diff options
888 files changed, 20277 insertions, 7985 deletions
diff --git a/Documentation/devicetree/bindings/display/msm/gpu.txt b/Documentation/devicetree/bindings/display/msm/gpu.txt index 67d0a58dbb77..43fac0fe09bb 100644 --- a/Documentation/devicetree/bindings/display/msm/gpu.txt +++ b/Documentation/devicetree/bindings/display/msm/gpu.txt @@ -1,23 +1,19 @@ Qualcomm adreno/snapdragon GPU Required properties: -- compatible: "qcom,adreno-3xx" +- compatible: "qcom,adreno-XYZ.W", "qcom,adreno" + for example: "qcom,adreno-306.0", "qcom,adreno" + Note that you need to list the less specific "qcom,adreno" (since this + is what the device is matched on), in addition to the more specific + with the chip-id. - reg: Physical base address and length of the controller's registers. - interrupts: The interrupt signal from the gpu. - clocks: device clocks See ../clocks/clock-bindings.txt for details. - clock-names: the following clocks are required: - * "core_clk" - * "iface_clk" - * "mem_iface_clk" -- qcom,chipid: gpu chip-id. Note this may become optional for future - devices if we can reliably read the chipid from hw -- qcom,gpu-pwrlevels: list of operating points - - compatible: "qcom,gpu-pwrlevels" - - for each qcom,gpu-pwrlevel: - - qcom,gpu-freq: requested gpu clock speed - - NOTE: downstream android driver defines additional parameters to - configure memory bandwidth scaling per OPP. + * "core" + * "iface" + * "mem_iface" Example: @@ -25,28 +21,18 @@ Example: ... gpu: qcom,kgsl-3d0@4300000 { - compatible = "qcom,adreno-3xx"; + compatible = "qcom,adreno-320.2", "qcom,adreno"; reg = <0x04300000 0x20000>; reg-names = "kgsl_3d0_reg_memory"; interrupts = <GIC_SPI 80 0>; interrupt-names = "kgsl_3d0_irq"; clock-names = - "core_clk", - "iface_clk", - "mem_iface_clk"; + "core", + "iface", + "mem_iface"; clocks = <&mmcc GFX3D_CLK>, <&mmcc GFX3D_AHB_CLK>, <&mmcc MMSS_IMEM_AHB_CLK>; - qcom,chipid = <0x03020100>; - qcom,gpu-pwrlevels { - compatible = "qcom,gpu-pwrlevels"; - qcom,gpu-pwrlevel@0 { - qcom,gpu-freq = <450000000>; - }; - qcom,gpu-pwrlevel@1 { - qcom,gpu-freq = <27000000>; - }; - }; }; }; diff --git a/Documentation/devicetree/bindings/display/multi-inno,mi0283qt.txt b/Documentation/devicetree/bindings/display/multi-inno,mi0283qt.txt new file mode 100644 index 000000000000..eed48c3d4875 --- /dev/null +++ b/Documentation/devicetree/bindings/display/multi-inno,mi0283qt.txt @@ -0,0 +1,27 @@ +Multi-Inno MI0283QT display panel + +Required properties: +- compatible: "multi-inno,mi0283qt". + +The node for this driver must be a child node of a SPI controller, hence +all mandatory properties described in ../spi/spi-bus.txt must be specified. + +Optional properties: +- dc-gpios: D/C pin. The presence/absence of this GPIO determines + the panel interface mode (IM[3:0] pins): + - present: IM=x110 4-wire 8-bit data serial interface + - absent: IM=x101 3-wire 9-bit data serial interface +- reset-gpios: Reset pin +- power-supply: A regulator node for the supply voltage. +- backlight: phandle of the backlight device attached to the panel +- rotation: panel rotation in degrees counter clockwise (0,90,180,270) + +Example: + mi0283qt@0{ + compatible = "multi-inno,mi0283qt"; + reg = <0>; + spi-max-frequency = <32000000>; + rotation = <90>; + dc-gpios = <&gpio 25 0>; + backlight = <&backlight>; + }; diff --git a/Documentation/devicetree/bindings/display/panel/boe,nv101wxmn51.txt b/Documentation/devicetree/bindings/display/panel/boe,nv101wxmn51.txt new file mode 100644 index 000000000000..b258d6a91ec6 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/boe,nv101wxmn51.txt @@ -0,0 +1,7 @@ +BOE OPTOELECTRONICS TECHNOLOGY 10.1" WXGA TFT LCD panel + +Required properties: +- compatible: should be "boe,nv101wxmn51" + +This binding is compatible with the simple-panel binding, which is specified +in simple-panel.txt in this directory. diff --git a/Documentation/devicetree/bindings/display/panel/netron-dy,e231732.txt b/Documentation/devicetree/bindings/display/panel/netron-dy,e231732.txt new file mode 100644 index 000000000000..c6d06b5eab51 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/netron-dy,e231732.txt @@ -0,0 +1,7 @@ +Netron-DY E231732 7.0" WSVGA TFT LCD panel + +Required properties: +- compatible: should be "netron-dy,e231732" + +This binding is compatible with the simple-panel binding, which is specified +in simple-panel.txt in this directory. diff --git a/Documentation/devicetree/bindings/display/panel/panel.txt b/Documentation/devicetree/bindings/display/panel/panel.txt new file mode 100644 index 000000000000..e2e6867852b8 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/panel.txt @@ -0,0 +1,4 @@ +Common display properties +------------------------- + +- rotation: Display rotation in degrees counter clockwise (0,90,180,270) diff --git a/Documentation/devicetree/bindings/display/panel/tianma,tm070jdhg30.txt b/Documentation/devicetree/bindings/display/panel/tianma,tm070jdhg30.txt new file mode 100644 index 000000000000..eb9501a82e25 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/tianma,tm070jdhg30.txt @@ -0,0 +1,7 @@ +Tianma Micro-electronics TM070JDHG30 7.0" WXGA TFT LCD panel + +Required properties: +- compatible: should be "tianma,tm070jdhg30" + +This binding is compatible with the simple-panel binding, which is specified +in simple-panel.txt in this directory. diff --git a/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt index 0dcb7c7d3e40..944657684d73 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt @@ -15,6 +15,9 @@ Properties: Second cell specifies the irq distribution mode to cores 0=Round Robin; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3 + The second cell in interrupts property is deprecated and may be ignored by + the kernel. + intc accessed via the special ARC AUX register interface, hence "reg" property is not specified. diff --git a/Documentation/devicetree/bindings/net/mediatek-net.txt b/Documentation/devicetree/bindings/net/mediatek-net.txt index c010fafc66a8..c7194e87d5f4 100644 --- a/Documentation/devicetree/bindings/net/mediatek-net.txt +++ b/Documentation/devicetree/bindings/net/mediatek-net.txt @@ -7,7 +7,7 @@ have dual GMAC each represented by a child node.. * Ethernet controller node Required properties: -- compatible: Should be "mediatek,mt7623-eth" +- compatible: Should be "mediatek,mt2701-eth" - reg: Address and length of the register set for the device - interrupts: Should contain the three frame engines interrupts in numeric order. These are fe_int0, fe_int1 and fe_int2. diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt index ff1bc4b1bb3b..fb5056b22685 100644 --- a/Documentation/devicetree/bindings/net/phy.txt +++ b/Documentation/devicetree/bindings/net/phy.txt @@ -19,8 +19,9 @@ Optional Properties: specifications. If neither of these are specified, the default is to assume clause 22. - If the phy's identifier is known then the list may contain an entry - of the form: "ethernet-phy-idAAAA.BBBB" where + If the PHY reports an incorrect ID (or none at all) then the + "compatible" list may contain an entry with the correct PHY ID in the + form: "ethernet-phy-idAAAA.BBBB" where AAAA - The value of the 16 bit Phy Identifier 1 register as 4 hex digits. This is the chip vendor OUI bits 3:18 BBBB - The value of the 16 bit Phy Identifier 2 register as diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index 16d3b5e7f5d1..f98498df2365 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -187,6 +187,7 @@ mpl MPL AG mqmaker mqmaker Inc. msi Micro-Star International Co. Ltd. mti Imagination Technologies Ltd. (formerly MIPS Technologies Inc.) +multi-inno Multi-Inno Technology Co.,Ltd mundoreader Mundo Reader S.L. murata Murata Manufacturing Co., Ltd. mxicy Macronix International Co., Ltd. @@ -196,6 +197,7 @@ nec NEC LCD Technologies, Ltd. neonode Neonode Inc. netgear NETGEAR netlogic Broadcom Corporation (formerly NetLogic Microsystems) +netron-dy Netron DY netxeon Shenzhen Netxeon Technology CO., LTD nexbox Nexbox newhaven Newhaven Display International @@ -296,6 +298,7 @@ technologic Technologic Systems terasic Terasic Inc. thine THine Electronics, Inc. ti Texas Instruments +tianma Tianma Micro-electronics Co., Ltd. tlm Trusted Logic Mobility topeet Topeet toradex Toradex AG diff --git a/Documentation/gpu/index.rst b/Documentation/gpu/index.rst index c9b08b02f57c..70a91b372b21 100644 --- a/Documentation/gpu/index.rst +++ b/Documentation/gpu/index.rst @@ -11,6 +11,7 @@ Linux GPU Driver Developer's Guide drm-kms-helpers drm-uapi i915 + tinydrm vga-switcheroo vgaarbiter todo diff --git a/Documentation/gpu/tinydrm.rst b/Documentation/gpu/tinydrm.rst new file mode 100644 index 000000000000..a913644bfc19 --- /dev/null +++ b/Documentation/gpu/tinydrm.rst @@ -0,0 +1,42 @@ +========================== +drm/tinydrm Driver library +========================== + +.. kernel-doc:: drivers/gpu/drm/tinydrm/core/tinydrm-core.c + :doc: overview + +Core functionality +================== + +.. kernel-doc:: drivers/gpu/drm/tinydrm/core/tinydrm-core.c + :doc: core + +.. kernel-doc:: include/drm/tinydrm/tinydrm.h + :internal: + +.. kernel-doc:: drivers/gpu/drm/tinydrm/core/tinydrm-core.c + :export: + +.. kernel-doc:: drivers/gpu/drm/tinydrm/core/tinydrm-pipe.c + :export: + +Additional helpers +================== + +.. kernel-doc:: include/drm/tinydrm/tinydrm-helpers.h + :internal: + +.. kernel-doc:: drivers/gpu/drm/tinydrm/core/tinydrm-helpers.c + :export: + +MIPI DBI Compatible Controllers +=============================== + +.. kernel-doc:: drivers/gpu/drm/tinydrm/mipi-dbi.c + :doc: overview + +.. kernel-doc:: include/drm/tinydrm/mipi-dbi.h + :internal: + +.. kernel-doc:: drivers/gpu/drm/tinydrm/mipi-dbi.c + :export: diff --git a/Documentation/media/uapi/cec/cec-func-close.rst b/Documentation/media/uapi/cec/cec-func-close.rst index 8267c31b317d..895d9c2d1c04 100644 --- a/Documentation/media/uapi/cec/cec-func-close.rst +++ b/Documentation/media/uapi/cec/cec-func-close.rst @@ -33,11 +33,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - Closes the cec device. Resources associated with the file descriptor are freed. The device configuration remain unchanged. diff --git a/Documentation/media/uapi/cec/cec-func-ioctl.rst b/Documentation/media/uapi/cec/cec-func-ioctl.rst index 9e8dbb118d6a..7dcfd178fb24 100644 --- a/Documentation/media/uapi/cec/cec-func-ioctl.rst +++ b/Documentation/media/uapi/cec/cec-func-ioctl.rst @@ -39,11 +39,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - The :c:func:`ioctl()` function manipulates cec device parameters. The argument ``fd`` must be an open file descriptor. diff --git a/Documentation/media/uapi/cec/cec-func-open.rst b/Documentation/media/uapi/cec/cec-func-open.rst index af3f5b5c24c6..0304388cd159 100644 --- a/Documentation/media/uapi/cec/cec-func-open.rst +++ b/Documentation/media/uapi/cec/cec-func-open.rst @@ -46,11 +46,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - To open a cec device applications call :c:func:`open()` with the desired device name. The function has no side effects; the device configuration remain unchanged. diff --git a/Documentation/media/uapi/cec/cec-func-poll.rst b/Documentation/media/uapi/cec/cec-func-poll.rst index cfb73e6027a5..6a863cfda6e0 100644 --- a/Documentation/media/uapi/cec/cec-func-poll.rst +++ b/Documentation/media/uapi/cec/cec-func-poll.rst @@ -39,11 +39,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - With the :c:func:`poll()` function applications can wait for CEC events. diff --git a/Documentation/media/uapi/cec/cec-intro.rst b/Documentation/media/uapi/cec/cec-intro.rst index 4a19ea5323a9..07ee2b8f89d6 100644 --- a/Documentation/media/uapi/cec/cec-intro.rst +++ b/Documentation/media/uapi/cec/cec-intro.rst @@ -3,11 +3,6 @@ Introduction ============ -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - HDMI connectors provide a single pin for use by the Consumer Electronics Control protocol. This protocol allows different devices connected by an HDMI cable to communicate. The protocol for CEC version 1.4 is defined @@ -31,3 +26,15 @@ control just the CEC pin. Drivers that support CEC will create a CEC device node (/dev/cecX) to give userspace access to the CEC adapter. The :ref:`CEC_ADAP_G_CAPS` ioctl will tell userspace what it is allowed to do. + +In order to check the support and test it, it is suggested to download +the `v4l-utils <https://git.linuxtv.org/v4l-utils.git/>`_ package. It +provides three tools to handle CEC: + +- cec-ctl: the Swiss army knife of CEC. Allows you to configure, transmit + and monitor CEC messages. + +- cec-compliance: does a CEC compliance test of a remote CEC device to + determine how compliant the CEC implementation is. + +- cec-follower: emulates a CEC follower. diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst index 2b0ddb14b280..a0e961f11017 100644 --- a/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst +++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst @@ -29,11 +29,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - All cec devices must support :ref:`ioctl CEC_ADAP_G_CAPS <CEC_ADAP_G_CAPS>`. To query device information, applications call the ioctl with a pointer to a struct :c:type:`cec_caps`. The driver fills the structure and diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst index b878637e91b3..09f09bbe28d4 100644 --- a/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst +++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst @@ -35,11 +35,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - To query the current CEC logical addresses, applications call :ref:`ioctl CEC_ADAP_G_LOG_ADDRS <CEC_ADAP_G_LOG_ADDRS>` with a pointer to a struct :c:type:`cec_log_addrs` where the driver stores the logical addresses. diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst index 3357deb43c85..a3cdc75cec3e 100644 --- a/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst +++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst @@ -35,11 +35,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - To query the current physical address applications call :ref:`ioctl CEC_ADAP_G_PHYS_ADDR <CEC_ADAP_G_PHYS_ADDR>` with a pointer to a __u16 where the driver stores the physical address. diff --git a/Documentation/media/uapi/cec/cec-ioc-dqevent.rst b/Documentation/media/uapi/cec/cec-ioc-dqevent.rst index e256c6605de7..6e589a1fae17 100644 --- a/Documentation/media/uapi/cec/cec-ioc-dqevent.rst +++ b/Documentation/media/uapi/cec/cec-ioc-dqevent.rst @@ -30,11 +30,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - CEC devices can send asynchronous events. These can be retrieved by calling :c:func:`CEC_DQEVENT`. If the file descriptor is in non-blocking mode and no event is pending, then it will return -1 and diff --git a/Documentation/media/uapi/cec/cec-ioc-g-mode.rst b/Documentation/media/uapi/cec/cec-ioc-g-mode.rst index 4f5818b9d277..e4ded9df0a84 100644 --- a/Documentation/media/uapi/cec/cec-ioc-g-mode.rst +++ b/Documentation/media/uapi/cec/cec-ioc-g-mode.rst @@ -31,11 +31,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - By default any filehandle can use :ref:`CEC_TRANSMIT`, but in order to prevent applications from stepping on each others toes it must be possible to obtain exclusive access to the CEC adapter. This ioctl sets the diff --git a/Documentation/media/uapi/cec/cec-ioc-receive.rst b/Documentation/media/uapi/cec/cec-ioc-receive.rst index bdf015b1d1dc..dc2adb391c0a 100644 --- a/Documentation/media/uapi/cec/cec-ioc-receive.rst +++ b/Documentation/media/uapi/cec/cec-ioc-receive.rst @@ -34,11 +34,6 @@ Arguments Description =========== -.. note:: - - This documents the proposed CEC API. This API is not yet finalized - and is currently only available as a staging kernel module. - To receive a CEC message the application has to fill in the ``timeout`` field of struct :c:type:`cec_msg` and pass it to :ref:`ioctl CEC_RECEIVE <CEC_RECEIVE>`. diff --git a/Documentation/power/states.txt b/Documentation/power/states.txt index 8a39ce45d8a0..008ecb588317 100644 --- a/Documentation/power/states.txt +++ b/Documentation/power/states.txt @@ -35,9 +35,7 @@ only one way to cause the system to go into the Suspend-To-RAM state (write The default suspend mode (ie. the one to be used without writing anything into /sys/power/mem_sleep) is either "deep" (if Suspend-To-RAM is supported) or "s2idle", but it can be overridden by the value of the "mem_sleep_default" -parameter in the kernel command line. On some ACPI-based systems, depending on -the information in the FADT, the default may be "s2idle" even if Suspend-To-RAM -is supported. +parameter in the kernel command line. The properties of all of the sleep states are described below. diff --git a/MAINTAINERS b/MAINTAINERS index adfc60d9c456..706ba94dcae0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1091,7 +1091,7 @@ F: arch/arm/boot/dts/aspeed-* F: drivers/*/*aspeed* ARM/ATMEL AT91RM9200, AT91SAM9 AND SAMA5 SOC SUPPORT -M: Nicolas Ferre <nicolas.ferre@atmel.com> +M: Nicolas Ferre <nicolas.ferre@microchip.com> M: Alexandre Belloni <alexandre.belloni@free-electrons.com> M: Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -1773,7 +1773,7 @@ F: drivers/soc/renesas/ F: include/linux/soc/renesas/ ARM/SOCFPGA ARCHITECTURE -M: Dinh Nguyen <dinguyen@opensource.altera.com> +M: Dinh Nguyen <dinguyen@kernel.org> S: Maintained F: arch/arm/mach-socfpga/ F: arch/arm/boot/dts/socfpga* @@ -1783,7 +1783,7 @@ W: http://www.rocketboards.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/dinguyen/linux.git ARM/SOCFPGA CLOCK FRAMEWORK SUPPORT -M: Dinh Nguyen <dinguyen@opensource.altera.com> +M: Dinh Nguyen <dinguyen@kernel.org> S: Maintained F: drivers/clk/socfpga/ @@ -2175,56 +2175,56 @@ F: include/linux/atm* F: include/uapi/linux/atm* ATMEL AT91 / AT32 MCI DRIVER -M: Ludovic Desroches <ludovic.desroches@atmel.com> +M: Ludovic Desroches <ludovic.desroches@microchip.com> S: Maintained F: drivers/mmc/host/atmel-mci.c ATMEL AT91 SAMA5D2-Compatible Shutdown Controller -M: Nicolas Ferre <nicolas.ferre@atmel.com> +M: Nicolas Ferre <nicolas.ferre@microchip.com> S: Supported F: drivers/power/reset/at91-sama5d2_shdwc.c ATMEL SAMA5D2 ADC DRIVER -M: Ludovic Desroches <ludovic.desroches@atmel.com> +M: Ludovic Desroches <ludovic.desroches@microchip.com> L: linux-iio@vger.kernel.org S: Supported F: drivers/iio/adc/at91-sama5d2_adc.c ATMEL Audio ALSA driver -M: Nicolas Ferre <nicolas.ferre@atmel.com> +M: Nicolas Ferre <nicolas.ferre@microchip.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported F: sound/soc/atmel ATMEL XDMA DRIVER -M: Ludovic Desroches <ludovic.desroches@atmel.com> +M: Ludovic Desroches <ludovic.desroches@microchip.com> L: linux-arm-kernel@lists.infradead.org L: dmaengine@vger.kernel.org S: Supported F: drivers/dma/at_xdmac.c ATMEL I2C DRIVER -M: Ludovic Desroches <ludovic.desroches@atmel.com> +M: Ludovic Desroches <ludovic.desroches@microchip.com> L: linux-i2c@vger.kernel.org S: Supported F: drivers/i2c/busses/i2c-at91.c ATMEL ISI DRIVER -M: Ludovic Desroches <ludovic.desroches@atmel.com> +M: Ludovic Desroches <ludovic.desroches@microchip.com> L: linux-media@vger.kernel.org S: Supported F: drivers/media/platform/soc_camera/atmel-isi.c F: include/media/atmel-isi.h ATMEL LCDFB DRIVER -M: Nicolas Ferre <nicolas.ferre@atmel.com> +M: Nicolas Ferre <nicolas.ferre@microchip.com> L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/fbdev/atmel_lcdfb.c F: include/video/atmel_lcdc.h ATMEL MACB ETHERNET DRIVER -M: Nicolas Ferre <nicolas.ferre@atmel.com> +M: Nicolas Ferre <nicolas.ferre@microchip.com> S: Supported F: drivers/net/ethernet/cadence/ @@ -2236,32 +2236,32 @@ S: Supported F: drivers/mtd/nand/atmel_nand* ATMEL SDMMC DRIVER -M: Ludovic Desroches <ludovic.desroches@atmel.com> +M: Ludovic Desroches <ludovic.desroches@microchip.com> L: linux-mmc@vger.kernel.org S: Supported F: drivers/mmc/host/sdhci-of-at91.c ATMEL SPI DRIVER -M: Nicolas Ferre <nicolas.ferre@atmel.com> +M: Nicolas Ferre <nicolas.ferre@microchip.com> S: Supported F: drivers/spi/spi-atmel.* ATMEL SSC DRIVER -M: Nicolas Ferre <nicolas.ferre@atmel.com> +M: Nicolas Ferre <nicolas.ferre@microchip.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported F: drivers/misc/atmel-ssc.c F: include/linux/atmel-ssc.h ATMEL Timer Counter (TC) AND CLOCKSOURCE DRIVERS -M: Nicolas Ferre <nicolas.ferre@atmel.com> +M: Nicolas Ferre <nicolas.ferre@microchip.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported F: drivers/misc/atmel_tclib.c F: drivers/clocksource/tcb_clksrc.c ATMEL USBA UDC DRIVER -M: Nicolas Ferre <nicolas.ferre@atmel.com> +M: Nicolas Ferre <nicolas.ferre@microchip.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported F: drivers/usb/gadget/udc/atmel_usba_udc.* @@ -3567,7 +3567,7 @@ F: drivers/infiniband/hw/cxgb3/ F: include/uapi/rdma/cxgb3-abi.h CXGB4 ETHERNET DRIVER (CXGB4) -M: Hariprasad S <hariprasad@chelsio.com> +M: Ganesh Goudar <ganeshgr@chelsio.com> L: netdev@vger.kernel.org W: http://www.chelsio.com S: Supported @@ -4154,7 +4154,7 @@ F: Documentation/gpu/i915.rst INTEL GVT-g DRIVERS (Intel GPU Virtualization) M: Zhenyu Wang <zhenyuw@linux.intel.com> M: Zhi Wang <zhi.a.wang@intel.com> -L: igvt-g-dev@lists.01.org +L: intel-gvt-dev@lists.freedesktop.org L: intel-gfx@lists.freedesktop.org W: https://01.org/igvt-g T: git https://github.com/01org/gvt-linux.git @@ -4245,6 +4245,12 @@ S: Supported F: drivers/gpu/drm/mediatek/ F: Documentation/devicetree/bindings/display/mediatek/ +DRM DRIVER FOR MI0283QT +M: Noralf Trønnes <noralf@tronnes.org> +S: Maintained +F: drivers/gpu/drm/tinydrm/mi0283qt.c +F: Documentation/devicetree/bindings/display/multi-inno,mi0283qt.txt + DRM DRIVER FOR MSM ADRENO GPU M: Rob Clark <robdclark@gmail.com> L: linux-arm-msm@vger.kernel.org @@ -9737,7 +9743,7 @@ S: Maintained F: drivers/pinctrl/pinctrl-at91.* PIN CONTROLLER - ATMEL AT91 PIO4 -M: Ludovic Desroches <ludovic.desroches@atmel.com> +M: Ludovic Desroches <ludovic.desroches@microchip.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-gpio@vger.kernel.org S: Supported @@ -10196,7 +10202,6 @@ F: drivers/media/tuners/qt1010* QUALCOMM ATHEROS ATH9K WIRELESS DRIVER M: QCA ath9k Development <ath9k-devel@qca.qualcomm.com> L: linux-wireless@vger.kernel.org -L: ath9k-devel@lists.ath9k.org W: http://wireless.kernel.org/en/users/Drivers/ath9k S: Supported F: drivers/net/wireless/ath/ath9k/ @@ -13067,7 +13072,7 @@ F: drivers/input/serio/userio.c F: include/uapi/linux/userio.h VIRTIO CONSOLE DRIVER -M: Amit Shah <amit.shah@redhat.com> +M: Amit Shah <amit@kernel.org> L: virtualization@lists.linux-foundation.org S: Maintained F: drivers/char/virtio_console.c @@ -1,8 +1,8 @@ VERSION = 4 PATCHLEVEL = 10 SUBLEVEL = 0 -EXTRAVERSION = -rc5 -NAME = Anniversary Edition +EXTRAVERSION = -rc8 +NAME = Fearless Coyote # *DOCUMENTATION* # To see a list of typical targets execute "make help" @@ -797,7 +797,7 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=incompatible-pointer-types) KBUILD_ARFLAGS := $(call ar-option,D) # check for 'asm goto' -ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y) +ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y) KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO endif diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h index a36e8601114d..d5da2115d78a 100644 --- a/arch/arc/include/asm/delay.h +++ b/arch/arc/include/asm/delay.h @@ -26,7 +26,9 @@ static inline void __delay(unsigned long loops) " lp 1f \n" " nop \n" "1: \n" - : : "r"(loops)); + : + : "r"(loops) + : "lp_count"); } extern void __bad_udelay(void); diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 689dd867fdff..8b90d25a15cc 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -71,14 +71,14 @@ ENTRY(stext) GET_CPU_ID r5 cmp r5, 0 mov.nz r0, r5 -#ifdef CONFIG_ARC_SMP_HALT_ON_RESET - ; Non-Master can proceed as system would be booted sufficiently - jnz first_lines_of_secondary -#else + bz .Lmaster_proceed + ; Non-Masters wait for Master to boot enough and bring them up - jnz arc_platform_smp_wait_to_boot -#endif - ; Master falls thru + ; when they resume, tail-call to entry point + mov blink, @first_lines_of_secondary + j arc_platform_smp_wait_to_boot + +.Lmaster_proceed: #endif ; Clear BSS before updating any globals diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 9274f8ade8c7..9f6b68fd4f3b 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -93,11 +93,10 @@ static void mcip_probe_n_setup(void) READ_BCR(ARC_REG_MCIP_BCR, mp); sprintf(smp_cpuinfo_buf, - "Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s%s\n", + "Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s\n", mp.ver, mp.num_cores, IS_AVAIL1(mp.ipi, "IPI "), IS_AVAIL1(mp.idu, "IDU "), - IS_AVAIL1(mp.llm, "LLM "), IS_AVAIL1(mp.dbg, "DEBUG "), IS_AVAIL1(mp.gfrc, "GFRC")); @@ -175,7 +174,6 @@ static void idu_irq_unmask(struct irq_data *data) raw_spin_unlock_irqrestore(&mcip_lock, flags); } -#ifdef CONFIG_SMP static int idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask, bool force) @@ -205,12 +203,27 @@ idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask, return IRQ_SET_MASK_OK; } -#endif + +static void idu_irq_enable(struct irq_data *data) +{ + /* + * By default send all common interrupts to all available online CPUs. + * The affinity of common interrupts in IDU must be set manually since + * in some cases the kernel will not call irq_set_affinity() by itself: + * 1. When the kernel is not configured with support of SMP. + * 2. When the kernel is configured with support of SMP but upper + * interrupt controllers does not support setting of the affinity + * and cannot propagate it to IDU. + */ + idu_irq_set_affinity(data, cpu_online_mask, false); + idu_irq_unmask(data); +} static struct irq_chip idu_irq_chip = { .name = "MCIP IDU Intc", .irq_mask = idu_irq_mask, .irq_unmask = idu_irq_unmask, + .irq_enable = idu_irq_enable, #ifdef CONFIG_SMP .irq_set_affinity = idu_irq_set_affinity, #endif @@ -243,36 +256,14 @@ static int idu_irq_xlate(struct irq_domain *d, struct device_node *n, const u32 *intspec, unsigned int intsize, irq_hw_number_t *out_hwirq, unsigned int *out_type) { - irq_hw_number_t hwirq = *out_hwirq = intspec[0]; - int distri = intspec[1]; - unsigned long flags; - + /* + * Ignore value of interrupt distribution mode for common interrupts in + * IDU which resides in intspec[1] since setting an affinity using value + * from Device Tree is deprecated in ARC. + */ + *out_hwirq = intspec[0]; *out_type = IRQ_TYPE_NONE; - /* XXX: validate distribution scheme again online cpu mask */ - if (distri == 0) { - /* 0 - Round Robin to all cpus, otherwise 1 bit per core */ - raw_spin_lock_irqsave(&mcip_lock, flags); - idu_set_dest(hwirq, BIT(num_online_cpus()) - 1); - idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR); - raw_spin_unlock_irqrestore(&mcip_lock, flags); - } else { - /* - * DEST based distribution for Level Triggered intr can only - * have 1 CPU, so generalize it to always contain 1 cpu - */ - int cpu = ffs(distri); - - if (cpu != fls(distri)) - pr_warn("IDU irq %lx distri mode set to cpu %x\n", - hwirq, cpu); - - raw_spin_lock_irqsave(&mcip_lock, flags); - idu_set_dest(hwirq, cpu); - idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_DEST); - raw_spin_unlock_irqrestore(&mcip_lock, flags); - } - return 0; } diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 88674d972c9d..2afbafadb6ab 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -90,22 +90,37 @@ void __init smp_cpus_done(unsigned int max_cpus) */ static volatile int wake_flag; +#ifdef CONFIG_ISA_ARCOMPACT + +#define __boot_read(f) f +#define __boot_write(f, v) f = v + +#else + +#define __boot_read(f) arc_read_uncached_32(&f) +#define __boot_write(f, v) arc_write_uncached_32(&f, v) + +#endif + static void arc_default_smp_cpu_kick(int cpu, unsigned long pc) { BUG_ON(cpu == 0); - wake_flag = cpu; + + __boot_write(wake_flag, cpu); } void arc_platform_smp_wait_to_boot(int cpu) { - while (wake_flag != cpu) + /* for halt-on-reset, we've waited already */ + if (IS_ENABLED(CONFIG_ARC_SMP_HALT_ON_RESET)) + return; + + while (__boot_read(wake_flag) != cpu) ; - wake_flag = 0; - __asm__ __volatile__("j @first_lines_of_secondary \n"); + __boot_write(wake_flag, 0); } - const char *arc_platform_smp_cpuinfo(void) { return plat_smp_ops.info ? : ""; diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index abd961f3e763..5f69c3bd59bb 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -241,8 +241,9 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, if (state.fault) goto fault; + /* clear any remanants of delay slot */ if (delay_mode(regs)) { - regs->ret = regs->bta; + regs->ret = regs->bta & ~1U; regs->status32 &= ~STATUS_DE_MASK; } else { regs->ret += state.instr_len; diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index f10fe8526239..01d178a2009f 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -617,7 +617,7 @@ dtb-$(CONFIG_ARCH_ORION5X) += \ orion5x-lacie-ethernet-disk-mini-v2.dtb \ orion5x-linkstation-lsgl.dtb \ orion5x-linkstation-lswtgl.dtb \ - orion5x-lschl.dtb \ + orion5x-linkstation-lschl.dtb \ orion5x-lswsgl.dtb \ orion5x-maxtor-shared-storage-2.dtb \ orion5x-netgear-wnr854t.dtb \ diff --git a/arch/arm/boot/dts/imx1.dtsi b/arch/arm/boot/dts/imx1.dtsi index b792eee3899b..2ee40bc9ec21 100644 --- a/arch/arm/boot/dts/imx1.dtsi +++ b/arch/arm/boot/dts/imx1.dtsi @@ -18,6 +18,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { gpio0 = &gpio1; diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi index ac2a9da62b6c..43ccbbf754a3 100644 --- a/arch/arm/boot/dts/imx23.dtsi +++ b/arch/arm/boot/dts/imx23.dtsi @@ -16,6 +16,14 @@ #size-cells = <1>; interrupt-parent = <&icoll>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { gpio0 = &gpio0; diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi index 831d09a28155..acd475659156 100644 --- a/arch/arm/boot/dts/imx25.dtsi +++ b/arch/arm/boot/dts/imx25.dtsi @@ -14,6 +14,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi index 9d8b5969ee3b..b397384248f4 100644 --- a/arch/arm/boot/dts/imx27.dtsi +++ b/arch/arm/boot/dts/imx27.dtsi @@ -19,6 +19,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi index 3aabf65a6a52..d6a2190b60ef 100644 --- a/arch/arm/boot/dts/imx28.dtsi +++ b/arch/arm/boot/dts/imx28.dtsi @@ -17,6 +17,14 @@ #size-cells = <1>; interrupt-parent = <&icoll>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &mac0; diff --git a/arch/arm/boot/dts/imx31.dtsi b/arch/arm/boot/dts/imx31.dtsi index 85cd8be22f71..23b0d2cf9acd 100644 --- a/arch/arm/boot/dts/imx31.dtsi +++ b/arch/arm/boot/dts/imx31.dtsi @@ -12,6 +12,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { serial0 = &uart1; diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi index 9f40e6229189..d0496c65cea2 100644 --- a/arch/arm/boot/dts/imx35.dtsi +++ b/arch/arm/boot/dts/imx35.dtsi @@ -13,6 +13,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx50.dtsi b/arch/arm/boot/dts/imx50.dtsi index fe0221e4cbf7..ceae909e2201 100644 --- a/arch/arm/boot/dts/imx50.dtsi +++ b/arch/arm/boot/dts/imx50.dtsi @@ -17,6 +17,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx51.dtsi b/arch/arm/boot/dts/imx51.dtsi index 33526cade735..1ee1d542d9ad 100644 --- a/arch/arm/boot/dts/imx51.dtsi +++ b/arch/arm/boot/dts/imx51.dtsi @@ -19,6 +19,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi index ca51dc03e327..2e516f4985e4 100644 --- a/arch/arm/boot/dts/imx53.dtsi +++ b/arch/arm/boot/dts/imx53.dtsi @@ -19,6 +19,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx6dl.dtsi b/arch/arm/boot/dts/imx6dl.dtsi index 1ade1951e620..7aa120fbdc71 100644 --- a/arch/arm/boot/dts/imx6dl.dtsi +++ b/arch/arm/boot/dts/imx6dl.dtsi @@ -137,7 +137,7 @@ &gpio4 { gpio-ranges = <&iomuxc 5 136 1>, <&iomuxc 6 145 1>, <&iomuxc 7 150 1>, <&iomuxc 8 146 1>, <&iomuxc 9 151 1>, <&iomuxc 10 147 1>, - <&iomuxc 11 151 1>, <&iomuxc 12 148 1>, <&iomuxc 13 153 1>, + <&iomuxc 11 152 1>, <&iomuxc 12 148 1>, <&iomuxc 13 153 1>, <&iomuxc 14 149 1>, <&iomuxc 15 154 1>, <&iomuxc 16 39 7>, <&iomuxc 23 56 1>, <&iomuxc 24 61 7>, <&iomuxc 31 46 1>; }; diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index 89b834f3fa17..e7d30f45b161 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -16,6 +16,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi index 19cbd879c448..cc9572ea2860 100644 --- a/arch/arm/boot/dts/imx6sl.dtsi +++ b/arch/arm/boot/dts/imx6sl.dtsi @@ -14,6 +14,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec; diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi index 10f333016197..dd4ec85ecbaa 100644 --- a/arch/arm/boot/dts/imx6sx.dtsi +++ b/arch/arm/boot/dts/imx6sx.dtsi @@ -15,6 +15,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { can0 = &flexcan1; diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi index 39845a7e0463..53d3f8e41e9b 100644 --- a/arch/arm/boot/dts/imx6ul.dtsi +++ b/arch/arm/boot/dts/imx6ul.dtsi @@ -15,6 +15,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { ethernet0 = &fec1; diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 8ff2cbdd8f0d..be33dfc86838 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -50,6 +50,14 @@ / { #address-cells = <1>; #size-cells = <1>; + /* + * The decompressor and also some bootloaders rely on a + * pre-existing /chosen node to be available to insert the + * command line and merge other ATAGS info. + * Also for U-Boot there must be a pre-existing /memory node. + */ + chosen {}; + memory { device_type = "memory"; reg = <0 0>; }; aliases { gpio0 = &gpio1; diff --git a/arch/arm/boot/dts/orion5x-lschl.dts b/arch/arm/boot/dts/orion5x-linkstation-lschl.dts index 947409252845..ea6c881634b9 100644 --- a/arch/arm/boot/dts/orion5x-lschl.dts +++ b/arch/arm/boot/dts/orion5x-linkstation-lschl.dts @@ -2,7 +2,7 @@ * Device Tree file for Buffalo Linkstation LS-CHLv3 * * Copyright (C) 2016 Ash Hughes <ashley.hughes@blueyonder.co.uk> - * Copyright (C) 2015, 2016 + * Copyright (C) 2015-2017 * Roger Shimizu <rogershimizu@gmail.com> * * This file is dual-licensed: you can use it either under the terms @@ -52,7 +52,7 @@ #include <dt-bindings/gpio/gpio.h> / { - model = "Buffalo Linkstation Live v3 (LS-CHL)"; + model = "Buffalo Linkstation LiveV3 (LS-CHL)"; compatible = "buffalo,lschl", "marvell,orion5x-88f5182", "marvell,orion5x"; memory { /* 128 MB */ diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi index c8b2944e304a..ace97e8576db 100644 --- a/arch/arm/boot/dts/stih407-family.dtsi +++ b/arch/arm/boot/dts/stih407-family.dtsi @@ -680,6 +680,7 @@ phy-names = "usb2-phy", "usb3-phy"; phys = <&usb2_picophy0>, <&phy_port2 PHY_TYPE_USB3>; + snps,dis_u3_susphy_quirk; }; }; diff --git a/arch/arm/configs/ezx_defconfig b/arch/arm/configs/ezx_defconfig index ea316c4b890e..d3f1768840e2 100644 --- a/arch/arm/configs/ezx_defconfig +++ b/arch/arm/configs/ezx_defconfig @@ -64,8 +64,8 @@ CONFIG_NETFILTER=y CONFIG_NETFILTER_NETLINK_QUEUE=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_SCTP=m -CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig index 18e59feaa307..7f479cdb3479 100644 --- a/arch/arm/configs/imote2_defconfig +++ b/arch/arm/configs/imote2_defconfig @@ -56,8 +56,8 @@ CONFIG_NETFILTER=y CONFIG_NETFILTER_NETLINK_QUEUE=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_EVENTS=y -CONFIG_NF_CT_PROTO_SCTP=m -CONFIG_NF_CT_PROTO_UDPLITE=m +CONFIG_NF_CT_PROTO_SCTP=y +CONFIG_NF_CT_PROTO_UDPLITE=y CONFIG_NF_CONNTRACK_AMANDA=m CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_H323=m diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index ce131ed5939d..ae738a6319f6 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -600,7 +600,7 @@ static int gpr_set(struct task_struct *target, const void *kbuf, const void __user *ubuf) { int ret; - struct pt_regs newregs; + struct pt_regs newregs = *task_pt_regs(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newregs, diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c index 699157759120..c03bf28d8bbc 100644 --- a/arch/arm/mach-imx/mmdc.c +++ b/arch/arm/mach-imx/mmdc.c @@ -60,7 +60,6 @@ #define to_mmdc_pmu(p) container_of(p, struct mmdc_pmu, pmu) -static enum cpuhp_state cpuhp_mmdc_state; static int ddr_type; struct fsl_mmdc_devtype_data { @@ -82,6 +81,7 @@ static const struct of_device_id imx_mmdc_dt_ids[] = { #ifdef CONFIG_PERF_EVENTS +static enum cpuhp_state cpuhp_mmdc_state; static DEFINE_IDA(mmdc_ida); PMU_EVENT_ATTR_STRING(total-cycles, mmdc_pmu_total_cycles, "event=0x00") diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 3a2e678b8d30..0122ad1a6027 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -610,9 +610,9 @@ static int __init early_abort_handler(unsigned long addr, unsigned int fsr, void __init early_abt_enable(void) { - fsr_info[22].fn = early_abort_handler; + fsr_info[FSR_FS_AEA].fn = early_abort_handler; local_abt_enable(); - fsr_info[22].fn = do_bad; + fsr_info[FSR_FS_AEA].fn = do_bad; } #ifndef CONFIG_ARM_LPAE diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h index 67532f242271..afc1f84e763b 100644 --- a/arch/arm/mm/fault.h +++ b/arch/arm/mm/fault.h @@ -11,11 +11,15 @@ #define FSR_FS5_0 (0x3f) #ifdef CONFIG_ARM_LPAE +#define FSR_FS_AEA 17 + static inline int fsr_fs(unsigned int fsr) { return fsr & FSR_FS5_0; } #else +#define FSR_FS_AEA 22 + static inline int fsr_fs(unsigned int fsr) { return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6; diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi index eada0b58ba1c..0cbe24b49710 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi @@ -55,6 +55,24 @@ #address-cells = <2>; #size-cells = <2>; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + /* 16 MiB reserved for Hardware ROM Firmware */ + hwrom_reserved: hwrom@0 { + reg = <0x0 0x0 0x0 0x1000000>; + no-map; + }; + + /* 2 MiB reserved for ARM Trusted Firmware (BL31) */ + secmon_reserved: secmon@10000000 { + reg = <0x0 0x10000000 0x0 0x200000>; + no-map; + }; + }; + cpus { #address-cells = <0x2>; #size-cells = <0x0>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts index 5d28e1cdc998..c59403adb387 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts @@ -151,6 +151,18 @@ status = "okay"; pinctrl-0 = <ð_rgmii_pins>; pinctrl-names = "default"; + phy-handle = <ð_phy0>; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + + eth_phy0: ethernet-phy@0 { + reg = <0>; + eee-broken-1000t; + }; + }; }; &ir { diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S index c53dbeae79f2..838dad5c209f 100644 --- a/arch/arm64/crypto/aes-modes.S +++ b/arch/arm64/crypto/aes-modes.S @@ -193,15 +193,16 @@ AES_ENTRY(aes_cbc_encrypt) cbz w6, .Lcbcencloop ld1 {v0.16b}, [x5] /* get iv */ - enc_prepare w3, x2, x5 + enc_prepare w3, x2, x6 .Lcbcencloop: ld1 {v1.16b}, [x1], #16 /* get next pt block */ eor v0.16b, v0.16b, v1.16b /* ..and xor with iv */ - encrypt_block v0, w3, x2, x5, w6 + encrypt_block v0, w3, x2, x6, w7 st1 {v0.16b}, [x0], #16 subs w4, w4, #1 bne .Lcbcencloop + st1 {v0.16b}, [x5] /* return iv */ ret AES_ENDPROC(aes_cbc_encrypt) @@ -211,7 +212,7 @@ AES_ENTRY(aes_cbc_decrypt) cbz w6, .LcbcdecloopNx ld1 {v7.16b}, [x5] /* get iv */ - dec_prepare w3, x2, x5 + dec_prepare w3, x2, x6 .LcbcdecloopNx: #if INTERLEAVE >= 2 @@ -248,7 +249,7 @@ AES_ENTRY(aes_cbc_decrypt) .Lcbcdecloop: ld1 {v1.16b}, [x1], #16 /* get next ct block */ mov v0.16b, v1.16b /* ...and copy to v0 */ - decrypt_block v0, w3, x2, x5, w6 + decrypt_block v0, w3, x2, x6, w7 eor v0.16b, v0.16b, v7.16b /* xor with iv => pt */ mov v7.16b, v1.16b /* ct is next iv */ st1 {v0.16b}, [x0], #16 @@ -256,6 +257,7 @@ AES_ENTRY(aes_cbc_decrypt) bne .Lcbcdecloop .Lcbcdecout: FRAME_POP + st1 {v7.16b}, [x5] /* return iv */ ret AES_ENDPROC(aes_cbc_decrypt) @@ -267,24 +269,15 @@ AES_ENDPROC(aes_cbc_decrypt) AES_ENTRY(aes_ctr_encrypt) FRAME_PUSH - cbnz w6, .Lctrfirst /* 1st time around? */ - umov x5, v4.d[1] /* keep swabbed ctr in reg */ - rev x5, x5 -#if INTERLEAVE >= 2 - cmn w5, w4 /* 32 bit overflow? */ - bcs .Lctrinc - add x5, x5, #1 /* increment BE ctr */ - b .LctrincNx -#else - b .Lctrinc -#endif -.Lctrfirst: + cbz w6, .Lctrnotfirst /* 1st time around? */ enc_prepare