diff options
| author | Dave Airlie <airlied@redhat.com> | 2021-07-21 11:58:26 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2021-07-21 11:58:28 +1000 |
| commit | 588b3eee528873d73bf777f329d35b2e65e24777 (patch) | |
| tree | 5c93b3d1c08f208fb959bfbffa584b00175e3910 | |
| parent | b4d7049acebf959e80d11611cd104bc5360fd13b (diff) | |
| parent | 17a1837d07be38d957af453e08788edbe1f9343a (diff) | |
Merge tag 'drm-misc-next-2021-07-16' of git://anongit.freedesktop.org/drm/drm-misc into drm-next
drm-misc-next for v5.15:
UAPI Changes:
Cross-subsystem Changes:
- udmabuf: Add support for mapping hugepages
- Add dma-buf stats to sysfs.
- Assorted fixes to fbdev/omap2.
- dma-buf: Document DMA_BUF_IOCTL_SYNC
- Improve dma-buf non-dynamic exporter expectations better.
- Add module parameters for dma-buf size and list limit.
- Add HDMI codec support to vc4, to replace vc4's own codec.
- Document dma-buf implicit fencing rules.
- dma_resv_test_signaled test_all handling.
Core Changes:
- Extract i915's eDP backlight code into DRM helpers.
- Assorted docbook updates.
- Rework drm_dp_aux documentation.
- Add support for the DP aux bus.
- Shrink dma-fence-chain slightly.
- Add alloc/free helpers for dma-fence-chain.
- Assorted fixes to TTM., drm/of, bridge
- drm_gem_plane_helper_prepare/cleanup_fb is now the default for gem drivers.
- Small fix for scheduler completion.
- Remove use of drm_device.irq_enabled.
- Print the driver name to dmesg when registering framebuffer.
- Export drm/gem's shadow plane handling, and use it in vkms.
- Assorted small fixes.
Driver Changes:
- Add eDP backlight to nouveau.
- Assorted fixes and cleanups to nouveau, panfrost, vmwgfx, anx7625,
amdgpu, gma500, radeon, mgag200, vgem, vc4, vkms, omapdrm.
- Add support for Samsung DB7430, Samsung ATNA33XC20, EDT ETMV570G2DHU,
EDT ETM0350G0DH6, Innolux EJ030NA panels.
- Fix some simple pannels missing bus_format and connector types.
- Add mks-guest-stats instrumentation support to vmwgfx.
- Merge i915-ttm topic branch.
- Make s6e63m0 panel use Mipi-DBI helpers.
- Add detect() supoprt for AST.
- Use interrupts for hotplug on vc4.
- vmwgfx is now moved to drm-misc-next, as sroland is no longer a maintainer for now.
- vmwgfx now uses copies of vmware's internal device headers.
- Slowly convert ti-sn65dsi83 over to atomic.
- Rework amdgpu dma-resv handling.
- Fix virtio fencing for planes.
- Ensure amdgpu can always evict to SYSTEM.
- Many drivers fixed for implicit fencing rules.
- Set default prepare/cleanup fb for tiny, vram and simple helpers too.
- Rework panfrost gpu reset and related serialization.
- Update VKMS todo list.
- Make bochs a tiny gpu driver, and use vram helper.
- Use linux irq interfaces instead of drm_irq in some drivers.
- Add support for Raspberry Pi Pico to GUD.
Signed-off-by: Dave Airlie <airlied@redhat.com>
# gpg: Signature made Fri 16 Jul 2021 21:06:04 AEST
# gpg: using RSA key B97BD6A80CAC4981091AE547FE558C72A67013C3
# gpg: Good signature from "Maarten Lankhorst <maarten.lankhorst@linux.intel.com>" [expired]
# gpg: aka "Maarten Lankhorst <maarten@debian.org>" [expired]
# gpg: aka "Maarten Lankhorst <maarten.lankhorst@canonical.com>" [expired]
# gpg: Note: This key has expired!
# Primary key fingerprint: B97B D6A8 0CAC 4981 091A E547 FE55 8C72 A670 13C3
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/444811c3-cbec-e9d5-9a6b-9632eda7962a@linux.intel.com
279 files changed, 16328 insertions, 14206 deletions
diff --git a/Documentation/ABI/testing/sysfs-kernel-dmabuf-buffers b/Documentation/ABI/testing/sysfs-kernel-dmabuf-buffers new file mode 100644 index 000000000000..a243984ed420 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-dmabuf-buffers @@ -0,0 +1,52 @@ +What: /sys/kernel/dmabuf/buffers +Date: May 2021 +KernelVersion: v5.13 +Contact: Hridya Valsaraju <hridya@google.com> +Description: The /sys/kernel/dmabuf/buffers directory contains a + snapshot of the internal state of every DMA-BUF. + /sys/kernel/dmabuf/buffers/<inode_number> will contain the + statistics for the DMA-BUF with the unique inode number + <inode_number> +Users: kernel memory tuning/debugging tools + +What: /sys/kernel/dmabuf/buffers/<inode_number>/exporter_name +Date: May 2021 +KernelVersion: v5.13 +Contact: Hridya Valsaraju <hridya@google.com> +Description: This file is read-only and contains the name of the exporter of + the DMA-BUF. + +What: /sys/kernel/dmabuf/buffers/<inode_number>/size +Date: May 2021 +KernelVersion: v5.13 +Contact: Hridya Valsaraju <hridya@google.com> +Description: This file is read-only and specifies the size of the DMA-BUF in + bytes. + +What: /sys/kernel/dmabuf/buffers/<inode_number>/attachments +Date: May 2021 +KernelVersion: v5.13 +Contact: Hridya Valsaraju <hridya@google.com> +Description: This directory will contain subdirectories representing every + attachment of the DMA-BUF. + +What: /sys/kernel/dmabuf/buffers/<inode_number>/attachments/<attachment_uid> +Date: May 2021 +KernelVersion: v5.13 +Contact: Hridya Valsaraju <hridya@google.com> +Description: This directory will contain information on the attached device + and the number of current distinct device mappings. + +What: /sys/kernel/dmabuf/buffers/<inode_number>/attachments/<attachment_uid>/device +Date: May 2021 +KernelVersion: v5.13 +Contact: Hridya Valsaraju <hridya@google.com> +Description: This file is read-only and is a symlink to the attached device's + sysfs entry. + +What: /sys/kernel/dmabuf/buffers/<inode_number>/attachments/<attachment_uid>/map_counter +Date: May 2021 +KernelVersion: v5.13 +Contact: Hridya Valsaraju <hridya@google.com> +Description: This file is read-only and contains a map_counter indicating the + number of distinct device mappings of the attachment. diff --git a/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi86.yaml b/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi86.yaml index 26932d2e86ab..1c2daf7c24cc 100644 --- a/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi86.yaml +++ b/Documentation/devicetree/bindings/display/bridge/ti,sn65dsi86.yaml @@ -70,6 +70,9 @@ properties: const: 1 description: See ../../pwm/pwm.yaml for description of the cell formats. + aux-bus: + $ref: /schemas/display/dp-aux-bus.yaml# + ports: $ref: /schemas/graph.yaml#/properties/ports @@ -150,7 +153,6 @@ properties: required: - compatible - reg - - enable-gpios - vccio-supply - vpll-supply - vcca-supply @@ -201,11 +203,26 @@ examples: port@1 { reg = <1>; - endpoint { + sn65dsi86_out: endpoint { remote-endpoint = <&panel_in_edp>; }; }; }; + + aux-bus { + panel { + compatible = "boe,nv133fhm-n62"; + power-supply = <&pp3300_dx_edp>; + backlight = <&backlight>; + hpd-gpios = <&sn65dsi86_bridge 2 GPIO_ACTIVE_HIGH>; + + port { + panel_in_edp: endpoint { + remote-endpoint = <&sn65dsi86_out>; + }; + }; + }; + }; }; }; - | diff --git a/Documentation/devicetree/bindings/display/dp-aux-bus.yaml b/Documentation/devicetree/bindings/display/dp-aux-bus.yaml new file mode 100644 index 000000000000..5e4afe9f98fb --- /dev/null +++ b/Documentation/devicetree/bindings/display/dp-aux-bus.yaml @@ -0,0 +1,37 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/dp-aux-bus.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: DisplayPort AUX bus + +maintainers: + - Douglas Anderson <dianders@chromium.org> + +description: + DisplayPort controllers provide a control channel to the sinks that + are hooked up to them. This is the DP AUX bus. Over the DP AUX bus + we can query properties about a sink and also configure it. In + particular, DP sinks support DDC over DP AUX which allows tunneling + a standard I2C DDC connection over the AUX channel. + + To model this relationship, DP sinks should be placed as children + of the DP controller under the "aux-bus" node. + + At the moment, this binding only handles the eDP case. It is + possible it will be extended in the future to handle the DP case. + For DP, presumably a connector would be listed under the DP AUX + bus instead of a panel. + +properties: + $nodename: + const: "aux-bus" + + panel: + $ref: panel/panel-common.yaml# + +additionalProperties: false + +required: + - panel diff --git a/Documentation/devicetree/bindings/display/panel/innolux,ej030na.yaml b/Documentation/devicetree/bindings/display/panel/innolux,ej030na.yaml new file mode 100644 index 000000000000..cda36c04e85c --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/innolux,ej030na.yaml @@ -0,0 +1,62 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/innolux,ej030na.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Innolux EJ030NA 3.0" (320x480 pixels) 24-bit TFT LCD panel + +description: | + The panel must obey the rules for a SPI slave device as specified in + spi/spi-controller.yaml + +maintainers: + - Paul Cercueil <paul@crapouillou.net> + +allOf: + - $ref: panel-common.yaml# + +properties: + compatible: + const: innolux,ej030na + + backlight: true + port: true + power-supply: true + reg: true + reset-gpios: true + +required: + - compatible + - reg + - power-supply + - reset-gpios + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + + spi { + #address-cells = <1>; + #size-cells = <0>; + + panel@0 { + compatible = "innolux,ej030na"; + reg = <0>; + + spi-max-frequency = <10000000>; + + reset-gpios = <&gpe 4 GPIO_ACTIVE_LOW>; + power-supply = <&lcd_power>; + + backlight = <&backlight>; + + port { + panel_input: endpoint { + remote-endpoint = <&panel_output>; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml index b3797ba2698b..3624363938dd 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-simple.yaml +++ b/Documentation/devicetree/bindings/display/panel/panel-simple.yaml @@ -110,6 +110,9 @@ properties: # Emerging Display Technology Corp. 5.7" VGA TFT LCD panel - edt,et057090dhu - edt,et070080dh6 + # Emerging Display Technology Corp. 3.5" WVGA TFT LCD panel with + # capacitive multitouch + - edt,etm0350g0dh6 # Emerging Display Technology Corp. 480x272 TFT Display with capacitive touch - edt,etm043080dh6gp # Emerging Display Technology Corp. 480x272 TFT Display @@ -128,6 +131,9 @@ properties: # Emerging Display Technology Corp. WVGA TFT Display with capacitive touch - edt,etm0700g0dh6 - edt,etm0700g0edh6 + # Emerging Display Technology Corp. 5.7" VGA TFT LCD panel with + # capacitive touch + - edt,etmv570g2dhu # Evervision Electronics Co. Ltd. VGG804821 5.0" WVGA TFT LCD Panel - evervision,vgg804821 # Foxlink Group 5" WVGA TFT LCD panel @@ -242,6 +248,8 @@ properties: - rocktech,rk101ii01d-ct # Rocktech Display Ltd. RK070ER9427 800(RGB)x480 TFT LCD panel - rocktech,rk070er9427 + # Samsung 13.3" FHD (1920x1080 pixels) eDP AMOLED panel + - samsung,atna33xc20 # Samsung 12.2" (2560x1600 pixels) TFT LCD panel - samsung,lsn122dl01-c01 # Samsung Electronics 10.1" WSVGA TFT LCD panel @@ -298,6 +306,8 @@ properties: enable-gpios: true port: true power-supply: true + no-hpd: true + hpd-gpios: true additionalProperties: false diff --git a/Documentation/devicetree/bindings/display/panel/samsung,lms397kf04.yaml b/Documentation/devicetree/bindings/display/panel/samsung,lms397kf04.yaml index 4cb75a5f2e3a..cd62968426fb 100644 --- a/Documentation/devicetree/bindings/display/panel/samsung,lms397kf04.yaml +++ b/Documentation/devicetree/bindings/display/panel/samsung,lms397kf04.yaml @@ -33,8 +33,11 @@ properties: backlight: true + spi-cpha: true + + spi-cpol: true + spi-max-frequency: - $ref: /schemas/types.yaml#/definitions/uint32 description: inherited as a SPI client node, the datasheet specifies maximum 300 ns minimum cycle which gives around 3 MHz max frequency maximum: 3000000 @@ -44,6 +47,9 @@ properties: required: - compatible - reg + - spi-cpha + - spi-cpol + - port additionalProperties: false @@ -52,15 +58,23 @@ examples: #include <dt-bindings/gpio/gpio.h> spi { + compatible = "spi-gpio"; + sck-gpios = <&gpio 0 GPIO_ACTIVE_HIGH>; + miso-gpios = <&gpio 1 GPIO_ACTIVE_HIGH>; + mosi-gpios = <&gpio 2 GPIO_ACTIVE_HIGH>; + cs-gpios = <&gpio 3 GPIO_ACTIVE_HIGH>; + num-chipselects = <1>; #address-cells = <1>; #size-cells = <0>; panel@0 { compatible = "samsung,lms397kf04"; spi-max-frequency = <3000000>; + spi-cpha; + spi-cpol; reg = <0>; vci-supply = <&lcd_3v0_reg>; vccio-supply = <&lcd_1v8_reg>; - reset-gpios = <&gpio 1 GPIO_ACTIVE_LOW>; + reset-gpios = <&gpio 4 GPIO_ACTIVE_LOW>; backlight = <&ktd259>; port { diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst index 7f21425d9435..f5ac4c90b237 100644 --- a/Documentation/driver-api/dma-buf.rst +++ b/Documentation/driver-api/dma-buf.rst @@ -88,6 +88,9 @@ consider though: - The DMA buffer FD is also pollable, see `Implicit Fence Poll Support`_ below for details. +- The DMA buffer FD also supports a few dma-buf-specific ioctls, see + `DMA Buffer ioctls`_ below for details. + Basic Operation and Device DMA Access ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -106,6 +109,16 @@ Implicit Fence Poll Support .. kernel-doc:: drivers/dma-buf/dma-buf.c :doc: implicit fence polling +DMA-BUF statistics +~~~~~~~~~~~~~~~~~~ +.. kernel-doc:: drivers/dma-buf/dma-buf-sysfs-stats.c + :doc: overview + +DMA Buffer ioctls +~~~~~~~~~~~~~~~~~ + +.. kernel-doc:: include/uapi/linux/dma-buf.h + Kernel Functions and Structures Reference ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/gpu/drm-uapi.rst b/Documentation/gpu/drm-uapi.rst index 04bdc7a91d53..7e51dd40bf6e 100644 --- a/Documentation/gpu/drm-uapi.rst +++ b/Documentation/gpu/drm-uapi.rst @@ -457,6 +457,19 @@ Userspace API Structures .. kernel-doc:: include/uapi/drm/drm_mode.h :doc: overview +.. _crtc_index: + +CRTC index +---------- + +CRTC's have both an object ID and an index, and they are not the same thing. +The index is used in cases where a densely packed identifier for a CRTC is +needed, for instance a bitmask of CRTC's. The member possible_crtcs of struct +drm_mode_get_plane is an example. + +DRM_IOCTL_MODE_GETRESOURCES populates a structure with an array of CRTC ID's, +and the CRTC index is its position in this array. + .. kernel-doc:: include/uapi/drm/drm.h :internal: diff --git a/Documentation/gpu/vkms.rst b/Documentation/gpu/vkms.rst index 2c9b376da5ca..941f0e7e5eef 100644 --- a/Documentation/gpu/vkms.rst +++ b/Documentation/gpu/vkms.rst @@ -98,9 +98,17 @@ with VKMS maintainers. IGT better support ------------------ -- Investigate: (1) test cases on kms_plane that are failing due to timeout on - capturing CRC; (2) when running kms_flip test cases in sequence, some - successful individual test cases are failing randomly. +Debugging: + +- kms_plane: some test cases are failing due to timeout on capturing CRC; + +- kms_flip: when running test cases in sequence, some successful individual + test cases are failing randomly; when individually, some successful test + cases display in the log the following error:: + + [drm:vkms_prepare_fb [vkms]] ERROR vmap failed: -4 + +Virtual hardware (vblank-less) mode: - VKMS already has support for vblanks simulated via hrtimers, which can be tested with kms_flip test; in some way, we can say that VKMS already mimics @@ -116,7 +124,17 @@ Add Plane Features There's lots of plane features we could add support for: -- Real overlay planes, not just cursor. +- Multiple overlay planes. [Good to get started] + +- Clearing primary plane: clear primary plane before plane composition (at the + start) for correctness of pixel blend ops. It also guarantees alpha channel + is cleared in the target buffer for stable crc. [Good to get started] + +- ARGB format on primary plane: blend the primary plane into background with + translucent alpha. + +- Support when the primary plane isn't exactly matching the output size: blend + the primary plane into the black background. - Full alpha blending on all planes. @@ -129,13 +147,8 @@ There's lots of plane features we could add support for: cursor api). For all of these, we also want to review the igt test coverage and make sure -all relevant igt testcases work on vkms. - -Prime Buffer Sharing --------------------- - -- Syzbot report - WARNING in vkms_gem_free_object: - https://syzkaller.appspot.com/bug?extid=e7ad70d406e74d8fc9d0 +all relevant igt testcases work on vkms. They are good options for internship +project. Runtime Configuration --------------------- @@ -153,7 +166,7 @@ module. Use/Test-cases: the refresh rate. The currently proposed solution is to expose vkms configuration through -configfs. All existing module options should be supported through configfs +configfs. All existing module options should be supported through configfs too. Writeback support @@ -162,6 +175,7 @@ Writeback support - The writeback and CRC capture operations share the use of composer_enabled boolean to ensure vblanks. Probably, when these operations work together, composer_enabled needs to refcounting the composer state to proper work. + [Good to get started] - Add support for cloned writeback outputs and related test cases using a cloned output in the IGT kms_writeback. diff --git a/MAINTAINERS b/MAINTAINERS index 6c8be735cc91..830816c5fea5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5770,7 +5770,7 @@ M: Gerd Hoffmann <kraxel@redhat.com> L: virtualization@lists.linux-foundation.org S: Maintained T: git git://anongit.freedesktop.org/drm/drm-misc -F: drivers/gpu/drm/bochs/ +F: drivers/gpu/drm/tiny/bochs.c DRM DRIVER FOR BOE HIMAX8279D PANELS M: Jerry Han <hanxu5@huaqin.corp-partner.google.com> @@ -5955,6 +5955,13 @@ S: Maintained F: Documentation/devicetree/bindings/display/panel/raydium,rm67191.yaml F: drivers/gpu/drm/panel/panel-raydium-rm67191.c +DRM DRIVER FOR SAMSUNG DB7430 PANELS +M: Linus Walleij <linus.walleij@linaro.org> +S: Maintained +T: git git://anongit.freedesktop.org/drm/drm-misc +F: Documentation/devicetree/bindings/display/panel/samsung,lms397kf04.yaml +F: drivers/gpu/drm/panel/panel-samsung-db7430.c + DRM DRIVER FOR SITRONIX ST7703 PANELS M: Guido Günther <agx@sigxcpu.org> R: Purism Kernel Team <kernel@puri.sm> @@ -6053,11 +6060,10 @@ F: drivers/gpu/drm/vboxvideo/ DRM DRIVER FOR VMWARE VIRTUAL GPU M: "VMware Graphics" <linux-graphics-maintainer@vmware.com> -M: Roland Scheidegger <sroland@vmware.com> M: Zack Rusin <zackr@vmware.com> L: dri-devel@lists.freedesktop.org S: Supported -T: git git://people.freedesktop.org/~sroland/linux +T: git git://anongit.freedesktop.org/drm/drm-misc F: drivers/gpu/drm/vmwgfx/ F: include/uapi/drm/vmwgfx_drm.h diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi index 77ae7561d436..781625d9344c 100644 --- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi @@ -255,21 +255,6 @@ #sound-dai-cells = <0>; }; - panel: panel { - /* Compatible will be filled in per-board */ - power-supply = <&pp3300_dx_edp>; - backlight = <&backlight>; - hpd-gpios = <&sn65dsi86_bridge 2 GPIO_ACTIVE_HIGH>; - - ports { - port { - panel_in_edp: endpoint { - remote-endpoint = <&sn65dsi86_out>; - }; - }; - }; - }; - pwmleds { compatible = "pwm-leds"; keyboard_backlight: keyboard-backlight { @@ -666,6 +651,21 @@ edp_brij_i2c: &i2c2 { }; }; }; + + aux-bus { + panel: panel { + /* Compatible will be filled in per-board */ + power-supply = <&pp3300_dx_edp>; + backlight = <&backlight>; + hpd-gpios = <&sn65dsi86_bridge 2 GPIO_ACTIVE_HIGH>; + + port { + panel_in_edp: endpoint { + remote-endpoint = <&sn65dsi86_out>; + }; + }; + }; + }; }; }; diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig index 4e16c71c24b7..9561e3d2d428 100644 --- a/drivers/dma-buf/Kconfig +++ b/drivers/dma-buf/Kconfig @@ -72,6 +72,17 @@ menuconfig DMABUF_HEAPS allows userspace to allocate dma-bufs that can be shared between drivers. +menuconfig DMABUF_SYSFS_STATS + bool "DMA-BUF sysfs statistics" + select DMA_SHARED_BUFFER + help + Choose this option to enable DMA-BUF sysfs statistics + in location /sys/kernel/dmabuf/buffers. + + /sys/kernel/dmabuf/buffers/<inode_number> will contain + statistics for the DMA-BUF with the unique inode number + <inode_number>. + source "drivers/dma-buf/heaps/Kconfig" endmenu diff --git a/drivers/dma-buf/Makefile b/drivers/dma-buf/Makefile index 995e05f609ff..40d81f23cacf 100644 --- a/drivers/dma-buf/Makefile +++ b/drivers/dma-buf/Makefile @@ -6,6 +6,7 @@ obj-$(CONFIG_DMABUF_HEAPS) += heaps/ obj-$(CONFIG_SYNC_FILE) += sync_file.o obj-$(CONFIG_SW_SYNC) += sw_sync.o sync_debug.o obj-$(CONFIG_UDMABUF) += udmabuf.o +obj-$(CONFIG_DMABUF_SYSFS_STATS) += dma-buf-sysfs-stats.o dmabuf_selftests-y := \ selftest.o \ diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.c b/drivers/dma-buf/dma-buf-sysfs-stats.c new file mode 100644 index 000000000000..a2638e84199c --- /dev/null +++ b/drivers/dma-buf/dma-buf-sysfs-stats.c @@ -0,0 +1,337 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * DMA-BUF sysfs statistics. + * + * Copyright (C) 2021 Google LLC. + */ + +#include <linux/dma-buf.h> +#include <linux/dma-resv.h> +#include <linux/kobject.h> +#include <linux/printk.h> +#include <linux/slab.h> +#include <linux/sysfs.h> + +#include "dma-buf-sysfs-stats.h" + +#define to_dma_buf_entry_from_kobj(x) container_of(x, struct dma_buf_sysfs_entry, kobj) + +/** + * DOC: overview + * + * ``/sys/kernel/debug/dma_buf/bufinfo`` provides an overview of every DMA-BUF + * in the system. However, since debugfs is not safe to be mounted in + * production, procfs and sysfs can be used to gather DMA-BUF statistics on + * production systems. + * + * The ``/proc/<pid>/fdinfo/<fd>`` files in procfs can be used to gather + * information about DMA-BUF fds. Detailed documentation about the interface + * is present in Documentation/filesystems/proc.rst. + * + * Unfortunately, the existing procfs interfaces can only provide information + * about the DMA-BUFs for which processes hold fds or have the buffers mmapped + * into their address space. This necessitated the creation of the DMA-BUF sysfs + * statistics interface to provide per-buffer information on production systems. + * + * The interface at ``/sys/kernel/dma-buf/buffers`` exposes information about + * every DMA-BUF when ``CONFIG_DMABUF_SYSFS_STATS`` is enabled. + * + * The following stats are exposed by the interface: + * + * * ``/sys/kernel/dmabuf/buffers/<inode_number>/exporter_name`` + * * ``/sys/kernel/dmabuf/buffers/<inode_number>/size`` + * * ``/sys/kernel/dmabuf/buffers/<inode_number>/attachments/<attach_uid>/device`` + * * ``/sys/kernel/dmabuf/buffers/<inode_number>/attachments/<attach_uid>/map_counter`` + * + * The information in the interface can also be used to derive per-exporter and + * per-device usage statistics. The data from the interface can be gathered + * on error conditions or other important events to provide a snapshot of + * DMA-BUF usage. It can also be collected periodically by telemetry to monitor + * various metrics. + * + * Detailed documentation about the interface is present in + * Documentation/ABI/testing/sysfs-kernel-dmabuf-buffers. + */ + +struct dma_buf_stats_attribute { + struct attribute attr; + ssize_t (*show)(struct dma_buf *dmabuf, + struct dma_buf_stats_attribute *attr, char *buf); +}; +#define to_dma_buf_stats_attr(x) container_of(x, struct dma_buf_stats_attribute, attr) + +static ssize_t dma_buf_stats_attribute_show(struct kobject *kobj, + struct attribute *attr, + char *buf) +{ + struct dma_buf_stats_attribute *attribute; + struct dma_buf_sysfs_entry *sysfs_entry; + struct dma_buf *dmabuf; + + attribute = to_dma_buf_stats_attr(attr); + sysfs_entry = to_dma_buf_entry_from_kobj(kobj); + dmabuf = sysfs_entry->dmabuf; + + if (!dmabuf || !attribute->show) + return -EIO; + + return attribute->show(dmabuf, attribute, buf); +} + +static const struct sysfs_ops dma_buf_stats_sysfs_ops = { + .show = dma_buf_stats_attribute_show, +}; + +static ssize_t exporter_name_show(struct dma_buf *dmabuf, + struct dma_buf_stats_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "%s\n", dmabuf->exp_name); +} + +static ssize_t size_show(struct dma_buf *dmabuf, + struct dma_buf_stats_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "%zu\n", dmabuf->size); +} + +static struct dma_buf_stats_attribute exporter_name_attribute = + __ATTR_RO(exporter_name); +static struct dma_buf_stats_attribute size_attribute = __ATTR_RO(size); + +static struct attribute *dma_buf_stats_default_attrs[] = { + &exporter_name_attribute.attr, + &size_attribute.attr, + NULL, +}; +ATTRIBUTE_GROUPS(dma_buf_stats_default); + +static void dma_buf_sysfs_release(struct kobject *kobj) +{ + struct dma_buf_sysfs_entry *sysfs_entry; + + sysfs_entry = to_dma_buf_entry_from_kobj(kobj); + kfree(sysfs_entry); +} + +static struct kobj_type dma_buf_ktype = { + .sysfs_ops = &dma_buf_stats_sysfs_ops, + .release = dma_buf_sysfs_release, + .default_groups = dma_buf_stats_default_groups, +}; + +#define to_dma_buf_attach_entry_from_kobj(x) container_of(x, struct dma_buf_attach_sysfs_entry, kobj) + +struct dma_buf_attach_stats_attribute { + struct attribute attr; + ssize_t (*show)(struct dma_buf_attach_sysfs_entry *sysfs_entry, + struct dma_buf_attach_stats_attribute *attr, char *buf); +}; +#define to_dma_buf_attach_stats_attr(x) container_of(x, struct dma_buf_attach_stats_attribute, attr) + +static ssize_t dma_buf_attach_stats_attribute_show(struct kobject *kobj, + struct attribute *attr, + char *buf) +{ + struct dma_buf_attach_stats_attribute *attribute; + struct dma_buf_attach_sysfs_entry *sysfs_entry; + + attribute = to_dma_buf_attach_stats_attr(attr); + sysfs_entry = to_dma_buf_attach_entry_from_kobj(kobj); + + if (!attribute->show) + return -EIO; + + return attribute->show(sysfs_entry, attribute, buf); +} + +static const struct sysfs_ops dma_buf_attach_stats_sysfs_ops = { + .show = dma_buf_attach_stats_attribute_show, +}; + +static ssize_t map_counter_show(struct dma_buf_attach_sysfs_entry *sysfs_entry, + struct dma_buf_attach_stats_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "%u\n", sysfs_entry->map_counter); +} + +static struct dma_buf_attach_stats_attribute map_counter_attribute = + __ATTR_RO(map_counter); + +static struct attribute *dma_buf_attach_stats_default_attrs[] = { + &map_counter_attribute.attr, + NULL, +}; +ATTRIBUTE_GROUPS(dma_buf_attach_stats_default); + +static void dma_buf_attach_sysfs_release(struct kobject *kobj) +{ + struct dma_buf_attach_sysfs_entry *sysfs_entry; + + sysfs_entry = to_dma_buf_attach_entry_from_kobj(kobj); + kfree(sysfs_entry); +} + +static struct kobj_type dma_buf_attach_ktype = { + .sysfs_ops = &dma_buf_attach_stats_sysfs_ops, + .release = dma_buf_attach_sysfs_release, + .default_groups = dma_buf_attach_stats_default_groups, +}; + +void dma_buf_attach_stats_teardown(struct dma_buf_attachment *attach) +{ + struct dma_buf_attach_sysfs_entry *sysfs_entry; + + sysfs_entry = attach->sysfs_entry; + if (!sysfs_entry) + return; + + sysfs_delete_link(&sysfs_entry->kobj, &attach->dev->kobj, "device"); + + kobject_del(&sysfs_entry->kobj); + kobject_put(&sysfs_entry->kobj); +} + +int dma_buf_attach_stats_setup(struct dma_buf_attachment *attach, + unsigned int uid) +{ + struct dma_buf_attach_sysfs_entry *sysfs_entry; + int ret; + struct dma_buf *dmabuf; + + if (!attach) + return -EINVAL; + + dmabuf = attach->dmabuf; + + sysfs_entry = kzalloc(sizeof(struct dma_buf_attach_sysfs_entry), + GFP_KERNEL); + if (!sysfs_entry) + return -ENOMEM; + + sysfs_entry->kobj.kset = dmabuf->sysfs_entry->attach_stats_kset; + + attach->sysfs_entry = sysfs_entry; + + ret = kobject_init_and_add(&sysfs_entry->kobj, &dma_buf_attach_ktype, + NULL, "%u", uid); + if (ret) + goto kobj_err; + + ret = sysfs_create_link(&sysfs_entry->kobj, &attach->dev->kobj, + "device"); + if (ret) + goto link_err; + + return 0; + +link_err: + kobject_del(&sysfs_entry->kobj); +kobj_err: + kobject_put(&sysfs_entry->kobj); + attach->sysfs_entry = NULL; + + return ret; +} +void dma_buf_stats_teardown(struct dma_buf *dmabuf) +{ + struct dma_buf_sysfs_entry *sysfs_entry; + + sysfs_entry = dmabuf->sysfs_entry; + if (!sysfs_entry) + return; + + kset_unregister(sysfs_entry->attach_stats_kset); + kobject_del(&sysfs_entry->kobj); + kobject_put(&sysfs_entry->kobj); +} + + +/* Statistics files do not need to send uevents. */ +static int dmabuf_sysfs_uevent_filter(struct kset *kset, struct kobject *kobj) +{ + return 0; +} + +static const struct kset_uevent_ops dmabuf_sysfs_no_uevent_ops = { + .filter = dmabuf_sysfs_uevent_filter, +}; + +static struct kset *dma_buf_stats_kset; +static struct kset *dma_buf_per_buffer_stats_kset; +int dma_buf_init_sysfs_statistics(void) +{ + dma_buf_stats_kset = kset_create_and_add("dmabuf", + &dmabuf_sysfs_no_uevent_ops, + kernel_kobj); + if (!dma_buf_stats_kset) + return -ENOMEM; + + dma_buf_per_buffer_stats_kset = kset_create_and_add("buffers", + &dmabuf_sysfs_no_uevent_ops, + &dma_buf_stats_kset->kobj); + if (!dma_buf_per_buffer_stats_kset) { + kset_unregister(dma_buf_stats_kset); + return -ENOMEM; + } + + return 0; +} + +void dma_buf_uninit_sysfs_statistics(void) +{ + kset_unregister(dma_buf_per_buffer_stats_kset); + kset_unregister(dma_buf_stats_kset); +} + +int dma_buf_stats_setup(struct dma_buf *dmabuf) +{ + struct dma_buf_sysfs_entry *sysfs_entry; + int ret; + struct kset *attach_stats_kset; + + if (!dmabuf || !dmabuf->file) + return -EINVAL; + + if (!dmabuf->exp_name) { + pr_err("exporter name must not be empty if stats needed\n"); + return -EINVAL; + } + + sysfs_entry = kzalloc(sizeof(struct dma_buf_sysfs_entry), GFP_KERNEL); + if (!sysfs_entry) + return -ENOMEM; + + sysfs_entry->kobj.kset = dma_buf_per_buffer_stats_kset; + sysfs_entry->dmabuf = dmabuf; + + dmabuf->sysfs_entry = sysfs_entry; + + /* create the directory for buffer stats */ + ret = kobject_init_and_add(&sysfs_entry->kobj, &dma_buf_ktype, NULL, + "%lu", file_inode(dmabuf->file)->i_ino); + if (ret) + goto err_sysfs_dmabuf; + + /* create the directory for attachment stats */ + attach_stats_kset = kset_create_and_add("attachments", + &dmabuf_sysfs_no_uevent_ops, + &sysfs_entry->kobj); + if (!attach_stats_kset) { + ret = -ENOMEM; + goto err_sysfs_attach; + } + + sysfs_entry->attach_stats_kset = attach_stats_kset; + + return 0; + +err_sysfs_attach: + kobject_del(&sysfs_entry->kobj); +err_sysfs_dmabuf: + kobject_put(&sysfs_entry->kobj); + dmabuf->sysfs_entry = NULL; + return ret; +} diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.h b/drivers/dma-buf/dma-buf-sysfs-stats.h new file mode 100644 index 000000000000..5f4703249117 --- /dev/null +++ b/drivers/dma-buf/dma-buf-sysfs-stats.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * DMA-BUF sysfs statistics. + * + * Copyright (C) 2021 Google LLC. + */ + +#ifndef _DMA_BUF_SYSFS_STATS_H +#define _DMA_BUF_SYSFS_STATS_H + +#ifdef CONFIG_DMABUF_SYSFS_STATS + +int dma_buf_init_sysfs_statistics(void); +void dma_buf_uninit_sysfs_statistics(void); + +int dma_buf_stats_setup(struct dma_buf *dmabuf); +int dma_buf_attach_stats_setup(struct dma_buf_attachment *attach, + unsigned int uid); +static inline void dma_buf_update_attachment_map_count(struct dma_buf_attachment *attach, + int delta) +{ + struct dma_buf_attach_sysfs_entry *entry = attach->sysfs_entry; + + entry->map_counter += delta; +} +void dma_buf_stats_teardown(struct dma_buf *dmabuf); +void dma_buf_attach_stats_teardown(struct dma_buf_attachment *attach); +static inline unsigned int dma_buf_update_attach_uid(struct dma_buf *dmabuf) +{ + struct dma_buf_sysfs_entry *entry = dmabuf->sysfs_entry; + + return entry->attachment_uid++; +} +#else + +static inline int dma_buf_init_sysfs_statistics(void) +{ + return 0; +} + +static inline void dma_buf_uninit_sysfs_statistics(void) {} + +static inline int dma_buf_stats_setup(struct dma_buf *dmabuf) +{ + return 0; +} +static inline int dma_buf_attach_stats_setup(struct dma_buf_attachment *attach, + unsigned int uid) +{ + return 0; +} + +static inline void dma_buf_stats_teardown(struct dma_buf *dmabuf) {} +static inline void dma_buf_attach_stats_teardown(struct dma_buf_attachment *attach) {} +static inline void dma_buf_update_attachment_map_count(struct dma_buf_attachment *attach, + int delta) {} +static inline unsigned int dma_buf_update_attach_uid(struct dma_buf *dmabuf) +{ + return 0; +} +#endif +#endif // _DMA_BUF_SYSFS_STATS_H diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 511fe0d217a0..510b42771974 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -29,6 +29,8 @@ #include <uapi/linux/dma-buf.h> #include <uapi/linux/magic.h> +#include "dma-buf-sysfs-stats.h" + static inline int is_dma_buf_file(struct file *); struct dma_buf_list { @@ -79,6 +81,7 @@ static void dma_buf_release(struct dentry *dentry) if (dmabuf->resv == (struct dma_resv *)&dmabuf[1]) dma_resv_fini(dmabuf->resv); + dma_buf_stats_teardown(dmabuf); module_put(dmabuf->owner); kfree(dmabuf->name); kfree(dmabuf); @@ -580,6 +583,10 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) file->f_mode |= FMODE_LSEEK; dmabuf->file = file; + ret = dma_buf_stats_setup(dmabuf); + if (ret) + goto err_sysfs; + mutex_init(&dmabuf->lock); INIT_LIST_HEAD(&dmabuf->attachments); @@ -589,6 +596,14 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) return dmabuf; +err_sysfs: + /* + * Set file->f_path.dentry->d_fsdata to NULL so that when + * dma_buf_release() gets invoked by dentry_ops, it exits + * early before calling the release() dma_buf op. + */ + file->f_path.dentry->d_fsdata = NULL; + fput(file); err_dmabuf: kfree(dmabuf); err_module: @@ -723,6 +738,7 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, { struct dma_buf_attachment *attach; int ret; + unsigned int attach_uid; if (WARN_ON(!dmabuf || !dev)) return ERR_PTR(-EINVAL); @@ -748,8 +764,13 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, } dma_resv_lock(dmabuf->resv, NULL); list_add(&attach->node, &dmabuf->attachments); + attach_uid = dma_buf_update_attach_uid(dmabuf); dma_resv_unlock(dmabuf->resv); + ret = dma_buf_attach_stats_setup(attach, attach_uid); + if (ret) + goto err_sysfs; + /* When either the importer or the exporter can't handle dynamic * mappings we cache the mapping here to avoid issues with the * reservation object lock. @@ -776,6 +797,7 @@ dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev, dma_resv_unlock(attach->dmabuf->resv); attach->sgt = sgt; attach->dir = DMA_BIDIRECTIONAL; + dma_buf_update_attachment_map_count(attach, 1 /* delta */); } return attach; @@ -792,6 +814,7 @@ err_unlock: if (dma_buf_is_dynamic(attach->dmabuf)) dma_resv_unlock(attach->dmabuf->resv); +err_sysfs: dma_buf_detach(dmabuf, attach); return ERR_PTR(ret); } @@ -841,6 +864,7 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) dma_resv_lock(attach->dmabuf->resv, NULL); __unmap_dma_buf(attach, attach->sgt, attach->dir); + dma_buf_update_attachment_map_count(attach, -1 /* delta */); if (dma_buf_is_dynamic(attach->dmabuf)) { dmabuf->ops->unpin(attach); @@ -854,6 +878,7 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach) if (dmabuf->ops->detach) dmabuf->ops->detach(dmabuf, attach); + dma_buf_attach_stats_teardown(attach); kfree(attach); } EXPORT_SYMBOL_GPL(dma_buf_detach); @@ -926,6 +951,9 @@ EXPORT_SYMBOL_GPL(dma_buf_unpin); * the underlying backing storage is pinned for as long as a mapping exists, * therefore users/importers should not hold onto a mapping for undue amounts of * time. + * + * Important: Dynamic importers must wait for the exclusive fence of the struct + * dma_resv attached to the DMA-BUF first. */ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, enum dma_data_direction direction) @@ -993,6 +1021,9 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach, } #endif /* CONFIG_DMA_API_DEBUG */ + if (!IS_ERR(sg_table)) + dma_buf_update_attachment_map_count(attach, 1 /* delta */); + return sg_table; } EXPORT_SYMBOL_GPL(dma_buf_map_attachment); @@ -1030,6 +1061,8 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach, if (dma_buf_is_dynamic(attach->dmabuf) && !IS_ENABLED(CONFIG_DMABUF_MOVE_NOTIFY)) dma_buf_unpin(attach); + + dma_buf_update_attachment_map_count(attach, -1 /* delta */); } EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment); @@ -1469,6 +1502,12 @@ static inline void dma_buf_uninit_debugfs(void) static int __init dma_buf_init(void) { + int ret; + + ret = dma_buf_init_sysfs_statistics(); + if (ret) + return ret; + dma_buf_mnt = kern_mount(&dma_buf_fs_type); if (IS_ERR(dma_buf_mnt)) return PTR_ERR(dma_buf_mnt); @@ -1484,5 +1523,6 @@ static void __exit dma_buf_deinit(void) { dma_buf_uninit_debugfs(); kern_unmount(dma_buf_mnt); + dma_buf_uninit_sysfs_statistics(); } __exitcall(dma_buf_deinit); diff --git a/drivers/dma-buf/dma-fence-chain.c b/drivers/dma-buf/dma-fence-chain.c index 7d129e68ac70..1b4cb3e5cec9 100644 --- a/drivers/dma-buf/dma-fence-chain.c +++ b/drivers/dma-buf/dma-fence-chain.c @@ -137,6 +137,7 @@ static void dma_fence_chain_cb(struct dma_fence *f, struct dma_fence_cb *cb) struct dma_fence_chain *chain; chain = container_of(cb, typeof(*chain), cb); + init_irq_work(&chain->work, dma_fence_chain_irq_work); irq_work_queue(&chain->work); dma_fence_put(f); } @@ -239,7 +240,6 @@ void dma_fence_chain_init(struct dma_fence_chain *chain, rcu_assign_pointer(chain->prev, prev); chain->fence = fence; chain->prev_seqno = 0; - init_irq_work(&chain->work, dma_fence_chain_irq_work); /* Try to reuse the context of the previous chain node. */ if (prev_chain && __dma_fence_is_later(seqno, prev->seqno, prev->ops)) { diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index f26c71747d43..e744fd87c63c 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -615,25 +615,21 @@ static inline int dma_resv_test_signaled_single(struct dma_fence *passed_fence) */ bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all) { - unsigned int seq, shared_count; + struct dma_fence *fence; + unsigned int seq; int ret; rcu_read_lock(); retry: ret = true; - shared_count = 0; seq = read_seqcount_begin(&obj->seq); if (test_all) { struct dma_resv_list *fobj = dma_resv_shared_list(obj); - unsigned int i; - - if (fobj) - shared_count = fobj->shared_count; + unsigned int i, shared_count; + shared_count = fobj ? fobj->shared_count : 0; for (i = 0; i < shared_count; ++i) { - struct dma_fence *fence; - fence = rcu_dereference(fobj->shared[i]); ret = dma_resv_test_signaled_single(fence); if (ret < 0) @@ -641,24 +637,19 @@ retry: else if (!ret) break; } - - if (read_seqcount_retry(&obj->seq, seq)) - goto retry; } - if (!shared_count) { - struct dma_fence *fence_excl = dma_resv_excl_fence(obj); - - if (fence_excl) { - ret = dma_resv_test_signaled_single(fence_excl); - if (ret < 0) - goto retry; + fence = dma_resv_excl_fence(obj); + if (ret && fence) { + ret = dma_resv_test_signaled_single(fence); + if (ret < 0) + goto retry; - if (read_seqcount_retry(&obj->seq, seq)) - goto retry; - } } + if (read_seqcount_retry(&obj->seq, seq)) + goto retry; + rcu_read_unlock(); return ret; } diff --git a/drivers/dma-buf/st-dma-fence-chain.c b/drivers/dma-buf/st-dma-fence-chain.c index 9525f7f56119..8ce1ea59d31b 100644 --- a/drivers/dma-buf/st-dma-fence-chain.c +++ b/drivers/dma-buf/st-dma-fence-chain.c @@ -58,28 +58,20 @@ static struct dma_fence *mock_fence(void) return &f->base; } -static inline struct mock_chain { - struct dma_fence_chain base; -} *to_mock_chain(struct dma_fence *f) { - return container_of(f, struct mock_chain, base.base); -} - static struct dma_fence *mock_chain(struct dma_fence *prev, struct dma_fence *fence, u64 seqno) { - struct mock_chain *f; + struct dma_fence_chain *f; - f = kmalloc(sizeof(*f), GFP_KERNEL); + f = dma_fence_chain_alloc(); if (!f) return NULL; - dma_fence_chain_init(&f->base, - dma_fence_get(prev), - dma_fence_get(fence), + dma_fence_chain_init(f, dma_fence_get(prev), dma_fence_get(fence), seqno); - return &f->base.base; + return &f->base; } static int sanitycheck(void *arg) diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c index db732f71e59a..8df761a10251 100644 --- a/drivers/dma-buf/udmabuf.c +++ b/drivers/dma-buf/udmabuf.c @@ -11,9 +11,15 @@ #include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/udmabuf.h> +#include <linux/hugetlb.h> -static const u32 list_limit = 1024; /* udmabuf_create_list->count limit */ -static const size_t size_limit_mb = 64; /* total dmabuf size, in megabytes */ +static int list_limit = 1024; +module_param(list_limit, int, 0644); +MODULE_PARM_DESC(list_limit, "udmabuf_create_list->count limit. Default is 1024."); + +static int size_limit_mb = 64; +module_param(size_limit_mb, int, 0644); +MODULE_PARM_DESC(size_limit_mb, "Max size of a dmabuf, in megabytes. Default is 64."); struct udmabuf { pgoff_t pagecount; @@ -160,10 +166,13 @@ static long udmabuf_create(struct miscdevice *device, { DEFINE_DMA_BUF_EXPORT_INFO(exp_info); struct file *memfd = NULL; + struct address_space *mapping = NULL; struct udmabuf *ubuf; struct dma_buf *buf; pgoff_t pgoff, pgcnt, pgidx, pgbuf = 0, pglimit; - struct page *page; + struct page *page, *hpage = NULL; + pgoff_t subpgoff, maxsubpgs; + struct hstate *hpstate; int seals, ret = -EINVAL; u32 i, flags; @@ -194,7 +203,8 @@ static long udmabuf_create(struct miscdevice *device, memfd = fget(list[i].memfd); if (!memfd) goto err; - if (!shmem_mapping(file_inode(memfd)->i_mapping)) + mapping = file_inode(memfd)->i_mapping; + if (!shmem_mapping(mapping) && !is_file_hugepages(memfd)) goto err; seals = memfd_fcntl(memfd, F_GET_SEALS, 0); if (seals == -EINVAL) @@ -205,17 +215,48 @@ static long udmabuf_create(struct miscdevice *device, goto err; pgoff = list[i].offset >> PAGE_SHIFT; pgcnt = list[i].size >> PAGE_SHIFT; + if (is_file_hugepages(memfd)) { + hpstate = hstate_file(memfd); + pgoff = list[i].offset >> huge_page_shift(hpstate); + subpgoff = (list[i].offset & + ~huge_page_mask(hpstate)) >> PAGE_SHIFT; + maxsubpgs = huge_page_size(hpstate) >> PAGE_SHIFT; + } for (pgidx = 0; pgidx < pgcnt; pgidx++) { - page = shmem_read_mapping_page( - file_inode(memfd)->i_mapping, pgoff + pgidx); - if (IS_ERR(page)) { - ret = PTR_ERR(page); - goto err; + if (is_file_hugepages(memfd)) { + if (!hpage) { + hpage = find_get_page_flags(mapping, pgoff, + FGP_ACCESSED); + if (IS_ERR(hpage)) { + ret = PTR_ERR(hpage); + goto err; + } + } + page = hpage + subpgoff; + get_page(page); + subpgoff++; + if (subpgoff == maxsubpgs) { + put_page(hpage); + hpage = NULL; + subpgoff = 0; + pgoff++; + } + } else { + page = shmem_read_mapping_page(mapping, + pgoff + pgidx); + if (IS_ERR(page)) { + ret = PTR_ERR(page); + goto err; + } } ubuf->pages[pgbuf++] = page; } fput(memfd); memfd = NULL; + if (hpage) { + put_page(hpage); + hpage = NULL; + } } exp_info.ops = &udmabuf_ops; diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 7ff89690a976..0d372354c2d0 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -35,6 +35,11 @@ config DRM_MIPI_DSI bool depends on DRM +config DRM_DP_AUX_BUS + tristate + depends on DRM + depends on OF + config DRM_DP_AUX_CHARDEV bool "DRM DP AUX Interface" depends on DRM @@ -317,8 +322,6 @@ source "drivers/gpu/drm/tilcdc/Kconfig" source "drivers/gpu/drm/qxl/Kconfig" -source "drivers/gpu/drm/bochs/Kconfig" - source "drivers/gpu/drm/virtio/Kconfig" source "drivers/gpu/drm/msm/Kconfig" diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index a118692a6df7..ad1112154898 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -33,6 +33,8 @@ drm-$(CONFIG_PCI) += drm_pci.o drm-$(CONFIG_DEBUG_FS) += drm_debugfs.o drm_debugfs_crc.o drm-$(CONFIG_DRM_LOAD_EDID_FIRMWARE) += drm_edid_load.o +obj-$(CONFIG_DRM_DP_AUX_BUS) += drm_dp_aux_bus.o + drm_vram_helper-y := drm_gem_vram_helper.o obj-$(CONFIG_DRM_VRAM_HELPER) += drm_vram_helper.o @@ -96,7 +98,6 @@ obj-y += omapdrm/ obj-$(CONFIG_DRM_SUN4I) += sun4i/ obj-y += tilcdc/ obj-$(CONFIG_DRM_QXL) += qxl/ -obj-$(CONFIG_DRM_BOCHS) += bochs/ obj-$(CONFIG_DRM_VIRTIO_GPU) += virtio/ obj-$(CONFIG_DRM_MSM) += msm/ obj-$(CONFIG_DRM_TEGRA) += tegra/ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h index a130e766cbdb..c905a4cfc173 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h @@ -34,6 +34,7 @@ struct amdgpu_fpriv; struct amdgpu_bo_list_entry { struct ttm_validate_buffer tv; struct amdgpu_bo_va *bo_va; + struct dma_fence_chain *chain; uint32_t priority; struct page **user_pages; bool user_invalidated; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 30fa1f61e0e5..a152363b0254 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -572,6 +572,20 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, goto out; } + amdgpu_bo_list_for_each_entry(e, p->bo_list) { + struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); + + e->bo_va = amdgpu_vm_bo_find(vm, bo); + + if (bo->tbo.base.dma_buf && !amdgpu_bo_explicit_sync(bo)) { + e->chain = dma_fence_chain_alloc(); + if (!e->chain) { + r = -ENOMEM; + goto error_validate; + } + } + } + amdgpu_cs_get_threshold_for_moves(p->adev, &p->bytes_moved_threshold, &p->bytes_moved_vis_threshold); p->bytes_moved = 0; @@ -599,15 +613,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, gws = p->bo_list->gws_obj; oa = p->bo_list->oa_obj; - amdgpu_bo_list_for_each_entry(e, p->bo_list) { - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); - - /* Make sure we use the exclusive slot for shared BOs */ - if (bo->prime_shared_count) - e->tv.num_shared = 0; - e->bo_va = amdgpu_vm_bo_find(vm, bo); - } - if (gds) { p->job->gds_base = amdgpu_bo_gpu_offset(gds) >> PAGE_SHIFT; p->job->gds_size = amdgpu_bo_size(gds) >> PAGE_SHIFT; @@ -629,8 +634,13 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, } error_validate: - if (r) + if (r) { + amdgpu_bo_list_for_each_entry(e, p->bo_list) { + dma_fence_chain_free(e->chain); + e->chain = NULL; + } ttm_eu_backoff_reservation(&p->ticket, &p->validated); + } out: return r; } @@ -670,9 +680,17 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, { unsigned i; - if (error && backoff) + if (error && backoff) { + struct amdgpu_bo_list_entry *e; + + amdgpu_bo_list_for_each_entry(e, parser->bo_list) { + dma_fence_chain_free(e->chain); + e->chain = NULL; + } + ttm_eu_backoff_reservation(&parser->ticket, &parser->validated); + } for (i = 0; i < parser->num_post_deps; i++) { drm_syncobj_put(parser->post_deps[i].syncobj); @@ -1109,7 +1127,7 @@ static int amdgpu_cs_process_syncobj_timeline_out_dep(struct amdgpu_cs_parser *p dep->chain = NULL; if (syncobj_deps[i].point) { - dep->chain = kmalloc(sizeof(*dep->chain), GFP_KERNEL); + dep->chain = dma_fence_chain_alloc(); if (!dep->chain) return -ENOMEM; } @@ -1117,7 +1135,7 @@ static int amdgpu_cs_process_syncobj_timeline_out_dep(struct amdgpu_cs_parser *p dep->syncobj = drm_syncobj_find(p->filp, syncobj_deps[i].handle); if (!dep->syncobj) { - kfree(dep->chain); + dma_fence_chain_free(dep->chain); return -EINVAL; } dep->point = syncobj_deps[i].point; @@ -1245,6 +1263,28 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, amdgpu_vm_move_to_lru_tail(p->adev, &fpriv->vm); + amdgpu_bo_list_for_each_entry(e, p->bo_list) { + struct dma_resv *resv = e->tv.bo->base.resv; + struct dma_fence_chain *chain = e->chain; + + if (!chain) + continue; + + /* + * Work around dma_resv shortcommings by wrapping up the + * submission in a dma_fence_chain and add it as exclusive + * fence, but first add the submission as shared fence to make + * sure that shared fences never signal before the exclusive + * one. + */ + dma_fence_chain_init(chain, dma_resv_excl_fence(resv), + dma_fence_get(p->fence), 1); + + dma_resv_add_shared_fence(resv, p->fence); + rcu_assign_pointer(resv->fence_excl, &chain->base); + e->chain = NULL; + } + ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence); mutex_unlock(&p->adev->notifier_lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index a9475b207510..ae6ab93c868b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -42,48 +42,6 @@ #include <linux/pci-p2pdma.h> #include <linux/pm_runtime.h> -static int -__dma_resv_make_exclusive(struct dma_resv *obj) -{ - struct dma_fence **fences; - unsigned int count; - int r; - - if (!dma_resv_shared_list(obj)) /* no shared fences to convert */ - return 0; - - r = dma_resv_get_fences(obj, NULL, &count, &fences); - if (r) - return r; - - if (count == 0) { - /* Now that was unexpected. */ - } else if (count == 1) { - dma_resv_add_excl_fence(obj, fences[0]); - dma_fence_put(fences[0]); - kfree(fences); - } else { - struct dma_fence_array *array; - - array = dma_fence_array_create(count, fences, - dma_fence_context_alloc(1), 0, - false); - if (!array) - goto err_fences_put; - - dma_resv_add_excl_fence(obj, &array->base); - dma_fence_put(&array->base); - } - - return 0; - -err_fences_put: - while (count--) - dma_fence_put(fences[count]); - kfree(fences); - return -ENOMEM; -} - /** * amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation * @@ -110,24 +68,6 @@ static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf, if (r < 0) goto out; - r = amdgpu_bo_reserve(bo, false); - if (unlikely(r != 0)) - goto out; - - /* - * We only create shared fences for internal use, but importers - * of the dmabuf rely on exclusive fences for implicitly - * tracking write hazards. As any of the current fences may - * correspond to a write, we need to convert all existing - * fences on the reservation object into a single exclusive - * fence. - */ - r = __dma_resv_make_exclusive(bo->tbo.base.resv); - if (r) - goto out; - - bo->prime_shared_count++; - amdgpu_bo_unreserve(bo); return 0; out: @@ -150,9 +90,6 @@ static void amdgpu_dma_buf_detach(struct dma_buf *dmabuf, struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); - if (attach->dev->driver != adev->dev->driver && bo->prime_shared_count) - bo->prime_shared_count--; - pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); } @@ -418,8 +355,6 @@ amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf) bo = gem_to_amdgpu_bo(gobj); bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT; bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT; - if (dma_buf->ops != &amdgpu_dmabuf_ops) - bo->prime_shared_count = 1; dma_resv_unlock(resv); return gobj; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index abb928894eac..a959624d576b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1281,7 +1281,7 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, #endif /* Get rid of things like offb */ - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "amdgpudrmfb"); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &amdgpu_kms_driver); if (ret) return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 72d9b92b1754..d4547d195173 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -490,7 +490,7 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring, r = drm_sched_init(&ring->sched, &amdgpu_sched_ops, num_hw_submission, amdgpu_job_hang_limit, - timeout, sched_score, ring->name); + timeout, NULL, sched_score, ring->name); if (r) { DRM_ERROR("Failed to create scheduler on ring %s.