); return error; } diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 483f05004e68..c255a2c90cd6 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -1,12 +1,14 @@ -from os import getenv +from os import getenv, path from subprocess import Popen, PIPE from re import sub cc = getenv("CC") cc_is_clang = b"clang version" in Popen([cc.split()[0], "-v"], stderr=PIPE).stderr.readline() +src_feature_tests = getenv('srctree') + '/tools/build/feature' def clang_has_option(option): - return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ] + cc_output = Popen([cc, option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines() + return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o))] == [ ] if cc_is_clang: from distutils.sysconfig import get_config_vars @@ -23,6 +25,8 @@ if cc_is_clang: vars[var] = sub("-fstack-protector-strong", "", vars[var]) if not clang_has_option("-fno-semantic-interposition"): vars[var] = sub("-fno-semantic-interposition", "", vars[var]) + if not clang_has_option("-ffat-lto-objects"): + vars[var] = sub("-ffat-lto-objects", "", vars[var]) from distutils.core import setup, Extension diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index a74b517f7497..94aa40f6e348 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -200,7 +200,8 @@ frame_callback(Dwfl_Frame *state, void *arg) bool isactivation; if (!dwfl_frame_pc(state, &pc, NULL)) { - pr_err("%s", dwfl_errmsg(-1)); + if (!ui->best_effort) + pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } @@ -208,7 +209,8 @@ frame_callback(Dwfl_Frame *state, void *arg) report_module(pc, ui); if (!dwfl_frame_pc(state, &pc, &isactivation)) { - pr_err("%s", dwfl_errmsg(-1)); + if (!ui->best_effort) + pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } @@ -222,7 +224,8 @@ frame_callback(Dwfl_Frame *state, void *arg) int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, - int max_stack) + int max_stack, + bool best_effort) { struct unwind_info *ui, ui_buf = { .sample = data, @@ -231,6 +234,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, .cb = cb, .arg = arg, .max_stack = max_stack, + .best_effort = best_effort }; Dwarf_Word ip; int err = -EINVAL, i; diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h index 0cbd2650e280..8c88bc4f2304 100644 --- a/tools/perf/util/unwind-libdw.h +++ b/tools/perf/util/unwind-libdw.h @@ -20,6 +20,7 @@ struct unwind_info { void *arg; int max_stack; int idx; + bool best_effort; struct unwind_entry entries[]; }; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 71a353349181..41e29fc7648a 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -96,6 +96,7 @@ struct unwind_info { struct perf_sample *sample; struct machine *machine; struct thread *thread; + bool best_effort; }; #define dw_read(ptr, type, end) ({ \ @@ -553,7 +554,8 @@ static int access_reg(unw_addr_space_t __maybe_unused as, ret = perf_reg_value(&val, &ui->sample->user_regs, id); if (ret) { - pr_err("unwind: can't read reg %d\n", regnum); + if (!ui->best_effort) + pr_err("unwind: can't read reg %d\n", regnum); return ret; } @@ -666,7 +668,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, return -1; ret = unw_init_remote(&c, addr_space, ui); - if (ret) + if (ret && !ui->best_effort) display_error(ret); while (!ret && (unw_step(&c) > 0) && i < max_stack) { @@ -704,12 +706,14 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack) + struct perf_sample *data, int max_stack, + bool best_effort) { struct unwind_info ui = { .sample = data, .thread = thread, .machine = thread->maps->machine, + .best_effort = best_effort }; if (!data->user_regs.regs) diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index e89a5479b361..509c287ee762 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -80,9 +80,11 @@ void unwind__finish_access(struct maps *maps) int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack) + struct perf_sample *data, int max_stack, + bool best_effort) { if (thread->maps->unwind_libunwind_ops) - return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack); + return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, + max_stack, best_effort); return 0; } diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index ab8ad469c8de..b2a03fa5289b 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -23,13 +23,19 @@ struct unwind_libunwind_ops { void (*finish_access)(struct maps *maps); int (*get_entries)(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack); + struct perf_sample *data, int max_stack, bool best_effort); }; #ifdef HAVE_DWARF_UNWIND_SUPPORT +/* + * When best_effort is set, don't report errors and fail silently. This could + * be expanded in the future to be more permissive about things other than + * error messages. + */ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack); + struct perf_sample *data, int max_stack, + bool best_effort); /* libunwind specific */ #ifdef HAVE_LIBUNWIND_SUPPORT #ifndef LIBUNWIND__ARCH_REG_ID @@ -65,7 +71,8 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, void *arg __maybe_unused, struct thread *thread __maybe_unused, struct perf_sample *data __maybe_unused, - int max_stack __maybe_unused) + int max_stack __maybe_unused, + bool best_effort __maybe_unused) { return 0; } diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 65dbdda3a054..1da76ccde448 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -1842,7 +1842,7 @@ static int nfit_test_dimm_init(struct nfit_test *t) return 0; } -static void security_init(struct nfit_test *t) +static void nfit_security_init(struct nfit_test *t) { int i; @@ -1938,7 +1938,7 @@ static int nfit_test0_alloc(struct nfit_test *t) if (nfit_test_dimm_init(t)) return -ENOMEM; smart_init(t); - security_init(t); + nfit_security_init(t); return ars_state_init(&t->pdev.dev, &t->ars_state); } diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c index 5aa52cc31dc2..c11832657d2b 100644 --- a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c +++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c @@ -2,6 +2,7 @@ /* Copyright (C) 2021. Huawei Technologies Co., Ltd */ #include <test_progs.h> #include "dummy_st_ops.skel.h" +#include "trace_dummy_st_ops.skel.h" /* Need to keep consistent with definition in include/linux/bpf.h */ struct bpf_dummy_ops_state { @@ -56,6 +57,7 @@ static void test_dummy_init_ptr_arg(void) .ctx_in = args, .ctx_size_in = sizeof(args), ); + struct trace_dummy_st_ops *trace_skel; struct dummy_st_ops *skel; int fd, err; @@ -64,12 +66,33 @@ static void test_dummy_init_ptr_arg(void) return; fd = bpf_program__fd(skel->progs.test_1); + + trace_skel = trace_dummy_st_ops__open(); + if (!ASSERT_OK_PTR(trace_skel, "trace_dummy_st_ops__open")) + goto done; + + err = bpf_program__set_attach_target(trace_skel->progs.fentry_test_1, + fd, "test_1"); + if (!ASSERT_OK(err, "set_attach_target(fentry_test_1)")) + goto done; + + err = trace_dummy_st_ops__load(trace_skel); + if (!ASSERT_OK(err, "load(trace_skel)")) + goto done; + + err = trace_dummy_st_ops__attach(trace_skel); + if (!ASSERT_OK(err, "attach(trace_skel)")) + goto done; + err = bpf_prog_test_run_opts(fd, &attr); ASSERT_OK(err, "test_run"); ASSERT_EQ(in_state.val, 0x5a, "test_ptr_ret"); ASSERT_EQ(attr.retval, exp_retval, "test_ret"); + ASSERT_EQ(trace_skel->bss->val, exp_retval, "fentry_val"); +done: dummy_st_ops__destroy(skel); + trace_dummy_st_ops__destroy(trace_skel); } static void test_dummy_multiple_args(void) diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c index b64df94ec476..db388f593d0a 100644 --- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -367,7 +367,7 @@ static inline int check_array_of_maps(void) VERIFY(check_default(&array_of_maps->map, map)); inner_map = bpf_map_lookup_elem(array_of_maps, &key); - VERIFY(inner_map != 0); + VERIFY(inner_map != NULL); VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES); return 1; @@ -394,7 +394,7 @@ static inline int check_hash_of_maps(void) VERIFY(check_default(&hash_of_maps->map, map)); inner_map = bpf_map_lookup_elem(hash_of_maps, &key); - VERIFY(inner_map != 0); + VERIFY(inner_map != NULL); VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES); return 1; diff --git a/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c b/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c new file mode 100644 index 000000000000..00a4be9d3074 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +int val = 0; + +SEC("fentry/test_1") +int BPF_PROG(fentry_test_1, __u64 *st_ops_ctx) +{ + __u64 state; + + /* Read the traced st_ops arg1 which is a pointer */ + bpf_probe_read_kernel(&state, sizeof(__u64), (void *)st_ops_ctx); + /* Read state->val */ + bpf_probe_read_kernel(&val, sizeof(__u32), (void *)state); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c index b9e991d43155..e7775d3bbe08 100644 --- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c +++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c @@ -18,8 +18,9 @@ #include "bpf_rlimit.h" #include "cgroup_helpers.h" -static int start_server(const struct sockaddr *addr, socklen_t len) +static int start_server(const struct sockaddr *addr, socklen_t len, bool dual) { + int mode = !dual; int fd; fd = socket(addr->sa_family, SOCK_STREAM, 0); @@ -28,6 +29,14 @@ static int start_server(const struct sockaddr *addr, socklen_t len) goto out; } + if (addr->sa_family == AF_INET6) { + if (setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (char *)&mode, + sizeof(mode)) == -1) { + log_err("Failed to set the dual-stack mode"); + goto close_out; + } + } + if (bind(fd, addr, len) == -1) { log_err("Failed to bind server socket"); goto close_out; @@ -47,24 +56,17 @@ out: return fd; } -static int connect_to_server(int server_fd) +static int connect_to_server(const struct sockaddr *addr, socklen_t len) { - struct sockaddr_storage addr; - socklen_t len = sizeof(addr); int fd = -1; - if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { - log_err("Failed to get server addr"); - goto out; - } - - fd = socket(addr.ss_family, SOCK_STREAM, 0); + fd = socket(addr->sa_family, SOCK_STREAM, 0); if (fd == -1) { log_err("Failed to create client socket"); goto out; } - if (connect(fd, (const struct sockaddr *)&addr, len) == -1) { + if (connect(fd, (const struct sockaddr *)addr, len) == -1) { log_err("Fail to connect to server"); goto close_out; } @@ -116,7 +118,8 @@ err: return map_fd; } -static int run_test(int server_fd, int results_fd, bool xdp) +static int run_test(int server_fd, int results_fd, bool xdp, + const struct sockaddr *addr, socklen_t len) { int client = -1, srv_client = -1; int ret = 0; @@ -142,7 +145,7 @@ static int run_test(int server_fd, int results_fd, bool xdp) goto err; } - client = connect_to_server(server_fd); + client = connect_to_server(addr, len); if (client == -1) goto err; @@ -199,12 +202,30 @@ out: return ret; } +static bool get_port(int server_fd, in_port_t *port) +{ + struct sockaddr_in addr; + socklen_t len = sizeof(addr); + + if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { + log_err("Failed to get server addr"); + return false; + } + + /* sin_port and sin6_port are located at the same offset. */ + *port = addr.sin_port; + return true; +} + int main(int argc, char **argv) { struct sockaddr_in addr4; struct sockaddr_in6 addr6; + struct sockaddr_in addr4dual; + struct sockaddr_in6 addr6dual; int server = -1; int server_v6 = -1; + int server_dual = -1; int results = -1; int err = 0; bool xdp; @@ -224,25 +245,43 @@ int main(int argc, char **argv) addr4.sin_family = AF_INET; addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK); addr4.sin_port = 0; + memcpy(&addr4dual, &addr4, sizeof(addr4dual)); memset(&addr6, 0, sizeof(addr6)); addr6.sin6_family = AF_INET6; addr6.sin6_addr = in6addr_loopback; addr6.sin6_port = 0; - server = start_server((const struct sockaddr *)&addr4, sizeof(addr4)); - if (server == -1) + memset(&addr6dual, 0, sizeof(addr6dual)); + addr6dual.sin6_family = AF_INET6; + addr6dual.sin6_addr = in6addr_any; + addr6dual.sin6_port = 0; + + server = start_server((const struct sockaddr *)&addr4, sizeof(addr4), + false); + if (server == -1 || !get_port(server, &addr4.sin_port)) goto err; server_v6 = start_server((const struct sockaddr *)&addr6, - sizeof(addr6)); - if (server_v6 == -1) + sizeof(addr6), false); + if (server_v6 == -1 || !get_port(server_v6, &addr6.sin6_port)) + goto err; + + server_dual = start_server((const struct sockaddr *)&addr6dual, + sizeof(addr6dual), true); + if (server_dual == -1 || !get_port(server_dual, &addr4dual.sin_port)) + goto err; + + if (run_test(server, results, xdp, + (const struct sockaddr *)&addr4, sizeof(addr4))) goto err; - if (run_test(server, results, xdp)) + if (run_test(server_v6, results, xdp, + (const struct sockaddr *)&addr6, sizeof(addr6))) goto err; - if (run_test(server_v6, results, xdp)) + if (run_test(server_dual, results, xdp, + (const struct