w3, x2, x6 ld1 {v4.16b}, [x5] - umov x5, v4.d[1] /* keep swabbed ctr in reg */ - rev x5, x5 + +.Lctrnotfirst: + umov x8, v4.d[1] /* keep swabbed ctr in reg */ + rev x8, x8 #if INTERLEAVE >= 2 - cmn w5, w4 /* 32 bit overflow? */ + cmn w8, w4 /* 32 bit overflow? */ bcs .Lctrloop .LctrloopNx: subs w4, w4, #INTERLEAVE @@ -292,11 +285,11 @@ AES_ENTRY(aes_ctr_encrypt) #if INTERLEAVE == 2 mov v0.8b, v4.8b mov v1.8b, v4.8b - rev x7, x5 - add x5, x5, #1 + rev x7, x8 + add x8, x8, #1 ins v0.d[1], x7 - rev x7, x5 - add x5, x5, #1 + rev x7, x8 + add x8, x8, #1 ins v1.d[1], x7 ld1 {v2.16b-v3.16b}, [x1], #32 /* get 2 input blocks */ do_encrypt_block2x @@ -305,7 +298,7 @@ AES_ENTRY(aes_ctr_encrypt) st1 {v0.16b-v1.16b}, [x0], #32 #else ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */ - dup v7.4s, w5 + dup v7.4s, w8 mov v0.16b, v4.16b add v7.4s, v7.4s, v8.4s mov v1.16b, v4.16b @@ -323,18 +316,12 @@ AES_ENTRY(aes_ctr_encrypt) eor v2.16b, v7.16b, v2.16b eor v3.16b, v5.16b, v3.16b st1 {v0.16b-v3.16b}, [x0], #64 - add x5, x5, #INTERLEAVE + add x8, x8, #INTERLEAVE #endif - cbz w4, .LctroutNx -.LctrincNx: - rev x7, x5 + rev x7, x8 ins v4.d[1], x7 + cbz w4, .Lctrout b .LctrloopNx -.LctroutNx: - sub x5, x5, #1 - rev x7, x5 - ins v4.d[1], x7 - b .Lctrout .Lctr1x: adds w4, w4, #INTERLEAVE beq .Lctrout @@ -342,30 +329,39 @@ AES_ENTRY(aes_ctr_encrypt) .Lctrloop: mov v0.16b, v4.16b encrypt_block v0, w3, x2, x6, w7 + + adds x8, x8, #1 /* increment BE ctr */ + rev x7, x8 + ins v4.d[1], x7 + bcs .Lctrcarry /* overflow? */ + +.Lctrcarrydone: subs w4, w4, #1 bmi .Lctrhalfblock /* blocks < 0 means 1/2 block */ ld1 {v3.16b}, [x1], #16 eor v3.16b, v0.16b, v3.16b st1 {v3.16b}, [x0], #16 - beq .Lctrout -.Lctrinc: - adds x5, x5, #1 /* increment BE ctr */ - rev x7, x5 - ins v4.d[1], x7 - bcc .Lctrloop /* no overflow? */ - umov x7, v4.d[0] /* load upper word of ctr */ - rev x7, x7 /* ... to handle the carry */ - add x7, x7, #1 - rev x7, x7 - ins v4.d[0], x7 - b .Lctrloop + bne .Lctrloop + +.Lctrout: + st1 {v4.16b}, [x5] /* return next CTR value */ + FRAME_POP + ret + .Lctrhalfblock: ld1 {v3.8b}, [x1] eor v3.8b, v0.8b, v3.8b st1 {v3.8b}, [x0] -.Lctrout: FRAME_POP ret + +.Lctrcarry: + umov x7, v4.d[0] /* load upper word of ctr */ + rev x7, x7 /* ... to handle the carry */ + add x7, x7, #1 + rev x7, x7 + ins v4.d[0], x7 + b .Lctrcarrydone AES_ENDPROC(aes_ctr_encrypt) .ltorg diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 23e9e13bd2aa..655e65f38f31 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -11,6 +11,7 @@ * for more details. */ +#include <linux/acpi.h> #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/init.h> @@ -209,7 +210,12 @@ static struct notifier_block init_cpu_capacity_notifier = { static int __init register_cpufreq_notifier(void) { - if (cap_parsing_failed) + /* + * on ACPI-based systems we need to use the default cpu capacity + * until we have the necessary code to parse the cpu capacity, so + * skip registering cpufreq notifier. + */ + if (!acpi_disabled || cap_parsing_failed) return -EINVAL; if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) { diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h index 3f9406d9b9d6..da87943328a5 100644 --- a/arch/parisc/include/asm/bitops.h +++ b/arch/parisc/include/asm/bitops.h @@ -6,7 +6,7 @@ #endif #include <linux/compiler.h> -#include <asm/types.h> /* for BITS_PER_LONG/SHIFT_PER_LONG */ +#include <asm/types.h> #include <asm/byteorder.h> #include <asm/barrier.h> #include <linux/atomic.h> @@ -17,6 +17,12 @@ * to include/asm-i386/bitops.h or kerneldoc */ +#if __BITS_PER_LONG == 64 +#define SHIFT_PER_LONG 6 +#else +#define SHIFT_PER_LONG 5 +#endif + #define CHOP_SHIFTCOUNT(x) (((unsigned long) (x)) & (BITS_PER_LONG - 1)) diff --git a/arch/parisc/include/uapi/asm/bitsperlong.h b/arch/parisc/include/uapi/asm/bitsperlong.h index e0a23c7bdd43..07fa7e50bdc0 100644 --- a/arch/parisc/include/uapi/asm/bitsperlong.h +++ b/arch/parisc/include/uapi/asm/bitsperlong.h @@ -3,10 +3,8 @@ #if defined(__LP64__) #define __BITS_PER_LONG 64 -#define SHIFT_PER_LONG 6 #else #define __BITS_PER_LONG 32 -#define SHIFT_PER_LONG 5 #endif #include <asm-generic/bitsperlong.h> diff --git a/arch/parisc/include/uapi/asm/swab.h b/arch/parisc/include/uapi/asm/swab.h index e78403b129ef..928e1bbac98f 100644 --- a/arch/parisc/include/uapi/asm/swab.h +++ b/arch/parisc/include/uapi/asm/swab.h @@ -1,6 +1,7 @@ #ifndef _PARISC_SWAB_H #define _PARISC_SWAB_H +#include <asm/bitsperlong.h> #include <linux/types.h> #include <linux/compiler.h> @@ -38,7 +39,7 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 x) } #define __arch_swab32 __arch_swab32 -#if BITS_PER_LONG > 32 +#if __BITS_PER_LONG > 32 /* ** From "PA-RISC 2.0 Architecture", HP Professional Books. ** See Appendix I page 8 , "Endian Byte Swapping". @@ -61,6 +62,6 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 x) return x; } #define __arch_swab64 __arch_swab64 -#endif /* BITS_PER_LONG > 32 */ +#endif /* __BITS_PER_LONG > 32 */ #endif /* _PARISC_SWAB_H */ diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a8ee573fe610..281f4f1fcd1f 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -164,7 +164,6 @@ config PPC select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE select HAVE_ARCH_HARDENED_USERCOPY select HAVE_KERNEL_GZIP - select HAVE_CC_STACKPROTECTOR config GENERIC_CSUM def_bool CPU_LITTLE_ENDIAN @@ -484,6 +483,7 @@ config RELOCATABLE bool "Build a relocatable kernel" depends on (PPC64 && !COMPILE_TEST) || (FLATMEM && (44x || FSL_BOOKE)) select NONSTATIC_KERNEL + select MODULE_REL_CRCS if MODVERSIONS help This builds a kernel image that is capable of running at the location the kernel is loaded at. For ppc32, there is no any diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h index b312b152461b..6e834caa3720 100644 --- a/arch/powerpc/include/asm/cpu_has_feature.h +++ b/arch/powerpc/include/asm/cpu_has_feature.h @@ -23,7 +23,9 @@ static __always_inline bool cpu_has_feature(unsigned long feature) { int i; +#ifndef __clang__ /* clang can't cope with this */ BUILD_BUG_ON(!__builtin_constant_p(feature)); +#endif #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG if (!static_key_initialized) { diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index a34c764ca8dd..233a7e8cc8e3 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -160,7 +160,9 @@ static __always_inline bool mmu_has_feature(unsigned long feature) { int i; +#ifndef __clang__ /* clang can't cope with this */ BUILD_BUG_ON(!__builtin_constant_p(feature)); +#endif #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG if (!static_key_initialized) { diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index cc12c61ef315..53885512b8d3 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -90,9 +90,5 @@ static inline int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sec } #endif -#if defined(CONFIG_MODVERSIONS) && defined(CONFIG_PPC64) -#define ARCH_RELOCATES_KCRCTAB -#define reloc_start PHYSICAL_START -#endif #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MODULE_H */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 0d4531aa2052..dff79798903d 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -649,9 +649,10 @@ #define SRR1_ISI_N_OR_G 0x10000000 /* ISI: Access is no-exec or G */ #define SRR1_ISI_PROT 0x08000000 /* ISI: Other protection fault */ #define SRR1_WAKEMASK 0x00380000 /* reason for wakeup */ -#define SRR1_WAKEMASK_P8 0x003c0000 /* reason for wakeup on POWER8 */ +#define SRR1_WAKEMASK_P8 0x003c0000 /* reason for wakeup on POWER8 and 9 */ #define SRR1_WAKESYSERR 0x00300000 /* System error */ #define SRR1_WAKEEE 0x00200000 /* External interrupt */ +#define SRR1_WAKEHVI 0x00240000 /* Hypervisor Virtualization Interrupt (P9) */ #define SRR1_WAKEMT 0x00280000 /* mtctrl */ #define SRR1_WAKEHMI 0x00280000 /* Hypervisor maintenance */ #define SRR1_WAKEDEC 0x00180000 /* Decrementer interrupt */ diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h deleted file mode 100644 index 6720190eabec..000000000000 --- a/arch/powerpc/include/asm/stackprotector.h +++ /dev/null @@ -1,40 +0,0 @@ -/* - * GCC stack protector support. - * - * Stack protector works by putting predefined pattern at the start of - * the stack frame and verifying that it hasn't been overwritten when - * returning from the function. The pattern is called stack canary - * and gcc expects it to be defined by a global variable called - * "__stack_chk_guard" on PPC. This unfortunately means that on SMP - * we cannot have a different canary value per task. - */ - -#ifndef _ASM_STACKPROTECTOR_H -#define _ASM_STACKPROTECTOR_H - -#include <linux/random.h> -#include <linux/version.h> -#include <asm/reg.h> - -extern unsigned long __stack_chk_guard; - -/* - * Initialize the stackprotector canary value. - * - * NOTE: this must only be called from functions that never return, - * and it must always be inlined. - */ -static __always_inline void boot_init_stack_canary(void) -{ - unsigned long canary; - - /* Try to get a semi random initial value. */ - get_random_bytes(&canary, sizeof(canary)); - canary ^= mftb(); - canary ^= LINUX_VERSION_CODE; - - current->stack_canary = canary; - __stack_chk_guard = current->stack_canary; -} - -#endif /* _ASM_STACKPROTECTOR_H */ diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index f0b238516e9b..e0b9e576905a 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -44,6 +44,7 @@ static inline int icp_hv_init(void) { return -ENODEV; } #ifdef CONFIG_PPC_POWERNV extern int icp_opal_init(void); +extern void icp_opal_flush_interrupt(void); #else static inline int icp_opal_init(void) { return -ENODEV; } #endif diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 23f8082d7bfa..f4c2b52e58b3 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -19,10 +19,6 @@ CFLAGS_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) -# -fstack-protector triggers protection checks in this code, -# but it is being used too early to link to meaningful stack_chk logic. -CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector) - ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE) diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 0601e6a7297c..195a9fc8f81c 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -91,9 +91,6 @@ int main(void) DEFINE(TI_livepatch_sp, offsetof(struct thread_info, livepatch_sp)); #endif -#ifdef CONFIG_CC_STACKPROTECTOR - DEFINE(TSK_STACK_CANARY, offsetof(struct task_struct, stack_canary)); -#endif DEFINE(KSP, offsetof(struct thread_struct, ksp)); DEFINE(PT_REGS, offsetof(struct thread_struct, regs)); #ifdef CONFIG_BOOKE diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index d88573bdd090..b94887165a10 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -545,7 +545,7 @@ static void *eeh_pe_detach_dev(void *data, void *userdata) static void *__eeh_clear_pe_frozen_state(void *data, void *flag) { struct eeh_pe *pe = (struct eeh_pe *)data; - bool *clear_sw_state = flag; + bool clear_sw_state = *(bool *)flag; int i, rc = 1; for (i = 0; rc && i < 3; i++) diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 5742dbdbee46..3841d749a430 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -674,11 +674,7 @@ BEGIN_FTR_SECTION mtspr SPRN_SPEFSCR,r0 /* restore SPEFSCR reg */ END_FTR_SECTION_IFSET(CPU_FTR_SPE) #endif /* CONFIG_SPE */ -#if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP) - lwz r0,TSK_STACK_CANARY(r2) - lis r4,__stack_chk_guard@ha - stw r0,__stack_chk_guard@l(r4) -#endif + lwz r0,_CCR(r1) mtcrf 0xFF,r0 /* r3-r12 are destroyed -- Cort */ diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index bb1807184bad..0b0f89685b67 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -286,14 +286,6 @@ static void dedotify_versions(struct modversion_info *vers, for (end = (void *)vers + size; vers < end; vers++) if (vers->name[0] == '.') { memmove(vers->name, vers->name+1, strlen(vers->name)); -#ifdef ARCH_RELOCATES_KCRCTAB - /* The TOC symbol has no CRC computed. To avoid CRC - * check failing, we must force it to the expected - * value (see CRC check in module.c). - */ - if (!strcmp(vers->name, "TOC.")) - vers->crc = -(unsigned long)reloc_start; -#endif } } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 04885cec24df..5dd056df0baa 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -64,12 +64,6 @@ #include <linux/kprobes.h> #include <linux/kdebug.h> -#ifdef CONFIG_CC_STACKPROTECTOR -#include <linux/stackprotector.h> -unsigned long __stack_chk_guard __read_mostly; -EXPORT_SYMBOL(__stack_chk_guard); -#endif - /* Transactional Memory debug */ #ifdef TM_DEBUG_SW #define TM_DEBUG(x...) printk(KERN_INFO x) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index ec47a939cbdd..ac83eb04a8b8 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2834,6 +2834,9 @@ static void __init prom_find_boot_cpu(void) cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu); + if (!PHANDLE_VALID(cpu_pkg)) + return; + prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval)); prom.cpu = be32_to_cpu(rval); diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 6fd30ac7d14a..62a50d6d1053 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -253,8 +253,11 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (unlikely(debugger_fault_handler(regs))) goto bail; - /* On a kernel SLB miss we can only check for a valid exception entry */ - if (!user_mode(regs) && (address >= TASK_SIZE)) { + /* + * The kernel should never take an execute fault nor should it + * take a page fault to a kernel address. + */ + if (!user_mode(regs) && (is_exec || (address >= TASK_SIZE))) { rc = SIGSEGV; goto bail; } @@ -391,20 +394,6 @@ good_area: if (is_exec) { /* - * An execution fault + no execute ? - * - * On CPUs that don't have CPU_FTR_COHERENT_ICACHE we - * deliberately create NX mappings, and use the fault to do the - * cache flush. This is usually handled in hash_page_do_lazy_icache() - * but we could end up here if that races with a concurrent PTE - * update. In that case we need to fall through here to the VMA - * check below. - */ - if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE) && - (regs->msr & SRR1_ISI_N_OR_G)) - goto bad_area; - - /* * Allow execution from readable areas if the MMU does not * provide separate controls over reading and executing. * diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index cfa53ccc8baf..34f1a0dbc898 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -65,7 +65,7 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa, if (!pmdp) return -ENOMEM; if (map_page_size == PMD_SIZE) { - ptep = (pte_t *)pudp; + ptep = pmdp_ptep(pmdp); goto set_the_pte; } ptep = pte_alloc_kernel(pmdp, ea); @@ -90,7 +90,7 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa, } pmdp = pmd_offset(pudp, ea); if (map_page_size == PMD_SIZE) { - ptep = (pte_t *)pudp; + ptep = pmdp_ptep(pmdp); goto set_the_pte; } if (!pmd_present(*pmdp)) { diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c index 61b79119065f..952713d6cf04 100644 --- a/arch/powerpc/mm/tlb-radix.c +++ b/arch/powerpc/mm/tlb-radix.c @@ -50,9 +50,7 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric) for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) { __tlbiel_pid(pid, set, ric); } - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - asm volatile(PPC_INVALIDATE_ERAT : : :"memory"); - return; + asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory"); } static inline void _tlbie_pid(unsigned long pid, unsigned long ric) @@ -85,8 +83,6 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid, asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1) : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory"); asm volatile("ptesync": : :"memory"); - if (cpu_has_feature(CPU_FTR_POWER9_DD1)) - asm volatile(PPC_INVALIDATE_ERAT : : :"memory"); } static inline void _tlbie_va(unsigned long va, unsigned long pid, diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index c789258ae1e1..eec0e8d0454d 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -155,8 +155,10 @@ static void pnv_smp_cpu_kill_self(void) wmask = SRR1_WAKEMASK_P8; idle_states = pnv_get_supported_cpuidle_states(); + /* We don't want to take decrementer interrupts while we are offline, - * so clear LPCR:PECE1. We keep PECE2 enabled. + * so clear LPCR:PECE1. We keep PECE2 (and LPCR_PECE_HVEE on P9) + * enabled as to let IPIs in. */ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1); @@ -206,8 +208,12 @@ static void pnv_smp_cpu_kill_self(void) * contains 0. */ if (((srr1 & wmask) == SRR1_WAKEEE) || + ((srr1 & wmask) == SRR1_WAKEHVI) || (local_paca->irq_happened & PACA_IRQ_EE)) { - icp_native_flush_interrupt(); + if (cpu_has_feature(CPU_FTR_ARCH_300)) + icp_opal_flush_interrupt(); + else + icp_native_flush_interrupt(); } else if ((srr1 & wmask) == SRR1_WAKEHDBELL) { unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER); asm volatile(PPC_MSGCLR(%0) : : "r" (msg)); @@ -221,6 +227,8 @@ static void pnv_smp_cpu_kill_self(void) if (srr1 && !generic_check_cpu_restart(cpu)) DBG("CPU%d Unexpected exit while offline !\n", cpu); } + + /* Re-enable decrementer interrupts */ mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1); DBG("CPU%d coming online...\n", cpu); } diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c index 60c57657c772..f9670eabfcfa 100644 --- a/arch/powerpc/sysdev/xics/icp-opal.c +++ b/arch/powerpc/sysdev/xics/icp-opal.c @@ -120,18 +120,49 @@ static void icp_opal_cause_ipi(int cpu, unsigned long data) { int hw_cpu = get_hard_smp_processor_id(cpu); + kvmppc_set_host_ipi(cpu, 1); opal_int_set_mfrr(hw_cpu, IPI_PRIORITY); } static irqreturn_t icp_opal_ipi_action(int irq, void *dev_id) { - int hw_cpu = hard_smp_processor_id(); + int cpu = smp_processor_id(); - opal_int_set_mfrr(hw_cpu, 0xff); + kvmppc_set_host_ipi(cpu, 0); + opal_int_set_mfrr(get_hard_smp_processor_id(cpu), 0xff); return smp_ipi_demux(); } +/* + * Called when an interrupt is received on an off-line CPU to + * clear the interrupt, so that the CPU can go back to nap mode. + */ +void icp_opal_flush_interrupt(void) +{ + unsigned int xirr; + unsigned int vec; + + do { + xirr = icp_opal_get_xirr(); + vec = xirr & 0x00ffffff; + if (vec == XICS_IRQ_SPURIOUS) + break; + if (vec == XICS_IPI) { + /* Clear pending IPI */ + int cpu = smp_processor_id(); + kvmppc_set_host_ipi(cpu, 0); + opal_int_set_mfrr(get_hard_smp_processor_id(cpu), 0xff); + } else { + pr_err("XICS: hw interrupt 0x%x to offline cpu, " + "disabling\n", vec); + xics_mask_unknown_vec(vec); + } + + /* EOI the interrupt */ + } while (opal_int_eoi(xirr) > 0); +} + #endif /* CONFIG_SMP */ static const struct icp_ops icp_opal_ops = { diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 7447ba509c30..12020b55887b 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -963,6 +963,11 @@ static int s390_fpregs_set(struct task_struct *target, if (target == current) save_fpu_regs(); + if (MACHINE_HAS_VX) + convert_vx_to_fp(fprs, target->thread.fpu.vxrs); + else + memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs)); + /* If setting FPC, must validate it first. */ if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) { u32 ufpc[2] = { target->thread.fpu.fpc, 0 }; @@ -1067,6 +1072,9 @@ static int s390_vxrs_low_set(struct task_struct *target, if (target == current) save_fpu_regs(); + for (i = 0; i < __NUM_VXRS_LOW; i++) + vxrs[i] = *((__u64 *)(target->thread.fpu.vxrs + i) + 1); + rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1); if (rc == 0) for (i = 0; i < __NUM_VXRS_LOW; i++) diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 7a1897c51c54..d56ef26d4681 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -202,7 +202,7 @@ static inline pgste_t ptep_xchg_start(struct mm_struct *mm, return pgste; } -static inline void ptep_xchg_commit(struct mm_struct *mm, +static inline pte_t ptep_xchg_commit(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pgste_t pgste, pte_t old, pte_t new) { @@ -220,6 +220,7 @@ static inline void ptep_xchg_commit(struct mm_struct *mm, } else { *ptep = new; } + return old; } pte_t ptep_xchg_direct(struct mm_struct *mm, unsigned long addr, @@ -231,7 +232,7 @@ pte_t ptep_xchg_direct(struct mm_struct *mm, unsigned long addr, preempt_disable(); pgste = ptep_xchg_start(mm, addr, ptep); old = ptep_flush_direct(mm, addr, ptep); - ptep_xchg_commit(mm, addr, ptep, pgste, old, new); + old = ptep_xchg_commit(mm, addr, ptep, pgste, old, new); preempt_enable(); return old; } @@ -246,7 +247,7 @@ pte_t ptep_xchg_lazy(struct mm_struct *mm, unsigned long addr, preempt_disable(); pgste = ptep_xchg_start(mm, addr, ptep); old = ptep_flush_lazy(mm, addr, ptep); - ptep_xchg_commit(mm, addr, ptep, pgste, old, new); + old = ptep_xchg_commit(mm, addr, ptep, pgste, old, new); preempt_enable(); return old; } diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h index b84be675e507..d0317993e947 100644 --- a/arch/sparc/include/asm/mmu_context_64.h +++ b/arch/sparc/include/asm/mmu_context_64.h @@ -35,15 +35,15 @@ void __tsb_context_switch(unsigned long pgd_pa, static inline void tsb_context_switch(struct mm_struct *mm) { __tsb_context_switch(__pa(mm->pgd), - &mm->context.tsb_block[0], + &mm->context.tsb_block[MM_TSB_BASE], #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) - (mm->context.tsb_block[1].tsb ? - &mm->context.tsb_block[1] : + (mm->context.tsb_block[MM_TSB_HUGE].tsb ? + &mm->context.tsb_block[MM_TSB_HUGE] : NULL) #else NULL #endif - , __pa(&mm->context.tsb_descr[0])); + , __pa(&mm->context.tsb_descr[MM_TSB_BASE])); } void tsb_grow(struct mm_struct *mm, diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c index 3bebf395252c..4d0248aa0928 100644 --- a/arch/sparc/kernel/irq_64.c +++ b/arch/sparc/kernel/irq_64.c @@ -1021,7 +1021,7 @@ static void __init alloc_one_queue(unsigned long *pa_ptr, unsigned long qmask) unsigned long order = get_order(size); unsigned long p; - p = __get_free_pages(GFP_KERNEL, order); + p = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order); if (!p) { prom_printf("SUN4V: Error, cannot allocate queue.\n"); prom_halt(); diff --git a/arch/sparc/kernel/sstate.c b/arch/sparc/kernel/sstate.c index c59af546f522..3caed4023589 100644 --- a/arch/sparc/kernel/sstate.c +++ b/arch/sparc/kernel/sstate.c @@ -43,8 +43,8 @@ static const char poweroff_msg[32] __attribute__((aligned(32))) = "Linux powering off"; static const char rebooting_msg[32] __attribute__((aligned(32))) = "Linux rebooting"; -static const char panicing_msg[32] __attribute__((aligned(32))) = - "Linux panicing"; +static const char panicking_msg[32] __attribute__((aligned(32))) = + "Linux panicking"; static int sstate_reboot_call(struct notifier_block *np, unsigned long type, void *_unused) { @@ -76,7 +76,7 @@ static struct notifier_block sstate_reboot_notifier = { static int sstate_panic_event(struct notifier_block *n, unsigned long event, void *ptr) { - do_set_sstate(HV_SOFT_STATE_TRANSITION, panicing_msg); + do_set_sstate(HV_SOFT_STATE_TRANSITION, panicking_msg); return NOTIFY_DONE; } diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 4bc10e44d1ca..dfc97a47c9a0 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2051,6 +2051,73 @@ void sun4v_resum_overflow(struct pt_regs *regs) atomic_inc(&sun4v_resum_oflow_cnt); } +/* Given a set of registers, get the virtual addressi that was being accessed + * by the faulting instructions at tpc. + */ +static unsigned long sun4v_get_vaddr(struct pt_regs *regs) +{ + unsigned int insn; + + if (!copy_from_user(&insn, (void __user *)regs->tpc, 4)) { + return compute_effective_address(regs, insn, + (insn >> 25) & 0x1f); + } + return 0; +} + +/* Attempt to handle non-resumable errors generated from userspace. + * Returns true if the signal was handled, false otherwise. + */ +bool sun4v_nonresum_error_user_handled(struct pt_regs *regs, + struct sun4v_error_entry *ent) { + + unsigned int attrs = ent->err_attrs; + + if (attrs & SUN4V_ERR_ATTRS_MEMORY) { + unsigned long addr = ent->err_raddr; + siginfo_t info; + + if (addr == ~(u64)0) { + /* This seems highly unlikely to ever occur */ + pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory error detected in unknown location!\n"); + } else { + unsigned long page_cnt = DIV_ROUND_UP(ent->err_size, + PAGE_SIZE); + + /* Break the unfortunate news. */ + pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory failed at %016lX\n", + addr); + pr_emerg("SUN4V NON-RECOVERABLE ERROR: Claiming %lu ages.\n", + page_cnt); + + while (page_cnt-- > 0) { + if (pfn_valid(addr >> PAGE_SHIFT)) + get_page(pfn_to_page(addr >> PAGE_SHIFT)); + addr += PAGE_SIZE; + } + } + info.si_signo = SIGKILL; + info.si_errno = 0; + info.si_trapno = 0; + force_sig_info(info.si_signo, &info, current); + + return true; + } + if (attrs & SUN4V_ERR_ATTRS_PIO) { + siginfo_t info; + + info.si_signo = SIGBUS; + info.si_code = BUS_ADRERR; + info.si_addr = (void __user *)sun4v_get_vaddr(regs); + force_sig_info(info.si_signo, &info, current); + + return true; + } + + /* Default to doing nothing */ + return false; +} + /* We run with %pil set to PIL_NORMAL_MAX and PSTATE_IE enabled in %pstate. * Log the event, clear the first word of the entry, and die. */ @@ -2075,6 +2142,12 @@ void sun4v_nonresum_error(struct pt_regs *regs, unsigned long offset) put_cpu(); + if (!(regs->tstate & TSTATE_PRIV) && + sun4v_nonresum_error_user_handled(regs, &local_copy)) { + /* DON'T PANIC: This userspace error was handled. */ + return; + } + #ifdef CONFIG_PCI /* Check for the special PCI poke sequence. */ if (pci_poke_in_progress && pci_poke_cpu == cpu) { diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 6ef688a1ef3e..7ff1b0c86a8e 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -1085,9 +1085,9 @@ static void aesni_free_simds(void) aesni_simd_skciphers[i]; i++) simd_skcipher_free(aesni_simd_skciphers[i]); - for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2) && - aesni_simd_skciphers2[i].simd; i++) - simd_skcipher_free(aesni_simd_skciphers2[i].simd); + for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2); i++) + if (aesni_simd_skciphers2[i].simd) + simd_skcipher_free(aesni_simd_skciphers2[i].simd); } static int __init aesni_init(void) @@ -1168,7 +1168,7 @@ static int __init aesni_init(void) simd = simd_skcipher_create_compat(algname, drvname, basename); err = PTR_ERR(simd); if (IS_ERR(simd)) - goto unregister_simds; + continue; aesni_simd_skciphers2[i].simd = simd; } diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index 17c3564d087a..22ef4f72cf32 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -161,7 +161,13 @@ static u64 rapl_timer_ms; static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) { - return rapl_pmus->pmus[topology_logical_package_id(cpu)]; + unsigned int pkgid = topology_logical_package_id(cpu); + + /* + * The unsigned check also catches the '-1' return value for non + * existent mappings in the topology map. + */ + return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL; } static inline u64 rapl_read_counter(struct perf_event *event) @@ -402,6 +408,8 @@ static int rapl_pmu_event_init(struct perf_event *event) /* must be done before validate_group */ pmu = cpu_to_rapl_pmu(event->cpu); + if (!pmu) + return -EINVAL; event->cpu = pmu->cpu; event->pmu_private = pmu; event->hw.event_base = msr; @@ -585,6 +593,20 @@ static int rapl_cpu_online(unsigned int cpu) struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); int target; + if (!pmu) { + pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); + if (!pmu) + return -ENOMEM; + + raw_spin_lock_init(&pmu->lock); + INIT_LIST_HEAD(&pmu->active_list); + pmu->pmu = &rapl_pmus->pmu; + pmu->timer_interval = ms_to_ktime(rapl_timer_ms); + rapl_hrtimer_init(pmu); + + rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu; + } + /* * Check if there is an online cpu in the package which collects rapl * events already. @@ -598,27 +620,6 @@ static int rapl_cpu_online(unsigned int cpu) return 0; } -static int rapl_cpu_prepare(unsigned int cpu) -{ - struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu); - - if (pmu) - return 0; - - pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); - if (!pmu) - return -ENOMEM; - - raw_spin_lock_init(&pmu->lock); - INIT_LIST_HEAD(&pmu->active_list); - pmu->pmu = &rapl_pmus->pmu; - pmu->timer_interval = ms_to_ktime(rapl_timer_ms); - pmu->cpu = -1; - rapl_hrtimer_init(pmu); - rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu; - return 0; -} - static int rapl_check_hw_unit(bool apply_quirk) { u64 msr_rapl_power_unit_bits; @@ -803,29 +804,21 @@ static int __init rapl_pmu_init(void) /* * Install callbacks. Core will call them for each online cpu. */ - - ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare", - rapl_cpu_prepare, NULL); - if (ret) - goto out; - ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE, "perf/x86/rapl:online", rapl_cpu_online, rapl_cpu_offline); if (ret) - goto out1; + goto out; ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1); if (ret) - goto out2; + goto out1; rapl_advertise(); return 0; -out2: - cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE); out1: - cpuhp_remove_state(CPUHP_PERF_X86_RAPL_PREP); + cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE); out: pr_warn("Initialization failed (%d), disabled\n", ret); cleanup_rapl_pmus(); @@ -836,7 +829,6 @@ module_init(rapl_pmu_init); static void __exit intel_rapl_exit(void) { cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE); - cpuhp_remove_state_nocalls(CPUHP_PERF_X86_RAPL_PREP); perf_pmu_unregister(&rapl_pmus->pmu); cleanup_rapl_pmus(); } diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 8c4ccdc3a3f3..1ab45976474d 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -100,7 +100,13 @@ ssize_t uncore_event_show(struct kobject *kobj, struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu) { - return pmu->boxes[topology_logical_package_id(cpu)]; + unsigned int pkgid = topology_logical_package_id(cpu); + + /* + * The unsigned check also catches the '-1' return value for non + * existent mappings in the topology map. + */ + return pkgid < max_packages ? pmu->boxes[pkgid] : NULL; } u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) @@ -764,30 +770,6 @@ static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu) pmu->registered = false; } -static void __uncore_exit_boxes(struct intel_uncore_type *type, int cpu) -{ - struct intel_uncore_pmu *pmu = type->pmus; - struct intel_uncore_box *box; - int i, pkg; - - if (pmu) { - pkg = topology_physical_package_id(cpu); - for (i = 0; i < type->num_boxes; i++, pmu++) { - box = pmu->boxes[pkg]; - if (box) - uncore_box_exit(box); - } - } -} - -static void uncore_exit_boxes(void *dummy) -{ - struct intel_uncore_type **types; - - for (types = uncore_msr_uncores; *types; types++) - __uncore_exit_boxes(*types++, smp_processor_id()); -} - static void uncore_free_boxes(struct intel_uncore_pmu *pmu) { int pkg; @@ -1058,86 +1040,6 @@ static void uncore_pci_exit(void) } } -static int uncore_cpu_dying(unsigned int cpu) -{ - struct intel_uncore_type *type, **types = uncore_msr_uncores; - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - int i, pkg; - - pkg = topology_logical_package_id(cpu); - for (; *types; types++) { - type = *types; - pmu = type->pmus; - for (i = 0; i < type->num_boxes; i++, pmu++) { - box = pmu->boxes[pkg]; - if (box && atomic_dec_return(&box->refcnt) == 0) - uncore_box_exit(box); - } - } - return 0; -} - -static int first_init; - -static int uncore_cpu_starting(unsigned int cpu) -{ - struct intel_uncore_type *type, **types = uncore_msr_uncores; - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - int i, pkg, ncpus = 1; - - if (first_init) { - /* - * On init we get the number of online cpus in the package - * and set refcount for all of them. - */ - ncpus = cpumask_weight(topology_core_cpumask(cpu)); - } - - pkg = topology_logical_package_id(cpu); - for (; *types; types++) { - type = *types; - pmu = type->pmus; - for (i = 0; i < type->num_boxes; i++, pmu++) { - box = pmu->boxes[pkg]; - if (!box) - continue; - /* The first cpu on a package activates the box */ - if (atomic_add_return(ncpus, &box->refcnt) == ncpus) - uncore_box_init(box); - } - } - - return 0; -} - -static int uncore_cpu_prepare(unsigned int cpu) -{ - struct intel_uncore_type *type, **types = uncore_msr_uncores; - struct intel_uncore_pmu *pmu; - struct intel_uncore_box *box; - int i, pkg; - - pkg = topology_logical_package_id(cpu); - for (; *types; types++) { - type = *types; - pmu = type->pmus; - for (i = 0; i < type->num_boxes; i++, pmu++) { - if (pmu->boxes[pkg]) - continue; - /* First cpu of a package allocates the box */ - box = uncore_alloc_box(type, cpu_to_node(cpu)); - if (!box) - return -ENOMEM; - box->pmu = pmu; - box->pkgid = pkg; - pmu->boxes[pkg] = box; - } - } - return 0; -} - static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu, int new_cpu) { @@ -1177,12 +1079,14 @@ static void uncore_change_context(struct intel_uncore_type **uncores, static int uncore_event_cpu_offline(unsigned int cpu) { - int target; + struct intel_uncore_type *type, **types = uncore_msr_uncores; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, pkg, target; /* Check if exiting cpu is used for collecting uncore events */ if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask)) - return 0; - + goto unref; /* Find a new cpu to collect uncore events */ target = cpumask_any_but(topology_core_cpumask(cpu), cpu); @@ -1194,12 +1098,82 @@ static int uncore_event_cpu_offline(unsigned int cpu) uncore_change_context(uncore_msr_uncores, cpu, target); uncore_change_context(uncore_pci_uncores, cpu, target); + +unref: + /* Clear the references */ + pkg = topology_logical_package_id(cpu); + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (box && atomic_dec_return(&box->refcnt) == 0) + uncore_box_exit(box); + } + } return 0; } +static int allocate_boxes(struct intel_uncore_type **types, + unsigned int pkg, unsigned int cpu) +{ + struct intel_uncore_box *box, *tmp; + struct intel_uncore_type *type; + struct intel_uncore_pmu *pmu; + LIST_HEAD(allocated); + int i; + + /* Try to allocate all required boxes */ + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + if (pmu->boxes[pkg]) + continue; + box = uncore_alloc_box(type, cpu_to_node(cpu)); + if (!box) + goto cleanup; + box->pmu = pmu; + box->pkgid = pkg; + list_add(&box->active_list, &allocated); + } + } + /* Install them in the pmus */ + list_for_each_entry_safe(box, tmp, &allocated, active_list) { + list_del_init(&box->active_list); + box->pmu->boxes[pkg] = box; + } + return 0; + +cleanup: + list_for_each_entry_safe(box, tmp, &allocated, active_list) { + list_del_init(&box->active_list); + kfree(box); + } + return -ENOMEM; +} + static int uncore_event_cpu_online(unsigned int cpu) { - int target; + struct intel_uncore_type *type, **types = uncore_msr_uncores; + struct intel_uncore_pmu *pmu; + struct intel_uncore_box *box; + int i, ret, pkg, target; + + pkg = topology_logical_package_id(cpu); + ret = allocate_boxes(types, pkg, cpu); + if (ret) + return ret; + + for (; *types; types++) { + type = *types; + pmu = type->pmus; + for (i = 0; i < type->num_boxes; i++, pmu++) { + box = pmu->boxes[pkg]; + if (!box && atomic_inc_return(&box->refcnt) == 1) + uncore_box_init(box); + } + } /* * Check if there is an online cpu in the package @@ -1389,38 +1363,16 @@ static int __init intel_uncore_init(void) if (cret && pret) return -ENODEV; - /* - * Install callbacks. Core will call them for each online cpu. - * - * The first online cpu of each package allocates and takes - * the refcounts for all other online cpus in that package. - * If msrs are not enabled no allocation is required and - * uncore_cpu_prepare() is not called for each online cpu. - */ - if (!cret) { - ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP, - "perf/x86/intel/uncore:prepare", - uncore_cpu_prepare, NULL); - if (ret) - goto err; - } else { - cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP, - "perf/x86/intel/uncore:prepare", - uncore_cpu_prepare, NULL); - } - first_init = 1; - cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING, - "perf/x86/uncore:starting", - uncore_cpu_starting, uncore_cpu_dying); - first_init = 0; - cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE, - "perf/x86/uncore:online", - uncore_event_cpu_online, uncore_event_cpu_offline); + /* Install hotplug callbacks to setup the targets for each package */ + ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE, + "perf/x86/intel/uncore:online", + uncore_event_cpu_online, + uncore_event_cpu_offline); + if (ret) + goto err; return 0; err: - /* Undo box->init_box() */ - on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1); uncore_types_exit(uncore_msr_uncores); uncore_pci_exit(); return ret; @@ -1429,9 +1381,7 @@ module_init(intel_uncore_init); static void __exit intel_uncore_exit(void) { - cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_ONLINE); - cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_STARTING); - cpuhp_remove_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP); + cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE); uncore_types_exit(uncore_msr_uncores); uncore_pci_exit(); } diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 38711df3bcb5..2266f864b747 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -140,6 +140,7 @@ extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); void reload_early_microcode(void); extern bool get_builtin_firmware(struct cpio_data *cd, const char *name); +extern bool initrd_gone; #else static inline int __init microcode_init(void) { return 0; }; static inline void __init load_ucode_bsp(void) { } diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 1be64da0384e..e6cfe7ba2d65 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -104,6 +104,7 @@ struct cpuinfo_x86 { __u8 x86_phys_bits; /* CPUID returned core id bits: */ __u8 x86_coreid_bits; + __u8 cu_id; /* Max extended CPUID function supported: */ __u32 extended_cpuid_level; /* Maximum supported CPUID level, -1=no CPUID: */ diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 1e35dd06b090..bd6b8c270c24 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1875,7 +1875,6 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_ack = irq_chip_ack_parent, .irq_eoi = ioapic_ack_level, .irq_set_affinity = ioapic_set_affinity, - .irq_retrigger = irq_chip_retrigger_hierarchy, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -1887,7 +1886,6 @@ static struct irq_chip ioapic_ir_chip __read_mostly = { .irq_ack = irq_chip_ack_parent, .irq_eoi = ioapic_ir_ack_level, .irq_set_affinity = ioapic_set_affinity, - .irq_retrigger = irq_chip_retrigger_hierarchy, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -2117,6 +2115,7 @@ static inline void __init check_timer(void) if (idx != -1 && irq_trigger(idx)) unmask_ioapic_irq(irq_get_chip_data(0)); } + irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); if (timer_irq_works()) { if (disable_timer_pin_1 > 0) @@ -2138,6 +2137,7 @@ static inline void __init check_timer(void) * legacy devices should be connected to IO APIC #0 */ replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2); + irq_domain_deactivate_irq(irq_data); irq_domain_activate_irq(irq_data); legacy_pic->unmask(0); if (timer_irq_works()) { diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 1d3167269a67..2b4cf04239b6 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -309,8 +309,22 @@ static void amd_get_topology(struct cpuinfo_x86 *c) /* get information required for multi-node processors */ if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { + u32 eax, ebx, ecx, edx; - node_id = cpuid_ecx(0x8000001e) & 7; + cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); + + node_id = ecx & 0xff; + smp_num_siblings = ((ebx >> 8) & 0xff) + 1; + + if (c->x86 == 0x15) + c->cu_id = ebx & 0xff; + + if (c->x86 >= 0x17) { + c->cpu_core_id = ebx & 0xff; + + if (smp_num_siblings > 1) + c->x86_max_cores /= smp_num_siblings; + } /* * We may have multiple LLCs if L3 caches exist, so check if we diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9bab7a8a4293..ede03e849a8b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1015,6 +1015,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->x86_model_id[0] = '\0'; /* Unset */ c->x86_max_cores = 1; c->x86_coreid_bits = 0; + c->cu_id = 0xff; #ifdef CONFIG_X86_64 c->x86_clflush_size = 64; c->x86_phys_bits = 36; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 00ef43233e03..537c6647d84c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1373,20 +1373,15 @@ static unsigned long mce_adjust_timer_default(unsigned long interval) static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; -static void __restart_timer(struct timer_list *t, unsigned long interval) +static void __start_timer(struct timer_list *t, unsigned long interval) { unsigned long when = jiffies + interval; unsigned long flags; local_irq_save(flags); - if (timer_pending(t)) { - if (time_before(when, t->expires)) - mod_timer(t, when); - } else { - t->expires = round_jiffies(when); - add_timer_on(t, smp_processor_id()); - } + if (!timer_pending(t) || time_before(when, t->expires)) + mod_timer(t, round_jiffies(when)); local_irq_restore(flags); } @@ -1421,7 +1416,7 @@ static void mce_timer_fn(unsigned long data) done: __this_cpu_write(mce_next_interval, iv); - __restart_timer(t, iv); + __start_timer(t, iv); } /* @@ -1432,7 +1427,7 @@ void mce_timer_kick(unsigned long interval) struct timer_list *t = this_cpu_ptr(&mce_timer); unsigned long iv = __this_cpu_read(mce_next_interval); - __restart_timer(t, interval); + __start_timer(t, interval); if (interval < iv) __this_cpu_write(mce_next_interval, interval); @@ -1779,17 +1774,15 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) } } -static void mce_start_timer(unsigned int cpu, struct timer_list *t) +static void mce_start_timer(struct timer_list *t) { unsigned long iv = check_interval * HZ; if (mca_cfg.ignore_ce || !iv) return; - per_cpu(mce_next_interval, cpu) = iv; - - t->expires = round_jiffies(jiffies + iv); - add_timer_on(t, cpu); + this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); } static void __mcheck_cpu_setup_timer(void) @@ -1806,7 +1799,7 @@ static void __mcheck_cpu_init_timer(void) unsigned int cpu = smp_processor_id(); setup_pinned_timer(t, mce_timer_fn, cpu); - mce_start_timer(cpu, t); + mce_start_timer(t); } /* Handle unconfigured int18 (should never happen) */ @@ -2566,7 +2559,7 @@ static int mce_cpu_dead(unsigned int cpu) static int mce_cpu_online(unsigned int cpu) { - struct timer_list *t = &per_cpu(mce_timer, cpu); + struct timer_list *t = this_cpu_ptr(&mce_timer); int ret; mce_device_create(cpu); @@ -2577,13 +2570,13 @@ static int mce_cpu_online(unsigned int cpu) return ret; } mce_reenable_cpu(); - mce_start_timer(cpu, t); + mce_start_timer(t); return 0; } static int mce_cpu_pre_down(unsigned int cpu) { - struct timer_list *t = &per_cpu(mce_timer, cpu); + struct timer_list *t = this_cpu_ptr(&mce_timer); mce_disable_cpu(); del_timer_sync(t); diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 6a31e2691f3a..079e81733a58 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -384,8 +384,9 @@ void load_ucode_amd_ap(unsigned int family) reget: if (!get_builtin_microcode(&cp, family)) { #ifdef CONFIG_BLK_DEV_INITRD - cp = find_cpio_data(ucode_path, (void *)initrd_start, - initrd_end - initrd_start, NULL); + if (!initrd_gone) + cp = find_cpio_data(ucode_path, (void *)initrd_start, + initrd_end - initrd_start, NULL); #endif if (!