\n", ring->name); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index d0d9bc445d7b..a25160797b61 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -829,7 +829,8 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data, break; } case AMDGPU_GEM_OP_SET_PLACEMENT: - if (robj->prime_shared_count && (args->value & AMDGPU_GEM_DOMAIN_VRAM)) { + if (robj->tbo.base.import_attach && + args->value & AMDGPU_GEM_DOMAIN_VRAM) { r = -EINVAL; amdgpu_bo_unreserve(robj); break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c index ec96e0b26b11..543000304a1c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -132,14 +132,11 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man, struct amdgpu_gtt_node *node; int r; - spin_lock(&mgr->lock); - if (tbo->resource && tbo->resource->mem_type != TTM_PL_TT && - atomic64_read(&mgr->available) < num_pages) { - spin_unlock(&mgr->lock); + if (!(place->flags & TTM_PL_FLAG_TEMPORARY) && + atomic64_add_return(num_pages, &mgr->used) > man->size) { + atomic64_sub(num_pages, &mgr->used); return -ENOSPC; } - atomic64_sub(num_pages, &mgr->available); - spin_unlock(&mgr->lock); node = kzalloc(struct_size(node, base.mm_nodes, 1), GFP_KERNEL); if (!node) { @@ -175,7 +172,8 @@ err_free: kfree(node); err_out: - atomic64_add(num_pages, &mgr->available); + if (!(place->flags & TTM_PL_FLAG_TEMPORARY)) + atomic64_sub(num_pages, &mgr->used); return r; } @@ -198,7 +196,9 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man, if (drm_mm_node_allocated(&node->base.mm_nodes[0])) drm_mm_remove_node(&node->base.mm_nodes[0]); spin_unlock(&mgr->lock); - atomic64_add(res->num_pages, &mgr->available); + + if (!(res->placement & TTM_PL_FLAG_TEMPORARY)) + atomic64_sub(res->num_pages, &mgr->used); kfree(node); } @@ -213,9 +213,8 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man, uint64_t amdgpu_gtt_mgr_usage(struct ttm_resource_manager *man) { struct amdgpu_gtt_mgr *mgr = to_gtt_mgr(man); - s64 result = man->size - atomic64_read(&mgr->available); - return (result > 0 ? result : 0) * PAGE_SIZE; + return atomic64_read(&mgr->used) * PAGE_SIZE; } /** @@ -265,9 +264,8 @@ static void amdgpu_gtt_mgr_debug(struct ttm_resource_manager *man, drm_mm_print(&mgr->mm, printer); spin_unlock(&mgr->lock); - drm_printf(printer, "man size:%llu pages, gtt available:%lld pages, usage:%lluMB\n", - man->size, (u64)atomic64_read(&mgr->available), - amdgpu_gtt_mgr_usage(man) >> 20); + drm_printf(printer, "man size:%llu pages, gtt used:%llu pages\n", + man->size, atomic64_read(&mgr->used)); } static const struct ttm_resource_manager_func amdgpu_gtt_mgr_func = { @@ -299,7 +297,7 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size) size = (adev->gmc.gart_size >> PAGE_SHIFT) - start; drm_mm_init(&mgr->mm, start, size); spin_lock_init(&mgr->lock); - atomic64_set(&mgr->available, gtt_size >> PAGE_SHIFT); + atomic64_set(&mgr->used, 0); ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_TT, &mgr->manager); ttm_resource_manager_set_used(man, true); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index 83af307e97cd..0d01cfaca77e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -617,7 +617,7 @@ void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev) int amdgpu_irq_get(struct amdgpu_device *adev, struct amdgpu_irq_src *src, unsigned type) { - if (!adev_to_drm(adev)->irq_enabled) + if (!adev->irq.installed) return -ENOENT; if (type >= src->num_types) @@ -647,7 +647,7 @@ int amdgpu_irq_get(struct amdgpu_device *adev, struct amdgpu_irq_src *src, int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src, unsigned type) { - if (!adev_to_drm(adev)->irq_enabled) + if (!adev->irq.installed) return -ENOENT; if (type >= src->num_types) @@ -678,7 +678,7 @@ int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src, bool amdgpu_irq_enabled(struct amdgpu_device *adev, struct amdgpu_irq_src *src, unsigned type) { - if (!adev_to_drm(adev)->irq_enabled) + if (!adev->irq.installed) return false; if (type >= src->num_types) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 795fa7445abe..261283f5b424 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -196,7 +196,7 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain) c++; } - BUG_ON(c >= AMDGPU_BO_MAX_PLACEMENTS); + BUG_ON(c > AMDGPU_BO_MAX_PLACEMENTS); placement->num_placement = c; placement->placement = places; @@ -913,7 +913,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, return -EINVAL; /* A shared bo cannot be migrated to VRAM */ - if (bo->prime_shared_count || bo->tbo.base.import_attach) { + if (bo->tbo.base.import_attach) { if (domain & AMDGPU_GEM_DOMAIN_GTT) domain = AMDGPU_GEM_DOMAIN_GTT; else diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index 38c834d0f930..e72f329e7f18 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -100,7 +100,6 @@ struct amdgpu_bo { struct ttm_buffer_object tbo; struct ttm_bo_kmap_obj kmap; u64 flags; - unsigned prime_shared_count; /* per VM structure for page tables and with virtual addresses */ struct amdgpu_vm_bo_base *vm_bo; /* Constant after initialization */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index 1b2ceccaf5b0..862eb3c1c4c5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -28,6 +28,8 @@ * Christian König <christian.koenig@amd.com> */ +#include <linux/dma-fence-chain.h> + #include "amdgpu.h" #include "amdgpu_trace.h" #include "amdgpu_amdkfd.h" @@ -186,6 +188,55 @@ int amdgpu_sync_vm_fence(struct amdgpu_sync *sync, struct dma_fence *fence) return amdgpu_sync_fence(sync, fence); } +/* Determine based on the owner and mode if we should sync to a fence or not */ +static bool amdgpu_sync_test_fence(struct amdgpu_device *adev, + enum amdgpu_sync_mode mode, + void *owner, struct dma_fence *f) +{ + void *fence_owner = amdgpu_sync_get_owner(f); + + /* Always sync to moves, no matter what */ + if (fence_owner == AMDGPU_FENCE_OWNER_UNDEFINED) + return true; + + /* We only want to trigger KFD eviction fences on + * evict or move jobs. Skip KFD fences otherwise. + */ + if (fence_owner == AMDGPU_FENCE_OWNER_KFD && + owner != AMDGPU_FENCE_OWNER_UNDEFINED) + return false; + + /* Never sync to VM updates either. */ + if (fence_owner == AMDGPU_FENCE_OWNER_VM && + owner != AMDGPU_FENCE_OWNER_UNDEFINED) + return false; + + /* Ignore fences depending on the sync mode */ + switch (mode) { + case AMDGPU_SYNC_ALWAYS: + return true; + + case AMDGPU_SYNC_NE_OWNER: + if (amdgpu_sync_same_dev(adev, f) && + fence_owner == owner) + return false; + break; + + case AMDGPU_SYNC_EQ_OWNER: + if (amdgpu_sync_same_dev(adev, f) && + fence_owner != owner) + return false; + break; + + case AMDGPU_SYNC_EXPLICIT: + return false; + } + + WARN(debug_evictions && fence_owner == AMDGPU_FENCE_OWNER_KFD, + "Adding eviction fence to sync obj"); + return true; +} + /** * amdgpu_sync_resv - sync to a reservation object * @@ -211,67 +262,34 @@ int amdgpu_sync_resv(struct amdgpu_device *adev, struct amdgpu_sync *sync, /* always sync to the exclusive fence */ f = dma_resv_excl_fence(resv); - r = amdgpu_sync_fence(sync, f); + dma_fence_chain_for_each(f, f) { + struct dma_fence_chain *chain = to_dma_fence_chain(f); + + if (amdgpu_sync_test_fence(adev, mode, owner, chain ? + chain->fence : f)) { + r = amdgpu_sync_fence(sync, f); + dma_fence_put(f); + if (r) + return r; + break; + } + } flist = dma_resv_shared_list(resv); - if (!flist || r) - return r; + if (!flist) + return 0; for (i = 0; i < flist->shared_count; ++i) { - void *fence_owner; - f = rcu_dereference_protected(flist->shared[i], dma_resv_held(resv)); - fence_owner = amdgpu_sync_get_owner(f); - - /* Always sync to moves, no matter what */ - if (fence_owner == AMDGPU_FENCE_OWNER_UNDEFINED) { + if (amdgpu_sync_test_fence(adev, mode, owner, f)) { r = amdgpu_sync_fence(sync, f); if (r) - break; - } - - /* We only want to trigger KFD eviction fences on - * evict or move jobs. Skip KFD fences otherwise. - */ - if (fence_owner == AMDGPU_FENCE_OWNER_KFD && - owner != AMDGPU_FENCE_OWNER_UNDEFINED) - continue; - - /* Never sync to VM updates either. */ - if (fence_owner == AMDGPU_FENCE_OWNER_VM && - owner != AMDGPU_FENCE_OWNER_UNDEFINED) - continue; - - /* Ignore fences depending on the sync mode */ - switch (mode) { - case AMDGPU_SYNC_ALWAYS: - break; - - case AMDGPU_SYNC_NE_OWNER: - if (amdgpu_sync_same_dev(adev, f) && - fence_owner == owner) - continue; - break; - - case AMDGPU_SYNC_EQ_OWNER: - if (amdgpu_sync_same_dev(adev, f) && - fence_owner != owner) - continue; - break; - - case AMDGPU_SYNC_EXPLICIT: - continue; + return r; } - - WARN(debug_evictions && fence_owner == AMDGPU_FENCE_OWNER_KFD, - "Adding eviction fence to sync obj"); - r = amdgpu_sync_fence(sync, f); - if (r) - break; } - return r; + return 0; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 3a55f08e00e1..acd95d3a4434 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -149,14 +149,16 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo, * BOs to be evicted from VRAM */ amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM | - AMDGPU_GEM_DOMAIN_GTT); + AMDGPU_GEM_DOMAIN_GTT | + AMDGPU_GEM_DOMAIN_CPU); abo->placements[0].fpfn = adev->gmc.visible_vram_size >> PAGE_SHIFT; abo->placements[0].lpfn = 0; abo->placement.busy_placement = &abo->placements[1]; abo->placement.num_busy_placement = 1; } else { /* Move to GTT memory */ - amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT); + amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT | + AMDGPU_GEM_DOMAIN_CPU); } break; case TTM_PL_TT: @@ -521,7 +523,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict, hop->fpfn = 0; hop->lpfn = 0; hop->mem_type = TTM_PL_TT; - hop->flags = 0; + hop->flags = TTM_PL_FLAG_TEMPORARY; return -EMULTIHOP; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index e69f3e8e06e5..3205fd520060 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -52,7 +52,7 @@ struct amdgpu_gtt_mgr { struct ttm_resource_manager manager; struct drm_mm mm; spinlock_t lock; - atomic64_t available; + atomic64_t used; }; struct amdgpu_preempt_mgr { diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c index ff45f23f3d56..93b7f09b96ca 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c @@ -13,7 +13,6 @@ #include <drm/drm_fb_helper.h> #include <drm/drm_gem_cma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> -#include <drm/drm_irq.h> #include <drm/drm_managed.h> #include <drm/drm_probe_helper.h> #include <drm/drm_vblank.h> @@ -301,8 +300,6 @@ struct komeda_kms_dev *komeda_kms_attach(struct komeda_dev *mdev) if (err) goto free_component_binding; - drm->irq_enabled = true; - drm_kms_helper_poll_init(drm); err = drm_dev_register(drm, 0); @@ -313,7 +310,6 @@ struct komeda_kms_dev *komeda_kms_attach(struct komeda_dev *mdev) free_interrupts: drm_kms_helper_poll_fini(drm); - drm->irq_enabled = false; free_component_binding: component_unbind_all(mdev->dev, drm); cleanup_mode_config: @@ -331,7 +327,6 @@ void komeda_kms_detach(struct komeda_kms_dev *kms) drm_dev_unregister(drm); drm_kms_helper_poll_fini(drm); drm_atomic_helper_shutdown(drm); - drm->irq_enabled = false; component_unbind_all(mdev->dev, drm); drm_mode_config_cleanup(drm); komeda_kms_cleanup_private_objs(kms); diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c index de59f3302516..78d15b04b105 100644 --- a/drivers/gpu/drm/arm/malidp_drv.c +++ b/drivers/gpu/drm/arm/malidp_drv.c @@ -847,8 +847,6 @@ static int malidp_bind(struct device *dev) if (ret < 0) goto irq_init_fail; - drm->irq_enabled = true; - ret = drm_vblank_init(drm, drm->mode_config.num_crtc); if (ret < 0) { DRM_ERROR("failed to initialise vblank\n"); @@ -874,7 +872,6 @@ register_fail: vblank_fail: malidp_se_irq_fini(hwdev); malidp_de_irq_fini(hwdev); - drm->irq_enabled = false; irq_init_fail: drm_atomic_helper_shutdown(drm); component_unbind_all(dev, drm); @@ -909,7 +906,6 @@ static void malidp_unbind(struct device *dev) drm_atomic_helper_shutdown(drm); malidp_se_irq_fini(hwdev); malidp_de_irq_fini(hwdev); - drm->irq_enabled = false; component_unbind_all(dev, drm); of_node_put(malidp->crtc.port); malidp->crtc.port = NULL; diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c index dab0a1f0983b..8e3e98f13db4 100644 --- a/drivers/gpu/drm/armada/armada_drv.c +++ b/drivers/gpu/drm/armada/armada_drv.c @@ -95,7 +95,7 @@ static int armada_drm_bind(struct device *dev) } /* Remove early framebuffers */ - ret = drm_aperture_remove_framebuffers(false, "armada-drm-fb"); + ret = drm_aperture_remove_framebuffers(false, &armada_drm_driver); if (ret) { dev_err(dev, "[" DRM_NAME ":%s] can't kick out simple-fb: %d\n", __func__, ret); @@ -130,8 +130,6 @@ static int armada_drm_bind(struct device *dev) if (ret) goto err_comp; - priv->drm.irq_enabled = true; - drm_mode_config_reset(&priv->drm); ret = armada_fbdev_init(&priv->drm); diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c index d3e3e5fdc390..424250535fed 100644 --- a/drivers/gpu/drm/armada/armada_overlay.c +++ b/drivers/gpu/drm/armada/armada_overlay.c @@ -247,8 +247,6 @@ static void armada_drm_overlay_plane_atomic_disable(struct drm_plane *plane, } static const struct drm_plane_helper_funcs armada_overlay_plane_helper_funcs = { - .prepare_fb = armada_drm_plane_prepare_fb, - .cleanup_fb = armada_drm_plane_cleanup_fb, .atomic_check = armada_drm_plane_atomic_check, .atomic_update = armada_drm_overlay_plane_atomic_update, .atomic_disable = armada_drm_overlay_plane_atomic_disable, diff --git a/drivers/gpu/drm/armada/armada_plane.c b/drivers/gpu/drm/armada/armada_plane.c index 40209e49f34a..959d7f0a5108 100644 --- a/drivers/gpu/drm/armada/armada_plane.c +++ b/drivers/gpu/drm/armada/armada_plane.c @@ -78,33 +78,6 @@ void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[2][3], } } -int armada_drm_plane_prepare_fb(struct drm_plane *plane, - struct drm_plane_state *state) -{ - DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n", - plane->base.id, plane->name, - state->fb ? state->fb->base.id : 0); - - /* - * Take a reference on the new framebuffer - we want to - * hold on to it while the hardware is displaying it. - */ - if (state->fb) - drm_framebuffer_get(state->fb); - return 0; -} - -void armada_drm_plane_cleanup_fb(struct drm_plane *plane, - struct drm_plane_state *old_state) -{ - DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n", - plane->base.id, plane->name, - old_state->fb ? old_state->fb->base.id : 0); - - if (old_state->fb) - drm_framebuffer_put(old_state->fb); -} - int armada_drm_plane_atomic_check(struct drm_plane *plane, struct drm_atomic_state *state) { @@ -282,8 +255,6 @@ static void armada_drm_primary_plane_atomic_disable(struct drm_plane *plane, } static const struct drm_plane_helper_funcs armada_primary_plane_helper_funcs = { - .prepare_fb = armada_drm_plane_prepare_fb, - .cleanup_fb = armada_drm_plane_cleanup_fb, .atomic_check = armada_drm_plane_atomic_check, .atomic_update = armada_drm_primary_plane_atomic_update, .atomic_disable = armada_drm_primary_plane_atomic_disable, diff --git a/drivers/gpu/drm/armada/armada_plane.h b/drivers/gpu/drm/armada/armada_plane.h index 51dab8d8da22..368415c609a6 100644 --- a/drivers/gpu/drm/armada/armada_plane.h +++ b/drivers/gpu/drm/armada/armada_plane.h @@ -21,8 +21,6 @@ struct armada_plane_state { void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[2][3], u16 pitches[3], bool interlaced); -int armada_drm_plane_prepare_fb(struct drm_plane *plane, - struct drm_plane_state *state); void armada_drm_plane_cleanup_fb(struct drm_plane *plane, struct drm_plane_state *old_state); int armada_drm_plane_atomic_check(struct drm_plane *plane, diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_crtc.c b/drivers/gpu/drm/aspeed/aspeed_gfx_crtc.c index 098f96d4d50d..827e62c1daba 100644 --- a/drivers/gpu/drm/aspeed/aspeed_gfx_crtc.c +++ b/drivers/gpu/drm/aspeed/aspeed_gfx_crtc.c @@ -220,7 +220,6 @@ static const struct drm_simple_display_pipe_funcs aspeed_gfx_funcs = { .enable = aspeed_gfx_pipe_enable, .disable = aspeed_gfx_pipe_disable, .update = aspeed_gfx_pipe_update, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, .enable_vblank = aspeed_gfx_enable_vblank, .disable_vblank = aspeed_gfx_disable_vblank, }; diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c index 5aa452b4efe6..86d5cd7b6318 100644 --- a/drivers/gpu/drm/ast/ast_drv.c +++ b/drivers/gpu/drm/ast/ast_drv.c @@ -100,7 +100,7 @@ static int ast_remove_conflicting_framebuffers(struct pci_dev *pdev) primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW; #endif - return drm_aperture_remove_conflicting_framebuffers(base, size, primary, "astdrmfb"); + return drm_aperture_remove_conflicting_framebuffers(base, size, primary, &ast_driver); } static int ast_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 36d9575aa27b..f5d58c3088fe 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -612,8 +612,7 @@ ast_primary_plane_helper_atomic_disable(struct drm_plane *plane, } static const struct drm_plane_helper_funcs ast_primary_plane_helper_funcs = { - .prepare_fb = drm_gem_vram_plane_helper_prepare_fb, - .cleanup_fb = drm_gem_vram_plane_helper_cleanup_fb, + DRM_GEM_VRAM_PLANE_HELPER_FUNCS, .atomic_check = ast_primary_plane_helper_atomic_check, .atomic_update = ast_primary_plane_helper_atomic_update, .atomic_disable = ast_primary_plane_helper_atomic_disable, @@ -1293,6 +1292,18 @@ static enum drm_mode_status ast_mode_valid(struct drm_connector *connector, return flags; } +static enum drm_connector_status ast_connector_detect(struct drm_connector + *connector, bool force) +{ + int r; + + r = ast_get_modes(connector); + if (r < 0) + return connector_status_disconnected; + + return connector_status_connected; +} + static void ast_connector_destroy(struct drm_connector *connector) { struct ast_connector *ast_connector = to_ast_connector(connector); @@ -1307,6 +1318,7 @@ static const struct drm_connector_helper_funcs ast_connector_helper_funcs = { static const struct drm_connector_funcs ast_connector_funcs = { .reset = drm_atomic_helper_connector_reset, + .detect = ast_connector_detect, .fill_modes = drm_helper_probe_single_connector_modes, .destroy = ast_connector_destroy, .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, @@ -1334,7 +1346,8 @@ static int ast_connector_init(struct drm_device *dev) connector->interlace_allowed = 0; connector->doublescan_allowed = 0; - connector->polled = DRM_CONNECTOR_POLL_CONNECT; + connector->polled = DRM_CONNECTOR_POLL_CONNECT | + DRM_CONNECTOR_POLL_DISCONNECT; drm_connector_attach_encoder(connector, encoder); @@ -1403,6 +1416,8 @@ int ast_mode_config_init(struct ast_private *ast) drm_mode_config_reset(dev); + drm_kms_helper_poll_init(dev); + return 0; } diff --git a/drivers/gpu/drm/bochs/Kconfig b/drivers/gpu/drm/bochs/Kconfig deleted file mode 100644 index 7bcdf294fed8..000000000000 --- a/drivers/gpu/drm/bochs/Kconfig +++ /dev/null @@ -1,11 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -config DRM_BOCHS - tristate "DRM Support for bochs dispi vga interface (qemu stdvga)" - depends on DRM && PCI && MMU - select DRM_KMS_HELPER - select DRM_VRAM_HELPER - select DRM_TTM - select DRM_TTM_HELPER - help - Choose this option for qemu. - If M is selected the module will be called bochs-drm. diff --git a/drivers/gpu/drm/bochs/Makefile b/drivers/gpu/drm/bochs/Makefile deleted file mode 100644 index 55473371300f..000000000000 --- a/drivers/gpu/drm/bochs/Makefile +++ /dev/null @@ -1,4 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -bochs-drm-y := bochs_drv.o bochs_mm.o bochs_kms.o bochs_hw.o - -obj-$(CONFIG_DRM_BOCHS) += bochs-drm.o diff --git a/drivers/gpu/drm/bochs/bochs.h b/drivers/gpu/drm/bochs/bochs.h deleted file mode 100644 index e9645c612aff..000000000000 --- a/drivers/gpu/drm/bochs/bochs.h +++ /dev/null @@ -1,98 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#include <linux/io.h> -#include <linux/console.h> - -#include <drm/drm_crtc.h> -#include <drm/drm_crtc_helper.h> -#include <drm/drm_encoder.h> -#include <drm/drm_fb_helper.h> -#include <drm/drm_gem.h> -#include <drm/drm_gem_vram_helper.h> -#include <drm/drm_simple_kms_helper.h> - -/* ---------------------------------------------------------------------- */ - -#define VBE_DISPI_IOPORT_INDEX 0x01CE -#define VBE_DISPI_IOPORT_DATA 0x01CF - -#define VBE_DISPI_INDEX_ID 0x0 -#define VBE_DISPI_INDEX_XRES 0x1 -#define VBE_DISPI_INDEX_YRES 0x2 -#define VBE_DISPI_INDEX_BPP 0x3 -#define VBE_DISPI_INDEX_ENABLE 0x4 -#define VBE_DISPI_INDEX_BANK 0x5 -#define VBE_DISPI_INDEX_VIRT_WIDTH 0x6 -#define VBE_DISPI_INDEX_VIRT_HEIGHT 0x7 -#define VBE_DISPI_INDEX_X_OFFSET 0x8 -#define VBE_DISPI_INDEX_Y_OFFSET 0x9 -#define VBE_DISPI_INDEX_VIDEO_MEMORY_64K 0xa - -#define VBE_DISPI_ID0 0xB0C0 -#define VBE_DISPI_ID1 0xB0C1 -#define VBE_DISPI_ID2 0xB0C2 -#define VBE_DISPI_ID3 0xB0C3 -#define VBE_DISPI_ID4 0xB0C4 -#define VBE_DISPI_ID5 0xB0C5 - -#define VBE_DISPI_DISABLED 0x00 -#define VBE_DISPI_ENABLED 0x01 -#define VBE_DISPI_GETCAPS 0x02 -#define VBE_DISPI_8BIT_DAC 0x20 -#define VBE_DISPI_LFB_ENABLED 0x40 -#define VBE_DISPI_NOCLEARMEM 0x80 - -/* ---------------------------------------------------------------------- */ - -enum bochs_types { - BOCHS_QEMU_STDVGA, - BOCHS_UNKNOWN, -}; - -struct bochs_device { - /* hw */ - void __iomem *mmio; - int ioports; - void __iomem *fb_map; - unsigned long fb_base; - unsigned long fb_size; - unsigned long qext_size; - - /* mode */ - u16 xres; - u16 yres; - u16 yres_virtual; - u32 stride; - u32 bpp; - struct edid *edid; - - /* drm */ - struct drm_device *dev; - struct drm_simple_display_pipe pipe; - struct drm_connector connector; -}; - -/* ---------------------------------------------------------------------- */ - -/* bochs_hw.c */ -int bochs_hw_init(struct drm_device *dev); -void bochs_hw_fini(struct drm_device *dev); - -void bochs_hw_blank(struct bochs_device *bochs, bool blank); -void bochs_hw_setmode(struct bochs_device *bochs, - struct drm_display_mode *mode); -void bochs_hw_setformat(struct bochs_device *bochs, - const struct drm_format_info *format); -void bochs_hw_setbase(struct bochs_device *bochs, - int x, int y, int stride, u64 addr); -int bochs_hw_load_edid(struct bochs_device *bochs); - -/* bochs_mm.c */ -int bochs_mm_init(struct bochs_device *bochs); -void bochs_mm_fini(struct bochs_device *bochs); - -/* bochs_kms.c */ -int bochs_kms_init(struct bochs_device *bochs); - -/* bochs_fbdev.c */ -extern const struct drm_mode_config_funcs bochs_mode_funcs; diff --git a/drivers/gpu/drm/bochs/bochs_drv.c b/drivers/gpu/drm/bochs/bochs_drv.c deleted file mode 100644 index c828cadbabff..000000000000 --- a/drivers/gpu/drm/bochs/bochs_drv.c +++ /dev/null @@ -1,205 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - */ - -#include <linux/module.h> -#include <linux/pci.h> - -#include <drm/drm_drv.h> -#include <drm/drm_aperture.h> -#include <drm/drm_atomic_helper.h> -#include <drm/drm_managed.h> - -#include "bochs.h" - -static int bochs_modeset = -1; -module_param_named(modeset, bochs_modeset, int, 0444); -MODULE_PARM_DESC(modeset, "enable/disable kernel modesetting"); - -/* ---------------------------------------------------------------------- */ -/* drm interface */ - -static void bochs_unload(struct drm_device *dev) -{ - struct bochs_device *bochs = dev->dev_private; - - bochs_mm_fini(bochs); -} - -static int bochs_load(struct drm_device *dev) -{ - struct bochs_device *bochs; - int ret; - - bochs = drmm_kzalloc(dev, sizeof(*bochs), GFP_KERNEL); - if (bochs == NULL) - return -ENOMEM; - dev->dev_private = bochs; - bochs->dev = dev; - - ret = bochs_hw_init(dev); - if (ret) - goto err; - - ret = bochs_mm_init(bochs); - if (ret) - goto err; - - ret = bochs_kms_init(bochs); - if (ret) - goto err; - - return 0; - -err: - bochs_unload(dev); - return ret; -} - -DEFINE_DRM_GEM_FOPS(bochs_fops); - -static const struct drm_driver bochs_driver = { - .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, - .fops = &bochs_fops, - .name = "bochs-drm", - .desc = "bochs dispi vga interface (qemu stdvga)", - .date = "20130925", - .major = 1, - .minor = 0, - DRM_GEM_VRAM_DRIVER, - .release = bochs_unload, -}; - -/* ---------------------------------------------------------------------- */ -/* pm interface */ - -#ifdef CONFIG_PM_SLEEP -static int bochs_pm_suspend(struct device *dev) -{ - struct drm_device *drm_dev = dev_get_drvdata(dev); - - return drm_mode_config_helper_suspend(drm_dev); -} - -static int bochs_pm_resume(struct device *dev) -{ - struct drm_device *drm_dev = dev_get_drvdata(dev); - - return drm_mode_config_helper_resume(drm_dev); -} -#endif - -static const struct dev_pm_ops bochs_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(bochs_pm_suspend, - bochs_pm_resume) -}; - -/* ---------------------------------------------------------------------- */ -/* pci interface */ - -static int bochs_pci_probe(struct pci_dev *pdev, - const struct pci_device_id *ent) -{ - struct drm_device *dev; - unsigned long fbsize; - int ret; - - fbsize = pci_resource_len(pdev, 0); - if (fbsize < 4 * 1024 * 1024) { - DRM_ERROR("less than 4 MB video memory, ignoring device\n"); - return -ENOMEM; - } - - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "bochsdrmfb"); - if (ret) - return ret; - - dev = drm_dev_alloc(&bochs_driver, &pdev->dev); - if (IS_ERR(dev)) - return PTR_ERR(dev); - - ret = pci_enable_device(pdev); - if (ret) - goto err_free_dev; - - pci_set_drvdata(pdev, dev); - - ret = bochs_load(dev); - if (ret) - goto err_free_dev; - - ret = drm_dev_register(dev, 0); - if (ret) - goto err_unload; - - drm_fbdev_generic_setup(dev, 32); - return ret; - -err_unload: - bochs_unload(dev); -err_free_dev: - drm_dev_put(dev); - return ret; -} - -static void bochs_pci_remove(struct pci_dev *pdev) -{ - struct drm_device *dev = pci_get_drvdata(pdev); - - drm_dev_unplug(dev); - drm_atomic_helper_shutdown(dev); - bochs_hw_fini(dev); - drm_dev_put(dev); -} - -static const struct pci_device_id bochs_pci_tbl[] = { - { - .vendor = 0x1234, - .device = 0x1111, - .subvendor = PCI_SUBVENDOR_ID_REDHAT_QUMRANET, - .subdevice = PCI_SUBDEVICE_ID_QEMU, - .driver_data = BOCHS_QEMU_STDVGA, - }, - { - .vendor = 0x1234, - .device = 0x1111, - .subvendor = PCI_ANY_ID, - .subdevice = PCI_ANY_ID, - .driver_data = BOCHS_UNKNOWN, - }, - { /* end of list */ } -}; - -static struct pci_driver bochs_pci_driver = { - .name = "bochs-drm", - .id_table = bochs_pci_tbl, - .probe = bochs_pci_probe, - .remove = bochs_pci_remove, - .driver.pm = &bochs_pm_ops, -}; - -/* ---------------------------------------------------------------------- */ -/* module init/exit */ - -static int __init bochs_init(void) -{ - if (vgacon_text_force() && bochs_modeset == -1) - return -EINVAL; - - if (bochs_modeset == 0) - return -EINVAL; - - return pci_register_driver(&bochs_pci_driver); -} - -static void __exit bochs_exit(void) -{ - pci_unregister_driver(&bochs_pci_driver); -} - -module_init(bochs_init); -module_exit(bochs_exit); - -MODULE_DEVICE_TABLE(pci, bochs_pci_tbl); -MODULE_AUTHOR("Gerd Hoffmann <kraxel@redhat.com>"); -MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/bochs/bochs_hw.c b/drivers/gpu/drm/bochs/bochs_hw.c deleted file mode 100644 index 7d3426d8cc69..000000000000 --- a/drivers/gpu/drm/bochs/bochs_hw.c +++ /dev/null @@ -1,323 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - */ - -#include <linux/pci.h> - -#include <drm/drm_drv.h> -#include <drm/drm_fourcc.h> - -#include <video/vga.h> -#include "bochs.h" - -/* ---------------------------------------------------------------------- */ - -static void bochs_vga_writeb(struct bochs_device *bochs, u16 ioport, u8 val) -{ - if (WARN_ON(ioport < 0x3c0 || ioport > 0x3df)) - return; - - if (bochs->mmio) { - int offset = ioport - 0x3c0 + 0x400; - writeb(val, bochs->mmio + offset); - } else { - outb(val, ioport); - } -} - -static u8 bochs_vga_readb(struct bochs_device *bochs, u16 ioport) -{ - if (WARN_ON(ioport < 0x3c0 || ioport > 0x3df)) - return 0xff; - - if (bochs->mmio) { - int offset = ioport - 0x3c0 + 0x400; - return readb(bochs->mmio + offset); - } else { - return inb(ioport); - } -} - -static u16 bochs_dispi_read(struct bochs_device *bochs, u16 reg) -{ - u16 ret = 0; - - if (bochs->mmio) { - int offset = 0x500 + (reg << 1); - ret = readw(bochs->mmio + offset); - } else { - outw(reg, VBE_DISPI_IOPORT_INDEX); - ret = inw(VBE_DISPI_IOPORT_DATA); - } - return ret; -} - -static void bochs_dispi_write(struct bochs_device *bochs, u16 reg, u16 val) -{ - if (bochs->mmio) { - int offset = 0x500 + (reg << 1); - writew(val, bochs->mmio + offset); - } else { - outw(reg, VBE_DISPI_IOPORT_INDEX); - outw(val, VBE_DISPI_IOPORT_DATA); - } -} - -static void bochs_hw_set_big_endian(struct bochs_device *bochs) -{ - if (bochs->qext_size < 8) - return; - - writel(0xbebebebe, bochs->mmio + 0x604); -} - -static void bochs_hw_set_little_endian(struct bochs_device *bochs) -{ - if (bochs->qext_size < 8) - return; - - writel(0x1e1e1e1e, bochs->mmio + 0x604); -} - -#ifdef __BIG_ENDIAN -#define bochs_hw_set_native_endian(_b) bochs_hw_set_big_endian(_b) -#else -#define bochs_hw_set_native_endian(_b) bochs_hw_set_little_endian(_b) -#endif - -static int bochs_get_edid_block(void *data, u8 *buf, - unsigned int block, size_t len) -{ - struct bochs_device *bochs = data; - size_t i, start = block * EDID_LENGTH; - - if (start + len > 0x400 /* vga register offset */) - return -1; - - for (i = 0; i < len; i++) { - buf[i] = readb(bochs->mmio + start + i); - } - return 0; -} - -int bochs_hw_load_edid(struct bochs_device *bochs) -{ - u8 header[8]; - - if (!bochs->mmio) - return -1; - - /* check header to detect whenever edid support is enabled in qemu */ - bochs_get_edid_block(bochs, header, 0, ARRAY_SIZE(header)); - if (drm_edid_header_is_valid(header) != 8) - return -1; - - kfree(bochs->edid); - bochs->edid = drm_do_get_edid(&bochs->connector, - bochs_get_edid_block, bochs); - if (bochs->edid == NULL) - return -1; - - return 0; -} - -int bochs_hw_init(struct drm_device *dev) -{ - struct bochs_device *bochs = dev->dev_private; - struct pci_dev *pdev = to_pci_dev(dev->dev); - unsigned long addr, size, mem, ioaddr, iosize; - u16 id; - - if (pdev->resource[2].flags & IORESOURCE_MEM) { - /* mmio bar with vga and bochs registers present */ - if (pci_request_region(pdev, 2, "bochs-drm") != 0) { - DRM_ERROR("Cannot request mmio region\n"); - return -EBUSY; - } - ioaddr = pci_resource_start(pdev, 2); - iosize = pci_resource_len(pdev, 2); - bochs->mmio = ioremap(ioaddr, iosize); - if (bochs->mmio == NULL) { - DRM_ERROR("Cannot map mmio region\n"); - return -ENOMEM; - } - } else { - ioaddr = VBE_DISPI_IOPORT_INDEX; - iosize = 2; - if (!request_region(ioaddr, iosize, "bochs-drm")) { - DRM_ERROR("Cannot request ioports\n"); - return -EBUSY; - } - bochs->ioports = 1; - } - - id = bochs_dispi_read(bochs, VBE_DISPI_INDEX_ID); - mem = bochs_dispi_read(bochs, VBE_DISPI_INDEX_VIDEO_MEMORY_64K) - * 64 * 1024; - if ((id & 0xfff0) != VBE_DISPI_ID0) { - DRM_ERROR("ID mismatch\n"); - return -ENODEV; - } - - if ((pdev->resource[0].flags & IORESOURCE_MEM) == 0) - return -ENODEV; - addr = pci_resource_start(pdev, 0); - size = pci_resource_len(pdev, 0); - if (addr == 0) - return -ENODEV; - if (size != mem) { - DRM_ERROR("Size mismatch: pci=%ld, bochs=%ld\n", - size, mem); - size = min(size, mem); - } - - if (pci_request_region(pdev, 0, "bochs-drm") != 0) - DRM_WARN("Cannot request framebuffer, boot fb still active?\n"); - - bochs->fb_map = ioremap(addr, size); - if (bochs->fb_map == NULL) { - DRM_ERROR("Cannot map framebuffer\n"); - return -ENOMEM; - } - bochs->fb_base = addr; - bochs->fb_size = size; - - DRM_INFO("Found bochs VGA, ID 0x%x.\n", id); - DRM_INFO("Framebuffer size %ld kB @ 0x%lx, %s @ 0x%lx.\n", - size / 1024, addr, - bochs->ioports ? "ioports" : "mmio", - ioaddr); - - if (bochs->mmio && pdev->revision >= 2) { - bochs->qext_size = readl(bochs->mmio + 0x600); - if (bochs->qext_size < 4 || bochs->qext_size > iosize) { - bochs->qext_size = 0; - goto noext; - } - DRM_DEBUG("Found qemu ext regs, size %ld\n", - bochs->qext_size); - bochs_hw_set_native_endian(bochs); - } - -noext: - return 0; -} - -void bochs_hw_fini(struct drm_device *dev) -{ - struct bochs_device *bochs = dev->dev_private; - - /* TODO: shot down existing vram mappings */ - - if (bochs->mmio) - iounmap(bochs->mmio); - if (bochs->ioports) - release_region(VBE_DISPI_IOPORT_INDEX, 2); - if (bochs->fb_map) - iounmap(bochs->fb_map); - pci_release_regions(to_pci_dev(dev->dev)); - kfree(bochs->edid); -} - -void bochs_hw_blank(struct bochs_device *bochs, bool blank) -{ - DRM_DEBUG_DRIVER("hw_blank %d\n", blank); - /* discard ar_flip_flop */ - (void)bochs_vga_readb(bochs, VGA_IS1_RC); - /* blank or unblank; we need only update index and set 0x20 */ - bochs_vga_writeb(bochs, VGA_ATT_W, blank ? 0 : 0x20); -} - -void bochs_hw_setmode(struct bochs_device *bochs, - struct drm_display_mode *mode) -{ - int idx; - - if (!drm_dev_enter(bochs->dev, &idx)) - return; - - bochs->xres = mode->hdisplay; - bochs->yres = mode->vdisplay; - bochs->bpp = 32; - bochs->stride = mode->hdisplay * (bochs->bpp / 8); - bochs->yres_virtual = bochs->fb_size / bochs->stride; - - DRM_DEBUG_DRIVER("%dx%d @ %d bpp, vy %d\n", - bochs->xres, bochs->yres, bochs->bpp, - bochs->yres_virtual); - - bochs_hw_blank(bochs, false); - - bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE, 0); - bochs_dispi_write(bochs, VBE_DISPI_INDEX_BPP, bochs->bpp); - bochs_dispi_write(bochs, VBE_DISPI_INDEX_XRES, bochs->xres); - bochs_dispi_write(bochs, VBE_DISPI_INDEX_YRES, bochs->yres); - bochs_dispi_write(bochs, VBE_DISPI_INDEX_BANK, 0); - bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_WIDTH, bochs->xres); - bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_HEIGHT, - bochs->yres_virtual); - bochs_dispi_write(bochs, VBE_DISPI_INDEX_X_OFFSET, 0); - bochs_dispi_write(bochs, VBE_DISPI_INDEX_Y_OFFSET, 0); - - bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE, - VBE_DISPI_ENABLED | VBE_DISPI_LFB_ENABLED); - - drm_dev_exit(idx); -} - -void bochs_hw_setformat(struct bochs_device *bochs, - const struct drm_format_info *format) -{ - int idx; - - if (!drm_dev_enter(bochs->dev, &idx)) - return; - - DRM_DEBUG_DRIVER("format %c%c%c%c\n", - (format->format >> 0) & 0xff, - (format->format >> 8) & 0xff, - (format->format >> 16) & 0xff, - (format->format >> 24) & 0xff); - - switch (format->format) { - case DRM_FORMAT_XRGB8888: - bochs_hw_set_little_endian(bochs); - break; - case DRM_FORMAT_BGRX8888: - bochs_hw_set_big_endian(bochs); - break; - default: - /* should not happen */ - DRM_ERROR("%s: Huh? Got framebuffer format 0x%x", - __func__, format->format); - break; - } - - drm_dev_exit(idx); -} - -void bochs_hw_setbase(struct bochs_device *bochs, - int x, int y, int stride, u64 addr) -{ - unsigned long offset; - unsigned int vx, vy, vwidth, idx; - - if (!drm_dev_enter(bochs->dev, &idx)) - return; - - bochs->stride = stride; - offset = (unsigned long)addr + - y * bochs->stride + - x * (bochs->bpp / 8); - vy = offset / bochs->stride; - vx = (offset % bochs->stride) * 8 / bochs->bpp; - vwidth = stride * 8 / bochs->bpp; - - DRM_DEBUG_DRIVER("x %d, y %d, addr %llx -> offset %lx, vx %d, vy %d\n", - x, y, addr, offset, vx, vy); - bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_WIDTH, vwidth); - bochs_dispi_write(bochs, VBE_DISPI_INDEX_X_OFFSET, vx); - bochs_dispi_write(bochs, VBE_DISPI_INDEX_Y_OFFSET, vy); - - drm_dev_exit(idx); -} diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c deleted file mode 100644 index 99410e77d51a..000000000000 --- a/drivers/gpu/drm/bochs/bochs_kms.c +++ /dev/null @@ -1,178 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - */ - -#include <linux/moduleparam.h> - -#include <drm/drm_atomic_helper.h> -#include <drm/drm_gem_framebuffer_helper.h> -#include <drm/drm_probe_helper.h> - -#include "bochs.h" - -static int defx = 1024; -static int defy = 768; - -module_param(defx, int, 0444); -module_param(defy, int, 0444); -MODULE_PARM_DESC(defx, "default x resolution"); -MODULE_PARM_DESC(defy, "default y resolution"); - -/* ---------------------------------------------------------------------- */ - -static const uint32_t bochs_formats[] = { - DRM_FORMAT_XRGB8888, - DRM_FORMAT_BGRX8888, -}; - -static void bochs_plane_update(struct bochs_device *bochs, - struct drm_plane_state *state) -{ - struct drm_gem_vram_object *gbo; - s64 gpu_addr; - - if (!state->fb || !bochs->stride) - return; - - gbo = drm_gem_vram_of_gem(state->fb->obj[0]); - gpu_addr = drm_gem_vram_offset(gbo); - if (WARN_ON_ONCE(gpu_addr < 0)) - return; /* Bug: we didn't pin the BO to VRAM in prepare_fb. */ - - bochs_hw_setbase(bochs, - state->crtc_x, - state->crtc_y, - state->fb->pitches[0], - state->fb->offsets[0] + gpu_addr); - bochs_hw_setformat(bochs, state->fb->format); -} - -static void bochs_pipe_enable(struct drm_simple_display_pipe *pipe, - struct drm_crtc_state *crtc_state, - struct drm_plane_state *plane_state) -{ - struct bochs_device *bochs = pipe->crtc.dev->dev_private; - - bochs_hw_setmode(bochs, &crtc_state->mode); - bochs_plane_update(bochs, plane_state); -} - -static void bochs_pipe_disable(struct drm_simple_display_pipe *pipe) -{ - struct bochs_device *bochs = pipe->crtc.dev->dev_private; - - bochs_hw_blank(bochs, true); -} - -static void bochs_pipe_update(struct drm_simple_display_pipe *pipe, - struct drm_plane_state *old_state) -{ - struct bochs_device *bochs = pipe->crtc.dev->dev_private; - - bochs_plane_update(bochs, pipe->plane.state); -} - -static const struct drm_simple_display_pipe_funcs bochs_pipe_funcs = { - .enable = bochs_pipe_enable, - .disable = bochs_pipe_disable, - .update = bochs_pipe_update, - .prepare_fb = drm_gem_vram_simple_display_pipe_prepare_fb, - .cleanup_fb = drm_gem_vram_simple_display_pipe_cleanup_fb, -}; - -static int bochs_connector_get_modes(struct drm_connector *connector) -{ - struct bochs_device *bochs = - container_of(connector, struct bochs_device, connector); - int count = 0; - - if (bochs->edid) - count = drm_add_edid_modes(connector, bochs->edid); - - if (!count) { - count = drm_add_modes_noedid(connector, 8192, 8192); - drm_set_preferred_mode(connector, defx, defy); - } - return count; -} - -static const struct drm_connector_helper_funcs bochs_connector_connector_helper_funcs = { - .get_modes = bochs_connector_get_modes, -}; - -static const struct drm_connector_funcs bochs_connector_connector_funcs = { - .fill_modes = drm_helper_probe_single_connector_modes, - .destroy = drm_connector_cleanup, - .reset = drm_atomic_helper_connector_reset, - .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, - .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, -}; - -static void bochs_connector_init(struct drm_device *dev) -{ - struct bochs_device *bochs = dev->dev_private; - struct drm_connector *connector = &bochs->connector; - - drm_connector_init(dev, connector, &bochs_connector_connector_funcs, - DRM_MODE_CONNECTOR_VIRTUAL); - drm_connector_helper_add(connector, - &bochs_connector_connector_helper_funcs); - - bochs_hw_load_edid(bochs); - if (bochs->edid) { - DRM_INFO("Found EDID data blob.\n"); - drm_connector_attach_edid_property(connector); - drm_connector_update_edid_property(connector, bochs->edid); - } -} - -static struct drm_framebuffer * -bochs_gem_fb_create(struct drm_device *dev, struct drm_file *file, - const struct drm_mode_fb_cmd2 *mode_cmd) -{ - if (mode_cmd->pixel_format != DRM_FORMAT_XRGB8888 && - mode_cmd->pixel_format != DRM_FORMAT_BGRX8888) - return ERR_PTR(-EINVAL); - - return drm_gem_fb_create(dev, file, mode_cmd); -} - -const struct drm_mode_config_funcs bochs_mode_funcs = { - .fb_create = bochs_gem_fb_create, - .mode_valid = drm_vram_helper_mode_valid, - .atomic_check = drm_atomic_helper_check, - .atomic_commit = drm_atomic_helper_commit, -}; - -int bochs_kms_init(struct bochs_device *bochs) -{ - int ret; - - ret = drmm_mode_config_init(bochs->dev); - if (ret) - return ret; - - bochs->dev->mode_config.max_width = 8192; - bochs->dev->mode_config.max_height = 8192; - - bochs->dev->mode_config.fb_base = bochs->fb_base; - bochs->dev->mode_config.preferred_depth = 24; - bochs->dev->mode_config.prefer_shadow = 0; - bochs->dev->mode_config.prefer_shadow_fbdev = 1; - bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true; - - bochs->dev->mode_config.funcs = &bochs_mode_funcs; - - bochs_connector_init(bochs->dev); - drm_simple_display_pipe_init(bochs->dev, - &bochs->pipe, - &bochs_pipe_funcs, - bochs_formats, - ARRAY_SIZE(bochs_formats), - NULL, - &bochs->connector); - - drm_mode_config_reset(bochs->dev); - - return 0; -} diff --git a/drivers/gpu/drm/bochs/bochs_mm.c b/drivers/gpu/drm/bochs/bochs_mm.c deleted file mode 100644 index 1b74f530b07c..000000000000 --- a/drivers/gpu/drm/bochs/bochs_mm.