sockaddr *)&addr4dual, sizeof(addr4dual))) goto err; printf("ok\n"); @@ -252,6 +291,7 @@ err: out: close(server); close(server_v6); + close(server_dual); close(results); return err; } diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 11779405dc80..25f4d54067c0 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -64,6 +64,7 @@ #include <sys/types.h> #include <sys/wait.h> #include <unistd.h> +#include <setjmp.h> #include "kselftest.h" @@ -183,7 +184,10 @@ struct __test_metadata *_metadata, \ struct __fixture_variant_metadata *variant) \ { \ - test_name(_metadata); \ + _metadata->setup_completed = true; \ + if (setjmp(_metadata->env) == 0) \ + test_name(_metadata); \ + __test_check_assert(_metadata); \ } \ static struct __test_metadata _##test_name##_object = \ { .name = #test_name, \ @@ -287,7 +291,9 @@ #define FIXTURE_TEARDOWN(fixture_name) \ void fixture_name##_teardown( \ struct __test_metadata __attribute__((unused)) *_metadata, \ - FIXTURE_DATA(fixture_name) __attribute__((unused)) *self) + FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \ + const FIXTURE_VARIANT(fixture_name) \ + __attribute__((unused)) *variant) /** * FIXTURE_VARIANT() - Optionally called once per fixture @@ -302,9 +308,9 @@ * ... * }; * - * Defines type of constant parameters provided to FIXTURE_SETUP() and TEST_F() - * as *variant*. Variants allow the same tests to be run with different - * arguments. + * Defines type of constant parameters provided to FIXTURE_SETUP(), TEST_F() and + * FIXTURE_TEARDOWN as *variant*. Variants allow the same tests to be run with + * different arguments. */ #define FIXTURE_VARIANT(fixture_name) struct _fixture_variant_##fixture_name @@ -356,10 +362,7 @@ * Defines a test that depends on a fixture (e.g., is part of a test case). * Very similar to TEST() except that *self* is the setup instance of fixture's * datatype exposed for use by the implementation. - * - * Warning: use of ASSERT_* here will skip TEARDOWN. */ -/* TODO(wad) register fixtures on dedicated test lists. */ #define TEST_F(fixture_name, test_name) \ __TEST_F_IMPL(fixture_name, test_name, -1, TEST_TIMEOUT_DEFAULT) @@ -381,12 +384,17 @@ /* fixture data is alloced, setup, and torn down per call. */ \ FIXTURE_DATA(fixture_name) self; \ memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \ - fixture_name##_setup(_metadata, &self, variant->data); \ - /* Let setup failure terminate early. */ \ - if (!_metadata->passed) \ - return; \ - fixture_name##_##test_name(_metadata, &self, variant->data); \ - fixture_name##_teardown(_metadata, &self); \ + if (setjmp(_metadata->env) == 0) { \ + fixture_name##_setup(_metadata, &self, variant->data); \ + /* Let setup failure terminate early. */ \ + if (!_metadata->passed) \ + return; \ + _metadata->setup_completed = true; \ + fixture_name##_##test_name(_metadata, &self, variant->data); \ + } \ + if (_metadata->setup_completed) \ + fixture_name##_teardown(_metadata, &self, variant->data); \ + __test_check_assert(_metadata); \ } \ static struct __test_metadata \ _##fixture_name##_##test_name##_object = { \ @@ -683,7 +691,7 @@ */ #define OPTIONAL_HANDLER(_assert) \ for (; _metadata->trigger; _metadata->trigger = \ - __bail(_assert, _metadata->no_print, _metadata->step)) + __bail(_assert, _metadata)) #define __INC_STEP(_metadata) \ /* Keep "step" below 255 (which is used for "SKIP" reporting). */ \ @@ -830,6 +838,9 @@ struct __test_metadata { bool timed_out; /* did this test timeout instead of exiting? */ __u8 step; bool no_print; /* manual trigger when TH_LOG_STREAM is not available */ + bool aborted; /* stopped test due to failed ASSERT */ + bool setup_completed; /* did setup finish? */ + jmp_buf env; /* for exiting out of test early */ struct __test_results *results; struct __test_metadata *prev, *next; }; @@ -848,16 +859,26 @@ static inline void __register_test(struct __test_metadata *t) __LIST_APPEND(t->fixture->tests, t); } -static inline int __bail(int for_realz, bool no_print, __u8 step) +static inline int __bail(int for_realz, struct __test_metadata *t) { + /* if this is ASSERT, return immediately. */ if (for_realz) { - if (no_print) - _exit(step); - abort(); + t->aborted = true; + longjmp(t->env, 1); } + /* otherwise, end the for loop and continue. */ return 0; } +static inline void __test_check_assert(struct __test_metadata *t) +{ + if (t->aborted) { + if (t->no_print) + _exit(t->step); + abort(); + } +} + struct __test_metadata *__active_test; static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) { diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index d444ee6aa3cb..b3bf5319bb0e 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1208,6 +1208,20 @@ ipv4_fcnal() set +e check_nexthop "dev veth1" "" log_test $? 