(cp.data && cp.size)) { /* diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 2af69d27da62..73102d932760 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -46,6 +46,8 @@ static struct microcode_ops *microcode_ops; static bool dis_ucode_ldr = true; +bool initrd_gone; + LIST_HEAD(microcode_cache); /* @@ -190,21 +192,24 @@ void load_ucode_ap(void) static int __init save_microcode_in_initrd(void) { struct cpuinfo_x86 *c = &boot_cpu_data; + int ret = -EINVAL; switch (c->x86_vendor) { case X86_VENDOR_INTEL: if (c->x86 >= 6) - return save_microcode_in_initrd_intel(); + ret = save_microcode_in_initrd_intel(); break; case X86_VENDOR_AMD: if (c->x86 >= 0x10) - return save_microcode_in_initrd_amd(c->x86); + ret = save_microcode_in_initrd_amd(c->x86); break; default: break; } - return -EINVAL; + initrd_gone = true; + + return ret; } struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) @@ -247,9 +252,16 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) * has the virtual address of the beginning of the initrd. It also * possibly relocates the ramdisk. In either case, initrd_start contains * the updated address so use that instead. + * + * initrd_gone is for the hotplug case where we've thrown out initrd + * already. */ - if (!use_pa && initrd_start) - start = initrd_start; + if (!use_pa) { + if (initrd_gone) + return (struct cpio_data){ NULL, 0, "" }; + if (initrd_start) + start = initrd_start; + } return find_cpio_data(path, (void *)start, size, NULL); #else /* !CONFIG_BLK_DEV_INITRD */ diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 3f329b74e040..8325d8a09ab0 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -41,7 +41,7 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; -/* Current microcode patch used in early patching */ +/* Current microcode patch used in early patching on the APs. */ struct microcode_intel *intel_ucode_patch; static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, @@ -607,12 +607,6 @@ int __init save_microcode_in_initrd_intel(void) struct ucode_cpu_info uci; struct cpio_data cp; - /* - * AP loading didn't find any microcode patch, no need to save anything. - */ - if (!intel_ucode_patch || IS_ERR(intel_ucode_patch)) - return 0; - if (!load_builtin_intel_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path, false); @@ -628,7 +622,6 @@ int __init save_microcode_in_initrd_intel(void) return 0; } - /* * @res_patch, output: a pointer to the patch we found. */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e4e97a5355ce..de7234401275 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -9,6 +9,7 @@ #include <asm/fpu/regset.h> #include <asm/fpu/signal.h> #include <asm/fpu/types.h> +#include <asm/fpu/xstate.h> #include <asm/traps.h> #include <linux/hardirq.h> @@ -183,7 +184,8 @@ void fpstate_init(union fpregs_state *state) * it will #GP. Make sure it is replaced after the memset(). */ if (static_cpu_has(X86_FEATURE_XSAVES)) - state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT; + state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | + xfeatures_mask; if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 85e87b46c318..dc6ba5bda9fc 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -352,6 +352,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer) } else { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq)); irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); disable_irq(hdev->irq); irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 46732dc3b73c..99b920d0e516 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -433,9 +433,15 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) int cpu1 = c->cpu_index, cpu2 = o->cpu_index; if (c->phys_proc_id == o->phys_proc_id && - per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) && - c->cpu_core_id == o->cpu_core_id) - return topology_sane(c, o, "smt"); + per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) { + if (c->cpu_core_id == o->cpu_core_id) + return topology_sane(c, o, "smt"); + + if ((c->cu_id != 0xff) && + (o->cu_id != 0xff) && + (c->cu_id == o->cu_id)) + return topology_sane(c, o, "smt"); + } } else if (c->phys_proc_id == o->phys_proc_id && c->cpu_core_id == o->cpu_core_id) { diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index e41af597aed8..37e7cf544e51 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1356,6 +1356,9 @@ void __init tsc_init(void) (unsigned long)cpu_khz / 1000, (unsigned long)cpu_khz % 1000); + /* Sanitize TSC ADJUST before cyc2ns gets initialized */ + tsc_store_and_check_tsc_adjust(true); + /* * Secondary CPUs do not run through tsc_init(), so set up * all the scale factors for all CPUs, assuming the same @@ -1386,8 +1389,6 @@ void __init tsc_init(void) if (unsynchronized_tsc()) mark_tsc_unstable("TSCs unsynchronized"); - else - tsc_store_and_check_tsc_adjust(true); check_system_tsc_reliable(); diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index d0db011051a5..728f75378475 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -286,13 +286,6 @@ void check_tsc_sync_source(int cpu) if (unsynchronized_tsc()) return; - if (tsc_clocksource_reliable) { - if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING) - pr_info( - "Skipped synchronization checks as TSC is reliable.\n"); - return; - } - /* * Set the maximum number of test runs to * 1 if the CPU does not provide the TSC_ADJUST MSR @@ -380,14 +373,19 @@ void check_tsc_sync_target(void) int cpus = 2; /* Also aborts if there is no TSC. */ - if (unsynchronized_tsc() || tsc_clocksource_reliable) + if (unsynchronized_tsc()) return; /* * Store, verify and sanitize the TSC adjust register. If * successful skip the test. + * + * The test is also skipped when the TSC is marked reliable. This + * is true for SoCs which have no fallback clocksource. On these + * SoCs the TSC is frequency synchronized, but still the TSC ADJUST + * register might have been wreckaged by the BIOS.. */ - if (tsc_store_and_check_tsc_adjust(false)) { + if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable) { atomic_inc(&skip_test); return; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d153be8929a6..e52c9088660f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3182,6 +3182,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) memcpy(dest, xsave, XSAVE_HDR_OFFSET); /* Set XSTATE_BV */ + xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE; *(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv; /* diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index ea9c49adaa1f..8aa6bea1cd6c 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -15,6 +15,7 @@ #include <linux/debugfs.h> #include <linux/mm.h> #include <linux/init.h> +#include <linux/sched.h> #include <linux/seq_file.h> #include <asm/pgtable.h> @@ -406,6 +407,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, } else note_page(m, &st, __pgprot(0), 1); + cond_resched(); start++; } diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 319148bd4b05..2f25a363068c 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -269,6 +269,22 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) efi_scratch.use_pgd = true; /* + * Certain firmware versions are way too sentimential and still believe + * they are exclusive and unquestionable owners of the first physical page, + * even though they explicitly mark it as EFI_CONVENTIONAL_MEMORY + * (but then write-access it later during SetVirtualAddressMap()). + * + * Create a 1:1 mapping for this page, to avoid triple faults during early + * boot with such firmware. We are free to hand this page to the BIOS, + * as trim_bios_range() will reserve the first page and isolate it away + * from memory allocators anyway. + */ + if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, _PAGE_RW)) { + pr_err("Failed to create 1:1 mapping for the first page!\n"); + return 1; + } + + /* * When making calls to the firmware everything needs to be 1:1 * mapped and addressable with 32-bit pointers. Map the kernel * text and allocate a new stack because we can't rely on the diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 848e8568fb3c..8fd4be610607 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -419,7 +419,7 @@ subsys_initcall(topology_init); void cpu_reset(void) { -#if XCHAL_HAVE_PTP_MMU +#if XCHAL_HAVE_PTP_MMU && IS_ENABLED(CONFIG_MMU) local_irq_disable(); /* * We have full MMU: all autoload ways, ways 7, 8 and 9 of DTLB must diff --git a/block/blk-lib.c b/block/blk-lib.c index f8c82a9b4012..ed1e78e24db0 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -306,11 +306,6 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, if (ret == 0 || (ret && ret != -EOPNOTSUPP)) goto out; - ret = __blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask, - ZERO_PAGE(0), biop); - if (ret == 0 || (ret && ret != -EOPNOTSUPP)) - goto out; - ret = 0; while (nr_sects != 0) { bio = next_bio(bio, min(nr_sects, (sector_t)BIO_MAX_PAGES), @@ -369,6 +364,10 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, return 0; } + if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask, + ZERO_PAGE(0))) + return 0; + blk_start_plug(&plug); ret = __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask, &bio, discard); diff --git a/crypto/algapi.c b/crypto/algapi.c index df939b54b09f..1fad2a6b3bbb 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -356,6 +356,7 @@ int crypto_register_alg(struct crypto_alg *alg) struct crypto_larval *larval; int err; + alg->cra_flags &= ~CRYPTO_ALG_DEAD; err = crypto_check_alg(alg); if (err) return err; diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index f849311e9fd4..533265f110e0 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -661,9 +661,9 @@ static int aead_recvmsg_sync(struct socket *sock, struct msghdr *msg, int flags) unlock: list_for_each_entry_safe(rsgl, tmp, &ctx->list, list) { af_alg_free_sg(&rsgl->sgl); + list_del(&rsgl->list); if (rsgl != &ctx->first_rsgl) sock_kfree_s(sk, rsgl, sizeof(*rsgl)); - list_del(&rsgl->list); } INIT_LIST_HEAD(&ctx->list); aead_wmem_wakeup(sk); diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c index 82b0b5710979..b0399e8f6d27 100644 --- a/drivers/acpi/acpica/tbdata.c +++ b/drivers/acpi/acpica/tbdata.c @@ -852,23 +852,18 @@ acpi_tb_install_and_load_table(acpi_physical_address address, ACPI_FUNCTION_TRACE(tb_install_and_load_table); - (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES); - /* Install the table and load it into the namespace */ status = acpi_tb_install_standard_table(address, flags, TRUE, override, &i); if (ACPI_FAILURE(status)) { - goto unlock_and_exit; + goto exit; } - (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); status = acpi_tb_load_table(i, acpi_gbl_root_node); - (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES); -unlock_and_exit: +exit: *table_index = i; - (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); return_ACPI_STATUS(status); } diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c index 5fdf251a9f97..01e1b3d63fc0 100644 --- a/drivers/acpi/acpica/tbinstal.c +++ b/drivers/acpi/acpica/tbinstal.c @@ -217,6 +217,10 @@ acpi_tb_install_standard_table(acpi_physical_address address, goto release_and_exit; } + /* Acquire the table lock */ + + (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES); + if (reload) { /* * Validate the incoming table signature. @@ -244,7 +248,7 @@ acpi_tb_install_standard_table(acpi_physical_address address, new_table_desc.signature.integer)); status = AE_BAD_SIGNATURE; - goto release_and_exit; + goto unlock_and_exit; } /* Check if table is already registered */ @@ -279,7 +283,7 @@ acpi_tb_install_standard_table(acpi_physical_address address, /* Table is still loaded, this is an error */ status = AE_ALREADY_EXISTS; - goto release_and_exit; + goto unlock_and_exit; } else { /* * Table was unloaded, allow it to be reloaded. @@ -290,6 +294,7 @@ acpi_tb_install_standard_table(acpi_physical_address address, * indicate the re-installation. */ acpi_tb_uninstall_table(&new_table_desc); + (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); *table_index = i; return_ACPI_STATUS(AE_OK); } @@ -303,11 +308,19 @@ acpi_tb_install_standard_table(acpi_physical_address address, /* Invoke table handler if present */ + (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); if (acpi_gbl_table_handler) { (void)acpi_gbl_table_handler(ACPI_TABLE_EVENT_INSTALL, new_table_desc.pointer, acpi_gbl_table_handler_context); } + (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES); + +unlock_and_exit: + + /* Release the table lock */ + + (void)acpi_ut_release_mutex(ACPI_MTX_TABLES); release_and_exit: diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 2f82b8eba360..7361d00818e2 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2704,6 +2704,7 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc) struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc); struct device *dev = acpi_desc->dev; struct acpi_nfit_flush_work flush; + int rc; /* bounce the device lock to flush acpi_nfit_add / acpi_nfit_notify */ device_lock(dev); @@ -2716,7 +2717,10 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc) INIT_WORK_ONSTACK(&flush.work, flush_probe); COMPLETION_INITIALIZER_ONSTACK(flush.cmp); queue_work(nfit_wq, &flush.work); - return wait_for_completion_interruptible(&flush.cmp); + + rc = wait_for_completion_interruptible(&flush.cmp); + cancel_work_sync(&flush.work); + return rc; } static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc, diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 9b6cebe227a0..54abb26b7366 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -674,14 +674,6 @@ static void acpi_sleep_suspend_setup(void) if (acpi_sleep_state_supported(i)) sleep_states[i] = 1; - /* - * Use suspend-to-idle by default if ACPI_FADT_LOW_POWER_S0 is set and - * the default suspend mode was not selected from the command line. - */ - if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0 && - mem_sleep_default > PM_SUSPEND_MEM) - mem_sleep_default = PM_SUSPEND_FREEZE; - suspend_set_ops(old_suspend_ordering ? &acpi_suspend_ops_old : &acpi_suspend_ops); freeze_set_ops(&acpi_freeze_ops); diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 02ded25c82e4..7f48156cbc0c 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -305,17 +305,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Dell System XPS L702X"), }, }, - { - /* https://bugzilla.redhat.com/show_bug.cgi?id=1204476 */ - /* https://bugs.launchpad.net/ubuntu/+source/linux-lts-trusty/+bug/1416940 */ - .callback = video_detect_force_native, - .ident = "HP Pavilion dv6", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv6 Notebook PC"), - }, - }, - { }, }; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 9cd0a2d41816..c2d3785ec227 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -1702,6 +1702,8 @@ unsigned ata_exec_internal_sg(struct ata_device *dev, if (qc->err_mask & ~AC_ERR_OTHER) qc->err_mask &= ~AC_ERR_OTHER; + } else if (qc->tf.command == ATA_CMD_REQ_SENSE_DATA) { + qc->result_tf.command |= ATA_SENSE; } /* finish up */ @@ -4356,10 +4358,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "ST380013AS", "3.20", ATA_HORKAGE_MAX_SEC_1024 }, /* - * Device times out with higher max sects. + * These devices time out with higher max sects. * https://bugzilla.kernel.org/show_bug.cgi?id=121671 */ - { "LITEON CX1-JB256-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 }, + { "LITEON CX1-JB*-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 }, /* Devices we expect to fail diagnostics */ diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index 823e938c9a78..2f32782cea6d 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -4132,6 +4132,9 @@ static int mv_platform_probe(struct platform_device *pdev) host->iomap = NULL; hpriv->base = devm_ioremap(&pdev->dev, res->start, resource_size(res)); + if (!hpriv->base) + return -ENOMEM; + hpriv->base -= SATAHC0_REG_BASE; hpriv->clk = clk_get(&pdev->dev, NULL); diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index 4497d263209f..ac350c518e0c 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -558,9 +558,6 @@ static void fw_load_abort(struct firmware_priv *fw_priv) struct firmware_buf *buf = fw_priv->buf; __fw_load_abort(buf); - - /* avoid user action after loading abort */ - fw_priv->buf = NULL; } static LIST_HEAD(pending_fw_head); @@ -713,7 +710,7 @@ static ssize_t firmware_loading_store(struct device *dev, mutex_lock(&fw_lock); fw_buf = fw_priv->buf; - if (!fw_buf) + if (fw_state_is_aborted(&fw_buf->fw_st)) goto out; switch (loading) { diff --git a/drivers/base/memory.c b/drivers/base/memory.c index dacb6a8418aa..fa26ffd25fa6 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -389,33 +389,33 @@ static ssize_t show_valid_zones(struct device *dev, { struct memory_block *mem = to_memory_block(dev); unsigned long start_pfn, end_pfn; + unsigned long valid_start, valid_end, valid_pages; unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; - struct page *first_page; struct zone *zone; int zone_shift = 0; start_pfn = section_nr_to_pfn(mem->start_section_nr); end_pfn = start_pfn + nr_pages; - first_page = pfn_to_page(start_pfn); /* The block contains more than one zone can not be offlined. */ - if (!test_pages_in_a_zone(start_pfn, end_pfn)) + if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) return sprintf(buf, "none\n"); - zone = page_zone(first_page); + zone = page_zone(pfn_to_page(valid_start)); + valid_pages = valid_end - valid_start; /* MMOP_ONLINE_KEEP */ sprintf(buf, "%s", zone->name); /* MMOP_ONLINE_KERNEL */ - zone_can_shift(start_pfn, nr_pages, ZONE_NORMAL, &zone_shift); + zone_can_shift(valid_start, valid_pages, ZONE_NORMAL, &zone_shift); if (zone_shift) { strcat(buf, " "); strcat(buf, (zone + zone_shift)->name); } /* MMOP_ONLINE_MOVABLE */ - zone_can_shift(start_pfn, nr_pages, ZONE_MOVABLE, &zone_shift); + zone_can_shift(valid_start, valid_pages, ZONE_MOVABLE, &zone_shift); if (zone_shift) { strcat(buf, " "); strcat(buf, (zone + zone_shift)->name); diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 872eac4cb1df..a14fac6a01d3 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -966,13 +966,13 @@ int __pm_runtime_idle(struct device *dev, int rpmflags) unsigned long flags; int retval; - might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); - if (rpmflags & RPM_GET_PUT) { if (!atomic_dec_and_test(&dev->power.usage_count)) return 0; } + might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); + spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_idle(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); @@ -998,13 +998,13 @@ int __pm_runtime_suspend(struct device *dev, int rpmflags) unsigned long flags; int retval; - might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); - if (rpmflags & RPM_GET_PUT) { if (!atomic_dec_and_test(&dev->power.usage_count)) return 0; } + might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); + spin_lock_irqsave(&dev->power.lock, flags); retval = rpm_suspend(dev, rpmflags); spin_unlock_irqrestore(&dev->power.lock, flags); @@ -1029,7 +1029,8 @@ int __pm_runtime_resume(struct device *dev, int rpmflags) unsigned long flags; int retval; - might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe); + might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe && + dev->power.runtime_status != RPM_ACTIVE); if (rpmflags & RPM_GET_PUT) atomic_inc(&dev->power.usage_count); diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h index f642c4264c27..168fa175d65a 100644 --- a/drivers/bcma/bcma_private.h +++ b/drivers/bcma/bcma_private.h @@ -45,6 +45,9 @@ int bcma_sprom_get(struct bcma_bus *bus); void bcma_core_chipcommon_early_init(struct bcma_drv_cc *cc); void bcma_core_chipcommon_init(struct bcma_drv_cc *cc); void bcma_chipco_bcm4331_ext_pa_lines_ctl(struct bcma_drv_cc *cc, bool enable); +#ifdef CONFIG_BCMA_DRIVER_MIPS +void bcma_chipco_serial_init(struct bcma_drv_cc *cc); +#endif /* CONFIG_BCMA_DRIVER_MIPS */ /* driver_chipcommon_b.c */ int bcma_core_chipcommon_b_init(struct bcma_drv_cc_b *ccb); diff --git a/drivers/bcma/driver_chipcommon.c b/drivers/bcma/driver_chipcommon.c index b4f6520e74f0..62f5bfa5065d 100644 --- a/drivers/bcma/driver_chipcommon.c +++ b/drivers/bcma/driver_chipcommon.c @@ -15,8 +15,6 @@ #include <linux/platform_device.h> #include <linux/bcma/bcma.h> -static void bcma_chipco_serial_init(struct bcma_drv_cc *cc); - static inline u32 bcma_cc_write32_masked(struct bcma_drv_cc *cc, u16 offset, u32 mask, u32 value) { @@ -186,9 +184,6 @@ void bcma_core_chipcommon_early_init(struct bcma_drv_cc *cc) if (cc->capabilities & BCMA_CC_CAP_PMU) bcma_pmu_early_init(cc); - if (IS_BUILTIN(CONFIG_BCM47XX) && bus->hosttype == BCMA_HOSTTYPE_SOC) - bcma_chipco_serial_init(cc); - if (bus->hosttype == BCMA_HOSTTYPE_SOC) bcma_core_chipcommon_flash_detect(cc); @@ -378,9 +373,9 @@ u32 bcma_chipco_gpio_pulldown(struct bcma_drv_cc *cc, u32 mask, u32 value) return res; } -static void bcma_chipco_serial_init(struct bcma_drv_cc *cc) +#ifdef CONFIG_BCMA_DRIVER_MIPS +void bcma_chipco_serial_init(struct bcma_drv_cc *cc) { -#if IS_BUILTIN(CONFIG_BCM47XX) unsigned int irq; u32 baud_base; u32 i; @@ -422,5 +417,5 @@ static void bcma_chipco_serial_init(struct bcma_drv_cc *cc) ports[i].baud_base = baud_base; ports[i].reg_shift = 0; } -#endif /* CONFIG_BCM47XX */ } +#endif /* CONFIG_BCMA_DRIVER_MIPS */ diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c index 96f171328200..89af807cf29c 100644 --- a/drivers/bcma/driver_mips.c +++ b/drivers/bcma/driver_mips.c @@ -278,9 +278,12 @@ static void bcma_core_mips_nvram_init(struct bcma_drv_mips *mcore) void bcma_core_mips_early_init(struct bcma_drv_mips *mcore) { + struct bcma_bus *bus = mcore->core->bus; + if (mcore->early_setup_done) return; + bcma_chipco_serial_init(&bus->drv_cc); bcma_core_mips_nvram_init(mcore); mcore->early_setup_done = true; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index b2bdfa81f929..265f1a7072e9 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -197,13 +197,13 @@ struct blkfront_info /* Number of pages per ring buffer. */ unsigned int nr_ring_pages; struct request_queue *rq; - unsigned int feature_flush; - unsigned int feature_fua; + unsigned int feature_flush:1; + unsigned int feature_fua:1; unsigned int feature_discard:1; unsigned int feature_secdiscard:1; + unsigned int feature_persistent:1; unsigned int discard_granularity; unsigned int discard_alignment; - unsigned int feature_persistent:1; /* Number of 4KB segments handled */ unsigned int max_indirect_segments; int is_ready; @@ -2223,7 +2223,7 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo) } else grants = info->max_indirect_segments; - psegs = grants / GRANTS_PER_PSEG; + psegs = DIV_ROUND_UP(grants, GRANTS_PER_PSEG); err = fill_grant_buffer(rinfo, (grants + INDIRECT_GREFS(grants)) * BLK_RING_SIZE(info)); @@ -2323,13 +2323,16 @@ static void blkfront_gather_backend_features(struct blkfront_info *info) blkfront_setup_discard(info); info->feature_persistent = - xenbus_read_unsigned(info->xbdev->otherend, - "feature-persistent", 0); + !!xenbus_read_unsigned(info->xbdev->otherend, + "feature-persistent", 0); indirect_segments = xenbus_read_unsigned(info->xbdev->otherend, "feature-max-indirect-segments", 0); - info->max_indirect_segments = min(indirect_segments, - xen_blkif_max_segments); + if (indirect_segments > xen_blkif_max_segments) + indirect_segments = xen_blkif_max_segments; + if (indirect_segments <= BLKIF_MAX_SEGMENTS_PER_REQUEST) + indirect_segments = 0; + info->max_indirect_segments = indirect_segments; } /* @@ -2652,6 +2655,9 @@ static int __init xlblk_init(void) if (!xen_domain()) return -ENODEV; + if (xen_blkif_max_segments < BLKIF_MAX_SEGMENTS_PER_REQUEST) + xen_blkif_max_segments = BLKIF_MAX_SEGMENTS_PER_REQUEST; + if (xen_blkif_max_ring_order > XENBUS_MAX_RING_GRANT_ORDER) { pr_info("Invalid max_ring_order (%d), will use default max: %d.\n", xen_blkif_max_ring_order, XENBUS_MAX_RING_GRANT_ORDER); diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index 6ce5ce8be2f2..87fba424817e 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -92,7 +92,6 @@ static void add_early_randomness(struct hwrng *rng) mutex_unlock(&reading_mutex); if (bytes_read > 0) add_device_randomness(rng_buffer, bytes_read); - memset(rng_buffer, 0, size); } static inline void cleanup_rng(struct kref *kref) @@ -288,7 +287,6 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf, } } out: - memset(rng_buffer, 0, rng_buffer_size()); return ret ? : err; out_unlock_reading: @@ -427,7 +425,6 @@ static int hwrng_fillfn(void *unused) /* Outside lock, sure, but y'know: randomness. */ add_hwgenerator_randomness((void *)rng_fillbuf, rc, rc * current_quality * 8 >> 10); - memset(rng_fillbuf, 0, rng_buffer_size()); } hwrng_fill = NULL; return 0; diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c index 4fda623e55bb..c94360671f41 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -784,8 +784,19 @@ static int brcm_avs_target_index(struct cpufreq_policy *policy, static int brcm_avs_suspend(struct cpufreq_policy *policy) { struct private_data *priv = policy->driver_data; + int ret; + + ret = brcm_avs_get_pmap(priv, &priv->pmap); + if (ret) + return ret; - return brcm_avs_get_pmap(priv, &priv->pmap); + /* + * We can't use the P-state returned by brcm_avs_get_pmap(), since + * that's the initial P-state from when the P-map was downloaded to the + * AVS co-processor, not necessarily the P-state we are running at now. + * So, we get the current P-state explicitly. + */ + return brcm_avs_get_pstate(priv, &priv->pmap.state); } static int brcm_avs_resume(struct cpufreq_policy *policy) @@ -954,9 +965,9 @@ static ssize_t show_brcm_avs_pmap(struct cpufreq_policy *policy, char *buf) brcm_avs_parse_p1(pmap.p1, &mdiv_p0, &pdiv, &ndiv); brcm_avs_parse_p2(pmap.p2, &mdiv_p1, &mdiv_p2, &mdiv_p3, &mdiv_p4); - return sprintf(buf, "0x%08x 0x%08x %u %u %u %u %u %u %u\n", + return sprintf(buf, "0x%08x 0x%08x %u %u %u %u %u %u %u %u %u\n", pmap.p1, pmap.p2, ndiv, pdiv, mdiv_p0, mdiv_p1, mdiv_p2, - mdiv_p3, mdiv_p4); + mdiv_p3, mdiv_p4, pmap.mode, pmap.state); } static ssize_t show_brcm_avs_voltage(struct cpufreq_policy *policy, char *buf) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index f91c25718d16..50bd6d987fc3 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1235,6 +1235,25 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata) cpudata->epp_default = intel_pstate_get_epp(cpudata, 0); } +#define MSR_IA32_POWER_CTL_BIT_EE 19 + +/* Disable energy efficiency optimization */ +static void intel_pstate_disable_ee(int cpu) +{ + u64 power_ctl; + int ret; + + ret = rdmsrl_on_cpu(cpu, MSR_IA32_POWER_CTL, &power_ctl); + if (ret) + return; + + if (!(power_ctl & BIT(MSR_IA32_POWER_CTL_BIT_EE))) { + pr_info("Disabling energy efficiency optimization\n"); + power_ctl |= BIT(MSR_IA32_POWER_CTL_BIT_EE); + wrmsrl_on_cpu(cpu, MSR_IA32_POWER_CTL, power_ctl); + } +} + static int atom_get_min_pstate(void) { u64 value; @@ -1845,6 +1864,11 @@ static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = { {} }; +static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = { + ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, core_params), + {} +}; + static int intel_pstate_init_cpu(unsigned int cpunum) { struct cpudata *cpu; @@ -1875,6 +1899,12 @@ static int intel_pstate_init_cpu(unsigned int cpunum) cpu->cpu = cpunum; if (hwp_active) { + const struct x86_cpu_id *id; + + id = x86_match_cpu(intel_pstate_cpu_ee_disable_ids); + if (id) + intel_pstate_disable_ee(cpunum); + intel_pstate_hwp_enable(cpu); pid_params.sample_rate_ms = 50; pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC; @@ -2005,7 +2035,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy) limits = &performance_limits; perf_limits = limits; } - if (policy->max >= policy->cpuinfo.max_freq) { + if (policy->max >= policy->cpuinfo.max_freq && + !limits->no_turbo) { pr_debug("set performance\n"); intel_pstate_set_performance_limits(perf_limits); goto out; @@ -2047,6 +2078,17 @@ static int intel_pstate_verify_policy(struct cpufreq_policy *policy) policy->policy != CPUFREQ_POLICY_PERFORMANCE) return -EINVAL; + /* When per-CPU limits are used, sysfs limits are not used */ + if (!per_cpu_limits) { + unsigned int max_freq, min_freq; + + max_freq = policy->cpuinfo.max_freq * + limits->max_sysfs_pct / 100; + min_freq = policy->cpuinfo.max_freq * + limits->min_sysfs_pct / 100; + cpufreq_verify_within_limits(policy, min_freq, max_freq); + } + return 0; } diff --git a/drivers/crypto/ccp/ccp-dev-v5.c b/drivers/crypto/ccp/ccp-dev-v5.c index e2ce8190ecc9..612898b4aaad 100644 --- a/drivers/crypto/ccp/ccp-dev-v5.c +++ b/drivers/crypto/ccp/ccp-dev-v5.c @@ -959,7 +959,7 @@ static irqreturn_t ccp5_irq_handler(int irq, void *data) static void ccp5_config(struct ccp_device *ccp) { /* Public side */ - iowrite32(0x00001249, ccp->io_regs + CMD5_REQID_CONFIG_OFFSET); + iowrite32(0x0, ccp->io_regs + CMD5_REQID_CONFIG_OFFSET); } static void ccp5other_config(struct ccp_device *ccp) diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h index 830f35e6005f..649e5610a5ce 100644 --- a/drivers/crypto/ccp/ccp-dev.h +++ b/drivers/crypto/ccp/ccp-dev.h @@ -238,6 +238,7 @@ struct ccp_dma_chan { struct ccp_device *ccp; spinlock_t lock; + struct list_head created; struct list_head pending; struct list_head active; struct list_head complete; diff --git a/drivers/crypto/ccp/ccp-dmaengine.c b/drivers/crypto/ccp/ccp-dmaengine.c index 6553912804f7..e5d9278f4019 100644 --- a/drivers/crypto/ccp/ccp-dmaengine.c +++ b/drivers/crypto/ccp/ccp-dmaengine.c @@ -63,6 +63,7 @@ static void ccp_free_chan_resources(struct dma_chan *dma_chan) ccp_free_desc_resources(chan->ccp, &chan->complete); ccp_free_desc_resources(chan->ccp, &chan->active); ccp_free_desc_resources(chan->ccp, &chan->pending); + ccp_free_desc_resources(chan->ccp, &chan->created); spin_unlock_irqrestore(&chan->lock, flags); } @@ -273,6 +274,7 @@ static dma_cookie_t ccp_tx_submit(struct dma_async_tx_descriptor *tx_desc) spin_lock_irqsave(&chan->lock, flags); cookie = dma_cookie_assign(tx_desc); + list_del(&desc->entry); list_add_tail(&desc->entry, &chan->pending); spin_unlock_irqrestore(&chan->lock, flags); @@ -426,7 +428,7 @@ static struct ccp_dma_desc *ccp_create_desc(struct dma_chan *dma_chan, spin_lock_irqsave(&chan->lock, sflags); - list_add_tail(&desc->entry, &chan->pending); + list_add_tail(&desc->entry, &chan->created); spin_unlock_irqrestore(&chan->lock, sflags); @@ -610,6 +612,7 @@ static int ccp_terminate_all(struct dma_chan *dma_chan) /*TODO: Purge the complete list? */ ccp_free_desc_resources(chan->ccp, &chan->active); ccp_free_desc_resources(chan->ccp, &chan->pending); + ccp_free_desc_resources(chan->ccp, &chan->created); spin_unlock_irqrestore(&chan->lock, flags); @@ -679,6 +682,7 @@ int ccp_dmaengine_register(struct ccp_device *ccp) chan->ccp = ccp; spin_lock_init(&chan->lock); + INIT_LIST_HEAD(&chan->created); INIT_LIST_HEAD(&chan->pending); INIT_LIST_HEAD(&chan->active); INIT_LIST_HEAD(&chan->complete); diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c index 2ed1e24b44a8..b4b78b37f8a6 100644 --- a/drivers/crypto/chelsio/chcr_algo.c +++ b/drivers/crypto/chelsio/chcr_algo.c @@ -158,7 +158,7 @@ int chcr_handle_resp(struct crypto_async_request *req, unsigned char *input, case CRYPTO_ALG_TYPE_AEAD: ctx_req.req.aead_req = (struct aead_request *)req; ctx_req.ctx.reqctx = aead_request_ctx(ctx_req.req.aead_req); - dma_unmap_sg(&u_ctx->lldi.pdev->dev, ctx_req.req.aead_req->dst, + dma_unmap_sg(&u_ctx->lldi.pdev->dev, ctx_req.ctx.reqctx->dst, ctx_req.ctx.reqctx->dst_nents, DMA_FROM_DEVICE); if (ctx_req.ctx.reqctx->skb) { kfree_skb(ctx_req.ctx.reqctx->skb); @@ -1362,8 +1362,7 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req, struct chcr_wr *chcr_req; struct cpl_rx_phys_dsgl *phys_cpl; struct phys_sge_parm sg_param; - struct scatterlist *src, *dst; - struct scatterlist src_sg[2], dst_sg[2]; + struct scatterlist *src; unsigned int frags = 0, transhdr_len; unsigned int ivsize = crypto_aead_ivsize(tfm), dst_size = 0; unsigned int kctx_len = 0; @@ -1383,19 +1382,21 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req, if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0) goto err; - src = scatterwalk_ffwd(src_sg, req->src, req->assoclen); - dst = src; + src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen); + reqctx->dst = src; + if (req->src != req->dst) { err = chcr_copy_assoc(req, aeadctx); if (err) return ERR_PTR(err); - dst = scatterwalk_ffwd(dst_sg, req->dst, req->assoclen); + reqctx->dst = scatterwalk_ffwd(reqctx->dstffwd, req->dst, + req->assoclen); } if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_NULL) { null = 1; assoclen = 0; } - reqctx->dst_nents = sg_nents_for_len(dst, req->cryptlen + + reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen + (op_type ? -authsize : authsize)); if (reqctx->dst_nents <= 0) { pr_err("AUTHENC:Invalid Destination sg entries\n"); @@ -1460,7 +1461,7 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req, sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize); sg_param.qid = qid; sg_param.align = 0; - if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, dst, + if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, reqctx->dst, &sg_param)) goto dstmap_fail; @@ -1711,8 +1712,7 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req, struct chcr_wr *chcr_req; struct cpl_rx_phys_dsgl *phys_cpl; struct phys_sge_parm sg_param; - struct scatterlist *src, *dst; - struct scatterlist src_sg[2], dst_sg[2]; + struct scatterlist *src; unsigned int frags = 0, transhdr_len, ivsize = AES_BLOCK_SIZE; unsigned int dst_size = 0, kctx_len; unsigned int sub_type; @@ -1728,17 +1728,19 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req, if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0) goto err; sub_type = get_aead_subtype(tfm); - src = scatterwalk_ffwd(src_sg, req->src, req->assoclen); - dst = src; + src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen); + reqctx->dst = src; + if (req->src != req->dst) { err = chcr_copy_assoc(req, aeadctx); if (err) { pr_err("AAD copy to destination buffer fails\n"); return ERR_PTR(err); } - dst = scatterwalk_ffwd(dst_sg, req->dst, req->assoclen); + reqctx->dst = scatterwalk_ffwd(reqctx->dstffwd, req->dst, + req->assoclen); } - reqctx->dst_nents = sg_nents_for_len(dst, req->cryptlen + + reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen + (op_type ? -authsize : authsize)); if (reqctx->dst_nents <= 0) { pr_err("CCM:Invalid Destination sg entries\n"); @@ -1777,7 +1779,7 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req, sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize); sg_param.qid = qid; sg_param.align = 0; - if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, dst, + if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, reqctx->dst, &sg_param)) goto dstmap_fail; @@ -1809,8 +1811,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req, struct chcr_wr *chcr_req; struct cpl_rx_phys_dsgl *phys_cpl; struct phys_sge_parm sg_param; - struct scatterlist *src, *dst; - struct scatterlist src_sg[2], dst_sg[2]; + struct scatterlist *src; unsigned int frags = 0, transhdr_len; unsigned int ivsize = AES_BLOCK_SIZE; unsigned int dst_size = 0, kctx_len; @@ -1832,13 +1833,14 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req, if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0) goto err; - src = scatterwalk_ffwd(src_sg, req->src, req->assoclen); - dst = src; + src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen); + reqctx->dst = src; if (req->src != req->dst) { err = chcr_copy_assoc(req, aeadctx); if (err) return ERR_PTR(err); - dst = scatterwalk_ffwd(dst_sg, req->dst, req->assoclen); + reqctx->dst = scatterwalk_ffwd(reqctx->dstffwd, req->dst, + req->assoclen); } if (!req->cryptlen) @@ -1848,7 +1850,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req, crypt_len = AES_BLOCK_SIZE; else crypt_len = req->cryptlen; - reqctx->dst_nents = sg_nents_for_len(dst, req->cryptlen + + reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen + (op_type ? -authsize : authsize)); if (reqctx->dst_nents <= 0) { pr_err("GCM:Invalid Destination sg entries\n"); @@ -1923,7 +1925,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req, sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize); sg_param.qid = qid; sg_param.align = 0; - if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, dst, + if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, reqctx->dst, &sg_param)) goto dstmap_fail; @@ -1937,7 +1939,8 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req, write_sg_to_skb(skb, &frags, src, req->cryptlen); } else { aes_gcm_empty_pld_pad(req->dst, authsize - 1); - write_sg_to_skb(skb, &frags, dst, crypt_len); + write_sg_to_skb(skb, &frags, reqctx->dst, crypt_len); + } create_wreq(ctx, chcr_req, req, skb, kctx_len, size, 1, @@ -2189,8 +2192,8 @@ static int chcr_gcm_setkey(struct crypto_aead *aead, const u8 *key, unsigned int ck_size; int ret = 0, key_ctx_size = 0; - if (get_aead_subtype(aead) == - CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106) { + if (get_aead_subtype(aead) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106 && + keylen > 3) { keylen -= 4; /* nonce/salt is present in the last 4 bytes */ memcpy(aeadctx->salt, key + keylen, 4); } diff --git a/drivers/crypto/chelsio/chcr_core.c b/drivers/crypto/chelsio/chcr_core.c index 918da8e6e2d8..1c65f07e1cc9 100644 --- a/drivers/crypto/chelsio/chcr_core.c +++ b/drivers/crypto/chelsio/chcr_core.c @@ -52,6 +52,7 @@ static struct cxgb4_uld_info chcr_uld_info = { int assign_chcr_device(struct chcr_dev **dev) { struct uld_ctx *u_ctx; + int ret = -ENXIO; /* * Which device to use if multiple devices are available TODO @@ -59,15 +60,14 @@ int assign_chcr_device(struct chcr_dev **dev) * must go to the same device to maintain the ordering. */ mutex_lock(&dev_mutex); /* TODO ? */ - u_ctx = list_first_entry(&uld_ctx_list, struct uld_ctx, entry); - if (!u_ctx) { - mutex_unlock(&dev_mutex); - return -ENXIO; + list_for_each_entry(u_ctx, &uld_ctx_list, entry) + if (u_ctx && u_ctx->dev) { + *dev = u_ctx->dev; + ret = 0; + break; } - - *dev = u_ctx->dev; mutex_unlock(&dev_mutex); - return 0; + return ret; } static int chcr_dev_add(struct uld_ctx *u_ctx) @@ -202,10 +202,8 @@ static int chcr_uld_state_change(void *handle, enum cxgb4_state state) static int __init chcr_crypto_init(void) { - if (cxgb4_register_uld(CXGB4_ULD_CRYPTO, &chcr_uld_info)) { + if (cxgb4_register_uld(CXGB4_ULD_CRYPTO, &chcr_uld_info)) pr_err("ULD register fail: No chcr crypto support in cxgb4"); - return -1; - } return 0; } diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h index d5af7d64a763..7ec0a8f12475 100644 --- a/drivers/crypto/chelsio/chcr_crypto.h +++ b/drivers/crypto/chelsio/chcr_crypto.h @@ -158,6 +158,9 @@ struct ablk_ctx { }; struct chcr_aead_reqctx { struct sk_buff *skb; + struct scatterlist *dst; + struct scatterlist srcffwd[2]; + struct scatterlist dstffwd[2]; short int dst_nents; u16 verify; u8 iv[CHCR_MAX_CRYPTO_IV_LEN]; diff --git a/drivers/crypto/qat/qat_c62x/adf_drv.c b/drivers/crypto/qat/qat_c62x/adf_drv.c index bc5cbc193aae..5b2d78a5b5aa 100644 --- a/drivers/crypto/qat/qat_c62x/adf_drv.c +++ b/drivers/crypto/qat/qat_c62x/adf_drv.c @@ -233,7 +233,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) &hw_data->accel_capabilities_mask); /* Find and map all the device's BARS */ - i = 0; + i = (hw_data->fuses & ADF_DEVICE_FUSECTL_MASK) ? 