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - */ - -#include "bochs.h" - -/* ---------------------------------------------------------------------- */ - -int bochs_mm_init(struct bochs_device *bochs) -{ - struct drm_vram_mm *vmm; - - vmm = drm_vram_helper_alloc_mm(bochs->dev, bochs->fb_base, - bochs->fb_size); - return PTR_ERR_OR_ZERO(vmm); -} - -void bochs_mm_fini(struct bochs_device *bochs) -{ - if (!bochs->dev->vram_mm) - return; - - drm_vram_helper_release_mm(bochs->dev); -} diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index 85b673613687..431b6e12a81f 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -303,6 +303,7 @@ config DRM_TI_SN65DSI86 select DRM_PANEL select DRM_MIPI_DSI select AUXILIARY_BUS + select DRM_DP_AUX_BUS help Texas Instruments SN65DSI86 DSI to eDP Bridge driver diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c index 7519b7a0f29d..a3d82377066b 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.c +++ b/drivers/gpu/drm/bridge/analogix/anx7625.c @@ -1730,7 +1730,6 @@ static int __maybe_unused anx7625_suspend(struct device *dev) if (!pm_runtime_enabled(dev) || !pm_runtime_suspended(dev)) { anx7625_runtime_pm_suspend(dev); disable_irq(ctx->pdata.intp_irq); - flush_workqueue(ctx->workqueue); } return 0; @@ -1790,7 +1789,8 @@ static int anx7625_i2c_probe(struct i2c_client *client, platform->pdata.intp_irq = client->irq; if (platform->pdata.intp_irq) { INIT_WORK(&platform->work, anx7625_work_func); - platform->workqueue = create_workqueue("anx7625_work"); + platform->workqueue = alloc_workqueue("anx7625_work", + WQ_FREEZABLE | WQ_MEM_RECLAIM, 1); if (!platform->workqueue) { DRM_DEV_ERROR(dev, "fail to create work queue\n"); ret = -ENOMEM; @@ -1874,6 +1874,7 @@ static const struct of_device_id anx_match_table[] = { {.compatible = "analogix,anx7625",}, {}, }; +MODULE_DEVICE_TABLE(of, anx_match_table); static struct i2c_driver anx7625_driver = { .driver = { diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c index 873995f0a741..d7986067eefe 100644 --- a/drivers/gpu/drm/bridge/nwl-dsi.c +++ b/drivers/gpu/drm/bridge/nwl-dsi.c @@ -48,12 +48,6 @@ enum transfer_direction { #define NWL_DSI_ENDPOINT_LCDIF 0 #define NWL_DSI_ENDPOINT_DCSS 1 -struct nwl_dsi_plat_clk_config { - const char *id; - struct clk *clk; - bool present; -}; - struct nwl_dsi_transfer { const struct mipi_dsi_msg *msg; struct mipi_dsi_packet packet; diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index 750f2172ef08..a32f70bc68ea 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -137,7 +137,6 @@ enum sn65dsi83_model { struct sn65dsi83 { struct drm_bridge bridge; - struct drm_display_mode mode; struct device *dev; struct regmap *regmap; struct device_node *host_node; @@ -147,8 +146,6 @@ struct sn65dsi83 { int dsi_lanes; bool lvds_dual_link; bool lvds_dual_link_even_odd_swap; - bool lvds_format_24bpp; - bool lvds_format_jeida; }; static const struct regmap_range sn65dsi83_readable_ranges[] = { @@ -291,7 +288,8 @@ err_dsi_attach: return ret; } -static void sn65dsi83_pre_enable(struct drm_bridge *bridge) +static void sn65dsi83_atomic_pre_enable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) { struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); @@ -306,7 +304,8 @@ static void sn65dsi83_pre_enable(struct drm_bridge *bridge) usleep_range(1000, 1100); } -static u8 sn65dsi83_get_lvds_range(struct sn65dsi83 *ctx) +static u8 sn65dsi83_get_lvds_range(struct sn65dsi83 *ctx, + const struct drm_display_mode *mode) { /* * The encoding of the LVDS_CLK_RANGE is as follows: @@ -322,7 +321,7 @@ static u8 sn65dsi83_get_lvds_range(struct sn65dsi83 *ctx) * the clock to 25..154 MHz, the range calculation can be simplified * as follows: */ - int mode_clock = ctx->mode.clock; + int mode_clock = mode->clock; if (ctx->lvds_dual_link) mode_clock /= 2; @@ -330,7 +329,8 @@ static u8 sn65dsi83_get_lvds_range(struct sn65dsi83 *ctx) return (mode_clock - 12500) / 25000; } -static u8 sn65dsi83_get_dsi_range(struct sn65dsi83 *ctx) +static u8 sn65dsi83_get_dsi_range(struct sn65dsi83 *ctx, + const struct drm_display_mode *mode) { /* * The encoding of the CHA_DSI_CLK_RANGE is as follows: @@ -346,7 +346,7 @@ static u8 sn65dsi83_get_dsi_range(struct sn65dsi83 *ctx) * DSI_CLK = mode clock * bpp / dsi_data_lanes / 2 * the 2 is there because the bus is DDR. */ - return DIV_ROUND_UP(clamp((unsigned int)ctx->mode.clock * + return DIV_ROUND_UP(clamp((unsigned int)mode->clock * mipi_dsi_pixel_format_to_bpp(ctx->dsi->format) / ctx->dsi_lanes / 2, 40000U, 500000U), 5000U); } @@ -364,23 +364,73 @@ static u8 sn65dsi83_get_dsi_div(struct sn65dsi83 *ctx) return dsi_div - 1; } -static void sn65dsi83_enable(struct drm_bridge *bridge) +static void sn65dsi83_atomic_enable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) { struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); + struct drm_atomic_state *state = old_bridge_state->base.state; + const struct drm_bridge_state *bridge_state; + const struct drm_crtc_state *crtc_state; + const struct drm_display_mode *mode; + struct drm_connector *connector; + struct drm_crtc *crtc; + bool lvds_format_24bpp; + bool lvds_format_jeida; unsigned int pval; + __le16 le16val; u16 val; int ret; + /* Get the LVDS format from the bridge state. */ + bridge_state = drm_atomic_get_new_bridge_state(state, bridge); + + switch (bridge_state->output_bus_cfg.format) { + case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG: + lvds_format_24bpp = false; + lvds_format_jeida = true; + break; + case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA: + lvds_format_24bpp = true; + lvds_format_jeida = true; + break; + case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG: + lvds_format_24bpp = true; + lvds_format_jeida = false; + break; + default: + /* + * Some bridges still don't set the correct + * LVDS bus pixel format, use SPWG24 default + * format until those are fixed. + */ + lvds_format_24bpp = true; + lvds_format_jeida = false; + dev_warn(ctx->dev, + "Unsupported LVDS bus format 0x%04x, please check output bridge driver. Falling back to SPWG24.\n", + bridge_state->output_bus_cfg.format); + break; + } + + /* + * Retrieve the CRTC adjusted mode. This requires a little dance to go + * from the bridge to the encoder, to the connector and to the CRTC. + */ + connector = drm_atomic_get_new_connector_for_encoder(state, + bridge->encoder); + crtc = drm_atomic_get_new_connector_state(state, connector)->crtc; + crtc_state = drm_atomic_get_new_crtc_state(state, crtc); + mode = &crtc_state->adjusted_mode; + /* Clear reset, disable PLL */ regmap_write(ctx->regmap, REG_RC_RESET, 0x00); regmap_write(ctx->regmap, REG_RC_PLL_EN, 0x00); /* Reference clock derived from DSI link clock. */ regmap_write(ctx->regmap, REG_RC_LVDS_PLL, - REG_RC_LVDS_PLL_LVDS_CLK_RANGE(sn65dsi83_get_lvds_range(ctx)) | + REG_RC_LVDS_PLL_LVDS_CLK_RANGE(sn65dsi83_get_lvds_range(ctx, mode)) | REG_RC_LVDS_PLL_HS_CLK_SRC_DPHY); regmap_write(ctx->regmap, REG_DSI_CLK, - REG_DSI_CLK_CHA_DSI_CLK_RANGE(sn65dsi83_get_dsi_range(ctx))); + REG_DSI_CLK_CHA_DSI_CLK_RANGE(sn65dsi83_get_dsi_range(ctx, mode))); regmap_write(ctx->regmap, REG_RC_DSI_CLK, REG_RC_DSI_CLK_DSI_CLK_DIVIDER(sn65dsi83_get_dsi_div(ctx))); @@ -394,20 +444,20 @@ static void sn65dsi83_enable(struct drm_bridge *bridge) regmap_write(ctx->regmap, REG_DSI_EQ, 0x00); /* Set up sync signal polarity. */ - val = (ctx->mode.flags & DRM_MODE_FLAG_NHSYNC ? + val = (mode->flags & DRM_MODE_FLAG_NHSYNC ? REG_LVDS_FMT_HS_NEG_POLARITY : 0) | - (ctx->mode.flags & DRM_MODE_FLAG_NVSYNC ? + (mode->flags & DRM_MODE_FLAG_NVSYNC ? REG_LVDS_FMT_VS_NEG_POLARITY : 0); /* Set up bits-per-pixel, 18bpp or 24bpp. */ - if (ctx->lvds_format_24bpp) { + if (lvds_format_24bpp) { val |= REG_LVDS_FMT_CHA_24BPP_MODE; if (ctx->lvds_dual_link) val |= REG_LVDS_FMT_CHB_24BPP_MODE; } /* Set up LVDS format, JEIDA/Format 1 or SPWG/Format 2 */ - if (ctx->lvds_format_jeida) { + if (lvds_format_jeida) { val |= REG_LVDS_FMT_CHA_24BPP_FORMAT1; if (ctx->lvds_dual_link) val |= REG_LVDS_FMT_CHB_24BPP_FORMAT1; @@ -426,29 +476,29 @@ static void sn65dsi83_enable(struct drm_bridge *bridge) REG_LVDS_LANE_CHB_LVDS_TERM); regmap_write(ctx->regmap, REG_LVDS_CM, 0x00); - val = cpu_to_le16(ctx->mode.hdisplay); + le16val = cpu_to_le16(mode->hdisplay); regmap_bulk_write(ctx->regmap, REG_VID_CHA_ACTIVE_LINE_LENGTH_LOW, - &val, 2); - val = cpu_to_le16(ctx->mode.vdisplay); + &le16val, 2); + le16val = cpu_to_le16(mode->vdisplay); regmap_bulk_write(ctx->regmap, REG_VID_CHA_VERTICAL_DISPLAY_SIZE_LOW, - &val, 2); + &le16val, 2); /* 32 + 1 pixel clock to ensure proper operation */ - val = cpu_to_le16(32 + 1); - regmap_bulk_write(ctx->regmap, REG_VID_CHA_SYNC_DELAY_LOW, &val, 2); - val = cpu_to_le16(ctx->mode.hsync_end - ctx->mode.hsync_start); + le16val = cpu_to_le16(32 + 1); + regmap_bulk_write(ctx->regmap, REG_VID_CHA_SYNC_DELAY_LOW, &le16val, 2); + le16val = cpu_to_le16(mode->hsync_end - mode->hsync_start); regmap_bulk_write(ctx->regmap, REG_VID_CHA_HSYNC_PULSE_WIDTH_LOW, - &val, 2); - val = cpu_to_le16(ctx->mode.vsync_end - ctx->mode.vsync_start); + &le16val, 2); + le16val = cpu_to_le16(mode->vsync_end - mode->vsync_start); regmap_bulk_write(ctx->regmap, REG_VID_CHA_VSYNC_PULSE_WIDTH_LOW, - &val, 2); + &le16val, 2); regmap_write(ctx->regmap, REG_VID_CHA_HORIZONTAL_BACK_PORCH, - ctx->mode.htotal - ctx->mode.hsync_end); + mode->htotal - mode->hsync_end); regmap_write(ctx->regmap, REG_VID_CHA_VERTICAL_BACK_PORCH, - ctx->mode.vtotal - ctx->mode.vsync_end); + mode->vtotal - mode->vsync_end); regmap_write(ctx->regmap, REG_VID_CHA_HORIZONTAL_FRONT_PORCH, - ctx->mode.hsync_start - ctx->mode.hdisplay); + mode->hsync_start - mode->hdisplay); regmap_write(ctx->regmap, REG_VID_CHA_VERTICAL_FRONT_PORCH, - ctx->mode.vsync_start - ctx->mode.vdisplay); + mode->vsync_start - mode->vdisplay); regmap_write(ctx->regmap, REG_VID_CHA_TEST_PATTERN, 0x00); /* Enable PLL */ @@ -472,7 +522,8 @@ static void sn65dsi83_enable(struct drm_bridge *bridge) regmap_write(ctx->regmap, REG_IRQ_STAT, pval); } -static void sn65dsi83_disable(struct drm_bridge *bridge) +static void sn65dsi83_atomic_disable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) { struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); @@ -481,7 +532,8 @@ static void sn65dsi83_disable(struct drm_bridge *bridge) regmap_write(ctx->regmap, REG_RC_PLL_EN, 0x00); } -static void sn65dsi83_post_disable(struct drm_bridge *bridge) +static void sn65dsi83_atomic_post_disable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) { struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); @@ -503,70 +555,44 @@ sn65dsi83_mode_valid(struct drm_bridge *bridge, return MODE_OK; } -static void sn65dsi83_mode_set(struct drm_bridge *bridge, - const struct drm_display_mode *mode, - const struct drm_display_mode *adj) -{ - struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); +#define MAX_INPUT_SEL_FORMATS 1 - ctx->mode = *adj; -} - -static bool sn65dsi83_mode_fixup(struct drm_bridge *bridge, - const struct drm_display_mode *mode, - struct drm_display_mode *adj) +static u32 * +sn65dsi83_atomic_get_input_bus_fmts(struct drm_bridge *bridge, + struct drm_bridge_state *bridge_state, + struct drm_crtc_state *crtc_state, + struct drm_connector_state *conn_state, + u32 output_fmt, + unsigned int *num_input_fmts) { - struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge); - u32 input_bus_format = MEDIA_BUS_FMT_RGB888_1X24; - struct drm_encoder *encoder = bridge->encoder; - struct drm_device *ddev = encoder->dev; - struct drm_connector *connector; + u32 *input_fmts; - /* The DSI format is always RGB888_1X24 */ - list_for_each_entry(connector, &ddev->mode_config.connector_list, head) { - switch (connector->display_info.bus_formats[0]) { - case MEDIA_BUS_FMT_RGB666_1X7X3_SPWG: - ctx->lvds_format_24bpp = false; - ctx->lvds_format_jeida = true; - break; - case MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA: - ctx->lvds_format_24bpp = true; - ctx->lvds_format_jeida = true; - break; - case MEDIA_BUS_FMT_RGB888_1X7X4_SPWG: - ctx->lvds_format_24bpp = true; - ctx->lvds_format_jeida = false; - break; - default: - /* - * Some bridges still don't set the correct - * LVDS bus pixel format, use SPWG24 default - * format until those are fixed. - */ - ctx->lvds_format_24bpp = true; - ctx->lvds_format_jeida = false; - dev_warn(ctx->dev, - "Unsupported LVDS bus format 0x%04x, please check output bridge driver. Falling back to SPWG24.\n", - connector->display_info.bus_formats[0]); - break; - } + *num_input_fmts = 0; - drm_display_info_set_bus_formats(&connector->display_info, - &input_bus_format, 1); - } + input_fmts = kcalloc(MAX_INPUT_SEL_FORMATS, sizeof(*input_fmts), + GFP_KERNEL); + if (!input_fmts) + return NULL; + + /* This is the DSI-end bus format */ + input_fmts[0] = MEDIA_BUS_FMT_RGB888_1X24; + *num_input_fmts = 1; - return true; + return input_fmts; } static const struct drm_bridge_funcs sn65dsi83_funcs = { - .attach = sn65dsi83_attach, - .pre_enable = sn65dsi83_pre_enable, - .enable = sn65dsi83_enable, - .disable = sn65dsi83_disable, - .post_disable = sn65dsi83_post_disable, - .mode_valid = sn65dsi83_mode_valid, - .mode_set = sn65dsi83_mode_set, - .mode_fixup = sn65dsi83_mode_fixup, + .attach = sn65dsi83_attach, + .atomic_pre_enable = sn65dsi83_atomic_pre_enable, + .atomic_enable = sn65dsi83_atomic_enable, + .atomic_disable = sn65dsi83_atomic_disable, + .atomic_post_disable = sn65dsi83_atomic_post_disable, + .mode_valid = sn65dsi83_mode_valid, + + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, + .atomic_reset = drm_atomic_helper_bridge_reset, + .atomic_get_input_bus_fmts = sn65dsi83_atomic_get_input_bus_fmts, }; static int sn65dsi83_parse_dt(struct sn65dsi83 *ctx, enum sn65dsi83_model model) diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 45a2969afb2b..9bf889302bcc 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -23,6 +23,7 @@ #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_bridge.h> +#include <drm/drm_dp_aux_bus.h> #include <drm/drm_dp_helper.h> #include <drm/drm_mipi_dsi.h> #include <drm/drm_of.h> @@ -116,6 +117,7 @@ * struct ti_sn65dsi86 - Platform data for ti-sn65dsi86 driver. * @bridge_aux: AUX-bus sub device for MIPI-to-eDP bridge functionality. * @gpio_aux: AUX-bus sub device for GPIO controller functionality. + * @aux_aux: AUX-bus sub device for eDP AUX channel functionality. * * @dev: Pointer to the top level (i2c) device. * @regmap: Regmap for accessing i2c. @@ -124,9 +126,8 @@ * @connector: Our connector. * @host_node: Remote DSI node. * @dsi: Our MIPI DSI source. - * @edid: Detected EDID of eDP panel. * @refclk: Our reference clock. - * @panel: Our panel. + * @next_bridge: The bridge on the eDP side. * @enable_gpio: The GPIO we toggle to enable the bridge. * @supplies: Data for bulk enabling/disabling our regulators. * @dp_lanes: Count of dp_lanes we're using. @@ -148,17 +149,17 @@ struct ti_sn65dsi86 { struct auxiliary_device bridge_aux; struct auxiliary_device gpio_aux; + struct auxiliary_device aux_aux; struct device *dev; struct regmap *regmap; struct drm_dp_aux aux; struct drm_bridge bridge; struct drm_connector connector; - struct edid *edid; struct device_node *host_node; struct mipi_dsi_device *dsi; struct clk *refclk; - struct drm_panel *panel; + struct drm_bridge *next_bridge; struct gpio_desc *enable_gpio; struct regulator_bulk_data supplies[SN_REGULATOR_SUPPLY_NUM]; int dp_lanes; @@ -393,35 +394,222 @@ static void ti_sn65dsi86_debugfs_init(struct ti_sn65dsi86 *pdata) debugfs_create_file("status", 0600, debugfs, pdata, &status_fops); } -/* Connector funcs */ -static struct ti_sn65dsi86 * -connector_to_ti_sn65dsi86(struct drm_connector *connector) +/* ----------------------------------------------------------------------------- + * Auxiliary Devices (*not* AUX) + */ + +static void ti_sn65dsi86_uninit_aux(void *data) { - return container_of(connector, struct ti_sn65dsi86, connector); + auxiliary_device_uninit(data); } -static int ti_sn_bridge_connector_get_modes(struct drm_connector *connector) +static void ti_sn65dsi86_delete_aux(void *data) { - struct ti_sn65dsi86 *pdata = connector_to_ti_sn65dsi86(connector); - struct edid *edid = pdata->edid; - int num, ret; + auxiliary_device_delete(data); +} - if (!edid) { - pm_runtime_get_sync(pdata->dev); - edid = pdata->edid = drm_get_edid(connector, &pdata->aux.ddc); - pm_runtime_put_autosuspend(pdata->dev); +/* + * AUX bus docs say that a non-NULL release is mandatory, but it makes no + * sense for the model used here where all of the aux devices are allocated + * in the single shared structure. We'll use this noop as a workaround. + */ +static void ti_sn65dsi86_noop(struct device *dev) {} + +static int ti_sn65dsi86_add_aux_device(struct ti_sn65dsi86 *pdata, + struct auxiliary_device *aux, + const char *name) +{ + struct device *dev = pdata->dev; + int ret; + + aux->name = name; + aux->dev.parent = dev; + aux->dev.release = ti_sn65dsi86_noop; + device_set_of_node_from_dev(&aux->dev, dev); + ret = auxiliary_device_init(aux); + if (ret) + return ret; + ret = devm_add_action_or_reset(dev, ti_sn65dsi86_uninit_aux, aux); + if (ret) + return ret; + + ret = auxiliary_device_add(aux); + if (ret) + return ret; + ret = devm_add_action_or_reset(dev, ti_sn65dsi86_delete_aux, aux); + + return ret; +} + +/* ----------------------------------------------------------------------------- + * AUX Adapter + */ + +static struct ti_sn65dsi86 *aux_to_ti_sn65dsi86(struct drm_dp_aux *aux) +{ + return container_of(aux, struct ti_sn65dsi86, aux); +} + +static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux, + struct drm_dp_aux_msg *msg) +{ + struct ti_sn65dsi86 *pdata = aux_to_ti_sn65dsi86(aux); + u32 request = msg->request & ~(DP_AUX_I2C_MOT | DP_AUX_I2C_WRITE_STATUS_UPDATE); + u32 request_val = AUX_CMD_REQ(msg->request); + u8 *buf = msg->buffer; + unsigned int len = msg->size; + unsigned int val; + int ret; + u8 addr_len[SN_AUX_LENGTH_REG + 1 - SN_AUX_ADDR_19_16_REG]; + + if (len > SN_AUX_MAX_PAYLOAD_BYTES) + return -EINVAL; + + pm_runtime_get_sync(pdata->dev); + mutex_lock(&pdata->comms_mutex); + + /* + * If someone tries to do a DDC over AUX transaction before pre_enable() + * on a device without a dedicated reference clock then we just can't + * do it. Fail right away. This prevents non-refclk users from reading + * the EDID before enabling the panel but such is life. + */ + if (!pdata->comms_enabled) { + ret = -EIO; + goto exit; } - if (edid && drm_edid_is_valid(edid)) { - ret = drm_connector_update_edid_property(connector, edid); - if (!ret) { - num = drm_add_edid_modes(connector, edid); - if (num) - return num; + switch (request) { + case DP_AUX_NATIVE_WRITE: + case DP_AUX_I2C_WRITE: + case DP_AUX_NATIVE_READ: + case DP_AUX_I2C_READ: + regmap_write(pdata->regmap, SN_AUX_CMD_REG, request_val); + /* Assume it's good */ + msg->reply = 0; + break; + default: + ret = -EINVAL; + goto exit; + } + + BUILD_BUG_ON(sizeof(addr_len) != sizeof(__be32)); + put_unaligned_be32((msg->address & SN_AUX_ADDR_MASK) << 8 | len, + addr_len); + regmap_bulk_write(pdata->regmap, SN_AUX_ADDR_19_16_REG, addr_len, + ARRAY_SIZE(addr_len)); + + if (request == DP_AUX_NATIVE_WRITE || request == DP_AUX_I2C_WRITE) + regmap_bulk_write(pdata->regmap, SN_AUX_WDATA_REG(0), buf, len); + + /* Clear old status bits before start so we don't get confused */ + regmap_write(pdata->regmap, SN_AUX_CMD_STATUS_REG, + AUX_IRQ_STATUS_NAT_I2C_FAIL | + AUX_IRQ_STATUS_AUX_RPLY_TOUT | + AUX_IRQ_STATUS_AUX_SHORT); + + regmap_write(pdata->regmap, SN_AUX_CMD_REG, request_val | AUX_CMD_SEND); + + /* Zero delay loop because i2c transactions are slow already */ + ret = regmap_read_poll_timeout(pdata->regmap, SN_AUX_CMD_REG, val, + !(val & AUX_CMD_SEND), 0, 50 * 1000); + if (ret) + goto exit; + + ret = regmap_read(pdata->regmap, SN_AUX_CMD_STATUS_REG, &val); + if (ret) + goto exit; + + if (val & AUX_IRQ_STATUS_AUX_RPLY_TOUT) { + /* + * The hardware tried the message seven times per the DP spec + * but it hit a timeout. We ignore defers here because they're + * handled in hardware. + */ + ret = -ETIMEDOUT; + goto exit; + } + + if (val & AUX_IRQ_STATUS_AUX_SHORT) { + ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &len); + if (ret) + goto exit; + } else if (val & AUX_IRQ_STATUS_NAT_I2C_FAIL) { + switch (request) { + case DP_AUX_I2C_WRITE: + case DP_AUX_I2C_READ: + msg->reply |= DP_AUX_I2C_REPLY_NACK; + break; + case DP_AUX_NATIVE_READ: + case DP_AUX_NATIVE_WRITE: + msg->reply |= DP_AUX_NATIVE_REPLY_NACK; + break; } + len = 0; + goto exit; } - return drm_panel_get_modes(pdata->panel, connector); + if (request != DP_AUX_NATIVE_WRITE && request != DP_AUX_I2C_WRITE && len != 0) + ret = regmap_bulk_read(pdata->regmap, SN_AUX_RDATA_REG(0), buf, len); + +exit: + mutex_unlock(&pdata->comms_mutex); + pm_runtime_mark_last_busy(pdata->dev); + pm_runtime_put_autosuspend(pdata->dev); + + if (ret) + return ret; + return len; +} + +static int ti_sn_aux_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) +{ + struct ti_sn65dsi86 *pdata = dev_get_drvdata(adev->dev.parent); + int ret; + + pdata->aux.name = "ti-sn65dsi86-aux"; + pdata->aux.dev = &adev->dev; + pdata->aux.transfer = ti_sn_aux_transfer; + drm_dp_aux_init(&pdata->aux); + + ret = devm_of_dp_aux_populate_ep_devices(&pdata->aux); + if (ret) + return ret; + + /* + * The eDP to MIPI bridge parts don't work until the AUX channel is + * setup so we don't add it in the main driver probe, we add it now. + */ + return ti_sn65dsi86_add_aux_device(pdata, &pdata->bridge_aux, "bridge"); +} + +static const struct auxiliary_device_id ti_sn_aux_id_table[] = { + { .name = "ti_sn65dsi86.aux", }, + {}, +}; + +static struct auxiliary_driver ti_sn_aux_driver = { + .name = "aux", + .probe = ti_sn_aux_probe, + .id_table = ti_sn_aux_id_table, +}; + +/* ----------------------------------------------------------------------------- + * DRM Connector Operations + */ + +static struct ti_sn65dsi86 * +connector_to_ti_sn65dsi86(struct drm_connector *connector) +{ + return container_of(connector, struct ti_sn65dsi86, connector); +} + +static int ti_sn_bridge_connector_get_modes(struct drm_connector *connector) +{ + struct ti_sn65dsi86 *pdata = connector_to_ti_sn65dsi86(connector); + + return drm_bridge_get_modes(pdata->next_bridge, connector); } static enum drm_mode_status @@ -448,23 +636,32 @@ static const struct drm_connector_funcs ti_sn_bridge_connector_funcs = { .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; -static struct ti_sn65dsi86 *bridge_to_ti_sn65dsi86(struct drm_bridge *bridge) +static int ti_sn_bridge_connector_init(struct ti_sn65dsi86 *pdata) { - return container_of(bridge, struct ti_sn65dsi86, bridge); -} + int ret; -static int ti_sn65dsi86_parse_regulators(struct ti_sn65dsi86 *pdata) -{ - unsigned int i; - const char * const ti_sn_bridge_supply_names[] = { - "vcca", "vcc", "vccio", "vpll", - }; + ret = drm_connector_init(pdata->bridge.dev, &pdata->connector, + &ti_sn_bridge_connector_funcs, + DRM_MODE_CONNECTOR_eDP); + if (ret) { + DRM_ERROR("Failed to initialize connector with drm\n"); + return ret; + } - for (i = 0; i < SN_REGULATOR_SUPPLY_NUM; i++) - pdata->supplies[i].supply = ti_sn_bridge_supply_names[i]; + drm_connector_helper_add(&pdata->connector, + &ti_sn_bridge_connector_helper_funcs); + drm_connector_attach_encoder(&pdata->connector, pdata->bridge.encoder); - return devm_regulator_bulk_get(pdata->dev, SN_REGULATOR_SUPPLY_NUM, - pdata->supplies); + return 0; +} + +/*------------------------------------------------------------------------------ + * DRM Bridge + */ + +static struct ti_sn65dsi86 *bridge_to_ti_sn65dsi86(struct drm_bridge *bridge) +{ + return container_of(bridge, struct ti_sn65dsi86, bridge); } static int ti_sn_bridge_attach(struct drm_bridge *bridge, @@ -491,17 +688,9 @@ static int ti_sn_bridge_attach(struct drm_bridge *bridge, return ret; } - ret = drm_connector_init(bridge->dev, &pdata->connector, - &ti_sn_bridge_connector_funcs, - DRM_MODE_CONNECTOR_eDP); - if (ret) { - DRM_ERROR("Failed to initialize connector with drm\n"); + ret = ti_sn_bridge_connector_init(pdata); + if (ret < 0) goto err_conn_init; - } - - drm_connector_helper_add(&pdata->connector, - &ti_sn_bridge_connector_helper_funcs); - drm_connector_attach_encoder(&pdata->connector, bridge->encoder); /* * TODO: ideally finding host resource and dsi dev registration needs @@ -547,8 +736,16 @@ static int ti_sn_bridge_attach(struct drm_bridge *bridge, } pdata->dsi = dsi; + /* Attach the next bridge */ + ret = drm_bridge_attach(bridge->encoder, pdata->next_bridge, + &pdata->bridge, flags); + if (ret < 0) + goto err_dsi_detach; + return 0; +err_dsi_detach: + mipi_dsi_detach(dsi); err_dsi_attach: mipi_dsi_device_unregister(dsi); err_dsi_host: @@ -567,8 +764,6 @@ static void ti_sn_bridge_disable(struct drm_bridge *bridge) { struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge); - drm_panel_disable(pdata->panel); - /* disable video stream */ regmap_update_bits(pdata->regmap, SN_ENH_FRAME_REG, VSTREAM_ENABLE, 0); /* semi auto link training mode OFF */ @@ -633,9 +828,9 @@ static int ti_sn_bridge_calc_min_dp_rate_idx(struct ti_sn65dsi86 *pdata) return i; } -static void ti_sn_bridge_read_valid_rates(struct ti_sn65dsi86 *pdata, - bool rate_valid[]) +static unsigned int ti_sn_bridge_read_valid_rates(struct ti_sn65dsi86 *pdata) { + unsigned int valid_rates = 0; unsigned int rate_per_200khz; unsigned int rate_mhz; u8 dpcd_val; @@ -675,13 +870,13 @@ static void ti_sn_bridge_read_valid_rates(struct ti_sn65dsi86 *pdata, j < ARRAY_SIZE(ti_sn_bridge_dp_rate_lut); j++) { if (ti_sn_bridge_dp_rate_lut[j] == rate_mhz) - rate_valid[j] = true; + valid_rates |= BIT(j); } } for (i = 0; i < ARRAY_SIZE(ti_sn_bridge_dp_rate_lut); i++) { - if (rate_valid[i]) - return; + if (valid_rates & BIT(i)) + return valid_rates; } DRM_DEV_ERROR(pdata->dev, "No matching eDP rates in table; falling back\n"); @@ -703,15 +898,17 @@ static void ti_sn_bridge_read_valid_rates(struct ti_sn65dsi86 *pdata, (int)dpcd_val); fallthrough; case DP_LINK_BW_5_4: - rate_valid[7] = 1; + valid_rates |= BIT(7); fallthrough; case DP_LINK_BW_2_7: - rate_valid[4] = 1; + valid_rates |= BIT(4); fallthrough; case DP_LINK_BW_1_62: - rate_valid[1] = 1; + valid_rates |= BIT(1); break; } + + return valid_rates; } static void ti_sn_bridge_set_video_timings(struct ti_sn65dsi86 *pdata) @@ -829,8 +1026,8 @@ exit: static void ti_sn_bridge_enable(struct drm_bridge *bridge) { struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge); - bool rate_valid[ARRAY_SIZE(ti_sn_bridge_dp_rate_lut)] = { }; const char *last_err_str = "No supported DP rate"; + unsigned int valid_rates; int dp_rate_idx; unsigned int val; int ret = -EINVAL; @@ -869,13 +1066,13 @@ static void ti_sn_bridge_enable(struct drm_bridge *bridge) regmap_update_bits(pdata->regmap, SN_SSC_CONFIG_REG, DP_NUM_LANES_MASK, val); - ti_sn_bridge_read_valid_rates(pdata, rate_valid); + valid_rates = ti_sn_bridge_read_valid_rates(pdata); /* Train until we run out of rates */ for (dp_rate_idx = ti_sn_bridge_calc_min_dp_rate_idx(pdata); dp_rate_idx < ARRAY_SIZE(ti_sn_bridge_dp_rate_lut); dp_rate_idx++) { - if (!rate_valid[dp_rate_idx]) + if (!(valid_rates & BIT(dp_rate_idx))) continue; ret = ti_sn_link_training(pdata, dp_rate_idx, &last_err_str); @@ -893,8 +1090,6 @@ static void ti_sn_bridge_enable(struct drm_bridge *bridge) /* enable video stream */ regmap_update_bits(pdata->regmap, SN_ENH_FRAME_REG, VSTREAM_ENABLE, VSTREAM_ENABLE); - - drm_panel_enable(pdata->panel); } static void ti_sn_bridge_pre_enable(struct drm_bridge *bridge) @@ -905,16 +1100,12 @@ static void ti_sn_bridge_pre_enable(struct drm_bridge *bridge) if (!pdata->refclk) ti_sn65dsi86_enable_comms(pdata); - - drm_panel_prepare(pdata->panel); } static void ti_sn_bridge_post_disable(struct drm_bridge *bridge) { struct ti_sn65dsi86 *pdata = bridge_to_ti_sn65dsi86(bridge); - drm_panel_unprepare(pdata->panel); - if (!pdata->refclk) ti_sn65dsi86_disable_comms(pdata); @@ -930,137 +1121,135 @@ static const struct drm_bridge_funcs ti_sn_bridge_funcs = { .post_disable = ti_sn_bridge_post_disable, }; -static struct ti_sn65dsi86 *aux_to_ti_sn65dsi86(struct drm_dp_aux *aux) -{ - return container_of(aux, struct ti_sn65dsi86, aux); -} - -static ssize_t ti_sn_aux_transfer(struct drm_dp_aux *aux, - struct drm_dp_aux_msg *msg) +static void ti_sn_bridge_parse_lanes(struct ti_sn65dsi86 *pdata, + struct device_node *np) { - struct ti_sn65dsi86 *pdata = aux_to_ti_sn65dsi86(aux); - u32 request = msg->request & ~(DP_AUX_I2C_MOT | DP_AUX_I2C_WRITE_STATUS_UPDATE); - u32 request_val = AUX_CMD_REQ(msg->request); - u8 *buf = msg->buffer; - unsigned int len = msg->size; - unsigned int val; - int ret; - u8 addr_len[SN_AUX_LENGTH_REG + 1 - SN_AUX_ADDR_19_16_REG]; - - if (len > SN_AUX_MAX_PAYLOAD_BYTES) - return -EINVAL; - - pm_runtime_get_sync(pdata->dev); - mutex_lock(&pdata->comms_mutex); + u32 lane_assignments[SN_MAX_DP_LANES] = { 0, 1, 2, 3 }; + u32 lane_polarities[SN_MAX_DP_LANES] = { }; + struct device_node *endpoint; + u8 ln_assign = 0; + u8 ln_polrs = 0; + int dp_lanes; + int i; /* - * If someone tries to do a DDC over AUX transaction before pre_enable() - * on a device without a dedicated reference clock then we just can't - * do it. Fail right away. This prevents non-refclk users from reading - * the EDID before enabling the panel but such is life. + * Read config from the device tree about lane remapping and lane + * polarities. These are optional and we assume identity map and + * normal polarity if nothing is specified. It's OK to specify just + * data-lanes but not lane-polarities but not vice versa. + * + * Error checking is light (we just make sure we don't crash or + * buffer overrun) and we assume dts is well formed and specifying + * mappings that the hardware supports. */ - if (!pdata->comms_enabled) { - ret = -EIO; - goto exit; + endpoint = of_graph_get_endpoint_by_regs(np, 1, -1); + dp_lanes = of_property_count_u32_elems(endpoint, "data-lanes"); + if (dp_lanes > 0 && dp_lanes <= SN_MAX_DP_LANES) { + of_property_read_u32_array(endpoint, "data-lanes", + lane_assignments, dp_lanes); + of_property_read_u32_array(endpoint, "lane-polarities", + lane_polarities, dp_lanes); + } else { + dp_lanes = SN_MAX_DP_LANES; } + of_node_put(endpoint); - switch (request) { - case DP_AUX_NATIVE_WRITE: - case DP_AUX_I2C_WRITE: - case DP_AUX_NATIVE_READ: - case DP_AUX_I2C_READ: - regmap_write(pdata->regmap, SN_AUX_CMD_REG, request_val); - /* Assume it's good */ - msg->reply = 0; - break; - default: - ret = -EINVAL; - goto exit; + /* + * Convert into register format. Loop over all lanes even if + * data-lanes had fewer elements so that we nicely initialize + * the LN_ASSIGN register. + */ + for (i = SN_MAX_DP_LANES - 1; i >= 0; i--) { + ln_assign = ln_assign << LN_ASSIGN_WIDTH | lane_assignments[i]; + ln_polrs = ln_polrs << 1 | lane_polarities[i]; } - BUILD_BUG_ON(sizeof(addr_len) != sizeof(__be32)); - put_unaligned_be32((msg->address & SN_AUX_ADDR_MASK) << 8 | len, - addr_len); - regmap_bulk_write(pdata->regmap, SN_AUX_ADDR_19_16_REG, addr_len, - ARRAY_SIZE(addr_len)); + /* Stash in our struct for when we power on */ + pdata->dp_lanes = dp_lanes; + pdata->ln_assign = ln_assign; + pdata->ln_polrs = ln_polrs; +} - if (request == DP_AUX_NATIVE_WRITE || request == DP_AUX_I2C_WRITE) - regmap_bulk_write(pdata->regmap, SN_AUX_WDATA_REG(0), buf, len); +static int ti_sn_bridge_parse_dsi_host(struct ti_sn65dsi86 *pdata) +{ + struct device_node *np = pdata->dev->of_node; - /* Clear old status bits before start so we don't get confused */ - regmap_write(pdata->regmap, SN_AUX_CMD_STATUS_REG, - AUX_IRQ_STATUS_NAT_I2C_FAIL | - AUX_IRQ_STATUS_AUX_RPLY_TOUT | - AUX_IRQ_STATUS_AUX_SHORT); + pdata->host_node = of_graph_get_remote_node(np, 0, 0); - regmap_write(pdata->regmap, SN_AUX_CMD_REG, request_val | AUX_CMD_SEND); + if (!pdata->host_node) { + DRM_ERROR("remote dsi host node not found\n"); + return -ENODEV; + } - /* Zero delay loop because i2c transactions are slow already */ - ret = regmap_read_poll_timeout(pdata->regmap, SN_AUX_CMD_REG, val, - !(val & AUX_CMD_SEND), 0, 50 * 1000); - if (ret) - goto exit; + return 0; +} - ret = regmap_read(pdata->regmap, SN_AUX_CMD_STATUS_REG, &val); - if (ret) - goto exit; +static int ti_sn_bridge_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) +{ + struct ti_sn65dsi86 *pdata = dev_get_drvdata(adev->dev.parent); + struct device_node *np = pdata->dev->of_node; + struct drm_panel *panel; + int ret; - if (val & AUX_IRQ_STATUS_AUX_RPLY_TOUT) { - /* - * The hardware tried the message seven times per the DP spec - * but it hit a timeout. We ignore defers here because they're - * handled in hardware. - */ - ret = -ETIMEDOUT; - goto exit; - } + ret = drm_of_find_panel_or_bridge(np, 1, 0, &panel, NULL); + if (ret) + return dev_err_probe(&adev->dev, ret, + "could not find any panel node\n"); - if (val & AUX_IRQ_STATUS_AUX_SHORT) { - ret = regmap_read(pdata->regmap, SN_AUX_LENGTH_REG, &len); - if (ret) - goto exit; - } else if (val & AUX_IRQ_STATUS_NAT_I2C_FAIL) { - switch (request) { - case DP_AUX_I2C_WRITE: - case DP_AUX_I2C_READ: - msg->reply |= DP_AUX_I2C_REPLY_NACK; - break; - case DP_AUX_NATIVE_READ: - case DP_AUX_NATIVE_WRITE: - msg->reply |= DP_AUX_NATIVE_REPLY_NACK; - break; - } - len = 0; - goto exit; + pdata->next_bridge = devm_drm_panel_bridge_add(pdata->dev, panel); + if (IS_ERR(pdata->next_bridge)) { + DRM_ERROR("failed to create panel bridge\n"); + return PTR_ERR(pdata->next_bridge); } - if (request != DP_AUX_NATIVE_WRITE && request != DP_AUX_I2C_WRITE && len != 0) - ret = regmap_bulk_read(pdata->regmap, SN_AUX_RDATA_REG(0), buf, len); - -exit: - mutex_unlock(&pdata->comms_mutex); - pm_runtime_mark_last_busy(pdata->dev); - pm_runtime_put_autosuspend(pdata->dev); + ti_sn_bridge_parse_lanes(pdata, np); + ret = ti_sn_bridge_parse_dsi_host(pdata); if (ret) return ret; - return len; + + pdata->bridge.funcs = &ti_sn_bridge_funcs; + pdata->bridge.of_node = np; + + drm_bridge_add(&pdata->bridge); + + return 0; } -static int ti_sn_bridge_parse_dsi_host(struct ti_sn65dsi86 *pdata) +static void ti_sn_bridge_remove(struct auxiliary_device *adev) { - struct device_node *np = pdata->dev->of_node; + struct ti_sn65dsi86 *pdata = dev_get_drvdata(adev->dev.parent); - pdata->host_node = of_graph_get_remote_node(np, 0, 0); + if (!pdata) + return; - if (!pdata->host_node) { - DRM_ERROR("remote dsi host node not found\n"); - return -ENODEV; + if (pdata->dsi) { + mipi_dsi_detach(pdata->dsi); + mipi_dsi_device_unregister(pdata->dsi); } - return 0; + drm_bridge_remove(&pdata->bridge); + + of_node_put(pdata->host_node); } +static const struct auxiliary_device_id ti_sn_bridge_id_table[] = { + { .name = "ti_sn65dsi86.bridge", }, + {}, +}; + +static struct auxiliary_driver ti_sn_bridge_driver = { + .name = "bridge", + .probe = ti_sn_bridge_probe, + .remove = ti_sn_bridge_remove, + .id_table = ti_sn_bridge_id_table, +}; + +/* ----------------------------------------------------------------------------- + * GPIO Controller + */ + #if defined(CONFIG_OF_GPIO) static int tn_sn_bridge_of_xlate(struct gpio_chip *chip, @@ -1265,171 +1454,27 @@ static inline void ti_sn_gpio_unregister(void) {} #endif -static void ti_sn_bridge_parse_lanes(struct ti_sn65dsi86 *pdata, - struct device_node *np) -{ - u32 lane_assignments[SN_MAX_DP_LANES] = { 0, 1, 2, 3 }; - u32 lane_polarities[SN_MAX_DP_LANES] = { }; - struct device_node *endpoint; - u8 ln_assign = 0; - u8 ln_polrs = 0; - int dp_lanes; - int i; - - /* - * Read config from the device tree about lane remapping and lane - * polarities. These are optional and we assume identity map and - * normal polarity if nothing is specified. It's OK to specify just - * data-lanes but not lane-polarities but not vice versa. - * - * Error checking is light (we just make sure we don't crash or - * buffer overrun) and we assume dts is well formed and specifying - * mappings that the hardware supports. - */ - endpoint = of_graph_get_endpoint_by_regs(np, 1, -1); - dp_lanes = of_property_count_u32_elems(endpoint, "data-lanes"); - if (dp_lanes > 0 && dp_lanes <= SN_MAX_DP_LANES) { - of_property_read_u32_array(endpoint, "data-lanes", - lane_assignments, dp_lanes); - of_property_read_u32_array(endpoint, "lane-polarities", - lane_polarities, dp_lanes); - } else { - dp_lanes = SN_MAX_DP_LANES; - } - of_node_put(endpoint); - - /* - * Convert into register format. Loop over all lanes even if - * data-lanes had fewer elements so that we nicely initialize - * the LN_ASSIGN register. - */ - for (i = SN_MAX_DP_LANES - 1; i >= 0; i--) { - ln_assign = ln_assign << LN_ASSIGN_WIDTH | lane_assignments[i]; - ln_polrs = ln_polrs << 1 | lane_polarities[i]; - } - - /* Stash in our struct for when we power on */ - pdata->dp_lanes = dp_lanes; - pdata->ln_assign = ln_assign; - pdata->ln_polrs = ln_polrs; -} - -static int ti_sn_bridge_probe(struct auxiliary_device *adev, - const struct auxiliary_device_id *id) -{ - struct ti_sn65dsi86 *pdata = dev_get_drvdata(adev->dev.parent); - struct device_node *np = pdata->dev->of_node; - int ret; - - ret = drm_of_find_panel_or_bridge(np, 1, 0, &pdata->panel, NULL); - if (ret) { - DRM_ERROR("could not find any panel node\n"); - return ret; - } - - ti_sn_bridge_parse_lanes(pdata, np); - - ret = ti_sn_bridge_parse_dsi_host(pdata); - if (ret) - return ret; - - pdata->aux.name = "ti-sn65dsi86-aux"; - pdata->aux.dev = pdata->dev; - pdata->aux.transfer = ti_sn_aux_transfer; - drm_dp_aux_init(&pdata->aux); - - pdata->bridge.funcs = &ti_sn_bridge_funcs; - pdata->bridge.of_node = np; - - drm_bridge_add(&pdata->bridge); - - return 0; -} - -static void ti_sn_bridge_remove(struct auxiliary_device *adev) -{ - struct ti_sn65dsi86 *pdata = dev_get_drvdata(adev->dev.parent); - - if (!pdata) - return; - - if (pdata->dsi) { - mipi_dsi_detach(pdata->dsi); - mipi_dsi_device_unregister(pdata->dsi); - } - - kfree(pdata->edid); - - drm_bridge_remove(&pdata->bridge); - - of_node_put(pdata->host_node); -} - -static const struct auxiliary_device_id ti_sn_bridge_id_table[] = { - { .name = "ti_sn65dsi86.bridge", }, - {}, -}; - -static struct auxiliary_driver ti_sn_bridge_driver = { - .name = "bridge", - .probe = ti_sn_bridge_probe, - .remove = ti_sn_bridge_remove, - .id_table = ti_sn_bridge_id_table, -}; +/* ----------------------------------------------------------------------------- + * Probe & Remove + */ static void ti_sn65dsi86_runtime_disable(void *data) { pm_runtime_disable(data); } -static void ti_sn65dsi86_uninit_aux(void *data) -{ - auxiliary_device_uninit(data); -} - -static void ti_sn65dsi86_delete_aux(void *data) -{ - auxiliary_device_delete(data); -} - -/* - * AUX bus docs say that a non-NULL release is mandatory, but it makes no - * sense for the model used here where all of the aux devices are allocated - * in the single shared structure. We'll use this noop as a workaround. - */ -static void ti_sn65dsi86_noop(struct device *dev) {} - -static int ti_sn65dsi86_add_aux_device(struct ti_sn65dsi86 *pdata, - struct auxiliary_device *aux, - const char *name) +static int ti_sn65dsi86_parse_regulators(struct ti_sn65dsi86 *pdata) { - struct device *dev = pdata->dev; - int ret; - - /* - * NOTE: It would be nice to set the "of_node" of our children to be - * the same "of_node"" that the top-level component has. That doesn't - * work, though, since pinctrl will try (and fail) to reserve the - * pins again. Until that gets sorted out the children will just need - * to look at the of_node of the main device. - */ - - aux->name = name; - aux->dev.parent = dev; - aux->dev.release = ti_sn65dsi86_noop; - ret = auxiliary_device_init(aux); - if (ret) - return ret; - ret = devm_add_action_or_reset(dev, ti_sn65dsi86_uninit_aux, aux); - if (ret) - return ret; + unsigned int i; + const char * const ti_sn_bridge_supply_names[] = { + "vcca", "vcc", "vccio", "vpll", + }; - ret = auxiliary_device_add(aux); - if (ret) - return ret; - ret = devm_add_action_or_reset(dev, ti_sn65dsi86_delete_aux, aux); + for (i = 0; i < SN_REGULATOR_SUPPLY_NUM; i++) + pdata->supplies[i].supply = ti_sn_bridge_supply_names[i]; - return ret; + return devm_regulator_bulk_get(pdata->dev, SN_REGULATOR_SUPPLY_NUM, + pdata->supplies); } static int ti_sn65dsi86_probe(struct i2c_client *client, @@ -1454,27 +1499,24 @@ static int ti_sn65dsi86_probe(struct i2c_client *client, pdata->regmap = devm_regmap_init_i2c(client, &ti_sn65dsi86_regmap_config); - if (IS_ERR(pdata->regmap)) { - DRM_ERROR("regmap i2c init failed\n"); - return PTR_ERR(pdata->regmap); - } + if (IS_ERR(pdata->regmap)) + return dev_err_probe(dev, PTR_ERR(pdata->regmap), + "regmap i2c init failed\n"); - pdata->enable_gpio = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW); - if (IS_ERR(pdata->enable_gpio)) { - DRM_ERROR("failed to get enable gpio from DT\n"); - ret = PTR_ERR(pdata->enable_gpio); - return ret; - } + pdata->enable_gpio = devm_gpiod_get_optional(dev, "enable", + GPIOD_OUT_LOW); + if (IS_ERR(pdata->enable_gpio)) + return dev_err_probe(dev, PTR_ERR(pdata->enable_gpio), + "failed to get enable gpio from DT\n"); ret = ti_sn65dsi86_parse_regulators(pdata); - if (ret) { - DRM_ERROR("failed to parse regulators\n"); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, "failed to parse regulators\n"); pdata->refclk = devm_clk_get_optional(dev, "refclk"); if (IS_ERR(pdata->refclk)) - return PTR_ERR(pdata->refclk); + return dev_err_probe(dev, PTR_ERR(pdata->refclk), + "failed to get reference clock\n"); pm_runtime_enable(dev); ret = devm_add_action_or_reset(dev, ti_sn65dsi86_runtime_disable, dev); @@ -1490,10 +1532,11 @@ static int ti_sn65dsi86_probe(struct i2c_client *client, * motiviation here is to solve the chicken-and-egg problem of probe * ordering. The bridge wants the panel to be there when it probes. * The panel wants its HPD GPIO (provided by sn65dsi86 on some boards) - * when it probes. There will soon be other devices (DDC I2C bus, PWM) - * that have the same problem. Having sub-devices allows the some sub - * devices to finish probing even if others return -EPROBE_DEFER and - * gets us around the problems. + * when it probes. The panel and maybe backlight might want the DDC + * bus. Soon the PWM provided by the bridge chip will have the same + * problem. Having sub-devices allows the some sub devices to finish + * probing even if others return -EPROBE_DEFER and gets us around the + * problems. */ if (IS_ENABLED(CONFIG_OF_GPIO)) { @@ -1502,7 +1545,13 @@ static int ti_sn65dsi86_probe(struct i2c_client *client, return ret; } - return ti_sn65dsi86_add_aux_device(pdata, &pdata->bridge_aux, "bridge"); + /* + * NOTE: At the end of the AUX channel probe we'll add the aux device + * for the bridge. This is because the bridge can't be used until the + * AUX channel is there and this is a very simple solution to the + * dependency problem. + */ + return ti_sn65dsi86_add_aux_device(pdata, &pdata->aux_aux, "aux"); } static struct i2c_device_id ti_sn65dsi86_id[] = { @@ -1539,12 +1588,18 @@ static int __init ti_sn65dsi86_init(void) if (ret) goto err_main_was_registered; - ret = auxiliary_driver_register(&ti_sn_bridge_driver); + ret = auxiliary_driver_register(&ti_sn_aux_driver); if (ret) goto err_gpio_was_registered; + ret = auxiliary_driver_register(&ti_sn_bridge_driver); + if (ret) + goto err_aux_was_registered; + return 0; +err_aux_was_registered: + auxiliary_driver_unregister(&ti_sn_aux_driver); err_gpio_was_registered: ti_sn_gpio_unregister(); err_main_was_registered: @@ -1557,6 +1612,7 @@ module_init(ti_sn65dsi86_init); static void __exit ti_sn65dsi86_exit(void) { auxiliary_driver_unregister(&ti_sn_bridge_driver); + auxiliary_driver_unregister(&ti_sn_aux_driver); ti_sn_gpio_unregister(); i2c_del_driver(&ti_sn65dsi86_driver); } diff --git a/drivers/gpu/drm/drm_aperture.c b/drivers/gpu/drm/drm_aperture.c index 9335d9d6cf9a..9ac39cf11694 100644 --- a/drivers/gpu/drm/drm_aperture.c +++ b/drivers/gpu/drm/drm_aperture.c @@ -33,6 +33,10 @@ * * .. code-block:: c * + * static const struct drm_driver example_driver = { + * ... + * }; + * * static int remove_conflicting_framebuffers(struct pci_dev *pdev) * { * bool primary = false; @@ -46,7 +50,7 @@ * #endif * * return drm_aperture_remove_conflicting_framebuffers(base, size, primary, - * "example driver"); + * &example_driver); * } * * static int probe(struct pci_dev *pdev) @@ -274,7 +278,7 @@ static void drm_aperture_detach_drivers(resource_size_t base, resource_size_t si * @base: the aperture's base address in physical memory * @size: aperture size in bytes * @primary: also kick vga16fb if present - * @name: requesting driver name + * @req_driver: requesting DRM driver * * This function removes graphics device drivers which use memory range described by * @base and @size. @@ -283,7 +287,7 @@ static void