0 "Nexthops removed on admin down" + + # nexthop route delete warning: route add with nhid and delete + # using device + run_cmd "$IP li set dev veth1 up" + run_cmd "$IP nexthop add id 12 via 172.16.1.3 dev veth1" + out1=`dmesg | grep "WARNING:.*fib_nh_match.*" | wc -l` + run_cmd "$IP route add 172.16.101.1/32 nhid 12" + run_cmd "$IP route delete 172.16.101.1/32 dev veth1" + out2=`dmesg | grep "WARNING:.*fib_nh_match.*" | wc -l` + [ $out1 -eq $out2 ] + rc=$? + log_test $rc 0 "Delete nexthop route warning" + run_cmd "$IP route delete 172.16.101.1/32 nhid 12" + run_cmd "$IP nexthop del id 12" } ipv4_grp_fcnal() diff --git a/tools/testing/selftests/pid_namespace/Makefile b/tools/testing/selftests/pid_namespace/Makefile index dcaefa224ca0..edafaca1aeb3 100644 --- a/tools/testing/selftests/pid_namespace/Makefile +++ b/tools/testing/selftests/pid_namespace/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -g -I../../../../usr/include/ -TEST_GEN_PROGS := regression_enomem +TEST_GEN_PROGS = regression_enomem -include ../lib.mk +LOCAL_HDRS += $(selfdir)/pidfd/pidfd.h -$(OUTPUT)/regression_enomem: regression_enomem.c ../pidfd/pidfd.h +include ../lib.mk diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index 17999e082aa7..070c1c876df1 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -95,7 +95,6 @@ TEST(wait_states) .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, .exit_signal = SIGCHLD, }; - int ret; pid_t pid; siginfo_t info = { .si_signo = 0, diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c index 18a3bde8bc96..28604c9f805c 100644 --- a/tools/testing/selftests/proc/proc-pid-vm.c +++ b/tools/testing/selftests/proc/proc-pid-vm.c @@ -46,6 +46,8 @@ #include <sys/time.h> #include <sys/resource.h> +#include "../kselftest.h" + static inline long sys_execveat(int dirfd, const char *pathname, char **argv, char **envp, int flags) { return syscall(SYS_execveat, dirfd, pathname, argv, envp, flags); @@ -368,7 +370,7 @@ int main(void) }; int i; - for (i = 0; i < sizeof(S)/sizeof(S[0]); i++) { + for (i = 0; i < ARRAY_SIZE(S); i++) { assert(memmem(buf, rv, S[i], strlen(S[i]))); } @@ -417,7 +419,7 @@ int main(void) }; int i; - for (i = 0; i < sizeof(S)/sizeof(S[0]); i++) { + for (i = 0; i < ARRAY_SIZE(S); i++) { assert(memmem(buf, rv, S[i], strlen(S[i]))); } } diff --git a/tools/testing/selftests/vDSO/vdso_test_correctness.c b/tools/testing/selftests/vDSO/vdso_test_correctness.c index c4aea794725a..e691a3cf1491 100644 --- a/tools/testing/selftests/vDSO/vdso_test_correctness.c +++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c @@ -20,6 +20,7 @@ #include <limits.h> #include "vdso_config.h" +#include "../kselftest.h" static const char **name; @@ -306,10 +307,8 @@ static void test_clock_gettime(void) return; } - for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]); - clock++) { + for (int clock = 0; clock < ARRAY_SIZE(clocknames); clock++) test_one_clock_gettime(clock, clocknames[clock]); - } /* Also test some invalid clock ids */ test_one_clock_gettime(-1, "invalid"); @@ -370,10 +369,8 @@ static void test_clock_gettime64(void) return; } - for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]); - clock++) { + for (int clock = 0; clock < ARRAY_SIZE(clocknames); clock++) test_one_clock_gettime64(clock, clocknames[clock]); - } /* Also test some invalid clock ids */ test_one_clock_gettime64(-1, "invalid"); diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 53df7d3893d3..0388c4d60af0 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -92,6 +92,10 @@ warn_32bit_failure: echo "If you are using a Fedora-like distribution, try:"; \ echo ""; \ echo " yum install glibc-devel.*i686"; \ + echo ""; \ + echo "If you are using a SUSE-like distribution, try:"; \ + echo ""; \ + echo " zypper install gcc-32bit glibc-devel-static-32bit"; \ exit 0; endif |