1 : 0; bar_mask = pci_select_bars(pdev, IORESOURCE_MEM); for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask, ADF_PCI_MAX_BARS * 2) { diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h index e8822536530b..33f0a6251e38 100644 --- a/drivers/crypto/qat/qat_common/adf_accel_devices.h +++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h @@ -69,6 +69,7 @@ #define ADF_ERRSOU5 (0x3A000 + 0xD8) #define ADF_DEVICE_FUSECTL_OFFSET 0x40 #define ADF_DEVICE_LEGFUSE_OFFSET 0x4C +#define ADF_DEVICE_FUSECTL_MASK 0x80000000 #define ADF_PCI_MAX_BARS 3 #define ADF_DEVICE_NAME_LENGTH 32 #define ADF_ETR_MAX_RINGS_PER_BANK 16 diff --git a/drivers/crypto/qat/qat_common/qat_hal.c b/drivers/crypto/qat/qat_common/qat_hal.c index 1e480f140663..8c4fd255a601 100644 --- a/drivers/crypto/qat/qat_common/qat_hal.c +++ b/drivers/crypto/qat/qat_common/qat_hal.c @@ -456,7 +456,7 @@ static int qat_hal_init_esram(struct icp_qat_fw_loader_handle *handle) unsigned int csr_val; int times = 30; - if (handle->pci_dev->device == ADF_C3XXX_PCI_DEVICE_ID) + if (handle->pci_dev->device != ADF_DH895XCC_PCI_DEVICE_ID) return 0; csr_val = ADF_CSR_RD(csr_addr, 0); @@ -716,7 +716,7 @@ int qat_hal_init(struct adf_accel_dev *accel_dev) (void __iomem *)((uintptr_t)handle->hal_cap_ae_xfer_csr_addr_v + LOCAL_TO_XFER_REG_OFFSET); handle->pci_dev = pci_info->pci_dev; - if (handle->pci_dev->device != ADF_C3XXX_PCI_DEVICE_ID) { + if (handle->pci_dev->device == ADF_DH895XCC_PCI_DEVICE_ID) { sram_bar = &pci_info->pci_bars[hw_data->get_sram_bar_id(hw_data)]; handle->hal_sram_addr_v = sram_bar->virt_addr; diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c index d5ba43a87a68..200828c60db9 100644 --- a/drivers/dma/cppi41.c +++ b/drivers/dma/cppi41.c @@ -153,6 +153,8 @@ struct cppi41_dd { /* context for suspend/resume */ unsigned int dma_tdfdq; + + bool is_suspended; }; #define FIST_COMPLETION_QUEUE 93 @@ -257,6 +259,10 @@ static struct cppi41_channel *desc_to_chan(struct cppi41_dd *cdd, u32 desc) BUG_ON(desc_num >= ALLOC_DECS_NUM); c = cdd->chan_busy[desc_num]; cdd->chan_busy[desc_num] = NULL; + + /* Usecount for chan_busy[], paired with push_desc_queue() */ + pm_runtime_put(cdd->ddev.dev); + return c; } @@ -317,12 +323,12 @@ static irqreturn_t cppi41_irq(int irq, void *data) while (val) { u32 desc, len; - int error; - error = pm_runtime_get(cdd->ddev.dev); - if (error < 0) - dev_err(cdd->ddev.dev, "%s pm runtime get: %i\n", - __func__, error); + /* + * This should never trigger, see the comments in + * push_desc_queue() + */ + WARN_ON(cdd->is_suspended); q_num = __fls(val); val &= ~(1 << q_num); @@ -343,9 +349,6 @@ static irqreturn_t cppi41_irq(int irq, void *data) c->residue = pd_trans_len(c->desc->pd6) - len; dma_cookie_complete(&c->txd); dmaengine_desc_get_callback_invoke(&c->txd, NULL); - - pm_runtime_mark_last_busy(cdd->ddev.dev); - pm_runtime_put_autosuspend(cdd->ddev.dev); } } return IRQ_HANDLED; @@ -447,6 +450,15 @@ static void push_desc_queue(struct cppi41_channel *c) */ __iowmb(); + /* + * DMA transfers can take at least 200ms to complete with USB mass + * storage connected. To prevent autosuspend timeouts, we must use + * pm_runtime_get/put() when chan_busy[] is modified. This will get + * cleared in desc_to_chan() or cppi41_stop_chan() depending on the + * outcome of the transfer. + */ + pm_runtime_get(cdd->ddev.dev); + desc_phys = lower_32_bits(c->desc_phys); desc_num = (desc_phys - cdd->descs_phys) / sizeof(struct cppi41_desc); WARN_ON(cdd->chan_busy[desc_num]); @@ -457,20 +469,26 @@ static void push_desc_queue(struct cppi41_channel *c) cppi_writel(reg, cdd->qmgr_mem + QMGR_QUEUE_D(c->q_num)); } -static void pending_desc(struct cppi41_channel *c) +/* + * Caller must hold cdd->lock to prevent push_desc_queue() + * getting called out of order. We have both cppi41_dma_issue_pending() + * and cppi41_runtime_resume() call this function. + */ +static void cppi41_run_queue(struct cppi41_dd *cdd) { - struct cppi41_dd *cdd = c->cdd; - unsigned long flags; + struct cppi41_channel *c, *_c; - spin_lock_irqsave(&cdd->lock, flags); - list_add_tail(&c->node, &cdd->pending); - spin_unlock_irqrestore(&cdd->lock, flags); + list_for_each_entry_safe(c, _c, &cdd->pending, node) { + push_desc_queue(c); + list_del(&c->node); + } } static void cppi41_dma_issue_pending(struct dma_chan *chan) { struct cppi41_channel *c = to_cpp41_chan(chan); struct cppi41_dd *cdd = c->cdd; + unsigned long flags; int error; error = pm_runtime_get(cdd->ddev.dev); @@ -482,10 +500,11 @@ static void cppi41_dma_issue_pending(struct dma_chan *chan) return; } - if (likely(pm_runtime_active(cdd->ddev.dev))) - push_desc_queue(c); - else - pending_desc(c); + spin_lock_irqsave(&cdd->lock, flags); + list_add_tail(&c->node, &cdd->pending); + if (!cdd->is_suspended) + cppi41_run_queue(cdd); + spin_unlock_irqrestore(&cdd->lock, flags); pm_runtime_mark_last_busy(cdd->ddev.dev); pm_runtime_put_autosuspend(cdd->ddev.dev); @@ -705,6 +724,9 @@ static int cppi41_stop_chan(struct dma_chan *chan) WARN_ON(!cdd->chan_busy[desc_num]); cdd->chan_busy[desc_num] = NULL; + /* Usecount for chan_busy[], paired with push_desc_queue() */ + pm_runtime_put(cdd->ddev.dev); + return 0; } @@ -1150,8 +1172,12 @@ static int __maybe_unused cppi41_resume(struct device *dev) static int __maybe_unused cppi41_runtime_suspend(struct device *dev) { struct cppi41_dd *cdd = dev_get_drvdata(dev); + unsigned long flags; + spin_lock_irqsave(&cdd->lock, flags); + cdd->is_suspended = true; WARN_ON(!list_empty(&cdd->pending)); + spin_unlock_irqrestore(&cdd->lock, flags); return 0; } @@ -1159,14 +1185,11 @@ static int __maybe_unused cppi41_runtime_suspend(struct device *dev) static int __maybe_unused cppi41_runtime_resume(struct device *dev) { struct cppi41_dd *cdd = dev_get_drvdata(dev); - struct cppi41_channel *c, *_c; unsigned long flags; spin_lock_irqsave(&cdd->lock, flags); - list_for_each_entry_safe(c, _c, &cdd->pending, node) { - push_desc_queue(c); - list_del(&c->node); - } + cdd->is_suspended = false; + cppi41_run_queue(cdd); spin_unlock_irqrestore(&cdd->lock, flags); return 0; diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index 740bbb942594..7539f73df9e0 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -1699,7 +1699,6 @@ static bool _chan_ns(const struct pl330_dmac *pl330, int i) static struct pl330_thread *pl330_request_channel(struct pl330_dmac *pl330) { struct pl330_thread *thrd = NULL; - unsigned long flags; int chans, i; if (pl330->state == DYING) @@ -1707,8 +1706,6 @@ static struct pl330_thread *pl330_request_channel(struct pl330_dmac *pl330) chans = pl330->pcfg.num_chan; - spin_lock_irqsave(&pl330->lock, flags); - for (i = 0; i < chans; i++) { thrd = &pl330->channels[i]; if ((thrd->free) && (!_manager_ns(thrd) || @@ -1726,8 +1723,6 @@ static struct pl330_thread *pl330_request_channel(struct pl330_dmac *pl330) thrd = NULL; } - spin_unlock_irqrestore(&pl330->lock, flags); - return thrd; } @@ -1745,7 +1740,6 @@ static inline void _free_event(struct pl330_thread *thrd, int ev) static void pl330_release_channel(struct pl330_thread *thrd) { struct pl330_dmac *pl330; - unsigned long flags; if (!thrd || thrd->free) return; @@ -1757,10 +1751,8 @@ static void pl330_release_channel(struct pl330_thread *thrd) pl330 = thrd->dmac; - spin_lock_irqsave(&pl330->lock, flags); _free_event(thrd, thrd->ev); thrd->free = true; - spin_unlock_irqrestore(&pl330->lock, flags); } /* Initialize the structure for PL330 configuration, that can be used @@ -2122,20 +2114,20 @@ static int pl330_alloc_chan_resources(struct dma_chan *chan) struct pl330_dmac *pl330 = pch->dmac; unsigned long flags; - spin_lock_irqsave(&pch->lock, flags); + spin_lock_irqsave(&pl330->lock, flags); dma_cookie_init(chan); pch->cyclic = false; pch->thread = pl330_request_channel(pl330); if (!pch->thread) { - spin_unlock_irqrestore(&pch->lock, flags); + spin_unlock_irqrestore(&pl330->lock, flags); return -ENOMEM; } tasklet_init(&pch->task, pl330_tasklet, (unsigned long) pch); - spin_unlock_irqrestore(&pch->lock, flags); + spin_unlock_irqrestore(&pl330->lock, flags); return 1; } @@ -2238,12 +2230,13 @@ static int pl330_pause(struct dma_chan *chan) static void pl330_free_chan_resources(struct dma_chan *chan) { struct dma_pl330_chan *pch = to_pchan(chan); + struct pl330_dmac *pl330 = pch->dmac; unsigned long flags; tasklet_kill(&pch->task); pm_runtime_get_sync(pch->dmac->ddma.dev); - spin_lock_irqsave(&pch->lock, flags); + spin_lock_irqsave(&pl330->lock, flags); pl330_release_channel(pch->thread); pch->thread = NULL; @@ -2251,7 +2244,7 @@ static void pl330_free_chan_resources(struct dma_chan *chan) if (pch->cyclic) list_splice_tail_init(&pch->work_list, &pch->dmac->desc_pool); - spin_unlock_irqrestore(&pch->lock, flags); + spin_unlock_irqrestore(&pl330->lock, flags); pm_runtime_mark_last_busy(pch->dmac->ddma.dev); pm_runtime_put_autosuspend(pch->dmac->ddma.dev); } diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c index 921dfa047202..260c4b4b492e 100644 --- a/drivers/firmware/efi/libstub/fdt.c +++ b/drivers/firmware/efi/libstub/fdt.c @@ -187,6 +187,7 @@ static efi_status_t update_fdt_memmap(void *fdt, struct efi_boot_memmap *map) struct exit_boot_struct { efi_memory_desc_t *runtime_map; int *runtime_entry_count; + void *new_fdt_addr; }; static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, @@ -202,7 +203,7 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, efi_get_virtmap(*map->map, *map->map_size, *map->desc_size, p->runtime_map, p->runtime_entry_count); - return EFI_SUCCESS; + return update_fdt_memmap(p->new_fdt_addr, map); } /* @@ -300,22 +301,13 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table, priv.runtime_map = runtime_map; priv.runtime_entry_count = &runtime_entry_count; + priv.new_fdt_addr = (void *)*new_fdt_addr; status = efi_exit_boot_services(sys_table, handle, &map, &priv, exit_boot_func); if (status == EFI_SUCCESS) { efi_set_virtual_address_map_t *svam; - status = update_fdt_memmap((void *)*new_fdt_addr, &map); - if (status != EFI_SUCCESS) { - /* - * The kernel won't get far without the memory map, but - * may still be able to print something meaningful so - * return success here. - */ - return EFI_SUCCESS; - } - /* Install the new virtual address map */ svam = sys_table->runtime->set_virtual_address_map; status = svam(runtime_entry_count * desc_size, desc_size, diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 90bc65d07a35..88e01e08e279 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -263,6 +263,8 @@ source "drivers/gpu/drm/mxsfb/Kconfig" source "drivers/gpu/drm/meson/Kconfig" +source "drivers/gpu/drm/tinydrm/Kconfig" + # Keep legacy drivers last menuconfig DRM_LEGACY diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 92de3991fa56..3ee95793d122 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -94,3 +94,4 @@ obj-$(CONFIG_DRM_ARCPGU)+= arc/ obj-y += hisilicon/ obj-$(CONFIG_DRM_ZTE) += zte/ obj-$(CONFIG_DRM_MXSFB) += mxsfb/ +obj-$(CONFIG_DRM_TINYDRM) += tinydrm/ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 94a64e3bc682..c1b913541739 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1037,7 +1037,6 @@ struct amdgpu_uvd { bool use_ctx_buf; struct amd_sched_entity entity; uint32_t srbm_soft_reset; - bool is_powergated; }; /* @@ -1066,7 +1065,6 @@ struct amdgpu_vce { struct amd_sched_entity entity; uint32_t srbm_soft_reset; unsigned num_rings; - bool is_powergated; }; /* @@ -1484,6 +1482,9 @@ struct amdgpu_device { spinlock_t gtt_list_lock; struct list_head gtt_list; + /* record hw reset is performed */ + bool has_hw_reset; + }; static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev) @@ -1702,13 +1703,14 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring) int amdgpu_gpu_reset(struct amdgpu_device *adev); bool amdgpu_need_backup(struct amdgpu_device *adev); void amdgpu_pci_config_reset(struct amdgpu_device *adev); -bool amdgpu_card_posted(struct amdgpu_device *adev); +bool amdgpu_need_post(struct amdgpu_device *adev); void amdgpu_update_display_priority(struct amdgpu_device *adev); int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data); int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type, u32 ip_instance, u32 ring, struct amdgpu_ring **out_ring); +void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes); void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain); bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo); int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index d9def01f276e..821f7cc2051f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -100,7 +100,7 @@ static bool igp_read_bios_from_vram(struct amdgpu_device *adev) resource_size_t size = 256 * 1024; /* ??? */ if (!(adev->flags & AMD_IS_APU)) - if (!amdgpu_card_posted(adev)) + if (amdgpu_need_post(adev)) return false; adev->bios = NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c index a5df1ef306d9..d9e5aa4a79ef 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c @@ -834,32 +834,57 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, case CHIP_TOPAZ: if (((adev->pdev->device == 0x6900) && (adev->pdev->revision == 0x81)) || ((adev->pdev->device == 0x6900) && (adev->pdev->revision == 0x83)) || - ((adev->pdev->device == 0x6907) && (adev->pdev->revision == 0x87))) + ((adev->pdev->device == 0x6907) && (adev->pdev->revision == 0x87))) { + info->is_kicker = true; strcpy(fw_name, "amdgpu/topaz_k_smc.bin"); - else + } else strcpy(fw_name, "amdgpu/topaz_smc.bin"); break; case CHIP_TONGA: if (((adev->pdev->device == 0x6939) && (adev->pdev->revision == 0xf1)) || - ((adev->pdev->device == 0x6938) && (adev->pdev->revision == 0xf1))) + ((adev->pdev->device == 0x6938) && (adev->pdev->revision == 0xf1))) { + info->is_kicker = true; strcpy(fw_name, "amdgpu/tonga_k_smc.bin"); - else + } else strcpy(fw_name, "amdgpu/tonga_smc.bin"); break; case CHIP_FIJI: strcpy(fw_name, "amdgpu/fiji_smc.bin"); break; case CHIP_POLARIS11: - if (type == CGS_UCODE_ID_SMU) - strcpy(fw_name, "amdgpu/polaris11_smc.bin"); - else if (type == CGS_UCODE_ID_SMU_SK) + if (type == CGS_UCODE_ID_SMU) { + if (((adev->pdev->device == 0x67ef) && + ((adev->pdev->revision == 0xe0) || + (adev->pdev->revision == 0xe2) || + (adev->pdev->revision == 0xe5))) || + ((adev->pdev->device == 0x67ff) && + ((adev->pdev->revision == 0xcf) || + (adev->pdev->revision == 0xef) || + (adev->pdev->revision == 0xff)))) { + info->is_kicker = true; + strcpy(fw_name, "amdgpu/polaris11_k_smc.bin"); + } else + strcpy(fw_name, "amdgpu/polaris11_smc.bin"); + } else if (type == CGS_UCODE_ID_SMU_SK) { strcpy(fw_name, "amdgpu/polaris11_smc_sk.bin"); + } break; case CHIP_POLARIS10: - if (type == CGS_UCODE_ID_SMU) - strcpy(fw_name, "amdgpu/polaris10_smc.bin"); - else if (type == CGS_UCODE_ID_SMU_SK) + if (type == CGS_UCODE_ID_SMU) { + if ((adev->pdev->device == 0x67df) && + ((adev->pdev->revision == 0xe0) || + (adev->pdev->revision == 0xe3) || + (adev->pdev->revision == 0xe4) || + (adev->pdev->revision == 0xe5) || + (adev->pdev->revision == 0xe7) || + (adev->pdev->revision == 0xef))) { + info->is_kicker = true; + strcpy(fw_name, "amdgpu/polaris10_k_smc.bin"); + } else + strcpy(fw_name, "amdgpu/polaris10_smc.bin"); + } else if (type == CGS_UCODE_ID_SMU_SK) { strcpy(fw_name, "amdgpu/polaris10_smc_sk.bin"); + } break; case CHIP_POLARIS12: strcpy(fw_name, "amdgpu/polaris12_smc.bin"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index cf2e8c4e9b8b..d2d0f60ff36d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -83,6 +83,13 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type, } break; } + + if (!(*out_ring && (*out_ring)->adev)) { + DRM_ERROR("Ring %d is not initialized on IP %d\n", + ring, ip_type); + return -EINVAL; + } + return 0; } @@ -344,8 +351,7 @@ static u64 amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev) * submission. This can result in a debt that can stop buffer migrations * temporarily. */ -static void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, - u64 num_bytes) +void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes) { spin_lock(&adev->mm_stats.lock); adev->mm_stats.accum_us -= bytes_to_us(adev, num_bytes); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 944ba0d3874a..6abb238b25c9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -619,25 +619,29 @@ void amdgpu_gtt_location(struct amdgpu_device *adev, struct amdgpu_mc *mc) * GPU helpers function. */ /** - * amdgpu_card_posted - check if the hw has already been initialized + * amdgpu_need_post - check if the hw need post or not * * @adev: amdgpu_device pointer * - * Check if the asic has been initialized (all asics). - * Used at driver startup. - * Returns true if initialized or false if not. + * Check if the asic has been initialized (all asics) at driver startup + * or post is needed if hw reset is performed. + * Returns true if need or false if not. */ -bool amdgpu_card_posted(struct amdgpu_device *adev) +bool amdgpu_need_post(struct amdgpu_device *adev) { uint32_t reg; + if (adev->has_hw_reset) { + adev->has_hw_reset = false; + return true; + } /* then check MEM_SIZE, in case the crtcs are off */ reg = RREG32(mmCONFIG_MEMSIZE); if (reg) - return true; + return false; - return false; + return true; } @@ -665,7 +669,7 @@ static bool amdgpu_vpost_needed(struct amdgpu_device *adev) return true; } } - return !amdgpu_card_posted(adev); + return amdgpu_need_post(adev); } /** @@ -2071,7 +2075,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon) amdgpu_atombios_scratch_regs_restore(adev); /* post card */ - if (!amdgpu_card_posted(adev) || !resume) { + if (amdgpu_need_post(adev)) { r = amdgpu_atom_asic_init(adev->mode_info.atom_context); if (r) DRM_ERROR("amdgpu asic init failed\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 9bd1b4eae32e..51d759463384 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -487,67 +487,44 @@ static int amdgpu_gem_va_check(void *param, struct amdgpu_bo *bo) * * @adev: amdgpu_device pointer * @bo_va: bo_va to update + * @list: validation list + * @operation: map or unmap * - * Update the bo_va directly after setting it's address. Errors are not + * Update the bo_va directly after setting its address. Errors are not * vital here, so they are not reported back to userspace. */ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, + struct list_head *list, uint32_t operation) { - struct ttm_validate_buffer tv, *entry; - struct amdgpu_bo_list_entry vm_pd; - struct ww_acquire_ctx ticket; - struct list_head list, duplicates; - int r; - - INIT_LIST_HEAD(&list); - INIT_LIST_HEAD(&duplicates); - - tv.bo = &bo_va->bo->tbo; - tv.shared = true; - list_add(&tv.head, &list); - - amdgpu_vm_get_pd_bo(bo_va->vm, &list, &vm_pd); + struct ttm_validate_buffer *entry; + int r = -ERESTARTSYS; - /* Provide duplicates to avoid -EALREADY */ - r = ttm_eu_reserve_buffers(&ticket, &list, true, &duplicates); - if (r) - goto error_print; - - list_for_each_entry(entry, &list, head) { + list_for_each_entry(entry, list, head) { struct amdgpu_bo *bo = container_of(entry->bo, struct amdgpu_bo, tbo); - - /* if anything is swapped out don't swap it in here, - just abort and wait for the next CS */ - if (!amdgpu_bo_gpu_accessible(bo)) - goto error_unreserve; - - if (bo->shadow && !amdgpu_bo_gpu_accessible(bo->shadow)) - goto error_unreserve; + if (amdgpu_gem_va_check(NULL, bo)) + goto error; } r = amdgpu_vm_validate_pt_bos(adev, bo_va->vm, amdgpu_gem_va_check, NULL); if (r) - goto error_unreserve; + goto error; r = amdgpu_vm_update_page_directory(adev, bo_va->vm); if (r) - goto error_unreserve; + goto error; r = amdgpu_vm_clear_freed(adev, bo_va->vm); if (r) - goto error_unreserve; + goto error; if (operation == AMDGPU_VA_OP_MAP) r = amdgpu_vm_bo_update(adev, bo_va, false); -error_unreserve: - ttm_eu_backoff_reservation(&ticket, &list); - -error_print: +error: if (r && r != -ERESTARTSYS) DRM_ERROR("Couldn't update BO_VA (%d)\n", r); } @@ -564,7 +541,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, struct amdgpu_bo_list_entry vm_pd; struct ttm_validate_buffer tv; struct ww_acquire_ctx ticket; - struct list_head list, duplicates; + struct list_head list; uint32_t invalid_flags, va_flags = 0; int r = 0; @@ -602,14 +579,13 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, return -ENOENT; abo = gem_to_amdgpu_bo(gobj); INIT_LIST_HEAD(&list); - INIT_LIST_HEAD(&duplicates); tv.bo = &abo->tbo; - tv.shared = true; + tv.shared = false; list_add(&tv.head, &list); amdgpu_vm_get_pd_bo(&fpriv->vm, &list, &vm_pd); - r = ttm_eu_reserve_buffers(&ticket, &list, true, &duplicates); + r = ttm_eu_reserve_buffers(&ticket, &list, true, NULL); if (r) { drm_gem_object_unreference_unlocked(gobj); return r; @@ -640,10 +616,10 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, default: break; } - ttm_eu_backoff_reservation(&ticket, &list); if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE) && !amdgpu_vm_debug) - amdgpu_gem_va_update_vm(adev, bo_va, args->operation); + amdgpu_gem_va_update_vm(adev, bo_va, &list, args->operation); + ttm_eu_backoff_reservation(&ticket, &list); drm_gem_object_unreference_unlocked(gobj); return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index d1aa291b2638..be80a4a68d7b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -323,6 +323,7 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev, struct amdgpu_bo *bo; enum ttm_bo_type type; unsigned long page_align; + u64 initial_bytes_moved; size_t acc_size; int r; @@ -374,8 +375,10 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev, * See https://bugs.freedesktop.org/show_bug.cgi?id=88758 */ +#ifndef CONFIG_COMPILE_TEST #warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \ thanks to write-combining +#endif if (bo->flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC) DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for " @@ -399,12 +402,20 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev, locked = ww_mutex_trylock(&bo->tbo.ttm_resv.lock); WARN_ON(!locked); } + + initial_bytes_moved = atomic64_read(&adev->num_bytes_moved); r = ttm_bo_init(&adev->mman.bdev, &bo->tbo, size, type, &bo->placement, page_align, !kernel, NULL, acc_size, sg, resv ? resv : &bo->tbo.ttm_resv, &amdgpu_ttm_bo_destroy); - if (unlikely(r != 0)) + amdgpu_cs_report_moved_bytes(adev, + atomic64_read(&adev->num_bytes_moved) - initial_bytes_moved); + + if (unlikely(r != 0)) { + if (!resv) + ww_mutex_unlock(&bo->tbo.resv->lock); return r; + } bo->tbo.priority = ilog2(bo->tbo.num_pages); if (kernel) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index a61882ddc804..346e80a7119b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -1142,12 +1142,22 @@ void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable) /* XXX select vce level based on ring/task */ adev->pm.dpm.vce_level = AMD_VCE_LEVEL_AC_ALL; mutex_unlock(&adev->pm.mutex); + amdgpu_pm_compute_clocks(adev); + amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE, + AMD_PG_STATE_UNGATE); + amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE, + AMD_CG_STATE_UNGATE); } else { + amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE, + AMD_PG_STATE_GATE); + amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE, + AMD_CG_STATE_GATE); mutex_lock(&adev->pm.mutex); adev->pm.dpm.vce_active = false; mutex_unlock(&adev->pm.mutex); + amdgpu_pm_compute_clocks(adev); } - amdgpu_pm_compute_clocks(adev); + } } @@ -1286,7 +1296,8 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev) if (!adev->pm.dpm_enabled) return; - amdgpu_display_bandwidth_update(adev); + if (adev->mode_info.num_crtc) + amdgpu_display_bandwidth_update(adev); for (i = 0; i < AMDGPU_MAX_RINGS; i++) { struct amdgpu_ring *ring = adev->rings[i]; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 1154b0a8881d..4c6094eefc51 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -529,6 +529,9 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_ case TTM_PL_TT: break; case TTM_PL_VRAM: + if (mem->start == AMDGPU_BO_INVALID_OFFSET) + return -EINVAL; + mem->bus.offset = mem->start << PAGE_SHIFT; /* check if it's visible */ if ((mem->bus.offset + mem->bus.size) > adev->mc.visible_vram_size) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 6f62ac473064..6d6ab7f11b4c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -1113,6 +1113,11 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work) amdgpu_dpm_enable_uvd(adev, false); } else { amdgpu_asic_set_uvd_clocks(adev, 0, 0); + /* shutdown the UVD block */ + amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD, + AMD_PG_STATE_GATE); + amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD, + AMD_CG_STATE_GATE); } } else { schedule_delayed_work(&adev->uvd.idle_work, UVD_IDLE_TIMEOUT); @@ -1129,6 +1134,10 @@ void amdgpu_uvd_ring_begin_use(struct amdgpu_ring *ring) amdgpu_dpm_enable_uvd(adev, true); } else { amdgpu_asic_set_uvd_clocks(adev, 53300, 40000); + amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD, + AMD_CG_STATE_UNGATE); + amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD, + AMD_PG_STATE_UNGATE); } } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 79bc9c7aad45..e2c06780ce49 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -321,6 +321,10 @@ static void amdgpu_vce_idle_work_handler(struct work_struct *work) amdgpu_dpm_enable_vce(adev, false); } else { amdgpu_asic_set_vce_clocks(adev, 0, 0); + amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE, + AMD_PG_STATE_GATE); + amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE, + AMD_CG_STATE_GATE); } } else { schedule_delayed_work(&adev->vce.idle_work, VCE_IDLE_TIMEOUT); @@ -346,6 +350,11 @@ void amdgpu_vce_ring_begin_use(struct amdgpu_ring *ring) amdgpu_dpm_enable_vce(adev, true); } else { amdgpu_asic_set_vce_clocks(adev, 53300, 40000); + amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE, + AMD_CG_STATE_UNGATE); + amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE, + AMD_PG_STATE_UNGATE); + } } mutex_unlock(&adev->vce.idle_mutex); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index 3fd951c71d1b..dcfb7df3caf4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -83,7 +83,6 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm) DRM_ERROR("failed to do bo_map on static CSA, err=%d\n", r); amdgpu_vm_bo_rmv(adev, bo_va); ttm_eu_backoff_reservation(&ticket, &list); - kfree(bo_va); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c index 9498e78b90d7..f97ecb49972e 100644 --- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c @@ -2210,7 +2210,6 @@ static void ci_clear_vc(struct amdgpu_device *adev) static int ci_upload_firmware(struct amdgpu_device *adev) { - struct ci_power_info *pi = ci_get_pi(adev); int i, ret; if (amdgpu_ci_is_smc_running(adev)) { @@ -2227,7 +2226,7 @@ static int ci_upload_firmware(struct amdgpu_device *adev) amdgpu_ci_stop_smc_clock(adev); amdgpu_ci_reset_smc(adev); - ret = amdgpu_ci_load_smc_ucode(adev, pi->sram_end); + ret = amdgpu_ci_load_smc_ucode(adev, SMC_RAM_END); return ret; @@ -4257,12 +4256,6 @@ static int ci_update_vce_dpm(struct amdgpu_device *adev, if (amdgpu_current_state->evclk != amdgpu_new_state->evclk) { if (amdgpu_new_state->evclk) { - /* turn the clocks on when encoding */ - ret = amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE, - AMD_CG_STATE_UNGATE); - if (ret) - return ret; - pi->smc_state_table.VceBootLevel = ci_get_vce_boot_level(adev); tmp = RREG32_SMC(ixDPM_TABLE_475); tmp &= ~DPM_TABLE_475__VceBootLevel_MASK; @@ -4274,9 +4267,6 @@ static int ci_update_vce_dpm(struct amdgpu_device *adev, ret = ci_enable_vce_dpm(adev, false); if (ret) return ret; - /* turn the clocks off when not encoding */ - ret = amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE, - AMD_CG_STATE_GATE); } } return ret; @@ -6278,13 +6268,13 @@ static int ci_dpm_sw_init(void *handle) adev->pm.current_mclk = adev->clock.default_mclk; adev->pm.int_thermal_type = THERMAL_TYPE_NONE; - if (amdgpu_dpm == 0) - return 0; - ret = ci_dpm_init_microcode(adev); if (ret) return ret; + if (amdgpu_dpm == 0) + return 0; + INIT_WORK(&adev->pm.dpm.thermal.work, amdgpu_dpm_thermal_work_handler); mutex_lock(&adev->pm.mutex); ret = ci_dpm_init(adev); @@ -6328,8 +6318,15 @@ static int ci_dpm_hw_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (!amdgpu_dpm) + if (!amdgpu_dpm) { + ret = ci_upload_firmware(adev); + if (ret) { + DRM_ERROR("ci_upload_firmware failed\n"); + return ret; + } + ci_dpm_start_smc(adev); return 0; + } mutex_lock(&adev->pm.mutex); ci_dpm_setup_asic(adev); @@ -6351,6 +6348,8 @@ static int ci_dpm_hw_fini(void *handle) mutex_lock(&adev->pm.mutex); ci_dpm_disable(adev); mutex_unlock(&adev->pm.mutex); + } else { + ci_dpm_stop_smc(adev); } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c index 7da688b0d27d..c4d4b35e54ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik.c +++ b/drivers/gpu/drm/amd/amdgpu/cik.c @@ -1176,6 +1176,7 @@ static int cik_gpu_pci_config_reset(struct amdgpu_device *adev) if (RREG32(mmCONFIG_MEMSIZE) != 0xffffffff) { /* enable BM */ pci_set_master(adev->pdev); + adev->has_hw_reset = true; r = 0; break; } @@ -1722,8 +1723,8 @@ static int cik_common_early_init(void *handle) AMD_PG_SUPPORT_GFX_SMG | AMD_PG_SUPPORT_GFX_DMG |*/ AMD_PG_SUPPORT_UVD | - /*AMD_PG_SUPPORT_VCE | - AMD_PG_SUPPORT_CP | + AMD_PG_SUPPORT_VCE | + /* AMD_PG_SUPPORT_CP | AMD_PG_SUPPORT_GDS | AMD_PG_SUPPORT_RLC_SMU_HS | AMD_PG_SUPPORT_ACP | diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index 1cf1d9d1aec1..5b24e89552ec 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -3737,9 +3737,15 @@ static void dce_v11_0_encoder_add(struct amdgpu_device *adev, default: encoder->possible_crtcs = 0x3; break; + case 3: + encoder->possible_crtcs = 0x7; + break; case 4: encoder->possible_crtcs = 0xf; break; + case 5: + encoder->possible_crtcs = 0x1f; + break; case 6: encoder->possible_crtcs = 0x3f; break; diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c index 762f8e82ceb7..e9a176891e13 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c @@ -627,11 +627,8 @@ static const struct drm_encoder_helper_funcs dce_virtual_encoder_helper_funcs = static void dce_virtual_encoder_destroy(struct drm_encoder *encoder) { - struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder); - - kfree(amdgpu_encoder->enc_priv); drm_encoder_cleanup(encoder); - kfree(amdgpu_encoder); + kfree(encoder); } static const struct drm_encoder_funcs dce_virtual_encoder_funcs = { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c index c998f6aaaf36..2086e7e68de4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c @@ -1325,21 +1325,19 @@ static u32 gfx_v6_0_create_bitmask(u32 bit_width) return (u32)(((u64)1 << bit_width) - 1); } -static u32 gfx_v6_0_get_rb_disabled(struct amdgpu_device *adev, - u32 max_rb_num_per_se, - u32 sh_per_se) +static u32 gfx_v6_0_get_rb_active_bitmap(struct amdgpu_device *adev) { u32 data, mask; - data = RREG32(mmCC_RB_BACKEND_DISABLE); - data &= CC_RB_BACKEND_DISABLE__BACKEND_DISABLE_MASK; - data |= RREG32(mmGC_USER_RB_BACKEND_DISABLE); + data = RREG32(mmCC_RB_BACKEND_DISABLE) | + RREG32(mmGC_USER_RB_BACKEND_DISABLE); - data >>= CC_RB_BACKEND_DISABLE__BACKEND_DISABLE__SHIFT; + data = REG_GET_FIELD(data, GC_USER_RB_BACKEND_DISABLE, BACKEND_DISABLE); - mask = gfx_v6_0_create_bitmask(max_rb_num_per_se / sh_per_se); + mask = gfx_v6_0_create_bitmask(adev->gfx.config.max_backends_per_se/ + adev->gfx.config.max_sh_per_se); - return data & mask; + return ~data & mask; } static void gfx_v6_0_raster_config(struct amdgpu_device *adev, u32 *rconf) @@ -1468,68 +1466,55 @@ static void gfx_v6_0_write_harvested_raster_configs(struct amdgpu_device *adev, gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); } -static void gfx_v6_0_setup_rb(struct amdgpu_device *adev, - u32 se_num, u32 sh_per_se, - u32 max_rb_num_per_se) +static void gfx_v6_0_setup_rb(struct amdgpu_device *adev) { int i, j; - u32 data, mask; - u32 disabled_rbs = 0; - u32 enabled_rbs = 0; + u32 data; + u32 raster_config = 0; + u32 active_rbs = 0; + u32 rb_bitmap_width_per_sh = adev->gfx.config.max_backends_per_se / + adev->gfx.config.max_sh_per_se; unsigned num_rb_pipes; mutex_lock(&adev->grbm_idx_mutex); - for (i = 0; i < se_num; i++) { - for (j = 0; j < sh_per_se; j++) { + for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { + for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { gfx_v6_0_select_se_sh(adev, i, j, 0xffffffff); - data = gfx_v6_0_get_rb_disabled(adev, max_rb_num_per_se, sh_per_se); - disabled_rbs |= data << ((i * sh_per_se + j) * 2); + data = gfx_v6_0_get_rb_active_bitmap(adev); + active_rbs |= data << ((i * adev->gfx.config.max_sh_per_se + j) * + rb_bitmap_width_per_sh); } } gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); - mutex_unlock(&adev->grbm_idx_mutex); - - mask = 1; - for (i = 0; i < max_rb_num_per_se * se_num; i++) { - if (!