drm_aperture_detach_drivers(resource_size_t base, resource_size_t si * 0 on success, or a negative errno code otherwise */ int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_size_t size, - bool primary, const char *name) + bool primary, const struct drm_driver *req_driver) { #if IS_REACHABLE(CONFIG_FB) struct apertures_struct *a; @@ -296,7 +300,7 @@ int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_ a->ranges[0].base = base; a->ranges[0].size = size; - ret = remove_conflicting_framebuffers(a, name, primary); + ret = remove_conflicting_framebuffers(a, req_driver->name, primary); kfree(a); if (ret) @@ -312,7 +316,7 @@ EXPORT_SYMBOL(drm_aperture_remove_conflicting_framebuffers); /** * drm_aperture_remove_conflicting_pci_framebuffers - remove existing framebuffers for PCI devices * @pdev: PCI device - * @name: requesting driver name + * @req_driver: requesting DRM driver * * This function removes graphics device drivers using memory range configured * for any of @pdev's memory bars. The function assumes that PCI device with @@ -321,7 +325,8 @@ EXPORT_SYMBOL(drm_aperture_remove_conflicting_framebuffers); * Returns: * 0 on success, or a negative errno code otherwise */ -int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const char *name) +int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, + const struct drm_driver *req_driver) { resource_size_t base, size; int bar, ret = 0; @@ -339,7 +344,7 @@ int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const * otherwise the vga fbdev driver falls over. */ #if IS_REACHABLE(CONFIG_FB) - ret = remove_conflicting_pci_framebuffers(pdev, name); + ret = remove_conflicting_pci_framebuffers(pdev, req_driver->name); #endif if (ret == 0) ret = vga_remove_vgacon(pdev); diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index bc3487964fb5..f7bf1ea62d58 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -35,6 +35,7 @@ #include <drm/drm_damage_helper.h> #include <drm/drm_device.h> #include <drm/drm_drv.h> +#include <drm/drm_gem_atomic_helper.h> #include <drm/drm_plane_helper.h> #include <drm/drm_print.h> #include <drm/drm_self_refresh_helper.h> @@ -2405,6 +2406,15 @@ int drm_atomic_helper_prepare_planes(struct drm_device *dev, ret = funcs->prepare_fb(plane, new_plane_state); if (ret) goto fail; + } else { + WARN_ON_ONCE(funcs->cleanup_fb); + + if (!drm_core_check_feature(dev, DRIVER_GEM)) + continue; + + ret = drm_gem_plane_helper_prepare_fb(plane, new_plane_state); + if (ret) + goto fail; } } diff --git a/drivers/gpu/drm/drm_debugfs_crc.c b/drivers/gpu/drm/drm_debugfs_crc.c index 3dd70d813f69..bbc3bc4ba844 100644 --- a/drivers/gpu/drm/drm_debugfs_crc.c +++ b/drivers/gpu/drm/drm_debugfs_crc.c @@ -46,10 +46,10 @@ * it reached a given hardware component (a CRC sampling "source"). * * Userspace can control generation of CRCs in a given CRTC by writing to the - * file dri/0/crtc-N/crc/control in debugfs, with N being the index of the CRTC. - * Accepted values are source names (which are driver-specific) and the "auto" - * keyword, which will let the driver select a default source of frame CRCs - * for this CRTC. + * file dri/0/crtc-N/crc/control in debugfs, with N being the :ref:`index of + * the CRTC<crtc_index>`. Accepted values are source names (which are + * driver-specific) and the "auto" keyword, which will let the driver select a + * default source of frame CRCs for this CRTC. * * Once frame CRC generation is enabled, userspace can capture them by reading * the dri/0/crtc-N/crc/data file. Each line in that file contains the frame diff --git a/drivers/gpu/drm/drm_dp_aux_bus.c b/drivers/gpu/drm/drm_dp_aux_bus.c new file mode 100644 index 000000000000..e49a70f3691b --- /dev/null +++ b/drivers/gpu/drm/drm_dp_aux_bus.c @@ -0,0 +1,326 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2021 Google Inc. + * + * The DP AUX bus is used for devices that are connected over a DisplayPort + * AUX bus. The devices on the far side of the bus are referred to as + * endpoints in this code. + * + * Commonly there is only one device connected to the DP AUX bus: a panel. + * Though historically panels (even DP panels) have been modeled as simple + * platform devices, putting them under the DP AUX bus allows the panel driver + * to perform transactions on that bus. + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/pm_domain.h> +#include <linux/pm_runtime.h> + +#include <drm/drm_dp_aux_bus.h> +#include <drm/drm_dp_helper.h> + +/** + * dp_aux_ep_match() - The match function for the dp_aux_bus. + * @dev: The device to match. + * @drv: The driver to try to match against. + * + * At the moment, we just match on device tree. + * + * Return: True if this driver matches this device; false otherwise. + */ +static int dp_aux_ep_match(struct device *dev, struct device_driver *drv) +{ + return !!of_match_device(drv->of_match_table, dev); +} + +/** + * dp_aux_ep_probe() - The probe function for the dp_aux_bus. + * @dev: The device to probe. + * + * Calls through to the endpoint driver probe. + * + * Return: 0 if no error or negative error code. + */ +static int dp_aux_ep_probe(struct device *dev) +{ + struct dp_aux_ep_driver *aux_ep_drv = to_dp_aux_ep_drv(dev->driver); + struct dp_aux_ep_device *aux_ep = to_dp_aux_ep_dev(dev); + int ret; + + ret = dev_pm_domain_attach(dev, true); + if (ret) + return dev_err_probe(dev, ret, "Failed to attach to PM Domain\n"); + + ret = aux_ep_drv->probe(aux_ep); + if (ret) + dev_pm_domain_detach(dev, true); + + return ret; +} + +/** + * dp_aux_ep_remove() - The remove function for the dp_aux_bus. + * @dev: The device to remove. + * + * Calls through to the endpoint driver remove. + * + * Return: 0 if no error or negative error code. + */ +static int dp_aux_ep_remove(struct device *dev) +{ + struct dp_aux_ep_driver *aux_ep_drv = to_dp_aux_ep_drv(dev->driver); + struct dp_aux_ep_device *aux_ep = to_dp_aux_ep_dev(dev); + + if (aux_ep_drv->remove) + aux_ep_drv->remove(aux_ep); + dev_pm_domain_detach(dev, true); + + return 0; +} + +/** + * dp_aux_ep_shutdown() - The shutdown function for the dp_aux_bus. + * @dev: The device to shutdown. + * + * Calls through to the endpoint driver shutdown. + */ +static void dp_aux_ep_shutdown(struct device *dev) +{ + struct dp_aux_ep_driver *aux_ep_drv; + + if (!dev->driver) + return; + + aux_ep_drv = to_dp_aux_ep_drv(dev->driver); + if (aux_ep_drv->shutdown) + aux_ep_drv->shutdown(to_dp_aux_ep_dev(dev)); +} + +static struct bus_type dp_aux_bus_type = { + .name = "dp-aux", + .match = dp_aux_ep_match, + .probe = dp_aux_ep_probe, + .remove = dp_aux_ep_remove, + .shutdown = dp_aux_ep_shutdown, +}; + +static ssize_t modalias_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return of_device_modalias(dev, buf, PAGE_SIZE); +} +static DEVICE_ATTR_RO(modalias); + +static struct attribute *dp_aux_ep_dev_attrs[] = { + &dev_attr_modalias.attr, + NULL, +}; +ATTRIBUTE_GROUPS(dp_aux_ep_dev); + +/** + * dp_aux_ep_dev_release() - Free memory for the dp_aux_ep device + * @dev: The device to free. + * + * Return: 0 if no error or negative error code. + */ +static void dp_aux_ep_dev_release(struct device *dev) +{ + kfree(to_dp_aux_ep_dev(dev)); +} + +static struct device_type dp_aux_device_type_type = { + .groups = dp_aux_ep_dev_groups, + .uevent = of_device_uevent_modalias, + .release = dp_aux_ep_dev_release, +}; + +/** + * of_dp_aux_ep_destroy() - Destroy an DP AUX endpoint device + * @dev: The device to destroy. + * @data: Not used + * + * This is just used as a callback by of_dp_aux_depopulate_ep_devices() and + * is called for _all_ of the child devices of the device providing the AUX bus. + * We'll only act on those that are of type "dp_aux_bus_type". + * + * This function is effectively an inverse of what's in the loop + * in of_dp_aux_populate_ep_devices(). + * + * Return: 0 if no error or negative error code. + */ +static int of_dp_aux_ep_destroy(struct device *dev, void *data) +{ + struct device_node *np = dev->of_node; + + if (dev->bus != &dp_aux_bus_type) + return 0; + + if (!of_node_check_flag(np, OF_POPULATED)) + return 0; + + of_node_clear_flag(np, OF_POPULATED); + of_node_put(np); + + device_unregister(dev); + + return 0; +} + +/** + * of_dp_aux_depopulate_ep_devices() - Undo of_dp_aux_populate_ep_devices + * @aux: The AUX channel whose devices we want to depopulate + * + * This will destroy all devices that were created + * by of_dp_aux_populate_ep_devices(). + */ +void of_dp_aux_depopulate_ep_devices(struct drm_dp_aux *aux) +{ + device_for_each_child_reverse(aux->dev, NULL, of_dp_aux_ep_destroy); +} +EXPORT_SYMBOL_GPL(of_dp_aux_depopulate_ep_devices); + +/** + * of_dp_aux_populate_ep_devices() - Populate the endpoint devices on the DP AUX + * @aux: The AUX channel whose devices we want to populate. It is required that + * drm_dp_aux_init() has already been called for this AUX channel. + * + * This will populate all the devices under the "aux-bus" node of the device + * providing the AUX channel (AKA aux->dev). + * + * When this function finishes, it is _possible_ (but not guaranteed) that + * our sub-devices will have finished probing. It should be noted that if our + * sub-devices return -EPROBE_DEFER that we will not return any error codes + * ourselves but our sub-devices will _not_ have actually probed successfully + * yet. There may be other cases (maybe added in the future?) where sub-devices + * won't have been probed yet when this function returns, so it's best not to + * rely on that. + * + * If this function succeeds you should later make sure you call + * of_dp_aux_depopulate_ep_devices() to undo it, or just use the devm version + * of this function. + * + * Return: 0 if no error or negative error code. + */ +int of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux) +{ + struct device_node *bus, *np; + struct dp_aux_ep_device *aux_ep; + int ret; + + /* drm_dp_aux_init() should have been called already; warn if not */ + WARN_ON_ONCE(!aux->ddc.algo); + + if (!aux->dev->of_node) + return 0; + + bus = of_get_child_by_name(aux->dev->of_node, "aux-bus"); + if (!bus) + return 0; + + for_each_available_child_of_node(bus, np) { + if (of_node_test_and_set_flag(np, OF_POPULATED)) + continue; + + aux_ep = kzalloc(sizeof(*aux_ep), GFP_KERNEL); + if (!aux_ep) + continue; + aux_ep->aux = aux; + + aux_ep->dev.parent = aux->dev; + aux_ep->dev.bus = &dp_aux_bus_type; + aux_ep->dev.type = &dp_aux_device_type_type; + aux_ep->dev.of_node = of_node_get(np); + dev_set_name(&aux_ep->dev, "aux-%s", dev_name(aux->dev)); + + ret = device_register(&aux_ep->dev); + if (ret) { + dev_err(aux->dev, "Failed to create AUX EP for %pOF: %d\n", np, ret); + of_node_clear_flag(np, OF_POPULATED); + of_node_put(np); + + /* + * As per docs of device_register(), call this instead + * of kfree() directly for error cases. + */ + put_device(&aux_ep->dev); + + /* + * Following in the footsteps of of_i2c_register_devices(), + * we won't fail the whole function here--we'll just + * continue registering any other devices we find. + */ + } + } + + of_node_put(bus); + + return 0; +} + +static void of_dp_aux_depopulate_ep_devices_void(void *data) +{ + of_dp_aux_depopulate_ep_devices(data); +} + +/** + * devm_of_dp_aux_populate_ep_devices() - devm wrapper for of_dp_aux_populate_ep_devices() + * @aux: The AUX channel whose devices we want to populate + * + * Handles freeing w/ devm on the device "aux->dev". + * + * Return: 0 if no error or negative error code. + */ +int devm_of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux) +{ + int ret; + + ret = of_dp_aux_populate_ep_devices(aux); + if (ret) + return ret; + + return devm_add_action_or_reset(aux->dev, + of_dp_aux_depopulate_ep_devices_void, + aux); +} +EXPORT_SYMBOL_GPL(devm_of_dp_aux_populate_ep_devices); + +int __dp_aux_dp_driver_register(struct dp_aux_ep_driver *drv, struct module *owner) +{ + drv->driver.owner = owner; + drv->driver.bus = &dp_aux_bus_type; + + return driver_register(&drv->driver); +} +EXPORT_SYMBOL_GPL(__dp_aux_dp_driver_register); + +void dp_aux_dp_driver_unregister(struct dp_aux_ep_driver *drv) +{ + driver_unregister(&drv->driver); +} +EXPORT_SYMBOL_GPL(dp_aux_dp_driver_unregister); + +static int __init dp_aux_bus_init(void) +{ + int ret; + + ret = bus_register(&dp_aux_bus_type); + if (ret) + return ret; + + return 0; +} + +static void __exit dp_aux_bus_exit(void) +{ + bus_unregister(&dp_aux_bus_type); +} + +subsys_initcall(dp_aux_bus_init); +module_exit(dp_aux_bus_exit); + +MODULE_AUTHOR("Douglas Anderson <dianders@chromium.org>"); +MODULE_DESCRIPTION("DRM DisplayPort AUX bus"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 55b53df6ce34..b5f75ca05774 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -33,9 +33,17 @@ #include <drm/drm_print.h> #include <drm/drm_vblank.h> #include <drm/drm_dp_mst_helper.h> +#include <drm/drm_panel.h> #include "drm_crtc_helper_internal.h" +struct dp_aux_backlight { + struct backlight_device *base; + struct drm_dp_aux *aux; + struct drm_edp_backlight_info info; + bool enabled; +}; + /** * DOC: dp helpers * @@ -3115,3 +3123,457 @@ int drm_dp_pcon_convert_rgb_to_ycbcr(struct drm_dp_aux *aux, u8 color_spc) return 0; } EXPORT_SYMBOL(drm_dp_pcon_convert_rgb_to_ycbcr); + +/** + * drm_edp_backlight_set_level() - Set the backlight level of an eDP panel via AUX + * @aux: The DP AUX channel to use + * @bl: Backlight capability info from drm_edp_backlight_init() + * @level: The brightness level to set + * + * Sets the brightness level of an eDP panel's backlight. Note that the panel's backlight must + * already have been enabled by the driver by calling drm_edp_backlight_enable(). + * + * Returns: %0 on success, negative error code on failure + */ +int drm_edp_backlight_set_level(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl, + u16 level) +{ + int ret; + u8 buf[2] = { 0 }; + + if (bl->lsb_reg_used) { + buf[0] = (level & 0xff00) >> 8; + buf[1] = (level & 0x00ff); + } else { + buf[0] = level; + } + + ret = drm_dp_dpcd_write(aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB, buf, sizeof(buf)); + if (ret != sizeof(buf)) { + drm_err(aux->drm_dev, + "%s: Failed to write aux backlight level: %d\n", + aux->name, ret); + return ret < 0 ? ret : -EIO; + } + + return 0; +} +EXPORT_SYMBOL(drm_edp_backlight_set_level); + +static int +drm_edp_backlight_set_enable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl, + bool enable) +{ + int ret; + u8 buf; + + /* The panel uses something other then DPCD for enabling its backlight */ + if (!bl->aux_enable) + return 0; + + ret = drm_dp_dpcd_readb(aux, DP_EDP_DISPLAY_CONTROL_REGISTER, &buf); + if (ret != 1) { + drm_err(aux->drm_dev, "%s: Failed to read eDP display control register: %d\n", + aux->name, ret); + return ret < 0 ? ret : -EIO; + } + if (enable) + buf |= DP_EDP_BACKLIGHT_ENABLE; + else + buf &= ~DP_EDP_BACKLIGHT_ENABLE; + + ret = drm_dp_dpcd_writeb(aux, DP_EDP_DISPLAY_CONTROL_REGISTER, buf); + if (ret != 1) { + drm_err(aux->drm_dev, "%s: Failed to write eDP display control register: %d\n", + aux->name, ret); + return ret < 0 ? ret : -EIO; + } + + return 0; +} + +/** + * drm_edp_backlight_enable() - Enable an eDP panel's backlight using DPCD + * @aux: The DP AUX channel to use + * @bl: Backlight capability info from drm_edp_backlight_init() + * @level: The initial backlight level to set via AUX, if there is one + * + * This function handles enabling DPCD backlight controls on a panel over DPCD, while additionally + * restoring any important backlight state such as the given backlight level, the brightness byte + * count, backlight frequency, etc. + * + * Note that certain panels, while supporting brightness level controls over DPCD, may not support + * having their backlights enabled via the standard %DP_EDP_DISPLAY_CONTROL_REGISTER. On such panels + * &drm_edp_backlight_info.aux_enable will be set to %false, this function will skip the step of + * programming the %DP_EDP_DISPLAY_CONTROL_REGISTER, and the driver must perform the required + * implementation specific step for enabling the backlight after calling this function. + * + * Returns: %0 on success, negative error code on failure. + */ +int drm_edp_backlight_enable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl, + const u16 level) +{ + int ret; + u8 dpcd_buf, new_dpcd_buf; + + ret = drm_dp_dpcd_readb(aux, DP_EDP_BACKLIGHT_MODE_SET_REGISTER, &dpcd_buf); + if (ret != 1) { + drm_dbg_kms(aux->drm_dev, + "%s: Failed to read backlight mode: %d\n", aux->name, ret); + return ret < 0 ? ret : -EIO; + } + + new_dpcd_buf = dpcd_buf; + + if ((dpcd_buf & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK) != DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD) { + new_dpcd_buf &= ~DP_EDP_BACKLIGHT_CONTROL_MODE_MASK; + new_dpcd_buf |= DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD; + + ret = drm_dp_dpcd_writeb(aux, DP_EDP_PWMGEN_BIT_COUNT, bl->pwmgen_bit_count); + if (ret != 1) + drm_dbg_kms(aux->drm_dev, "%s: Failed to write aux pwmgen bit count: %d\n", + aux->name, ret); + } + + if (bl->pwm_freq_pre_divider) { + ret = drm_dp_dpcd_writeb(aux, DP_EDP_BACKLIGHT_FREQ_SET, bl->pwm_freq_pre_divider); + if (ret != 1) + drm_dbg_kms(aux->drm_dev, + "%s: Failed to write aux backlight frequency: %d\n", + aux->name, ret); + else + new_dpcd_buf |= DP_EDP_BACKLIGHT_FREQ_AUX_SET_ENABLE; + } + + if (new_dpcd_buf != dpcd_buf) { + ret = drm_dp_dpcd_writeb(aux, DP_EDP_BACKLIGHT_MODE_SET_REGISTER, new_dpcd_buf); + if (ret != 1) { + drm_dbg_kms(aux->drm_dev, "%s: Failed to write aux backlight mode: %d\n", + aux->name, ret); + return ret < 0 ? ret : -EIO; + } + } + + ret = drm_edp_backlight_set_level(aux, bl, level); + if (ret < 0) + return ret; + ret = drm_edp_backlight_set_enable(aux, bl, true); + if (ret < 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(drm_edp_backlight_enable); + +/** + * drm_edp_backlight_disable() - Disable an eDP backlight using DPCD, if supported + * @aux: The DP AUX channel to use + * @bl: Backlight capability info from drm_edp_backlight_init() + * + * This function handles disabling DPCD backlight controls on a panel over AUX. Note that some + * panels have backlights that are enabled/disabled by other means, despite having their brightness + * values controlled through DPCD. On such panels &drm_edp_backlight_info.aux_enable will be set to + * %false, this function will become a no-op (and we will skip updating + * %DP_EDP_DISPLAY_CONTROL_REGISTER), and the driver must take care to perform it's own + * implementation specific step for disabling the backlight. + * + * Returns: %0 on success or no-op, negative error code on failure. + */ +int drm_edp_backlight_disable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl) +{ + int ret; + + ret = drm_edp_backlight_set_enable(aux, bl, false); + if (ret < 0) + return ret; + + return 0; +} +EXPORT_SYMBOL(drm_edp_backlight_disable); + +static inline int +drm_edp_backlight_probe_max(struct drm_dp_aux *aux, struct drm_edp_backlight_info *bl, + u16 driver_pwm_freq_hz, const u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE]) +{ + int fxp, fxp_min, fxp_max, fxp_actual, f = 1; + int ret; + u8 pn, pn_min, pn_max; + + ret = drm_dp_dpcd_readb(aux, DP_EDP_PWMGEN_BIT_COUNT, &pn); + if (ret != 1) { + drm_dbg_kms(aux->drm_dev, "%s: Failed to read pwmgen bit count cap: %d\n", + aux->name, ret); + return -ENODEV; + } + + pn &= DP_EDP_PWMGEN_BIT_COUNT_MASK; + bl->max = (1 << pn) - 1; + if (!driver_pwm_freq_hz) + return 0; + + /* + * Set PWM Frequency divider to match desired frequency provided by the driver. + * The PWM Frequency is calculated as 27Mhz / (F x P). + * - Where F = PWM Frequency Pre-Divider value programmed by field 7:0 of the + * EDP_BACKLIGHT_FREQ_SET register (DPCD Address 00728h) + * - Where P = 2^Pn, where Pn is the value programmed by field 4:0 of the + * EDP_PWMGEN_BIT_COUNT register (DPCD Address 00724h) + */ + + /* Find desired value of (F x P) + * Note that, if F x P is out of supported range, the maximum value or minimum value will + * applied automatically. So no need to check that. + */ + fxp = DIV_ROUND_CLOSEST(1000 * DP_EDP_BACKLIGHT_FREQ_BASE_KHZ, driver_pwm_freq_hz); + + /* Use highest possible value of Pn for more granularity of brightness adjustment while + * satifying the conditions below. + * - Pn is in the range of Pn_min and Pn_max + * - F is in the range of 1 and 255 + * - FxP is within 25% of desired value. + * Note: 25% is arbitrary value and may need some tweak. + */ + ret = drm_dp_dpcd_readb(aux, DP_EDP_PWMGEN_BIT_COUNT_CAP_MIN, &pn_min); + if (ret != 1) { + drm_dbg_kms(aux->drm_dev, "%s: Failed to read pwmgen bit count cap min: %d\n", + aux->name, ret); + return 0; + } + ret = drm_dp_dpcd_readb(aux, DP_EDP_PWMGEN_BIT_COUNT_CAP_MAX, &pn_max); + if (ret != 1) { + drm_dbg_kms(aux->drm_dev, "%s: Failed to read pwmgen bit count cap max: %d\n", + aux->name, ret); + return 0; + } + pn_min &= DP_EDP_PWMGEN_BIT_COUNT_MASK; + pn_max &= DP_EDP_PWMGEN_BIT_COUNT_MASK; + + /* Ensure frequency is within 25% of desired value */ + fxp_min = DIV_ROUND_CLOSEST(fxp * 3, 4); + fxp_max = DIV_ROUND_CLOSEST(fxp * 5, 4); + if (fxp_min < (1 << pn_min) || (255 << pn_max) < fxp_max) { + drm_dbg_kms(aux->drm_dev, + "%s: Driver defined backlight frequency (%d) out of range\n", + aux->name, driver_pwm_freq_hz); + return 0; + } + + for (pn = pn_max; pn >= pn_min; pn--) { + f = clamp(DIV_ROUND_CLOSEST(fxp, 1 << pn), 1, 255); + fxp_actual = f << pn; + if (fxp_min <= fxp_actual && fxp_actual <= fxp_max) + break; + } + + ret = drm_dp_dpcd_writeb(aux, DP_EDP_PWMGEN_BIT_COUNT, pn); + if (ret != 1) { + drm_dbg_kms(aux->drm_dev, "%s: Failed to write aux pwmgen bit count: %d\n", + aux->name, ret); + return 0; + } + bl->pwmgen_bit_count = pn; + bl->max = (1 << pn) - 1; + + if (edp_dpcd[2] & DP_EDP_BACKLIGHT_FREQ_AUX_SET_CAP) { + bl->pwm_freq_pre_divider = f; + drm_dbg_kms(aux->drm_dev, "%s: Using backlight frequency from driver (%dHz)\n", + aux->name, driver_pwm_freq_hz); + } + + return 0; +} + +static inline int +drm_edp_backlight_probe_level(struct drm_dp_aux *aux, struct drm_edp_backlight_info *bl, + u8 *current_mode) +{ + int ret; + u8 buf[2]; + u8 mode_reg; + + ret = drm_dp_dpcd_readb(aux, DP_EDP_BACKLIGHT_MODE_SET_REGISTER, &mode_reg); + if (ret != 1) { + drm_dbg_kms(aux->drm_dev, "%s: Failed to read backlight mode: %d\n", + aux->name, ret); + return ret < 0 ? ret : -EIO; + } + + *current_mode = (mode_reg & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK); + if (*current_mode == DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD) { + int size = 1 + bl->lsb_reg_used; + + ret = drm_dp_dpcd_read(aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB, buf, size); + if (ret != size) { + drm_dbg_kms(aux->drm_dev, "%s: Failed to read backlight level: %d\n", + aux->name, ret); + return ret < 0 ? ret : -EIO; + } + + if (bl->lsb_reg_used) + return (buf[0] << 8) | buf[1]; + else + return buf[0]; + } + + /* + * If we're not in DPCD control mode yet, the programmed brightness value is meaningless and + * the driver should assume max brightness + */ + return bl->max; +} + +/** + * drm_edp_backlight_init() - Probe a display panel's TCON using the standard VESA eDP backlight + * interface. + * @aux: The DP aux device to use for probing + * @bl: The &drm_edp_backlight_info struct to fill out with information on the backlight + * @driver_pwm_freq_hz: Optional PWM frequency from the driver in hz + * @edp_dpcd: A cached copy of the eDP DPCD + * @current_level: Where to store the probed brightness level + * @current_mode: Where to store the currently set backlight control mode + * + * Initializes a &drm_edp_backlight_info struct by probing @aux for it's backlight capabilities, + * along with also probing the current and maximum supported brightness levels. + * + * If @driver_pwm_freq_hz is non-zero, this will be used as the backlight frequency. Otherwise, the + * default frequency from the panel is used. + * + * Returns: %0 on success, negative error code on failure. + */ +int +drm_edp_backlight_init(struct drm_dp_aux *aux, struct drm_edp_backlight_info *bl, + u16 driver_pwm_freq_hz, const u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE], + u16 *current_level, u8 *current_mode) +{ + int ret; + + if (edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP) + bl->aux_enable = true; + if (edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT) + bl->lsb_reg_used = true; + + ret = drm_edp_backlight_probe_max(aux, bl, driver_pwm_freq_hz, edp_dpcd); + if (ret < 0) + return ret; + + ret = drm_edp_backlight_probe_level(aux, bl, current_mode); + if (ret < 0) + return ret; + *current_level = ret; + + drm_dbg_kms(aux->drm_dev, + "%s: Found backlight level=%d/%d pwm_freq_pre_divider=%d mode=%x\n", + aux->name, *current_level, bl->max, bl->pwm_freq_pre_divider, *current_mode); + drm_dbg_kms(aux->drm_dev, + "%s: Backlight caps: pwmgen_bit_count=%d lsb_reg_used=%d aux_enable=%d\n", + aux->name, bl->pwmgen_bit_count, bl->lsb_reg_used, bl->aux_enable); + return 0; +} +EXPORT_SYMBOL(drm_edp_backlight_init); + +#if IS_BUILTIN(CONFIG_BACKLIGHT_CLASS_DEVICE) || \ + (IS_MODULE(CONFIG_DRM_KMS_HELPER) && IS_MODULE(CONFIG_BACKLIGHT_CLASS_DEVICE)) + +static int dp_aux_backlight_update_status(struct backlight_device *bd) +{ + struct dp_aux_backlight *bl = bl_get_data(bd); + u16 brightness = backlight_get_brightness(bd); + int ret = 0; + + if (!backlight_is_blank(bd)) { + if (!bl->enabled) { + drm_edp_backlight_enable(bl->aux, &bl->info, brightness); + bl->enabled = true; + return 0; + } + ret = drm_edp_backlight_set_level(bl->aux, &bl->info, brightness); + } else { + if (bl->enabled) { + drm_edp_backlight_disable(bl->aux, &bl->info); + bl->enabled = false; + } + } + + return ret; +} + +static const struct backlight_ops dp_aux_bl_ops = { + .update_status = dp_aux_backlight_update_status, +}; + +/** + * drm_panel_dp_aux_backlight - create and use DP AUX backlight + * @panel: DRM panel + * @aux: The DP AUX channel to use + * + * Use this function to create and handle backlight if your panel + * supports backlight control over DP AUX channel using DPCD + * registers as per VESA's standard backlight control interface. + * + * When the panel is enabled backlight will be enabled after a + * successful call to &drm_panel_funcs.enable() + * + * When the panel is disabled backlight will be disabled before the + * call to &drm_panel_funcs.disable(). + * + * A typical implementation for a panel driver supporting backlight + * control over DP AUX will call this function at probe time. + * Backlight will then be handled transparently without requiring + * any intervention from the driver. + * + * drm_panel_dp_aux_backlight() must be called after the call to drm_panel_init(). + * + * Return: 0 on success or a negative error code on failure. + */ +int drm_panel_dp_aux_backlight(struct drm_panel *panel, struct drm_dp_aux *aux) +{ + struct dp_aux_backlight *bl; + struct backlight_properties props = { 0 }; + u16 current_level; + u8 current_mode; + u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE]; + int ret; + + if (!panel || !panel->dev || !aux) + return -EINVAL; + + ret = drm_dp_dpcd_read(aux, DP_EDP_DPCD_REV, edp_dpcd, + EDP_DISPLAY_CTL_CAP_SIZE); + if (ret < 0) + return ret; + + if (!drm_edp_backlight_supported(edp_dpcd)) { + DRM_DEV_INFO(panel->dev, "DP AUX backlight is not supported\n"); + return 0; + } + + bl = devm_kzalloc(panel->dev, sizeof(*bl), GFP_KERNEL); + if (!bl) + return -ENOMEM; + + bl->aux = aux; + + ret = drm_edp_backlight_init(aux, &bl->info, 0, edp_dpcd, + ¤t_level, ¤t_mode); + if (ret < 0) + return ret; + + props.type = BACKLIGHT_RAW; + props.brightness = current_level; + props.max_brightness = bl->info.max; + + bl->base = devm_backlight_device_register(panel->dev, "dp_aux_backlight", + panel->dev, bl, + &dp_aux_bl_ops, &props); + if (IS_ERR(bl->base)) + return PTR_ERR(bl->base); + + backlight_disable(bl->base); + + panel->backlight = bl->base; + + return 0; +} +EXPORT_SYMBOL(drm_panel_dp_aux_backlight); + +#endif diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index d62fb1a3c916..68deb1de8235 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1148,15 +1148,6 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma) return -EACCES; } - if (node->readonly) { - if (vma->vm_flags & VM_WRITE) { - drm_gem_object_put(obj); - return -EINVAL; - } - - vma->vm_flags &= ~VM_MAYWRITE; - } - ret = drm_gem_mmap_obj(obj, drm_vma_node_size(node) << PAGE_SHIFT, vma); @@ -1311,6 +1302,9 @@ EXPORT_SYMBOL(drm_gem_unlock_reservations); * @fence_array: array of dma_fence * for the job to block on. * @fence: the dma_fence to add to the list of dependencies. * + * This functions consumes the reference for @fence both on success and error + * cases. + * * Returns: * 0 on success, or an error on failing to expand the array. */ diff --git a/drivers/gpu/drm/drm_gem_atomic_helper.c b/drivers/gpu/drm/drm_gem_atomic_helper.c index a27135084ae5..26af09b959d4 100644 --- a/drivers/gpu/drm/drm_gem_atomic_helper.c +++ b/drivers/gpu/drm/drm_gem_atomic_helper.c @@ -135,6 +135,9 @@ * GEM based framebuffer drivers which have their buffers always pinned in * memory. * + * This function is the default implementation for GEM drivers of + * &drm_plane_helper_funcs.prepare_fb if no callback is provided. + * * See drm_atomic_set_fence_for_plane() for a discussion of implicit and * explicit fencing in atomic modeset updates. */ @@ -180,6 +183,27 @@ EXPORT_SYMBOL(drm_gem_simple_display_pipe_prepare_fb); */ /** + * __drm_gem_duplicate_shadow_plane_state - duplicates shadow-buffered plane state + * @plane: the plane + * @new_shadow_plane_state: the new shadow-buffered plane state + * + * This function duplicates shadow-buffered plane state. This is helpful for drivers + * that subclass struct drm_shadow_plane_state. + * + * The function does not duplicate existing mappings of the shadow buffers. + * Mappings are maintained during the atomic commit by the plane's prepare_fb + * and cleanup_fb helpers. See drm_gem_prepare_shadow_fb() and drm_gem_cleanup_shadow_fb() + * for corresponding helpers. + */ +void +__drm_gem_duplicate_shadow_plane_state(struct drm_plane *plane, + struct drm_shadow_plane_state *new_shadow_plane_state) +{ + __drm_atomic_helper_plane_duplicate_state(plane, &new_shadow_plane_state->base); +} +EXPORT_SYMBOL(__drm_gem_duplicate_shadow_plane_state); + +/** * drm_gem_duplicate_shadow_plane_state - duplicates shadow-buffered plane state * @plane: the plane * @@ -208,13 +232,26 @@ drm_gem_duplicate_shadow_plane_state(struct drm_plane *plane) new_shadow_plane_state = kzalloc(sizeof(*new_shadow_plane_state), GFP_KERNEL); if (!new_shadow_plane_state) return NULL; - __drm_atomic_helper_plane_duplicate_state(plane, &new_shadow_plane_state->base); + __drm_gem_duplicate_shadow_plane_state(plane, new_shadow_plane_state); return &new_shadow_plane_state->base; } EXPORT_SYMBOL(drm_gem_duplicate_shadow_plane_state); /** + * __drm_gem_destroy_shadow_plane_state - cleans up shadow-buffered plane state + * @shadow_plane_state: the shadow-buffered plane state + * + * This function cleans up shadow-buffered plane state. Helpful for drivers that + * subclass struct drm_shadow_plane_state. + */ +void __drm_gem_destroy_shadow_plane_state(struct drm_shadow_plane_state *shadow_plane_state) +{ + __drm_atomic_helper_plane_destroy_state(&shadow_plane_state->base); +} +EXPORT_SYMBOL(__drm_gem_destroy_shadow_plane_state); + +/** * drm_gem_destroy_shadow_plane_state - deletes shadow-buffered plane state * @plane: the plane * @plane_state: the plane state of type struct drm_shadow_plane_state @@ -229,12 +266,27 @@ void drm_gem_destroy_shadow_plane_state(struct drm_plane *plane, struct drm_shadow_plane_state *shadow_plane_state = to_drm_shadow_plane_state(plane_state); - __drm_atomic_helper_plane_destroy_state(&shadow_plane_state->base); + __drm_gem_destroy_shadow_plane_state(shadow_plane_state); kfree(shadow_plane_state); } EXPORT_SYMBOL(drm_gem_destroy_shadow_plane_state); /** + * __drm_gem_reset_shadow_plane - resets a shadow-buffered plane + * @plane: the plane + * @shadow_plane_state: the shadow-buffered plane state + * + * This function resets state for shadow-buffered planes. Helpful + * for drivers that subclass struct drm_shadow_plane_state. + */ +void __drm_gem_reset_shadow_plane(struct drm_plane *plane, + struct drm_shadow_plane_state *shadow_plane_state) +{ + __drm_atomic_helper_plane_reset(plane, &shadow_plane_state->base); +} +EXPORT_SYMBOL(__drm_gem_reset_shadow_plane); + +/** * drm_gem_reset_shadow_plane - resets a shadow-buffered plane * @plane: the plane * @@ -255,7 +307,7 @@ void drm_gem_reset_shadow_plane(struct drm_plane *plane) shadow_plane_state = kzalloc(sizeof(*shadow_plane_state), GFP_KERNEL); if (!shadow_plane_state) return; - __drm_atomic_helper_plane_reset(plane, &shadow_plane_state->base); + __drm_gem_reset_shadow_plane(plane, shadow_plane_state); } EXPORT_SYMBOL(drm_gem_reset_shadow_plane); diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 6d625cee7a6a..d5e6d4568f99 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -505,13 +505,13 @@ int drm_gem_shmem_dumb_create(struct drm_file *file, struct drm_device *dev, if (!args->pitch || !args->size) { args->pitch = min_pitch; - args->size = args->pitch * args->height; + args->size = PAGE_ALIGN(args->pitch * args->height); } else { /* ensure sane minimum values */ if (args->pitch < min_pitch) args->pitch = min_pitch; if (args->size < args->pitch * args->height) - args->size = args->pitch * args->height; + args->size = PAGE_ALIGN(args->pitch * args->height); } shmem = drm_gem_shmem_create_with_handle(file, dev, args->size, &args->handle); diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 2a1229b8364e..1e9b82e51a07 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -1012,9 +1012,8 @@ static void drm_vram_mm_cleanup(struct drm_vram_mm *vmm) * Helpers for integration with struct drm_device */ -/* deprecated; use drmm_vram_mm_init() */ -struct drm_vram_mm *drm_vram_helper_alloc_mm( - struct drm_device *dev, uint64_t vram_base, size_t vram_size) +static struct drm_vram_mm *drm_vram_helper_alloc_mm(struct drm_device *dev, uint64_t vram_base, + size_t vram_size) { int ret; @@ -1036,9 +1035,8 @@ err_kfree: dev->vram_mm = NULL; return ERR_PTR(ret); } -EXPORT_SYMBOL(drm_vram_helper_alloc_mm); -void drm_vram_helper_release_mm(struct drm_device *dev) +static void drm_vram_helper_release_mm(struct drm_device *dev) { if (!dev->vram_mm) return; @@ -1047,7 +1045,6 @@ void drm_vram_helper_release_mm(struct drm_device *dev) kfree(dev->vram_mm); dev->vram_mm = NULL; } -EXPORT_SYMBOL(drm_vram_helper_release_mm); static void drm_vram_mm_release(struct drm_device *dev, void *ptr) { diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index c3bd664ea733..945dd82e2ea3 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -74,10 +74,8 @@ * only supports devices with a single interrupt on the main device stored in * &drm_device.dev and set as the device paramter in drm_dev_alloc(). * - * These IRQ helpers are strictly optional. Drivers which roll their own only - * need to set &drm_device.irq_enabled to signal the DRM core that vblank - * interrupts are working. Since these helpers don't automatically clean up the - * requested interrupt like e.g. devm_request_irq() they're not really + * These IRQ helpers are strictly optional. Since these helpers don't automatically + * clean up the requested interrupt like e.g. devm_request_irq() they're not really * recommended. */ @@ -91,9 +89,7 @@ * and after the installation. * * This is the simplified helper interface provided for drivers with no special - * needs. Drivers which need to install interrupt handlers for multiple - * interrupts must instead set &drm_device.irq_enabled to signal the DRM core - * that vblank interrupts are available. + * needs. * * @irq must match the interrupt number that would be passed to request_irq(), * if called directly instead of using this helper function. @@ -156,8 +152,7 @@ EXPORT_SYMBOL(drm_irq_install); * * Calls the driver's &drm_driver.irq_uninstall function and unregisters the IRQ * handler. This should only be called by drivers which used drm_irq_install() - * to set up their interrupt handler. Other drivers must only reset - * &drm_device.irq_enabled to false. + * to set up their interrupt handler. * * Note that for kernel modesetting drivers it is a bug if this function fails. * The sanity checks are only to catch buggy user modesetting drivers which call diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c index 43a9b739bba7..10b4e59384ae 100644 --- a/drivers/gpu/drm/drm_mipi_dbi.c +++ b/drivers/gpu/drm/drm_mipi_dbi.c @@ -928,6 +928,59 @@ static int mipi_dbi_spi1_transfer(struct mipi_dbi *dbi, int dc, return 0; } +static int mipi_dbi_typec1_command_read(struct mipi_dbi *dbi, u8 *cmd, + u8 *data, size_t len) +{ + struct spi_device *spi = dbi->spi; + u32 speed_hz = min_t(u32, MIPI_DBI_MAX_SPI_READ_SPEED, + spi->max_speed_hz / 2); + struct spi_transfer tr[2] = { + { + .speed_hz = speed_hz, + .bits_per_word = 9, + .tx_buf = dbi->tx_buf9, + .len = 2, + }, { + .speed_hz = speed_hz, + .bits_per_word = 8, + .len = len, + .rx_buf = data, + }, + }; + struct spi_message m; + u16 *dst16; + int ret; + + if (!len) + return -EINVAL; + + if (!spi_is_bpw_supported(spi, 9)) { + /* + * FIXME: implement something like mipi_dbi_spi1e_transfer() but + * for reads using emulation. + */ + dev_err(&spi->dev, + "reading on host not supporting 9 bpw not yet implemented\n"); + return -EOPNOTSUPP; + } + + /* + * Turn the 8bit command into a 16bit version of the command in the + * buffer. Only 9 bits of this will be used when executing the actual + * transfer. + */ + dst16 = dbi->tx_buf9; + dst16[0] = *cmd; + + spi_message_init_with_transfers(&m, tr, ARRAY_SIZE(tr)); + ret = spi_sync(spi, &m); + + if (!ret) + MIPI_DBI_DEBUG_COMMAND(*cmd, data, len); + + return ret; +} + static int mipi_dbi_typec1_command(struct mipi_dbi *dbi, u8 *cmd, u8 *parameters, size_t num) { @@ -935,7 +988,7 @@ static int mipi_dbi_typec1_command(struct mipi_dbi *dbi, u8 *cmd, int ret; if (mipi_dbi_command_is_read(dbi, *cmd)) - return -EOPNOTSUPP; + return mipi_dbi_typec1_command_read(dbi, cmd, parameters, num); MIPI_DBI_DEBUG_COMMAND(*cmd, parameters, num); diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c index ca04c34e8251..997b8827fed2 100644 --- a/drivers/gpu/drm/drm_of.c +++ b/drivers/gpu/drm/drm_of.c @@ -315,7 +315,7 @@ static int drm_of_lvds_get_remote_pixels_type( remote_port = of_graph_get_remote_port(endpoint); if (!remote_port) { - of_node_put(remote_port); + of_node_put(endpoint); return -EPIPE; } @@ -331,8 +331,10 @@ static int drm_of_lvds_get_remote_pixels_type( * configurations by passing the endpoints explicitly to * drm_of_lvds_get_dual_link_pixel_order(). */ - if (!current_pt || pixels_type != current_pt) + if (!current_pt || pixels_type != current_pt) { + of_node_put(endpoint); return -EINVAL; + } } return pixels_type; diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c index 0b095a313c44..735f4f34bcc4 100644 --- a/drivers/gpu/drm/drm_simple_kms_helper.c +++ b/drivers/gpu/drm/drm_simple_kms_helper.c @@ -9,6 +9,8 @@ #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_bridge.h> +#include <drm/drm_drv.h> +#include <drm/drm_gem_atomic_helper.h> #include <drm/drm_managed.h> #include <drm/drm_plane_helper.h> #include <drm/drm_probe_helper.h> @@ -225,8 +227,14 @@ static int drm_simple_kms_plane_prepare_fb(struct drm_plane *plane, struct drm_simple_display_pipe *pipe; pipe = container_of(plane, struct drm_simple_display_pipe, plane); - if (!pipe->funcs || !pipe->funcs->prepare_fb) - return 0; + if (!pipe->funcs || !pipe->funcs->prepare_fb) { + if (WARN_ON_ONCE(!drm_core_check_feature(plane->dev, DRIVER_GEM))) + return 0; + + WARN_ON_ONCE(pipe->funcs && pipe->funcs->cleanup_fb); + + return drm_gem_simple_display_pipe_prepare_fb(pipe, state); + } return pipe->funcs->prepare_fb(pipe, state); } diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index fdd2ec87cdd1..1c5b9ef6da37 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -861,7 +861,7 @@ static int drm_syncobj_transfer_to_timeline(struct drm_file *file_private, &fence); if (ret) goto err; - chain = kzalloc(sizeof(struct dma_fence_chain), GFP_KERNEL); + chain = dma_fence_chain_alloc(); if (!chain) { ret = -ENOMEM; goto err1; @@ -1402,10 +1402,10 @@ drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data, goto err_points; } for (i = 0; i < args->count_handles; i++) { - chains[i] = kzalloc(sizeof(struct dma_fence_chain), GFP_KERNEL); + chains[i] = dma_fence_chain_alloc(); if (!chains[i]) { for (j = 0; j < i; j++) - kfree(chains[j]); + dma_fence_chain_free(chains[j]); ret = -ENOMEM; goto err_chains; } diff --git a/drivers/gpu/drm/drm_vblank.c b/drivers/gpu/drm/drm_vblank.c index 3417e1ac7918..bba6781cc48f 100644 --- a/drivers/gpu/drm/drm_vblank.c +++ b/drivers/gpu/drm/drm_vblank.c @@ -1737,6 +1737,15 @@ static void drm_wait_vblank_reply(struct drm_device *dev, unsigned int pipe, reply->tval_usec = ts.tv_nsec / 1000; } +static bool drm_wait_vblank_supported(struct drm_device *dev) +{ + if (IS_ENABLED(CONFIG_DRM_LEGACY)) { + if (unlikely(drm_core_check_feature(dev, DRIVER_LEGACY))) + return dev->irq_enabled; + } + return drm_dev_has_vblank(dev); +} + int drm_wait_vblank_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { @@ -1748,7 +1757,7 @@ int drm_wait_vblank_ioctl(struct drm_device *dev, void *data, unsigned int pipe_index; unsigned int flags, pipe, high_pipe; - if (!dev->irq_enabled) + if (!drm_wait_vblank_supported(dev)) return -EOPNOTSUPP; if (vblwait->request.type & _DRM_VBLANK_SIGNAL) @@ -2023,7 +2032,7 @@ int drm_crtc_get_sequence_ioctl(struct drm_device *dev, void *data, if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EOPNOTSUPP; - if (!dev->irq_enabled) + if (!drm_dev_has_vblank(dev)) return -EOPNOTSUPP; crtc = drm_crtc_find(dev, file_priv, get_seq->crtc_id); @@ -2082,7 +2091,7 @@ int drm_crtc_queue_sequence_ioctl(struct drm_device *dev, void *data, if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EOPNOTSUPP; - if (!dev->irq_enabled) + if (!drm_dev_has_vblank(dev)) return -EOPNOTSUPP; crtc = drm_crtc_find(dev, file_priv, queue_seq->crtc_id); diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 19826e504efc..feb6da1b6ceb 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -190,7 +190,8 @@ int etnaviv_sched_init(struct etnaviv_gpu *gpu) ret = drm_sched_init(&gpu->sched, &etnaviv_sched_ops, etnaviv_hw_jobs_limit, etnaviv_job_hang_limit, - msecs_to_jiffies(500), NULL, dev_name(gpu->dev)); + msecs_to_jiffies(500), NULL, NULL, + dev_name(gpu->dev)); if (ret) return ret; diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c index e60257f1f24b..d8f1cf4d6b69 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.c +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c @@ -300,16 +300,6 @@ static int exynos_drm_bind(struct device *dev) drm_mode_config_reset(drm); - /* - * enable drm irq mode. - * - with irq_enabled = true, we can use the vblank feature. - * - * P.S. note that we wouldn't use drm irq handler but - * just specific driver own one instead because - * drm framework supports only one irq handler. - */ - drm->irq_enabled = true; - /* init kms poll for handling hpd */ drm_kms_helper_poll_init(drm); diff --git a/drivers/gpu/drm/gma500/oaktrail_lvds.c b/drivers/gpu/drm/gma500/oaktrail_lvds.c index 432bdcc57ac9..f9b1f88c73bd 100644 --- a/drivers/gpu/drm/gma500/oaktrail_lvds.c +++ b/drivers/gpu/drm/gma500/oaktrail_lvds.c @@ -113,11 +113,11 @@ static void oaktrail_lvds_mode_set(struct drm_encoder *encoder, /* Find the connector we're trying to set up */ list_for_each_entry(connector, &mode_config->connector_list, head) { - if (!connector->encoder || connector->encoder->crtc != crtc) - continue; + if (connector->encoder && connector->encoder->crtc == crtc) + break; } - if (!connector) { + if (list_entry_is_head(connector, &mode_config->connector_list, head)) { DRM_ERROR("Couldn't find connector when setting mode"); gma_power_end(dev); return; diff --git a/drivers/gpu/drm/gud/gud_drv.c b/drivers/gpu/drm/gud/gud_drv.c index e8b672dc9832..eb4e08846da4 100644 --- a/drivers/gpu/drm/gud/gud_drv.c +++ b/drivers/gpu/drm/gud/gud_drv.c @@ -364,7 +364,6 @@ static void gud_debugfs_init(struct drm_minor *minor) static const struct drm_simple_display_pipe_funcs gud_pipe_funcs = { .check = gud_pipe_check, .update = gud_pipe_update, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, }; static const struct drm_mode_config_funcs gud_mode_config_funcs = { @@ -394,14 +393,42 @@ static const struct drm_driver gud_drm_driver = { .minor = 0, }; -static void gud_free_buffers_and_mutex(struct drm_device *drm, void *unused) +static int gud_alloc_bulk_buffer(struct gud_device *gdrm) { - struct gud_device *gdrm = to_gud_device(drm); + unsigned int i, num_pages; + struct page **pages; + void *ptr; + int ret; + + gdrm->bulk_buf = vmalloc_32(gdrm->bulk_len); + if (!gdrm->bulk_buf) + return -ENOMEM; + + num_pages = DIV_ROUND_UP(gdrm->bulk_len, PAGE_SIZE); + pages = kmalloc_array(num_pages, sizeof(struct page *), GFP_KERNEL); + if (!pages) + return -ENOMEM; + + for (i = 0, ptr = gdrm->bulk_buf; i < num_pages; i++, ptr += PAGE_SIZE) + pages[i] = vmalloc_to_page(ptr); + + ret = sg_alloc_table_from_pages(&gdrm->bulk_sgt, pages, num_pages, + 0, gdrm->bulk_len, GFP_KERNEL); + kfree(pages); + + return ret; +} + +static void gud_free_buffers_and_mutex(void *data) +{ + struct gud_device *gdrm = data; vfree(gdrm->compress_buf); - kfree(gdrm->bulk_buf); + gdrm->compress_buf = NULL; + sg_free_table(&gdrm->bulk_sgt); + vfree(gdrm->bulk_buf); + gdrm->bulk_buf = NULL; mutex_destroy(&gdrm->ctrl_lock); - mutex_destroy(&gdrm->damage_lock); } static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id) @@ -455,7 +482,7 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id) INIT_WORK(&gdrm->work, gud_flush_work); gud_clear_damage(gdrm); - ret = drmm_add_action_or_reset(drm, gud_free_buffers_and_mutex, NULL); + ret = devm_add_action(dev, gud_free_buffers_and_mutex, gdrm); if (ret) return ret; @@ -536,24 +563,17 @@ static int gud_probe(struct usb_interface *intf, const struct usb_device_id *id) if (desc.max_buffer_size) max_buffer_size = le32_to_cpu(desc.max_buffer_size); -retry: - /* - * Use plain kmalloc here since devm_kmalloc() places struct devres at the beginning - * of the buffer it allocates. This wastes a lot of memory when allocating big buffers. - * Asking for 2M would actually allocate 4M. This would also prevent getting the biggest - * possible buffer potentially leading to split transfers. - */ - gdrm->bulk_buf = kmalloc(max_buffer_size, GFP_KERNEL | __GFP_NOWARN); - if (!gdrm->bulk_buf) { - max_buffer_size = roundup_pow_of_two(max_buffer_size) / 2; - if (max_buffer_size < SZ_512K) - return -ENOMEM; - goto retry; - } + /* Prevent a misbehaving device from allocating loads of RAM. 4096x4096@XRGB8888 = 64 MB */ + if (max_buffer_size > SZ_64M) + max_buffer_size = SZ_64M; gdrm->bulk_pipe = usb_sndbulkpipe(interface_to_usbdev(intf), usb_endpoint_num(bulk_out)); gdrm->bulk_len = max_buffer_size; + ret = gud_alloc_bulk_buffer(gdrm); + if (ret) + return ret; + if (gdrm->compression & GUD_COMPRESSION_LZ4) { gdrm->lz4_comp_mem = devm_kmalloc(dev, LZ4_MEM_COMPRESS, GFP_KERNEL); if (!gdrm->lz4_comp_mem) @@ -640,6 +660,7 @@ static int gud_resume(struct usb_interface *intf) static const struct usb_device_id gud_id_table[] = { { USB_DEVICE_INTERFACE_CLASS(0x1d50, 0x614d, USB_CLASS_VENDOR_SPEC) }, + { USB_DEVICE_INTERFACE_CLASS(0x16d0, 0x10a9, USB_CLASS_VENDOR_SPEC) }, { } }; diff --git a/drivers/gpu/drm/gud/gud_internal.h b/drivers/gpu/drm/gud/gud_internal.h index b65105585578..2a388e27d5d7 100644 --- a/drivers/gpu/drm/gud/gud_internal.h +++ b/drivers/gpu/drm/gud/gud_internal.h @@ -5,6 +5,7 @@ #include <linux/list.h> #include <linux/mutex.h> +#include <linux/scatterlist.h> #include <linux/usb.h> #include <linux/workqueue.h> #include <uapi/drm/drm_fourcc.h> @@ -26,6 +27,7 @@ struct gud_device { unsigned int bulk_pipe; void *bulk_buf; size_t bulk_len; + struct sg_table bulk_sgt; u8 compression; void *lz4_comp_mem; diff --git a/drivers/gpu/drm/gud/gud_pipe.c b/drivers/gpu/drm/gud/gud_pipe.c index 2f83ab6b8e61..8f56bf618ac2 100644 --- a/drivers/gpu/drm/gud/gud_pipe.c +++ b/drivers/gpu/drm/gud/gud_pipe.c @@ -24,6 +24,19 @@ #include "gud_internal.h" /* + * Some userspace rendering loops runs all displays in the same loop. + * This means that a fast display will have to wait for a slow one. + * For this reason gud does flushing asynchronous by default. + * The down side is that in e.g. a single display setup userspace thinks + * the display is insanely fast since the driver reports back immediately + * that the flush/pageflip is done. This wastes CPU and power. + * Such users might want to set this module parameter to false. + */ +static bool gud_async_flush = true; +module_param_named(async_flush, gud_async_flush, bool, 0644); +MODULE_PARM_DESC(async_flush, "Enable asynchronous flushing [default=true]"); + +/* * FIXME: The driver is probably broken on Big Endian machines. * See discussion: * https://lore.kernel.org/dri-devel/CAKb7UvihLX0hgBOP3VBG7O+atwZcUVCPVuBdfmDMpg0NjXe-cQ@mail.gmail.com/ @@ -220,13 +233,51 @@ vunmap: return ret; } +struct gud_usb_bulk_context { + struct timer_list timer; + struct usb_sg_request sgr; +}; + +static void gud_usb_bulk_timeout(struct timer_list *t) +{ + struct gud_usb_bulk_context *ctx = from_timer(ctx, t, timer); + + usb_sg_cancel(&ctx->sgr); +} + +static int gud_usb_bulk(struct gud_device *gdrm, size_t len) +{ + struct gud_usb_bulk_context ctx; + int ret; + + ret = usb_sg_init(&ctx.sgr, gud_to_usb_device(gdrm), gdrm->bulk_pipe, 0, + gdrm->bulk_sgt.sgl, gdrm->bulk_sgt.nents, len, GFP_KERNEL); + if (ret) + return ret; + + timer_setup_on_stack(&ctx.timer, gud_usb_bulk_timeout, 0); + mod_timer(&ctx.timer, jiffies + msecs_to_jiffies(3000)); + + usb_sg_wait(&ctx.sgr); + + if (!del_timer_sync(&ctx.timer)) + ret = -ETIMEDOUT; + else if (ctx.sgr.status < 0) + ret = ctx.sgr.status; + else if (ctx.sgr.bytes != len) + ret = -EIO; + + destroy_timer_on_stack(&ctx.timer); + + return ret; +} + static int gud_flush_rect(struct gud_device *gdrm, struct drm_framebuffer *fb, const struct drm_format_info *format, struct drm_rect *rect) { - struct usb_device *usb = gud_to_usb_device(gdrm); struct gud_set_buffer_req req; - int ret, actual_length; size_t len, trlen; + int ret; drm_dbg(&gdrm->drm, "Flushing [FB:%d] " DRM_RECT_FMT "\n", fb->base.id, DRM_RECT_ARG(rect)); @@ -255,10 +306,7 @@ static int gud_flush_rect(struct gud_device *gdrm, struct drm_framebuffer *fb, return ret; } - ret = usb_bulk_msg(usb, gdrm->bulk_pipe, gdrm->bulk_buf, trlen, - &actual_length, msecs_to_jiffies(3000)); - if (!ret && trlen != actual_length) - ret = -EIO; + ret = gud_usb_bulk(gdrm, trlen); if (ret) gdrm->stats_num_errors++; @@ -543,6 +591,8 @@ void gud_pipe_update(struct drm_simple_display_pipe *pipe, if (gdrm->flags & GUD_DISPLAY_FLAG_FULL_UPDATE) drm_rect_init(&damage, 0, 0, fb->width, fb->height); gud_fb_queue_damage(gdrm, fb, &damage); + if (!gud_async_flush) + flush_work(&gdrm->work); } if (!crtc->state->enable) diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c index fa8da0ef707e..89bed78f1466 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c @@ -152,8 +152,7 @@ static const struct drm_plane_funcs hibmc_plane_funcs = { }; static const struct drm_plane_helper_funcs hibmc_plane_helper_funcs = { - .prepare_fb = drm_gem_vram_plane_helper_prepare_fb, - .cleanup_fb = drm_gem_vram_plane_helper_cleanup_fb, + DRM_GEM_VRAM_PLANE_HELPER_FUNCS, .atomic_check = hibmc_plane_atomic_check, .atomic_update = hibmc_plane_atomic_update, }; diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c index f4bc5386574a..f73a8e0ea12e 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c +++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c @@ -19,7 +19,6 @@ #include <drm/drm_drv.