(disabled_rbs & mask)) - enabled_rbs |= mask; - mask <<= 1; - } - adev->gfx.config.backend_enable_mask = enabled_rbs; - adev->gfx.config.num_rbs = hweight32(enabled_rbs); + adev->gfx.config.backend_enable_mask = active_rbs; + adev->gfx.config.num_rbs = hweight32(active_rbs); num_rb_pipes = min_t(unsigned, adev->gfx.config.max_backends_per_se * adev->gfx.config.max_shader_engines, 16); - mutex_lock(&adev->grbm_idx_mutex); - for (i = 0; i < se_num; i++) { - gfx_v6_0_select_se_sh(adev, i, 0xffffffff, 0xffffffff); - data = 0; - for (j = 0; j < sh_per_se; j++) { - switch (enabled_rbs & 3) { - case 1: - data |= (RASTER_CONFIG_RB_MAP_0 << (i * sh_per_se + j) * 2); - break; - case 2: - data |= (RASTER_CONFIG_RB_MAP_3 << (i * sh_per_se + j) * 2); - break; - case 3: - default: - data |= (RASTER_CONFIG_RB_MAP_2 << (i * sh_per_se + j) * 2); - break; - } - enabled_rbs >>= 2; - } - gfx_v6_0_raster_config(adev, &data); + gfx_v6_0_raster_config(adev, &raster_config); - if (!adev->gfx.config.backend_enable_mask || - adev->gfx.config.num_rbs >= num_rb_pipes) - WREG32(mmPA_SC_RASTER_CONFIG, data); - else - gfx_v6_0_write_harvested_raster_configs(adev, data, - adev->gfx.config.backend_enable_mask, - num_rb_pipes); + if (!adev->gfx.config.backend_enable_mask || + adev->gfx.config.num_rbs >= num_rb_pipes) { + WREG32(mmPA_SC_RASTER_CONFIG, raster_config); + } else { + gfx_v6_0_write_harvested_raster_configs(adev, raster_config, + adev->gfx.config.backend_enable_mask, + num_rb_pipes); + } + + /* cache the values for userspace */ + for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { + for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { + gfx_v6_0_select_se_sh(adev, i, j, 0xffffffff); + adev->gfx.config.rb_config[i][j].rb_backend_disable = + RREG32(mmCC_RB_BACKEND_DISABLE); + adev->gfx.config.rb_config[i][j].user_rb_backend_disable = + RREG32(mmGC_USER_RB_BACKEND_DISABLE); + adev->gfx.config.rb_config[i][j].raster_config = + RREG32(mmPA_SC_RASTER_CONFIG); + } } gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); mutex_unlock(&adev->grbm_idx_mutex); @@ -1540,36 +1525,44 @@ static void gmc_v6_0_init_compute_vmid(struct amdgpu_device *adev) } */ -static u32 gfx_v6_0_get_cu_enabled(struct amdgpu_device *adev, u32 cu_per_sh) +static void gfx_v6_0_set_user_cu_inactive_bitmap(struct amdgpu_device *adev, + u32 bitmap) { - u32 data, mask; + u32 data; - data = RREG32(mmCC_GC_SHADER_ARRAY_CONFIG); - data &= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_CUS_MASK; - data |= RREG32(mmGC_USER_SHADER_ARRAY_CONFIG); + if (!bitmap) + return; - data >>= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_CUS__SHIFT; + data = bitmap << GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS__SHIFT; + data &= GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_CUS_MASK; - mask = gfx_v6_0_create_bitmask(cu_per_sh); + WREG32(mmGC_USER_SHADER_ARRAY_CONFIG, data); +} - return ~data & mask; +static u32 gfx_v6_0_get_cu_enabled(struct amdgpu_device *adev) +{ + u32 data, mask; + + data = RREG32(mmCC_GC_SHADER_ARRAY_CONFIG) | + RREG32(mmGC_USER_SHADER_ARRAY_CONFIG); + + mask = gfx_v6_0_create_bitmask(adev->gfx.config.max_cu_per_sh); + return ~REG_GET_FIELD(data, CC_GC_SHADER_ARRAY_CONFIG, INACTIVE_CUS) & mask; } -static void gfx_v6_0_setup_spi(struct amdgpu_device *adev, - u32 se_num, u32 sh_per_se, - u32 cu_per_sh) +static void gfx_v6_0_setup_spi(struct amdgpu_device *adev) { int i, j, k; u32 data, mask; u32 active_cu = 0; mutex_lock(&adev->grbm_idx_mutex); - for (i = 0; i < se_num; i++) { - for (j = 0; j < sh_per_se; j++) { + for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { + for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { gfx_v6_0_select_se_sh(adev, i, j, 0xffffffff); data = RREG32(mmSPI_STATIC_THREAD_MGMT_3); - active_cu = gfx_v6_0_get_cu_enabled(adev, cu_per_sh); + active_cu = gfx_v6_0_get_cu_enabled(adev); mask = 1; for (k = 0; k < 16; k++) { @@ -1717,6 +1710,9 @@ static void gfx_v6_0_gpu_init(struct amdgpu_device *adev) gb_addr_config |= 2 << GB_ADDR_CONFIG__ROW_SIZE__SHIFT; break; } + gb_addr_config &= ~GB_ADDR_CONFIG__NUM_SHADER_ENGINES_MASK; + if (adev->gfx.config.max_shader_engines == 2) + gb_addr_config |= 1 << GB_ADDR_CONFIG__NUM_SHADER_ENGINES__SHIFT; adev->gfx.config.gb_addr_config = gb_addr_config; WREG32(mmGB_ADDR_CONFIG, gb_addr_config); @@ -1735,13 +1731,9 @@ static void gfx_v6_0_gpu_init(struct amdgpu_device *adev) #endif gfx_v6_0_tiling_mode_table_init(adev); - gfx_v6_0_setup_rb(adev, adev->gfx.config.max_shader_engines, - adev->gfx.config.max_sh_per_se, - adev->gfx.config.max_backends_per_se); + gfx_v6_0_setup_rb(adev); - gfx_v6_0_setup_spi(adev, adev->gfx.config.max_shader_engines, - adev->gfx.config.max_sh_per_se, - adev->gfx.config.max_cu_per_sh); + gfx_v6_0_setup_spi(adev); gfx_v6_0_get_cu_info(adev); @@ -2941,61 +2933,16 @@ static void gfx_v6_0_enable_gfx_cgpg(struct amdgpu_device *adev, } } -static u32 gfx_v6_0_get_cu_active_bitmap(struct amdgpu_device *adev, - u32 se, u32 sh) -{ - - u32 mask = 0, tmp, tmp1; - int i; - - mutex_lock(&adev->grbm_idx_mutex); - gfx_v6_0_select_se_sh(adev, se, sh, 0xffffffff); - tmp = RREG32(mmCC_GC_SHADER_ARRAY_CONFIG); - tmp1 = RREG32(mmGC_USER_SHADER_ARRAY_CONFIG); - gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); - mutex_unlock(&adev->grbm_idx_mutex); - - tmp &= 0xffff0000; - - tmp |= tmp1; - tmp >>= 16; - - for (i = 0; i < adev->gfx.config.max_cu_per_sh; i ++) { - mask <<= 1; - mask |= 1; - } - - return (~tmp) & mask; -} - static void gfx_v6_0_init_ao_cu_mask(struct amdgpu_device *adev) { - u32 i, j, k, active_cu_number = 0; - - u32 mask, counter, cu_bitmap; - u32 tmp = 0; - - for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { - for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { - mask = 1; - cu_bitmap = 0; - counter = 0; - for (k = 0; k < adev->gfx.config.max_cu_per_sh; k++) { - if (gfx_v6_0_get_cu_active_bitmap(adev, i, j) & mask) { - if (counter < 2) - cu_bitmap |= mask; - counter++; - } - mask <<= 1; - } + u32 tmp; - active_cu_number += counter; - tmp |= (cu_bitmap << (i * 16 + j * 8)); - } - } + WREG32(mmRLC_PG_ALWAYS_ON_CU_MASK, adev->gfx.cu_info.ao_cu_mask); - WREG32(mmRLC_PG_AO_CU_MASK, tmp); - WREG32_FIELD(RLC_MAX_PG_CU, MAX_POWERED_UP_CU, active_cu_number); + tmp = RREG32(mmRLC_MAX_PG_CU); + tmp &= ~RLC_MAX_PG_CU__MAX_POWERED_UP_CU_MASK; + tmp |= (adev->gfx.cu_info.number << RLC_MAX_PG_CU__MAX_POWERED_UP_CU__SHIFT); + WREG32(mmRLC_MAX_PG_CU, tmp); } static void gfx_v6_0_enable_gfx_static_mgpg(struct amdgpu_device *adev, @@ -3770,18 +3717,26 @@ static void gfx_v6_0_get_cu_info(struct amdgpu_device *adev) int i, j, k, counter, active_cu_number = 0; u32 mask, bitmap, ao_bitmap, ao_cu_mask = 0; struct amdgpu_cu_info *cu_info = &adev->gfx.cu_info; + unsigned disable_masks[4 * 2]; memset(cu_info, 0, sizeof(*cu_info)); + amdgpu_gfx_parse_disable_cu(disable_masks, 4, 2); + + mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { mask = 1; ao_bitmap = 0; counter = 0; - bitmap = gfx_v6_0_get_cu_active_bitmap(adev, i, j); + gfx_v6_0_select_se_sh(adev, i, j, 0xffffffff); + if (i < 4 && j < 2) + gfx_v6_0_set_user_cu_inactive_bitmap( + adev, disable_masks[i * 2 + j]); + bitmap = gfx_v6_0_get_cu_enabled(adev); cu_info->bitmap[i][j] = bitmap; - for (k = 0; k < adev->gfx.config.max_cu_per_sh; k ++) { + for (k = 0; k < 16; k++) { if (bitmap & mask) { if (counter < 2) ao_bitmap |= mask; @@ -3794,6 +3749,9 @@ static void gfx_v6_0_get_cu_info(struct amdgpu_device *adev) } } + gfx_v6_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); + mutex_unlock(&adev->grbm_idx_mutex); + cu_info->number = active_cu_number; cu_info->ao_cu_mask = ao_cu_mask; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index e3589b55a1e1..1f9354541f29 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -1983,6 +1983,14 @@ static void gfx_v7_0_gpu_init(struct amdgpu_device *adev) WREG32(mmPA_CL_ENHANCE, PA_CL_ENHANCE__CLIP_VTX_REORDER_ENA_MASK | (3 << PA_CL_ENHANCE__NUM_CLIP_SEQ__SHIFT)); WREG32(mmPA_SC_ENHANCE, PA_SC_ENHANCE__ENABLE_PA_SC_OUT_OF_ORDER_MASK); + + tmp = RREG32(mmSPI_ARB_PRIORITY); + tmp = REG_SET_FIELD(tmp, SPI_ARB_PRIORITY, PIPE_ORDER_TS0, 2); + tmp = REG_SET_FIELD(tmp, SPI_ARB_PRIORITY, PIPE_ORDER_TS1, 2); + tmp = REG_SET_FIELD(tmp, SPI_ARB_PRIORITY, PIPE_ORDER_TS2, 2); + tmp = REG_SET_FIELD(tmp, SPI_ARB_PRIORITY, PIPE_ORDER_TS3, 2); + WREG32(mmSPI_ARB_PRIORITY, tmp); + mutex_unlock(&adev->grbm_idx_mutex); udelay(50); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 35f9cd83b821..67afc901905c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -3898,6 +3898,14 @@ static void gfx_v8_0_gpu_init(struct amdgpu_device *adev) PA_SC_FIFO_SIZE__SC_HIZ_TILE_FIFO_SIZE__SHIFT) | (adev->gfx.config.sc_earlyz_tile_fifo_size << PA_SC_FIFO_SIZE__SC_EARLYZ_TILE_FIFO_SIZE__SHIFT)); + + tmp = RREG32(mmSPI_ARB_PRIORITY); + tmp = REG_SET_FIELD(tmp, SPI_ARB_PRIORITY, PIPE_ORDER_TS0, 2); + tmp = REG_SET_FIELD(tmp, SPI_ARB_PRIORITY, PIPE_ORDER_TS1, 2); + tmp = REG_SET_FIELD(tmp, SPI_ARB_PRIORITY, PIPE_ORDER_TS2, 2); + tmp = REG_SET_FIELD(tmp, SPI_ARB_PRIORITY, PIPE_ORDER_TS3, 2); + WREG32(mmSPI_ARB_PRIORITY, tmp); + mutex_unlock(&adev->grbm_idx_mutex); } @@ -7260,7 +7268,7 @@ static void gfx_v8_0_ring_emit_ce_meta_init(struct amdgpu_ring *ring, uint64_t c static union { struct amdgpu_ce_ib_state regular; struct amdgpu_ce_ib_state_chained_ib chained; - } ce_payload = {0}; + } ce_payload = {}; if (ring->adev->virt.chained_ib_support) { ce_payload_addr = csa_addr + offsetof(struct amdgpu_gfx_meta_data_chained_ib, ce_payload); @@ -7287,7 +7295,7 @@ static void gfx_v8_0_ring_emit_de_meta_init(struct amdgpu_ring *ring, uint64_t c static union { struct amdgpu_de_ib_state regular; struct amdgpu_de_ib_state_chained_ib chained; - } de_payload = {0}; + } de_payload = {}; gds_addr = csa_addr + 4096; if (ring->adev->virt.chained_ib_support) { diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c index e2b0b1646f99..0635829b18cf 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c @@ -254,6 +254,9 @@ static void gmc_v6_0_mc_program(struct amdgpu_device *adev) } WREG32(mmHDP_REG_COHERENCY_FLUSH_CNTL, 0); + if (adev->mode_info.num_crtc) + amdgpu_display_set_vga_render_state(adev, false); + gmc_v6_0_mc_stop(adev, &save); if (gmc_v6_0_wait_for_idle((void *)adev)) { @@ -283,7 +286,6 @@ static void gmc_v6_0_mc_program(struct amdgpu_device *adev) dev_warn(adev->dev, "Wait for MC idle timedout !\n"); } gmc_v6_0_mc_resume(adev, &save); - amdgpu_display_set_vga_render_state(adev, false); } static int gmc_v6_0_mc_init(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c index 8785ca570729..f5a343cb0010 100644 --- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c @@ -1550,11 +1550,6 @@ static int kv_update_vce_dpm(struct amdgpu_device *adev, if (amdgpu_new_state->evclk > 0 && amdgpu_current_state->evclk == 0) { kv_dpm_powergate_vce(adev, false); - /* turn the clocks on when encoding */ - ret = amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE, - AMD_CG_STATE_UNGATE); - if (ret) - return ret; if (pi->caps_stable_p_state) pi->vce_boot_level = table->count - 1; else @@ -1573,15 +1568,9 @@ static int kv_update_vce_dpm(struct amdgpu_device *adev, amdgpu_kv_send_msg_to_smc_with_parameter(adev, PPSMC_MSG_VCEDPM_SetEnabledMask, (1 << pi->vce_boot_level)); - kv_enable_vce_dpm(adev, true); } else if (amdgpu_new_state->evclk == 0 && amdgpu_current_state->evclk > 0) { kv_enable_vce_dpm(adev, false); - /* turn the clocks off when not encoding */ - ret = amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_VCE, - AMD_CG_STATE_GATE); - if (ret) - return ret; kv_dpm_powergate_vce(adev, true); } @@ -1688,70 +1677,44 @@ static void kv_dpm_powergate_uvd(struct amdgpu_device *adev, bool gate) struct kv_power_info *pi = kv_get_pi(adev); int ret; - if (pi->uvd_power_gated == gate) - return; - pi->uvd_power_gated = gate; if (gate) { - if (pi->caps_uvd_pg) { - /* disable clockgating so we can properly shut down the block */ - ret = amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD, - AMD_CG_STATE_UNGATE); - /* shutdown the UVD block */ - ret = amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD, - AMD_PG_STATE_GATE); - /* XXX: check for errors */ - } + /* stop the UVD block */ + ret = amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD, + AMD_PG_STATE_GATE); kv_update_uvd_dpm(adev, gate); if (pi->caps_uvd_pg) /* power off the UVD block */ amdgpu_kv_notify_message_to_smu(adev, PPSMC_MSG_UVDPowerOFF); } else { - if (pi->caps_uvd_pg) { + if (pi->caps_uvd_pg) /* power on the UVD block */ amdgpu_kv_notify_message_to_smu(adev, PPSMC_MSG_UVDPowerON); /* re-init the UVD block */ - ret = amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD, - AMD_PG_STATE_UNGATE); - /* enable clockgating. hw will dynamically gate/ungate clocks on the fly */ - ret = amdgpu_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_UVD, - AMD_CG_STATE_GATE); - /* XXX: check for errors */ - } kv_update_uvd_dpm(adev, gate); + + ret = amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_UVD, + AMD_PG_STATE_UNGATE); } } static void kv_dpm_powergate_vce(struct amdgpu_device *adev, bool gate) { struct kv_power_info *pi = kv_get_pi(adev); - int ret; if (pi->vce_power_gated == gate) return; pi->vce_power_gated = gate; - if (gate) { - if (pi->caps_vce_pg) { - /* shutdown the VCE block */ - ret = amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE, - AMD_PG_STATE_GATE); - /* XXX: check for errors */ - /* power off the VCE block */ - amdgpu_kv_notify_message_to_smu(adev, PPSMC_MSG_VCEPowerOFF); - } - } else { - if (pi->caps_vce_pg) { - /* power on the VCE block */ - amdgpu_kv_notify_message_to_smu(adev, PPSMC_MSG_VCEPowerON); - /* re-init the VCE block */ - ret = amdgpu_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE, - AMD_PG_STATE_UNGATE); - /* XXX: check for errors */ - } - } + if (!pi->caps_vce_pg) + return; + + if (gate) + amdgpu_kv_notify_message_to_smu(adev, PPSMC_MSG_VCEPowerOFF); + else + amdgpu_kv_notify_message_to_smu(adev, PPSMC_MSG_VCEPowerON); } static void kv_dpm_powergate_samu(struct amdgpu_device *adev, bool gate) @@ -3009,8 +2972,7 @@ static int kv_dpm_late_init(void *handle) kv_dpm_powergate_acp(adev, true); kv_dpm_powergate_samu(adev, true); - kv_dpm_powergate_vce(adev, true); - kv_dpm_powergate_uvd(adev, true); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c index da46992f7b18..b71e3faa40db 100644 --- a/drivers/gpu/drm/amd/amdgpu/si.c +++ b/drivers/gpu/drm/amd/amdgpu/si.c @@ -1010,24 +1010,81 @@ static struct amdgpu_allowed_register_entry si_allowed_read_registers[] = { {PA_SC_RASTER_CONFIG, false, true}, }; -static uint32_t si_read_indexed_register(struct amdgpu_device *adev, - u32 se_num, u32 sh_num, - u32 reg_offset) +static uint32_t si_get_register_value(struct amdgpu_device *adev, + bool indexed, u32 se_num, + u32 sh_num, u32 reg_offset) { - uint32_t val; + if (indexed) { + uint32_t val; + unsigned se_idx = (se_num == 0xffffffff) ? 0 : se_num; + unsigned sh_idx = (sh_num == 0xffffffff) ? 0 : sh_num; + + switch (reg_offset) { + case mmCC_RB_BACKEND_DISABLE: + return adev->gfx.config.rb_config[se_idx][sh_idx].rb_backend_disable; + case mmGC_USER_RB_BACKEND_DISABLE: + return adev->gfx.config.rb_config[se_idx][sh_idx].user_rb_backend_disable; + case mmPA_SC_RASTER_CONFIG: + return adev->gfx.config.rb_config[se_idx][sh_idx].raster_config; + } - mutex_lock(&adev->grbm_idx_mutex); - if (se_num != 0xffffffff || sh_num != 0xffffffff) - amdgpu_gfx_select_se_sh(adev, se_num, sh_num, 0xffffffff); + mutex_lock(&adev->grbm_idx_mutex); + if (se_num != 0xffffffff || sh_num != 0xffffffff) + amdgpu_gfx_select_se_sh(adev, se_num, sh_num, 0xffffffff); - val = RREG32(reg_offset); + val = RREG32(reg_offset); - if (se_num != 0xffffffff || sh_num != 0xffffffff) - amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); - mutex_unlock(&adev->grbm_idx_mutex); - return val; + if (se_num != 0xffffffff || sh_num != 0xffffffff) + amdgpu_gfx_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); + mutex_unlock(&adev->grbm_idx_mutex); + return val; + } else { + unsigned idx; + + switch (reg_offset) { + case mmGB_ADDR_CONFIG: + return adev->gfx.config.gb_addr_config; + case mmMC_ARB_RAMCFG: + return adev->gfx.config.mc_arb_ramcfg; + case mmGB_TILE_MODE0: + case mmGB_TILE_MODE1: + case mmGB_TILE_MODE2: + case mmGB_TILE_MODE3: + case mmGB_TILE_MODE4: + case mmGB_TILE_MODE5: + case mmGB_TILE_MODE6: + case mmGB_TILE_MODE7: + case mmGB_TILE_MODE8: + case mmGB_TILE_MODE9: + case mmGB_TILE_MODE10: + case mmGB_TILE_MODE11: + case mmGB_TILE_MODE12: + case mmGB_TILE_MODE13: + case mmGB_TILE_MODE14: + case mmGB_TILE_MODE15: + case mmGB_TILE_MODE16: + case mmGB_TILE_MODE17: + case mmGB_TILE_MODE18: + case mmGB_TILE_MODE19: + case mmGB_TILE_MODE20: + case mmGB_TILE_MODE21: + case mmGB_TILE_MODE22: + case mmGB_TILE_MODE23: + case mmGB_TILE_MODE24: + case mmGB_TILE_MODE25: + case mmGB_TILE_MODE26: + case mmGB_TILE_MODE27: + case mmGB_TILE_MODE28: + case mmGB_TILE_MODE29: + case mmGB_TILE_MODE30: + case mmGB_TILE_MODE31: + idx = (reg_offset - mmGB_TILE_MODE0); + return adev->gfx.config.tile_mode_array[idx]; + default: + return RREG32(reg_offset); + } + } } - static int si_read_register(struct amdgpu_device *adev, u32 se_num, u32 sh_num, u32 reg_offset, u32 *value) { @@ -1039,10 +1096,9 @@ static int si_read_register(struct amdgpu_device *adev, u32 se_num, continue; if (!si_allowed_read_registers[i].untouched) - *value = si_allowed_read_registers[i].grbm_indexed ? - si_read_indexed_register(adev, se_num, - sh_num, reg_offset) : - RREG32(reg_offset); + *value = si_get_register_value(adev, + si_allowed_read_registers[i].grbm_indexed, + se_num, sh_num, reg_offset); return 0; } return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/si_enums.h b/drivers/gpu/drm/amd/amdgpu/si_enums.h index fde2086246fa..dc9e0e6b4558 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_enums.h +++ b/drivers/gpu/drm/amd/amdgpu/si_enums.h @@ -143,8 +143,8 @@ #define RLC_CLEAR_STATE_DESCRIPTOR_OFFSET 0x3D #define TAHITI_GB_ADDR_CONFIG_GOLDEN 0x12011003 -#define VERDE_GB_ADDR_CONFIG_GOLDEN 0x12010002 -#define HAINAN_GB_ADDR_CONFIG_GOLDEN 0x02010001 +#define VERDE_GB_ADDR_CONFIG_GOLDEN 0x02010002 +#define HAINAN_GB_ADDR_CONFIG_GOLDEN 0x02011003 #define PACKET3(op, n) ((RADEON_PACKET_TYPE3 << 30) | \ (((op) & 0xFF) << 8) | \ diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c index 7fb9137dd89b..b34cefc7ebd5 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c @@ -159,9 +159,6 @@ static int uvd_v4_2_hw_init(void *handle) uvd_v4_2_enable_mgcg(adev, true); amdgpu_asic_set_uvd_clocks(adev, 10000, 10000); - r = uvd_v4_2_start(adev); - if (r) - goto done; ring->ready = true; r = amdgpu_ring_test_ring(ring); @@ -198,7 +195,6 @@ static int uvd_v4_2_hw_init(void *handle) amdgpu_ring_commit(ring); done: - if (!r) DRM_INFO("UVD initialized successfully.\n"); @@ -217,7 +213,9 @@ static int uvd_v4_2_hw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct amdgpu_ring *ring = &adev->uvd.ring; - uvd_v4_2_stop(adev); + if (RREG32(mmUVD_STATUS) != 0) + uvd_v4_2_stop(adev); + ring->ready = false; return 0; @@ -267,37 +265,26 @@ static int uvd_v4_2_start(struct amdgpu_device *adev) struct amdgpu_ring *ring = &adev->uvd.ring; uint32_t rb_bufsz; int i, j, r; + u32 tmp; /* disable byte swapping */ u32 lmi_swap_cntl = 0; u32 mp_swap_cntl = 0; - WREG32(mmUVD_CGC_GATE, 0); - uvd_v4_2_set_dcm(adev, true); - - uvd_v4_2_mc_resume(adev); + /* set uvd busy */ + WREG32_P(mmUVD_STATUS, 1<<2, ~(1<<2)); - /* disable interupt */ - WREG32_P(mmUVD_MASTINT_EN, 0, ~(1 << 1)); - - /* Stall UMC and register bus before resetting VCPU */ - WREG32_P(mmUVD_LMI_CTRL2, 1 << 8, ~(1 << 8)); - mdelay(1); - - /* put LMI, VCPU, RBC etc... into reset */ - WREG32(mmUVD_SOFT_RESET, UVD_SOFT_RESET__LMI_SOFT_RESET_MASK | - UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK | UVD_SOFT_RESET__LBSI_SOFT_RESET_MASK | - UVD_SOFT_RESET__RBC_SOFT_RESET_MASK | UVD_SOFT_RESET__CSM_SOFT_RESET_MASK | - UVD_SOFT_RESET__CXW_SOFT_RESET_MASK | UVD_SOFT_RESET__TAP_SOFT_RESET_MASK | - UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK); - mdelay(5); + uvd_v4_2_set_dcm(adev, true); + WREG32(mmUVD_CGC_GATE, 0); /* take UVD block out of reset */ WREG32_P(mmSRBM_SOFT_RESET, 0, ~SRBM_SOFT_RESET__SOFT_RESET_UVD_MASK); mdelay(5); - /* initialize UVD memory controller */ - WREG32(mmUVD_LMI_CTRL, 0x40 | (1 << 8) | (1 << 13) | - (1 << 21) | (1 << 9) | (1 << 20)); + /* enable VCPU clock */ + WREG32(mmUVD_VCPU_CNTL, 1 << 9); + + /* disable interupt */ + WREG32_P(mmUVD_MASTINT_EN, 0, ~(1 << 1)); #ifdef __BIG_ENDIAN /* swap (8 in 32) RB and IB */ @@ -306,6 +293,11 @@ static int uvd_v4_2_start(struct amdgpu_device *adev) #endif WREG32(mmUVD_LMI_SWAP_CNTL, lmi_swap_cntl); WREG32(mmUVD_MP_SWAP_CNTL, mp_swap_cntl); + /* initialize UVD memory controller */ + WREG32(mmUVD_LMI_CTRL, 0x203108); + + tmp = RREG32(mmUVD_MPC_CNTL); + WREG32(mmUVD_MPC_CNTL, tmp | 0x10); WREG32(mmUVD_MPC_SET_MUXA0, 0x40c2040); WREG32(mmUVD_MPC_SET_MUXA1, 0x0); @@ -314,18 +306,20 @@ static int uvd_v4_2_start(struct amdgpu_device *adev) WREG32(mmUVD_MPC_SET_ALU, 0); WREG32(mmUVD_MPC_SET_MUX, 0x88); - /* take all subblocks out of reset, except VCPU */ - WREG32(mmUVD_SOFT_RESET, UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK); - mdelay(5); + uvd_v4_2_mc_resume(adev); - /* enable VCPU clock */ - WREG32(mmUVD_VCPU_CNTL, 1 << 9); + tmp = RREG32_UVD_CTX(ixUVD_LMI_CACHE_CTRL); + WREG32_UVD_CTX(ixUVD_LMI_CACHE_CTRL, tmp & (~0x10)); /* enable UMC */ WREG32_P(mmUVD_LMI_CTRL2, 0, ~(1 << 8)); - /* boot up the VCPU */ - WREG32(mmUVD_SOFT_RESET, 0); + WREG32_P(mmUVD_SOFT_RESET, 0, ~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK); + + WREG32_P(mmUVD_SOFT_RESET, 0, ~UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK); + + WREG32_P(mmUVD_SOFT_RESET, 0, ~UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK); + mdelay(10); for (i = 0; i < 10; ++i) { @@ -357,6 +351,8 @@ static int uvd_v4_2_start(struct amdgpu_device *adev) /* enable interupt */ WREG32_P(mmUVD_MASTINT_EN, 3<<1, ~(3 << 1)); + WREG32_P(mmUVD_STATUS, 0, ~(1<<2)); + /* force RBC into idle state */ WREG32(mmUVD_RBC_RB_CNTL, 0x11010101); @@ -393,22 +389,57 @@ static int uvd_v4_2_start(struct amdgpu_device *adev) */ static void uvd_v4_2_stop(struct amdgpu_device *adev) { - /* force RBC into idle state */ + uint32_t i, j; + uint32_t status; + WREG32(mmUVD_RBC_RB_CNTL, 0x11010101); + for (i = 0; i < 10; ++i) { + for (j = 0; j < 100; ++j) { + status = RREG32(mmUVD_STATUS); + if (status & 2) + break; + mdelay(1); + } + if (status & 2) + break; + } + + for (i = 0; i < 10; ++i) { + for (j = 0; j < 100; ++j) { + status = RREG32(mmUVD_LMI_STATUS); + if (status & 0xf) + break; + mdelay(1); + } + if (status & 0xf) + break; + } + /* Stall UMC and register bus before resetting VCPU */ WREG32_P(mmUVD_LMI_CTRL2, 1 << 8, ~(1 << 8)); - mdelay(1); - /* put VCPU into reset */ - WREG32(mmUVD_SOFT_RESET, UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK); - mdelay(5); + for (i = 0; i < 10; ++i) { + for (j = 0; j < 100; ++j) { + status = RREG32(mmUVD_LMI_STATUS); + if (status & 0x240) + break; + mdelay(1); + } + if (status & 0x240) + break; + } - /* disable VCPU clock */ - WREG32(mmUVD_VCPU_CNTL, 0x0); + WREG32_P(0x3D49, 0, ~(1 << 2)); - /* Unstall UMC and register bus */ - WREG32_P(mmUVD_LMI_CTRL2, 0, ~(1 << 8)); + WREG32_P(mmUVD_VCPU_CNTL, 0, ~(1 << 9)); + + /* put LMI, VCPU, RBC etc... into reset */ + WREG32(mmUVD_SOFT_RESET, UVD_SOFT_RESET__LMI_SOFT_RESET_MASK | + UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK | + UVD_SOFT_RESET__LMI_UMC_SOFT_RESET_MASK); + + WREG32(mmUVD_STATUS, 0); uvd_v4_2_set_dcm(adev, false); } @@ -694,8 +725,26 @@ static int uvd_v4_2_set_powergating_state(void *handle, if (state == AMD_PG_STATE_GATE) { uvd_v4_2_stop(adev); + if (adev->pg_flags & AMD_PG_SUPPORT_UVD && amdgpu_dpm == 0) { + if (!(RREG32_SMC(ixCURRENT_PG_STATUS) & + CURRENT_PG_STATUS__UVD_PG_STATUS_MASK)) { + WREG32(mmUVD_PGFSM_CONFIG, (UVD_PGFSM_CONFIG__UVD_PGFSM_FSM_ADDR_MASK | + UVD_PGFSM_CONFIG__UVD_PGFSM_POWER_DOWN_MASK | + UVD_PGFSM_CONFIG__UVD_PGFSM_P1_SELECT_MASK)); + mdelay(20); + } + } return 0; } else { + if (adev->pg_flags & AMD_PG_SUPPORT_UVD && amdgpu_dpm == 0) { + if (RREG32_SMC(ixCURRENT_PG_STATUS) & + CURRENT_PG_STATUS__UVD_PG_STATUS_MASK) { + WREG32(mmUVD_PGFSM_CONFIG, (UVD_PGFSM_CONFIG__UVD_PGFSM_FSM_ADDR_MASK | + UVD_PGFSM_CONFIG__UVD_PGFSM_POWER_UP_MASK | + UVD_PGFSM_CONFIG__UVD_PGFSM_P1_SELECT_MASK)); + mdelay(30); + } + } return uvd_v4_2_start(adev); } } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c index 9b49824233ae..ad8c02e423d4 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c @@ -152,9 +152,9 @@ static int uvd_v5_0_hw_init(void *handle) uint32_t tmp; int r; - r = uvd_v5_0_start(adev); - if (r) - goto done; + amdgpu_asic_set_uvd_clocks(adev, 10000, 10000); + uvd_v5_0_set_clockgating_state(adev, AMD_CG_STATE_UNGATE); + uvd_v5_0_enable_mgcg(adev, true); ring->ready = true; r = amdgpu_ring_test_ring(ring); @@ -189,11 +189,13 @@ static int uvd_v5_0_hw_init(void *handle) amdgpu_ring_write(ring, 3); amdgpu_ring_commit(ring); + done: if (!r) DRM_INFO("UVD initialized successfully.\n"); return r; + } /** @@ -208,7 +210,9 @@ static int uvd_v5_0_hw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct amdgpu_ring *ring = &adev->uvd.ring; - uvd_v5_0_stop(adev); + if (RREG32(mmUVD_STATUS) != 0) + uvd_v5_0_stop(adev); + ring->ready = false; return 0; @@ -310,10 +314,6 @@ static int uvd_v5_0_start(struct amdgpu_device *adev) uvd_v5_0_mc_resume(adev); - amdgpu_asic_set_uvd_clocks(adev, 10000, 10000); - uvd_v5_0_set_clockgating_state(adev, AMD_CG_STATE_UNGATE); - uvd_v5_0_enable_mgcg(adev, true); - /* disable interupt */ WREG32_P(mmUVD_MASTINT_EN, 0, ~(1 << 1)); @@ -456,6 +456,8 @@ static void uvd_v5_0_stop(struct amdgpu_device *adev) /* Unstall UMC and register bus */ WREG32_P(mmUVD_LMI_CTRL2, 0, ~(1 << 8)); + + WREG32(mmUVD_STATUS, 0); } /** @@ -792,9 +794,6 @@ static int uvd_v5_0_set_clockgating_state(void *handle, struct amdgpu_device *adev = (struct amdgpu_device *)handle; bool enable = (state == AMD_CG_STATE_GATE) ? true : false; - if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG)) - return 0; - if (enable) { /* wait for STATUS to clear */ if (uvd_v5_0_wait_for_idle(handle)) @@ -824,17 +823,12 @@ static int uvd_v5_0_set_powergating_state(void *handle, struct amdgpu_device *adev = (struct amdgpu_device *)handle; int ret = 0; - if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD)) - return 0; - if (state == AMD_PG_STATE_GATE) { uvd_v5_0_stop(adev); - adev->uvd.is_powergated = true; } else { ret = uvd_v5_0_start(adev); if (ret) goto out; - adev->uvd.is_powergated = false; } out: @@ -848,7 +842,8 @@ static void uvd_v5_0_get_clockgating_state(void *handle, u32 *flags) mutex_lock(&adev->pm.mutex); - if (adev->uvd.is_powergated) { + if (RREG32_SMC(ixCURRENT_PG_STATUS) & + CURRENT_PG_STATUS__UVD_PG_STATUS_MASK) { DRM_INFO("Cannot get clockgating state when UVD is powergated.\n"); goto out; } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index de7e03544d00..18a6de4e1512 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -155,9 +155,9 @@ static int uvd_v6_0_hw_init(void *handle) uint32_t tmp; int r; - r = uvd_v6_0_start(adev); - if (r) - goto done; + amdgpu_asic_set_uvd_clocks(adev, 10000, 10000); + uvd_v6_0_set_clockgating_state(adev, AMD_CG_STATE_UNGATE); + uvd_v6_0_enable_mgcg(adev, true); ring->ready = true; r = amdgpu_ring_test_ring(ring); @@ -212,7 +212,9 @@ static int uvd_v6_0_hw_fini(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct amdgpu_ring *ring = &adev->uvd.ring; - uvd_v6_0_stop(adev); + if (RREG32(mmUVD_STATUS) != 0) + uvd_v6_0_stop(adev); + ring->ready = false; return 0; @@ -397,9 +399,6 @@ static int uvd_v6_0_start(struct amdgpu_device *adev) lmi_swap_cntl = 0; mp_swap_cntl = 0; - amdgpu_asic_set_uvd_clocks(adev, 10000, 10000); - uvd_v6_0_set_clockgating_state(adev, AMD_CG_STATE_UNGATE); - uvd_v6_0_enable_mgcg(adev, true); uvd_v6_0_mc_resume(adev); /* disable interupt */ @@ -554,6 +553,8 @@ static void uvd_v6_0_stop(struct amdgpu_device *adev) /* Unstall UMC and register bus */ WREG32_P(mmUVD_LMI_CTRL2, 0, ~(1 << 8)); + + WREG32(mmUVD_STATUS, 0); } /** @@ -1018,9 +1019,6 @@ static int uvd_v6_0_set_clockgating_state(void *handle, struct amdgpu_device *adev = (struct amdgpu_device *)handle; bool enable = (state == AMD_CG_STATE_GATE) ? true : false; - if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG)) - return 0; - if (enable) { /* wait for STATUS to clear */ if (uvd_v6_0_wait_for_idle(handle)) @@ -1049,19 +1047,14 @@ static int uvd_v6_0_set_powergating_state(void *handle, struct amdgpu_device *adev = (struct amdgpu_device *)handle; int ret = 0; - if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD)) - return 0; - WREG32(mmUVD_POWER_STATUS, UVD_POWER_STATUS__UVD_PG_EN_MASK); if (state == AMD_PG_STATE_GATE) { uvd_v6_0_stop(adev); - adev->uvd.is_powergated = true; } else { ret = uvd_v6_0_start(adev); if (ret) goto out; - adev->uvd.is_powergated = false; } out: @@ -1075,7 +1068,8 @@ static void uvd_v6_0_get_clockgating_state(void *handle, u32 *flags) mutex_lock(&adev->pm.mutex); - if (adev->uvd.is_powergated) { + if (RREG32_SMC(ixCURRENT_PG_STATUS) & + CURRENT_PG_STATUS__UVD_PG_STATUS_MASK) { DRM_INFO("Cannot get clockgating state when UVD is powergated.\n"); goto out; } diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c index 38ed903dd6f8..9ea99348e493 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c @@ -42,10 +42,9 @@ #define VCE_V2_0_DATA_SIZE (23552 * AMDGPU_MAX_VCE_HANDLES) #define VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK 0x02 -static void vce_v2_0_mc_resume(struct amdgpu_device *adev); static void vce_v2_0_set_ring_funcs(struct amdgpu_device *adev); static void vce_v2_0_set_irq_funcs(struct amdgpu_device *adev); -static int vce_v2_0_wait_for_idle(void *handle); + /** * vce_v2_0_ring_get_rptr - get read pointer * @@ -140,6 +139,86 @@ static int vce_v2_0_firmware_loaded(struct amdgpu_device *adev) return -ETIMEDOUT; } +static void vce_v2_0_disable_cg(struct amdgpu_device *adev) +{ + WREG32(mmVCE_CGTT_CLK_OVERRIDE, 7); +} + +static void vce_v2_0_init_cg(struct amdgpu_device *adev) +{ + u32 tmp; + + tmp = RREG32(mmVCE_CLOCK_GATING_A); + tmp &= ~0xfff; + tmp |= ((0 << 0) | (4 << 4)); + tmp |= 0x40000; + WREG32(mmVCE_CLOCK_GATING_A, tmp); + + tmp = RREG32(mmVCE_UENC_CLOCK_GATING); + tmp &= ~0xfff; + tmp |= ((0 << 0) | (4 << 4)); + WREG32(mmVCE_UENC_CLOCK_GATING, tmp); + + tmp = RREG32(mmVCE_CLOCK_GATING_B); + tmp |= 0x10; + tmp &= ~0x100000; + WREG32(mmVCE_CLOCK_GATING_B, tmp); +} + +static void vce_v2_0_mc_resume(struct amdgpu_device *adev) +{ + uint64_t addr = adev->vce.gpu_addr; + uint32_t size; + + WREG32_P(mmVCE_CLOCK_GATING_A, 0, ~(1 << 16)); + WREG32_P(mmVCE_UENC_CLOCK_GATING, 0x1FF000, ~0xFF9FF000); + WREG32_P(mmVCE_UENC_REG_CLOCK_GATING, 0x3F, ~0x3F); + WREG32(mmVCE_CLOCK_GATING_B, 0xf7); + + WREG32(mmVCE_LMI_CTRL, 0x00398000); + WREG32_P(mmVCE_LMI_CACHE_CTRL, 0x0, ~0x1); + WREG32(mmVCE_LMI_SWAP_CNTL, 0); + WREG32(mmVCE_LMI_SWAP_CNTL1, 0); + WREG32(mmVCE_LMI_VM_CTRL, 0); + + addr += AMDGPU_VCE_FIRMWARE_OFFSET; + size = VCE_V2_0_FW_SIZE; + WREG32(mmVCE_VCPU_CACHE_OFFSET0, addr & 0x7fffffff); + WREG32(mmVCE_VCPU_CACHE_SIZE0, size); + + addr += size; + size = VCE_V2_0_STACK_SIZE; + WREG32(mmVCE_VCPU_CACHE_OFFSET1, addr & 0x7fffffff); + WREG32(mmVCE_VCPU_CACHE_SIZE1, size); + + addr += size; + size = VCE_V2_0_DATA_SIZE; + WREG32(mmVCE_VCPU_CACHE_OFFSET2, addr & 0x7fffffff); + WREG32(mmVCE_VCPU_CACHE_SIZE2, size); + + WREG32_P(mmVCE_LMI_CTRL2, 0x0, ~0x100); + WREG32_FIELD(VCE_SYS_INT_EN, VCE_SYS_INT_TRAP_INTERRUPT_EN, 1); +} + +static bool vce_v2_0_is_idle(void *handle) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + return !(RREG32(mmSRBM_STATUS2) & SRBM_STATUS2__VCE_BUSY_MASK); +} + +static int vce_v2_0_wait_for_idle(void *handle) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + unsigned i; + + for (i = 0; i < adev->usec_timeout; i++) { + if (vce_v2_0_is_idle(handle)) + return 0; + } + return -ETIMEDOUT; +} + /** * vce_v2_0_start - start VCE block * @@ -152,11 +231,14 @@ static int vce_v2_0_start(struct amdgpu_device *adev) struct amdgpu_ring *ring; int r; - vce_v2_0_mc_resume(adev); - /* set BUSY flag */ WREG32_P(mmVCE_STATUS, 1, ~1); + vce_v2_0_init_cg(adev); + vce_v2_0_disable_cg(adev); + + vce_v2_0_mc_resume(adev); + ring = &adev->vce.ring[0]; WREG32(mmVCE_RB_RPTR, ring->wptr); WREG32(mmVCE_RB_WPTR, ring->wptr); @@ -189,6 +271,145 @@ static int vce_v2_0_start(struct amdgpu_device *adev) return 0; } +static int vce_v2_0_stop(struct amdgpu_device *adev) +{ + int i, j; + int status; + + if (vce_v2_0_lmi_clean(adev)) { + DRM_INFO("vce is not idle \n"); + return 0; + } +/* + for (i = 0; i < 10; ++i) { + for (j = 0; j < 100; ++j) { + status = RREG32(mmVCE_FW_REG_STATUS); + if (!(status & 1)) + break; + mdelay(1); + } + break; + } +*/ + if (vce_v2_0_wait_for_idle(adev)) { + DRM_INFO("VCE is busy, Can't set clock gateing"); + return 0; + } + + /* Stall UMC and register bus before resetting VCPU */ + WREG32_P(mmVCE_LMI_CTRL2, 1 << 8, ~(1 << 8)); + + for (i = 0; i < 10; ++i) { + for (j = 0; j < 100; ++j) { + status = RREG32(mmVCE_LMI_STATUS); + if (status & 0x240) + break; + mdelay(1); + } + break; + } + + WREG32_P(mmVCE_VCPU_CNTL, 0, ~0x80001); + + /* put LMI, VCPU, RBC etc... into reset */ + WREG32_P(mmVCE_SOFT_RESET, 1, ~0x1); + + WREG32(mmVCE_STATUS, 0); + + return 0; +} + +static void vce_v2_0_set_sw_cg(struct amdgpu_device *adev, bool gated) +{ + u32 tmp; + + if (gated) { + tmp = RREG32(mmVCE_CLOCK_GATING_B); + tmp |= 0xe70000; + WREG32(mmVCE_CLOCK_GATING_B, tmp); + + tmp = RREG32(mmVCE_UENC_CLOCK_GATING); + tmp |= 0xff000000; + WREG32(mmVCE_UENC_CLOCK_GATING, tmp); + + tmp = RREG32(mmVCE_UENC_REG_CLOCK_GATING); + tmp &= ~0x3fc; + WREG32(mmVCE_UENC_REG_CLOCK_GATING, tmp); + + WREG32(mmVCE_CGTT_CLK_OVERRIDE, 0); + } else { + tmp = RREG32(mmVCE_CLOCK_GATING_B); + tmp |= 0xe7; + tmp &= ~0xe70000; + WREG32(mmVCE_CLOCK_GATING_B, tmp); + + tmp = RREG32(mmVCE_UENC_CLOCK_GATING); + tmp |= 0x1fe000; + tmp &= ~0xff000000; + WREG32(mmVCE_UENC_CLOCK_GATING, tmp); + + tmp = RREG32(mmVCE_UENC_REG_CLOCK_GATING); + tmp |= 0x3fc; + WREG32(mmVCE_UENC_REG_CLOCK_GATING, tmp); + } +} + +static void vce_v2_0_set_dyn_cg(struct amdgpu_device *adev, bool gated) +{ + u32 orig, tmp; + +/* LMI_MC/LMI_UMC always set in dynamic, + * set {CGC_*_GATE_MODE, CGC_*_SW_GATE} = {0, 0} + */ + tmp = RREG32(mmVCE_CLOCK_GATING_B); + tmp &= ~0x00060006; + +/* Exception for ECPU, IH, SEM, SYS blocks needs to be turned on/off by SW */ + if (gated) { + tmp |= 0xe10000; + WREG32(mmVCE_CLOCK_GATING_B, tmp); + } else { + tmp |= 0xe1; + tmp &= ~0xe10000; + WREG32(mmVCE_CLOCK_GATING_B, tmp); + } + + orig = tmp = RREG32(mmVCE_UENC_CLOCK_GATING); + tmp &= ~0x1fe000; + tmp &= ~0xff000000; + if (tmp != orig) + WREG32(mmVCE_UENC_CLOCK_GATING, tmp); + + orig = tmp = RREG32(mmVCE_UENC_REG_CLOCK_GATING); + tmp &= ~0x3fc; + if (tmp != orig) + WREG32(mmVCE_UENC_REG_CLOCK_GATING, tmp); + + /* set VCE_UENC_REG_CLOCK_GATING always in dynamic mode */ + WREG32(mmVCE_UENC_REG_CLOCK_GATING, 0x00); + + if(gated) + WREG32(mmVCE_CGTT_CLK_OVERRIDE, 0); +} + +static void vce_v2_0_enable_mgcg(struct amdgpu_device *adev, bool enable, + bool sw_cg) +{ + if (enable && (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG)) { + if (sw_cg) + vce_v2_0_set_sw_cg(adev, true); + else + vce_v2_0_set_dyn_cg(adev, true); + } else { + vce_v2_0_disable_cg(adev); + + if (sw_cg) + vce_v2_0_set_sw_cg(adev, false); + else + vce_v2_0_set_dyn_cg(adev, false); + } +} + static int vce_v2_0_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -254,11 +475,8 @@ static int vce_v2_0_hw_init(void *handle) int r, i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - r = vce_v2_0_start(adev); - /* this error mean vcpu not in running state, so just skip ring test, not stop driver initialize */ - if (r) - return 0; - + amdgpu_asic_set_vce_clocks(adev, 10000, 10000); + vce_v2_0_enable_mgcg(adev, true, false); for (i = 0; i < adev->vce.num_rings; i++) adev->vce.ring[i].ready = false; @@ -312,190 +530,6 @@ static int vce_v2_0_resume(void *handle) return r; } -static void vce_v2_0_set_sw_cg(struct amdgpu_device *adev, bool gated) -{ - u32 tmp; - - if (gated) { - tmp = RREG32(mmVCE_CLOCK_GATING_B); - tmp |= 0xe70000; - WREG32(mmVCE_CLOCK_GATING_B, tmp); - - tmp = RREG32(mmVCE_UENC_CLOCK_GATING); - tmp |= 0xff000000; - WREG32(mmVCE_UENC_CLOCK_GATING, tmp); - - tmp = RREG32(mmVCE_UENC_REG_CLOCK_GATING); - tmp &= ~0x3fc; - WREG32(mmVCE_UENC_REG_CLOCK_GATING, tmp); - - WREG32(mmVCE_CGTT_CLK_OVERRIDE, 0); - } else { - tmp = RREG32(mmVCE_CLOCK_GATING_B); - tmp |= 0xe7; - tmp &= ~0xe70000; - WREG32(mmVCE_CLOCK_GATING_B, tmp); - - tmp = RREG32(mmVCE_UENC_CLOCK_GATING); - tmp |= 0x1fe000; - tmp &= ~0xff000000; - WREG32(mmVCE_UENC_CLOCK_GATING, tmp); - - tmp = RREG32(mmVCE_UENC_REG_CLOCK_GATING); - tmp |= 0x3fc; - WREG32(mmVCE_UENC_REG_CLOCK_GATING, tmp); - } -} - -static void vce_v2_0_set_dyn_cg(struct amdgpu_device *adev, bool gated) -{ - if (vce_v2_0_wait_for_idle(adev)) { - DRM_INFO("VCE is busy, Can't set clock gateing"); - return; - } - - WREG32_P(mmVCE_LMI_CTRL2, 0x100, ~0x100); - - if (vce_v2_0_lmi_clean(adev)) { - DRM_INFO("LMI is busy, Can't set clock gateing"); - return; - } - - WREG32_P(mmVCE_VCPU_CNTL, 0, ~VCE_VCPU_CNTL__CLK_EN_MASK); - WREG32_P(mmVCE_SOFT_RESET, - VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK, - ~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK); - WREG32(mmVCE_STATUS, 0); - - if (gated) - WREG32(mmVCE_CGTT_CLK_OVERRIDE, 0); - /* LMI_MC/LMI_UMC always set in dynamic, set {CGC_*_GATE_MODE, CGC_*_SW_GATE} = {0, 0} */ - if (gated) { - /* Force CLOCK OFF , set {CGC_*_GATE_MODE, CGC_*_SW_GATE} = {*, 1} */ - WREG32(mmVCE_CLOCK_GATING_B, 0xe90010); - } else { - /* Force CLOCK ON, set {CGC_*_GATE_MODE, CGC_*_SW_GATE} = {1, 0} */ - WREG32(mmVCE_CLOCK_GATING_B, 0x800f1); - } - - /* Set VCE_UENC_CLOCK_GATING always in dynamic mode {*_FORCE_ON, *_FORCE_OFF} = {0, 0}*/; - WREG32(mmVCE_UENC_CLOCK_GATING, 0x40); - - /* set VCE_UENC_REG_CLOCK_GATING always in dynamic mode */ - WREG32(mmVCE_UENC_REG_CLOCK_GATING, 0x00); - - WREG32_P(mmVCE_LMI_CTRL2, 0, ~0x100); - if(!gated) { - WREG32_P(mmVCE_VCPU_CNTL, VCE_VCPU_CNTL__CLK_EN_MASK, ~VCE_VCPU_CNTL__CLK_EN_MASK); - mdelay(100); - WREG32_P(mmVCE_SOFT_RESET, 0, ~VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK); - - vce_v2_0_firmware_loaded(adev); - WREG32_P(mmVCE_STATUS, 0, ~VCE_STATUS__JOB_BUSY_MASK); - } -} - -static void vce_v2_0_disable_cg(struct amdgpu_device *adev) -{ - WREG32(mmVCE_CGTT_CLK_OVERRIDE, 7); -} - -static void vce_v2_0_enable_mgcg(struct amdgpu_device *adev, bool enable) -{ - bool sw_cg = false; - - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_VCE_MGCG)) { - if (sw_cg) - vce_v2_0_set_sw_cg(adev, true); - else - vce_v2_0_set_dyn_cg(adev, true); - } else { - vce_v2_0_disable_cg(adev); - - if (sw_cg) - vce_v2_0_set_sw_cg(adev, false); - else - vce_v2_0_set_dyn_cg(adev, false); - } -} - -static void vce_v2_0_init_cg(struct amdgpu_device *adev) -{ - u32 tmp; - - tmp = RREG32(mmVCE_CLOCK_GATING_A); - tmp &= ~0xfff; - tmp |= ((0 << 0) | (4 << 4)); - tmp |= 0x40000; - WREG32(mmVCE_CLOCK_GATING_A, tmp); - - tmp = RREG32(mmVCE_UENC_CLOCK_GATING); - tmp &= ~0xfff; - tmp |= ((0 << 0) | (4 << 4)); - WREG32(mmVCE_UENC_CLOCK_GATING, tmp); - - tmp = RREG32(mmVCE_CLOCK_GATING_B); - tmp |= 0x10; - tmp &= ~0x100000; - WREG32(mmVCE_CLOCK_GATING_B, tmp); -} - -static void vce_v2_0_mc_resume(struct amdgpu_device *adev) -{ - uint64_t addr = adev->vce.gpu_addr; - uint32_t size; - - WREG32_P(mmVCE_CLOCK_GATING_A, 0, ~(1 << 16)); - WREG32_P(mmVCE_UENC_CLOCK_GATING, 0x1FF000, ~0xFF9FF000); - WREG32_P(mmVCE_UENC_REG_CLOCK_GATING, 0x3F, ~0x3F); - WREG32(mmVCE_CLOCK_GATING_B, 0xf7); - - WREG32(mmVCE_LMI_CTRL, 0x00398000); - WREG32_P(mmVCE_LMI_CACHE_CTRL, 0x0, ~0x1); - WREG32(mmVCE_LMI_SWAP_CNTL, 0); - WREG32(mmVCE_LMI_SWAP_CNTL1, 0); - WREG32(mmVCE_LMI_VM_CTRL, 0); - - addr += AMDGPU_VCE_FIRMWARE_OFFSET; - size = VCE_V2_0_FW_SIZE; - WREG32(mmVCE_VCPU_CACHE_OFFSET0, addr & 0x7fffffff); - WREG32(mmVCE_VCPU_CACHE_SIZE0, size); - - addr += size; - size = VCE_V2_0_STACK_SIZE; - WREG32(mmVCE_VCPU_CACHE_OFFSET1, addr & 0x7fffffff); - WREG32(mmVCE_VCPU_CACHE_SIZE1, size); - - addr += size; - size = VCE_V2_0_DATA_SIZE; - WREG32(mmVCE_VCPU_CACHE_OFFSET2, addr & 0x7fffffff); - WREG32(mmVCE_VCPU_CACHE_SIZE2, size); - - WREG32_P(mmVCE_LMI_CTRL2, 0x0, ~0x100); - WREG32_FIELD(VCE_SYS_INT_EN, VCE_SYS_INT_TRAP_INTERRUPT_EN, 1); - - vce_v2_0_init_cg(adev); -} - -static bool vce_v2_0_is_idle(void *handle) -{ - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - - return !(RREG32(mmSRBM_STATUS2) & SRBM_STATUS2__VCE_BUSY_MASK); -} - -static int vce_v2_0_wait_for_idle(void *handle) -{ - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - unsigned i; - - for (i = 0; i < adev->usec_timeout; i++) { - if (vce_v2_0_is_idle(handle)) - return 0; - } - return -ETIMEDOUT; -} - static int vce_v2_0_soft_reset(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -539,33 +573,20 @@ static int vce_v2_0_process_interrupt(struct amdgpu_device *adev, return 0; } -static void vce_v2_0_set_bypass_mode(struct amdgpu_device *adev, bool enable) -{ - u32 tmp = RREG32_SMC(ixGCK_DFS_BYPASS_CNTL); - - if (enable) - tmp |= GCK_DFS_BYPASS_CNTL__BYPASSECLK_MASK; - else - tmp &= ~GCK_DFS_BYPASS_CNTL__BYPASSECLK_MASK; - - WREG32_SMC(ixGCK_DFS_BYPASS_CNTL, tmp); -} - - static int vce_v2_0_set_clockgating_state(void *handle, enum amd_clockgating_state state) { bool gate = false; - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - bool enable = (state == AMD_CG_STATE_GATE) ? true : false; - + bool sw_cg = false; - vce_v2_0_set_bypass_mode(adev, enable); + struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (state == AMD_CG_STATE_GATE) + if (state == AMD_CG_STATE_GATE) { gate = true; + sw_cg = true; + } - vce_v2_0_enable_mgcg(adev, gate); + vce_v2_0_enable_mgcg(adev, gate, sw_cg); return 0; } @@ -582,12 +603,8 @@ static int vce_v2_0_set_powergating_state(void *handle, */ struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (!(adev->pg_flags & AMD_PG_SUPPORT_VCE)) - return 0; - if (state == AMD_PG_STATE_GATE) - /* XXX do we need a vce_v2_0_stop()? */ - return 0; + return vce_v2_0_stop(adev); else return vce_v2_0_start(adev); } diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c index 8db26559fd1b..93ec8815bb13 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c @@ -230,10 +230,6 @@ static int vce_v3_0_start(struct amdgpu_device *adev) struct amdgpu_ring *ring; int idx, r; - vce_v3_0_override_vce_clock_gating(adev, true); - if (!(adev->flags & AMD_IS_APU)) - amdgpu_asic_set_vce_clocks(adev, 10000, 10000); - ring = &adev->vce.ring[0]; WREG32(mmVCE_RB_RPTR, ring->wptr); WREG32(mmVCE_RB_WPTR, ring->wptr); @@ -436,9 +432,9 @@ static int vce_v3_0_hw_init(void *handle) int r, i; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - r = vce_v3_0_start(adev); - if (r) - return r; + vce_v3_0_override_vce_clock_gating(adev, true); + if (!(adev->flags & AMD_IS_APU)) + amdgpu_asic_set_vce_clocks(adev, 10000, 10000); for (i = 0; i < adev->vce.num_rings; i++) adev->vce.ring[i].ready = false; @@ -514,6 +510,8 @@ static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx) WREG32(mmVCE_LMI_SWAP_CNTL, 0); WREG32(mmVCE_LMI_SWAP_CNTL1, 0); WREG32(mmVCE_LMI_VM_CTRL, 0); + WREG32_OR(mmVCE_VCPU_CNTL, 0x00100000); + if (adev->asic_type >= CHIP_STONEY) { WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR0, (adev->vce.gpu_addr >> 8)); WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR1, (adev->vce.gpu_addr >> 8)); @@ -766,17 +764,14 @@ static int vce_v3_0_set_powergating_state(void *handle, struct amdgpu_device *adev = (struct amdgpu_device *)handle; int ret = 0; - if (!(adev->pg_flags & AMD_PG_SUPPORT_VCE)) - return 0; - if (state == AMD_PG_STATE_GATE) { - adev->vce.is_powergated = true; - /* XXX do we need a vce_v3_0_stop()? */ + ret = vce_v3_0_stop(adev); + if (ret) + goto out; } else { ret = vce_v3_0_start(adev); if (ret) goto out; - adev->vce.is_powergated = false; } out: @@ -790,7 +785,8 @@ static void vce_v3_0_get_clockgating_state(void *handle, u32 *flags) mutex_lock(&adev->pm.mutex); - if (adev->vce.is_powergated) { + if (RREG32_SMC(ixCURRENT_PG_STATUS) & + CURRENT_PG_STATUS__VCE_PG_STATUS_MASK) { DRM_INFO("Cannot get clockgating state when VCE is powergated.