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_gem_vram_helper.h> -#include <drm/drm_irq.h> #include <drm/drm_managed.h> #include <drm/drm_vblank.h> @@ -28,7 +27,7 @@ DEFINE_DRM_GEM_FOPS(hibmc_fops); -static irqreturn_t hibmc_drm_interrupt(int irq, void *arg) +static irqreturn_t hibmc_interrupt(int irq, void *arg) { struct drm_device *dev = (struct drm_device *)arg; struct hibmc_drm_private *priv = to_hibmc_drm_private(dev); @@ -63,7 +62,6 @@ static const struct drm_driver hibmc_driver = { .dumb_create = hibmc_dumb_create, .dumb_map_offset = drm_gem_ttm_dumb_map_offset, .gem_prime_mmap = drm_gem_prime_mmap, - .irq_handler = hibmc_drm_interrupt, }; static int __maybe_unused hibmc_pm_suspend(struct device *dev) @@ -251,10 +249,12 @@ static int hibmc_hw_init(struct hibmc_drm_private *priv) static int hibmc_unload(struct drm_device *dev) { + struct hibmc_drm_private *priv = to_hibmc_drm_private(dev); + struct pci_dev *pdev = to_pci_dev(dev->dev); + drm_atomic_helper_shutdown(dev); - if (dev->irq_enabled) - drm_irq_uninstall(dev); + free_irq(pdev->irq, dev); pci_disable_msi(to_pci_dev(dev->dev)); @@ -291,7 +291,9 @@ static int hibmc_load(struct drm_device *dev) if (ret) { drm_warn(dev, "enabling MSI failed: %d\n", ret); } else { - ret = drm_irq_install(dev, pdev->irq); + /* PCI devices require shared interrupts. */ + ret = request_irq(pdev->irq, hibmc_interrupt, IRQF_SHARED, + dev->driver->name, dev); if (ret) drm_warn(dev, "install irq failed: %d\n", ret); } @@ -314,7 +316,7 @@ static int hibmc_pci_probe(struct pci_dev *pdev, struct drm_device *dev; int ret; - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "hibmcdrmfb"); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &hibmc_driver); if (ret) return ret; diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c index e590e19db657..98ae9a48f3fe 100644 --- a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c +++ b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_drv.c @@ -185,8 +185,6 @@ static int kirin_drm_kms_init(struct drm_device *dev, DRM_ERROR("failed to initialize vblank.\n"); goto err_unbind_all; } - /* with irq_enabled = true, we can use the vblank feature. */ - dev->irq_enabled = true; /* reset all the states of crtc/plane/encoder/connector */ drm_mode_config_reset(dev); diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c index eb06c92c4bfd..cd818a629183 100644 --- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c +++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c @@ -82,7 +82,7 @@ static int hyperv_setup_gen1(struct hyperv_drm_device *hv) return -ENODEV; } - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "hypervdrmfb"); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &hyperv_driver); if (ret) { drm_err(dev, "Not able to remove boot fb\n"); return ret; @@ -127,7 +127,7 @@ static int hyperv_setup_gen2(struct hyperv_drm_device *hv, drm_aperture_remove_conflicting_framebuffers(screen_info.lfb_base, screen_info.lfb_size, false, - "hypervdrmfb"); + &hyperv_driver); hv->fb_size = (unsigned long)hv->mmio_megabytes * 1024 * 1024; diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 4f22cac1c49b..f57dfc74d6ce 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -155,6 +155,7 @@ gem-y += \ gem/i915_gem_stolen.o \ gem/i915_gem_throttle.o \ gem/i915_gem_tiling.o \ + gem/i915_gem_ttm.o \ gem/i915_gem_userptr.o \ gem/i915_gem_wait.o \ gem/i915_gemfs.o diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 2589065fb630..eec6c9e9cda7 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -11778,7 +11778,7 @@ intel_user_framebuffer_create(struct drm_device *dev, /* object is backed with LMEM for discrete */ i915 = to_i915(obj->base.dev); - if (HAS_LMEM(i915) && !i915_gem_object_is_lmem(obj)) { + if (HAS_LMEM(i915) && !i915_gem_object_validates_to_lmem(obj)) { /* object is "remote", not in local memory */ i915_gem_object_put(obj); return ERR_PTR(-EREMOTE); diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index d7b5e26e1394..d94f361b548b 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -314,7 +314,7 @@ struct intel_panel { /* DPCD backlight */ union { struct { - u8 pwmgen_bit_count; + struct drm_edp_backlight_info info; } vesa; struct { bool sdr_uses_aux; diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index 8e9ac9ba1d38..6ac568617ef3 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -107,7 +107,7 @@ intel_dp_aux_supports_hdr_backlight(struct intel_connector *connector) u8 tcon_cap[4]; ret = drm_dp_dpcd_read(aux, INTEL_EDP_HDR_TCON_CAP0, tcon_cap, sizeof(tcon_cap)); - if (ret < 0) + if (ret != sizeof(tcon_cap)) return false; if (!(tcon_cap[1] & INTEL_EDP_HDR_TCON_BRIGHTNESS_NITS_CAP)) @@ -137,7 +137,7 @@ intel_dp_aux_hdr_get_backlight(struct intel_connector *connector, enum pipe pipe u8 tmp; u8 buf[2] = { 0 }; - if (drm_dp_dpcd_readb(&intel_dp->aux, INTEL_EDP_HDR_GETSET_CTRL_PARAMS, &tmp) < 0) { + if (drm_dp_dpcd_readb(&intel_dp->aux, INTEL_EDP_HDR_GETSET_CTRL_PARAMS, &tmp) != 1) { drm_err(&i915->drm, "Failed to read current backlight mode from DPCD\n"); return 0; } @@ -153,7 +153,8 @@ intel_dp_aux_hdr_get_backlight(struct intel_connector *connector, enum pipe pipe return panel->backlight.max; } - if (drm_dp_dpcd_read(&intel_dp->aux, INTEL_EDP_BRIGHTNESS_NITS_LSB, buf, sizeof(buf)) < 0) { + if (drm_dp_dpcd_read(&intel_dp->aux, INTEL_EDP_BRIGHTNESS_NITS_LSB, buf, + sizeof(buf)) != sizeof(buf)) { drm_err(&i915->drm, "Failed to read brightness from DPCD\n"); return 0; } @@ -172,7 +173,8 @@ intel_dp_aux_hdr_set_aux_backlight(const struct drm_connector_state *conn_state, buf[0] = level & 0xFF; buf[1] = (level & 0xFF00) >> 8; - if (drm_dp_dpcd_write(&intel_dp->aux, INTEL_EDP_BRIGHTNESS_NITS_LSB, buf, 4) < 0) + if (drm_dp_dpcd_write(&intel_dp->aux, INTEL_EDP_BRIGHTNESS_NITS_LSB, buf, + sizeof(buf)) != sizeof(buf)) drm_err(dev, "Failed to write brightness level to DPCD\n"); } @@ -203,7 +205,7 @@ intel_dp_aux_hdr_enable_backlight(const struct intel_crtc_state *crtc_state, u8 old_ctrl, ctrl; ret = drm_dp_dpcd_readb(&intel_dp->aux, INTEL_EDP_HDR_GETSET_CTRL_PARAMS, &old_ctrl); - if (ret < 0) { + if (ret != 1) { drm_err(&i915->drm, "Failed to read current backlight control mode: %d\n", ret); return; } @@ -221,7 +223,7 @@ intel_dp_aux_hdr_enable_backlight(const struct intel_crtc_state *crtc_state, } if (ctrl != old_ctrl) - if (drm_dp_dpcd_writeb(&intel_dp->aux, INTEL_EDP_HDR_GETSET_CTRL_PARAMS, ctrl) < 0) + if (drm_dp_dpcd_writeb(&intel_dp->aux, INTEL_EDP_HDR_GETSET_CTRL_PARAMS, ctrl) != 1) drm_err(&i915->drm, "Failed to configure DPCD brightness controls\n"); } @@ -268,153 +270,19 @@ intel_dp_aux_hdr_setup_backlight(struct intel_connector *connector, enum pipe pi } /* VESA backlight callbacks */ -static void set_vesa_backlight_enable(struct intel_dp *intel_dp, bool enable) -{ - struct drm_i915_private *i915 = dp_to_i915(intel_dp); - u8 reg_val = 0; - - /* Early return when display use other mechanism to enable backlight. */ - if (!(intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP)) - return; - - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_EDP_DISPLAY_CONTROL_REGISTER, - ®_val) < 0) { - drm_dbg_kms(&i915->drm, "Failed to read DPCD register 0x%x\n", - DP_EDP_DISPLAY_CONTROL_REGISTER); - return; - } - if (enable) - reg_val |= DP_EDP_BACKLIGHT_ENABLE; - else - reg_val &= ~(DP_EDP_BACKLIGHT_ENABLE); - - if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_EDP_DISPLAY_CONTROL_REGISTER, - reg_val) != 1) { - drm_dbg_kms(&i915->drm, "Failed to %s aux backlight\n", - enabledisable(enable)); - } -} - -static bool intel_dp_aux_vesa_backlight_dpcd_mode(struct intel_connector *connector) -{ - struct intel_dp *intel_dp = intel_attached_dp(connector); - struct drm_i915_private *i915 = dp_to_i915(intel_dp); - u8 mode_reg; - - if (drm_dp_dpcd_readb(&intel_dp->aux, - DP_EDP_BACKLIGHT_MODE_SET_REGISTER, - &mode_reg) != 1) { - drm_dbg_kms(&i915->drm, - "Failed to read the DPCD register 0x%x\n", - DP_EDP_BACKLIGHT_MODE_SET_REGISTER); - return false; - } - - return (mode_reg & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK) == - DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD; -} - -/* - * Read the current backlight value from DPCD register(s) based - * on if 8-bit(MSB) or 16-bit(MSB and LSB) values are supported - */ static u32 intel_dp_aux_vesa_get_backlight(struct intel_connector *connector, enum pipe unused) { - struct intel_dp *intel_dp = intel_attached_dp(connector); - struct drm_i915_private *i915 = dp_to_i915(intel_dp); - u8 read_val[2] = { 0x0 }; - u16 level = 0; - - /* - * If we're not in DPCD control mode yet, the programmed brightness - * value is meaningless and we should assume max brightness - */ - if (!intel_dp_aux_vesa_backlight_dpcd_mode(connector)) - return connector->panel.backlight.max; - - if (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB, - &read_val, sizeof(read_val)) < 0) { - drm_dbg_kms(&i915->drm, "Failed to read DPCD register 0x%x\n", - DP_EDP_BACKLIGHT_BRIGHTNESS_MSB); - return 0; - } - level = read_val[0]; - if (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT) - level = (read_val[0] << 8 | read_val[1]); - - return level; + return connector->panel.backlight.level; } -/* - * Sends the current backlight level over the aux channel, checking if its using - * 8-bit or 16 bit value (MSB and LSB) - */ static void -intel_dp_aux_vesa_set_backlight(const struct drm_connector_state *conn_state, - u32 level) +intel_dp_aux_vesa_set_backlight(const struct drm_connector_state *conn_state, u32 level) { struct intel_connector *connector = to_intel_connector(conn_state->connector); - struct intel_dp *intel_dp = intel_attached_dp(connector); - struct drm_i915_private *i915 = dp_to_i915(intel_dp); - u8 vals[2] = { 0x0 }; - - vals[0] = level; - - /* Write the MSB and/or LSB */ - if (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_BYTE_COUNT) { - vals[0] = (level & 0xFF00) >> 8; - vals[1] = (level & 0xFF); - } - if (drm_dp_dpcd_write(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB, - vals, sizeof(vals)) < 0) { - drm_dbg_kms(&i915->drm, - "Failed to write aux backlight level\n"); - return; - } -} - -/* - * Set PWM Frequency divider to match desired frequency in vbt. - * The PWM Frequency is calculated as 27Mhz / (F x P). - * - Where F = PWM Frequency Pre-Divider value programmed by field 7:0 of the - * EDP_BACKLIGHT_FREQ_SET register (DPCD Address 00728h) - * - Where P = 2^Pn, where Pn is the value programmed by field 4:0 of the - * EDP_PWMGEN_BIT_COUNT register (DPCD Address 00724h) - */ -static bool intel_dp_aux_vesa_set_pwm_freq(struct intel_connector *connector) -{ - struct drm_i915_private *dev_priv = to_i915(connector->base.dev); - struct intel_dp *intel_dp = intel_attached_dp(connector); - const u8 pn = connector->panel.backlight.edp.vesa.pwmgen_bit_count; - int freq, fxp, f, fxp_actual, fxp_min, fxp_max; - - freq = dev_priv->vbt.backlight.pwm_freq_hz; - if (!freq) { - drm_dbg_kms(&dev_priv->drm, - "Use panel default backlight frequency\n"); - return false; - } - - fxp = DIV_ROUND_CLOSEST(KHz(DP_EDP_BACKLIGHT_FREQ_BASE_KHZ), freq); - f = clamp(DIV_ROUND_CLOSEST(fxp, 1 << pn), 1, 255); - fxp_actual = f << pn; - - /* Ensure frequency is within 25% of desired value */ - fxp_min = DIV_ROUND_CLOSEST(fxp * 3, 4); - fxp_max = DIV_ROUND_CLOSEST(fxp * 5, 4); - - if (fxp_min > fxp_actual || fxp_actual > fxp_max) { - drm_dbg_kms(&dev_priv->drm, "Actual frequency out of range\n"); - return false; - } + struct intel_panel *panel = &connector->panel; + struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder); - if (drm_dp_dpcd_writeb(&intel_dp->aux, - DP_EDP_BACKLIGHT_FREQ_SET, (u8) f) < 0) { - drm_dbg_kms(&dev_priv->drm, - "Failed to write aux backlight freq\n"); - return false; - } - return true; + drm_edp_backlight_set_level(&intel_dp->aux, &panel->backlight.edp.vesa.info, level); } static void @@ -422,159 +290,46 @@ intel_dp_aux_vesa_enable_backlight(const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state, u32 level) { struct intel_connector *connector = to_intel_connector(conn_state->connector); - struct intel_dp *intel_dp = intel_attached_dp(connector); - struct drm_i915_private *i915 = dp_to_i915(intel_dp); struct intel_panel *panel = &connector->panel; - u8 dpcd_buf, new_dpcd_buf, edp_backlight_mode; - u8 pwmgen_bit_count = panel->backlight.edp.vesa.pwmgen_bit_count; - - if (drm_dp_dpcd_readb(&intel_dp->aux, - DP_EDP_BACKLIGHT_MODE_SET_REGISTER, &dpcd_buf) != 1) { - drm_dbg_kms(&i915->drm, "Failed to read DPCD register 0x%x\n", - DP_EDP_BACKLIGHT_MODE_SET_REGISTER); - return; - } - - new_dpcd_buf = dpcd_buf; - edp_backlight_mode = dpcd_buf & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK; - - switch (edp_backlight_mode) { - case DP_EDP_BACKLIGHT_CONTROL_MODE_PWM: - case DP_EDP_BACKLIGHT_CONTROL_MODE_PRESET: - case DP_EDP_BACKLIGHT_CONTROL_MODE_PRODUCT: - new_dpcd_buf &= ~DP_EDP_BACKLIGHT_CONTROL_MODE_MASK; - new_dpcd_buf |= DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD; - - if (drm_dp_dpcd_writeb(&intel_dp->aux, - DP_EDP_PWMGEN_BIT_COUNT, - pwmgen_bit_count) < 0) - drm_dbg_kms(&i915->drm, - "Failed to write aux pwmgen bit count\n"); - - break; - - /* Do nothing when it is already DPCD mode */ - case DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD: - default: - break; - } - - if (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_FREQ_AUX_SET_CAP) - if (intel_dp_aux_vesa_set_pwm_freq(connector)) - new_dpcd_buf |= DP_EDP_BACKLIGHT_FREQ_AUX_SET_ENABLE; - - if (new_dpcd_buf != dpcd_buf) { - if (drm_dp_dpcd_writeb(&intel_dp->aux, - DP_EDP_BACKLIGHT_MODE_SET_REGISTER, new_dpcd_buf) < 0) { - drm_dbg_kms(&i915->drm, - "Failed to write aux backlight mode\n"); - } - } + struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder); - intel_dp_aux_vesa_set_backlight(conn_state, level); - set_vesa_backlight_enable(intel_dp, true); + drm_edp_backlight_enable(&intel_dp->aux, &panel->backlight.edp.vesa.info, level); } static void intel_dp_aux_vesa_disable_backlight(const struct drm_connector_state *old_conn_state, u32 level) { - set_vesa_backlight_enable(enc_to_intel_dp(to_intel_encoder(old_conn_state->best_encoder)), - false); -} - -static u32 intel_dp_aux_vesa_calc_max_backlight(struct intel_connector *connector) -{ - struct drm_i915_private *i915 = to_i915(connector->base.dev); - struct intel_dp *intel_dp = intel_attached_dp(connector); + struct intel_connector *connector = to_intel_connector(old_conn_state->connector); struct intel_panel *panel = &connector->panel; - u32 max_backlight = 0; - int freq, fxp, fxp_min, fxp_max, fxp_actual, f = 1; - u8 pn, pn_min, pn_max; - - if (drm_dp_dpcd_readb(&intel_dp->aux, DP_EDP_PWMGEN_BIT_COUNT, &pn) == 1) { - pn &= DP_EDP_PWMGEN_BIT_COUNT_MASK; - max_backlight = (1 << pn) - 1; - } - - /* Find desired value of (F x P) - * Note that, if F x P is out of supported range, the maximum value or - * minimum value will applied automatically. So no need to check that. - */ - freq = i915->vbt.backlight.pwm_freq_hz; - drm_dbg_kms(&i915->drm, "VBT defined backlight frequency %u Hz\n", - freq); - if (!freq) { - drm_dbg_kms(&i915->drm, - "Use panel default backlight frequency\n"); - return max_backlight; - } - - fxp = DIV_ROUND_CLOSEST(KHz(DP_EDP_BACKLIGHT_FREQ_BASE_KHZ), freq); - - /* Use highest possible value of Pn for more granularity of brightness - * adjustment while satifying the conditions below. - * - Pn is in the range of Pn_min and Pn_max - * - F is in the range of 1 and 255 - * - FxP is within 25% of desired value. - * Note: 25% is arbitrary value and may need some tweak. - */ - if (drm_dp_dpcd_readb(&intel_dp->aux, - DP_EDP_PWMGEN_BIT_COUNT_CAP_MIN, &pn_min) != 1) { - drm_dbg_kms(&i915->drm, - "Failed to read pwmgen bit count cap min\n"); - return max_backlight; - } - if (drm_dp_dpcd_readb(&intel_dp->aux, - DP_EDP_PWMGEN_BIT_COUNT_CAP_MAX, &pn_max) != 1) { - drm_dbg_kms(&i915->drm, - "Failed to read pwmgen bit count cap max\n"); - return max_backlight; - } - pn_min &= DP_EDP_PWMGEN_BIT_COUNT_MASK; - pn_max &= DP_EDP_PWMGEN_BIT_COUNT_MASK; - - fxp_min = DIV_ROUND_CLOSEST(fxp * 3, 4); - fxp_max = DIV_ROUND_CLOSEST(fxp * 5, 4); - if (fxp_min < (1 << pn_min) || (255 << pn_max) < fxp_max) { - drm_dbg_kms(&i915->drm, - "VBT defined backlight frequency out of range\n"); - return max_backlight; - } - - for (pn = pn_max; pn >= pn_min; pn--) { - f = clamp(DIV_ROUND_CLOSEST(fxp, 1 << pn), 1, 255); - fxp_actual = f << pn; - if (fxp_min <= fxp_actual && fxp_actual <= fxp_max) - break; - } - - drm_dbg_kms(&i915->drm, "Using eDP pwmgen bit count of %d\n", pn); - if (drm_dp_dpcd_writeb(&intel_dp->aux, - DP_EDP_PWMGEN_BIT_COUNT, pn) < 0) { - drm_dbg_kms(&i915->drm, - "Failed to write aux pwmgen bit count\n"); - return max_backlight; - } - panel->backlight.edp.vesa.pwmgen_bit_count = pn; - - max_backlight = (1 << pn) - 1; + struct intel_dp *intel_dp = enc_to_intel_dp(connector->encoder); - return max_backlight; + drm_edp_backlight_disable(&intel_dp->aux, &panel->backlight.edp.vesa.info); } -static int intel_dp_aux_vesa_setup_backlight(struct intel_connector *connector, - enum pipe pipe) +static int intel_dp_aux_vesa_setup_backlight(struct intel_connector *connector, enum pipe pipe) { + struct intel_dp *intel_dp = intel_attached_dp(connector); struct intel_panel *panel = &connector->panel; + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + u16 current_level; + u8 current_mode; + int ret; - panel->backlight.max = intel_dp_aux_vesa_calc_max_backlight(connector); - if (!panel->backlight.max) - return -ENODEV; + ret = drm_edp_backlight_init(&intel_dp->aux, &panel->backlight.edp.vesa.info, + i915->vbt.backlight.pwm_freq_hz, intel_dp->edp_dpcd, + ¤t_level, ¤t_mode); + if (ret < 0) + return ret; + panel->backlight.max = panel->backlight.edp.vesa.info.max; panel->backlight.min = 0; - panel->backlight.level = intel_dp_aux_vesa_get_backlight(connector, pipe); - panel->backlight.enabled = intel_dp_aux_vesa_backlight_dpcd_mode(connector) && - panel->backlight.level != 0; + if (current_mode == DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD) { + panel->backlight.level = current_level; + panel->backlight.enabled = panel->backlight.level != 0; + } else { + panel->backlight.level = panel->backlight.max; + panel->backlight.enabled = false; + } return 0; } @@ -585,16 +340,12 @@ intel_dp_aux_supports_vesa_backlight(struct intel_connector *connector) struct intel_dp *intel_dp = intel_attached_dp(connector); struct drm_i915_private *i915 = dp_to_i915(intel_dp); - /* Check the eDP Display control capabilities registers to determine if - * the panel can support backlight control over the aux channel. - * - * TODO: We currently only support AUX only backlight configurations, not backlights which + /* TODO: We currently only support AUX only backlight configurations, not backlights which * require a mix of PWM and AUX controls to work. In the mean time, these machines typically * work just fine using normal PWM controls anyway. */ - if (intel_dp->edp_dpcd[1] & DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP && - (intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP) && - (intel_dp->edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_AUX_SET_CAP)) { + if ((intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP) && + drm_edp_backlight_supported(intel_dp->edp_dpcd)) { drm_dbg_kms(&i915->drm, "AUX Backlight Control Supported!\n"); return true; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c index 548ddf39d853..93bf63bbaff1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_create.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c @@ -85,13 +85,10 @@ i915_gem_setup(struct drm_i915_gem_object *obj, u64 size) return -E2BIG; /* - * For now resort to CPU based clearing for device local-memory, in the - * near future this will use the blitter engine for accelerated, GPU - * based clearing. + * I915_BO_ALLOC_USER will make sure the object is cleared before + * any user access. */ - flags = 0; - if (mr->type == INTEL_MEMORY_LOCAL) - flags = I915_BO_ALLOC_CPU_CLEAR; + flags = I915_BO_ALLOC_USER; ret = mr->ops->init_object(mr, obj, size, flags); if (ret) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index a8abc9af5ff4..8e195fa7626a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -2983,7 +2983,7 @@ __free_fence_array(struct eb_fence *fences, unsigned int n) while (n--) { drm_syncobj_put(ptr_mask_bits(fences[n].syncobj, 2)); dma_fence_put(fences[n].dma_fence); - kfree(fences[n].chain_fence); + dma_fence_chain_free(fences[n].chain_fence); } kvfree(fences); } @@ -3097,9 +3097,7 @@ add_timeline_fence_array(struct i915_execbuffer *eb, return -EINVAL; } - f->chain_fence = - kmalloc(sizeof(*f->chain_fence), - GFP_KERNEL); + f->chain_fence = dma_fence_chain_alloc(); if (!f->chain_fence) { drm_syncobj_put(syncobj); dma_fence_put(fence); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c index 3b4aa28a076d..d539dffa1554 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c @@ -4,74 +4,10 @@ */ #include "intel_memory_region.h" -#include "intel_region_ttm.h" #include "gem/i915_gem_region.h" #include "gem/i915_gem_lmem.h" #include "i915_drv.h" -static void lmem_put_pages(struct drm_i915_gem_object *obj, - struct sg_table *pages) -{ - intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node); - obj->mm.dirty = false; - sg_free_table(pages); - kfree(pages); -} - -static int lmem_get_pages(struct drm_i915_gem_object *obj) -{ - unsigned int flags; - struct sg_table *pages; - - flags = I915_ALLOC_MIN_PAGE_SIZE; - if (obj->flags & I915_BO_ALLOC_CONTIGUOUS) - flags |= I915_ALLOC_CONTIGUOUS; - - obj->mm.st_mm_node = intel_region_ttm_node_alloc(obj->mm.region, - obj->base.size, - flags); - if (IS_ERR(obj->mm.st_mm_node)) - return PTR_ERR(obj->mm.st_mm_node); - - /* Range manager is always contigous */ - if (obj->mm.region->is_range_manager) - obj->flags |= I915_BO_ALLOC_CONTIGUOUS; - pages = intel_region_ttm_node_to_st(obj->mm.region, obj->mm.st_mm_node); - if (IS_ERR(pages)) { - intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node); - return PTR_ERR(pages); - } - - __i915_gem_object_set_pages(obj, pages, i915_sg_dma_sizes(pages->sgl)); - - if (obj->flags & I915_BO_ALLOC_CPU_CLEAR) { - void __iomem *vaddr = - i915_gem_object_lmem_io_map(obj, 0, obj->base.size); - - if (!vaddr) { - struct sg_table *pages = - __i915_gem_object_unset_pages(obj); - - if (!IS_ERR_OR_NULL(pages)) - lmem_put_pages(obj, pages); - } - - memset_io(vaddr, 0, obj->base.size); - io_mapping_unmap(vaddr); - } - - return 0; -} - -const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops = { - .name = "i915_gem_object_lmem", - .flags = I915_GEM_OBJECT_HAS_IOMEM, - - .get_pages = lmem_get_pages, - .put_pages = lmem_put_pages, - .release = i915_gem_object_release_memory_region, -}; - void __iomem * i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj, unsigned long n, @@ -87,10 +23,50 @@ i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj, return io_mapping_map_wc(&obj->mm.region->iomap, offset, size); } +/** + * i915_gem_object_validates_to_lmem - Whether the object is resident in + * lmem when pages are present. + * @obj: The object to check. + * + * Migratable objects residency may change from under us if the object is + * not pinned or locked. This function is intended to be used to check whether + * the object can only reside in lmem when pages are present. + * + * Return: Whether the object is always resident in lmem when pages are + * present. + */ +bool i915_gem_object_validates_to_lmem(struct drm_i915_gem_object *obj) +{ + struct intel_memory_region *mr = READ_ONCE(obj->mm.region); + + return !i915_gem_object_migratable(obj) && + mr && (mr->type == INTEL_MEMORY_LOCAL || + mr->type == INTEL_MEMORY_STOLEN_LOCAL); +} + +/** + * i915_gem_object_is_lmem - Whether the object is resident in + * lmem + * @obj: The object to check. + * + * Even if an object is allowed to migrate and change memory region, + * this function checks whether it will always be present in lmem when + * valid *or* if that's not the case, whether it's currently resident in lmem. + * For migratable and evictable objects, the latter only makes sense when + * the object is locked. + * + * Return: Whether the object migratable but resident in lmem, or not + * migratable and will be present in lmem when valid. + */ bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj) { - struct intel_memory_region *mr = obj->mm.region; + struct intel_memory_region *mr = READ_ONCE(obj->mm.region); +#ifdef CONFIG_LOCKDEP + if (i915_gem_object_migratable(obj) && + i915_gem_object_evictable(obj)) + assert_object_held(obj); +#endif return mr && (mr->type == INTEL_MEMORY_LOCAL || mr->type == INTEL_MEMORY_STOLEN_LOCAL); } @@ -103,23 +79,3 @@ i915_gem_object_create_lmem(struct drm_i915_private *i915, return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_LMEM], size, flags); } - -int __i915_gem_lmem_object_init(struct intel_memory_region *mem, - struct drm_i915_gem_object *obj, - resource_size_t size, - unsigned int flags) -{ - static struct lock_class_key lock_class; - struct drm_i915_private *i915 = mem->i915; - - drm_gem_private_object_init(&i915->drm, &obj->base, size); - i915_gem_object_init(obj, &i915_gem_lmem_obj_ops, &lock_class, flags); - - obj->read_domains = I915_GEM_DOMAIN_WC | I915_GEM_DOMAIN_GTT; - - i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE); - - i915_gem_object_init_memory_region(obj, mem); - - return 0; -} diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h index fac6bc5a5ebb..ea76fd11ccb0 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h @@ -26,9 +26,4 @@ i915_gem_object_create_lmem(struct drm_i915_private *i915, resource_size_t size, unsigned int flags); -int __i915_gem_lmem_object_init(struct intel_memory_region *mem, - struct drm_i915_gem_object *obj, - resource_size_t size, - unsigned int flags); - #endif /* !__I915_GEM_LMEM_H */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 215326764606..4f50a508c7a0 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -19,6 +19,7 @@ #include "i915_gem_mman.h" #include "i915_trace.h" #include "i915_user_extensions.h" +#include "i915_gem_ttm.h" #include "i915_vma.h" static inline bool @@ -624,6 +625,8 @@ mmap_offset_attach(struct drm_i915_gem_object *obj, struct i915_mmap_offset *mmo; int err; + GEM_BUG_ON(obj->ops->mmap_offset || obj->ops->mmap_ops); + mmo = lookup_mmo(obj, mmap_type); if (mmo) goto out; @@ -666,40 +669,47 @@ err: } static int -__assign_mmap_offset(struct drm_file *file, - u32 handle, +__assign_mmap_offset(struct drm_i915_gem_object *obj, enum i915_mmap_type mmap_type, - u64 *offset) + u64 *offset, struct drm_file *file) { - struct drm_i915_gem_object *obj; struct i915_mmap_offset *mmo; - int err; - obj = i915_gem_object_lookup(file, handle); - if (!obj) - return -ENOENT; + if (i915_gem_object_never_mmap(obj)) + return -ENODEV; - if (i915_gem_object_never_mmap(obj)) { - err = -ENODEV; - goto out; + if (obj->ops->mmap_offset) { + *offset = obj->ops->mmap_offset(obj); + return 0; } if (mmap_type != I915_MMAP_TYPE_GTT && !i915_gem_object_has_struct_page(obj) && - !i915_gem_object_type_has(obj, I915_GEM_OBJECT_HAS_IOMEM)) { - err = -ENODEV; - goto out; - } + !i915_gem_object_type_has(obj, I915_GEM_OBJECT_HAS_IOMEM)) + return -ENODEV; mmo = mmap_offset_attach(obj, mmap_type, file); - if (IS_ERR(mmo)) { - err = PTR_ERR(mmo); - goto out; - } + if (IS_ERR(mmo)) + return PTR_ERR(mmo); *offset = drm_vma_node_offset_addr(&mmo->vma_node); - err = 0; -out: + return 0; +} + +static int +__assign_mmap_offset_handle(struct drm_file *file, + u32 handle, + enum i915_mmap_type mmap_type, + u64 *offset) +{ + struct drm_i915_gem_object *obj; + int err; + + obj = i915_gem_object_lookup(file, handle); + if (!obj) + return -ENOENT; + + err = __assign_mmap_offset(obj, mmap_type, offset, file); i915_gem_object_put(obj); return err; } @@ -719,7 +729,7 @@ i915_gem_dumb_mmap_offset(struct drm_file *file, else mmap_type = I915_MMAP_TYPE_GTT; - return __assign_mmap_offset(file, handle, mmap_type, offset); + return __assign_mmap_offset_handle(file, handle, mmap_type, offset); } /** @@ -787,7 +797,7 @@ i915_gem_mmap_offset_ioctl(struct drm_device *dev, void *data, return -EINVAL; } - return __assign_mmap_offset(file, args->handle, type, &args->offset); + return __assign_mmap_offset_handle(file, args->handle, type, &args->offset); } static void vm_open(struct vm_area_struct *vma) @@ -891,8 +901,18 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma) * destroyed and will be invalid when the vma manager lock * is released. */ - mmo = container_of(node, struct i915_mmap_offset, vma_node); - obj = i915_gem_object_get_rcu(mmo->obj); + if (!node->driver_private) { + mmo = container_of(node, struct i915_mmap_offset, vma_node); + obj = i915_gem_object_get_rcu(mmo->obj); + + GEM_BUG_ON(obj && obj->ops->mmap_ops); + } else { + obj = i915_gem_object_get_rcu + (container_of(node, struct drm_i915_gem_object, + base.vma_node)); + + GEM_BUG_ON(obj && !obj->ops->mmap_ops); + } } drm_vma_offset_unlock_lookup(dev->vma_offset_manager); rcu_read_unlock(); @@ -914,7 +934,9 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma) } vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; - vma->vm_private_data = mmo; + + if (i915_gem_object_has_iomem(obj)) + vma->vm_flags |= VM_IO; /* * We keep the ref on mmo->obj, not vm_file, but we require @@ -928,6 +950,15 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma) /* Drop the initial creation reference, the vma is now holding one. */ fput(anon); + if (obj->ops->mmap_ops) { + vma->vm_page_prot = pgprot_decrypted(vm_get_page_prot(vma->vm_flags)); + vma->vm_ops = obj->ops->mmap_ops; + vma->vm_private_data = node->driver_private; + return 0; + } + + vma->vm_private_data = mmo; + switch (mmo->mmap_type) { case I915_MMAP_TYPE_WC: vma->vm_page_prot = diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 5706d471692d..cf18c430d51f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -172,7 +172,7 @@ static void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *f } } -static void __i915_gem_free_object_rcu(struct rcu_head *head) +void __i915_gem_free_object_rcu(struct rcu_head *head) { struct drm_i915_gem_object *obj = container_of(head, typeof(*obj), rcu); @@ -208,59 +208,69 @@ static void __i915_gem_object_free_mmaps(struct drm_i915_gem_object *obj) } } -static void __i915_gem_free_objects(struct drm_i915_private *i915, - struct llist_node *freed) +void __i915_gem_free_object(struct drm_i915_gem_object *obj) { - struct drm_i915_gem_object *obj, *on; + trace_i915_gem_object_destroy(obj); - llist_for_each_entry_safe(obj, on, freed, freed) { - trace_i915_gem_object_destroy(obj); + if (!list_empty(&obj->vma.list)) { + struct i915_vma *vma; - if (!list_empty(&obj->vma.list)) { - struct i915_vma *vma; + /* + * Note that the vma keeps an object reference while + * it is active, so it *should* not sleep while we + * destroy it. Our debug code errs insits it *might*. + * For the moment, play along. + */ + spin_lock(&obj->vma.lock); + while ((vma = list_first_entry_or_null(&obj->vma.list, + struct i915_vma, + obj_link))) { + GEM_BUG_ON(vma->obj != obj); + spin_unlock(&obj->vma.lock); + + __i915_vma_put(vma); - /* - * Note that the vma keeps an object reference while - * it is active, so it *should* not sleep while we - * destroy it. Our debug code errs insits it *might*. - * For the moment, play along. - */ spin_lock(&obj->vma.lock); - while ((vma = list_first_entry_or_null(&obj->vma.list, - struct i915_vma, - obj_link))) { - GEM_BUG_ON(vma->obj != obj); - spin_unlock(&obj->vma.lock); + } + spin_unlock(&obj->vma.lock); + } - __i915_vma_put(vma); + __i915_gem_object_free_mmaps(obj); - spin_lock(&obj->vma.lock); - } - spin_unlock(&obj->vma.lock); - } + GEM_BUG_ON(!list_empty(&obj->lut_list)); - __i915_gem_object_free_mmaps(obj); + atomic_set(&obj->mm.pages_pin_count, 0); + __i915_gem_object_put_pages(obj); + GEM_BUG_ON(i915_gem_object_has_pages(obj)); + bitmap_free(obj->bit_17); - GEM_BUG_ON(!list_empty(&obj->lut_list)); + if (obj->base.import_attach) + drm_prime_gem_destroy(&obj->base, NULL); - atomic_set(&obj->mm.pages_pin_count, 0); - __i915_gem_object_put_pages(obj); - GEM_BUG_ON(i915_gem_object_has_pages(obj)); - bitmap_free(obj->bit_17); + drm_gem_free_mmap_offset(&obj->base); - if (obj->base.import_attach) - drm_prime_gem_destroy(&obj->base, NULL); + if (obj->ops->release) + obj->ops->release(obj); - drm_gem_free_mmap_offset(&obj->base); + if (obj->mm.n_placements > 1) + kfree(obj->mm.placements); - if (obj->ops->release) - obj->ops->release(obj); + if (obj->shares_resv_from) + i915_vm_resv_put(obj->shares_resv_from); +} - if (obj->mm.n_placements > 1) - kfree(obj->mm.placements); +static void __i915_gem_free_objects(struct drm_i915_private *i915, + struct llist_node *freed) +{ + struct drm_i915_gem_object *obj, *on; - if (obj->shares_resv_from) - i915_vm_resv_put(obj->shares_resv_from); + llist_for_each_entry_safe(obj, on, freed, freed) { + might_sleep(); + if (obj->ops->delayed_free) { + obj->ops->delayed_free(obj); + continue; + } + __i915_gem_free_object(obj); /* But keep the pointer alive for RCU-protected lookups */ call_rcu(&obj->rcu, __i915_gem_free_object_rcu); @@ -318,6 +328,7 @@ static void i915_gem_free_object(struct drm_gem_object *gem_obj) * worker and performing frees directly from subsequent allocations for * crude but effective memory throttling. */ + if (llist_add(&obj->freed, &i915->mm.free_list)) queue_work(i915->wq, &i915->mm.free_work); } @@ -410,6 +421,60 @@ int i915_gem_object_read_from_page(struct drm_i915_gem_object *obj, u64 offset, return 0; } +/** + * i915_gem_object_evictable - Whether object is likely evictable after unbind. + * @obj: The object to check + * + * This function checks whether the object is likely unvictable after unbind. + * If the object is not locked when checking, the result is only advisory. + * If the object is locked when checking, and the function returns true, + * then an eviction should indeed be possible. But since unlocked vma + * unpinning and unbinding is currently possible, the object can actually + * become evictable even if this function returns false. + * + * Return: true if the object may be evictable. False otherwise. + */ +bool i915_gem_object_evictable(struct drm_i915_gem_object *obj) +{ + struct i915_vma *vma; + int pin_count = atomic_read(&obj->mm.pages_pin_count); + + if (!pin_count) + return true; + + spin_lock(&obj->vma.lock); + list_for_each_entry(vma, &obj->vma.list, obj_link) { + if (i915_vma_is_pinned(vma)) { + spin_unlock(&obj->vma.lock); + return false; + } + if (atomic_read(&vma->pages_count)) + pin_count--; + } + spin_unlock(&obj->vma.lock); + GEM_WARN_ON(pin_count < 0); + + return pin_count == 0; +} + +/** + * i915_gem_object_migratable - Whether the object is migratable out of the + * current region. + * @obj: Pointer to the object. + * + * Return: Whether the object is allowed to be resident in other + * regions than the current while pages are present. + */ +bool i915_gem_object_migratable(struct drm_i915_gem_object *obj) +{ + struct intel_memory_region *mr = READ_ONCE(obj->mm.region); + + if (!mr) + return false; + + return obj->mm.n_placements > 1; +} + void i915_gem_init__objects(struct drm_i915_private *i915) { INIT_WORK(&i915->mm.free_work, __i915_gem_free_work); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 7c0eb425cb3b..e9eecebf5c9d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -200,6 +200,9 @@ static inline bool i915_gem_object_trylock(struct drm_i915_gem_object *obj) static inline void i915_gem_object_unlock(struct drm_i915_gem_object *obj) { + if (obj->ops->adjust_lru) + obj->ops->adjust_lru(obj); + dma_resv_unlock(obj->base.resv); } @@ -339,14 +342,14 @@ struct scatterlist * __i915_gem_object_get_sg(struct drm_i915_gem_object *obj, struct i915_gem_object_page_iter *iter, unsigned int n, - unsigned int *offset, bool allow_alloc); + unsigned int *offset, bool allow_alloc, bool dma); static inline struct scatterlist * i915_gem_object_get_sg(struct drm_i915_gem_object *obj, unsigned int n, unsigned int *offset, bool allow_alloc) { - return __i915_gem_object_get_sg(obj, &obj->mm.get_page, n, offset, allow_alloc); + return __i915_gem_object_get_sg(obj, &obj->mm.get_page, n, offset, allow_alloc, false); } static inline struct scatterlist * @@ -354,7 +357,7 @@ i915_gem_object_get_sg_dma(struct drm_i915_gem_object *obj, unsigned int n, unsigned int *offset, bool allow_alloc) { - return __i915_gem_object_get_sg(obj, &obj->mm.get_dma_page, n, offset, allow_alloc); + return __i915_gem_object_get_sg(obj, &obj->mm.get_dma_page, n, offset, allow_alloc, true); } struct page * @@ -587,6 +590,16 @@ int i915_gem_object_read_from_page(struct drm_i915_gem_object *obj, u64 offset, bool i915_gem_object_is_shmem(const struct drm_i915_gem_object *obj); +void __i915_gem_free_object_rcu(struct rcu_head *head); + +void __i915_gem_free_object(struct drm_i915_gem_object *obj); + +bool i915_gem_object_evictable(struct drm_i915_gem_object *obj); + +bool i915_gem_object_migratable(struct drm_i915_gem_object *obj); + +bool i915_gem_object_validates_to_lmem(struct drm_i915_gem_object *obj); + #ifdef CONFIG_MMU_NOTIFIER static inline bool i915_gem_object_is_userptr(struct drm_i915_gem_object *obj) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index d047ea126029..2a23b77424b3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -61,10 +61,26 @@ struct drm_i915_gem_object_ops { const struct drm_i915_gem_pread *arg); int (*pwrite)(struct drm_i915_gem_object *obj, const struct drm_i915_gem_pwrite *arg); + u64 (*mmap_offset)(struct drm_i915_gem_object *obj); int (*dmabuf_export)(struct drm_i915_gem_object *obj); + + /** + * adjust_lru - notify that the madvise value was updated + * @obj: The gem object + * + * The madvise value may have been updated, or object was recently + * referenced so act accordingly (Perhaps changing an LRU list etc). + */ + void (*adjust_lru)(struct drm_i915_gem_object *obj); + + /** + * delayed_free - Override the default delayed free implementation + */ + void (*delayed_free)(struct drm_i915_gem_object *obj); void (*release)(struct drm_i915_gem_object *obj); + const struct vm_operations_struct *mmap_ops; const char *name; /* friendly name for debug, e.g. lockdep classes */ }; @@ -187,12 +203,14 @@ struct drm_i915_gem_object { #define I915_BO_ALLOC_VOLATILE BIT(1) #define I915_BO_ALLOC_STRUCT_PAGE BIT(2) #define I915_BO_ALLOC_CPU_CLEAR BIT(3) +#define I915_BO_ALLOC_USER BIT(4) #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | \ I915_BO_ALLOC_VOLATILE | \ I915_BO_ALLOC_STRUCT_PAGE | \ - I915_BO_ALLOC_CPU_CLEAR) -#define I915_BO_READONLY BIT(4) -#define I915_TILING_QUIRK_BIT 5 /* unknown swizzling; do not release! */ + I915_BO_ALLOC_CPU_CLEAR | \ + I915_BO_ALLOC_USER) +#define I915_BO_READONLY BIT(5) +#define I915_TILING_QUIRK_BIT 6 /* unknown swizzling; do not release! */ /* * Is the object to be mapped as read-only to the GPU @@ -310,6 +328,12 @@ struct drm_i915_gem_object { bool dirty:1; } mm; + struct { + struct sg_table *cached_io_st; + struct i915_gem_object_page_iter get_io_page; + bool created:1; + } ttm; + /** Record of address bit 17 of each page at last unbind. */ unsigned long *bit_17; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 6444e097016d..086005c1c7ea 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -467,9 +467,8 @@ __i915_gem_object_get_sg(struct drm_i915_gem_object *obj, struct i915_gem_object_page_iter *iter, unsigned int n, unsigned int *offset, - bool allow_alloc) + bool allow_alloc, bool dma) { - const bool dma = iter == &obj->mm.get_dma_page; struct scatterlist *sg; unsigned int idx, count; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_region.c b/drivers/gpu/drm/i915/gem/i915_gem_region.c index f25e6646c5b7..d1f1840540dd 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_region.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_region.c @@ -18,11 +18,7 @@ void i915_gem_object_init_memory_region(struct drm_i915_gem_object *obj, mutex_lock(&mem->objects.lock); - if (obj->flags & I915_BO_ALLOC_VOLATILE) - list_add(&obj->mm.region_link, &mem->objects.purgeable); - else - list_add(&obj->mm.region_link, &mem->objects.list); - + list_add(&obj->mm.region_link, &mem->objects.list); mutex_unlock(&mem->objects.lock); } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c new file mode 100644 index 000000000000..bf33724bed5c --- /dev/null +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -0,0 +1,647 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include <drm/ttm/ttm_bo_driver.h> +#include <drm/ttm/ttm_placement.h> + +#include "i915_drv.h" +#include "intel_memory_region.h" +#include "intel_region_ttm.h" + +#include "gem/i915_gem_object.h" +#include "gem/i915_gem_region.h" +#include "gem/i915_gem_ttm.h" +#include "gem/i915_gem_mman.h" + +#define I915_PL_LMEM0 TTM_PL_PRIV +#define I915_PL_SYSTEM TTM_PL_SYSTEM +#define I915_PL_STOLEN TTM_PL_VRAM +#define I915_PL_GGTT TTM_PL_TT + +#define I915_TTM_PRIO_PURGE 0 +#define I915_TTM_PRIO_NO_PAGES 1 +#define I915_TTM_PRIO_HAS_PAGES 2 + +/** + * struct i915_ttm_tt - TTM page vector with additional private information + * @ttm: The base TTM page vector. + * @dev: The struct device used for dma mapping and unmapping. + * @cached_st: The cached scatter-gather table. + * + * Note that DMA may be going on right up to the point where the page- + * vector is unpopulated in delayed destroy. Hence keep the + * scatter-gather table mapped and cached up to that point. This is + * different from the cached gem object io scatter-gather table which + * doesn't have an associated dma mapping. + */ +struct i915_ttm_tt { + struct ttm_tt ttm; + struct device *dev; + struct sg_table *cached_st; +}; + +static const struct ttm_place lmem0_sys_placement_flags[] = { + { + .fpfn = 0, + .lpfn = 0, + .mem_type = I915_PL_LMEM0, + .flags = 0, + }, { + .fpfn = 0, + .lpfn = 0, + .mem_type = I915_PL_SYSTEM, + .flags = 0, + } +}; + +static struct ttm_placement i915_lmem0_placement = { + .num_placement = 1, + .placement = &lmem0_sys_placement_flags[0], + .num_busy_placement = 1, + .busy_placement = &lmem0_sys_placement_flags[0], +}; + +static struct ttm_placement i915_sys_placement = { + .num_placement = 1, + .placement = &lmem0_sys_placement_flags[1], + .num_busy_placement = 1, + .busy_placement = &lmem0_sys_placement_flags[1], +}; + +static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj); + +static struct ttm_tt *i915_ttm_tt_create(struct ttm_buffer_object *bo, + uint32_t page_flags) +{ + struct ttm_resource_manager *man = + ttm_manager_type(bo->bdev, bo->resource->mem_type); + struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + struct i915_ttm_tt *i915_tt; + int ret; + + i915_tt = kzalloc(sizeof(*i915_tt), GFP_KERNEL); + if (!i915_tt) + return NULL; + + if (obj->flags & I915_BO_ALLOC_CPU_CLEAR && + man->use_tt) + page_flags |= TTM_PAGE_FLAG_ZERO_ALLOC; + + ret = ttm_tt_init(&i915_tt->ttm, bo, page_flags, ttm_write_combined); + if (ret) { + kfree(i915_tt); + return NULL; + } + + i915_tt->dev = obj->base.dev->dev; + + return &i915_tt->ttm; +} + +static void i915_ttm_tt_unpopulate(struct ttm_device *bdev, struct ttm_tt *ttm) +{ + struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); + + if (i915_tt->cached_st) { + dma_unmap_sgtable(i915_tt->dev, i915_tt->cached_st, + DMA_BIDIRECTIONAL, 0); + sg_free_table(i915_tt->cached_st); + kfree(i915_tt->cached_st); + i915_tt->cached_st = NULL; + } + ttm_pool_free(&bdev->pool, ttm); +} + +static void i915_ttm_tt_destroy(struct ttm_device *bdev, struct ttm_tt *ttm) +{ + struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); + + ttm_tt_destroy_common(bdev, ttm); + kfree(i915_tt); +} + +static bool i915_ttm_eviction_valuable(struct ttm_buffer_object *bo, + const struct ttm_place *place) +{ + struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + + /* Will do for now. Our pinned objects are still on TTM's LRU lists */ + if (!i915_gem_object_evictable(obj)) + return false; + + /* This isn't valid with a buddy allocator */ + return ttm_bo_eviction_valuable(bo, place); +} + +static void i915_ttm_evict_flags(struct ttm_buffer_object *bo, + struct ttm_placement *placement) +{ + *placement = i915_sys_placement; +} + +static int i915_ttm_move_notify(struct ttm_buffer_object *bo) +{ + struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + int ret; + + ret = i915_gem_object_unbind(obj, I915_GEM_OBJECT_UNBIND_ACTIVE); + if (ret) + return ret; + + ret = __i915_gem_object_put_pages(obj); + if (ret) + return ret; + + return 0; +} + +static void i915_ttm_free_cached_io_st(struct drm_i915_gem_object *obj) +{ + struct radix_tree_iter iter; + void __rcu **slot; + + if (!obj->ttm.cached_io_st) + return; + + rcu_read_lock(); + radix_tree_for_each_slot(slot, &obj->ttm.get_io_page.radix, &iter, 0) + radix_tree_delete(&obj->ttm.get_io_page.radix, iter.index); + rcu_read_unlock(); + + sg_free_table(obj->ttm.cached_io_st); + kfree(obj->ttm.cached_io_st); + obj->ttm.cached_io_st = NULL; +} + +static void i915_ttm_purge(struct drm_i915_gem_object *obj) +{ + struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + struct ttm_operation_ctx ctx = { + .interruptible = true, + .no_wait_gpu = false, + }; + struct ttm_placement place = {}; + int ret; + + if (obj->mm.madv == __I915_MADV_PURGED) + return; + + /* TTM's purge interface. Note that we might be reentering. */ + ret = ttm_bo_validate(bo, &place, &ctx); + + if (!ret) { + i915_ttm_free_cached_io_st(obj); + obj->mm.madv = __I915_MADV_PURGED; + } +} + +static void i915_ttm_swap_notify(struct ttm_buffer_object *bo) +{ + struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + int ret = i915_ttm_move_notify(bo); + + GEM_WARN_ON(ret); + GEM_WARN_ON(obj->ttm.cached_io_st); + if (!ret && obj->mm.madv != I915_MADV_WILLNEED) + i915_ttm_purge(obj); +} + +static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo) +{ + struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + + if (likely(obj)) { + /* This releases all gem object bindings to the backend. */ + __i915_gem_free_object(obj); + } +} + +static struct intel_memory_region * +i915_ttm_region(struct ttm_device *bdev, int ttm_mem_type) +{ + struct drm_i915_private *i915 = container_of(bdev, typeof(*i915), bdev); + + /* There's some room for optimization here... */ + GEM_BUG_ON(ttm_mem_type != I915_PL_SYSTEM && + ttm_mem_type < I915_PL_LMEM0); + if (ttm_mem_type == I915_PL_SYSTEM) + return intel_memory_region_lookup(i915, INTEL_MEMORY_SYSTEM, + 0); + + return intel_memory_region_lookup(i915, INTEL_MEMORY_LOCAL, + ttm_mem_type - I915_PL_LMEM0); +} + +static struct sg_table *i915_ttm_tt_get_st(struct ttm_tt *ttm) +{ + struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); + struct scatterlist *sg; + struct sg_table *st; + int ret; + + if (i915_tt->cached_st) + return i915_tt->cached_st; + + st = kzalloc(sizeof(*st), GFP_KERNEL); + if (!st) + return ERR_PTR(-ENOMEM); + + sg = __sg_alloc_table_from_pages + (st, ttm->pages, ttm->num_pages, 0, + (unsigned long)ttm->num_pages << PAGE_SHIFT, + i915_sg_segment_size(), NULL, 0, GFP_KERNEL); + if (IS_ERR(sg)) { + kfree(st); + return ERR_CAST(sg); + } + + ret = dma_map_sgtable(i915_tt->dev, st, DMA_BIDIRECTIONAL, 0); + if (ret) { + sg_free_table(st); + kfree(st); + return ERR_PTR(ret); + } + + i915_tt->cached_st = st; + return st; +} + +static struct sg_table * +i915_ttm_resource_get_st(struct drm_i915_gem_object *obj, + struct ttm_resource *res) +{ + struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + struct ttm_resource_manager *man = + ttm_manager_type(bo->bdev, res->mem_type); + + if (man->use_tt) + return i915_ttm_tt_get_st(bo->ttm); + + return intel_region_ttm_node_to_st(obj->mm.region, res); +} + +static int i915_ttm_move(struct ttm_buffer_object *bo, bool evict, + struct ttm_operation_ctx *ctx, + struct ttm_resource *dst_mem, + struct ttm_place *hop) +{ + struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + struct ttm_resource_manager *dst_man = + ttm_manager_type(bo->bdev, dst_mem->mem_type); + struct ttm_resource_manager *src_man = + ttm_manager_type(bo->bdev, bo->resource->mem_type); + struct intel_memory_region *dst_reg, *src_reg; + union { + struct ttm_kmap_iter_tt tt; + struct ttm_kmap_iter_iomap io; + } _dst_iter, _src_iter; + struct ttm_kmap_iter *dst_iter, *src_iter; + struct sg_table *dst_st; + int ret; + + dst_reg = i915_ttm_region(bo->bdev, dst_mem->mem_type); + src_reg = i915_ttm_region(bo->bdev, bo->resource->mem_type); + GEM_BUG_ON(!dst_reg || !src_reg); + + /* Sync for now. We could do the actual copy async. */ + ret = ttm_bo_wait_ctx(bo, ctx); + if (ret) + return ret; + + ret = i915_ttm_move_notify(bo); + if (ret) + return ret; + + if (obj->mm.madv != I915_MADV_WILLNEED) { + i915_ttm_purge(obj); + ttm_resource_free(bo, &dst_mem); + return 0; + } + + /* Populate ttm with pages if needed. Typically system memory. */ + if (bo->ttm && (dst_man->use_tt || + (bo->ttm->page_flags & TTM_PAGE_FLAG_SWAPPED))) { + ret = ttm_tt_populate(bo->bdev, bo->ttm, ctx); + if (ret) + return ret; + } + + dst_st = i915_ttm_resource_get_st(obj, dst_mem); + if (IS_ERR(dst_st)) + return PTR_ERR(dst_st); + + /* If we start mapping GGTT, we can no longer use man::use_tt here. */ + dst_iter = dst_man->use_tt ? + ttm_kmap_iter_tt_init(&_dst_iter.tt, bo->ttm) : + ttm_kmap_iter_iomap_init(&_dst_iter.io, &dst_reg->iomap, + dst_st, dst_reg->region.start); + + src_iter = src_man->use_tt ? + ttm_kmap_iter_tt_init(&_src_iter.tt, bo->ttm) : + ttm_kmap_iter_iomap_init(&_src_iter.io, &src_reg->iomap, + obj->ttm.cached_io_st, + src_reg->region.start); + + ttm_move_memcpy(bo, dst_mem->num_pages, dst_iter, src_iter); + ttm_bo_move_sync_cleanup(bo, dst_mem); + i915_ttm_free_cached_io_st(obj); + + if (!dst_man->use_tt) { + obj->ttm.cached_io_st = dst_st; + obj->ttm.get_io_page.sg_pos = dst_st->sgl; + obj->ttm.get_io_page.sg_idx = 0; + } + + return 0; +} + +static int i915_ttm_io_mem_reserve(struct ttm_device *bdev, struct ttm_resource *mem) +{ + if (mem->mem_type < I915_PL_LMEM0) + return 0; + + mem->bus.caching = ttm_write_combined; + mem->bus.is_iomem = true; + + return 0; +} + +static unsigned long i915_ttm_io_mem_pfn(struct ttm_buffer_object *bo, + unsigned long page_offset) +{ + struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + unsigned long base = obj->mm.region->iomap.base - obj->mm.region->region.start; + struct scatterlist *sg; + unsigned int ofs; + + GEM_WARN_ON(bo->ttm); + + sg = __i915_gem_object_get_sg(obj, &obj->ttm.get_io_page, page_offset, &ofs, true, true); + + return ((base + sg_dma_address(sg)) >> PAGE_SHIFT) + ofs; +} + +static struct ttm_device_funcs i915_ttm_bo_driver = { + .ttm_tt_create = i915_ttm_tt_create, + .ttm_tt_unpopulate = i915_ttm_tt_unpopulate, + .ttm_tt_destroy = i915_ttm_tt_destroy, + .eviction_valuable = i915_ttm_eviction_valuable, + .evict_flags = i915_ttm_evict_flags, + .move = i915_ttm_move, + .swap_notify = i915_ttm_swap_notify, + .delete_mem_notify = i915_ttm_delete_mem_notify, + .io_mem_reserve = i915_ttm_io_mem_reserve, + .io_mem_pfn = i915_ttm_io_mem_pfn, +}; + +/** + * i915_ttm_driver - Return a pointer to the TTM device funcs + * + * Return: Pointer to statically allocated TTM device funcs. + */ +struct ttm_device_funcs *i915_ttm_driver(void) +{ + return &i915_ttm_bo_driver; +} + +static int i915_ttm_get_pages(struct drm_i915_gem_object *obj) +{ + struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + struct ttm_operation_ctx ctx = { + .interruptible = true, + .no_wait_gpu = false, + }; + struct sg_table *st; + int ret; + + /* Move to the requested placement. */ + ret = ttm_bo_validate(bo, &i915_lmem0_placement, &ctx); + if (ret) + return ret == -ENOSPC ? -ENXIO : ret; + + /* Object either has a page vector or is an iomem object */ + st = bo->ttm ? i915_ttm_tt_get_st(bo->ttm) : obj->ttm.cached_io_st; + if (IS_ERR(st)) + return PTR_ERR(st); + + __i915_gem_object_set_pages(obj, st, i915_sg_dma_sizes(st->sgl)); + + i915_ttm_adjust_lru(obj); + + return ret; +} + +static void i915_ttm_put_pages(struct drm_i915_gem_object *obj, + struct sg_table *st) +{ + /* + * We're currently not called from a shrinker, so put_pages() + * typically means the object is about to destroyed, or called + * from move_notify(). So just avoid doing much for now. + * If the object is not destroyed next, The TTM eviction logic + * and shrinkers will move it out if needed. + */ + + i915_ttm_adjust_lru(obj); +} + +static void i915_ttm_adjust_lru(struct drm_i915_gem_object *obj) +{ + struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + + /* + * Don't manipulate the TTM LRUs while in TTM bo destruction. + * We're called through i915_ttm_delete_mem_notify(). + */ + if (!kref_read(&bo->kref)) + return; + + /* + * Put on the correct LRU list depending on the MADV status + */ + spin_lock(&bo->bdev->lru_lock); + if (obj->mm.madv != I915_MADV_WILLNEED) { + bo->priority = I915_TTM_PRIO_PURGE; + } else if (!i915_gem_object_has_pages(obj)) { + if (bo->priority < I915_TTM_PRIO_HAS_PAGES) + bo->priority = I915_TTM_PRIO_HAS_PAGES; + } else { + if (bo->priority > I915_TTM_PRIO_NO_PAGES) + bo->priority = I915_TTM_PRIO_NO_PAGES; + } + + ttm_bo_move_to_lru_tail(bo, bo->resource, NULL); + spin_unlock(&bo->bdev->lru_lock); +} + +/* + * TTM-backed gem object destruction requires some clarification. + * Basically we have two possibilities here. We can either rely on the + * i915 delayed destruction and put the TTM object when the object + * is idle. This would be detected by TTM which would bypass the + * TTM delayed destroy handling. The other approach is to put the TTM + * object early and rely on the TTM destroyed handling, and then free + * the leftover parts of the GEM object once TTM's destroyed list handling is + * complete. For now, we rely on the latter for two reasons: + * a) TTM can evict an object even when it's on the delayed destroy list, + * which in theory allows for complete eviction. + * b) There is work going on in TTM to allow freeing an object even when + * it's not idle, and using the TTM destroyed list handling could help us + * benefit from that. + */ +static void i915_ttm_delayed_free(struct drm_i915_gem_object *obj) +{ + if (obj->ttm.created) { + ttm_bo_put(i915_gem_to_ttm(obj)); + } else { + __i915_gem_free_object(obj); + call_rcu(&obj->rcu, __i915_gem_free_object_rcu); + } +} + +static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) +{ + struct vm_area_struct *area = vmf->vma; + struct drm_i915_gem_object *obj = + i915_ttm_to_gem(area->vm_private_data); + + /* Sanity check that we allow writing into this object */ + if (unlikely(i915_gem_object_is_readonly(obj) && + area->vm_flags & VM_WRITE)) + return VM_FAULT_SIGBUS; + + return ttm_bo_vm_fault(vmf); +} + +static int +vm_access_ttm(struct vm_area_struct *area, unsigned long addr, + void *buf, int len, int write) +{ + struct drm_i915_gem_object *obj = + i915_ttm_to_gem(area->vm_private_data); + + if (i915_gem_object_is_readonly(obj) && write) + return -EACCES; + + return ttm_bo_vm_access(area, addr, buf, len, write); +} + +static void ttm_vm_open(struct vm_area_struct *vma) +{ + struct drm_i915_gem_object *obj = + i915_ttm_to_gem(vma->vm_private_data); + + GEM_BUG_ON(!obj); + i915_gem_object_get(obj); +} + +static void ttm_vm_close(struct vm_area_struct *vma) +{ + struct drm_i915_gem_object *obj = + i915_ttm_to_gem(vma->vm_private_data); + + GEM_BUG_ON(!obj); + i915_gem_object_put(obj); +} + +static const struct vm_operations_struct vm_ops_ttm = { + .fault = vm_fault_ttm, + .access = vm_access_ttm, + .open = ttm_vm_open, + .close = ttm_vm_close, +}; + +static u64 i915_ttm_mmap_offset(struct drm_i915_gem_object *obj) +{ + /* The ttm_bo must be allocated with I915_BO_ALLOC_USER */ + GEM_BUG_ON(!drm_mm_node_allocated(&obj->base.vma_node.vm_node)); + + return drm_vma_node_offset_addr(&obj->base.vma_node); +} + +const struct drm_i915_gem_object_ops i915_gem_ttm_obj_ops = { + .name = "i915_gem_object_ttm", + .flags = I915_GEM_OBJECT_HAS_IOMEM, + + .get_pages = i915_ttm_get_pages, + .put_pages = i915_ttm_put_pages, + .truncate = i915_ttm_purge, + .adjust_lru = i915_ttm_adjust_lru, + .delayed_free = i915_ttm_delayed_free, + .mmap_offset = i915_ttm_mmap_offset, + .mmap_ops = &vm_ops_ttm, +}; + +void i915_ttm_bo_destroy(struct ttm_buffer_object *bo) +{ + struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + + i915_gem_object_release_memory_region(obj); + mutex_destroy(&obj->ttm.get_io_page.lock); + if (obj->ttm.created) + call_rcu(&obj->rcu, __i915_gem_free_object_rcu); +} + +/** + * __i915_gem_ttm_object_init - Initialize a ttm-backed i915 gem object + * @mem: The initial memory region for the object. + * @obj: The gem object. + * @size: Object size in bytes. + * @flags: gem object flags. + * + * Return: 0 on success, negative error code on failure. + */ +int __i915_gem_ttm_object_init(struct intel_memory_region *mem, + struct drm_i915_gem_object *obj, + resource_size_t size, + unsigned int flags) +{ + static struct lock_class_key lock_class; + struct drm_i915_private *i915 = mem->i915; + enum ttm_bo_type bo_type; + size_t alignment = 0; + int ret; + + /* Adjust alignment to GPU- and CPU huge page sizes. */ + + if (mem->is_range_manager) { + if (size >= SZ_1G) + alignment = SZ_1G >> PAGE_SHIFT; + else if (size >= SZ_2M) + alignment = SZ_2M >> PAGE_SHIFT; + else if (size >= SZ_64K) + alignment = SZ_64K >> PAGE_SHIFT; + } + + drm_gem_private_object_init(&i915->drm, &obj->base, size); + i915_gem_object_init(obj, &i915_gem_ttm_obj_ops, &lock_class, flags); + i915_gem_object_init_memory_region(obj, mem); + i915_gem_object_make_unshrinkable(obj); + obj->read_domains = I915_GEM_DOMAIN_WC | I915_GEM_DOMAIN_GTT; + i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE); + INIT_RADIX_TREE(&obj->ttm.get_io_page.radix, GFP_KERNEL | __GFP_NOWARN); + mutex_init(&obj->ttm.get_io_page.lock); + + bo_type = (obj->flags & I915_BO_ALLOC_USER) ? ttm_bo_type_device : + ttm_bo_type_kernel; + + /* + * If this function fails, it will call the destructor, but + * our caller still owns the object. So no freeing in the + * destructor until obj->ttm.created is true. + * Similarly, in delayed_destroy, we can't call ttm_bo_put() + * until successful initialization. + */ + obj->base.vma_node.driver_private = i915_gem_to_ttm(obj); + ret = ttm_bo_init(&i915->bdev, i915_gem_to_ttm(obj), size, + bo_type, &i915_sys_placement, alignment, + true, NULL, NULL, i915_ttm_bo_destroy); + + if (!ret) + obj->ttm.created = true; + + /* i915 wants -ENXIO when out of memory region space. */ + return (ret == -ENOSPC) ? -ENXIO : ret; +} diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.h b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h new file mode 100644 index 000000000000..b8d3dcbb50df --- /dev/null +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ +#ifndef _I915_GEM_TTM_H_ +#define _I915_GEM_TTM_H_ + +#include "gem/i915_gem_object_types.h" + +/** + * i915_gem_to_ttm - Convert a struct drm_i915_gem_object to a + * struct ttm_buffer_object. + * @obj: Pointer to the gem object. + * + * Return: Pointer to the embedded struct ttm_buffer_object. + */ +static inline struct ttm_buffer_object * +i915_gem_to_ttm(struct drm_i915_gem_object *obj) +{ + return &obj->__do_not_access; +} + +/* + * i915 ttm gem object destructor. Internal use only. + */ +void i915_ttm_bo_destroy(struct ttm_buffer_object *bo); + +/** + * i915_ttm_to_gem - Convert a struct ttm_buffer_object to an embedding + * struct drm_i915_gem_object. + * + * Return: Pointer to the embedding struct ttm_buffer_object, or NULL + * if the object was not an i915 ttm object. + */ +static inline struct drm_i915_gem_object * +i915_ttm_to_gem(struct ttm_buffer_object *bo) +{ + if (GEM_WARN_ON(bo->destroy != i915_ttm_bo_destroy)) + return NULL; + + return container_of(bo, struct drm_i915_gem_object, __do_not_access); +} + +int __i915_gem_ttm_object_init(struct intel_memory_region *mem, + struct drm_i915_gem_object *obj, + resource_size_t size, + unsigned int flags); +#endif diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index 5575172c66f5..bc32622a8c5f 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -578,16 +578,17 @@ static bool assert_mmap_offset(struct drm_i915_private *i915, int expected) { struct drm_i915_gem_object *obj; - struct i915_mmap_offset *mmo; + u64 offset; + int ret; obj = i915_gem_object_create_internal(i915, size); if (IS_ERR(obj)) - return false; + return expected && expected == PTR_ERR(obj); - mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL); + ret = __assign_mmap_offset(obj, I915_MMAP_TYPE_GTT, &offset, NULL); i915_gem_object_put(obj); - return PTR_ERR_OR_ZERO(mmo) == expected; + return ret == expected; } static void disable_retire_worker(struct drm_i915_private *i915) @@ -622,8 +623,8 @@ static int igt_mmap_offset_exhaustion(void *arg) struct drm_mm *mm = &i915->drm.vma_offset_manager->vm_addr_space_mm; struct drm_i915_gem_object *obj; struct drm_mm_node *hole, *next; - struct i915_mmap_offset *mmo; int loop, err = 0; + u64 offset; /* Disable background reaper */ disable_retire_worker(i915); @@ -684,13 +685,13 @@ static int igt_mmap_offset_exhaustion(void *arg) obj = i915_gem_object_create_internal(i915, PAGE_SIZE); if (IS_ERR(obj)) { err = PTR_ERR(obj); + pr_err("Unable to create object for reclaimed hole\n"); goto out; } - mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL); - if (IS_ERR(mmo)) { + err = __assign_mmap_offset(obj, I915_MMAP_TYPE_GTT, &offset, NULL); + if (err) { pr_err("Unable to insert object into reclaimed hole\n"); - err = PTR_ERR(mmo); goto err_obj; } @@ -865,10 +866,10 @@ static int __igt_mmap(struct drm_i915_private *i915, struct drm_i915_gem_object *obj, enum i915_mmap_type type) { - struct i915_mmap_offset *mmo; struct vm_area_struct *area; unsigned long addr; int err, i; + u64 offset; if (!can_mmap(obj, type)) return 0; @@ -879,11 +880,11 @@ static int __igt_mmap(struct drm_i915_private *i915, if (err) return err; - mmo = mmap_offset_attach(obj, type, NULL); - if (IS_ERR(mmo)) - return PTR_ERR(mmo); + err = __assign_mmap_offset(obj, type, &offset, NULL); + if (err) + return err; - addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED); + addr = igt_mmap_offset(i915, offset, obj->base.size, PROT_WRITE, MAP_SHARED); if (IS_ERR_VALUE(addr)) return addr; @@ -897,13 +898,6 @@ static int __igt_mmap(struct drm_i915_private *i915, goto out_unmap; } - if (area->vm_private_data != mmo) { - pr_err("%s: vm_area_struct did not point back to our mmap_offset object!\n", - obj->mm.region->name); - err = -EINVAL; - goto out_unmap; - } - for (i = 0; i < obj->base.size / sizeof(u32); i++) { u32 __user *ux = u64_to_user_ptr((u64)(addr + i * sizeof(*ux))); u32 x; @@ -961,7 +955,7 @@ static int igt_mmap(void *arg) struct drm_i915_gem_object *obj; int err; - obj = i915_gem_object_create_region(mr, sizes[i], 0); + obj = i915_gem_object_create_region(mr, sizes[i], I915_BO_ALLOC_USER); if (obj == ERR_PTR(-ENODEV)) continue; @@ -1004,12 +998,12 @@ static int __igt_mmap_access(struct drm_i915_private *i915, struct drm_i915_gem_object *obj, enum i915_mmap_type type) { - struct i915_mmap_offset *mmo; unsigned long __user *ptr; unsigned long A, B; unsigned long x, y; unsigned long addr; int err; + u64 offset; memset(&A, 0xAA, sizeof(A)); memset(&B, 0xBB, sizeof(B)); @@ -1017,11 +1011,11 @@ static int __igt_mmap_access(struct drm_i915_private *i915, if (!can_mmap(obj, type) || !can_access(obj)) return 0; - mmo = mmap_offset_attach(obj, type, NULL); - if (IS_ERR(mmo)) - return PTR_ERR(mmo); + err = __assign_mmap_offset(obj, type, &offset, NULL); + if (err) + return err; - addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED); + addr = igt_mmap_offset(i915, offset, obj->base.size, PROT_WRITE, MAP_SHARED); if (IS_ERR_VALUE(addr)) return addr; ptr = (unsigned long __user *)addr; @@ -1081,7 +1075,7 @@ static int igt_mmap_access(void *arg) struct drm_i915_gem_object *obj; int err; - obj = i915_gem_object_create_region(mr, PAGE_SIZE, 0); + obj = i915_gem_object_create_region(mr, PAGE_SIZE, I915_BO_ALLOC_USER); if (obj == ERR_PTR(-ENODEV)) continue; @@ -1111,11 +1105,11 @@ static int __igt_mmap_gpu(struct drm_i915_private *i915, enum i915_mmap_type type) { struct intel_engine_cs *engine; - struct i915_mmap_offset *mmo; unsigned long addr; u32 __user *ux; u32 bbe; int err; + u64 offset; /* * Verify that the mmap access into the backing store aligns with @@ -1132,11 +1126,11 @@ static int __igt_mmap_gpu(struct drm_i915_private *i915, if (err) return err; - mmo = mmap_offset_attach(obj, type, NULL); - if (IS_ERR(mmo)) - return PTR_ERR(mmo); + err = __assign_mmap_offset(obj, type, &offset, NULL); + if (err) + return err; - addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED); + addr = igt_mmap_offset(i915, offset, obj->base.size, PROT_WRITE, MAP_SHARED); if (IS_ERR_VALUE(addr)) return addr; @@ -1226,7 +1220,7 @@ static int igt_mmap_gpu(void *arg) struct drm_i915_gem_object *obj; int err; - obj = i915_gem_object_create_region(mr, PAGE_SIZE, 0); + obj = i915_gem_object_create_region(mr, PAGE_SIZE, I915_BO_ALLOC_USER); if (obj == ERR_PTR(-ENODEV)) continue; @@ -1303,18 +1297,18 @@ static int __igt_mmap_revoke(struct drm_i915_private *i915, struct drm_i915_gem_object *obj, enum i915_mmap_type type) { - struct i915_mmap_offset *mmo; unsigned long addr; int err; + u64 offset; if (!can_mmap(obj, type)) return 0; - mmo = mmap_offset_attach(obj, type, NULL); - if (IS_ERR(mmo)) - return PTR_ERR(mmo); + err = __assign_mmap_offset(obj, type, &offset, NULL); + if (err) + return err; - addr = igt_mmap_node(i915, &mmo->vma_node, 0, PROT_WRITE, MAP_SHARED); + addr = igt_mmap_offset(i915, offset, obj->base.size, PROT_WRITE, MAP_SHARED); if (IS_ERR_VALUE(addr)) return addr; @@ -1350,10 +1344,20 @@ static int __igt_mmap_revoke(struct drm_i915_private *i915, } } - err = check_absent(addr, obj->base.size); - if (err) { - pr_err("%s: was not absent\n", obj->mm.region->name); - goto out_unmap; + if (!obj->ops->mmap_ops) { + err = check_absent(addr, obj->base.size); + if (err) { + pr_err("%s: was not absent\n", obj->mm.region->name); + goto out_unmap; + } + } else { + /* ttm allows access to evicted regions by design */ + + err = check_present(addr, obj->base.size); + if (err) { + pr_err("%s: was not present\n", obj->mm.region->name); + goto out_unmap; + } } out_unmap: @@ -1371,7 +1375,7 @@ static int igt_mmap_revoke(void *arg) struct drm_i915_gem_object *obj; int err; - obj = i915_gem_object_create_region(mr, PAGE_SIZE, 0); + obj = i915_gem_object_create_region(mr, PAGE_SIZE, I915_BO_ALLOC_USER); if (obj == ERR_PTR(-ENODEV)) continue; diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c index f7366b054f8e..4ae1f717a94c 100644 --- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c +++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c @@ -9,6 +9,7 @@ #include "intel_region_ttm.h" #include "gem/i915_gem_lmem.h" #include "gem/i915_gem_region.h" +#include "gem/i915_gem_ttm.h" #include "intel_region_lmem.h" static int init_fake_lmem_bar(struct intel_memory_region *mem) @@ -107,7 +108,7 @@ out_no_io: static const struct intel_memory_region_ops intel_region_lmem_ops = { .init = region_lmem_init, .release = region_lmem_release, - .init_object = __i915_gem_lmem_object_init, + .init_object = __i915_gem_ttm_object_init, }; struct intel_memory_region * diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 73de45472f60..30d8cd8c69b1 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -561,7 +561,7 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv) if (ret) goto err_perf; - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "inteldrmfb"); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, dev_priv->drm.driver); if (ret) goto err_ggtt; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 02f68f32322f..fd9db6de5113 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1138,6 +1138,8 @@ struct drm_i915_private { /* For i915gm/i945gm vblank irq workaround */ u8 vblank_enabled; + bool irq_enabled; + /* perform PHY state sanity checks? */ bool chv_phy_assert[2]; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 589388dec48a..6a0a3f0e36e1 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1005,8 +1005,11 @@ i915_gem_madvise_ioctl(struct drm_device *dev, void *data, } } - if (obj->mm.madv != __I915_MADV_PURGED) + if (obj->mm.madv != __I915_MADV_PURGED) { obj->mm.madv = args->madv; + if (obj->ops->adjust_lru) + obj->ops->adjust_lru(obj); + } if (i915_gem_object_has_pages(obj)) { unsigned long flags; diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 47b484976919..1d4c683c9de9 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -4487,14 +4487,14 @@ int intel_irq_install(struct drm_i915_private *dev_priv) */ dev_priv->runtime_pm.irqs_enabled = true; - dev_priv->drm.irq_enabled = true; + dev_priv->irq_enabled = true; intel_irq_reset(dev_priv); ret = request_irq(irq, intel_irq_handler(dev_priv), IRQF_SHARED, DRIVER_NAME, dev_priv); if (ret < 0) { - dev_priv->drm.irq_enabled = false; + dev_priv->irq_enabled = false; return ret; } @@ -4520,10 +4520,10 @@ void intel_irq_uninstall(struct drm_i915_private *dev_priv) * intel_modeset_driver_remove() calling us out of sequence. * Would be nice if it didn't do that... */ - if (!dev_priv->drm.irq_enabled) + if (!dev_priv->irq_enabled) return; - dev_priv->drm.irq_enabled = false; + dev_priv->irq_enabled = false; intel_irq_reset(dev_priv); diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c index e6024eb7cca4..12fb5423fd5e 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.c +++ b/drivers/gpu/drm/i915/intel_memory_region.c @@ -149,7 +149,6 @@ intel_memory_region_create(struct drm_i915_private *i915, mutex_init(&mem->objects.lock); INIT_LIST_HEAD(&mem->objects.list); - INIT_LIST_HEAD(&mem->objects.purgeable); INIT_LIST_HEAD(&mem->reserved); mutex_init(&mem->mm_lock); diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h index 1f7dac63abb7..c7e635d62e1a 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.h +++ b/drivers/gpu/drm/i915/intel_memory_region.h @@ -101,7 +101,6 @@ struct intel_memory_region { struct { struct mutex lock; /* Protects access to objects */ struct list_head list; - struct list_head purgeable; } objects; size_t chunk_size; diff --git a/drivers/gpu/drm/i915/intel_region_ttm.c b/drivers/gpu/drm/i915/intel_region_ttm.c index 82a6727ede46..27fe0668d094 100644 --- a/drivers/gpu/drm/i915/intel_region_ttm.c +++ b/drivers/gpu/drm/i915/intel_region_ttm.c @@ -11,6 +11,7 @@ #include "intel_region_ttm.h" +#include "gem/i915_gem_ttm.h" /* For the funcs/ops export only */ /** * DOC: TTM support structure * @@ -20,9 +21,6 @@ * i915 GEM regions to TTM memory types and resource managers. */ -/* A Zero-initialized driver for now. We don't have a TTM backend yet. */ -static struct ttm_device_funcs i915_ttm_bo_driver; - /** * intel_region_ttm_device_init - Initialize a TTM device * @dev_priv: Pointer to an i915 device private structure. @@ -33,7 +31,7 @@ int intel_region_ttm_device_init(struct drm_i915_private *dev_priv) { struct drm_device *drm = &dev_priv->drm; - return ttm_device_init(&dev_priv->bdev, &i915_ttm_bo_driver, + return ttm_device_init(&dev_priv->bdev, i915_ttm_driver(), drm->dev, drm->anon_inode->i_mapping, drm->vma_offset_manager, false, false); } @@ -177,6 +175,7 @@ struct sg_table *intel_region_ttm_node_to_st(struct intel_memory_region *mem, mem->region.start); } +#ifdef CONFIG_DRM_I915_SELFTEST /** * intel_region_ttm_node_alloc - Allocate memory resources from a region * @mem: The memory region, @@ -224,3 +223,4 @@ intel_region_ttm_node_alloc(struct intel_memory_region *mem, ret = -ENXIO; return ret ? ERR_PTR(ret) : res; } +#endif diff --git a/drivers/gpu/drm/i915/intel_region_ttm.h b/drivers/gpu/drm/i915/intel_region_ttm.h index 11b0574ab791..e8cf830fda6f 100644 --- a/drivers/gpu/drm/i915/intel_region_ttm.h +++ b/drivers/gpu/drm/i915/intel_region_ttm.h @@ -12,6 +12,7 @@ struct drm_i915_private; struct intel_memory_region; struct ttm_resource; +struct ttm_device_funcs; int intel_region_ttm_device_init(struct drm_i915_private *dev_priv); @@ -24,11 +25,15 @@ void intel_region_ttm_fini(struct intel_memory_region *mem); struct sg_table *intel_region_ttm_node_to_st(struct intel_memory_region *mem, struct ttm_resource *res); +void intel_region_ttm_node_free(struct intel_memory_region *mem, + struct ttm_resource *node); + +struct ttm_device_funcs *i915_ttm_driver(void); + +#ifdef CONFIG_DRM_I915_SELFTEST struct ttm_resource * intel_region_ttm_node_alloc(struct intel_memory_region *mem, resource_size_t size, unsigned int flags); - -void intel_region_ttm_node_free(struct intel_memory_region *mem, - struct ttm_resource *node); +#endif #endif /* _INTEL_REGION_TTM_H_ */ diff --git a/drivers/gpu/drm/i915/selftests/igt_mmap.c b/drivers/gpu/drm/i915/selftests/igt_mmap.c index 583a4ff8b8c9..e920a461bd36 100644 --- a/drivers/gpu/drm/i915/selftests/igt_mmap.c +++ b/drivers/gpu/drm/i915/selftests/igt_mmap.c @@ -9,15 +9,28 @@ #include "i915_drv.h" #include "igt_mmap.h" -unsigned long igt_mmap_node(struct drm_i915_private *i915, - struct drm_vma_offset_node *node, - unsigned long addr, - unsigned long prot, - unsigned long flags) +unsigned long igt_mmap_offset(struct drm_i915_private *i915, + u64 offset, + unsigned long size, + unsigned long prot, + unsigned long flags) { + struct drm_vma_offset_node *node; struct file *file; + unsigned long addr; int err; + /* no need to refcount, we own this object */ + drm_vma_offset_lock_lookup(i915->drm.vma_offset_manager); + node = drm_vma_offset_exact_lookup_locked(i915->drm.vma_offset_manager, + offset / PAGE_SIZE, size / PAGE_SIZE); + drm_vma_offset_unlock_lookup(i915->drm.vma_offset_manager); + + if (GEM_WARN_ON(!node)) { + pr_info("Failed to lookup %llx\n", offset); + return -ENOENT; + } + /* Pretend to open("/dev/dri/card0") */ file = mock_drm_getfile(i915->drm.primary, O_RDWR); if (IS_ERR(file)) @@ -29,7 +42,7 @@ unsigned long igt_mmap_node(struct drm_i915_private *i915, goto out_file; } - addr = vm_mmap(file, addr, drm_vma_node_size(node) << PAGE_SHIFT, + addr = vm_mmap(file, 0, drm_vma_node_size(node) << PAGE_SHIFT, prot, flags, drm_vma_node_offset_addr(node)); drm_vma_node_revoke(node, file->private_data); diff --git a/drivers/gpu/drm/i915/selftests/igt_mmap.h b/drivers/gpu/drm/i915/selftests/igt_mmap.h index 6e716cb59d7e..acbe34d81a6d 100644 --- a/drivers/gpu/drm/i915/selftests/igt_mmap.h +++ b/drivers/gpu/drm/i915/selftests/igt_mmap.h @@ -7,13 +7,15 @@ #ifndef IGT_MMAP_H #define IGT_MMAP_H +#include <linux/types.h> + struct drm_i915_private; struct drm_vma_offset_node; -unsigned long igt_mmap_node(struct drm_i915_private *i915, - struct drm_vma_offset_node *node, - unsigned long addr, - unsigned long prot, - unsigned long flags); +unsigned long igt_mmap_offset(struct drm_i915_private *i915, + u64 offset, + unsigned long size, + unsigned long prot, + unsigned long flags); #endif /* IGT_MMAP_H */ diff --git a/drivers/gpu/drm/imx/dcss/dcss-kms.c b/drivers/gpu/drm/imx/dcss/dcss-kms.c index 37ae68a7fba5..917834b1c80e 100644 --- a/drivers/gpu/drm/imx/dcss/dcss-kms.c +++ b/drivers/gpu/drm/imx/dcss/dcss-kms.c @@ -133,8 +133,6 @@ struct dcss_kms_dev *dcss_kms_attach(struct dcss_dev *dcss) if (ret) goto cleanup_mode_config; - drm->irq_enabled = true; - ret = dcss_kms_bridge_connector_init(kms); if (ret) goto cleanup_mode_config; @@ -178,7 +176,6 @@ void dcss_kms_detach(struct dcss_kms_dev *kms) drm_kms_helper_poll_fini(drm); drm_atomic_helper_shutdown(drm); drm_crtc_vblank_off(&kms->crtc.base); - drm->irq_enabled = false; drm_mode_config_cleanup(drm); dcss_crtc_deinit(&kms->crtc, drm); drm->dev_private = NULL; diff --git a/drivers/gpu/drm/imx/dcss/dcss-plane.c b/drivers/gpu/drm/imx/dcss/dcss-plane.c index 044d3bdf313c..ac45d54acd4e 100644 --- a/drivers/gpu/drm/imx/dcss/dcss-plane.c +++ b/drivers/gpu/drm/imx/dcss/dcss-plane.c @@ -361,7 +361,6 @@ static void dcss_plane_atomic_disable(struct drm_plane *plane, } static const struct drm_plane_helper_funcs dcss_plane_helper_funcs = { - .prepare_fb = drm_gem_plane_helper_prepare_fb, .atomic_check = dcss_plane_atomic_check, .atomic_update = dcss_plane_atomic_update, .atomic_disable = dcss_plane_atomic_disable, diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index 76819a8ac37f..9558e9e1b431 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -208,17 +208,6 @@ static int imx_drm_bind(struct device *dev) return PTR_ERR(drm); /* - * enable drm irq mode. - * - with irq_enabled = true, we can use the vblank feature. - * - * P.S. note that we wouldn't use drm irq handler but - * just specific driver own one instead because - * drm framework supports only one irq handler and - * drivers can well take care of their interrupts - */ - drm->irq_enabled = true; - - /* * set max width and height as default value(4096x4096). * this value would be used to check framebuffer size limitation * at drm_mode_addfb(). diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index 8710f55d2579..ef114b6aa691 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -772,7 +772,6 @@ static void ipu_plane_atomic_update(struct drm_plane *plane, } static const struct drm_plane_helper_funcs ipu_plane_helper_funcs = { - .prepare_fb = drm_gem_plane_helper_prepare_fb, .atomic_check = ipu_plane_atomic_check, .atomic_disable = ipu_plane_atomic_disable, .atomic_update = ipu_plane_atomic_update, diff --git a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c index 5244f4763477..c296472164d9 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c @@ -830,7 +830,6 @@ static const struct drm_plane_helper_funcs ingenic_drm_plane_helper_funcs = { .atomic_update = ingenic_drm_plane_atomic_update, .atomic_check = ingenic_drm_plane_atomic_check, .atomic_disable = ingenic_drm_plane_atomic_disable, - .prepare_fb = drm_gem_plane_helper_prepare_fb, }; static const struct drm_crtc_helper_funcs ingenic_drm_crtc_helper_funcs = { diff --git a/drivers/gpu/drm/ingenic/ingenic-ipu.c b/drivers/gpu/drm/ingenic/ingenic-ipu.c index 61b6d9fdbba1..aeb8a757d213 100644 --- a/drivers/gpu/drm/ingenic/ingenic-ipu.c +++ b/drivers/gpu/drm/ingenic/ingenic-ipu.c @@ -625,7 +625,6 @@ static const struct drm_plane_helper_funcs ingenic_ipu_plane_helper_funcs = { .atomic_update = ingenic_ipu_plane_atomic_update, .atomic_check = ingenic_ipu_plane_atomic_check, .atomic_disable = ingenic_ipu_plane_atomic_disable, - .prepare_fb = drm_gem_plane_helper_prepare_fb, }; static int diff --git a/drivers/gpu/drm/lima/lima_sched.c b/drivers/gpu/drm/lima/lima_sched.c index ecf3267334ff..dba8329937a3 100644 --- a/drivers/gpu/drm/lima/lima_sched.c +++ b/drivers/gpu/drm/lima/lima_sched.c @@ -508,7 +508,8 @@ int lima_sched_pipe_init(struct lima_sched_pipe *pipe, const char *name) INIT_WORK(&pipe->recover_work, lima_sched_recover_work); return drm_sched_init(&pipe->base, &lima_sched_ops, 1, - lima_job_hang_limit, msecs_to_jiffies(timeout), + lima_job_hang_limit, + msecs_to_jiffies(timeout), NULL, NULL, name); } diff --git a/drivers/gpu/drm/mcde/mcde_display.c b/drivers/gpu/drm/mcde/mcde_display.c index 4ddc55d58f38..ce12a36e2db4 100644 --- a/drivers/gpu/drm/mcde/mcde_display.c +++ b/drivers/gpu/drm/mcde/mcde_display.c @@ -1479,7 +1479,6 @@ static struct drm_simple_display_pipe_funcs mcde_display_funcs = { .update = mcde_display_update, .enable_vblank = mcde_display_enable_vblank, .disable_vblank = mcde_display_disable_vblank, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, }; int mcde_display_init(struct drm_device *drm) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index b46bdb8985da..9b60bec33d3b 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -270,12 +270,6 @@ static int mtk_drm_kms_init(struct drm_device *drm) goto err_component_unbind; } - /* - * We don't use the drm_irq_install() helpers provided by the DRM - * core, so we need to set this manually in order to allow the - * DRM_IOCTL_WAIT_VBLANK to operate correctly. - */ - drm->irq_enabled = true; ret = drm_vblank_init(drm, MAX_CRTC); if (ret < 0) goto err_component_unbind; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c index b5582dcf564c..1667a7e7de38 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c @@ -227,7 +227,6 @@ static void mtk_plane_atomic_update(struct drm_plane *plane, } static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = { - .prepare_fb = drm_gem_plane_helper_prepare_fb, .atomic_check = mtk_plane_atomic_check, .atomic_update = mtk_plane_atomic_update, .atomic_disable = mtk_plane_atomic_disable, diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index a7388bf7c838..bc0d60df04ae 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -21,7 +21,6 @@ #include <drm/drm_fb_helper.h> #include <drm/drm_gem_cma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> -#include <drm/drm_irq.h> #include <drm/drm_modeset_helper_vtables.h> #include <drm/drm_probe_helper.h> #include <drm/drm_vblank.h> @@ -94,9 +93,6 @@ DEFINE_DRM_GEM_CMA_FOPS(fops); static const struct drm_driver meson_driver = { .