\n"); goto out; } diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 4922fff08c3c..50bdb24ef8d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -721,6 +721,7 @@ static int vi_gpu_pci_config_reset(struct amdgpu_device *adev) if (RREG32(mmCONFIG_MEMSIZE) != 0xffffffff) { /* enable BM */ pci_set_master(adev->pdev); + adev->has_hw_reset = true; return 0; } udelay(1); diff --git a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_d.h b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_d.h index f9fd2ea4625b..dbc2e723f659 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_d.h +++ b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_d.h @@ -1310,5 +1310,6 @@ #define ixROM_SW_DATA_62 0xc060012c #define ixROM_SW_DATA_63 0xc0600130 #define ixROM_SW_DATA_64 0xc0600134 +#define ixCURRENT_PG_STATUS 0xc020029c #endif /* SMU_7_0_1_D_H */ diff --git a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_sh_mask.h index 25882a4dea5d..34c6ff52710e 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_sh_mask.h @@ -5452,5 +5452,7 @@ #define ROM_SW_DATA_63__ROM_SW_DATA__SHIFT 0x0 #define ROM_SW_DATA_64__ROM_SW_DATA_MASK 0xffffffff #define ROM_SW_DATA_64__ROM_SW_DATA__SHIFT 0x0 +#define CURRENT_PG_STATUS__VCE_PG_STATUS_MASK 0x00000002 +#define CURRENT_PG_STATUS__UVD_PG_STATUS_MASK 0x00000004 #endif /* SMU_7_0_1_SH_MASK_H */ diff --git a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_1_d.h b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_1_d.h index a9ef1562f43b..66597c64f525 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_1_d.h +++ b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_1_d.h @@ -1121,5 +1121,6 @@ #define ixROM_SW_DATA_62 0xc060011c #define ixROM_SW_DATA_63 0xc0600120 #define ixROM_SW_DATA_64 0xc0600124 +#define ixCURRENT_PG_STATUS 0xc020029c #endif /* SMU_7_1_1_D_H */ diff --git a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_1_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_1_sh_mask.h index 2c997f7b5d13..fb06f2e2f6e6 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_1_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_1_sh_mask.h @@ -4860,5 +4860,7 @@ #define ROM_SW_DATA_63__ROM_SW_DATA__SHIFT 0x0 #define ROM_SW_DATA_64__ROM_SW_DATA_MASK 0xffffffff #define ROM_SW_DATA_64__ROM_SW_DATA__SHIFT 0x0 +#define CURRENT_PG_STATUS__VCE_PG_STATUS_MASK 0x00000002 +#define CURRENT_PG_STATUS__UVD_PG_STATUS_MASK 0x00000004 #endif /* SMU_7_1_1_SH_MASK_H */ diff --git a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_d.h b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_d.h index 22dd4c2b7290..4446d43d2a8f 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_d.h +++ b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_d.h @@ -1271,5 +1271,6 @@ #define ixROM_SW_DATA_62 0xc060011c #define ixROM_SW_DATA_63 0xc0600120 #define ixROM_SW_DATA_64 0xc0600124 +#define ixCURRENT_PG_STATUS 0xc020029c #endif /* SMU_7_1_2_D_H */ diff --git a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_sh_mask.h index 518fd02e9d35..627906674fe8 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_sh_mask.h @@ -5830,5 +5830,7 @@ #define ROM_SW_DATA_63__ROM_SW_DATA__SHIFT 0x0 #define ROM_SW_DATA_64__ROM_SW_DATA_MASK 0xffffffff #define ROM_SW_DATA_64__ROM_SW_DATA__SHIFT 0x0 +#define CURRENT_PG_STATUS__VCE_PG_STATUS_MASK 0x00000002 +#define CURRENT_PG_STATUS__UVD_PG_STATUS_MASK 0x00000004 #endif /* SMU_7_1_2_SH_MASK_H */ diff --git a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_d.h b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_d.h index eca2b851f25f..0333d880bc9e 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_d.h +++ b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_d.h @@ -1244,5 +1244,5 @@ #define ixGC_CAC_ACC_CU14 0xc8 #define ixGC_CAC_ACC_CU15 0xc9 #define ixGC_CAC_OVRD_CU 0xe7 - +#define ixCURRENT_PG_STATUS 0xc020029c #endif /* SMU_7_1_3_D_H */ diff --git a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_sh_mask.h index 1ede9e274714..654c1093d362 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_sh_mask.h @@ -6076,5 +6076,8 @@ #define GC_CAC_OVRD_CU__OVRRD_SELECT__SHIFT 0x0 #define GC_CAC_OVRD_CU__OVRRD_VALUE_MASK 0xffff0000 #define GC_CAC_OVRD_CU__OVRRD_VALUE__SHIFT 0x10 +#define CURRENT_PG_STATUS__VCE_PG_STATUS_MASK 0x00000002 +#define CURRENT_PG_STATUS__UVD_PG_STATUS_MASK 0x00000004 + #endif /* SMU_7_1_3_SH_MASK_H */ diff --git a/drivers/gpu/drm/amd/include/cgs_common.h b/drivers/gpu/drm/amd/include/cgs_common.h index 1d26ae768147..17b9d41f3e87 100644 --- a/drivers/gpu/drm/amd/include/cgs_common.h +++ b/drivers/gpu/drm/amd/include/cgs_common.h @@ -171,6 +171,7 @@ struct cgs_firmware_info { uint32_t ucode_start_address; void *kptr; + bool is_kicker; }; struct cgs_mode_info { diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c index 3eccac735db3..b33935fcf428 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c @@ -161,28 +161,25 @@ int cz_dpm_powergate_uvd(struct pp_hwmgr *hwmgr, bool bgate) { struct cz_hwmgr *cz_hwmgr = (struct cz_hwmgr *)(hwmgr->backend); - if (cz_hwmgr->uvd_power_gated == bgate) - return 0; - cz_hwmgr->uvd_power_gated = bgate; if (bgate) { - cgs_set_clockgating_state(hwmgr->device, - AMD_IP_BLOCK_TYPE_UVD, - AMD_CG_STATE_GATE); cgs_set_powergating_state(hwmgr->device, AMD_IP_BLOCK_TYPE_UVD, AMD_PG_STATE_GATE); + cgs_set_clockgating_state(hwmgr->device, + AMD_IP_BLOCK_TYPE_UVD, + AMD_CG_STATE_GATE); cz_dpm_update_uvd_dpm(hwmgr, true); cz_dpm_powerdown_uvd(hwmgr); } else { cz_dpm_powerup_uvd(hwmgr); - cgs_set_powergating_state(hwmgr->device, - AMD_IP_BLOCK_TYPE_UVD, - AMD_CG_STATE_UNGATE); cgs_set_clockgating_state(hwmgr->device, AMD_IP_BLOCK_TYPE_UVD, AMD_PG_STATE_UNGATE); + cgs_set_powergating_state(hwmgr->device, + AMD_IP_BLOCK_TYPE_UVD, + AMD_CG_STATE_UNGATE); cz_dpm_update_uvd_dpm(hwmgr, false); } @@ -193,47 +190,34 @@ int cz_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate) { struct cz_hwmgr *cz_hwmgr = (struct cz_hwmgr *)(hwmgr->backend); - if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, - PHM_PlatformCaps_VCEPowerGating)) { - if (cz_hwmgr->vce_power_gated != bgate) { - if (bgate) { - cgs_set_clockgating_state( - hwmgr->device, - AMD_IP_BLOCK_TYPE_VCE, - AMD_CG_STATE_GATE); - cgs_set_powergating_state( - hwmgr->device, - AMD_IP_BLOCK_TYPE_VCE, - AMD_PG_STATE_GATE); - cz_enable_disable_vce_dpm(hwmgr, false); - cz_dpm_powerdown_vce(hwmgr); - cz_hwmgr->vce_power_gated = true; - } else { - cz_dpm_powerup_vce(hwmgr); - cz_hwmgr->vce_power_gated = false; - cgs_set_powergating_state( - hwmgr->device, - AMD_IP_BLOCK_TYPE_VCE, - AMD_CG_STATE_UNGATE); - cgs_set_clockgating_state( - hwmgr->device, - AMD_IP_BLOCK_TYPE_VCE, - AMD_PG_STATE_UNGATE); - cz_dpm_update_vce_dpm(hwmgr); - cz_enable_disable_vce_dpm(hwmgr, true); - return 0; - } - } + if (bgate) { + cgs_set_powergating_state( + hwmgr->device, + AMD_IP_BLOCK_TYPE_VCE, + AMD_PG_STATE_GATE); + cgs_set_clockgating_state( + hwmgr->device, + AMD_IP_BLOCK_TYPE_VCE, + AMD_CG_STATE_GATE); + cz_enable_disable_vce_dpm(hwmgr, false); + cz_dpm_powerdown_vce(hwmgr); + cz_hwmgr->vce_power_gated = true; } else { - cz_hwmgr->vce_power_gated = bgate; + cz_dpm_powerup_vce(hwmgr); + cz_hwmgr->vce_power_gated = false; + cgs_set_clockgating_state( + hwmgr->device, + AMD_IP_BLOCK_TYPE_VCE, + AMD_PG_STATE_UNGATE); + cgs_set_powergating_state( + hwmgr->device, + AMD_IP_BLOCK_TYPE_VCE, + AMD_CG_STATE_UNGATE); cz_dpm_update_vce_dpm(hwmgr); - cz_enable_disable_vce_dpm(hwmgr, !bgate); + cz_enable_disable_vce_dpm(hwmgr, true); return 0; } - if (!cz_hwmgr->vce_power_gated) - cz_dpm_update_vce_dpm(hwmgr); - return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c index 4b0a94cc995e..953e0c9ad7cd 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c @@ -1396,3 +1396,25 @@ int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, return 0; } + +int atomctrl_get_svi2_info(struct pp_hwmgr *hwmgr, uint8_t voltage_type, + uint8_t *svd_gpio_id, uint8_t *svc_gpio_id, + uint16_t *load_line) +{ + ATOM_VOLTAGE_OBJECT_INFO_V3_1 *voltage_info = + (ATOM_VOLTAGE_OBJECT_INFO_V3_1 *)get_voltage_info_table(hwmgr->device); + + const ATOM_VOLTAGE_OBJECT_V3 *voltage_object; + + PP_ASSERT_WITH_CODE((NULL != voltage_info), + "Could not find Voltage Table in BIOS.", return -EINVAL); + + voltage_object = atomctrl_lookup_voltage_type_v3 + (voltage_info, voltage_type, VOLTAGE_OBJ_SVID2); + + *svd_gpio_id = voltage_object->asSVID2Obj.ucSVDGpioId; + *svc_gpio_id = voltage_object->asSVID2Obj.ucSVCGpioId; + *load_line = voltage_object->asSVID2Obj.usLoadLine_PSI; + + return 0; +} diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h index fc898afce002..e9fe2e84006b 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.h @@ -311,5 +311,8 @@ extern int atomctrl_get_smc_sclk_range_table(struct pp_hwmgr *hwmgr, struct pp_a extern int atomctrl_get_avfs_information(struct pp_hwmgr *hwmgr, struct pp_atom_ctrl__avfs_parameters *param); +extern int atomctrl_get_svi2_info(struct pp_hwmgr *hwmgr, uint8_t voltage_type, + uint8_t *svd_gpio_id, uint8_t *svc_gpio_id, + uint16_t *load_line); #endif diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c index a1fc4fcac1e0..8cf71f3c6d0e 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c @@ -147,22 +147,22 @@ int smu7_powergate_uvd(struct pp_hwmgr *hwmgr, bool bgate) data->uvd_power_gated = bgate; if (bgate) { - cgs_set_clockgating_state(hwmgr->device, - AMD_IP_BLOCK_TYPE_UVD, - AMD_CG_STATE_GATE); cgs_set_powergating_state(hwmgr->device, AMD_IP_BLOCK_TYPE_UVD, AMD_PG_STATE_GATE); + cgs_set_clockgating_state(hwmgr->device, + AMD_IP_BLOCK_TYPE_UVD, + AMD_CG_STATE_GATE); smu7_update_uvd_dpm(hwmgr, true); smu7_powerdown_uvd(hwmgr); } else { smu7_powerup_uvd(hwmgr); - cgs_set_powergating_state(hwmgr->device, - AMD_IP_BLOCK_TYPE_UVD, - AMD_CG_STATE_UNGATE); cgs_set_clockgating_state(hwmgr->device, AMD_IP_BLOCK_TYPE_UVD, AMD_CG_STATE_UNGATE); + cgs_set_powergating_state(hwmgr->device, + AMD_IP_BLOCK_TYPE_UVD, + AMD_CG_STATE_UNGATE); smu7_update_uvd_dpm(hwmgr, false); } @@ -173,12 +173,12 @@ int smu7_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate) { struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend); - if (data->vce_power_gated == bgate) - return 0; - data->vce_power_gated = bgate; if (bgate) { + cgs_set_powergating_state(hwmgr->device, + AMD_IP_BLOCK_TYPE_VCE, + AMD_PG_STATE_UNGATE); cgs_set_clockgating_state(hwmgr->device, AMD_IP_BLOCK_TYPE_VCE, AMD_CG_STATE_GATE); @@ -186,10 +186,13 @@ int smu7_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate) smu7_powerdown_vce(hwmgr); } else { smu7_powerup_vce(hwmgr); - smu7_update_vce_dpm(hwmgr, false); cgs_set_clockgating_state(hwmgr->device, AMD_IP_BLOCK_TYPE_VCE, AMD_CG_STATE_UNGATE); + cgs_set_powergating_state(hwmgr->device, + AMD_IP_BLOCK_TYPE_VCE, + AMD_PG_STATE_UNGATE); + smu7_update_vce_dpm(hwmgr, false); } return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 0a6c833720df..f75ee33ec5bb 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -1383,6 +1383,15 @@ static void smu7_init_dpm_defaults(struct pp_hwmgr *hwmgr) data->force_pcie_gen = PP_PCIEGenInvalid; data->ulv_supported = hwmgr->feature_mask & PP_ULV_MASK ? true : false; + if (hwmgr->chip_id == CHIP_POLARIS12 || hwmgr->smumgr->is_kicker) { + uint8_t tmp1, tmp2; + uint16_t tmp3 = 0; + atomctrl_get_svi2_info(hwmgr, VOLTAGE_TYPE_VDDC, &tmp1, &tmp2, + &tmp3); + tmp3 = (tmp3 >> 5) & 0x3; + data->vddc_phase_shed_control = ((tmp3 << 1) | (tmp3 >> 1)) & 0x3; + } + data->fast_watermark_threshold = 100; if (atomctrl_is_voltage_controled_by_gpio_v3(hwmgr, VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2)) @@ -2624,6 +2633,7 @@ static int smu7_force_dpm_level(struct pp_hwmgr *hwmgr, smu7_force_clock_level(hwmgr, PP_SCLK, 1<<sclk_mask); smu7_force_clock_level(hwmgr, PP_MCLK, 1<<mclk_mask); smu7_force_clock_level(hwmgr, PP_PCIE, 1<<pcie_mask); + break; case AMD_DPM_FORCED_LEVEL_MANUAL: hwmgr->dpm_level = level; @@ -2633,9 +2643,9 @@ static int smu7_force_dpm_level(struct pp_hwmgr *hwmgr, break; } - if (level & (AMD_DPM_FORCED_LEVEL_PROFILE_PEAK | AMD_DPM_FORCED_LEVEL_HIGH)) + if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK && hwmgr->saved_dpm_level != AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) smu7_fan_ctrl_set_fan_speed_percent(hwmgr, 100); - else + else if (level != AMD_DPM_FORCED_LEVEL_PROFILE_PEAK && hwmgr->saved_dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) smu7_fan_ctrl_reset_fan_speed_to_default(hwmgr); return 0; @@ -4397,16 +4407,14 @@ static int smu7_get_sclks(struct pp_hwmgr *hwmgr, struct amd_pp_clocks *clocks) if (table_info == NULL || table_info->vdd_dep_on_sclk == NULL) return -EINVAL; dep_sclk_table = table_info->vdd_dep_on_sclk; - for (i = 0; i < dep_sclk_table->count; i++) { + for (i = 0; i < dep_sclk_table->count; i++) clocks->clock[i] = dep_sclk_table->entries[i].clk; - clocks->count++; - } + clocks->count = dep_sclk_table->count; } else if (hwmgr->pp_table_version == PP_TABLE_V0) { sclk_table = hwmgr->dyn_state.vddc_dependency_on_sclk; - for (i = 0; i < sclk_table->count; i++) { + for (i = 0; i < sclk_table->count; i++) clocks->clock[i] = sclk_table->entries[i].clk; - clocks->count++; - } + clocks->count = sclk_table->count; } return 0; @@ -4440,14 +4448,13 @@ static int smu7_get_mclks(struct pp_hwmgr *hwmgr, struct amd_pp_clocks *clocks) clocks->clock[i] = dep_mclk_table->entries[i].clk; clocks->latency[i] = smu7_get_mem_latency(hwmgr, dep_mclk_table->entries[i].clk); - clocks->count++; } + clocks->count = dep_mclk_table->count; } else if (hwmgr->pp_table_version == PP_TABLE_V0) { mclk_table = hwmgr->dyn_state.vddc_dependency_on_mclk; - for (i = 0; i < mclk_table->count; i++) { + for (i = 0; i < mclk_table->count; i++) clocks->clock[i] = mclk_table->entries[i].clk; - clocks->count++; - } + clocks->count = mclk_table->count; } return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h index 27e7f76ad8a6..f221e17b67e7 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h @@ -268,7 +268,7 @@ struct smu7_hwmgr { uint32_t fast_watermark_threshold; /* ---- Phase Shedding ---- */ - bool vddc_phase_shed_control; + uint8_t vddc_phase_shed_control; /* ---- DI/DT ---- */ struct smu7_display_timing display_timing; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c index 3341c0fbd069..1dc31aa72781 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c @@ -477,6 +477,151 @@ static const struct gpu_pt_config_reg DIDTConfig_Polaris12[] = { { 0xFFFFFFFF } }; +static const struct gpu_pt_config_reg DIDTConfig_Polaris11_Kicker[] = +{ +/* --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- + * Offset Mask Shift Value Type + * --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- + */ + /* DIDT_SQ */ + { ixDIDT_SQ_WEIGHT0_3, DIDT_SQ_WEIGHT0_3__WEIGHT0_MASK, DIDT_SQ_WEIGHT0_3__WEIGHT0__SHIFT, 0x004c, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT0_3, DIDT_SQ_WEIGHT0_3__WEIGHT1_MASK, DIDT_SQ_WEIGHT0_3__WEIGHT1__SHIFT, 0x00d0, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT0_3, DIDT_SQ_WEIGHT0_3__WEIGHT2_MASK, DIDT_SQ_WEIGHT0_3__WEIGHT2__SHIFT, 0x0069, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT0_3, DIDT_SQ_WEIGHT0_3__WEIGHT3_MASK, DIDT_SQ_WEIGHT0_3__WEIGHT3__SHIFT, 0x0048, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_WEIGHT4_7, DIDT_SQ_WEIGHT4_7__WEIGHT4_MASK, DIDT_SQ_WEIGHT4_7__WEIGHT4__SHIFT, 0x005f, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT4_7, DIDT_SQ_WEIGHT4_7__WEIGHT5_MASK, DIDT_SQ_WEIGHT4_7__WEIGHT5__SHIFT, 0x007a, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT4_7, DIDT_SQ_WEIGHT4_7__WEIGHT6_MASK, DIDT_SQ_WEIGHT4_7__WEIGHT6__SHIFT, 0x001f, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT4_7, DIDT_SQ_WEIGHT4_7__WEIGHT7_MASK, DIDT_SQ_WEIGHT4_7__WEIGHT7__SHIFT, 0x002d, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_WEIGHT8_11, DIDT_SQ_WEIGHT8_11__WEIGHT8_MASK, DIDT_SQ_WEIGHT8_11__WEIGHT8__SHIFT, 0x0088, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT8_11, DIDT_SQ_WEIGHT8_11__WEIGHT9_MASK, DIDT_SQ_WEIGHT8_11__WEIGHT9__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT8_11, DIDT_SQ_WEIGHT8_11__WEIGHT10_MASK, DIDT_SQ_WEIGHT8_11__WEIGHT10__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_WEIGHT8_11, DIDT_SQ_WEIGHT8_11__WEIGHT11_MASK, DIDT_SQ_WEIGHT8_11__WEIGHT11__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_CTRL1, DIDT_SQ_CTRL1__MIN_POWER_MASK, DIDT_SQ_CTRL1__MIN_POWER__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL1, DIDT_SQ_CTRL1__MAX_POWER_MASK, DIDT_SQ_CTRL1__MAX_POWER__SHIFT, 0xffff, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_CTRL_OCP, DIDT_SQ_CTRL_OCP__UNUSED_0_MASK, DIDT_SQ_CTRL_OCP__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL_OCP, DIDT_SQ_CTRL_OCP__OCP_MAX_POWER_MASK, DIDT_SQ_CTRL_OCP__OCP_MAX_POWER__SHIFT, 0x00ff, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__MAX_POWER_DELTA_MASK, DIDT_SQ_CTRL2__MAX_POWER_DELTA__SHIFT, 0x3fff, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__UNUSED_0_MASK, DIDT_SQ_CTRL2__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK, DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT, 0x000f, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__UNUSED_1_MASK, DIDT_SQ_CTRL2__UNUSED_1__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK, DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL2, DIDT_SQ_CTRL2__UNUSED_2_MASK, DIDT_SQ_CTRL2__UNUSED_2__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK, DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT, 0x0001, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT, 0x0001, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK, DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT, 0x0001, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK, DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x01aa, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_STALL_CTRL, DIDT_SQ_STALL_CTRL__UNUSED_0_MASK, DIDT_SQ_STALL_CTRL__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_TUNING_CTRL, DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK, DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_TUNING_CTRL, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT, 0x0dde, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_TUNING_CTRL, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK, DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT, 0x0dde, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_TUNING_CTRL, DIDT_SQ_TUNING_CTRL__UNUSED_0_MASK, DIDT_SQ_TUNING_CTRL__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_CTRL_EN_MASK, DIDT_SQ_CTRL0__DIDT_CTRL_EN__SHIFT, 0x0001, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__USE_REF_CLOCK_MASK, DIDT_SQ_CTRL0__USE_REF_CLOCK__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__PHASE_OFFSET_MASK, DIDT_SQ_CTRL0__PHASE_OFFSET__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_CTRL_RST_MASK, DIDT_SQ_CTRL0__DIDT_CTRL_RST__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK, DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK, DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT, 0x0008, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK, DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT, 0x0008, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_SQ_CTRL0, DIDT_SQ_CTRL0__UNUSED_0_MASK, DIDT_SQ_CTRL0__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + /* DIDT_TD */ + { ixDIDT_TD_WEIGHT0_3, DIDT_TD_WEIGHT0_3__WEIGHT0_MASK, DIDT_TD_WEIGHT0_3__WEIGHT0__SHIFT, 0x000a, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT0_3, DIDT_TD_WEIGHT0_3__WEIGHT1_MASK, DIDT_TD_WEIGHT0_3__WEIGHT1__SHIFT, 0x0010, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT0_3, DIDT_TD_WEIGHT0_3__WEIGHT2_MASK, DIDT_TD_WEIGHT0_3__WEIGHT2__SHIFT, 0x0017, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT0_3, DIDT_TD_WEIGHT0_3__WEIGHT3_MASK, DIDT_TD_WEIGHT0_3__WEIGHT3__SHIFT, 0x002f, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_WEIGHT4_7, DIDT_TD_WEIGHT4_7__WEIGHT4_MASK, DIDT_TD_WEIGHT4_7__WEIGHT4__SHIFT, 0x0046, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT4_7, DIDT_TD_WEIGHT4_7__WEIGHT5_MASK, DIDT_TD_WEIGHT4_7__WEIGHT5__SHIFT, 0x005d, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT4_7, DIDT_TD_WEIGHT4_7__WEIGHT6_MASK, DIDT_TD_WEIGHT4_7__WEIGHT6__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_WEIGHT4_7, DIDT_TD_WEIGHT4_7__WEIGHT7_MASK, DIDT_TD_WEIGHT4_7__WEIGHT7__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_CTRL1, DIDT_TD_CTRL1__MIN_POWER_MASK, DIDT_TD_CTRL1__MIN_POWER__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL1, DIDT_TD_CTRL1__MAX_POWER_MASK, DIDT_TD_CTRL1__MAX_POWER__SHIFT, 0xffff, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_CTRL_OCP, DIDT_TD_CTRL_OCP__UNUSED_0_MASK, DIDT_TD_CTRL_OCP__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL_OCP, DIDT_TD_CTRL_OCP__OCP_MAX_POWER_MASK, DIDT_TD_CTRL_OCP__OCP_MAX_POWER__SHIFT, 0x00ff, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__MAX_POWER_DELTA_MASK, DIDT_TD_CTRL2__MAX_POWER_DELTA__SHIFT, 0x3fff, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__UNUSED_0_MASK, DIDT_TD_CTRL2__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK, DIDT_TD_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT, 0x000f, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__UNUSED_1_MASK, DIDT_TD_CTRL2__UNUSED_1__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK, DIDT_TD_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL2, DIDT_TD_CTRL2__UNUSED_2_MASK, DIDT_TD_CTRL2__UNUSED_2__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK, DIDT_TD_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT, 0x0001, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT, 0x0001, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK, DIDT_TD_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT, 0x0001, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK, DIDT_TD_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x01aa, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_STALL_CTRL, DIDT_TD_STALL_CTRL__UNUSED_0_MASK, DIDT_TD_STALL_CTRL__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_TUNING_CTRL, DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK, DIDT_TD_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_TUNING_CTRL, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT, 0x0dde, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_TUNING_CTRL, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK, DIDT_TD_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT, 0x0dde, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_TUNING_CTRL, DIDT_TD_TUNING_CTRL__UNUSED_0_MASK, DIDT_TD_TUNING_CTRL__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_CTRL_EN_MASK, DIDT_TD_CTRL0__DIDT_CTRL_EN__SHIFT, 0x0001, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__USE_REF_CLOCK_MASK, DIDT_TD_CTRL0__USE_REF_CLOCK__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__PHASE_OFFSET_MASK, DIDT_TD_CTRL0__PHASE_OFFSET__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_CTRL_RST_MASK, DIDT_TD_CTRL0__DIDT_CTRL_RST__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK, DIDT_TD_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK, DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT, 0x0008, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK, DIDT_TD_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT, 0x0008, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TD_CTRL0, DIDT_TD_CTRL0__UNUSED_0_MASK, DIDT_TD_CTRL0__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + /* DIDT_TCP */ + { ixDIDT_TCP_WEIGHT0_3, DIDT_TCP_WEIGHT0_3__WEIGHT0_MASK, DIDT_TCP_WEIGHT0_3__WEIGHT0__SHIFT, 0x0004, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT0_3, DIDT_TCP_WEIGHT0_3__WEIGHT1_MASK, DIDT_TCP_WEIGHT0_3__WEIGHT1__SHIFT, 0x0037, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT0_3, DIDT_TCP_WEIGHT0_3__WEIGHT2_MASK, DIDT_TCP_WEIGHT0_3__WEIGHT2__SHIFT, 0x0001, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT0_3, DIDT_TCP_WEIGHT0_3__WEIGHT3_MASK, DIDT_TCP_WEIGHT0_3__WEIGHT3__SHIFT, 0x00ff, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_WEIGHT4_7, DIDT_TCP_WEIGHT4_7__WEIGHT4_MASK, DIDT_TCP_WEIGHT4_7__WEIGHT4__SHIFT, 0x0054, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT4_7, DIDT_TCP_WEIGHT4_7__WEIGHT5_MASK, DIDT_TCP_WEIGHT4_7__WEIGHT5__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT4_7, DIDT_TCP_WEIGHT4_7__WEIGHT6_MASK, DIDT_TCP_WEIGHT4_7__WEIGHT6__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_WEIGHT4_7, DIDT_TCP_WEIGHT4_7__WEIGHT7_MASK, DIDT_TCP_WEIGHT4_7__WEIGHT7__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_CTRL1, DIDT_TCP_CTRL1__MIN_POWER_MASK, DIDT_TCP_CTRL1__MIN_POWER__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL1, DIDT_TCP_CTRL1__MAX_POWER_MASK, DIDT_TCP_CTRL1__MAX_POWER__SHIFT, 0xffff, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_CTRL_OCP, DIDT_TCP_CTRL_OCP__UNUSED_0_MASK, DIDT_TCP_CTRL_OCP__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL_OCP, DIDT_TCP_CTRL_OCP__OCP_MAX_POWER_MASK, DIDT_TCP_CTRL_OCP__OCP_MAX_POWER__SHIFT, 0xffff, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__MAX_POWER_DELTA_MASK, DIDT_TCP_CTRL2__MAX_POWER_DELTA__SHIFT, 0x3dde, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__UNUSED_0_MASK, DIDT_TCP_CTRL2__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK, DIDT_TCP_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT, 0x0032, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__UNUSED_1_MASK, DIDT_TCP_CTRL2__UNUSED_1__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK, DIDT_TCP_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL2, DIDT_TCP_CTRL2__UNUSED_2_MASK, DIDT_TCP_CTRL2__UNUSED_2__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK, DIDT_TCP_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT, 0x0001, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT, 0x0001, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK, DIDT_TCP_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT, 0x0001, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK, DIDT_TCP_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT,0x01aa, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_STALL_CTRL, DIDT_TCP_STALL_CTRL__UNUSED_0_MASK, DIDT_TCP_STALL_CTRL__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_TUNING_CTRL, DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK, DIDT_TCP_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT, 0x0001, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_TUNING_CTRL, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT, 0x3dde, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_TUNING_CTRL, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK, DIDT_TCP_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT, 0x3dde, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_TUNING_CTRL, DIDT_TCP_TUNING_CTRL__UNUSED_0_MASK, DIDT_TCP_TUNING_CTRL__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_CTRL_EN_MASK, DIDT_TCP_CTRL0__DIDT_CTRL_EN__SHIFT, 0x0001, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__USE_REF_CLOCK_MASK, DIDT_TCP_CTRL0__USE_REF_CLOCK__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__PHASE_OFFSET_MASK, DIDT_TCP_CTRL0__PHASE_OFFSET__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_CTRL_RST_MASK, DIDT_TCP_CTRL0__DIDT_CTRL_RST__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK, DIDT_TCP_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK, DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT, 0x0010, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK, DIDT_TCP_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT, 0x0010, GPU_CONFIGREG_DIDT_IND }, + { ixDIDT_TCP_CTRL0, DIDT_TCP_CTRL0__UNUSED_0_MASK, DIDT_TCP_CTRL0__UNUSED_0__SHIFT, 0x0000, GPU_CONFIGREG_DIDT_IND }, + + { 0xFFFFFFFF } /* End of list */ +}; static int smu7_enable_didt(struct pp_hwmgr *hwmgr, const bool enable) { @@ -630,7 +775,10 @@ int smu7_enable_didt_config(struct pp_hwmgr *hwmgr) } else if (hwmgr->chip_id == CHIP_POLARIS11) { result = smu7_program_pt_config_registers(hwmgr, GCCACConfig_Polaris11); PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result); - result = smu7_program_pt_config_registers(hwmgr, DIDTConfig_Polaris11); + if (hwmgr->smumgr->is_kicker) + result = smu7_program_pt_config_registers(hwmgr, DIDTConfig_Polaris11_Kicker); + else + result = smu7_program_pt_config_registers(hwmgr, DIDTConfig_Polaris11); PP_ASSERT_WITH_CODE((result == 0), "DIDT Config failed.", return result); } else if (hwmgr->chip_id == CHIP_POLARIS12) { result = smu7_program_pt_config_registers(hwmgr, GCCACConfig_Polaris11); diff --git a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h index 9b6531bd6350..7c318a95e0c2 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h +++ b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h @@ -137,6 +137,7 @@ struct pp_smumgr { uint32_t usec_timeout; bool reload_fw; const struct pp_smumgr_func *smumgr_funcs; + bool is_kicker; }; extern int smum_early_init(struct pp_instance *handle); diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c index 0e26900e459e..80e2329a1b9e 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smc.c @@ -494,6 +494,7 @@ static int polaris10_populate_ulv_level(struct pp_hwmgr *hwmgr, struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend); struct phm_ppt_v1_information *table_info = (struct phm_ppt_v1_information *)(hwmgr->pptable); + struct pp_smumgr *smumgr = hwmgr->smumgr; state->CcPwrDynRm = 0; state->CcPwrDynRm1 = 0; @@ -502,7 +503,10 @@ static int polaris10_populate_ulv_level(struct pp_hwmgr *hwmgr, state->VddcOffsetVid = (uint8_t)(table_info->us_ulv_voltage_offset * VOLTAGE_VID_OFFSET_SCALE2 / VOLTAGE_VID_OFFSET_SCALE1); - state->VddcPhase = (data->vddc_phase_shed_control) ? 0 : 1; + if (smumgr->chip_id == CHIP_POLARIS12 || smumgr->is_kicker) + state->VddcPhase = data->vddc_phase_shed_control ^ 0x3; + else + state->VddcPhase = (data->vddc_phase_shed_control) ? 0 : 1; CONVERT_FROM_HOST_TO_SMC_UL(state->CcPwrDynRm); CONVERT_FROM_HOST_TO_SMC_UL(state->CcPwrDynRm1); diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c index 6749fbe26c74..35ac27681415 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c @@ -533,6 +533,8 @@ int smu7_upload_smu_firmware_image(struct pp_smumgr *smumgr) cgs_get_firmware_info(smumgr->device, smu7_convert_fw_type_to_cgs(UCODE_ID_SMU_SK), &info); + smumgr->is_kicker = info.is_kicker; + result = smu7_upload_smc_firmware_data(smumgr, info.image_size, (uint32_t *)info.kptr, SMU7_SMC_SIZE); return result; diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c index 60c36928284c..c0956a4207a9 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c @@ -37,8 +37,10 @@ MODULE_FIRMWARE("amdgpu/tonga_k_smc.bin"); MODULE_FIRMWARE("amdgpu/fiji_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris10_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris10_smc_sk.bin"); +MODULE_FIRMWARE("amdgpu/polaris10_k_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris11_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris11_smc_sk.bin"); +MODULE_FIRMWARE("amdgpu/polaris11_k_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris12_smc.bin"); diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h index 1051181d8c0d..5a8fa1c85229 100644 --- a/drivers/gpu/drm/ast/ast_drv.h +++ b/drivers/gpu/drm/ast/ast_drv.h @@ -114,6 +114,7 @@ struct ast_private { struct ttm_bo_kmap_obj cache_kmap; int next_cursor; bool support_wide_screen; + bool DisableP2A; enum ast_tx_chip tx_chip_type; u8 dp501_maxclk; diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 5992ed2166ec..993909430736 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -124,6 +124,12 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post) } else *need_post = false; + /* Check P2A Access */ + ast->DisableP2A = true; + data = ast_read32(ast, 0xf004); + if (data != 0xFFFFFFFF) + ast->DisableP2A = false; + /* Check if we support wide screen */ switch (ast->chip) { case AST1180: @@ -140,15 +146,17 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post) ast->support_wide_screen = true; else { ast->support_wide_screen = false; - /* Read SCU7c (silicon revision register) */ - ast_write32(ast, 0xf004, 0x1e6e0000); - ast_write32(ast, 0xf000, 0x1); - data = ast_read32(ast, 0x1207c); - data &= 0x300; - if (ast->chip == AST2300 && data == 0x0) /* ast1300 */ - ast->support_wide_screen = true; - if (ast->chip == AST2400 && data == 0x100) /* ast1400 */ - ast->support_wide_screen = true; + if (ast->DisableP2A == false) { + /* Read SCU7c (silicon revision register) */ + ast_write32(ast, 0xf004, 0x1e6e0000); + ast_write32(ast, 0xf000, 0x1); + data = ast_read32(ast, 0x1207c); + data &= 0x300; + if (ast->chip == AST2300 && data == 0x0) /* ast1300 */ + ast->support_wide_screen = true; + if (ast->chip == AST2400 && data == 0x100) /* ast1400 */ + ast->support_wide_screen = true; + } } break; } @@ -216,80 +224,81 @@ static int ast_get_dram_info(struct drm_device *dev) uint32_t data, data2; uint32_t denum, num, div, ref_pll; - ast_write32(ast, 0xf004, 0x1e6e0000); - ast_write32(ast, 0xf000, 0x1); - - - ast_write32(ast, 0x10000, 0xfc600309); - - do { - if (pci_channel_offline(dev->pdev)) - return -EIO; - } while (ast_read32(ast, 0x10000) != 0x01); - data = ast_read32(ast, 0x10004); - - if (data & 0x40) + if (ast->DisableP2A) + { ast->dram_bus_width = 16; + ast->dram_type = AST_DRAM_1Gx16; + ast->mclk = 396; + } else - ast->dram_bus_width = 32; + { + ast_write32(ast, 0xf004, 0x1e6e0000); + ast_write32(ast, 0xf000, 0x1); + data = ast_read32(ast, 0x10004); + + if (data & 0x40) + ast->dram_bus_width = 16; + else + ast->dram_bus_width = 32; + + if (ast->chip == AST2300 || ast->chip == AST2400) { + switch (data & 0x03) { + case 0: + ast->dram_type = AST_DRAM_512Mx16; + break; + default: + case 1: + ast->dram_type = AST_DRAM_1Gx16; + break; + case 2: + ast->dram_type = AST_DRAM_2Gx16; + break; + case 3: + ast->dram_type = AST_DRAM_4Gx16; + break; + } + } else { + switch (data & 0x0c) { + case 0: + case 4: + ast->dram_type = AST_DRAM_512Mx16; + break; + case 8: + if (data & 0x40) + ast->dram_type = AST_DRAM_1Gx16; + else + ast->dram_type = AST_DRAM_512Mx32; + break; + case 0xc: + ast->dram_type = AST_DRAM_1Gx32; + break; + } + } - if (ast->chip == AST2300 || ast->chip == AST2400) { - switch (data & 0x03) { - case 0: - ast->dram_type = AST_DRAM_512Mx16; - break; - default: - case 1: - ast->dram_type = AST_DRAM_1Gx16; - break; - case 2: - ast->dram_type = AST_DRAM_2Gx16; - break; + data = ast_read32(ast, 0x10120); + data2 = ast_read32(ast, 0x10170); + if (data2 & 0x2000) + ref_pll = 14318; + else + ref_pll = 12000; + + denum = data & 0x1f; + num = (data & 0x3fe0) >> 5; + data = (data & 0xc000) >> 14; + switch (data) { case 3: - ast->dram_type = AST_DRAM_4Gx16; - break; - } - } else { - switch (data & 0x0c) { - case 0: - case 4: - ast->dram_type = AST_DRAM_512Mx16; + div = 0x4; break; - case 8: - if (data & 0x40) - ast->dram_type = AST_DRAM_1Gx16; - else - ast->dram_type = AST_DRAM_512Mx32; + case 2: + case 1: + div = 0x2; break; - case 0xc: - ast->dram_type = AST_DRAM_1Gx32; + default: + div = 0x1; break; } + ast->mclk = ref_pll * (num + 2) / (denum + 2) * (div * 1000); } - - data = ast_read32(ast, 0x10120); - data2 = ast_read32(ast, 0x10170); - if (data2 & 0x2000) - ref_pll = 14318; - else - ref_pll = 12000; - - denum = data & 0x1f; - num = (data & 0x3fe0) >> 5; - data = (data & 0xc000) >> 14; - switch (data) { - case 3: - div = 0x4; - break; - case 2: - case 1: - div = 0x2; - break; - default: - div = 0x1; - break; - } - ast->mclk = ref_pll * (num + 2) / (denum + 2) * (div * 1000); return 0; } diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c index 810c51d92b99..5331ee1df086 100644 --- a/drivers/gpu/drm/ast/ast_post.c +++ b/drivers/gpu/drm/ast/ast_post.c @@ -379,12 +379,20 @@ void ast_post_gpu(struct drm_device *dev) ast_open_key(ast); ast_set_def_ext_reg(dev); - if (ast->chip == AST2300 || ast->chip == AST2400) - ast_init_dram_2300(dev); - else - ast_init_dram_reg(dev); + if (ast->DisableP2A == false) + { + if (ast->chip == AST2300 || ast->chip == AST2400) + ast_init_dram_2300(dev); + else + ast_init_dram_reg(dev); - ast_init_3rdtx(dev); + ast_init_3rdtx(dev); + } + else + { + if (ast->tx_chip_type != AST_TX_NONE) + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xcf, 0x80); /* Enable DVO */ + } } /* AST 2300 DRAM settings */ diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 5a0c7082c8f8..afec53832145 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -288,15 +288,15 @@ drm_atomic_get_crtc_state(struct drm_atomic_state *state, EXPORT_SYMBOL(drm_atomic_get_crtc_state); static void set_out_fence_for_crtc(struct drm_atomic_state *state, - struct drm_crtc *crtc, s64 __user *fence_ptr) + struct drm_crtc *crtc, s32 __user *fence_ptr) { state->crtcs[drm_crtc_index(crtc)].out_fence_ptr = fence_ptr; } -static s64 __user *get_out_fence_for_crtc(struct drm_atomic_state *state, +static s32 __user *get_out_fence_for_crtc(struct drm_atomic_state *state, struct drm_crtc *crtc) { - s64 __user *fence_ptr; + s32 __user *fence_ptr; fence_ptr = state->crtcs[drm_crtc_index(crtc)].out_fence_ptr; state->crtcs[drm_crtc_index(crtc)].out_fence_ptr = NULL; @@ -507,7 +507,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc, state->color_mgmt_changed |= replaced; return ret; } else if (property == config->prop_out_fence_ptr) { - s64 __user *fence_ptr = u64_to_user_ptr(val); + s32 __user *fence_ptr = u64_to_user_ptr(val); if (!fence_ptr) return 0; @@ -1914,7 +1914,7 @@ EXPORT_SYMBOL(drm_atomic_clean_old_fb); */ struct drm_out_fence_state { - s64 __user *out_fence_ptr; + s32 __user *out_fence_ptr; struct sync_file *sync_file; int fd; }; @@ -1951,7 +1951,7 @@ static int prepare_crtc_signaling(struct drm_device *dev, return 0; for_each_new_crtc_in_state(state, crtc, crtc_state, i) { - u64 __user *fence_ptr; + s32 __user *fence_ptr; fence_ptr = get_out_fence_for_crtc(crtc_state->state, crtc); @@ -2031,13 +2031,16 @@ static void complete_crtc_signaling(struct drm_device *dev, } for_each_new_crtc_in_state(state, crtc, crtc_state, i) { + struct drm_pending_vblank_event *event = crtc_state->event; /* - * TEST_ONLY and PAGE_FLIP_EVENT are mutually - * exclusive, if they weren't, this code should be - * called on success for TEST_ONLY too. + * Free the allocated event. drm_atomic_helper_setup_commit + * can allocate an event too, so only free it if it's ours + * to prevent a double free in drm_atomic_state_clear. */ - if (crtc_state->event) - drm_event_cancel_free(dev, &crtc_state->event->base); + if (event && (event->base.fence || event->base.file_priv)) { + drm_event_cancel_free(dev, &event->base); + crtc_state->event = NULL; + } } if (!fence_state) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 5d9830f6a190..9203f3e933f7 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -370,7 +370,7 @@ mode_fixup(struct drm_atomic_state *state) struct drm_connector *connector; struct drm_connector_state *conn_state; int i; - bool ret; + int ret; for_each_crtc_in_state(state, crtc, crtc_state, i) { if (!crtc_state->mode_changed && diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index e4d2c8a49076..45464c8b797d 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -378,6 +378,9 @@ int drm_connector_register(struct drm_connector *connector) { int ret = 0; + if (!connector->dev->registered) + return 0; + mutex_lock(&connector->mutex); if (connector->registered) goto unlock; diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index 45ce224688ce..b5c6bb46a425 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -776,6 +776,8 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags) if (ret) goto err_minors; + dev->registered = true; + if (dev->driver->load) { ret = dev->driver->load(dev, flags); if (ret) @@ -823,6 +825,8 @@ void drm_dev_unregister(struct drm_device *dev) drm_lastclose(dev); + dev->registered = false; + if (drm_core_check_feature(dev, DRIVER_MODESET)) drm_modeset_unregister_all(dev); diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index c91240598471..0dd5da8c55e5 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -858,6 +858,9 @@ void drm_fb_helper_fini(struct drm_fb_helper *fb_helper) } fb_helper->fbdev = NULL; + cancel_work_sync(&fb_helper->resume_work); + cancel_work_sync(&fb_helper->dirty_work); + mutex_lock(&kernel_fb_helper_lock); if (!list_empty(&fb_helper->kernel_fb_list)) { list_del(&fb_helper->kernel_fb_list); diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c index 3dfe3c886502..308d442a531b 100644 --- a/drivers/gpu/drm/drm_panel.c +++ b/drivers/gpu/drm/drm_panel.c @@ -137,7 +137,7 @@ EXPORT_SYMBOL(drm_panel_detach); * Return: A pointer to the panel registered for the specified device tree * node or NULL if no panel matching the device tree node can be found. */ -struct drm_panel *of_drm_find_panel(struct device_node *np) +struct drm_panel *of_drm_find_panel(const struct device_node *np) { struct drm_panel *panel; diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index d69af00bdd6a..0fd6f7a18364 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -13,9 +13,11 @@ #include <linux/platform_device.h> #include <linux/clk.h> #include <linux/component.h> +#include <linux/mfd/syscon.h> #include <linux/of_device.h> #include <linux/of_gpio.h> #include <linux/pm_runtime.h> +#include <linux/regmap.h> #include <video/exynos5433_decon.h> @@ -25,6 +27,9 @@ #include "exynos_drm_plane.h" #include "exynos_drm_iommu.h" +#define DSD_CFG_MUX 0x1004 +#define DSD_CFG_MUX_TE_UNMASK_GLOBAL BIT(13) + #define WINDOWS_NR 3 #define MIN_FB_WIDTH_FOR_16WORD_BURST 128 @@ -57,6 +62,7 @@ struct decon_context { struct exynos_drm_plane planes[WINDOWS_NR]; struct exynos_drm_plane_config configs[WINDOWS_NR]; void __iomem *addr; + struct regmap *sysreg; struct clk *clks[ARRAY_SIZE(decon_clks_name)]; int pipe; unsigned long flags; @@ -118,18 +124,29 @@ static void decon_disable_vblank(struct exynos_drm_crtc *crtc) static void decon_setup_trigger(struct decon_context *ctx) { - u32 val = !