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, - /* IRQ */ - .irq_handler = meson_irq, - /* CMA Ops */ DRM_GEM_CMA_DRIVER_OPS_WITH_DUMB_CREATE(meson_dumb_create), @@ -285,7 +281,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) * Remove early framebuffers (ie. simplefb). The framebuffer can be * located anywhere in RAM */ - ret = drm_aperture_remove_framebuffers(false, "meson-drm-fb"); + ret = drm_aperture_remove_framebuffers(false, &meson_driver); if (ret) goto free_drm; @@ -335,7 +331,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) if (ret) goto free_drm; - ret = drm_irq_install(drm, priv->vsync_irq); + ret = request_irq(priv->vsync_irq, meson_irq, 0, drm->driver->name, drm); if (ret) goto free_drm; @@ -354,7 +350,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) return 0; uninstall_irq: - drm_irq_uninstall(drm); + free_irq(priv->vsync_irq, drm); free_drm: drm_dev_put(drm); @@ -382,7 +378,7 @@ static void meson_drv_unbind(struct device *dev) drm_kms_helper_poll_fini(drm); drm_atomic_helper_shutdown(drm); component_unbind_all(dev, drm); - drm_irq_uninstall(drm); + free_irq(priv->vsync_irq, drm); drm_dev_put(drm); if (priv->afbcd.ops) { diff --git a/drivers/gpu/drm/meson/meson_overlay.c b/drivers/gpu/drm/meson/meson_overlay.c index ed063152aecd..dfef8afcc245 100644 --- a/drivers/gpu/drm/meson/meson_overlay.c +++ b/drivers/gpu/drm/meson/meson_overlay.c @@ -747,7 +747,6 @@ static const struct drm_plane_helper_funcs meson_overlay_helper_funcs = { .atomic_check = meson_overlay_atomic_check, .atomic_disable = meson_overlay_atomic_disable, .atomic_update = meson_overlay_atomic_update, - .prepare_fb = drm_gem_plane_helper_prepare_fb, }; static bool meson_overlay_format_mod_supported(struct drm_plane *plane, diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c index a18510dae4c8..8640a8a8a469 100644 --- a/drivers/gpu/drm/meson/meson_plane.c +++ b/drivers/gpu/drm/meson/meson_plane.c @@ -422,7 +422,6 @@ static const struct drm_plane_helper_funcs meson_plane_helper_funcs = { .atomic_check = meson_plane_atomic_check, .atomic_disable = meson_plane_atomic_disable, .atomic_update = meson_plane_atomic_update, - .prepare_fb = drm_gem_plane_helper_prepare_fb, }; static bool meson_plane_format_mod_supported(struct drm_plane *plane, diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c index a701d9563257..6b9243713b3c 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.c +++ b/drivers/gpu/drm/mgag200/mgag200_drv.c @@ -262,17 +262,26 @@ static void mgag200_g200se_init_unique_id(struct mga_device *mdev) mdev->model.g200se.unique_rev_id); } -static int mgag200_device_init(struct mga_device *mdev, unsigned long flags) +static struct mga_device * +mgag200_device_create(struct pci_dev *pdev, enum mga_type type, unsigned long flags) { - struct drm_device *dev = &mdev->base; + struct mga_device *mdev; + struct drm_device *dev; int ret; - mdev->flags = mgag200_flags_from_driver_data(flags); - mdev->type = mgag200_type_from_driver_data(flags); + mdev = devm_drm_dev_alloc(&pdev->dev, &mgag200_driver, struct mga_device, base); + if (IS_ERR(mdev)) + return mdev; + dev = &mdev->base; + + pci_set_drvdata(pdev, dev); + + mdev->flags = flags; + mdev->type = type; ret = mgag200_regs_init(mdev); if (ret) - return ret; + return ERR_PTR(ret); if (mdev->type == G200_PCI || mdev->type == G200_AGP) mgag200_g200_init_refclk(mdev); @@ -281,33 +290,9 @@ static int mgag200_device_init(struct mga_device *mdev, unsigned long flags) ret = mgag200_mm_init(mdev); if (ret) - return ret; + return ERR_PTR(ret); ret = mgag200_modeset_init(mdev); - if (ret) { - drm_err(dev, "Fatal error during modeset init: %d\n", ret); - return ret; - } - - return 0; -} - -static struct mga_device * -mgag200_device_create(struct pci_dev *pdev, unsigned long flags) -{ - struct drm_device *dev; - struct mga_device *mdev; - int ret; - - mdev = devm_drm_dev_alloc(&pdev->dev, &mgag200_driver, - struct mga_device, base); - if (IS_ERR(mdev)) - return mdev; - dev = &mdev->base; - - pci_set_drvdata(pdev, dev); - - ret = mgag200_device_init(mdev, flags); if (ret) return ERR_PTR(ret); @@ -335,14 +320,27 @@ static const struct pci_device_id mgag200_pciidlist[] = { MODULE_DEVICE_TABLE(pci, mgag200_pciidlist); +static enum mga_type mgag200_type_from_driver_data(kernel_ulong_t driver_data) +{ + return (enum mga_type)(driver_data & MGAG200_TYPE_MASK); +} + +static unsigned long mgag200_flags_from_driver_data(kernel_ulong_t driver_data) +{ + return driver_data & MGAG200_FLAG_MASK; +} + static int mgag200_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { + kernel_ulong_t driver_data = ent->driver_data; + enum mga_type type = mgag200_type_from_driver_data(driver_data); + unsigned long flags = mgag200_flags_from_driver_data(driver_data); struct mga_device *mdev; struct drm_device *dev; int ret; - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "mgag200drmfb"); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &mgag200_driver); if (ret) return ret; @@ -350,12 +348,12 @@ mgag200_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (ret) return ret; - mdev = mgag200_device_create(pdev, ent->driver_data); + mdev = mgag200_device_create(pdev, type, flags); if (IS_ERR(mdev)) return PTR_ERR(mdev); dev = &mdev->base; - ret = drm_dev_register(dev, ent->driver_data); + ret = drm_dev_register(dev, 0); if (ret) return ret; diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.h b/drivers/gpu/drm/mgag200/mgag200_drv.h index 749a075fe9e4..f7a0537c0d0a 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.h +++ b/drivers/gpu/drm/mgag200/mgag200_drv.h @@ -166,8 +166,6 @@ struct mga_device { enum mga_type type; - int bpp_shifts[4]; - int fb_mtrr; union { @@ -192,18 +190,6 @@ static inline struct mga_device *to_mga_device(struct drm_device *dev) return container_of(dev, struct mga_device, base); } -static inline enum mga_type -mgag200_type_from_driver_data(kernel_ulong_t driver_data) -{ - return (enum mga_type)(driver_data & MGAG200_TYPE_MASK); -} - -static inline unsigned long -mgag200_flags_from_driver_data(kernel_ulong_t driver_data) -{ - return driver_data & MGAG200_FLAG_MASK; -} - /* mgag200_mode.c */ int mgag200_modeset_init(struct mga_device *mdev); diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index 9d576240faed..3b3059f471c2 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -1137,10 +1137,11 @@ static void mgag200_set_mode_regs(struct mga_device *mdev, WREG8(MGA_MISC_OUT, misc); } -static u8 mgag200_get_bpp_shift(struct mga_device *mdev, - const struct drm_format_info *format) +static u8 mgag200_get_bpp_shift(const struct drm_format_info *format) { - return mdev->bpp_shifts[format->cpp[0] - 1]; + static const u8 bpp_shift[] = {0, 1, 0, 2}; + + return bpp_shift[format->cpp[0] - 1]; } /* @@ -1152,7 +1153,7 @@ static u32 mgag200_calculate_offset(struct mga_device *mdev, const struct drm_framebuffer *fb) { u32 offset = fb->pitches[0] / fb->format->cpp[0]; - u8 bppshift = mgag200_get_bpp_shift(mdev, fb->format); + u8 bppshift = mgag200_get_bpp_shift(fb->format); if (fb->format->cpp[0] * 8 == 24) offset = (offset * 3) >> (4 - bppshift); @@ -1189,7 +1190,7 @@ static void mgag200_set_format_regs(struct mga_device *mdev, bpp = format->cpp[0] * 8; - bppshift = mgag200_get_bpp_shift(mdev, format); + bppshift = mgag200_get_bpp_shift(format); switch (bpp) { case 24: scale = ((1 << bppshift) * 3) - 1; @@ -1699,11 +1700,6 @@ int mgag200_modeset_init(struct mga_device *mdev) size_t format_count = ARRAY_SIZE(mgag200_simple_display_pipe_formats); int ret; - mdev->bpp_shifts[0] = 0; - mdev->bpp_shifts[1] = 1; - mdev->bpp_shifts[2] = 0; - mdev->bpp_shifts[3] = 2; - mgag200_init_regs(mdev); ret = drmm_mode_config_init(dev); diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c index 227404077e39..67fae60f2fa5 100644 --- a/drivers/gpu/drm/msm/msm_fbdev.c +++ b/drivers/gpu/drm/msm/msm_fbdev.c @@ -169,7 +169,7 @@ struct drm_fb_helper *msm_fbdev_init(struct drm_device *dev) } /* the fw fb could be anywhere in memory */ - ret = drm_aperture_remove_framebuffers(false, "msm"); + ret = drm_aperture_remove_framebuffers(false, dev->driver); if (ret) goto fini; diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 1e8a971a86f2..39c35414d7b5 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -812,17 +812,15 @@ int msm_gem_sync_object(struct drm_gem_object *obj, struct dma_fence *fence; int i, ret; - fobj = dma_resv_shared_list(obj->resv); - if (!fobj || (fobj->shared_count == 0)) { - fence = dma_resv_excl_fence(obj->resv); - /* don't need to wait on our own fences, since ring is fifo */ - if (fence && (fence->context != fctx->context)) { - ret = dma_fence_wait(fence, true); - if (ret) - return ret; - } + fence = dma_resv_excl_fence(obj->resv); + /* don't need to wait on our own fences, since ring is fifo */ + if (fence && (fence->context != fctx->context)) { + ret = dma_fence_wait(fence, true); + if (ret) + return ret; } + fobj = dma_resv_shared_list(obj->resv); if (!exclusive || !fobj) return 0; diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 44f84bfd0c0e..b71da71a3dd8 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -587,9 +587,7 @@ static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev, break; } - post_deps[i].chain = - kmalloc(sizeof(*post_deps[i].chain), - GFP_KERNEL); + post_deps[i].chain = dma_fence_chain_alloc(); if (!post_deps[i].chain) { ret = -ENOMEM; break; @@ -606,7 +604,7 @@ static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev, if (ret) { for (j = 0; j <= i; ++j) { - kfree(post_deps[j].chain); + dma_fence_chain_free(post_deps[j].chain); if (post_deps[j].syncobj) drm_syncobj_put(post_deps[j].syncobj); } diff --git a/drivers/gpu/drm/mxsfb/mxsfb_kms.c b/drivers/gpu/drm/mxsfb/mxsfb_kms.c index 300e7bab0f43..8797c671d0d5 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_kms.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_kms.c @@ -500,13 +500,11 @@ static bool mxsfb_format_mod_supported(struct drm_plane *plane, } static const struct drm_plane_helper_funcs mxsfb_plane_primary_helper_funcs = { - .prepare_fb = drm_gem_plane_helper_prepare_fb, .atomic_check = mxsfb_plane_atomic_check, .atomic_update = mxsfb_plane_primary_atomic_update, }; static const struct drm_plane_helper_funcs mxsfb_plane_overlay_helper_funcs = { - .prepare_fb = drm_gem_plane_helper_prepare_fb, .atomic_check = mxsfb_plane_atomic_check, .atomic_update = mxsfb_plane_overlay_atomic_update, }; diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index f949767698fc..093e1f7163b3 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -31,6 +31,7 @@ #include <linux/dma-mapping.h> #include <linux/hdmi.h> #include <linux/component.h> +#include <linux/iopoll.h> #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> @@ -1649,15 +1650,30 @@ nv50_sor_update(struct nouveau_encoder *nv_encoder, u8 head, core->func->sor->ctrl(core, nv_encoder->or, nv_encoder->ctrl, asyh); } +/* TODO: Should we extend this to PWM-only backlights? + * As well, should we add a DRM helper for waiting for the backlight to acknowledge + * the panel backlight has been shut off? Intel doesn't seem to do this, and uses a + * fixed time delay from the vbios… + */ static void nv50_sor_atomic_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); + struct nouveau_drm *drm = nouveau_drm(nv_encoder->base.base.dev); struct nouveau_crtc *nv_crtc = nouveau_crtc(nv_encoder->crtc); struct nouveau_connector *nv_connector = nv50_outp_get_old_connector(state, nv_encoder); + struct nouveau_backlight *backlight = nv_connector->backlight; struct drm_dp_aux *aux = &nv_connector->aux; + int ret; u8 pwr; + if (backlight && backlight->uses_dpcd) { + ret = drm_edp_backlight_disable(aux, &backlight->edp_info); + if (ret < 0) + NV_ERROR(drm, "Failed to disable backlight on [CONNECTOR:%d:%s]: %d\n", + nv_connector->base.base.id, nv_connector->base.name, ret); + } + if (nv_encoder->dcb->type == DCB_OUTPUT_DP) { int ret = drm_dp_dpcd_readb(aux, DP_SET_POWER, &pwr); @@ -1696,6 +1712,9 @@ nv50_sor_atomic_enable(struct drm_encoder *encoder, struct drm_atomic_state *sta struct drm_device *dev = encoder->dev; struct nouveau_drm *drm = nouveau_drm(dev); struct nouveau_connector *nv_connector; +#ifdef CONFIG_DRM_NOUVEAU_BACKLIGHT + struct nouveau_backlight *backlight; +#endif struct nvbios *bios = &drm->vbios; bool hda = false; u8 proto = NV507D_SOR_SET_CONTROL_PROTOCOL_CUSTOM; @@ -1770,6 +1789,14 @@ nv50_sor_atomic_enable(struct drm_encoder *encoder, struct drm_atomic_state *sta proto = NV887D_SOR_SET_CONTROL_PROTOCOL_DP_B; nv50_audio_enable(encoder, nv_crtc, nv_connector, state, mode); + +#ifdef CONFIG_DRM_NOUVEAU_BACKLIGHT + backlight = nv_connector->backlight; + if (backlight && backlight->uses_dpcd) + drm_edp_backlight_enable(&nv_connector->aux, &backlight->edp_info, + (u16)backlight->dev->props.brightness); +#endif + break; default: BUG(); @@ -2295,6 +2322,7 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state) nv50_crc_atomic_start_reporting(state); if (!flushed) nv50_crc_atomic_release_notifier_contexts(state); + drm_atomic_helper_commit_hw_done(state); drm_atomic_helper_cleanup_planes(dev, state); drm_atomic_helper_commit_cleanup_done(state); diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c index 72f35a2babcb..1cbd71abc80a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_backlight.c +++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c @@ -42,11 +42,6 @@ static struct ida bl_ida; #define BL_NAME_SIZE 15 // 12 for name + 2 for digits + 1 for '\0' -struct nouveau_backlight { - struct backlight_device *dev; - int id; -}; - static bool nouveau_get_backlight_name(char backlight_name[BL_NAME_SIZE], struct nouveau_backlight *bl) @@ -148,6 +143,98 @@ static const struct backlight_ops nv50_bl_ops = { .update_status = nv50_set_intensity, }; +/* + * eDP brightness callbacks need to happen under lock, since we need to + * enable/disable the backlight ourselves for modesets + */ +static int +nv50_edp_get_brightness(struct backlight_device *bd) +{ + struct drm_connector *connector = dev_get_drvdata(bd->dev.parent); + struct drm_device *dev = connector->dev; + struct drm_crtc *crtc; + struct drm_modeset_acquire_ctx ctx; + int ret = 0; + + drm_modeset_acquire_init(&ctx, 0); + +retry: + ret = drm_modeset_lock(&dev->mode_config.connection_mutex, &ctx); + if (ret == -EDEADLK) + goto deadlock; + else if (ret < 0) + goto out; + + crtc = connector->state->crtc; + if (!crtc) + goto out; + + ret = drm_modeset_lock(&crtc->mutex, &ctx); + if (ret == -EDEADLK) + goto deadlock; + else if (ret < 0) + goto out; + + if (!crtc->state->active) + goto out; + + ret = bd->props.brightness; +out: + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); + return ret; +deadlock: + drm_modeset_backoff(&ctx); + goto retry; +} + +static int +nv50_edp_set_brightness(struct backlight_device *bd) +{ + struct drm_connector *connector = dev_get_drvdata(bd->dev.parent); + struct nouveau_connector *nv_connector = nouveau_connector(connector); + struct drm_device *dev = connector->dev; + struct drm_crtc *crtc; + struct drm_dp_aux *aux = &nv_connector->aux; + struct nouveau_backlight *nv_bl = nv_connector->backlight; + struct drm_modeset_acquire_ctx ctx; + int ret = 0; + + drm_modeset_acquire_init(&ctx, 0); +retry: + ret = drm_modeset_lock(&dev->mode_config.connection_mutex, &ctx); + if (ret == -EDEADLK) + goto deadlock; + else if (ret < 0) + goto out; + + crtc = connector->state->crtc; + if (!crtc) + goto out; + + ret = drm_modeset_lock(&crtc->mutex, &ctx); + if (ret == -EDEADLK) + goto deadlock; + else if (ret < 0) + goto out; + + if (crtc->state->active) + ret = drm_edp_backlight_set_level(aux, &nv_bl->edp_info, bd->props.brightness); + +out: + drm_modeset_drop_locks(&ctx); + drm_modeset_acquire_fini(&ctx); + return ret; +deadlock: + drm_modeset_backoff(&ctx); + goto retry; +} + +static const struct backlight_ops nv50_edp_bl_ops = { + .get_brightness = nv50_edp_get_brightness, + .update_status = nv50_edp_set_brightness, +}; + static int nva3_get_intensity(struct backlight_device *bd) { @@ -194,8 +281,13 @@ static const struct backlight_ops nva3_bl_ops = { .update_status = nva3_set_intensity, }; +/* FIXME: perform backlight probing for eDP _before_ this, this only gets called after connector + * registration which happens after the initial modeset + */ static int -nv50_backlight_init(struct nouveau_encoder *nv_encoder, +nv50_backlight_init(struct nouveau_backlight *bl, + struct nouveau_connector *nv_conn, + struct nouveau_encoder *nv_encoder, struct backlight_properties *props, const struct backlight_ops **ops) { @@ -205,6 +297,41 @@ nv50_backlight_init(struct nouveau_encoder *nv_encoder, if (!nvif_rd32(device, NV50_PDISP_SOR_PWM_CTL(ffs(nv_encoder->dcb->or) - 1))) return -ENODEV; + if (nv_conn->type == DCB_CONNECTOR_eDP) { + int ret; + u16 current_level; + u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE]; + u8 current_mode; + + ret = drm_dp_dpcd_read(&nv_conn->aux, DP_EDP_DPCD_REV, edp_dpcd, + EDP_DISPLAY_CTL_CAP_SIZE); + if (ret < 0) + return ret; + + if (drm_edp_backlight_supported(edp_dpcd)) { + NV_DEBUG(drm, "DPCD backlight controls supported on %s\n", + nv_conn->base.name); + + ret = drm_edp_backlight_init(&nv_conn->aux, &bl->edp_info, 0, edp_dpcd, + ¤t_level, ¤t_mode); + if (ret < 0) + return ret; + + ret = drm_edp_backlight_enable(&nv_conn->aux, &bl->edp_info, current_level); + if (ret < 0) { + NV_ERROR(drm, "Failed to enable backlight on %s: %d\n", + nv_conn->base.name, ret); + return ret; + } + + *ops = &nv50_edp_bl_ops; + props->brightness = current_level; + props->max_brightness = bl->edp_info.max; + bl->uses_dpcd = true; + return 0; + } + } + if (drm->client.device.info.chipset <= 0xa0 || drm->client.device.info.chipset == 0xaa || drm->client.device.info.chipset == 0xac) @@ -245,6 +372,10 @@ nouveau_backlight_init(struct drm_connector *connector) if (!nv_encoder) return 0; + bl = kzalloc(sizeof(*bl), GFP_KERNEL); + if (!bl) + return -ENOMEM; + switch (device->info.family) { case NV_DEVICE_INFO_V0_CURIE: ret = nv40_backlight_init(nv_encoder, &props, &ops); @@ -257,20 +388,19 @@ nouveau_backlight_init(struct drm_connector *connector) case NV_DEVICE_INFO_V0_VOLTA: case NV_DEVICE_INFO_V0_TURING: case NV_DEVICE_INFO_V0_AMPERE: //XXX: not confirmed - ret = nv50_backlight_init(nv_encoder, &props, &ops); + ret = nv50_backlight_init(bl, nouveau_connector(connector), + nv_encoder, &props, &ops); break; default: - return 0; + ret = 0; + goto fail_alloc; } - if (ret == -ENODEV) - return 0; - else if (ret) - return ret; - - bl = kzalloc(sizeof(*bl), GFP_KERNEL); - if (!bl) - return -ENOMEM; + if (ret) { + if (ret == -ENODEV) + ret = 0; + goto fail_alloc; + } if (!nouveau_get_backlight_name(backlight_name, bl)) { NV_ERROR(drm, "Failed to retrieve a unique name for the backlight interface\n"); @@ -287,7 +417,9 @@ nouveau_backlight_init(struct drm_connector *connector) } nouveau_connector(connector)->backlight = bl; - bl->dev->props.brightness = bl->dev->ops->get_brightness(bl->dev); + if (!bl->dev->props.brightness) + bl->dev->props.brightness = + bl->dev->ops->get_brightness(bl->dev); backlight_update_status(bl->dev); return 0; diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 4f3a5357dd56..6d07e653f82d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -149,6 +149,8 @@ nouveau_bo_del_ttm(struct ttm_buffer_object *bo) */ if (bo->base.dev) drm_gem_object_release(&bo->base); + else + dma_resv_fini(&bo->base._resv); kfree(nvbo); } @@ -330,6 +332,10 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align, if (IS_ERR(nvbo)) return PTR_ERR(nvbo); + nvbo->bo.base.size = size; + dma_resv_init(&nvbo->bo.base._resv); + drm_vma_node_reset(&nvbo->bo.base.vma_node); + ret = nouveau_bo_init(nvbo, size, align, domain, sg, robj); if (ret) return ret; diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h index d0b859c4a80e..40f90e353540 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.h +++ b/drivers/gpu/drm/nouveau/nouveau_connector.h @@ -46,7 +46,14 @@ struct nvkm_i2c_port; struct dcb_output; #ifdef CONFIG_DRM_NOUVEAU_BACKLIGHT -struct nouveau_backlight; +struct nouveau_backlight { + struct backlight_device *dev; + + struct drm_edp_backlight_info edp_info; + bool uses_dpcd : 1; + + int id; +}; #endif #define nouveau_conn_atom(p) \ diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index a616cf4573b8..5e1ff870823b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -553,8 +553,6 @@ nouveau_drm_device_init(struct drm_device *dev) if (ret) goto fail_master; - dev->irq_enabled = true; - nvxx_client(&drm->client.base)->debug = nvkm_dbgopt(nouveau_debug, "DRM"); @@ -738,7 +736,7 @@ static int nouveau_drm_probe(struct pci_dev *pdev, nvkm_device_del(&device); /* Remove conflicting drivers (vesafb, efifb etc). */ - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "nouveaufb"); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &driver_pci); if (ret) return ret; @@ -795,7 +793,6 @@ nouveau_drm_device_remove(struct drm_device *dev) drm_dev_unregister(dev); - dev->irq_enabled = false; client = nvxx_client(&drm->client.base); device = nvkm_device_find(client->device); diff --git a/drivers/gpu/drm/nouveau/nouveau_encoder.h b/drivers/gpu/drm/nouveau/nouveau_encoder.h index 1ffcc0a491fd..77c2fed76e8b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_encoder.h +++ b/drivers/gpu/drm/nouveau/nouveau_encoder.h @@ -30,6 +30,7 @@ #include <subdev/bios/dcb.h> #include <drm/drm_encoder_slave.h> +#include <drm/drm_dp_helper.h> #include <drm/drm_dp_mst_helper.h> #include "dispnv04/disp.h" struct nv50_head_atom; diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 6b43918035df..05d0b3eb3690 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -358,7 +358,7 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan, bool e fobj = dma_resv_shared_list(resv); fence = dma_resv_excl_fence(resv); - if (fence && (!exclusive || !fobj || !fobj->shared_count)) { + if (fence) { struct nouveau_channel *prev = NULL; bool must_wait = true; diff --git a/drivers/gpu/drm/omapdrm/omap_drv.h b/drivers/gpu/drm/omapdrm/omap_drv.h index d6f136984da9..591d4c273f02 100644 --- a/drivers/gpu/drm/omapdrm/omap_drv.h +++ b/drivers/gpu/drm/omapdrm/omap_drv.h @@ -48,6 +48,8 @@ struct omap_drm_private { struct dss_device *dss; struct dispc_device *dispc; + bool irq_enabled; + unsigned int num_pipes; struct omap_drm_pipeline pipes[8]; struct omap_drm_pipeline *channels[8]; diff --git a/drivers/gpu/drm/omapdrm/omap_irq.c b/drivers/gpu/drm/omapdrm/omap_irq.c index 15148d4b35b5..4aca14dab927 100644 --- a/drivers/gpu/drm/omapdrm/omap_irq.c +++ b/drivers/gpu/drm/omapdrm/omap_irq.c @@ -253,13 +253,6 @@ static const u32 omap_underflow_irqs[] = { [OMAP_DSS_VIDEO3] = DISPC_IRQ_VID3_FIFO_UNDERFLOW, }; -/* - * We need a special version, instead of just using drm_irq_install(), - * because we need to register the irq via omapdss. Once omapdss and - * omapdrm are merged together we can assign the dispc hwmod data to - * ourselves and drop these and just use drm_irq_{install,uninstall}() - */ - int omap_drm_irq_install(struct drm_device *dev) { struct omap_drm_private *priv = dev->dev_private; @@ -291,7 +284,7 @@ int omap_drm_irq_install(struct drm_device *dev) if (ret < 0) return ret; - dev->irq_enabled = true; + priv->irq_enabled = true; return 0; } @@ -300,10 +293,10 @@ void omap_drm_irq_uninstall(struct drm_device *dev) { struct omap_drm_private *priv = dev->dev_private; - if (!dev->irq_enabled) + if (!priv->irq_enabled) return; - dev->irq_enabled = false; + priv->irq_enabled = false; dispc_free_irq(priv->dispc, dev); } diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c index 801da917507d..512af976b7e9 100644 --- a/drivers/gpu/drm/omapdrm/omap_plane.c +++ b/drivers/gpu/drm/omapdrm/omap_plane.c @@ -6,6 +6,7 @@ #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> +#include <drm/drm_gem_atomic_helper.h> #include <drm/drm_plane_helper.h> #include "omap_dmm_tiler.h" @@ -29,6 +30,8 @@ static int omap_plane_prepare_fb(struct drm_plane *plane, if (!new_state->fb) return 0; + drm_gem_plane_helper_prepare_fb(plane, new_state); + return omap_framebuffer_pin(new_state->fb); } diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index ef87d92cdf49..bfc6c23b2509 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -82,6 +82,7 @@ config DRM_PANEL_SIMPLE depends on BACKLIGHT_CLASS_DEVICE depends on PM select VIDEOMODE_HELPERS + select DRM_DP_AUX_BUS help DRM panel driver for dumb panels that need at most a regulator and a GPIO to be powered up. Optionally a backlight can be attached so @@ -133,6 +134,15 @@ config DRM_PANEL_ILITEK_ILI9881C Say Y if you want to enable support for panels based on the Ilitek ILI9881c controller. +config DRM_PANEL_INNOLUX_EJ030NA + tristate "Innolux EJ030NA 320x480 LCD panel" + depends on OF && SPI + select REGMAP_SPI + help + Say Y here to enable support for the Innolux/Chimei EJ030NA + 320x480 3.0" panel as found in the RS97 V2.1, RG300(non-ips) + and LDK handheld gaming consoles. + config DRM_PANEL_INNOLUX_P079ZCA tristate "Innolux P079ZCA panel" depends on OF @@ -343,6 +353,16 @@ config DRM_PANEL_RONBO_RB070D30 Say Y here if you want to enable support for Ronbo Electronics RB070D30 1024x600 DSI panel. +config DRM_PANEL_SAMSUNG_DB7430 + tristate "Samsung DB7430-based DPI panels" + depends on OF && SPI && GPIOLIB + depends on BACKLIGHT_CLASS_DEVICE + select DRM_MIPI_DBI + help + Say Y here if you want to enable support for the Samsung + DB7430 DPI display controller used in such devices as the + LMS397KF04 480x800 DPI panel. + config DRM_PANEL_SAMSUNG_S6D16D0 tristate "Samsung S6D16D0 DSI video mode panel" depends on OF @@ -377,6 +397,7 @@ config DRM_PANEL_SAMSUNG_S6E63M0_SPI depends on SPI depends on DRM_PANEL_SAMSUNG_S6E63M0 default DRM_PANEL_SAMSUNG_S6E63M0 + select DRM_MIPI_DBI help Say Y here if you want to be able to access the Samsung S6E63M0 panel using SPI. diff --git a/drivers/gpu/drm/panel/Makefile b/drivers/gpu/drm/panel/Makefile index cae4d976c069..1b865e8ea7c9 100644 --- a/drivers/gpu/drm/panel/Makefile +++ b/drivers/gpu/drm/panel/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_DRM_PANEL_FEIXIN_K101_IM2BA02) += panel-feixin-k101-im2ba02.o obj-$(CONFIG_DRM_PANEL_FEIYANG_FY07024DI26A30D) += panel-feiyang-fy07024di26a30d.o obj-$(CONFIG_DRM_PANEL_ILITEK_IL9322) += panel-ilitek-ili9322.o obj-$(CONFIG_DRM_PANEL_ILITEK_ILI9881C) += panel-ilitek-ili9881c.o +obj-$(CONFIG_DRM_PANEL_INNOLUX_EJ030NA) += panel-innolux-ej030na.o obj-$(CONFIG_DRM_PANEL_INNOLUX_P079ZCA) += panel-innolux-p079zca.o obj-$(CONFIG_DRM_PANEL_JDI_LT070ME05000) += panel-jdi-lt070me05000.o obj-$(CONFIG_DRM_PANEL_KHADAS_TS050) += panel-khadas-ts050.o @@ -33,6 +34,7 @@ obj-$(CONFIG_DRM_PANEL_RASPBERRYPI_TOUCHSCREEN) += panel-raspberrypi-touchscreen obj-$(CONFIG_DRM_PANEL_RAYDIUM_RM67191) += panel-raydium-rm67191.o obj-$(CONFIG_DRM_PANEL_RAYDIUM_RM68200) += panel-raydium-rm68200.o obj-$(CONFIG_DRM_PANEL_RONBO_RB070D30) += panel-ronbo-rb070d30.o +obj-$(CONFIG_DRM_PANEL_SAMSUNG_DB7430) += panel-samsung-db7430.o obj-$(CONFIG_DRM_PANEL_SAMSUNG_LD9040) += panel-samsung-ld9040.o obj-$(CONFIG_DRM_PANEL_SAMSUNG_S6D16D0) += panel-samsung-s6d16d0.o obj-$(CONFIG_DRM_PANEL_SAMSUNG_S6E3HA2) += panel-samsung-s6e3ha2.o diff --git a/drivers/gpu/drm/panel/panel-innolux-ej030na.c b/drivers/gpu/drm/panel/panel-innolux-ej030na.c new file mode 100644 index 000000000000..34b98f70bd22 --- /dev/null +++ b/drivers/gpu/drm/panel/panel-innolux-ej030na.c @@ -0,0 +1,289 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Innolux/Chimei EJ030NA TFT LCD panel driver + * + * Copyright (C) 2020, Paul Cercueil <paul@crapouillou.net> + * Copyright (C) 2020, Christophe Branchereau <cbranchereau@gmail.com> + */ + +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/gpio/consumer.h> +#include <linux/media-bus-format.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/regmap.h> +#include <linux/regulator/consumer.h> +#include <linux/spi/spi.h> + +#include <drm/drm_modes.h> +#include <drm/drm_panel.h> + +struct ej030na_info { + const struct drm_display_mode *display_modes; + unsigned int num_modes; + u16 width_mm, height_mm; + u32 bus_format, bus_flags; +}; + +struct ej030na { + struct drm_panel panel; + struct spi_device *spi; + struct regmap *map; + + const struct ej030na_info *panel_info; + + struct regulator *supply; + struct gpio_desc *reset_gpio; +}; + +static inline struct ej030na *to_ej030na(struct drm_panel *panel) +{ + return container_of(panel, struct ej030na, panel); +} + +static const struct reg_sequence ej030na_init_sequence[] = { + { 0x05, 0x1e }, + { 0x05, 0x5c }, + { 0x02, 0x14 }, + { 0x03, 0x40 }, + { 0x04, 0x07 }, + { 0x06, 0x12 }, + { 0x07, 0xd2 }, + { 0x0c, 0x06 }, + { 0x0d, 0x40 }, + { 0x0e, 0x40 }, + { 0x0f, 0x40 }, + { 0x10, 0x40 }, + { 0x11, 0x40 }, + { 0x2f, 0x40 }, + { 0x5a, 0x02 }, + + { 0x30, 0x07 }, + { 0x31, 0x57 }, + { 0x32, 0x53 }, + { 0x33, 0x77 }, + { 0x34, 0xb8 }, + { 0x35, 0xbd }, + { 0x36, 0xb8 }, + { 0x37, 0xe7 }, + { 0x38, 0x04 }, + { 0x39, 0xff }, + + { 0x40, 0x0b }, + { 0x41, 0xb8 }, + { 0x42, 0xab }, + { 0x43, 0xb9 }, + { 0x44, 0x6a }, + { 0x45, 0x56 }, + { 0x46, 0x61 }, + { 0x47, 0x08 }, + { 0x48, 0x0f }, + { 0x49, 0x0f }, + + { 0x2b, 0x01 }, +}; + +static int ej030na_prepare(struct drm_panel *panel) +{ + struct ej030na *priv = to_ej030na(panel); + struct device *dev = &priv->spi->dev; + int err; + + err = regulator_enable(priv->supply); + if (err) { + dev_err(dev, "Failed to enable power supply: %d\n", err); + return err; + } + + /* Reset the chip */ + gpiod_set_value_cansleep(priv->reset_gpio, 1); + usleep_range(50, 150); + gpiod_set_value_cansleep(priv->reset_gpio, 0); + usleep_range(50, 150); + + err = regmap_multi_reg_write(priv->map, ej030na_init_sequence, + ARRAY_SIZE(ej030na_init_sequence)); + if (err) { + dev_err(dev, "Failed to init registers: %d\n", err); + goto err_disable_regulator; + } + + msleep(120); + + return 0; + +err_disable_regulator: + regulator_disable(priv->supply); + return err; +} + +static int ej030na_unprepare(struct drm_panel *panel) +{ + struct ej030na *priv = to_ej030na(panel); + + gpiod_set_value_cansleep(priv->reset_gpio, 1); + regulator_disable(priv->supply); + + return 0; +} + +static int ej030na_get_modes(struct drm_panel *panel, + struct drm_connector *connector) +{ + struct ej030na *priv = to_ej030na(panel); + const struct ej030na_info *panel_info = priv->panel_info; + struct drm_display_mode *mode; + unsigned int i; + + for (i = 0; i < panel_info->num_modes; i++) { + mode = drm_mode_duplicate(connector->dev, + &panel_info->display_modes[i]); + if (!mode) + return -ENOMEM; + + drm_mode_set_name(mode); + + mode->type = DRM_MODE_TYPE_DRIVER; + if (panel_info->num_modes == 1) + mode->type |= DRM_MODE_TYPE_PREFERRED; + + drm_mode_probed_add(connector, mode); + } + + connector->display_info.bpc = 8; + connector->display_info.width_mm = panel_info->width_mm; + connector->display_info.height_mm = panel_info->height_mm; + + drm_display_info_set_bus_formats(&connector->display_info, + &panel_info->bus_format, 1); + connector->display_info.bus_flags = panel_info->bus_flags; + + return panel_info->num_modes; +} + +static const struct drm_panel_funcs ej030na_funcs = { + .prepare = ej030na_prepare, + .unprepare = ej030na_unprepare, + .get_modes = ej030na_get_modes, +}; + +static const struct regmap_config ej030na_regmap_config = { + .reg_bits = 8, + .val_bits = 8, + .max_register = 0x5a, +}; + +static int ej030na_probe(struct spi_device *spi) +{ + struct device *dev = &spi->dev; + struct ej030na *priv; + int err; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->spi = spi; + spi_set_drvdata(spi, priv); + + priv->map = devm_regmap_init_spi(spi, &ej030na_regmap_config); + if (IS_ERR(priv->map)) { + dev_err(dev, "Unable to init regmap\n"); + return PTR_ERR(priv->map); + } + + priv->panel_info = of_device_get_match_data(dev); + if (!priv->panel_info) + return -EINVAL; + + priv->supply = devm_regulator_get(dev, "power"); + if (IS_ERR(priv->supply)) { + dev_err(dev, "Failed to get power supply\n"); + return PTR_ERR(priv->supply); + } + + priv->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(priv->reset_gpio)) { + dev_err(dev, "Failed to get reset GPIO\n"); + return PTR_ERR(priv->reset_gpio); + } + + drm_panel_init(&priv->panel, dev, &ej030na_funcs, + DRM_MODE_CONNECTOR_DPI); + + err = drm_panel_of_backlight(&priv->panel); + if (err) + return err; + + drm_panel_add(&priv->panel); + + return 0; +} + +static int ej030na_remove(struct spi_device *spi) +{ + struct ej030na *priv = spi_get_drvdata(spi); + + drm_panel_remove(&priv->panel); + drm_panel_disable(&priv->panel); + drm_panel_unprepare(&priv->panel); + + return 0; +} + +static const struct drm_display_mode ej030na_modes[] = { + { /* 60 Hz */ + .clock = 14400, + .hdisplay = 320, + .hsync_start = 320 + 10, + .hsync_end = 320 + 10 + 37, + .htotal = 320 + 10 + 37 + 33, + .vdisplay = 480, + .vsync_start = 480 + 102, + .vsync_end = 480 + 102 + 9 + 9, + .vtotal = 480 + 102 + 9 + 9, + .flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC, + }, + { /* 50 Hz */ + .clock = 12000, + .hdisplay = 320, + .hsync_start = 320 + 10, + .hsync_end = 320 + 10 + 37, + .htotal = 320 + 10 + 37 + 33, + .vdisplay = 480, + .vsync_start = 480 + 102, + .vsync_end = 480 + 102 + 9, + .vtotal = 480 + 102 + 9 + 9, + .flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC, + }, +}; + +static const struct ej030na_info ej030na_info = { + .display_modes = ej030na_modes, + .num_modes = ARRAY_SIZE(ej030na_modes), + .width_mm = 70, + .height_mm = 51, + .bus_format = MEDIA_BUS_FMT_RGB888_3X8_DELTA, + .bus_flags = DRM_BUS_FLAG_PIXDATA_SAMPLE_POSEDGE | DRM_BUS_FLAG_DE_LOW, +}; + +static const struct of_device_id ej030na_of_match[] = { + { .compatible = "innolux,ej030na", .data = &ej030na_info }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, ej030na_of_match); + +static struct spi_driver ej030na_driver = { + .driver = { + .name = "panel-innolux-ej030na", + .of_match_table = ej030na_of_match, + }, + .probe = ej030na_probe, + .remove = ej030na_remove, +}; +module_spi_driver(ej030na_driver); + +MODULE_AUTHOR("Paul Cercueil <paul@crapouillou.net>"); +MODULE_AUTHOR("Christophe Branchereau <cbranchereau@gmail.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/panel/panel-samsung-db7430.c b/drivers/gpu/drm/panel/panel-samsung-db7430.c new file mode 100644 index 000000000000..ead479719f00 --- /dev/null +++ b/drivers/gpu/drm/panel/panel-samsung-db7430.c @@ -0,0 +1,347 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Panel driver for the Samsung LMS397KF04 480x800 DPI RGB panel. + * According to the data sheet the display controller is called DB7430. + * Found in the Samsung Galaxy Beam GT-I8350 mobile phone. + * Linus Walleij <linus.walleij@linaro.org> + */ +#include <drm/drm_mipi_dbi.h> +#include <drm/drm_modes.h> +#include <drm/drm_panel.h> + +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/media-bus-format.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/regulator/consumer.h> +#include <linux/spi/spi.h> + +#include <video/mipi_display.h> + +#define DB7430_ACCESS_PROT_OFF 0xb0 +#define DB7430_UNKNOWN_B4 0xb4 +#define DB7430_USER_SELECT 0xb5 +#define DB7430_UNKNOWN_B7 0xb7 +#define DB7430_UNKNOWN_B8 0xb8 +#define DB7430_PANEL_DRIVING 0xc0 +#define DB7430_SOURCE_CONTROL 0xc1 +#define DB7430_GATE_INTERFACE 0xc4 +#define DB7430_DISPLAY_H_TIMING 0xc5 +#define DB7430_RGB_SYNC_OPTION 0xc6 +#define DB7430_GAMMA_SET_RED 0xc8 +#define DB7430_GAMMA_SET_GREEN 0xc9 +#define DB7430_GAMMA_SET_BLUE 0xca +#define DB7430_BIAS_CURRENT_CTRL 0xd1 +#define DB7430_DDV_CTRL 0xd2 +#define DB7430_GAMMA_CTRL_REF 0xd3 +#define DB7430_UNKNOWN_D4 0xd4 +#define DB7430_DCDC_CTRL 0xd5 +#define DB7430_VCL_CTRL 0xd6 +#define DB7430_UNKNOWN_F8 0xf8 +#define DB7430_UNKNOWN_FC 0xfc + +#define DATA_MASK 0x100 + +/** + * struct db7430 - state container for a panel controlled by the DB7430 + * controller + */ +struct db7430 { + /** @dev: the container device */ + struct device *dev; + /** @dbi: the DBI bus abstraction handle */ + struct mipi_dbi dbi; + /** @panel: the DRM panel instance for this device */ + struct drm_panel panel; + /** @width: the width of this panel in mm */ + u32 width; + /** @height: the height of this panel in mm */ + u32 height; + /** @reset: reset GPIO line */ + struct gpio_desc *reset; + /** @regulators: VCCIO and VIO supply regulators */ + struct regulator_bulk_data regulators[2]; +}; + +static const struct drm_display_mode db7430_480_800_mode = { + /* + * 31 ns period min (htotal*vtotal*vrefresh)/1000 + * gives a Vrefresh of ~71 Hz. + */ + .clock = 32258, + .hdisplay = 480, + .hsync_start = 480 + 10, + .hsync_end = 480 + 10 + 4, + .htotal = 480 + 10 + 4 + 40, + .vdisplay = 800, + .vsync_start = 800 + 6, + .vsync_end = 800 + 6 + 1, + .vtotal = 800 + 6 + 1 + 7, + .width_mm = 53, + .height_mm = 87, + .flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC, +}; + +static inline struct db7430 *to_db7430(struct drm_panel *panel) +{ + return container_of(panel, struct db7430, panel); +} + +static int db7430_power_on(struct db7430 *db) +{ + struct mipi_dbi *dbi = &db->dbi; + int ret; + + /* Power up */ + ret = regulator_bulk_enable(ARRAY_SIZE(db->regulators), + db->regulators); + if (ret) { + dev_err(db->dev, "failed to enable regulators: %d\n", ret); + return ret; + } + msleep(50); + + /* Assert reset >=1 ms */ + gpiod_set_value_cansleep(db->reset, 1); + usleep_range(1000, 5000); + /* De-assert reset */ + gpiod_set_value_cansleep(db->reset, 0); + /* Wait >= 10 ms */ + msleep(10); + dev_dbg(db->dev, "de-asserted RESET\n"); + + /* + * This is set to 0x0a (RGB/BGR order + horizontal flip) in order + * to make the display behave normally. If this is not set the displays + * normal output behaviour is horizontally flipped and BGR ordered. Do + * it twice because the first message doesn't always "take". + */ + mipi_dbi_command(dbi, MIPI_DCS_SET_ADDRESS_MODE, 0x0a); + mipi_dbi_command(dbi, MIPI_DCS_SET_ADDRESS_MODE, 0x0a); + mipi_dbi_command(dbi, DB7430_ACCESS_PROT_OFF, 0x00); + mipi_dbi_command(dbi, DB7430_PANEL_DRIVING, 0x28, 0x08); + mipi_dbi_command(dbi, DB7430_SOURCE_CONTROL, + 0x01, 0x30, 0x15, 0x05, 0x22); + mipi_dbi_command(dbi, DB7430_GATE_INTERFACE, + 0x10, 0x01, 0x00); + mipi_dbi_command(dbi, DB7430_DISPLAY_H_TIMING, + 0x06, 0x55, 0x03, 0x07, 0x0b, + 0x33, 0x00, 0x01, 0x03); + /* + * 0x00 in datasheet 0x01 in vendor code 0x00, it seems 0x01 means + * DE active high and 0x00 means DE active low. + */ + mipi_dbi_command(dbi, DB7430_RGB_SYNC_OPTION, 0x01); + mipi_dbi_command(dbi, DB7430_GAMMA_SET_RED, + /* R positive gamma */ 0x00, + 0x0A, 0x31, 0x3B, 0x4E, 0x58, 0x59, 0x5B, 0x58, 0x5E, 0x62, + 0x60, 0x61, 0x5E, 0x62, 0x55, 0x55, 0x7F, 0x08, + /* R negative gamma */ 0x00, + 0x0A, 0x31, 0x3B, 0x4E, 0x58, 0x59, 0x5B, 0x58, 0x5E, 0x62, + 0x60, 0x61, 0x5E, 0x62, 0x55, 0x55, 0x7F, 0x08); + mipi_dbi_command(dbi, DB7430_GAMMA_SET_GREEN, + /* G positive gamma */ 0x00, + 0x25, 0x15, 0x28, 0x3D, 0x4A, 0x48, 0x4C, 0x4A, 0x52, 0x59, + 0x59, 0x5B, 0x56, 0x60, 0x5D, 0x55, 0x7F, 0x0A, + /* G negative gamma */ 0x00, + 0x25, 0x15, 0x28, 0x3D, 0x4A, 0x48, 0x4C, 0x4A, 0x52, 0x59, + 0x59, 0x5B, 0x56, 0x60, 0x5D, 0x55, 0x7F, 0x0A); + mipi_dbi_command(dbi, DB7430_GAMMA_SET_BLUE, + /* B positive gamma */ 0x00, + 0x48, 0x10, 0x1F, 0x2F, 0x35, 0x38, 0x3D, 0x3C, 0x45, 0x4D, + 0x4E, 0x52, 0x51, 0x60, 0x7F, 0x7E, 0x7F, 0x0C, + /* B negative gamma */ 0x00, + 0x48, 0x10, 0x1F, 0x2F, 0x35, 0x38, 0x3D, 0x3C, 0x45, 0x4D, + 0x4E, 0x52, 0x51, 0x60, 0x7F, 0x7E, 0x7F, 0x0C); + mipi_dbi_command(dbi, DB7430_BIAS_CURRENT_CTRL, 0x33, 0x13); + mipi_dbi_command(dbi, DB7430_DDV_CTRL, 0x11, 0x00, 0x00); + mipi_dbi_command(dbi, DB7430_GAMMA_CTRL_REF, 0x50, 0x50); + mipi_dbi_command(dbi, DB7430_DCDC_CTRL, 0x2f, 0x11, 0x1e, 0x46); + mipi_dbi_command(dbi, DB7430_VCL_CTRL, 0x11, 0x0a); + + return 0; +} + +static int db7430_power_off(struct db7430 *db) +{ + /* Go into RESET and disable regulators */ + gpiod_set_value_cansleep(db->reset, 1); + return regulator_bulk_disable(ARRAY_SIZE(db->regulators), + db->regulators); +} + +static int db7430_unprepare(struct drm_panel *panel) +{ + return db7430_power_off(to_db7430(panel)); +} + +static int db7430_disable(struct drm_panel *panel) +{ + struct db7430 *db = to_db7430(panel); + struct mipi_dbi *dbi = &db->dbi; + + mipi_dbi_command(dbi, MIPI_DCS_SET_DISPLAY_OFF); + msleep(25); + mipi_dbi_command(dbi, MIPI_DCS_ENTER_SLEEP_MODE); + msleep(120); + + return 0; +} + +static int db7430_prepare(struct drm_panel *panel) +{ + return db7430_power_on(to_db7430(panel)); +} + +static int db7430_enable(struct drm_panel *panel) +{ + struct db7430 *db = to_db7430(panel); + struct mipi_dbi *dbi = &db->dbi; + + /* Exit sleep mode */ + mipi_dbi_command(dbi, MIPI_DCS_EXIT_SLEEP_MODE); + msleep(20); + + /* NVM (non-volatile memory) load sequence */ + mipi_dbi_command(dbi, DB7430_UNKNOWN_D4, 0x52, 0x5e); + mipi_dbi_command(dbi, DB7430_UNKNOWN_F8, 0x01, 0xf5, 0xf2, 0x71, 0x44); + mipi_dbi_command(dbi, DB7430_UNKNOWN_FC, 0x00, 0x08); + msleep(150); + + /* CABC turn on sequence (BC = backlight control) */ + mipi_dbi_command(dbi, DB7430_UNKNOWN_B4, 0x0f, 0x00, 0x50); + mipi_dbi_command(dbi, DB7430_USER_SELECT, 0x80); + mipi_dbi_command(dbi, DB7430_UNKNOWN_B7, 0x24); + mipi_dbi_command(dbi, DB7430_UNKNOWN_B8, 0x01); + + /* Turn on display */ + mipi_dbi_command(dbi, MIPI_DCS_SET_DISPLAY_ON); + + return 0; +} + +/** + * db7430_get_modes() - return the mode + * @panel: the panel to get the mode for + * @connector: reference to the central DRM connector control structure + */ +static int db7430_get_modes(struct drm_panel *panel, + struct drm_connector *connector) +{ + struct db7430 *db = to_db7430(panel); + struct drm_display_mode *mode; + static const u32 bus_format = MEDIA_BUS_FMT_RGB888_1X24; + + mode = drm_mode_duplicate(connector->dev, &db7430_480_800_mode); + if (!mode) { + dev_err(db->dev, "failed to add mode\n"); + return -ENOMEM; + } + + connector->display_info.bpc = 8; + connector->display_info.width_mm = mode->width_mm; + connector->display_info.height_mm = mode->height_mm; + connector->display_info.bus_flags = + DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE; + drm_display_info_set_bus_formats(&connector->display_info, + &bus_format, 1); + + drm_mode_set_name(mode); + mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; + + drm_mode_probed_add(connector, mode); + + return 1; +} + +static const struct drm_panel_funcs db7430_drm_funcs = { + .disable = db7430_disable, + .unprepare = db7430_unprepare, + .prepare = db7430_prepare, + .enable = db7430_enable, + .get_modes = db7430_get_modes, +}; + +static int db7430_probe(struct spi_device *spi) +{ + struct device *dev = &spi->dev; + struct db7430 *db; + int ret; + + db = devm_kzalloc(dev, sizeof(*db), GFP_KERNEL); + if (!db) + return -ENOMEM; + db->dev = dev; + + /* + * VCI is the analog voltage supply + * VCCIO is the digital I/O voltage supply + */ + db->regulators[0].supply = "vci"; + db->regulators[1].supply = "vccio"; + ret = devm_regulator_bulk_get(dev, + ARRAY_SIZE(db->regulators), + db->regulators); + if (ret) + return dev_err_probe(dev, ret, "failed to get regulators\n"); + + db->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(db->reset)) { + ret = PTR_ERR(db->reset); + return dev_err_probe(dev, ret, "no RESET GPIO\n"); + } + + ret = mipi_dbi_spi_init(spi, &db->dbi, NULL); + if (ret) + return dev_err_probe(dev, ret, "MIPI DBI init failed\n"); + + drm_panel_init(&db->panel, dev, &db7430_drm_funcs, + DRM_MODE_CONNECTOR_DPI); + + /* FIXME: if no external backlight, use internal backlight */ + ret = drm_panel_of_backlight(&db->panel); + if (ret) + return dev_err_probe(dev, ret, "failed to add backlight\n"); + + spi_set_drvdata(spi, db); + + drm_panel_add(&db->panel); + dev_dbg(dev, "added panel\n"); + + return 0; +} + +static int db7430_remove(struct spi_device *spi) +{ + struct db7430 *db = spi_get_drvdata(spi); + + drm_panel_remove(&db->panel); + return 0; +} + +/* + * The DB7430 display controller may be used in several display products, + * so list the different variants here and add per-variant data if needed. + */ +static const struct of_device_id db7430_match[] = { + { .compatible = "samsung,lms397kf04", }, + {}, +}; +MODULE_DEVICE_TABLE(of, db7430_match); + +static struct spi_driver db7430_driver = { + .probe = db7430_probe, + .remove = db7430_remove, + .driver = { + .name = "db7430-panel", + .of_match_table = db7430_match, + }, +}; +module_spi_driver(db7430_driver); + +MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>"); +MODULE_DESCRIPTION("Samsung DB7430 panel driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0-dsi.c b/drivers/gpu/drm/panel/panel-samsung-s6e63m0-dsi.c index 07a48f621289..e0b1a7e354f3 100644 --- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0-dsi.c +++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0-dsi.c @@ -16,7 +16,8 @@ #define MCS_GLOBAL_PARAM 0xb0 #define S6E63M0_DSI_MAX_CHUNK 15 /* CMD + 15 bytes max */ -static int s6e63m0_dsi_dcs_read(struct device *dev, const u8 cmd, u8 *data) +static int s6e63m0_dsi_dcs_read(struct device *dev, void *trsp, + const u8 cmd, u8 *data) { struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev); int ret; @@ -32,7 +33,8 @@ static int s6e63m0_dsi_dcs_read(struct device *dev, const u8 cmd, u8 *data) return 0; } -static int s6e63m0_dsi_dcs_write(struct device *dev, const u8 *data, size_t len) +static int s6e63m0_dsi_dcs_write(struct device *dev, void *trsp, + const u8 *data, size_t len) { struct mipi_dsi_device *dsi = to_mipi_dsi_device(dev); const u8 *seqp = data; @@ -99,8 +101,8 @@ static int s6e63m0_dsi_probe(struct mipi_dsi_device *dsi) dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_BURST; - ret = s6e63m0_probe(dev, s6e63m0_dsi_dcs_read, s6e63m0_dsi_dcs_write, - true); + ret = s6e63m0_probe(dev, NULL, s6e63m0_dsi_dcs_read, + s6e63m0_dsi_dcs_write, true); if (ret) return ret; diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c b/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c index 326deb3177b6..3669cc3719ce 100644 --- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c +++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0-spi.c @@ -5,62 +5,38 @@ #include <linux/spi/spi.h> #include <linux/delay.h> +#include <drm/drm_mipi_dbi.h> #include <drm/drm_print.h> #include "panel-samsung-s6e63m0.h" -#define DATA_MASK 0x100 +static const u8 s6e63m0_dbi_read_commands[] = { + MCS_READ_ID1, + MCS_READ_ID2, + MCS_READ_ID3, + 0, /* sentinel */ +}; -static int s6e63m0_spi_dcs_read(struct device *dev, const u8 cmd, u8 *data) +static int s6e63m0_spi_dcs_read(struct device *dev, void *trsp, + const u8 cmd, u8 *data) { - struct spi_device *spi = to_spi_device(dev); - u16 buf[1]; - u16 rbuf[1]; + struct mipi_dbi *dbi = trsp; int ret; - /* SPI buffers are always in CPU order */ - buf[0] = (u16)cmd; - ret = spi_write_then_read(spi, buf, 2, rbuf, 2); - dev_dbg(dev, "READ CMD: %04x RET: %04x\n", buf[0], rbuf[0]); - if (!ret) - /* These high 8 bits of the 9 contains the readout */ - *data = (rbuf[0] & 0x1ff) >> 1; + ret = mipi_dbi_command_read(dbi, cmd, data); + if (ret) + dev_err(dev, "error on DBI read command %02x\n", cmd); return ret; } -static int s6e63m0_spi_write_word(struct device *dev, u16 data) -{ - struct spi_device *spi = to_spi_device(dev); - - /* SPI buffers are always in CPU order */ - return spi_write(spi, &data, 2); -} - -static int s6e63m0_spi_dcs_write(struct device *dev, const u8 *data, size_t len) +static int s6e63m0_spi_dcs_write(struct device *dev, void *trsp, + const u8 *data, size_t len) { - int ret = 0; - - dev_dbg(dev, "SPI writing dcs seq: %*ph\n", (int)len, data); - - /* - * This sends 9 bits with the first bit (bit 8) set to 0 - * This indicates that this is a command. Anything after the - * command is data. - */ - ret = s6e63m0_spi_write_word(dev, *data); - - while (!ret && --len) { - ++data; - /* This sends 9 bits with the first bit (bit 8) set to 1 */ - ret = s6e63m0_spi_write_word(dev, *data | DATA_MASK); - } - - if (ret) { - dev_err(dev, "SPI error %d writing dcs seq: %*ph\n", ret, - (int)len, data); - } + struct mipi_dbi *dbi = trsp; + int ret; + ret = mipi_dbi_command_stackbuf(dbi, data[0], (data + 1), (len - 1)); usleep_range(300, 310); return ret; @@ -69,18 +45,21 @@ static int s6e63m0_spi_dcs_write(struct device *dev, const u8 *data, size_t len) static int s6e63m0_spi_probe(struct spi_device *spi) { struct device *dev = &spi->dev; + struct mipi_dbi *dbi; int ret; - spi->bits_per_word = 9; - /* Preserve e.g. SPI_3WIRE setting */ - spi->mode |= SPI_MODE_3; - ret = spi_setup(spi); - if (ret < 0) { - dev_err(dev, "spi setup failed.