(ctx->out_type & I80_HW_TRG) - ? TRIGCON_TRIGEN_PER_F | TRIGCON_TRIGEN_F | - TRIGCON_TE_AUTO_MASK | TRIGCON_SWTRIGEN - : TRIGCON_TRIGEN_PER_F | TRIGCON_TRIGEN_F | - TRIGCON_HWTRIGMASK | TRIGCON_HWTRIGEN; - writel(val, ctx->addr + DECON_TRIGCON); + if (!(ctx->out_type & (IFTYPE_I80 | I80_HW_TRG))) + return; + + if (!(ctx->out_type & I80_HW_TRG)) { + writel(TRIGCON_TE_AUTO_MASK | TRIGCON_SWTRIGEN + | TRIGCON_TE_AUTO_MASK | TRIGCON_SWTRIGEN, + ctx->addr + DECON_TRIGCON); + return; + } + + writel(TRIGCON_TRIGEN_PER_F | TRIGCON_TRIGEN_F | TRIGCON_HWTRIGMASK + | TRIGCON_HWTRIGEN, ctx->addr + DECON_TRIGCON); + + if (regmap_update_bits(ctx->sysreg, DSD_CFG_MUX, + DSD_CFG_MUX_TE_UNMASK_GLOBAL, ~0)) + DRM_ERROR("Cannot update sysreg.\n"); } static void decon_commit(struct exynos_drm_crtc *crtc) { struct decon_context *ctx = crtc->ctx; struct drm_display_mode *m = &crtc->base.mode; + bool interlaced = false; u32 val; if (test_bit(BIT_SUSPENDED, &ctx->flags)) @@ -140,13 +157,16 @@ static void decon_commit(struct exynos_drm_crtc *crtc) m->crtc_hsync_end = m->crtc_htotal - 92; m->crtc_vsync_start = m->crtc_vdisplay + 1; m->crtc_vsync_end = m->crtc_vsync_start + 1; + if (m->flags & DRM_MODE_FLAG_INTERLACE) + interlaced = true; } - if (ctx->out_type & (IFTYPE_I80 | I80_HW_TRG)) - decon_setup_trigger(ctx); + decon_setup_trigger(ctx); /* lcd on and use command if */ val = VIDOUT_LCD_ON; + if (interlaced) + val |= VIDOUT_INTERLACE_EN_F; if (ctx->out_type & IFTYPE_I80) { val |= VIDOUT_COMMAND_IF; } else { @@ -155,15 +175,21 @@ static void decon_commit(struct exynos_drm_crtc *crtc) writel(val, ctx->addr + DECON_VIDOUTCON0); - val = VIDTCON2_LINEVAL(m->vdisplay - 1) | - VIDTCON2_HOZVAL(m->hdisplay - 1); + if (interlaced) + val = VIDTCON2_LINEVAL(m->vdisplay / 2 - 1) | + VIDTCON2_HOZVAL(m->hdisplay - 1); + else + val = VIDTCON2_LINEVAL(m->vdisplay - 1) | + VIDTCON2_HOZVAL(m->hdisplay - 1); writel(val, ctx->addr + DECON_VIDTCON2); if (!(ctx->out_type & IFTYPE_I80)) { - val = VIDTCON00_VBPD_F( - m->crtc_vtotal - m->crtc_vsync_end - 1) | - VIDTCON00_VFPD_F( - m->crtc_vsync_start - m->crtc_vdisplay - 1); + int vbp = m->crtc_vtotal - m->crtc_vsync_end; + int vfp = m->crtc_vsync_start - m->crtc_vdisplay; + + if (interlaced) + vbp = vbp / 2 - 1; + val = VIDTCON00_VBPD_F(vbp - 1) | VIDTCON00_VFPD_F(vfp - 1); writel(val, ctx->addr + DECON_VIDTCON00); val = VIDTCON01_VSPW_F( @@ -278,12 +304,22 @@ static void decon_update_plane(struct exynos_drm_crtc *crtc, if (test_bit(BIT_SUSPENDED, &ctx->flags)) return; - val = COORDINATE_X(state->crtc.x) | COORDINATE_Y(state->crtc.y); - writel(val, ctx->addr + DECON_VIDOSDxA(win)); + if (crtc->base.mode.flags & DRM_MODE_FLAG_INTERLACE) { + val = COORDINATE_X(state->crtc.x) | + COORDINATE_Y(state->crtc.y / 2); + writel(val, ctx->addr + DECON_VIDOSDxA(win)); + + val = COORDINATE_X(state->crtc.x + state->crtc.w - 1) | + COORDINATE_Y((state->crtc.y + state->crtc.h) / 2 - 1); + writel(val, ctx->addr + DECON_VIDOSDxB(win)); + } else { + val = COORDINATE_X(state->crtc.x) | COORDINATE_Y(state->crtc.y); + writel(val, ctx->addr + DECON_VIDOSDxA(win)); - val = COORDINATE_X(state->crtc.x + state->crtc.w - 1) | - COORDINATE_Y(state->crtc.y + state->crtc.h - 1); - writel(val, ctx->addr + DECON_VIDOSDxB(win)); + val = COORDINATE_X(state->crtc.x + state->crtc.w - 1) | + COORDINATE_Y(state->crtc.y + state->crtc.h - 1); + writel(val, ctx->addr + DECON_VIDOSDxB(win)); + } val = VIDOSD_Wx_ALPHA_R_F(0x0) | VIDOSD_Wx_ALPHA_G_F(0x0) | VIDOSD_Wx_ALPHA_B_F(0x0); @@ -355,8 +391,6 @@ static void decon_swreset(struct decon_context *ctx) udelay(10); } - WARN(tries == 0, "failed to disable DECON\n"); - writel(VIDCON0_SWRESET, ctx->addr + DECON_VIDCON0); for (tries = 2000; tries; --tries) { if (~readl(ctx->addr + DECON_VIDCON0) & VIDCON0_SWRESET) @@ -557,6 +591,13 @@ static irqreturn_t decon_irq_handler(int irq, void *dev_id) if (val) { writel(val, ctx->addr + DECON_VIDINTCON1); + if (ctx->out_type & IFTYPE_HDMI) { + val = readl(ctx->addr + DECON_VIDOUTCON0); + val &= VIDOUT_INTERLACE_EN_F | VIDOUT_INTERLACE_FIELD_F; + if (val == + (VIDOUT_INTERLACE_EN_F | VIDOUT_INTERLACE_FIELD_F)) + return IRQ_HANDLED; + } drm_crtc_handle_vblank(&ctx->crtc->base); } @@ -637,6 +678,15 @@ static int exynos5433_decon_probe(struct platform_device *pdev) ctx->out_type |= IFTYPE_I80; } + if (ctx->out_type | I80_HW_TRG) { + ctx->sysreg = syscon_regmap_lookup_by_phandle(dev->of_node, + "samsung,disp-sysreg"); + if (IS_ERR(ctx->sysreg)) { + dev_err(dev, "failed to get system register\n"); + return PTR_ERR(ctx->sysreg); + } + } + for (i = 0; i < ARRAY_SIZE(decon_clks_name); i++) { struct clk *clk; diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index 745cfbdf6b39..a9fa444c6053 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -125,10 +125,8 @@ static struct fimd_driver_data exynos3_fimd_driver_data = { .timing_base = 0x20000, .lcdblk_offset = 0x210, .lcdblk_bypass_shift = 1, - .trg_type = I80_HW_TRG, .has_shadowcon = 1, .has_vidoutcon = 1, - .has_trigger_per_te = 1, }; static struct fimd_driver_data exynos4_fimd_driver_data = { diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index 603d8425cca6..2b8bf2dd6387 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -1683,7 +1683,7 @@ struct platform_driver g2d_driver = { .probe = g2d_probe, .remove = g2d_remove, .driver = { - .name = "s5p-g2d", + .name = "exynos-drm-g2d", .owner = THIS_MODULE, .pm = &g2d_pm_ops, .of_match_table = exynos_g2d_match, diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 752e8a3afc79..0814ed76445c 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -35,6 +35,7 @@ #include <linux/io.h> #include <linux/of_address.h> #include <linux/of_device.h> +#include <linux/of_graph.h> #include <linux/hdmi.h> #include <linux/component.h> #include <linux/mfd/syscon.h> @@ -132,6 +133,7 @@ struct hdmi_context { struct regulator_bulk_data regul_bulk[ARRAY_SIZE(supply)]; struct regulator *reg_hdmi_en; struct exynos_drm_clk phy_clk; + struct drm_bridge *bridge; }; static inline struct hdmi_context *encoder_to_hdmi(struct drm_encoder *e) @@ -508,9 +510,9 @@ static const struct hdmiphy_config hdmiphy_5433_configs[] = { { .pixel_clock = 27000000, .conf = { - 0x01, 0x51, 0x22, 0x51, 0x08, 0xfc, 0x88, 0x46, - 0x72, 0x50, 0x24, 0x0c, 0x24, 0x0f, 0x7c, 0xa5, - 0xd4, 0x2b, 0x87, 0x00, 0x00, 0x04, 0x00, 0x30, + 0x01, 0x51, 0x2d, 0x75, 0x01, 0x00, 0x88, 0x02, + 0x72, 0x50, 0x44, 0x8c, 0x27, 0x00, 0x7c, 0xac, + 0xd6, 0x2b, 0x67, 0x00, 0x00, 0x04, 0x00, 0x30, 0x08, 0x10, 0x01, 0x01, 0x48, 0x40, 0x00, 0x40, }, }, @@ -518,9 +520,9 @@ static const struct hdmiphy_config hdmiphy_5433_configs[] = { .pixel_clock = 27027000, .conf = { 0x01, 0x51, 0x2d, 0x72, 0x64, 0x09, 0x88, 0xc3, - 0x71, 0x50, 0x24, 0x14, 0x24, 0x0f, 0x7c, 0xa5, - 0xd4, 0x2b, 0x87, 0x00, 0x00, 0x04, 0x00, 0x30, - 0x28, 0x10, 0x01, 0x01, 0x48, 0x40, 0x00, 0x40, + 0x71, 0x50, 0x44, 0x8c, 0x27, 0x00, 0x7c, 0xac, + 0xd6, 0x2b, 0x67, 0x00, 0x00, 0x04, 0x00, 0x30, + 0x08, 0x10, 0x01, 0x01, 0x48, 0x40, 0x00, 0x40, }, }, { @@ -586,6 +588,15 @@ static const struct hdmiphy_config hdmiphy_5433_configs[] = { 0x08, 0x10, 0x01, 0x01, 0x48, 0x4a, 0x00, 0x40, }, }, + { + .pixel_clock = 297000000, + .conf = { + 0x01, 0x51, 0x3E, 0x05, 0x40, 0xF0, 0x88, 0xC2, + 0x52, 0x53, 0x44, 0x8C, 0x27, 0x00, 0x7C, 0xAC, + 0xD6, 0x2B, 0x67, 0x00, 0x00, 0x04, 0x00, 0x30, + 0x08, 0x10, 0x01, 0x01, 0x48, 0x40, 0x00, 0x40, + }, + }, }; static const char * const hdmi_clk_gates4[] = { @@ -787,7 +798,8 @@ static void hdmi_reg_infoframes(struct hdmi_context *hdata) sizeof(buf)); if (ret > 0) { hdmi_reg_writeb(hdata, HDMI_VSI_CON, HDMI_VSI_CON_EVERY_VSYNC); - hdmi_reg_write_buf(hdata, HDMI_VSI_HEADER0, buf, ret); + hdmi_reg_write_buf(hdata, HDMI_VSI_HEADER0, buf, 3); + hdmi_reg_write_buf(hdata, HDMI_VSI_DATA(0), buf + 3, ret - 3); } ret = hdmi_audio_infoframe_init(&frm.audio); @@ -911,7 +923,15 @@ static int hdmi_create_connector(struct drm_encoder *encoder) drm_connector_register(connector); drm_mode_connector_attach_encoder(connector, encoder); - return 0; + if (hdata->bridge) { + encoder->bridge = hdata->bridge; + hdata->bridge->encoder = encoder; + ret = drm_bridge_attach(encoder, hdata->bridge, NULL); + if (ret) + DRM_ERROR("Failed to attach bridge\n"); + } + + return ret; } static bool hdmi_mode_fixup(struct drm_encoder *encoder, @@ -1580,6 +1600,31 @@ static void hdmiphy_clk_enable(struct exynos_drm_clk *clk, bool enable) hdmiphy_disable(hdata); } +static int hdmi_bridge_init(struct hdmi_context *hdata) +{ + struct device *dev = hdata->dev; + struct device_node *ep, *np; + + ep = of_graph_get_endpoint_by_regs(dev->of_node, 1, -1); + if (!ep) + return 0; + + np = of_graph_get_remote_port_parent(ep); + of_node_put(ep); + if (!np) { + DRM_ERROR("failed to get remote port parent"); + return -EINVAL; + } + + hdata->bridge = of_drm_find_bridge(np); + of_node_put(np); + + if (!hdata->bridge) + return -EPROBE_DEFER; + + return 0; +} + static int hdmi_resources_init(struct hdmi_context *hdata) { struct device *dev = hdata->dev; @@ -1619,17 +1664,18 @@ static int hdmi_resources_init(struct hdmi_context *hdata) hdata->reg_hdmi_en = devm_regulator_get_optional(dev, "hdmi-en"); - if (PTR_ERR(hdata->reg_hdmi_en) == -ENODEV) - return 0; + if (PTR_ERR(hdata->reg_hdmi_en) != -ENODEV) { + if (IS_ERR(hdata->reg_hdmi_en)) + return PTR_ERR(hdata->reg_hdmi_en); - if (IS_ERR(hdata->reg_hdmi_en)) - return PTR_ERR(hdata->reg_hdmi_en); - - ret = regulator_enable(hdata->reg_hdmi_en); - if (ret) - DRM_ERROR("failed to enable hdmi-en regulator\n"); + ret = regulator_enable(hdata->reg_hdmi_en); + if (ret) { + DRM_ERROR("failed to enable hdmi-en regulator\n"); + return ret; + } + } - return ret; + return hdmi_bridge_init(hdata); } static struct of_device_id hdmi_match_types[] = { diff --git a/drivers/gpu/drm/fsl-dcu/fsl_tcon.c b/drivers/gpu/drm/fsl-dcu/fsl_tcon.c index 3194e544ee27..b3d70a63c5a3 100644 --- a/drivers/gpu/drm/fsl-dcu/fsl_tcon.c +++ b/drivers/gpu/drm/fsl-dcu/fsl_tcon.c @@ -72,10 +72,8 @@ struct fsl_tcon *fsl_tcon_init(struct device *dev) return NULL; tcon = devm_kzalloc(dev, sizeof(*tcon), GFP_KERNEL); - if (!tcon) { - ret = -ENOMEM; + if (!tcon) goto err_node_put; - } ret = fsl_tcon_init_regmap(dev, tcon, np); if (ret) { @@ -89,9 +87,13 @@ struct fsl_tcon *fsl_tcon_init(struct device *dev) goto err_node_put; } - of_node_put(np); - clk_prepare_enable(tcon->ipg_clk); + ret = clk_prepare_enable(tcon->ipg_clk); + if (ret) { + dev_err(dev, "Couldn't enable the TCON clock\n"); + goto err_node_put; + } + of_node_put(np); dev_info(dev, "Using TCON in bypass mode\n"); return tcon; diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c index 7311aeab16f7..3b6caaca9751 100644 --- a/drivers/gpu/drm/i915/gvt/aperture_gm.c +++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c @@ -49,20 +49,21 @@ static int alloc_gm(struct intel_vgpu *vgpu, bool high_gm) if (high_gm) { node = &vgpu->gm.high_gm_node; size = vgpu_hidden_sz(vgpu); - start = gvt_hidden_gmadr_base(gvt); - end = gvt_hidden_gmadr_end(gvt); + start = ALIGN(gvt_hidden_gmadr_base(gvt), I915_GTT_PAGE_SIZE); + end = ALIGN(gvt_hidden_gmadr_end(gvt), I915_GTT_PAGE_SIZE); flags = PIN_HIGH; } else { node = &vgpu->gm.low_gm_node; size = vgpu_aperture_sz(vgpu); - start = gvt_aperture_gmadr_base(gvt); - end = gvt_aperture_gmadr_end(gvt); + start = ALIGN(gvt_aperture_gmadr_base(gvt), I915_GTT_PAGE_SIZE); + end = ALIGN(gvt_aperture_gmadr_end(gvt), I915_GTT_PAGE_SIZE); flags = PIN_MAPPABLE; } mutex_lock(&dev_priv->drm.struct_mutex); ret = i915_gem_gtt_insert(&dev_priv->ggtt.base, node, - size, 4096, I915_COLOR_UNEVICTABLE, + size, I915_GTT_PAGE_SIZE, + I915_COLOR_UNEVICTABLE, start, end, flags); mutex_unlock(&dev_priv->drm.struct_mutex); if (ret) @@ -254,7 +255,7 @@ static int alloc_resource(struct intel_vgpu *vgpu, if (request > avail) goto no_enough_resource; - vgpu_aperture_sz(vgpu) = request; + vgpu_aperture_sz(vgpu) = ALIGN(request, I915_GTT_PAGE_SIZE); item = "high GM space"; max = gvt_hidden_sz(gvt) - HOST_HIGH_GM_SIZE; @@ -265,7 +266,7 @@ static int alloc_resource(struct intel_vgpu *vgpu, if (request > avail) goto no_enough_resource; - vgpu_hidden_sz(vgpu) = request; + vgpu_hidden_sz(vgpu) = ALIGN(request, I915_GTT_PAGE_SIZE); item = "fence"; max = gvt_fence_sz(gvt) - HOST_FENCE; diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index 9a4b23c3ee97..b9c8e2407682 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -481,7 +481,6 @@ struct parser_exec_state { (s->vgpu->gvt->device_info.gmadr_bytes_in_cmd >> 2) static unsigned long bypass_scan_mask = 0; -static bool bypass_batch_buffer_scan = true; /* ring ALL, type = 0 */ static struct sub_op_bits sub_op_mi[] = { @@ -1135,6 +1134,8 @@ static int skl_decode_mi_display_flip(struct parser_exec_state *s, u32 dword2 = cmd_val(s, 2); u32 plane = (dword0 & GENMASK(12, 8)) >> 8; + info->plane = PRIMARY_PLANE; + switch (plane) { case MI_DISPLAY_FLIP_SKL_PLANE_1_A: info->pipe = PIPE_A; @@ -1148,12 +1149,28 @@ static int skl_decode_mi_display_flip(struct parser_exec_state *s, info->pipe = PIPE_C; info->event = PRIMARY_C_FLIP_DONE; break; + + case MI_DISPLAY_FLIP_SKL_PLANE_2_A: + info->pipe = PIPE_A; + info->event = SPRITE_A_FLIP_DONE; + info->plane = SPRITE_PLANE; + break; + case MI_DISPLAY_FLIP_SKL_PLANE_2_B: + info->pipe = PIPE_B; + info->event = SPRITE_B_FLIP_DONE; + info->plane = SPRITE_PLANE; + break; + case MI_DISPLAY_FLIP_SKL_PLANE_2_C: + info->pipe = PIPE_C; + info->event = SPRITE_C_FLIP_DONE; + info->plane = SPRITE_PLANE; + break; + default: gvt_err("unknown plane code %d\n", plane); return -EINVAL; } - info->pipe = PRIMARY_PLANE; info->stride_val = (dword1 & GENMASK(15, 6)) >> 6; info->tile_val = (dword1 & GENMASK(2, 0)); info->surf_val = (dword2 & GENMASK(31, 12)) >> 12; @@ -1525,9 +1542,6 @@ static int batch_buffer_needs_scan(struct parser_exec_state *s) { struct intel_gvt *gvt = s->vgpu->gvt; - if (bypass_batch_buffer_scan) - return 0; - if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)) { /* BDW decides privilege based on address space */ if (cmd_val(s, 0) & (1 << 8)) diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index c0c884aeb30e..6d8fde880c39 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -83,7 +83,7 @@ static int pipe_is_enabled(struct intel_vgpu *vgpu, int pipe) return 0; } -/* EDID with 1024x768 as its resolution */ +/* EDID with 1920x1200 as its resolution */ static unsigned char virtual_dp_monitor_edid[] = { /*Header*/ 0x00, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x00, @@ -97,11 +97,16 @@ static unsigned char virtual_dp_monitor_edid[] = { 0xfc, 0x81, 0xa4, 0x55, 0x4d, 0x9d, 0x25, 0x12, 0x50, 0x54, /* Established Timings: maximum resolution is 1024x768 */ 0x21, 0x08, 0x00, - /* Standard Timings. All invalid */ - 0x00, 0xc0, 0x00, 0xc0, 0x00, 0x40, 0x00, 0x80, 0x00, 0x00, - 0x00, 0x40, 0x00, 0x00, 0x00, 0x01, - /* 18 Byte Data Blocks 1: invalid */ - 0x00, 0x00, 0x80, 0xa0, 0x70, 0xb0, + /* + * Standard Timings. + * below new resolutions can be supported: + * 1920x1080, 1280x720, 1280x960, 1280x1024, + * 1440x900, 1600x1200, 1680x1050 + */ + 0xd1, 0xc0, 0x81, 0xc0, 0x81, 0x40, 0x81, 0x80, 0x95, 0x00, + 0xa9, 0x40, 0xb3, 0x00, 0x01, 0x01, + /* 18 Byte Data Blocks 1: max resolution is 1920x1200 */ + 0x28, 0x3c, 0x80, 0xa0, 0x70, 0xb0, 0x23, 0x40, 0x30, 0x20, 0x36, 0x00, 0x06, 0x44, 0x21, 0x00, 0x00, 0x1a, /* 18 Byte Data Blocks 2: invalid */ 0x00, 0x00, 0x00, 0xfd, 0x00, 0x18, 0x3c, 0x18, 0x50, 0x11, 0x00, 0x0a, @@ -115,7 +120,7 @@ static unsigned char virtual_dp_monitor_edid[] = { /* Extension Block Count */ 0x00, /* Checksum */ - 0xef, + 0x45, }; #define DPCD_HEADER_SIZE 0xb @@ -328,3 +333,15 @@ int intel_vgpu_init_display(struct intel_vgpu *vgpu) else return setup_virtual_dp_monitor(vgpu, PORT_B, GVT_DP_B); } + +/** + * intel_vgpu_reset_display- reset vGPU virtual display emulation + * @vgpu: a vGPU + * + * This function is used to reset vGPU virtual display emulation stuffs + * + */ +void intel_vgpu_reset_display(struct intel_vgpu *vgpu) +{ + emulate_monitor_status_change(vgpu); +} diff --git a/drivers/gpu/drm/i915/gvt/display.h b/drivers/gpu/drm/i915/gvt/display.h index 7a60cb848268..8b234ea961f6 100644 --- a/drivers/gpu/drm/i915/gvt/display.h +++ b/drivers/gpu/drm/i915/gvt/display.h @@ -158,6 +158,7 @@ void intel_gvt_emulate_vblank(struct intel_gvt *gvt); void intel_gvt_check_vblank_emulation(struct intel_gvt *gvt); int intel_vgpu_init_display(struct intel_vgpu *vgpu); +void intel_vgpu_reset_display(struct intel_vgpu *vgpu); void intel_vgpu_clean_display(struct intel_vgpu *vgpu); #endif diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c index f32bb6f6495c..46eb9fd3c03f 100644 --- a/drivers/gpu/drm/i915/gvt/execlist.c +++ b/drivers/gpu/drm/i915/gvt/execlist.c @@ -364,58 +364,30 @@ static void free_workload(struct intel_vgpu_workload *workload) #define get_desc_from_elsp_dwords(ed, i) \ ((struct execlist_ctx_descriptor_format *)&((ed)->data[i * 2])) - -#define BATCH_BUFFER_ADDR_MASK ((1UL << 32) - (1U << 2)) -#define BATCH_BUFFER_ADDR_HIGH_MASK ((1UL << 16) - (1U)) -static int set_gma_to_bb_cmd(struct intel_shadow_bb_entry *entry_obj, - unsigned long add, int gmadr_bytes) -{ - if (WARN_ON(gmadr_bytes != 4 && gmadr_bytes != 8)) - return -1; - - *((u32 *)(entry_obj->bb_start_cmd_va + (1 << 2))) = add & - BATCH_BUFFER_ADDR_MASK; - if (gmadr_bytes == 8) { - *((u32 *)(entry_obj->bb_start_cmd_va + (2 << 2))) = - add & BATCH_BUFFER_ADDR_HIGH_MASK; - } - - return 0; -} - static void prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload) { - int gmadr_bytes = workload->vgpu->gvt->device_info.gmadr_bytes_in_cmd; + const int gmadr_bytes = workload->vgpu->gvt->device_info.gmadr_bytes_in_cmd; + struct intel_shadow_bb_entry *entry_obj; /* pin the gem object to ggtt */ - if (!list_empty(&workload->shadow_bb)) { - struct intel_shadow_bb_entry *entry_obj = - list_first_entry(&workload->shadow_bb, - struct intel_shadow_bb_entry, - list); - struct intel_shadow_bb_entry *temp; + list_for_each_entry(entry_obj, &workload->shadow_bb, list) { + struct i915_vma *vma; - list_for_each_entry_safe(entry_obj, temp, &workload->shadow_bb, - list) { - struct i915_vma *vma; - - vma = i915_gem_object_ggtt_pin(entry_obj->obj, NULL, 0, - 4, 0); - if (IS_ERR(vma)) { - gvt_err("Cannot pin\n"); - return; - } - - /* FIXME: we are not tracking our pinned VMA leaving it - * up to the core to fix up the stray pin_count upon - * free. - */ - - /* update the relocate gma with shadow batch buffer*/ - set_gma_to_bb_cmd(entry_obj, - i915_ggtt_offset(vma), - gmadr_bytes); + vma = i915_gem_object_ggtt_pin(entry_obj->obj, NULL, 0, 4, 0); + if (IS_ERR(vma)) { + gvt_err("Cannot pin\n"); + return; } + + /* FIXME: we are not tracking our pinned VMA leaving it + * up to the core to fix up the stray pin_count upon + * free. + */ + + /* update the relocate gma with shadow batch buffer*/ + entry_obj->bb_start_cmd_va[1] = i915_ggtt_offset(vma); + if (gmadr_bytes == 8) + entry_obj->bb_start_cmd_va[2] = 0; } } @@ -515,7 +487,7 @@ static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload) static void release_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx) { - if (wa_ctx->indirect_ctx.size == 0) + if (!wa_ctx->indirect_ctx.obj) return; i915_gem_object_unpin_map(wa_ctx->indirect_ctx.obj); @@ -826,7 +798,7 @@ int intel_vgpu_init_execlist(struct intel_vgpu *vgpu) INIT_LIST_HEAD(&vgpu->workload_q_head[i]); } - vgpu->workloads = kmem_cache_create("gvt-g vgpu workload", + vgpu->workloads = kmem_cache_create("gvt-g_vgpu_workload", sizeof(struct intel_vgpu_workload), 0, SLAB_HWCACHE_ALIGN, NULL); diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c index 2fae2a2ca96f..1cb29b2d7dc6 100644 --- a/drivers/gpu/drm/i915/gvt/firmware.c +++ b/drivers/gpu/drm/i915/gvt/firmware.c @@ -48,31 +48,6 @@ struct gvt_firmware_header { unsigned char data[1]; }; -#define RD(offset) (readl(mmio + offset.reg)) -#define WR(v, offset) (writel(v, mmio + offset.reg)) - -static void bdw_forcewake_get(void __iomem *mmio) -{ - WR(_MASKED_BIT_DISABLE(0xffff), FORCEWAKE_MT); - - RD(ECOBUS); - - if (wait_for((RD(FORCEWAKE_ACK_HSW) & FORCEWAKE_KERNEL) == 0, 50)) - gvt_err("fail to wait forcewake idle\n"); - - WR(_MASKED_BIT_ENABLE(FORCEWAKE_KERNEL), FORCEWAKE_MT); - - if (wait_for((RD(FORCEWAKE_ACK_HSW) & FORCEWAKE_KERNEL), 50)) - gvt_err("fail to wait forcewake ack\n"); - - if (wait_for((RD(GEN6_GT_THREAD_STATUS_REG) & - GEN6_GT_THREAD_STATUS_CORE_MASK) == 0, 50)) - gvt_err("fail to wait c0 wake up\n"); -} - -#undef RD -#undef WR - #define dev_to_drm_minor(d) dev_get_drvdata((d)) static ssize_t @@ -91,9 +66,9 @@ static struct bin_attribute firmware_attr = { .mmap = NULL, }; -static int expose_firmware_sysfs(struct intel_gvt *gvt, - void __iomem *mmio) +static int expose_firmware_sysfs(struct intel_gvt *gvt) { + struct drm_i915_private *dev_priv = gvt->dev_priv; struct intel_gvt_device_info *info = &gvt->device_info; struct pci_dev *pdev = gvt->dev_priv->drm.pdev; struct intel_gvt_mmio_info *e; @@ -132,7 +107,7 @@ static int expose_firmware_sysfs(struct intel_gvt *gvt, for (j = 0; j < e->length; j += 4) *(u32 *)(p + e->offset + j) = - readl(mmio + e->offset + j); + I915_READ_NOTRACE(_MMIO(e->offset + j)); } memcpy(gvt->firmware.mmio, p, info->mmio_size); @@ -235,7 +210,6 @@ int intel_gvt_load_firmware(struct intel_gvt *gvt) struct gvt_firmware_header *h; const struct firmware *fw; char *path; - void __iomem *mmio; void *mem; int ret; @@ -260,17 +234,6 @@ int intel_gvt_load_firmware(struct intel_gvt *gvt) firmware->mmio = mem; - mmio = pci_iomap(pdev, info->mmio_bar, info->mmio_size); - if (!mmio) { - kfree(path); - kfree(firmware->cfg_space); - kfree(firmware->mmio); - return -EINVAL; - } - - if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)) - bdw_forcewake_get(mmio); - sprintf(path, "%s/vid_0x%04x_did_0x%04x_rid_0x%04x.golden_hw_state", GVT_FIRMWARE_PATH, pdev->vendor, pdev->device, pdev->revision); @@ -300,13 +263,11 @@ int intel_gvt_load_firmware(struct intel_gvt *gvt) release_firmware(fw); firmware->firmware_loaded = true; - pci_iounmap(pdev, mmio); return 0; out_free_fw: release_firmware(fw); expose_firmware: - expose_firmware_sysfs(gvt, mmio); - pci_iounmap(pdev, mmio); + expose_firmware_sysfs(gvt); return 0; } diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 47dec4acf7ff..28c92346db0e 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -606,21 +606,33 @@ struct intel_vgpu_guest_page *intel_vgpu_find_guest_page( static inline int init_shadow_page(struct intel_vgpu *vgpu, struct intel_vgpu_shadow_page *p, int type) { + struct device *kdev = &vgpu->gvt->dev_priv->drm.pdev->dev; + dma_addr_t daddr; + + daddr = dma_map_page(kdev, p->page, 0, 4096, PCI_DMA_BIDIRECTIONAL); + if (dma_mapping_error(kdev, daddr)) { + gvt_err("fail to map dma addr\n"); + return -EINVAL; + } + p->vaddr = page_address(p->page); p->type = type; INIT_HLIST_NODE(&p->node); - p->mfn = intel_gvt_hypervisor_virt_to_mfn(p->vaddr); - if (p->mfn == INTEL_GVT_INVALID_ADDR) - return -EFAULT; - + p->mfn = daddr >> GTT_PAGE_SHIFT; hash_add(vgpu->gtt.shadow_page_hash_table, &p->node, p->mfn); return 0; } -static inline void clean_shadow_page(struct intel_vgpu_shadow_page *p) +static inline void clean_shadow_page(struct intel_vgpu *vgpu, + struct intel_vgpu_shadow_page *p) { + struct device *kdev = &vgpu->gvt->dev_priv->drm.pdev->dev; + + dma_unmap_page(kdev, p->mfn << GTT_PAGE_SHIFT, 4096, + PCI_DMA_BIDIRECTIONAL); + if (!hlist_unhashed(&p->node)) hash_del(&p->node); } @@ -670,7 +682,7 @@ static void ppgtt_free_shadow_page(struct intel_vgpu_ppgtt_spt *spt) { trace_spt_free(spt->vgpu->id, spt, spt->shadow_page.type); - clean_shadow_page(&spt->shadow_page); + clean_shadow_page(spt->vgpu, &spt->shadow_page); intel_vgpu_clean_guest_page(spt->vgpu, &spt->guest_page); list_del_init(&spt->post_shadow_list); @@ -1875,8 +1887,9 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu, int page_entry_num = GTT_PAGE_SIZE >> vgpu->gvt->device_info.gtt_entry_size_shift; void *scratch_pt; - unsigned long mfn; int i; + struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev; + dma_addr_t daddr; if (WARN_ON(type < GTT_TYPE_PPGTT_PTE_PT || type >= GTT_TYPE_MAX)) return -EINVAL; @@ -1887,16 +1900,18 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu, return -ENOMEM; } - mfn = intel_gvt_hypervisor_virt_to_mfn(scratch_pt); - if (mfn == INTEL_GVT_INVALID_ADDR) { - gvt_err("fail to translate vaddr:0x%lx\n", (unsigned long)scratch_pt); - free_page((unsigned long)scratch_pt); - return -EFAULT; + daddr = dma_map_page(dev, virt_to_page(scratch_pt), 0, + 4096, PCI_DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, daddr)) { + gvt_err("fail to dmamap scratch_pt\n"); + __free_page(virt_to_page(scratch_pt)); + return -ENOMEM; } - gtt->scratch_pt[type].page_mfn = mfn; + gtt->scratch_pt[type].page_mfn = + (unsigned long)(daddr >> GTT_PAGE_SHIFT); gtt->scratch_pt[type].page = virt_to_page(scratch_pt); gvt_dbg_mm("vgpu%d create scratch_pt: type %d mfn=0x%lx\n", - vgpu->id, type, mfn); + vgpu->id, type, gtt->scratch_pt[type].page_mfn); /* Build the tree by full filled the scratch pt with the entries which * point to the next level scratch pt or scratch page. The @@ -1930,9 +1945,14 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu, static int release_scratch_page_tree(struct intel_vgpu *vgpu) { int i; + struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev; + dma_addr_t daddr; for (i = GTT_TYPE_PPGTT_PTE_PT; i < GTT_TYPE_MAX; i++) { if (vgpu->gtt.scratch_pt[i].page != NULL) { + daddr = (dma_addr_t)(vgpu->gtt.scratch_pt[i].page_mfn << + GTT_PAGE_SHIFT); + dma_unmap_page(dev, daddr, 4096, PCI_DMA_BIDIRECTIONAL); __free_page(vgpu->gtt.scratch_pt[i].page); vgpu->gtt.scratch_pt[i].page = NULL; vgpu->gtt.scratch_pt[i].page_mfn = 0; @@ -2192,6 +2212,8 @@ int intel_gvt_init_gtt(struct intel_gvt *gvt) { int ret; void *page; + struct device *dev = &gvt->dev_priv->drm.pdev->dev; + dma_addr_t daddr; gvt_dbg_core("init gtt\n"); @@ -2209,14 +2231,16 @@ int intel_gvt_init_gtt(struct intel_gvt *gvt) gvt_err("fail to allocate scratch ggtt page\n"); return -ENOMEM; } - gvt->gtt.scratch_ggtt_page = virt_to_page(page); - gvt->gtt.scratch_ggtt_mfn = intel_gvt_hypervisor_virt_to_mfn(page); - if (gvt->gtt.scratch_ggtt_mfn == INTEL_GVT_INVALID_ADDR) { - gvt_err("fail to translate scratch ggtt page\n"); - __free_page(gvt->gtt.scratch_ggtt_page); - return -EFAULT; + daddr = dma_map_page(dev, virt_to_page(page), 0, + 4096, PCI_DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, daddr)) { + gvt_err("fail to dmamap scratch ggtt page\n"); + __free_page(virt_to_page(page)); + return -ENOMEM; } + gvt->gtt.scratch_ggtt_page = virt_to_page(page); + gvt->gtt.scratch_ggtt_mfn = (unsigned long)(daddr >> GTT_PAGE_SHIFT); if (enable_out_of_sync) { ret = setup_spt_oos(gvt); @@ -2239,6 +2263,12 @@ int intel_gvt_init_gtt(struct intel_gvt *gvt) */ void intel_gvt_clean_gtt(struct intel_gvt *gvt) { + struct device *dev = &gvt->dev_priv->drm.pdev->dev; + dma_addr_t daddr = (dma_addr_t)(gvt->gtt.scratch_ggtt_mfn << + GTT_PAGE_SHIFT); + + dma_unmap_page(dev, daddr, 4096, PCI_DMA_BIDIRECTIONAL); + __free_page(gvt->gtt.scratch_ggtt_page); if (enable_out_of_sync) diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c index e6bf5c533fbe..3b9d59e457ba 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.c +++ b/drivers/gpu/drm/i915/gvt/gvt.c @@ -68,8 +68,6 @@ static const struct intel_gvt_ops intel_gvt_ops = { */ int intel_gvt_init_host(void) { - int ret; - if (intel_gvt_host.initialized) return 0; @@ -96,11 +94,6 @@ int intel_gvt_init_host(void) if (!intel_gvt_host.mpt) return -EINVAL; - /* Try to detect if we're running in host instead of VM. */ - ret = intel_gvt_hypervisor_detect_host(); - if (ret) - return -ENODEV; - gvt_dbg_core("Running with hypervisor %s in host mode\n", supported_hypervisors[intel_gvt_host.hypervisor_type]); diff --git a/drivers/gpu/drm/i915/gvt/hypercall.h b/drivers/gpu/drm/i915/gvt/hypercall.h index 30e543f5a703..df7f33abd393 100644 --- a/drivers/gpu/drm/i915/gvt/hypercall.h +++ b/drivers/gpu/drm/i915/gvt/hypercall.h @@ -38,7 +38,6 @@ * both Xen and KVM by providing dedicated hypervisor-related MPT modules. */ struct intel_gvt_mpt { - int (*detect_host)(void); int (*host_init)(struct device *dev, void *gvt, const void *ops); void (*host_exit)(struct device *dev, void *gvt); int (*attach_vgpu)(void *vgpu, unsigned long *handle); diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c index f7be02ac4be1..92bb247e3478 100644 --- a/drivers/gpu/drm/i915/gvt/interrupt.c +++ b/drivers/gpu/drm/i915/gvt/interrupt.c @@ -176,26 +176,15 @@ int intel_vgpu_reg_imr_handler(struct intel_vgpu *vgpu, { struct intel_gvt *gvt = vgpu->gvt; struct intel_gvt_irq_ops *ops = gvt->irq.ops; - u32 changed, masked, unmasked; u32 imr = *(u32 *)p_data; - gvt_dbg_irq("write IMR %x with val %x\n", - reg, imr); - - gvt_dbg_irq("old vIMR %x\n", vgpu_vreg(vgpu, reg)); - - /* figure out newly masked/unmasked bits */ - changed = vgpu_vreg(vgpu, reg) ^ imr; - masked = (vgpu_vreg(vgpu, reg) & changed) ^ changed; - unmasked = masked ^ changed; - - gvt_dbg_irq("changed %x, masked %x, unmasked %x\n", - changed, masked, unmasked); + gvt_dbg_irq("write IMR %x, new %08x, old %08x, changed %08x\n", + reg, imr, vgpu_vreg(vgpu, reg), vgpu_vreg(vgpu, reg) ^ imr); vgpu_vreg(vgpu, reg) = imr; ops->check_pending_irq(vgpu); - gvt_dbg_irq("IRQ: new vIMR %x\n", vgpu_vreg(vgpu, reg)); + return 0; } @@ -217,14 +206,11 @@ int intel_vgpu_reg_master_irq_handler(struct intel_vgpu *vgpu, { struct intel_gvt *gvt = vgpu->gvt; struct intel_gvt_irq_ops *ops = gvt->irq.ops; - u32 changed, enabled, disabled; u32 ier = *(u32 *)p_data; u32 virtual_ier = vgpu_vreg(vgpu, reg); - gvt_dbg_irq("write master irq reg %x with val %x\n", - reg, ier); - - gvt_dbg_irq("old vreg %x\n", vgpu_vreg(vgpu, reg)); + gvt_dbg_irq("write MASTER_IRQ %x, new %08x, old %08x, changed %08x\n", + reg, ier, virtual_ier, virtual_ier ^ ier); /* * GEN8_MASTER_IRQ is a special irq register, @@ -236,16 +222,8 @@ int intel_vgpu_reg_master_irq_handler(struct intel_vgpu *vgpu, vgpu_vreg(vgpu, reg) &= ~GEN8_MASTER_IRQ_CONTROL; vgpu_vreg(vgpu, reg) |= ier; - /* figure out newly enabled/disable bits */ - changed = virtual_ier ^ ier; - enabled = (virtual_ier & changed) ^ changed; - disabled = enabled ^ changed; - - gvt_dbg_irq("changed %x, enabled %x, disabled %x\n", - changed, enabled, disabled); - ops->check_pending_irq(vgpu); - gvt_dbg_irq("new vreg %x\n", vgpu_vreg(vgpu, reg)); + return 0; } @@ -268,21 +246,11 @@ int intel_vgpu_reg_ier_handler(struct intel_vgpu *vgpu, struct intel_gvt *gvt = vgpu->gvt; struct intel_gvt_irq_ops *ops = gvt->irq.ops; struct intel_gvt_irq_info *info; - u32 changed, enabled, disabled; u32 ier = *(u32 *)p_data; - gvt_dbg_irq("write IER %x with val %x\n", - reg, ier); - - gvt_dbg_irq("old vIER %x\n", vgpu_vreg(vgpu, reg)); + gvt_dbg_irq("write IER %x, new %08x, old %08x, changed %08x\n", + reg, ier, vgpu_vreg(vgpu, reg), vgpu_vreg(vgpu, reg) ^ ier); - /* figure out newly enabled/disable bits */ - changed = vgpu_vreg(vgpu, reg) ^ ier; - enabled = (vgpu_vreg(vgpu, reg) & changed) ^ changed; - disabled = enabled ^ changed; - - gvt_dbg_irq("changed %x, enabled %x, disabled %x\n", - changed, enabled, disabled); vgpu_vreg(vgpu, reg) = ier; info = regbase_to_irq_info(gvt, ier_to_regbase(reg)); @@ -293,7 +261,7 @@ int intel_vgpu_reg_ier_handler(struct intel_vgpu *vgpu, update_upstream_irq(vgpu, info); ops->check_pending_irq(vgpu); - gvt_dbg_irq("new vIER %x\n", vgpu_vreg(vgpu, reg)); + return 0; } @@ -317,7 +285,8 @@ int intel_vgpu_reg_iir_handler(struct intel_vgpu *vgpu, unsigned int reg, iir_to_regbase(reg)); u32 iir = *(u32 *)p_data; - gvt_dbg_irq("write IIR %x with val %x\n", reg, iir); + gvt_dbg_irq("write IIR %x, new %08x, old %08x, changed %08x\n", + reg, iir, vgpu_vreg(vgpu, reg), vgpu_vreg(vgpu, reg) ^ iir); if (WARN_ON(!info)) return -EINVAL; @@ -619,6 +588,10 @@ static void gen8_init_irq( SET_BIT_INFO(irq, 3, PRIMARY_A_FLIP_DONE, INTEL_GVT_IRQ_INFO_DE_PIPE_A); SET_BIT_INFO(irq, 3, PRIMARY_B_FLIP_DONE, INTEL_GVT_IRQ_INFO_DE_PIPE_B); SET_BIT_INFO(irq, 3, PRIMARY_C_FLIP_DONE, INTEL_GVT_IRQ_INFO_DE_PIPE_C); + + SET_BIT_INFO(irq, 4, SPRITE_A_FLIP_DONE, INTEL_GVT_IRQ_INFO_DE_PIPE_A); + SET_BIT_INFO(irq, 4, SPRITE_B_FLIP_DONE, INTEL_GVT_IRQ_INFO_DE_PIPE_B); + SET_BIT_INFO(irq, 4, SPRITE_C_FLIP_DONE, INTEL_GVT_IRQ_INFO_DE_PIPE_C); } /* GEN8 interrupt PCU events */ diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 0c9234a87a20..0f7f5d97f582 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -77,7 +77,7 @@ struct kvmgt_guest_info { struct gvt_dma { struct rb_node node; gfn_t gfn; - kvm_pfn_t pfn; + unsigned long iova; }; static inline bool handle_valid(unsigned long handle) @@ -89,6 +89,35 @@ static int kvmgt_guest_init(struct mdev_device *mdev); static void intel_vgpu_release_work(struct work_struct *work); static bool kvmgt_guest_exit(struct kvmgt_guest_info *info); +static int gvt_dma_map_iova(struct intel_vgpu *vgpu, kvm_pfn_t pfn, + unsigned long *iova) +{ + struct page *page; + struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev; + dma_addr_t daddr; + + page = pfn_to_page(pfn); + if (is_error_page(page)) + return -EFAULT; + + daddr = dma_map_page(dev, page, 0, PAGE_SIZE, + PCI_DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, daddr)) + return -ENOMEM; + + *iova = (unsigned long)(daddr >> PAGE_SHIFT); + return 0; +} + +static void gvt_dma_unmap_iova(struct intel_vgpu *vgpu, unsigned long iova) +{ + struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev; + dma_addr_t daddr; + + daddr = (dma_addr_t)(iova << PAGE_SHIFT); + dma_unmap_page(dev, daddr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); +} + static struct gvt_dma *__gvt_cache_find(struct intel_vgpu *vgpu, gfn_t gfn) { struct rb_node *node = vgpu->vdev.cache.rb_node; @@ -111,21 +140,22 @@ out: return ret; } -static kvm_pfn_t gvt_cache_find(struct intel_vgpu *vgpu, gfn_t gfn) +static unsigned long gvt_cache_find(struct intel_vgpu *vgpu, gfn_t gfn) { struct gvt_dma *entry; - kvm_pfn_t pfn; + unsigned long iova; mutex_lock(&vgpu->vdev.cache_lock); entry = __gvt_cache_find(vgpu, gfn); - pfn = (entry == NULL) ? 0 : entry->pfn; + iova = (entry == NULL) ? INTEL_GVT_INVALID_ADDR : entry->iova; mutex_unlock(&vgpu->vdev.cache_lock); - return pfn; + return iova; } -static void gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn, kvm_pfn_t pfn) +static void gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn, + unsigned long iova) { struct gvt_dma *new, *itr; struct rb_node **link = &vgpu->vdev.cache.rb_node, *parent = NULL; @@ -135,7 +165,7 @@ static void gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn, kvm_pfn_t pfn) return; new->gfn = gfn; - new->pfn = pfn; + new->iova = iova; mutex_lock(&vgpu->vdev.cache_lock); while (*link) { @@ -182,6 +212,7 @@ static void gvt_cache_remove(struct intel_vgpu *vgpu, gfn_t gfn) } g1 = gfn; + gvt_dma_unmap_iova(vgpu, this->iova); rc = vfio_unpin_pages(dev, &g1, 1); WARN_ON(rc != 1); __gvt_cache_remove_entry(vgpu, this); @@ -204,6 +235,7 @@ static void gvt_cache_destroy(struct intel_vgpu *vgpu) mutex_lock(&vgpu->vdev.cache_lock); while ((node = rb_first(&vgpu->vdev.cache))) { dma = rb_entry(node, struct gvt_dma, node); + gvt_dma_unmap_iova(vgpu, dma->iova); gfn = dma->gfn; vfio_unpin_pages(dev, &gfn, 1); @@ -230,8 +262,8 @@ static struct intel_vgpu_type *intel_gvt_find_vgpu_type(struct intel_gvt *gvt, return NULL; } -static ssize_t available_instance_show(struct kobject *kobj, struct device *dev, - char *buf) +static ssize_t available_instances_show(struct kobject *kobj, + struct device *dev, char *buf) { struct intel_vgpu_type *type; unsigned int num = 0; @@ -269,12 +301,12 @@ static ssize_t description_show(struct kobject *kobj, struct device *dev, type->fence); } -static MDEV_TYPE_ATTR_RO(available_instance); +static MDEV_TYPE_ATTR_RO(available_instances); static MDEV_TYPE_ATTR_RO(device_api); static MDEV_TYPE_ATTR_RO(description); static struct attribute *type_attrs[] = { - &mdev_type_attr_available_instance.attr, + &mdev_type_attr_available_instances.attr, &mdev_type_attr_device_api.attr, &mdev_type_attr_description.attr, NULL, @@ -965,11 +997,6 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd, sparse->areas[0].offset = PAGE_ALIGN(vgpu_aperture_offset(vgpu)); sparse->areas[0].size = vgpu_aperture_sz(vgpu); - if (!caps.buf) { - kfree(caps.buf); - caps.buf = NULL; - caps.size = 0; - } break; case VFIO_PCI_BAR3_REGION_INDEX ... VFIO_PCI_BAR5_REGION_INDEX: @@ -1248,43 +1275,6 @@ static void kvmgt_page_track_flush_slot(struct kvm *kvm, spin_unlock(&kvm->mmu_lock); } -static bool kvmgt_check_guest(void) -{ - unsigned int eax, ebx, ecx, edx; - char s[12]; - unsigned int *i; - - eax = KVM_CPUID_SIGNATURE; - ebx = ecx = edx = 0; - - asm volatile ("cpuid" - : "+a"(eax), "=b"(ebx), "=c"(ecx), "=d"(edx) - : - : "cc", "memory"); - i = (unsigned int *)s; - i[0] = ebx; - i[1] = ecx; - i[2] = edx; - - return !strncmp(s, "KVMKVMKVM", strlen("KVMKVMKVM")); -} - -/** - * NOTE: - * It's actually impossible to check if we are running in KVM host, - * since the "KVM host" is simply native. So we only dectect guest here. - */ -static int kvmgt_detect_host(void) -{ -#ifdef CONFIG_INTEL_IOMMU - if (intel_iommu_gfx_mapped) { - gvt_err("Hardware IOMMU compatibility not yet supported, try to boot with intel_iommu=igfx_off\n"); - return -ENODEV; - } -#endif - return kvmgt_check_guest() ? -ENODEV : 0; -} - static bool __kvmgt_vgpu_exist(struct intel_vgpu *vgpu, struct kvm *kvm) { struct intel_vgpu *itr; @@ -1390,7 +1380,7 @@ static int kvmgt_inject_msi(unsigned long handle, u32 addr, u16 data) static unsigned long kvmgt_gfn_to_pfn(unsigned long handle, unsigned long gfn) { - unsigned long pfn; + unsigned long iova, pfn; struct kvmgt_guest_info *info; struct device *dev; int rc; @@ -1399,9 +1389,9 @@ static unsigned long kvmgt_gfn_to_pfn(unsigned long handle, unsigned long gfn) return INTEL_GVT_INVALID_ADDR; info = (struct kvmgt_guest_info *)handle; - pfn = gvt_cache_find(info->vgpu, gfn); - if (pfn != 0) - return pfn; + iova = gvt_cache_find(info->vgpu, gfn); + if (iova != INTEL_GVT_INVALID_ADDR) + return iova; pfn = INTEL_GVT_INVALID_ADDR; dev = mdev_dev(info->vgpu->vdev.mdev); @@ -1410,9 +1400,16 @@ static unsigned long kvmgt_gfn_to_pfn(unsigned long handle, unsigned long gfn) gvt_err("vfio_pin_pages failed for gfn 0x%lx: %d\n", gfn, rc); return INTEL_GVT_INVALID_ADDR; } + /* transfer to host iova for GFX to use DMA */ + rc = gvt_dma_map_iova(info->vgpu, pfn, &iova); + if (rc) { + gvt_err("gvt_dma_map_iova failed for gfn: 0x%lx\n", gfn); + vfio_unpin_pages(dev, &gfn, 1); + return INTEL_GVT_INVALID_ADDR; + } - gvt_cache_add(info->vgpu, gfn, pfn); - return pfn; + gvt_cache_add(info->vgpu, gfn, iova); + return iova; } static int kvmgt_rw_gpa(unsigned long handle, unsigned long gpa, @@ -1459,7 +1456,6 @@ static unsigned long kvmgt_virt_to_pfn(void *addr) } struct intel_gvt_mpt kvmgt_mpt = { - .detect_host = kvmgt_detect_host, .host_init = kvmgt_host_init, .host_exit = kvmgt_host_exit, .attach_vgpu = kvmgt_attach_vgpu, diff --git a/drivers/gpu/drm/i915/gvt/mpt.h b/drivers/gpu/drm/i915/gvt/mpt.h index 1af5830c0a56..419353624c5a 100644 --- a/drivers/gpu/drm/i915/gvt/mpt.h +++ b/drivers/gpu/drm/i915/gvt/mpt.h @@ -44,18 +44,6 @@ */ /** - * intel_gvt_hypervisor_detect_host - check if GVT-g is running within - * hypervisor host/privilged domain - * - * Returns: - * Zero on success, -ENODEV if current kernel is running inside a VM - */ -static inline int intel_gvt_hypervisor_detect_host(void) -{ - return intel_gvt_host.mpt->detect_host(); -} - -/** * intel_gvt_hypervisor_host_init - init GVT-g host side * * Returns: diff --git a/drivers/gpu/drm/i915/gvt/render.c b/drivers/gpu/drm/i915/gvt/render.c index 44136b1f3aab..2b3a642284b6 100644 --- a/drivers/gpu/drm/i915/gvt/render.c +++ b/drivers/gpu/drm/i915/gvt/render.c @@ -236,12 +236,18 @@ static void restore_mocs(struct intel_vgpu *vgpu, int ring_id) } } +#define CTX_CONTEXT_CONTROL_VAL 0x03 + void intel_gvt_load_render_mmio(struct intel_vgpu *vgpu, int ring_id) { struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; struct render_mmio *mmio; u32 v; int i, array_size; + u32 *reg_state = vgpu->shadow_ctx->engine[ring_id].lrc_reg_state; + u32 ctx_ctrl = reg_state[CTX_CONTEXT_CONTROL_VAL]; + u32 inhibit_mask = + _MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT); if (IS_SKYLAKE(vgpu->gvt->dev_priv)) { mmio = gen9_render_mmio_list; @@ -257,6 +263,17 @@ void intel_gvt_load_render_mmio(struct intel_vgpu *vgpu, int ring_id) continue; mmio->value = I915_READ(mmio->reg); + + /* + * if it is an inhibit context, load in_context mmio + * into HW by mmio write. If it is not, skip this mmio + * write. + */ + if (mmio->in_context && + ((ctx_ctrl & inhibit_mask) != inhibit_mask) && + i915.enable_execlists) + continue; + if (mmio->mask) v = vgpu_vreg(vgpu, mmio->reg) | (mmio->mask << 16); else diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c index 678b0be85376..06c9584ac5f0 100644 --- a/drivers/gpu/drm/i915/gvt/sched_policy.c +++ b/drivers/gpu/drm/i915/gvt/sched_policy.c @@ -125,7 +125,6 @@ static void tbs_sched_func(struct work_struct *work) vgpu_data = scheduler->current_vgpu->sched_data; head = &vgpu_data->list; } else { - gvt_dbg_sched("no current vgpu search from q head\n"); head = &sched_data->runq_head; } diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 7ea68a75dc46..d6b6d0efdd1a 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -169,7 +169,8 @@ static int dispatch_workload(struct intel_vgpu_workload *workload) gvt_dbg_sched("ring id %d prepare to dispatch workload %p\n", ring_id, workload); - shadow_ctx->desc_template = workload->ctx_desc.addressing_mode << + shadow_ctx->desc_template &= ~(0x3 << GEN8_CTX_ADDRESSING_MODE_SHIFT); + shadow_ctx->desc_template |= workload->ctx_desc.addressing_mode << GEN8_CTX_ADDRESSING_MODE_SHIFT; mutex_lock(&dev_priv->drm.struct_mutex); @@ -456,7 +457,7 @@ static int workload_thread(void *priv) } complete: - gvt_dbg_sched("will complete workload %p\n, status: %d\n", + gvt_dbg_sched("will complete workload %p, status: %d\n", workload, workload->status); if (workload->req) diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h index 3b30c28bff51..2833dfa8c9ae 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.h +++ b/drivers/gpu/drm/i915/gvt/scheduler.h @@ -113,7 +113,7 @@ struct intel_shadow_bb_entry { struct drm_i915_gem_object *obj; void *va; unsigned long len; - void *bb_start_cmd_va; + u32 *bb_start_cmd_va; }; #define workload_q_head(vgpu, ring_id) \ diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 7295bc8e12fb..95a97aa0051e 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -74,7 +74,7 @@ void populate_pvinfo_page(struct intel_vgpu *vgpu) int intel_gvt_init_vgpu_types(struct intel_gvt *gvt) { unsigned int num_types; - unsigned int i, low_avail; + unsigned int i, low_avail, high_avail; unsigned int min_low; /* vGPU type name is defined as GVTg_Vx_y which contains @@ -89,9 +89,9 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt) * to indicate how many vGPU instance can be created for this * type. * - * Currently use static size here as we init type earlier.. */ - low_avail = MB_TO_BYTES(256) - HOST_LOW_GM_SIZE; + low_avail = gvt_aperture_sz(gvt) - HOST_LOW_GM_SIZE; + high_avail = gvt_hidden_sz(gvt) - HOST_HIGH_GM_SIZE; num_types = 4; gvt->types = kzalloc(num_types * sizeof(struct intel_vgpu_type), @@ -106,7 +106,8 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt) gvt->types[i].low_gm_size = min_low; gvt->types[i].high_gm_size = max((min_low<<3), MB_TO_BYTES(384U)); gvt->types[i].fence = 4; - gvt->types[i].max_instance = low_avail / min_low; + gvt->types[i].max_instance = min(low_avail / min_low, + high_avail / gvt->types[i].high_gm_size); gvt->types[i].avail_instance = gvt->types[i].max_instance; if (IS_GEN8(gvt->dev_priv)) @@ -142,9 +143,9 @@ static void intel_gvt_update_vgpu_types(struct intel_gvt *gvt) /* Need to depend on maxium hw resource size but keep on * static config for now. */ - low_gm_avail = MB_TO_BYTES(256) - HOST_LOW_GM_SIZE - + low_gm_avail = gvt_aperture_sz(gvt) - HOST_LOW_GM_SIZE - gvt->gm.vgpu_allocated_low_gm_size; - high_gm_avail = MB_TO_BYTES(256) * 8UL - HOST_HIGH_GM_SIZE - + high_gm_avail = gvt_hidden_sz(gvt) - HOST_HIGH_GM_SIZE - gvt->gm.vgpu_allocated_high_gm_size; fence_avail = gvt_fence_sz(gvt) - HOST_FENCE - gvt->fence.vgpu_allocated_fence_num; @@ -384,6 +385,7 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, intel_vgpu_reset_resource(vgpu); intel_vgpu_reset_mmio(vgpu); populate_pvinfo_page(vgpu); + intel_vgpu_reset_display(vgpu); if (dmlr) intel_vgpu_reset_cfg_space(vgpu); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 4ae69ebe166e..f6017f2cfb86 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -213,7 +213,8 @@ static void intel_detect_pch(struct drm_i915_private *dev_priv) } else if (id == INTEL_PCH_KBP_DEVICE_ID_TYPE) { dev_priv->pch_type = PCH_KBP; DRM_DEBUG_KMS("Found KabyPoint PCH\n"); - WARN_ON(!IS_KABYLAKE(dev_priv)); + WARN_ON(!IS_SKYLAKE(dev_priv) && + !IS_KABYLAKE(dev_priv)); } else if ((id == INTEL_PCH_P2X_DEVICE_ID_TYPE) || (id == INTEL_PCH_P3X_DEVICE_ID_TYPE) || ((id == INTEL_PCH_QEMU_DEVICE_ID_TYPE) && @@ -824,10 +825,6 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv, if (ret < 0) return ret; - ret = intel_gvt_init(dev_priv); - if (ret < 0) - goto err_workqueues; - /* This must be called before any calls to HAS_PCH_* */ intel_detect_pch(dev_priv); @@ -841,7 +838,7 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv, intel_init_audio_hooks(dev_priv); ret = i915_gem_load_init(dev_priv); if (ret < 0) - goto err_gvt; + goto err_workqueues; intel_display_crc_init(dev_priv); @@ -853,8 +850,6 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv, return 0; -err_gvt: - intel_gvt_cleanup(dev_priv); err_workqueues: i915_workqueues_cleanup(dev_priv); return ret; @@ -1077,6 +1072,10 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv) DRM_DEBUG_DRIVER("can't enable MSI"); } + ret = intel_gvt_init(dev_priv); + if (ret) + goto out_ggtt; + return 0; out_ggtt: @@ -1290,6 +1289,8 @@ void i915_driver_unload(struct drm_device *dev) intel_display_power_get(dev_priv, POWER_DOMAIN_INIT); + intel_gvt_cleanup(dev_priv); + i915_driver_unregister(dev_priv); drm_vblank_cleanup(dev); @@ -2377,7 +2378,7 @@ static int intel_runtime_suspend(struct device *kdev) assert_forcewakes_inactive(dev_priv); - if (!IS_VALLEYVIEW(dev_priv) || !IS_CHERRYVIEW(dev_priv)) + if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv)) intel_hpd_poll_init(dev_priv); DRM_DEBUG_KMS("Device suspended\n"); @@ -2426,6 +2427,7 @@ static int intel_runtime_resume(struct device *kdev) * we can do is to hope that things will still work (and disable RPM). */ i915_gem_init_swizzling(dev_priv); + i915_gem_restore_fences(dev_priv); intel_runtime_pm_enable_interrupts(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 244628065f94..e44c598ecb82 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2242,6 +2242,11 @@ struct drm_i915_private { struct i915_frontbuffer_tracking fb_tracking; + struct intel_atomic_helper { + struct llist_head free_list; + struct work_struct free_work; + } atomic_helper; + u16 orig_clock; bool mchbar_need_disable; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index c8689892a89f..88f3628b4e29 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -440,7 +440,7 @@ i915_gem_object_wait_reservation(struct reservation_object *resv, timeout = i915_gem_object_wait_fence(shared[i], flags, timeout, rps); - if (timeout <= 0) + if (timeout < 0) break; dma_fence_put(shared[i]); @@ -453,7 +453,7 @@ i915_gem_object_wait_reservation(struct reservation_object *resv, excl = reservation_object_get_excl_rcu(resv); } - if (excl && timeout > 0) + if (excl && timeout >= 0) timeout = i915_gem_object_wait_fence(excl, flags, timeout, rps); dma_fence_put(excl); @@ -2009,8 +2009,16 @@ void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv) for (i = 0; i < dev_priv->num_fence_regs; i++) { struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i]; - if (WARN_ON(reg->pin_count)) - continue; + /* Ideally we want to assert that the fence register is not + * live at this point (i.e. that no piece of code will be + * trying to write through fence + GTT, as that both violates + * our tracking of activity and associated locking/barriers, + * but also is illegal given that the hw is powered down). + * + * Previously we used reg->pin_count as a "liveness" indicator. + * That is not sufficient, and we need a more fine-grained + * tool if we want to have a sanity check here. + */ if (!reg->vma) continue; @@ -2735,21 +2743,17 @@ static void i915_gem_reset_engine(struct intel_engine_cs *engine) engine->irq_seqno_barrier(engine); request = i915_gem_find_active_request(engine); - if (!request) - return; + if (request && i915_gem_reset_request(request)) { + DRM_DEBUG_DRIVER("resetting %s to restart from tail of request 0x%x\n", + engine->name, request->global_seqno); - if (!i915_gem_reset_request(request)) - return; - - DRM_DEBUG_DRIVER("resetting %s to restart from tail of request 0x%x\n", - engine->name, request->global_seqno); + /* If this context is now banned, skip all pending requests. */ + if (i915_gem_context_is_banned(request->ctx)) + engine_skip_context(request); + } /* Setup the CS to resume from the breadcrumb of the hung request */ engine->reset_hw(engine, request); - - /* If this context is now banned, skip all of its pending requests. */ - if (i915_gem_context_is_banned(request->ctx)) - engine_skip_context(request); } void i915_gem_reset_finish(struct drm_i915_private *dev_priv) @@ -3517,7 +3521,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj, vma->display_alignment = max_t(u64, vma->display_alignment, alignment); /* Treat this as an end-of-frame, like intel_user_framebuffer_dirty() */ - if (obj->cache_dirty) { + if (obj->cache_dirty || obj->base.write_domain == I915_GEM_DOMAIN_CPU) { i915_gem_clflush_object(obj, true); intel_fb_obj_flush(obj, false, ORIGIN_DIRTYFB); } diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 57bec08e80c5..d02cfaefe1c8 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1180,14 +1180,14 @@ validate_exec_list(struct drm_device *dev, if (exec[i].offset != gen8_canonical_addr(exec[i].offset & PAGE_MASK)) return -EINVAL; - - /* From drm_mm perspective address space is continuous, - * so from this point we're always using non-canonical - * form internally. - */ - exec[i].offset = gen8_noncanonical_addr(exec[i].offset); } + /* From drm_mm perspective address space is continuous, + * so from this point we're always using non-canonical + * form internally. + */ + exec[i].offset = gen8_noncanonical_addr(exec[i].offset); + if (exec[i].alignment && !is_power_of_2(exec[i].alignment)) return -EINVAL; diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 30d8dbd04f0b..2801a4d56324 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -755,9 +755,10 @@ static bool gen8_ppgtt_clear_pt(struct i915_address_space *vm, GEM_BUG_ON(pte_end > GEN8_PTES); bitmap_clear(pt->used_ptes, pte, num_entries); - - if (bitmap_empty(pt->used_ptes, GEN8_PTES)) - return true; + if (USES_FULL_PPGTT(vm->i915)) { + if (bitmap_empty(pt->used_ptes, GEN8_PTES)) + return true; + } pt_vaddr = kmap_px(pt); diff --git a/drivers/gpu/drm/i915/i915_gem_internal.c b/drivers/gpu/drm/i915/i915_gem_internal.c index 17ce53d0d092..933019e1b206 100644 --- a/drivers/gpu/drm/i915/i915_gem_internal.c +++ b/drivers/gpu/drm/i915/i915_gem_internal.c @@ -46,16 +46,39 @@ static struct sg_table * i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj) { struct drm_i915_private *i915 = to_i915(obj->base.dev); - unsigned int npages = obj->base.size / PAGE_SIZE; struct sg_table *st; struct scatterlist *sg; + unsigned int npages; int max_order; gfp_t gfp; + max_order = MAX_ORDER; +#ifdef CONFIG_SWIOTLB + if (swiotlb_nr_tbl()) { + unsigned int max_segment; + + max_segment = swiotlb_max_segment(); + if (max_segment) { + max_segment = max_t(unsigned int, max_segment, + PAGE_SIZE) >> PAGE_SHIFT; + max_order = min(max_order, ilog2(max_segment)); + } + } +#endif + + gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_RECLAIMABLE; + if (IS_I965GM(i915) || IS_I965G(i915)) { + /* 965gm cannot relocate objects above 4GiB. */ + gfp &= ~__GFP_HIGHMEM; + gfp |= __GFP_DMA32; + } + +create_st: st = kmalloc(sizeof(*st), GFP_KERNEL); if (!st) return ERR_PTR(-ENOMEM); + npages = obj->base.size / PAGE_SIZE; if (sg_alloc_table(st, npages, GFP_KERNEL)) { kfree(st); return ERR_PTR(-ENOMEM); @@ -64,19 +87,6 @@ i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj) sg = st->sgl; st->nents = 0; - max_order = MAX_ORDER; -#ifdef CONFIG_SWIOTLB - if (swiotlb_nr_tbl()) /* minimum max swiotlb size is IO_TLB_SEGSIZE */ - max_order = min(max_order, ilog2(IO_TLB_SEGPAGES)); -#endif - - gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_RECLAIMABLE; - if (IS_I965GM(i915) || IS_I965G(i915)) { - /* 965gm cannot relocate objects above 4GiB. */ - gfp &= ~__GFP_HIGHMEM; - gfp |= __GFP_DMA32; - } - do { int order = min(fls(npages) - 1, max_order); struct page *page; @@ -104,8 +114,15 @@ i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj) sg = __sg_next(sg); } while (1); - if (i915_gem_gtt_prepare_pages(obj, st)) + if (i915_gem_gtt_prepare_pages(obj, st)) { + /* Failed to dma-map try again with single page sg segments */ + if (get_order(st->sgl->length)) { + internal_free_pages(st); + max_order = 0; + goto create_st; + } goto err; + } /* Mark the pages as dontneed whilst they are still pinned. As soon * as they are unpinned they are allowed to be reaped by the shrinker, diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c index 72b7f7d9461d..f31deeb72703 100644 --- a/drivers/gpu/drm/i915/i915_gem_request.c +++ b/drivers/gpu/drm/i915/i915_gem_request.c @@ -1025,8 +1025,13 @@ __i915_request_wait_for_execute(struct drm_i915_gem_request *request, break; } + if (!timeout) { + timeout = -ETIME; + break; + } + timeout = io_schedule_timeout(timeout); - } while (timeout); + } while (1); finish_wait(&request->execute.wait, &wait); if (flags & I915_WAIT_LOCKED) diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index ec7c5d80fe4f..9673bcc3b6ad 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -405,6 +405,11 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv) mutex_init(&dev_priv->mm.stolen_lock); + if (intel_vgpu_active(dev_priv)) { + DRM_INFO("iGVT-g active, disabling use of stolen memory\n"); + return 0; + } + #ifdef CONFIG_INTEL_IOMMU if (intel_iommu_gfx_mapped && INTEL_GEN(dev_priv) < 8) { DRM_INFO("DMAR active, disabling use of stolen memory\n"); diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index b1361cfd4c5c..974ac08df473 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -173,7 +173,7 @@ i915_tiling_ok(struct drm_i915_gem_object *obj, else tile_width = 512; - if (!IS_ALIGNED(stride, tile_width)) + if (!stride || !IS_ALIGNED(stride, tile_width)) return false; /* 965+ just needs multiples of tile width */ diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index ee313247673b..53bb7de6020d 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -3123,19 +3123,16 @@ static void ibx_hpd_irq_setup(struct drm_i915_private *dev_priv) I915_WRITE(PCH_PORT_HOTPLUG, hotplug); } -static void spt_hpd_irq_setup(struct drm_i915_private *dev_priv) +static void spt_hpd_detection_setup(struct drm_i915_private *dev_priv) { - u32 hotplug_irqs, hotplug, enabled_irqs; - - hotplug_irqs = SDE_HOTPLUG_MASK_SPT; - enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_spt); - - ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs); + u32 hotplug; /* Enable digital hotplug on the PCH */ hotplug = I915_READ(PCH_PORT_HOTPLUG); - hotplug |= PORTD_HOTPLUG_ENABLE | PORTC_HOTPLUG_ENABLE | - PORTB_HOTPLUG_ENABLE | PORTA_HOTPLUG_ENABLE; + hotplug |= PORTA_HOTPLUG_ENABLE | + PORTB_HOTPLUG_ENABLE | + PORTC_HOTPLUG_ENABLE | + PORTD_HOTPLUG_ENABLE; I915_WRITE(PCH_PORT_HOTPLUG, hotplug); hotplug = I915_READ(PCH_PORT_HOTPLUG2); @@ -3143,6 +3140,18 @@ static void spt_hpd_irq_setup(struct drm_i915_private *dev_priv) I915_WRITE(PCH_PORT_HOTPLUG2, hotplug); } +static void spt_hpd_irq_setup(struct drm_i915_private *dev_priv) +{ + u32 hotplug_irqs, enabled_irqs; + + hotplug_irqs = SDE_HOTPLUG_MASK_SPT; + enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_spt); + + ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs); + + spt_hpd_detection_setup(dev_priv); +} + static void ilk_hpd_irq_setup(struct drm_i915_private *dev_priv) { u32 hotplug_irqs, hotplug, enabled_irqs; @@ -3177,18 +3186,15 @@ static void ilk_hpd_irq_setup(struct drm_i915_private *dev_priv) ibx_hpd_irq_setup(dev_priv); } -static void bxt_hpd_irq_setup(struct drm_i915_private *dev_priv) +static void __bxt_hpd_detection_setup(struct drm_i915_private *dev_priv, + u32 enabled_irqs) { - u32 hotplug_irqs, hotplug, enabled_irqs; - - enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_bxt); - hotplug_irqs = BXT_DE_PORT_HOTPLUG_MASK; - - bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs); + u32 hotplug; hotplug = I915_READ(PCH_PORT_HOTPLUG); - hotplug |= PORTC_HOTPLUG_ENABLE | PORTB_HOTPLUG_ENABLE | - PORTA_HOTPLUG_ENABLE; + hotplug |= PORTA_HOTPLUG_ENABLE | + PORTB_HOTPLUG_ENABLE | + PORTC_HOTPLUG_ENABLE; DRM_DEBUG_KMS("Invert bit setting: hp_ctl:%x hp_port:%x\n", hotplug, enabled_irqs); @@ -3198,7 +3204,6 @@ static void bxt_hpd_irq_setup(struct drm_i915_private *dev_priv) * For BXT invert bit has to be set based on AOB design * for HPD detection logic, update it based on VBT fields. */ - if ((enabled_irqs & BXT_DE_PORT_HP_DDIA) && intel_bios_is_port_hpd_inverted(dev_priv, PORT_A)) hotplug |= BXT_DDIA_HPD_INVERT; @@ -3212,6 +3217,23 @@ static void bxt_hpd_irq_setup(struct drm_i915_private *dev_priv) I915_WRITE(PCH_PORT_HOTPLUG, hotplug); } +static void bxt_hpd_detection_setup(struct drm_i915_private *dev_priv) +{ + __bxt_hpd_detection_setup(dev_priv, BXT_DE_PORT_HOTPLUG_MASK); +} + +static void bxt_hpd_irq_setup(struct drm_i915_private *dev_priv) +{ + u32 hotplug_irqs, enabled_irqs; + + enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_bxt); + hotplug_irqs = BXT_DE_PORT_HOTPLUG_MASK; + + bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs); + + __bxt_hpd_detection_setup(dev_priv, enabled_irqs); +} + static void ibx_irq_postinstall(struct drm_device *dev) { struct drm_i915_private *dev_priv = to_i915(dev); @@ -3227,6 +3249,12 @@ static void ibx_irq_postinstall(struct drm_device *dev) gen5_assert_iir_is_zero(dev_priv, SDEIIR); I915_WRITE(SDEIMR, ~mask); + + if (HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv) || + HAS_PCH_LPT(dev_priv)) + ; /* TODO: Enable HPD detection on older PCH platforms too */ + else + spt_hpd_detection_setup(dev_priv); } static void gen5_gt_irq_postinstall(struct drm_device *dev) @@ -3438,6 +3466,9 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) GEN5_IRQ_INIT(GEN8_DE_PORT_, ~de_port_masked, de_port_enables); GEN5_IRQ_INIT(GEN8_DE_MISC_, ~de_misc_masked, de_misc_masked); + + if (IS_GEN9_LP(dev_priv)) + bxt_hpd_detection_setup(dev_priv); } static int gen8_irq_postinstall(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 72f9f36ae5ce..675323189f2c 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -3307,8 +3307,10 @@ enum skl_disp_power_wells { /* * Logical Context regs */ -#define CCID _MMIO(0x2180) -#define CCID_EN (1<<0) +#define CCID _MMIO(0x2180) +#define CCID_EN BIT(0) +#define CCID_EXTENDED_STATE_RESTORE BIT(2) +#define CCID_EXTENDED_STATE_SAVE BIT(3) /* * Notes on SNB/IVB/VLV context size: * - Power context is saved elsewhere (LLC or stolen) diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 385e29af8baa..2bf5aca6e37c 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -499,6 +499,7 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector) struct drm_i915_private *dev_priv = to_i915(crt->base.base.dev); struct edid *edid; struct i2c_adapter *i2c; + bool ret = false; BUG_ON(crt->base.type != INTEL_OUTPUT_ANALOG); @@ -515,17 +516,17 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector) */ if (!is_digital) { DRM_DEBUG_KMS("CRT detected via DDC:0x50 [EDID]\n"); - return true; + ret = true; + } else { + DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n"); } - - DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n"); } else { DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [no valid EDID found]\n"); } kfree(edid); - return false; + return ret; } static enum drm_connector_status diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 36ecc864e711..a2fece5e9fb3 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2578,8 +2578,9 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv, * We only keep the x/y offsets, so push all of the * gtt offset into the x/y offsets. */ - _intel_adjust_tile_offset(&x, &y, tile_size, - tile_width, tile_height, pitch_tiles, + _intel_adjust_tile_offset(&x, &y, + tile_width, tile_height, + tile_size, pitch_tiles, gtt_offset_rotated * tile_size, 0); gtt_offset_rotated += rot_info->plane[i].width * rot_info->plane[i].height; @@ -4253,10 +4254,10 @@ static void page_flip_completed(struct intel_crtc *intel_crtc) drm_crtc_vblank_put(&intel_crtc->base); wake_up_all(&dev_priv->pending_flip_queue); - queue_work(dev_priv->wq, &work->unpin_work); - trace_i915_flip_complete(intel_crtc->plane, work->pending_flip_obj); + + queue_work(dev_priv->wq, &work->unpin_work); } static int intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc) @@ -6882,6 +6883,12 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc) } state = drm_atomic_state_alloc(crtc->dev); + if (!state) { + DRM_DEBUG_KMS("failed to disable [CRTC:%d:%s], out of memory", + crtc->base.id, crtc->name); + return; + } + state->acquire_ctx = crtc->dev->mode_config.acquire_ctx; /* Everything's already locked, -EDEADLK can't happen. */ @@ -14563,8 +14570,14 @@ intel_atomic_commit_ready(struct i915_sw_fence *fence, break; case FENCE_FREE: - drm_atomic_state_put(&state->base); - break; + { + struct intel_atomic_helper *helper = + &to_i915(state->base.dev)->atomic_helper; + + if (llist_add(&state->freed, &helper->free_list)) + schedule_work(&helper->free_work); + break; + } } return NOTIFY_DONE; @@ -16587,6 +16600,18 @@ fail: drm_modeset_acquire_fini(&ctx); } +static void intel_atomic_helper_free_state(struct work_struct *work) +{ + struct drm_i915_private *dev_priv = + container_of(work, typeof(*dev_priv), atomic_helper.free_work); + struct intel_atomic_state *state, *next; + struct llist_node *freed; + + freed = llist_del_all(&dev_priv->atomic_helper.free_list); + llist_for_each_entry_safe(state, next, freed, freed) + drm_atomic_state_put(&state->base); +} + int intel_modeset_init(struct drm_device *dev) { struct drm_i915_private *dev_priv = to_i915(dev); @@ -16606,6 +16631,9 @@ int intel_modeset_init(struct drm_device *dev) dev->mode_config.funcs = &intel_mode_funcs; + INIT_WORK(&dev_priv->atomic_helper.free_work, + intel_atomic_helper_free_state); + intel_init_quirks(dev); intel_init_pm(dev_priv); @@ -17263,6 +17291,9 @@ void intel_modeset_cleanup(struct drm_device *dev) { struct drm_i915_private *dev_priv = to_i915(dev); + flush_work(&dev_priv->atomic_helper.free_work); + WARN_ON(!llist_empty(&dev_priv->atomic_helper.free_list)); + intel_disable_gt_powersave(dev_priv); /* diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 3d8ac8aa7214..d1670b8afbf5 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -2887,6 +2887,9 @@ static void vlv_detach_power_sequencer(struct intel_dp *intel_dp) WARN_ON(intel_dp->active_pipe != INVALID_PIPE); + if (WARN_ON(pipe != PIPE_A && pipe != PIPE_B)) + return; + edp_panel_vdd_off_sync(intel_dp); /* @@ -2914,9 +2917,6 @@ static void vlv_steal_power_sequencer(struct drm_device *dev, lockdep_assert_held(&dev_priv->pps_mutex); - if (WARN_ON(pipe != PIPE_A && pipe != PIPE_B)) - return; - for_each_intel_encoder(dev, encoder) { struct intel_dp *intel_dp; enum port port; @@ -4406,8 +4406,8 @@ static bool bxt_digital_port_connected(struct drm_i915_private *dev_priv, * * Return %true if @port is connected, %false otherwise. */ -static bool intel_digital_port_connected(struct drm_i915_private *dev_priv, - struct intel_digital_port *port) +bool intel_digital_port_connected(struct drm_i915_private *dev_priv, + struct intel_digital_port *port) { if (HAS_PCH_IBX(dev_priv)) return ibx_digital_port_connected(dev_priv, port); diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c index c92a2558beb4..e59e43a9f3a6 100644 --- a/drivers/gpu/drm/i915/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c @@ -1855,7 +1855,8 @@ bxt_get_dpll(struct intel_crtc *crtc, return NULL; if ((encoder->type == INTEL_OUTPUT_DP || - encoder->type == INTEL_OUTPUT_EDP) && + encoder->type == INTEL_OUTPUT_EDP || + encoder->type == INTEL_OUTPUT_DP_MST) && !bxt_ddi_dp_set_dpll_hw_state(clock, &dpll_hw_state)) return NULL; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 0cec0013ace0..40fed65a791d 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -371,6 +371,8 @@ struct intel_atomic_state { struct skl_wm_values wm_results; struct i915_sw_fence commit_ready; + + struct llist_node freed; }; struct intel_plane_state { @@ -1485,6 +1487,8 @@ bool __intel_dp_read_desc(struct intel_dp *intel_dp, bool intel_dp_read_desc(struct intel_dp *intel_dp); int intel_dp_link_required(int pixel_clock, int bpp); int intel_dp_max_data_rate(int max_link_clock, int max_lanes); +bool intel_digital_port_connected(struct drm_i915_private *dev_priv, + struct intel_digital_port *port); /* intel_dp_aux_backlight.c */ int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector); diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c index 290384e86c63..d23c0fcff751 100644 --- a/drivers/gpu/drm/i915/intel_gvt.c +++ b/drivers/gpu/drm/i915/intel_gvt.c @@ -67,6 +67,11 @@ int intel_gvt_init(struct drm_i915_private *dev_priv) return 0; } + if (intel_vgpu_active(dev_priv)) { + DRM_DEBUG_DRIVER("GVT-g is disabled for guest\n"); + goto bail; + } + if (!is_supported_device(dev_priv)) { DRM_DEBUG_DRIVER("Unsupported device. GVT-g is disabled\n"); goto bail; diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 432ee495dec2..ebf8023d21e6 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -360,7 +360,8 @@ execlists_update_context_pdps(struct i915_hw_ppgtt *ppgtt, u32 *reg_state) static u64 execlists_update_context(struct drm_i915_gem_request *rq) { struct intel_context *ce = &rq->ctx->engine[rq->engine->id]; - struct i915_hw_ppgtt *ppgtt = rq->ctx->ppgtt; + struct i915_hw_ppgtt *ppgtt = + rq->ctx->ppgtt ?: rq->i915->mm.aliasing_ppgtt; u32 *reg_state = ce->lrc_reg_state; reg_state[CTX_RING_TAIL+1] = rq->tail; @@ -1389,7 +1390,20 @@ static void reset_common_ring(struct intel_engine_cs *engine, { struct drm_i915_private *dev_priv = engine->i915; struct execlist_port *port = engine->execlist_port; - struct intel_context *ce = &request->ctx->engine[engine->id]; + struct intel_context *ce; + + /* If the request was innocent, we leave the request in the ELSP + * and will try to replay it on restarting. The context image may + * have been corrupted by the reset, in which case we may have + * to service a new GPU hang, but more likely we can continue on + * without impact. + * + * If the request was guilty, we presume the context is corrupt + * and have to at least restore the RING register in the context + * image back to the expected values to skip over the guilty request. + */ + if (!request || request->fence.error != -EIO) + return; /* We want a simple context + ring to execute the breadcrumb update. * We cannot rely on the context being intact across the GPU hang, @@ -1398,6 +1412,7 @@ static void reset_common_ring(struct intel_engine_cs *engine, * future request will be after userspace has had the opportunity * to recreate its own state. */ + ce = &request->ctx->engine[engine->id]; execlists_init_reg_state(ce->lrc_reg_state, request->ctx, engine, ce->ring); diff --git a/drivers/gpu/drm/i915/intel_lspcon.c b/drivers/gpu/drm/i915/intel_lspcon.c index f6d4e6940257..c300647ef604 100644 --- a/drivers/gpu/drm/i915/intel_lspcon.c +++ b/drivers/gpu/drm/i915/intel_lspcon.c @@ -158,6 +158,8 @@ static bool lspcon_probe(struct intel_lspcon *lspcon) static void lspcon_resume_in_pcon_wa(struct intel_lspcon *lspcon) { struct intel_dp *intel_dp = lspcon_to_intel_dp(lspcon); + struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); unsigned long start = jiffies; if (!lspcon->desc_valid) @@ -173,7 +175,8 @@ static void lspcon_resume_in_pcon_wa(struct intel_lspcon *lspcon) if (!__intel_dp_read_desc(intel_dp, &desc)) return; - if (!memcmp(&intel_dp->desc, &desc, sizeof(desc))) { + if (intel_digital_port_connected(dev_priv, dig_port) && + !memcmp(&intel_dp->desc, &desc, sizeof(desc))) { DRM_DEBUG_KMS("LSPCON recovering in PCON mode after %u ms\n", jiffies_to_msecs(jiffies - start)); return; diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c index f4429f67a4e3..4a862a358c70 100644 --- a/drivers/gpu/drm/i915/intel_opregion.c +++ b/drivers/gpu/drm/i915/intel_opregion.c @@ -982,7 +982,18 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv) opregion->vbt_size = vbt_size; } else { vbt = base + OPREGION_VBT_OFFSET; - vbt_size = OPREGION_ASLE_EXT_OFFSET - OPREGION_VBT_OFFSET; + /* + * The VBT specification says that if the ASLE ext + * mailbox is not used its area is reserved, but + * on some CHT boards the VBT extends into the + * ASLE ext area. Allow this even though it is + * against the spec, so we do not end up rejecting + * the VBT on those boards (and end up not finding the + * LCD panel because of this). + */ + vbt_size = (mboxes & MBOX_ASLE_EXT) ? + OPREGION_ASLE_EXT_OFFSET : OPREGION_SIZE; + vbt_size -= OPREGION_VBT_OFFSET; if (intel_bios_is_valid_vbt(vbt, vbt_size)) { DRM_DEBUG_KMS("Found valid VBT in ACPI OpRegion (Mailbox #4)\n"); opregion->vbt = vbt; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 69035e4f9b3b..91bc4abf5d3e 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -599,10 +599,62 @@ out: static void reset_ring_common(struct intel_engine_cs *engine, struct drm_i915_gem_request *request) { - struct intel_ring *ring = request->ring; + /* Try to restore the logical GPU state to match the continuation + * of the request queue. If we skip the context/PD restore, then + * the next request may try to execute assuming that its context + * is valid and loaded on the GPU and so may try to access invalid + * memory, prompting repeated GPU hangs. + * + * If the request was guilty, we still restore the logical state + * in case the next request requires it (e.g. the aliasing ppgtt), + * but skip over the hung batch. + * + * If the request was innocent, we try to replay the request with + * the restored context. + */ + if (request) { + struct drm_i915_private *dev_priv = request->i915; + struct intel_context *ce = &request->ctx->engine[engine->id]; + struct i915_hw_ppgtt *ppgtt; + + /* FIXME consider gen8 reset */ + + if (ce->state) { + I915_WRITE(CCID, + i915_ggtt_offset(ce->state) | + BIT(8) /* must be set! */ | + CCID_EXTENDED_STATE_SAVE | + CCID_EXTENDED_STATE_RESTORE | + CCID_EN); + } - ring->head = request->postfix; - ring->last_retired_head = -1; + ppgtt = request->ctx->ppgtt ?: engine->i915->mm.aliasing_ppgtt; + if (ppgtt) { + u32 pd_offset = ppgtt->pd.base.ggtt_offset << 10; + + I915_WRITE(RING_PP_DIR_DCLV(engine), PP_DIR_DCLV_2G); + I915_WRITE(RING_PP_DIR_BASE(engine), pd_offset); + + /* Wait for the PD reload to complete */ + if (intel_wait_for_register(dev_priv, + RING_PP_DIR_BASE(engine), + BIT(0), 0, + 10)) + DRM_ERROR("Wait for reload of ppgtt page-directory timed out\n"); + + ppgtt->pd_dirty_rings &= ~intel_engine_flag(engine); + } + + /* If the rq hung, jump to its breadcrumb and skip the batch */ + if (request->fence.error == -EIO) { + struct intel_ring *ring = request->ring; + + ring->head = request->postfix; + ring->last_retired_head = -1; + } + } else { + engine->legacy_active_context = NULL; + } } static int intel_ring_workarounds_emit(struct drm_i915_gem_request *req) diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index 45dceb672e20..4b7b92a7bcf7 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -255,8 +255,8 @@ static int imx_drm_bind(struct device *dev) * this value would be used to check framebuffer size limitation * at drm_mode_addfb(). */ - drm->mode_config.min_width = 64; - drm->mode_config.min_height = 64; + drm->mode_config.min_width = 1; + drm->mode_config.min_height = 1; drm->mode_config.max_width = 4096; drm->mode_config.max_height = 4096; drm->mode_config.funcs = &imx_drm_mode_config_funcs; diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c index 8f8aa4a63122..4826bb781723 100644 --- a/drivers/gpu/drm/imx/imx-tve.c +++ b/drivers/gpu/drm/imx/imx-tve.c @@ -98,6 +98,8 @@ /* TVE_TST_MODE_REG */ #define TVE_TVDAC_TEST_MODE_MASK (0x7 << 0) +#define IMX_TVE_DAC_VOLTAGE 2750000 + enum { TVE_MODE_TVOUT, TVE_MODE_VGA, @@ -616,9 +618,8 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data) tve->dac_reg = devm_regulator_get(dev, "dac"); if (!IS_ERR(tve->dac_reg)) { - ret = regulator_set_voltage(tve->dac_reg, 2750000, 2750000); - if (ret) - return ret; + if (regulator_get_voltage(tve->dac_reg) != IMX_TVE_DAC_VOLTAGE) + dev_warn(dev, "dac voltage is not %d uV\n", IMX_TVE_DAC_VOLTAGE); ret = regulator_enable(tve->dac_reg); if (ret) return ret; diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index 7f78da695dff..5b8e23d051f2 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -72,3 +72,10 @@ config DRM_MSM_DSI_28NM_8960_PHY help Choose this option if the 28nm DSI PHY 8960 variant is used on the platform. + +config DRM_MSM_DSI_14NM_PHY + bool "Enable DSI 14nm PHY driver in MSM DRM (used by MSM8996/APQ8096)" + depends on DRM_MSM_DSI + default y + help + Choose this option if DSI PHY on 8996 is used on the platform. diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 028c24df2291..39055362da95 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -76,11 +76,13 @@ msm-$(CONFIG_DRM_MSM_DSI) += dsi/dsi.o \ msm-$(CONFIG_DRM_MSM_DSI_28NM_PHY) += dsi/phy/dsi_phy_28nm.o msm-$(CONFIG_DRM_MSM_DSI_20NM_PHY) += dsi/phy/dsi_phy_20nm.o msm-$(CONFIG_DRM_MSM_DSI_28NM_8960_PHY) += dsi/phy/dsi_phy_28nm_8960.o +msm-$(CONFIG_DRM_MSM_DSI_14NM_PHY) += dsi/phy/dsi_phy_14nm.o ifeq ($(CONFIG_DRM_MSM_DSI_PLL),y) msm-y += dsi/pll/dsi_pll.o msm-$(CONFIG_DRM_MSM_DSI_28NM_PHY) += dsi/pll/dsi_pll_28nm.o msm-$(CONFIG_DRM_MSM_DSI_28NM_8960_PHY) += dsi/pll/dsi_pll_28nm_8960.o +msm-$(CONFIG_DRM_MSM_DSI_14NM_PHY) += dsi/pll/dsi_pll_14nm.o endif obj-$(CONFIG_DRM_MSM) += msm.o diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index b8647198c11c..4414cf73735d 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -12,6 +12,7 @@ */ #include "msm_gem.h" +#include "msm_mmu.h" #include "a5xx_gpu.h" extern bool hang_debug; @@ -327,7 +328,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) /* Enable RBBM error reporting bits */ gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL0, 0x00000001); - if (adreno_gpu->quirks & ADRENO_QUIRK_FAULT_DETECT_MASK) { + if (adreno_gpu->info->quirks & ADRENO_QUIRK_FAULT_DETECT_MASK) { /* * Mask out the activity signals from RB1-3 to avoid false * positives @@ -381,7 +382,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, (0x400 << 11 | 0x300 << 22)); - if (adreno_gpu->quirks & ADRENO_QUIRK_TWO_PASS_USE_WFI) + if (adreno_gpu->info->quirks & ADRENO_QUIRK_TWO_PASS_USE_WFI) gpu_rmw(gpu, REG_A5XX_PC_DBG_ECO_CNTL, 0, (1 << 8)); gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, 0xc0200100); @@ -573,6 +574,19 @@ static bool a5xx_idle(struct msm_gpu *gpu) return true; } +static int a5xx_fault_handler(void *arg, unsigned long iova, int flags) +{ + struct msm_gpu *gpu = arg; + pr_warn_ratelimited("*** gpu fault: iova=%08lx, flags=%d (%u,%u,%u,%u)\n", + iova, flags, + gpu_read(gpu, REG_A5XX_CP_SCRATCH_REG(4)), + gpu_read(gpu, REG_A5XX_CP_SCRATCH_REG(5)), + gpu_read(gpu, REG_A5XX_CP_SCRATCH_REG(6)), + gpu_read(gpu, REG_A5XX_CP_SCRATCH_REG(7))); + + return -EFAULT; +} + static void a5xx_cp_err_irq(struct msm_gpu *gpu) { u32 status = gpu_read(gpu, REG_A5XX_CP_INTERRUPT_STATUS); @@ -884,5 +898,8 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) return ERR_PTR(ret); } + if (gpu->aspace) + msm_mmu_set_fault_handler(gpu->aspace->mmu, gpu, a5xx_fault_handler); + return gpu; } diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 893eb2b2531b..ece39b16a864 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -75,12 +75,14 @@ static const struct adreno_info gpulist[] = { .gmem = (SZ_1M + SZ_512K), .init = a4xx_gpu_init, }, { - .rev = ADRENO_REV(5, 3, 0, ANY_ID), + .rev = ADRENO_REV(5, 3, 0, 2), .revn = 530, .name = "A530", .pm4fw = "a530_pm4.fw", .pfpfw = "a530_pfp.fw", .gmem = SZ_1M, + .quirks = ADRENO_QUIRK_TWO_PASS_USE_WFI | + ADRENO_QUIRK_FAULT_DETECT_MASK, .init = a5xx_gpu_init, .gpmufw = "a530v3_gpmu.fw2", }, @@ -181,22 +183,51 @@ static void set_gpu_pdev(struct drm_device *dev, priv->gpu_pdev = pdev; } -static const struct { - const char *str; - uint32_t flag; -} quirks[] = { - { "qcom,gpu-quirk-two-pass-use-wfi", ADRENO_QUIRK_TWO_PASS_USE_WFI }, - { "qcom,gpu-quirk-fault-detect-mask", ADRENO_QUIRK_FAULT_DETECT_MASK }, -}; +static int find_chipid(struct device *dev, u32 *chipid) +{ + struct device_node *node = dev->of_node; + const char *compat; + int ret; + + /* first search the compat strings for qcom,adreno-XYZ.W: */ + ret = of_property_read_string_index(node, "compatible", 0, &compat); + if (ret == 0) { + unsigned rev, patch; + + if (sscanf(compat, "qcom,adreno-%u.%u", &rev, &patch) == 2) { + *chipid = 0; + *chipid |= (rev / 100) << 24; /* core */ + rev %= 100; + *chipid |= (rev / 10) << 16; /* major */ + rev %= 10; + *chipid |= rev << 8; /* minor */ + *chipid |= patch; + + return 0; + } + } |