\n"); - return ret; - } - return s6e63m0_probe(dev, s6e63m0_spi_dcs_read, s6e63m0_spi_dcs_write, - false); + dbi = devm_kzalloc(dev, sizeof(*dbi), GFP_KERNEL); + if (!dbi) + return -ENOMEM; + + ret = mipi_dbi_spi_init(spi, dbi, NULL); + if (ret) + return dev_err_probe(dev, ret, "MIPI DBI init failed\n"); + /* Register our custom MCS read commands */ + dbi->read_commands = s6e63m0_dbi_read_commands; + + return s6e63m0_probe(dev, dbi, s6e63m0_spi_dcs_read, + s6e63m0_spi_dcs_write, false); } static int s6e63m0_spi_remove(struct spi_device *spi) diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c index 603c5dfe8768..35d72ac663d6 100644 --- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c +++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.c @@ -22,31 +22,6 @@ #include "panel-samsung-s6e63m0.h" -/* Manufacturer Command Set */ -#define MCS_ELVSS_ON 0xb1 -#define MCS_TEMP_SWIRE 0xb2 -#define MCS_PENTILE_1 0xb3 -#define MCS_PENTILE_2 0xb4 -#define MCS_GAMMA_DELTA_Y_RED 0xb5 -#define MCS_GAMMA_DELTA_X_RED 0xb6 -#define MCS_GAMMA_DELTA_Y_GREEN 0xb7 -#define MCS_GAMMA_DELTA_X_GREEN 0xb8 -#define MCS_GAMMA_DELTA_Y_BLUE 0xb9 -#define MCS_GAMMA_DELTA_X_BLUE 0xba -#define MCS_MIECTL1 0xc0 -#define MCS_BCMODE 0xc1 -#define MCS_ERROR_CHECK 0xd5 -#define MCS_READ_ID1 0xda -#define MCS_READ_ID2 0xdb -#define MCS_READ_ID3 0xdc -#define MCS_LEVEL_2_KEY 0xf0 -#define MCS_MTP_KEY 0xf1 -#define MCS_DISCTL 0xf2 -#define MCS_SRCCTL 0xf6 -#define MCS_IFCTL 0xf7 -#define MCS_PANELCTL 0xf8 -#define MCS_PGAMMACTL 0xfa - #define S6E63M0_LCD_ID_VALUE_M2 0xA4 #define S6E63M0_LCD_ID_VALUE_SM2 0xB4 #define S6E63M0_LCD_ID_VALUE_SM2_1 0xB6 @@ -283,8 +258,9 @@ static u8 const s6e63m0_elvss_per_gamma[NUM_GAMMA_LEVELS] = { struct s6e63m0 { struct device *dev; - int (*dcs_read)(struct device *dev, const u8 cmd, u8 *val); - int (*dcs_write)(struct device *dev, const u8 *data, size_t len); + void *transport_data; + int (*dcs_read)(struct device *dev, void *trsp, const u8 cmd, u8 *val); + int (*dcs_write)(struct device *dev, void *trsp, const u8 *data, size_t len); struct drm_panel panel; struct backlight_device *bl_dev; u8 lcd_type; @@ -340,7 +316,7 @@ static void s6e63m0_dcs_read(struct s6e63m0 *ctx, const u8 cmd, u8 *data) if (ctx->error < 0) return; - ctx->error = ctx->dcs_read(ctx->dev, cmd, data); + ctx->error = ctx->dcs_read(ctx->dev, ctx->transport_data, cmd, data); } static void s6e63m0_dcs_write(struct s6e63m0 *ctx, const u8 *data, size_t len) @@ -348,7 +324,7 @@ static void s6e63m0_dcs_write(struct s6e63m0 *ctx, const u8 *data, size_t len) if (ctx->error < 0 || len == 0) return; - ctx->error = ctx->dcs_write(ctx->dev, data, len); + ctx->error = ctx->dcs_write(ctx->dev, ctx->transport_data, data, len); } #define s6e63m0_dcs_write_seq_static(ctx, seq ...) \ @@ -713,9 +689,9 @@ static int s6e63m0_backlight_register(struct s6e63m0 *ctx, u32 max_brightness) return ret; } -int s6e63m0_probe(struct device *dev, - int (*dcs_read)(struct device *dev, const u8 cmd, u8 *val), - int (*dcs_write)(struct device *dev, const u8 *data, size_t len), +int s6e63m0_probe(struct device *dev, void *trsp, + int (*dcs_read)(struct device *dev, void *trsp, const u8 cmd, u8 *val), + int (*dcs_write)(struct device *dev, void *trsp, const u8 *data, size_t len), bool dsi_mode) { struct s6e63m0 *ctx; @@ -726,6 +702,7 @@ int s6e63m0_probe(struct device *dev, if (!ctx) return -ENOMEM; + ctx->transport_data = trsp; ctx->dsi_mode = dsi_mode; ctx->dcs_read = dcs_read; ctx->dcs_write = dcs_write; diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.h b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.h index c669fec91763..306605ed1117 100644 --- a/drivers/gpu/drm/panel/panel-samsung-s6e63m0.h +++ b/drivers/gpu/drm/panel/panel-samsung-s6e63m0.h @@ -3,9 +3,36 @@ #ifndef _PANEL_SAMSUNG_S6E63M0_H #define _PANEL_SAMSUNG_S6E63M0_H -int s6e63m0_probe(struct device *dev, - int (*dcs_read)(struct device *dev, const u8 cmd, u8 *val), - int (*dcs_write)(struct device *dev, const u8 *data, +/* Manufacturer Command Set */ +#define MCS_ELVSS_ON 0xb1 +#define MCS_TEMP_SWIRE 0xb2 +#define MCS_PENTILE_1 0xb3 +#define MCS_PENTILE_2 0xb4 +#define MCS_GAMMA_DELTA_Y_RED 0xb5 +#define MCS_GAMMA_DELTA_X_RED 0xb6 +#define MCS_GAMMA_DELTA_Y_GREEN 0xb7 +#define MCS_GAMMA_DELTA_X_GREEN 0xb8 +#define MCS_GAMMA_DELTA_Y_BLUE 0xb9 +#define MCS_GAMMA_DELTA_X_BLUE 0xba +#define MCS_MIECTL1 0xc0 +#define MCS_BCMODE 0xc1 +#define MCS_ERROR_CHECK 0xd5 +#define MCS_READ_ID1 0xda +#define MCS_READ_ID2 0xdb +#define MCS_READ_ID3 0xdc +#define MCS_LEVEL_2_KEY 0xf0 +#define MCS_MTP_KEY 0xf1 +#define MCS_DISCTL 0xf2 +#define MCS_SRCCTL 0xf6 +#define MCS_IFCTL 0xf7 +#define MCS_PANELCTL 0xf8 +#define MCS_PGAMMACTL 0xfa + +int s6e63m0_probe(struct device *dev, void *trsp, + int (*dcs_read)(struct device *dev, void *trsp, + const u8 cmd, u8 *val), + int (*dcs_write)(struct device *dev, void *trsp, + const u8 *data, size_t len), bool dsi_mode); int s6e63m0_remove(struct device *dev); diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 21939d4352cf..9b286bd4444f 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -36,6 +36,8 @@ #include <drm/drm_crtc.h> #include <drm/drm_device.h> +#include <drm/drm_dp_aux_bus.h> +#include <drm/drm_dp_helper.h> #include <drm/drm_mipi_dsi.h> #include <drm/drm_panel.h> @@ -131,6 +133,22 @@ struct panel_desc { unsigned int prepare_to_enable; /** + * @delay.power_to_enable: Time for the power to enable the display on. + * + * The time (in milliseconds) to wait after powering up the display + * before asserting its enable pin. + */ + unsigned int power_to_enable; + + /** + * @delay.disable_to_power_off: Time for the disable to power the display off. + * + * The time (in milliseconds) to wait before powering off the display + * after deasserting its enable pin. + */ + unsigned int disable_to_power_off; + + /** * @delay.enable: Time for the panel to display a valid frame. * * The time (in milliseconds) that it takes for the panel to @@ -185,6 +203,7 @@ struct panel_simple { struct regulator *supply; struct i2c_adapter *ddc; + struct drm_dp_aux *aux; struct gpio_desc *enable_gpio; struct gpio_desc *hpd_gpio; @@ -344,6 +363,10 @@ static int panel_simple_suspend(struct device *dev) struct panel_simple *p = dev_get_drvdata(dev); gpiod_set_value_cansleep(p->enable_gpio, 0); + + if (p->desc->delay.disable_to_power_off) + msleep(p->desc->delay.disable_to_power_off); + regulator_disable(p->supply); p->unprepared_time = ktime_get(); @@ -404,6 +427,9 @@ static int panel_simple_prepare_once(struct panel_simple *p) return err; } + if (p->desc->delay.power_to_enable) + msleep(p->desc->delay.power_to_enable); + gpiod_set_value_cansleep(p->enable_gpio, 1); delay = p->desc->delay.prepare; @@ -657,7 +683,8 @@ static void panel_simple_parse_panel_timing_node(struct device *dev, dev_err(dev, "Reject override mode: No display_timing found\n"); } -static int panel_simple_probe(struct device *dev, const struct panel_desc *desc) +static int panel_simple_probe(struct device *dev, const struct panel_desc *desc, + struct drm_dp_aux *aux) { struct panel_simple *panel; struct display_timing dt; @@ -673,6 +700,7 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc) panel->enabled = false; panel->prepared_time = 0; panel->desc = desc; + panel->aux = aux; panel->no_hpd = of_property_read_bool(dev->of_node, "no-hpd"); if (!panel->no_hpd) { @@ -707,6 +735,8 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc) if (!panel->ddc) return -EPROBE_DEFER; + } else if (aux) { + panel->ddc = &aux->ddc; } if (desc == &panel_dpi) { @@ -742,10 +772,8 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc) desc->bpc != 8); break; case DRM_MODE_CONNECTOR_eDP: - if (desc->bus_format == 0) - dev_warn(dev, "Specify missing bus_format\n"); - if (desc->bpc != 6 && desc->bpc != 8) - dev_warn(dev, "Expected bpc in {6,8} but got: %u\n", desc->bpc); + if (desc->bpc != 6 && desc->bpc != 8 && desc->bpc != 10) + dev_warn(dev, "Expected bpc in {6,8,10} but got: %u\n", desc->bpc); break; case DRM_MODE_CONNECTOR_DSI: if (desc->bpc != 6 && desc->bpc != 8) @@ -775,6 +803,11 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc) break; } + if (!panel->enable_gpio && desc->delay.disable_to_power_off) + dev_warn(dev, "Need a delay after disabling panel GPIO, but a GPIO wasn't provided\n"); + if (!panel->enable_gpio && desc->delay.power_to_enable) + dev_warn(dev, "Need a delay before enabling panel GPIO, but a GPIO wasn't provided\n"); + dev_set_drvdata(dev, panel); /* @@ -793,6 +826,15 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc) if (err) goto disable_pm_runtime; + if (!panel->base.backlight && panel->aux) { + pm_runtime_get_sync(dev); + err = drm_panel_dp_aux_backlight(&panel->base, panel->aux); + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + if (err) + goto disable_pm_runtime; + } + drm_panel_add(&panel->base); return 0; @@ -801,7 +843,7 @@ disable_pm_runtime: pm_runtime_dont_use_autosuspend(dev); pm_runtime_disable(dev); free_ddc: - if (panel->ddc) + if (panel->ddc && (!panel->aux || panel->ddc != &panel->aux->ddc)) put_device(&panel->ddc->dev); return err; @@ -817,7 +859,7 @@ static int panel_simple_remove(struct device *dev) pm_runtime_dont_use_autosuspend(dev); pm_runtime_disable(dev); - if (panel->ddc) + if (panel->ddc && (!panel->aux || panel->ddc != &panel->aux->ddc)) put_device(&panel->ddc->dev); return 0; @@ -1179,6 +1221,8 @@ static const struct panel_desc auo_g104sn02 = { .width = 211, .height = 158, }, + .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, + .connector_type = DRM_MODE_CONNECTOR_LVDS, }; static const struct drm_display_mode auo_g121ean01_mode = { @@ -1929,6 +1973,32 @@ static const struct panel_desc edt_et035012dm6 = { .bus_flags = DRM_BUS_FLAG_DE_LOW | DRM_BUS_FLAG_PIXDATA_SAMPLE_POSEDGE, }; +static const struct drm_display_mode edt_etm0350g0dh6_mode = { + .clock = 6520, + .hdisplay = 320, + .hsync_start = 320 + 20, + .hsync_end = 320 + 20 + 68, + .htotal = 320 + 20 + 68, + .vdisplay = 240, + .vsync_start = 240 + 4, + .vsync_end = 240 + 4 + 18, + .vtotal = 240 + 4 + 18, + .flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC, +}; + +static const struct panel_desc edt_etm0350g0dh6 = { + .modes = &edt_etm0350g0dh6_mode, + .num_modes = 1, + .bpc = 6, + .size = { + .width = 70, + .height = 53, + }, + .bus_format = MEDIA_BUS_FMT_RGB888_1X24, + .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE, + .connector_type = DRM_MODE_CONNECTOR_DPI, +}; + static const struct drm_display_mode edt_etm043080dh6gp_mode = { .clock = 10870, .hdisplay = 480, @@ -1980,6 +2050,9 @@ static const struct panel_desc edt_etm0430g0dh6 = { .width = 95, .height = 54, }, + .bus_format = MEDIA_BUS_FMT_RGB666_1X18, + .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_SAMPLE_POSEDGE, + .connector_type = DRM_MODE_CONNECTOR_DPI, }; static const struct drm_display_mode edt_et057090dhu_mode = { @@ -2044,6 +2117,33 @@ static const struct panel_desc edt_etm0700g0bdh6 = { }, .bus_format = MEDIA_BUS_FMT_RGB666_1X18, .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE, + .connector_type = DRM_MODE_CONNECTOR_DPI, +}; + +static const struct drm_display_mode edt_etmv570g2dhu_mode = { + .clock = 25175, + .hdisplay = 640, + .hsync_start = 640, + .hsync_end = 640 + 16, + .htotal = 640 + 16 + 30 + 114, + .vdisplay = 480, + .vsync_start = 480 + 10, + .vsync_end = 480 + 10 + 3, + .vtotal = 480 + 10 + 3 + 35, + .flags = DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_PHSYNC, +}; + +static const struct panel_desc edt_etmv570g2dhu = { + .modes = &edt_etmv570g2dhu_mode, + .num_modes = 1, + .bpc = 6, + .size = { + .width = 115, + .height = 86, + }, + .bus_format = MEDIA_BUS_FMT_RGB888_1X24, + .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE, + .connector_type = DRM_MODE_CONNECTOR_DPI, }; static const struct display_timing evervision_vgg804821_timing = { @@ -3521,6 +3621,36 @@ static const struct panel_desc rocktech_rk101ii01d_ct = { .connector_type = DRM_MODE_CONNECTOR_LVDS, }; +static const struct drm_display_mode samsung_atna33xc20_mode = { + .clock = 138770, + .hdisplay = 1920, + .hsync_start = 1920 + 48, + .hsync_end = 1920 + 48 + 32, + .htotal = 1920 + 48 + 32 + 80, + .vdisplay = 1080, + .vsync_start = 1080 + 8, + .vsync_end = 1080 + 8 + 8, + .vtotal = 1080 + 8 + 8 + 16, + .flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NVSYNC, +}; + +static const struct panel_desc samsung_atna33xc20 = { + .modes = &samsung_atna33xc20_mode, + .num_modes = 1, + .bpc = 10, + .size = { + .width = 294, + .height = 165, + }, + .delay = { + .disable_to_power_off = 200, + .power_to_enable = 400, + .hpd_absent_delay = 200, + .unprepare = 500, + }, + .connector_type = DRM_MODE_CONNECTOR_eDP, +}; + static const struct drm_display_mode samsung_lsn122dl01_c01_mode = { .clock = 271560, .hdisplay = 2560, @@ -4330,6 +4460,9 @@ static const struct of_device_id platform_of_match[] = { .compatible = "edt,et035012dm6", .data = &edt_et035012dm6, }, { + .compatible = "edt,etm0350g0dh6", + .data = &edt_etm0350g0dh6, + }, { .compatible = "edt,etm043080dh6gp", .data = &edt_etm043080dh6gp, }, { @@ -4351,6 +4484,9 @@ static const struct of_device_id platform_of_match[] = { .compatible = "edt,etm0700g0edh6", .data = &edt_etm0700g0bdh6, }, { + .compatible = "edt,etmv570g2dhu", + .data = &edt_etmv570g2dhu, + }, { .compatible = "evervision,vgg804821", .data = &evervision_vgg804821, }, { @@ -4522,6 +4658,9 @@ static const struct of_device_id platform_of_match[] = { .compatible = "rocktech,rk101ii01d-ct", .data = &rocktech_rk101ii01d_ct, }, { + .compatible = "samsung,atna33xc20", + .data = &samsung_atna33xc20, + }, { .compatible = "samsung,lsn122dl01-c01", .data = &samsung_lsn122dl01_c01, }, { @@ -4632,7 +4771,7 @@ static int panel_simple_platform_probe(struct platform_device *pdev) if (!id) return -ENODEV; - return panel_simple_probe(&pdev->dev, id->data); + return panel_simple_probe(&pdev->dev, id->data, NULL); } static int panel_simple_platform_remove(struct platform_device *pdev) @@ -4912,7 +5051,7 @@ static int panel_simple_dsi_probe(struct mipi_dsi_device *dsi) desc = id->data; - err = panel_simple_probe(&dsi->dev, &desc->desc); + err = panel_simple_probe(&dsi->dev, &desc->desc, NULL); if (err < 0) return err; @@ -4957,6 +5096,38 @@ static struct mipi_dsi_driver panel_simple_dsi_driver = { .shutdown = panel_simple_dsi_shutdown, }; +static int panel_simple_dp_aux_ep_probe(struct dp_aux_ep_device *aux_ep) +{ + const struct of_device_id *id; + + id = of_match_node(platform_of_match, aux_ep->dev.of_node); + if (!id) + return -ENODEV; + + return panel_simple_probe(&aux_ep->dev, id->data, aux_ep->aux); +} + +static void panel_simple_dp_aux_ep_remove(struct dp_aux_ep_device *aux_ep) +{ + panel_simple_remove(&aux_ep->dev); +} + +static void panel_simple_dp_aux_ep_shutdown(struct dp_aux_ep_device *aux_ep) +{ + panel_simple_shutdown(&aux_ep->dev); +} + +static struct dp_aux_ep_driver panel_simple_dp_aux_ep_driver = { + .driver = { + .name = "panel-simple-dp-aux", + .of_match_table = platform_of_match, /* Same as platform one! */ + .pm = &panel_simple_pm_ops, + }, + .probe = panel_simple_dp_aux_ep_probe, + .remove = panel_simple_dp_aux_ep_remove, + .shutdown = panel_simple_dp_aux_ep_shutdown, +}; + static int __init panel_simple_init(void) { int err; @@ -4965,15 +5136,25 @@ static int __init panel_simple_init(void) if (err < 0) return err; + err = dp_aux_dp_driver_register(&panel_simple_dp_aux_ep_driver); + if (err < 0) + goto err_did_platform_register; + if (IS_ENABLED(CONFIG_DRM_MIPI_DSI)) { err = mipi_dsi_driver_register(&panel_simple_dsi_driver); - if (err < 0) { - platform_driver_unregister(&panel_simple_platform_driver); - return err; - } + if (err < 0) + goto err_did_aux_ep_register; } return 0; + +err_did_aux_ep_register: + dp_aux_dp_driver_unregister(&panel_simple_dp_aux_ep_driver); + +err_did_platform_register: + platform_driver_unregister(&panel_simple_platform_driver); + + return err; } module_init(panel_simple_init); @@ -4982,6 +5163,7 @@ static void __exit panel_simple_exit(void) if (IS_ENABLED(CONFIG_DRM_MIPI_DSI)) mipi_dsi_driver_unregister(&panel_simple_dsi_driver); + dp_aux_dp_driver_unregister(&panel_simple_dp_aux_ep_driver); platform_driver_unregister(&panel_simple_platform_driver); } module_exit(panel_simple_exit); diff --git a/drivers/gpu/drm/panfrost/panfrost_device.c b/drivers/gpu/drm/panfrost/panfrost_device.c index 125ed973feaa..bd9b7be63b0f 100644 --- a/drivers/gpu/drm/panfrost/panfrost_device.c +++ b/drivers/gpu/drm/panfrost/panfrost_device.c @@ -54,7 +54,8 @@ static int panfrost_clk_init(struct panfrost_device *pfdev) if (IS_ERR(pfdev->bus_clock)) { dev_err(pfdev->dev, "get bus_clock failed %ld\n", PTR_ERR(pfdev->bus_clock)); - return PTR_ERR(pfdev->bus_clock); + err = PTR_ERR(pfdev->bus_clock); + goto disable_clock; } if (pfdev->bus_clock) { @@ -291,55 +292,100 @@ void panfrost_device_fini(struct panfrost_device *pfdev) panfrost_clk_fini(pfdev); } -const char *panfrost_exception_name(struct panfrost_device *pfdev, u32 exception_code) -{ - switch (exception_code) { - /* Non-Fault Status code */ - case 0x00: return "NOT_STARTED/IDLE/OK"; - case 0x01: return "DONE"; - case 0x02: return "INTERRUPTED"; - case 0x03: return "STOPPED"; - case 0x04: return "TERMINATED"; - case 0x08: return "ACTIVE"; - /* Job exceptions */ - case 0x40: return "JOB_CONFIG_FAULT"; - case 0x41: return "JOB_POWER_FAULT"; - case 0x42: return "JOB_READ_FAULT"; - case 0x43: return "JOB_WRITE_FAULT"; - case 0x44: return "JOB_AFFINITY_FAULT"; - case 0x48: return "JOB_BUS_FAULT"; - case 0x50: return "INSTR_INVALID_PC"; - case 0x51: return "INSTR_INVALID_ENC"; - case 0x52: return "INSTR_TYPE_MISMATCH"; - case 0x53: return "INSTR_OPERAND_FAULT"; - case 0x54: return "INSTR_TLS_FAULT"; - case 0x55: return "INSTR_BARRIER_FAULT"; - case 0x56: return "INSTR_ALIGN_FAULT"; - case 0x58: return "DATA_INVALID_FAULT"; - case 0x59: return "TILE_RANGE_FAULT"; - case 0x5A: return "ADDR_RANGE_FAULT"; - case 0x60: return "OUT_OF_MEMORY"; - /* GPU exceptions */ - case 0x80: return "DELAYED_BUS_FAULT"; - case 0x88: return "SHAREABILITY_FAULT"; - /* MMU exceptions */ - case 0xC1: return "TRANSLATION_FAULT_LEVEL1"; - case 0xC2: return "TRANSLATION_FAULT_LEVEL2"; - case 0xC3: return "TRANSLATION_FAULT_LEVEL3"; - case 0xC4: return "TRANSLATION_FAULT_LEVEL4"; - case 0xC8: return "PERMISSION_FAULT"; - case 0xC9 ... 0xCF: return "PERMISSION_FAULT"; - case 0xD1: return "TRANSTAB_BUS_FAULT_LEVEL1"; - case 0xD2: return "TRANSTAB_BUS_FAULT_LEVEL2"; - case 0xD3: return "TRANSTAB_BUS_FAULT_LEVEL3"; - case 0xD4: return "TRANSTAB_BUS_FAULT_LEVEL4"; - case 0xD8: return "ACCESS_FLAG"; - case 0xD9 ... 0xDF: return "ACCESS_FLAG"; - case 0xE0 ... 0xE7: return "ADDRESS_SIZE_FAULT"; - case 0xE8 ... 0xEF: return "MEMORY_ATTRIBUTES_FAULT"; +#define PANFROST_EXCEPTION(id) \ + [DRM_PANFROST_EXCEPTION_ ## id] = { \ + .name = #id, \ } - return "UNKNOWN"; +struct panfrost_exception_info { + const char *name; +}; + +static const struct panfrost_exception_info panfrost_exception_infos[] = { + PANFROST_EXCEPTION(OK), + PANFROST_EXCEPTION(DONE), + PANFROST_EXCEPTION(INTERRUPTED), + PANFROST_EXCEPTION(STOPPED), + PANFROST_EXCEPTION(TERMINATED), + PANFROST_EXCEPTION(KABOOM), + PANFROST_EXCEPTION(EUREKA), + PANFROST_EXCEPTION(ACTIVE), + PANFROST_EXCEPTION(JOB_CONFIG_FAULT), + PANFROST_EXCEPTION(JOB_POWER_FAULT), + PANFROST_EXCEPTION(JOB_READ_FAULT), + PANFROST_EXCEPTION(JOB_WRITE_FAULT), + PANFROST_EXCEPTION(JOB_AFFINITY_FAULT), + PANFROST_EXCEPTION(JOB_BUS_FAULT), + PANFROST_EXCEPTION(INSTR_INVALID_PC), + PANFROST_EXCEPTION(INSTR_INVALID_ENC), + PANFROST_EXCEPTION(INSTR_TYPE_MISMATCH), + PANFROST_EXCEPTION(INSTR_OPERAND_FAULT), + PANFROST_EXCEPTION(INSTR_TLS_FAULT), + PANFROST_EXCEPTION(INSTR_BARRIER_FAULT), + PANFROST_EXCEPTION(INSTR_ALIGN_FAULT), + PANFROST_EXCEPTION(DATA_INVALID_FAULT), + PANFROST_EXCEPTION(TILE_RANGE_FAULT), + PANFROST_EXCEPTION(ADDR_RANGE_FAULT), + PANFROST_EXCEPTION(IMPRECISE_FAULT), + PANFROST_EXCEPTION(OOM), + PANFROST_EXCEPTION(OOM_AFBC), + PANFROST_EXCEPTION(UNKNOWN), + PANFROST_EXCEPTION(DELAYED_BUS_FAULT), + PANFROST_EXCEPTION(GPU_SHAREABILITY_FAULT), + PANFROST_EXCEPTION(SYS_SHAREABILITY_FAULT), + PANFROST_EXCEPTION(GPU_CACHEABILITY_FAULT), + PANFROST_EXCEPTION(TRANSLATION_FAULT_0), + PANFROST_EXCEPTION(TRANSLATION_FAULT_1), + PANFROST_EXCEPTION(TRANSLATION_FAULT_2), + PANFROST_EXCEPTION(TRANSLATION_FAULT_3), + PANFROST_EXCEPTION(TRANSLATION_FAULT_4), + PANFROST_EXCEPTION(TRANSLATION_FAULT_IDENTITY), + PANFROST_EXCEPTION(PERM_FAULT_0), + PANFROST_EXCEPTION(PERM_FAULT_1), + PANFROST_EXCEPTION(PERM_FAULT_2), + PANFROST_EXCEPTION(PERM_FAULT_3), + PANFROST_EXCEPTION(TRANSTAB_BUS_FAULT_0), + PANFROST_EXCEPTION(TRANSTAB_BUS_FAULT_1), + PANFROST_EXCEPTION(TRANSTAB_BUS_FAULT_2), + PANFROST_EXCEPTION(TRANSTAB_BUS_FAULT_3), + PANFROST_EXCEPTION(ACCESS_FLAG_0), + PANFROST_EXCEPTION(ACCESS_FLAG_1), + PANFROST_EXCEPTION(ACCESS_FLAG_2), + PANFROST_EXCEPTION(ACCESS_FLAG_3), + PANFROST_EXCEPTION(ADDR_SIZE_FAULT_IN0), + PANFROST_EXCEPTION(ADDR_SIZE_FAULT_IN1), + PANFROST_EXCEPTION(ADDR_SIZE_FAULT_IN2), + PANFROST_EXCEPTION(ADDR_SIZE_FAULT_IN3), + PANFROST_EXCEPTION(ADDR_SIZE_FAULT_OUT0), + PANFROST_EXCEPTION(ADDR_SIZE_FAULT_OUT1), + PANFROST_EXCEPTION(ADDR_SIZE_FAULT_OUT2), + PANFROST_EXCEPTION(ADDR_SIZE_FAULT_OUT3), + PANFROST_EXCEPTION(MEM_ATTR_FAULT_0), + PANFROST_EXCEPTION(MEM_ATTR_FAULT_1), + PANFROST_EXCEPTION(MEM_ATTR_FAULT_2), + PANFROST_EXCEPTION(MEM_ATTR_FAULT_3), + PANFROST_EXCEPTION(MEM_ATTR_NONCACHE_0), + PANFROST_EXCEPTION(MEM_ATTR_NONCACHE_1), + PANFROST_EXCEPTION(MEM_ATTR_NONCACHE_2), + PANFROST_EXCEPTION(MEM_ATTR_NONCACHE_3), +}; + +const char *panfrost_exception_name(u32 exception_code) +{ + if (WARN_ON(exception_code >= ARRAY_SIZE(panfrost_exception_infos) || + !panfrost_exception_infos[exception_code].name)) + return "Unknown exception type"; + + return panfrost_exception_infos[exception_code].name; +} + +bool panfrost_exception_needs_reset(const struct panfrost_device *pfdev, + u32 exception_code) +{ + /* Right now, none of the GPU we support need a reset, but this + * might change. + */ + return false; } void panfrost_device_reset(struct panfrost_device *pfdev) diff --git a/drivers/gpu/drm/panfrost/panfrost_device.h b/drivers/gpu/drm/panfrost/panfrost_device.h index f614e98771e4..8b25278f34c8 100644 --- a/drivers/gpu/drm/panfrost/panfrost_device.h +++ b/drivers/gpu/drm/panfrost/panfrost_device.h @@ -97,11 +97,12 @@ struct panfrost_device { spinlock_t as_lock; unsigned long as_in_use_mask; unsigned long as_alloc_mask; + unsigned long as_faulty_mask; struct list_head as_lru_list; struct panfrost_job_slot *js; - struct panfrost_job *jobs[NUM_JOB_SLOTS]; + struct panfrost_job *jobs[NUM_JOB_SLOTS][2]; struct list_head scheduled_jobs; struct panfrost_perfcnt *perfcnt; @@ -109,6 +110,7 @@ struct panfrost_device { struct mutex sched_lock; struct { + struct workqueue_struct *wq; struct work_struct work; atomic_t pending; } reset; @@ -121,8 +123,12 @@ struct panfrost_device { }; struct panfrost_mmu { + struct panfrost_device *pfdev; + struct kref refcount; struct io_pgtable_cfg pgtbl_cfg; struct io_pgtable_ops *pgtbl_ops; + struct drm_mm mm; + spinlock_t mm_lock; int as; atomic_t as_count; struct list_head list; @@ -133,9 +139,7 @@ struct panfrost_file_priv { struct drm_sched_entity sched_entity[NUM_JOB_SLOTS]; - struct panfrost_mmu mmu; - struct drm_mm mm; - spinlock_t mm_lock; + struct panfrost_mmu *mmu; }; static inline struct panfrost_device *to_panfrost_device(struct drm_device *ddev) @@ -171,6 +175,91 @@ void panfrost_device_reset(struct panfrost_device *pfdev); int panfrost_device_resume(struct device *dev); int panfrost_device_suspend(struct device *dev); -const char *panfrost_exception_name(struct panfrost_device *pfdev, u32 exception_code); +enum drm_panfrost_exception_type { + DRM_PANFROST_EXCEPTION_OK = 0x00, + DRM_PANFROST_EXCEPTION_DONE = 0x01, + DRM_PANFROST_EXCEPTION_INTERRUPTED = 0x02, + DRM_PANFROST_EXCEPTION_STOPPED = 0x03, + DRM_PANFROST_EXCEPTION_TERMINATED = 0x04, + DRM_PANFROST_EXCEPTION_KABOOM = 0x05, + DRM_PANFROST_EXCEPTION_EUREKA = 0x06, + DRM_PANFROST_EXCEPTION_ACTIVE = 0x08, + DRM_PANFROST_EXCEPTION_MAX_NON_FAULT = 0x3f, + DRM_PANFROST_EXCEPTION_JOB_CONFIG_FAULT = 0x40, + DRM_PANFROST_EXCEPTION_JOB_POWER_FAULT = 0x41, + DRM_PANFROST_EXCEPTION_JOB_READ_FAULT = 0x42, + DRM_PANFROST_EXCEPTION_JOB_WRITE_FAULT = 0x43, + DRM_PANFROST_EXCEPTION_JOB_AFFINITY_FAULT = 0x44, + DRM_PANFROST_EXCEPTION_JOB_BUS_FAULT = 0x48, + DRM_PANFROST_EXCEPTION_INSTR_INVALID_PC = 0x50, + DRM_PANFROST_EXCEPTION_INSTR_INVALID_ENC = 0x51, + DRM_PANFROST_EXCEPTION_INSTR_TYPE_MISMATCH = 0x52, + DRM_PANFROST_EXCEPTION_INSTR_OPERAND_FAULT = 0x53, + DRM_PANFROST_EXCEPTION_INSTR_TLS_FAULT = 0x54, + DRM_PANFROST_EXCEPTION_INSTR_BARRIER_FAULT = 0x55, + DRM_PANFROST_EXCEPTION_INSTR_ALIGN_FAULT = 0x56, + DRM_PANFROST_EXCEPTION_DATA_INVALID_FAULT = 0x58, + DRM_PANFROST_EXCEPTION_TILE_RANGE_FAULT = 0x59, + DRM_PANFROST_EXCEPTION_ADDR_RANGE_FAULT = 0x5a, + DRM_PANFROST_EXCEPTION_IMPRECISE_FAULT = 0x5b, + DRM_PANFROST_EXCEPTION_OOM = 0x60, + DRM_PANFROST_EXCEPTION_OOM_AFBC = 0x61, + DRM_PANFROST_EXCEPTION_UNKNOWN = 0x7f, + DRM_PANFROST_EXCEPTION_DELAYED_BUS_FAULT = 0x80, + DRM_PANFROST_EXCEPTION_GPU_SHAREABILITY_FAULT = 0x88, + DRM_PANFROST_EXCEPTION_SYS_SHAREABILITY_FAULT = 0x89, + DRM_PANFROST_EXCEPTION_GPU_CACHEABILITY_FAULT = 0x8a, + DRM_PANFROST_EXCEPTION_TRANSLATION_FAULT_0 = 0xc0, + DRM_PANFROST_EXCEPTION_TRANSLATION_FAULT_1 = 0xc1, + DRM_PANFROST_EXCEPTION_TRANSLATION_FAULT_2 = 0xc2, + DRM_PANFROST_EXCEPTION_TRANSLATION_FAULT_3 = 0xc3, + DRM_PANFROST_EXCEPTION_TRANSLATION_FAULT_4 = 0xc4, + DRM_PANFROST_EXCEPTION_TRANSLATION_FAULT_IDENTITY = 0xc7, + DRM_PANFROST_EXCEPTION_PERM_FAULT_0 = 0xc8, + DRM_PANFROST_EXCEPTION_PERM_FAULT_1 = 0xc9, + DRM_PANFROST_EXCEPTION_PERM_FAULT_2 = 0xca, + DRM_PANFROST_EXCEPTION_PERM_FAULT_3 = 0xcb, + DRM_PANFROST_EXCEPTION_TRANSTAB_BUS_FAULT_0 = 0xd0, + DRM_PANFROST_EXCEPTION_TRANSTAB_BUS_FAULT_1 = 0xd1, + DRM_PANFROST_EXCEPTION_TRANSTAB_BUS_FAULT_2 = 0xd2, + DRM_PANFROST_EXCEPTION_TRANSTAB_BUS_FAULT_3 = 0xd3, + DRM_PANFROST_EXCEPTION_ACCESS_FLAG_0 = 0xd8, + DRM_PANFROST_EXCEPTION_ACCESS_FLAG_1 = 0xd9, + DRM_PANFROST_EXCEPTION_ACCESS_FLAG_2 = 0xda, + DRM_PANFROST_EXCEPTION_ACCESS_FLAG_3 = 0xdb, + DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_IN0 = 0xe0, + DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_IN1 = 0xe1, + DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_IN2 = 0xe2, + DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_IN3 = 0xe3, + DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_OUT0 = 0xe4, + DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_OUT1 = 0xe5, + DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_OUT2 = 0xe6, + DRM_PANFROST_EXCEPTION_ADDR_SIZE_FAULT_OUT3 = 0xe7, + DRM_PANFROST_EXCEPTION_MEM_ATTR_FAULT_0 = 0xe8, + DRM_PANFROST_EXCEPTION_MEM_ATTR_FAULT_1 = 0xe9, + DRM_PANFROST_EXCEPTION_MEM_ATTR_FAULT_2 = 0xea, + DRM_PANFROST_EXCEPTION_MEM_ATTR_FAULT_3 = 0xeb, + DRM_PANFROST_EXCEPTION_MEM_ATTR_NONCACHE_0 = 0xec, + DRM_PANFROST_EXCEPTION_MEM_ATTR_NONCACHE_1 = 0xed, + DRM_PANFROST_EXCEPTION_MEM_ATTR_NONCACHE_2 = 0xee, + DRM_PANFROST_EXCEPTION_MEM_ATTR_NONCACHE_3 = 0xef, +}; + +static inline bool +panfrost_exception_is_fault(u32 exception_code) +{ + return exception_code > DRM_PANFROST_EXCEPTION_MAX_NON_FAULT; +} + +const char *panfrost_exception_name(u32 exception_code); +bool panfrost_exception_needs_reset(const struct panfrost_device *pfdev, + u32 exception_code); + +static inline void +panfrost_device_schedule_reset(struct panfrost_device *pfdev) +{ + atomic_set(&pfdev->reset.pending, 1); + queue_work(pfdev->reset.wq, &pfdev->reset.work); +} #endif diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 075ec0ef746c..1ffaef5ec5ff 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -138,12 +138,6 @@ panfrost_lookup_bos(struct drm_device *dev, if (!job->bo_count) return 0; - job->implicit_fences = kvmalloc_array(job->bo_count, - sizeof(struct dma_fence *), - GFP_KERNEL | __GFP_ZERO); - if (!job->implicit_fences) - return -ENOMEM; - ret = drm_gem_objects_lookup(file_priv, (void __user *)(uintptr_t)args->bo_handles, job->bo_count, &job->bos); @@ -174,7 +168,7 @@ panfrost_lookup_bos(struct drm_device *dev, } /** - * panfrost_copy_in_sync() - Sets up job->in_fences[] with the sync objects + * panfrost_copy_in_sync() - Sets up job->deps with the sync objects * referenced by the job. * @dev: DRM device * @file_priv: DRM file for this fd @@ -194,22 +188,14 @@ panfrost_copy_in_sync(struct drm_device *dev, { u32 *handles; int ret = 0; - int i; + int i, in_fence_count; - job->in_fence_count = args->in_sync_count; + in_fence_count = args->in_sync_count; - if (!job->in_fence_count) + if (!in_fence_count) return 0; - job->in_fences = kvmalloc_array(job->in_fence_count, - sizeof(struct dma_fence *), - GFP_KERNEL | __GFP_ZERO); - if (!job->in_fences) { - DRM_DEBUG("Failed to allocate job in fences\n"); - return -ENOMEM; - } - - handles = kvmalloc_array(job->in_fence_count, sizeof(u32), GFP_KERNEL); + handles = kvmalloc_array(in_fence_count, sizeof(u32), GFP_KERNEL); if (!handles) { ret = -ENOMEM; DRM_DEBUG("Failed to allocate incoming syncobj handles\n"); @@ -218,16 +204,23 @@ panfrost_copy_in_sync(struct drm_device *dev, if (copy_from_user(handles, (void __user *)(uintptr_t)args->in_syncs, - job->in_fence_count * sizeof(u32))) { + in_fence_count * sizeof(u32))) { ret = -EFAULT; DRM_DEBUG("Failed to copy in syncobj handles\n"); goto fail; } - for (i = 0; i < job->in_fence_count; i++) { + for (i = 0; i < in_fence_count; i++) { + struct dma_fence *fence; + ret = drm_syncobj_find_fence(file_priv, handles[i], 0, 0, - &job->in_fences[i]); - if (ret == -EINVAL) + &fence); + if (ret) + goto fail; + + ret = drm_gem_fence_array_add(&job->deps, fence); + + if (ret) goto fail; } @@ -265,6 +258,8 @@ static int panfrost_ioctl_submit(struct drm_device *dev, void *data, kref_init(&job->refcount); + xa_init_flags(&job->deps, XA_FLAGS_ALLOC); + job->pfdev = pfdev; job->jc = args->jc; job->requirements = args->requirements; @@ -417,7 +412,7 @@ static int panfrost_ioctl_madvise(struct drm_device *dev, void *data, * anyway, so let's not bother. */ if (!list_is_singular(&bo->mappings.list) || - WARN_ON_ONCE(first->mmu != &priv->mmu)) { + WARN_ON_ONCE(first->mmu != priv->mmu)) { ret = -EINVAL; goto out_unlock_mappings; } @@ -449,32 +444,6 @@ int panfrost_unstable_ioctl_check(void) return 0; } -#define PFN_4G (SZ_4G >> PAGE_SHIFT) -#define PFN_4G_MASK (PFN_4G - 1) -#define PFN_16M (SZ_16M >> PAGE_SHIFT) - -static void panfrost_drm_mm_color_adjust(const struct drm_mm_node *node, - unsigned long color, - u64 *start, u64 *end) -{ - /* Executable buffers can't start or end on a 4GB boundary */ - if (!(color & PANFROST_BO_NOEXEC)) { - u64 next_seg; - - if ((*start & PFN_4G_MASK) == 0) - (*start)++; - - if ((*end & PFN_4G_MASK) == 0) - (*end)--; - - next_seg = ALIGN(*start, PFN_4G); - if (next_seg - *start <= PFN_16M) - *start = next_seg + 1; - - *end = min(*end, ALIGN(*start, PFN_4G) - 1); - } -} - static int panfrost_open(struct drm_device *dev, struct drm_file *file) { @@ -489,15 +458,11 @@ panfrost_open(struct drm_device *dev, struct drm_file *file) panfrost_priv->pfdev = pfdev; file->driver_priv = panfrost_priv; - spin_lock_init(&panfrost_priv->mm_lock); - - /* 4G enough for now. can be 48-bit */ - drm_mm_init(&panfrost_priv->mm, SZ_32M >> PAGE_SHIFT, (SZ_4G - SZ_32M) >> PAGE_SHIFT); - panfrost_priv->mm.color_adjust = panfrost_drm_mm_color_adjust; - - ret = panfrost_mmu_pgtable_alloc(panfrost_priv); - if (ret) - goto err_pgtable; + panfrost_priv->mmu = panfrost_mmu_ctx_create(pfdev); + if (IS_ERR(panfrost_priv->mmu)) { + ret = PTR_ERR(panfrost_priv->mmu); + goto err_free; + } ret = panfrost_job_open(panfrost_priv); if (ret) @@ -506,9 +471,8 @@ panfrost_open(struct drm_device *dev, struct drm_file *file) return 0; err_job: - panfrost_mmu_pgtable_free(panfrost_priv); -err_pgtable: - drm_mm_takedown(&panfrost_priv->mm); + panfrost_mmu_ctx_put(panfrost_priv->mmu); +err_free: kfree(panfrost_priv); return ret; } @@ -521,8 +485,7 @@ panfrost_postclose(struct drm_device *dev, struct drm_file *file) panfrost_perfcnt_close(file); panfrost_job_close(panfrost_priv); - panfrost_mmu_pgtable_free(panfrost_priv); - drm_mm_takedown(&panfrost_priv->mm); + panfrost_mmu_ctx_put(panfrost_priv->mmu); kfree(panfrost_priv); } diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c index 3e0723bc36bd..23377481f4e3 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem.c @@ -60,7 +60,7 @@ panfrost_gem_mapping_get(struct panfrost_gem_object *bo, mutex_lock(&bo->mappings.lock); list_for_each_entry(iter, &bo->mappings.list, node) { - if (iter->mmu == &priv->mmu) { + if (iter->mmu == priv->mmu) { kref_get(&iter->refcount); mapping = iter; break; @@ -74,16 +74,13 @@ panfrost_gem_mapping_get(struct panfrost_gem_object *bo, static void panfrost_gem_teardown_mapping(struct panfrost_gem_mapping *mapping) { - struct panfrost_file_priv *priv; - if (mapping->active) panfrost_mmu_unmap(mapping); - priv = container_of(mapping->mmu, struct panfrost_file_priv, mmu); - spin_lock(&priv->mm_lock); + spin_lock(&mapping->mmu->mm_lock); if (drm_mm_node_allocated(&mapping->mmnode)) drm_mm_remove_node(&mapping->mmnode); - spin_unlock(&priv->mm_lock); + spin_unlock(&mapping->mmu->mm_lock); } static void panfrost_gem_mapping_release(struct kref *kref) @@ -94,6 +91,7 @@ static void panfrost_gem_mapping_release(struct kref *kref) panfrost_gem_teardown_mapping(mapping); drm_gem_object_put(&mapping->obj->base.base); + panfrost_mmu_ctx_put(mapping->mmu); kfree(mapping); } @@ -143,11 +141,11 @@ int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv) else align = size >= SZ_2M ? SZ_2M >> PAGE_SHIFT : 0; - mapping->mmu = &priv->mmu; - spin_lock(&priv->mm_lock); - ret = drm_mm_insert_node_generic(&priv->mm, &mapping->mmnode, + mapping->mmu = panfrost_mmu_ctx_get(priv->mmu); + spin_lock(&mapping->mmu->mm_lock); + ret = drm_mm_insert_node_generic(&mapping->mmu->mm, &mapping->mmnode, size >> PAGE_SHIFT, align, color, 0); - spin_unlock(&priv->mm_lock); + spin_unlock(&mapping->mmu->mm_lock); if (ret) goto err; @@ -176,7 +174,7 @@ void panfrost_gem_close(struct drm_gem_object *obj, struct drm_file *file_priv) mutex_lock(&bo->mappings.lock); list_for_each_entry(iter, &bo->mappings.list, node) { - if (iter->mmu == &priv->mmu) { + if (iter->mmu == priv->mmu) { mapping = iter; list_del(&iter->node); break; diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c index 0e70e27fd8c3..bbe628b306ee 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gpu.c +++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c @@ -33,7 +33,7 @@ static irqreturn_t panfrost_gpu_irq_handler(int irq, void *data) address |= gpu_read(pfdev, GPU_FAULT_ADDRESS_LO); dev_warn(pfdev->dev, "GPU Fault 0x%08x (%s) at 0x%016llx\n", - fault_status & 0xFF, panfrost_exception_name(pfdev, fault_status), + fault_status, panfrost_exception_name(fault_status & 0xFF), address); if (state & GPU_IRQ_MULTIPLE_FAULT) diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 2df3e999a38d..71a72fb50e6b 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -4,6 +4,7 @@ #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/io.h> +#include <linux/iopoll.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/dma-resv.h> @@ -25,17 +26,8 @@ #define job_write(dev, reg, data) writel(data, dev->iomem + (reg)) #define job_read(dev, reg) readl(dev->iomem + (reg)) -enum panfrost_queue_status { - PANFROST_QUEUE_STATUS_ACTIVE, - PANFROST_QUEUE_STATUS_STOPPED, - PANFROST_QUEUE_STATUS_STARTING, - PANFROST_QUEUE_STATUS_FAULT_PENDING, -}; - struct panfrost_queue_state { struct drm_gpu_scheduler sched; - atomic_t status; - struct mutex lock; u64 fence_context; u64 emit_seqno; }; @@ -43,6 +35,7 @@ struct panfrost_queue_state { struct panfrost_job_slot { struct panfrost_queue_state queue[NUM_JOB_SLOTS]; spinlock_t job_lock; + int irq; }; static struct panfrost_job * @@ -148,9 +141,52 @@ static void panfrost_job_write_affinity(struct panfrost_device *pfdev, job_write(pfdev, JS_AFFINITY_NEXT_HI(js), affinity >> 32); } +static u32 +panfrost_get_job_chain_flag(const struct panfrost_job *job) +{ + struct panfrost_fence *f = to_panfrost_fence(job->done_fence); + + if (!panfrost_has_hw_feature(job->pfdev, HW_FEATURE_JOBCHAIN_DISAMBIGUATION)) + return 0; + + return (f->seqno & 1) ? JS_CONFIG_JOB_CHAIN_FLAG : 0; +} + +static struct panfrost_job * +panfrost_dequeue_job(struct panfrost_device *pfdev, int slot) +{ + struct panfrost_job *job = pfdev->jobs[slot][0]; + + WARN_ON(!job); + pfdev->jobs[slot][0] = pfdev->jobs[slot][1]; + pfdev->jobs[slot][1] = NULL; + + return job; +} + +static unsigned int +panfrost_enqueue_job(struct panfrost_device *pfdev, int slot, + struct panfrost_job *job) +{ + if (WARN_ON(!job)) + return 0; + + if (!pfdev->jobs[slot][0]) { + pfdev->jobs[slot][0] = job; + return 0; + } + + WARN_ON(pfdev->jobs[slot][1]); + pfdev->jobs[slot][1] = job; + WARN_ON(panfrost_get_job_chain_flag(job) == + panfrost_get_job_chain_flag(pfdev->jobs[slot][0])); + return 1; +} + static void panfrost_job_hw_submit(struct panfrost_job *job, int js) { struct panfrost_device *pfdev = job->pfdev; + unsigned int subslot; u32 cfg; u64 jc_head = job->jc; int ret; @@ -165,7 +201,7 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js) return; } - cfg = panfrost_mmu_as_get(pfdev, &job->file_priv->mmu); + cfg = panfrost_mmu_as_get(pfdev, job->file_priv->mmu); job_write(pfdev, JS_HEAD_NEXT_LO(js), jc_head & 0xFFFFFFFF); job_write(pfdev, JS_HEAD_NEXT_HI(js), jc_head >> 32); @@ -176,7 +212,8 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js) * start */ cfg |= JS_CONFIG_THREAD_PRI(8) | JS_CONFIG_START_FLUSH_CLEAN_INVALIDATE | - JS_CONFIG_END_FLUSH_CLEAN_INVALIDATE; + JS_CONFIG_END_FLUSH_CLEAN_INVALIDATE | + panfrost_get_job_chain_flag(job); if (panfrost_has_hw_feature(pfdev, HW_FEATURE_FLUSH_REDUCTION)) cfg |= JS_CONFIG_ENABLE_FLUSH_REDUCTION; @@ -190,20 +227,33 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js) job_write(pfdev, JS_FLUSH_ID_NEXT(js), job->flush_id); /* GO ! */ - dev_dbg(pfdev->dev, "JS: Submitting atom %p to js[%d] with head=0x%llx", - job, js, jc_head); - job_write(pfdev, JS_COMMAND_NEXT(js), JS_COMMAND_START); + spin_lock(&pfdev->js->job_lock); + subslot = panfrost_enqueue_job(pfdev, js, job); + /* Don't queue the job if a reset is in progress */ + if (!atomic_read(&pfdev->reset.pending)) { + job_write(pfdev, JS_COMMAND_NEXT(js), JS_COMMAND_START); + dev_dbg(pfdev->dev, + "JS: Submitting atom %p to js[%d][%d] with head=0x%llx AS %d", + job, js, subslot, jc_head, cfg & 0xf); + } + spin_unlock(&pfdev->js->job_lock); } -static void panfrost_acquire_object_fences(struct drm_gem_object **bos, - int bo_count, - struct dma_fence **implicit_fences) +static int panfrost_acquire_object_fences(struct drm_gem_object **bos, + int bo_count, + struct xarray *deps) { - int i; + int i, ret; - for (i = 0; i < bo_count; i++) - implicit_fences[i] = dma_resv_get_excl_unlocked(bos[i]->resv); + for (i = 0; i < bo_count; i++) { + /* panfrost always uses write mode in its current uapi */ + ret = drm_gem_fence_array_add_implicit(deps, bos[i], true); + if (ret) + return ret; + } + + return 0; } static void panfrost_attach_object_fences(struct drm_gem_object **bos, @@ -224,14 +274,13 @@ int panfrost_job_push(struct panfrost_job *job) struct ww_acquire_ctx acquire_ctx; int ret = 0; - mutex_lock(&pfdev->sched_lock); ret = drm_gem_lock_reservations(job->bos, job->bo_count, &acquire_ctx); - if (ret) { - mutex_unlock(&pfdev->sched_lock); + if (ret) return ret; - } + + mutex_lock(&pfdev->sched_lock); ret = drm_sched_job_init(&job->base, entity, NULL); if (ret) { @@ -241,10 +290,14 @@ int panfrost_job_push(struct panfrost_job *job) job->render_done_fence = dma_fence_get(&job->base.s_fence->finished); - kref_get(&job->refcount); /* put by scheduler job completion */ + ret = panfrost_acquire_object_fences(job->bos, job->bo_count, + &job->deps); + if (ret) { + mutex_unlock(&pfdev->sched_lock); + goto unlock; + } - panfrost_acquire_object_fences(job->bos, job->bo_count, - job->implicit_fences); + kref_get(&job->refcount); /* put by scheduler job completion */ drm_sched_entity_push_job(&job->base, entity); @@ -263,18 +316,15 @@ static void panfrost_job_cleanup(struct kref *ref) { struct panfrost_job *job = container_of(ref, struct panfrost_job, refcount); + struct dma_fence *fence; + unsigned long index; unsigned int i; - if (job->in_fences) { - for (i = 0; i < job->in_fence_count; i++) - dma_fence_put(job->in_fences[i]); - kvfree(job->in_fences); - } - if (job->implicit_fences) { - for (i = 0; i < job->bo_count; i++) - dma_fence_put(job->implicit_fences[i]); - kvfree(job->implicit_fences); + xa_for_each(&job->deps, index, fence) { + dma_fence_put(fence); } + xa_destroy(&job->deps); + dma_fence_put(job->done_fence); dma_fence_put(job->render_done_fence); @@ -317,26 +367,9 @@ static struct dma_fence *panfrost_job_dependency(struct drm_sched_job *sched_job struct drm_sched_entity *s_entity) { struct panfrost_job *job = to_panfrost_job(sched_job); - struct dma_fence *fence; - unsigned int i; - /* Explicit fences */ - for (i = 0; i < job->in_fence_count; i++) { - if (job->in_fences[i]) { - fence = job->in_fences[i]; - job->in_fences[i] = NULL; - return fence; - } - } - - /* Implicit fences, max. one per BO */ - for (i = 0; i < job->bo_count; i++) { - if (job->implicit_fences[i]) { - fence = job->implicit_fences[i]; - job->implicit_fences[i] = NULL; - return fence; - } - } + if (!xa_empty(&job->deps)) + return xa_erase(&job->deps, job->last_dep++); return NULL; } @@ -351,11 +384,15 @@ static struct dma_fence *panfrost_job_run(struct drm_sched_job *sched_job) if (unlikely(job->base.s_fence->finished.error)) return NULL; - pfdev->jobs[slot] = job; + /* Nothing to execute: can happen if the job has finished while + * we were resetting the GPU. + */ + if (!job->jc) + return NULL; fence = panfrost_fence_create(pfdev, slot); if (IS_ERR(fence)) - return NULL; + return fence; if (job->done_fence) dma_fence_put(job->done_fence); @@ -379,57 +416,314 @@ void panfrost_job_enable_interrupts(struct panfrost_device *pfdev) job_write(pfdev, JOB_INT_MASK, irq_mask); } -static bool panfrost_scheduler_stop(struct panfrost_queue_state *queue, - struct drm_sched_job *bad) +static void panfrost_job_handle_err(struct panfrost_device *pfdev, + struct panfrost_job *job, + unsigned int js) { - enum panfrost_queue_status old_status; - bool stopped = false; + u32 js_status = job_read(pfdev, JS_STATUS(js)); + const char *exception_name = panfrost_exception_name(js_status); + bool signal_fence = true; + + if (!panfrost_exception_is_fault(js_status)) { + dev_dbg(pfdev->dev, "js event, js=%d, status=%s, head=0x%x, tail=0x%x", + js, exception_name, + job_read(pfdev, JS_HEAD_LO(js)), + job_read(pfdev, JS_TAIL_LO(js))); + } else { + dev_err(pfdev->dev, "js fault, js=%d, status=%s, head=0x%x, tail=0x%x", + js, exception_name, + job_read(pfdev, JS_HEAD_LO(js)), + job_read(pfdev, JS_TAIL_LO(js))); + } - mutex_lock(&queue->lock); - old_status = atomic_xchg(&queue->status, - PANFROST_QUEUE_STATUS_STOPPED); - if (old_status == PANFROST_QUEUE_STATUS_STOPPED) - goto out; + if (js_status == DRM_PANFROST_EXCEPTION_STOPPED) { + /* Update the job head so we can resume */ + job->jc = job_read(pfdev, JS_TAIL_LO(js)) | + ((u64)job_read(pfdev, JS_TAIL_HI(js)) << 32); + + /* The job will be resumed, don't signal the fence */ + signal_fence = false; + } else if (js_status == DRM_PANFROST_EXCEPTION_TERMINATED) { + /* Job has been hard-stopped, flag it as canceled */ + dma_fence_set_error(job->done_fence, -ECANCELED); + job->jc = 0; + } else if (panfrost_exception_is_fault(js_status)) { + /* We might want to provide finer-grained error code based on + * the exception type, but unconditionally setting to EINVAL + * is good enough for now. + */ + dma_fence_set_error(job->done_fence, -EINVAL); + job->jc = 0; + } - WARN_ON(old_status != PANFROST_QUEUE_STATUS_ACTIVE); - drm_sched_stop(&queue->sched, bad); - if (bad) - drm_sched_increase_karma(bad); + panfrost_mmu_as_put(pfdev, job->file_priv->mmu); + panfrost_devfreq_record_idle(&pfdev->pfdevfreq); - stopped = true; + if (signal_fence) + dma_fence_signal_locked(job->done_fence); - /* - * Set the timeout to max so the timer doesn't get started - * when we return from the timeout handler (restored in - * panfrost_scheduler_start()). + pm_runtime_put_autosuspend(pfdev->dev); + + if (panfrost_exception_needs_reset(pfdev, js_status)) { + atomic_set(&pfdev->reset.pending, 1); + drm_sched_fault(&pfdev->js->queue[js].sched); + } +} + +static void panfrost_job_handle_done(struct panfrost_device *pfdev, + struct panfrost_job *job) +{ + /* Set ->jc to 0 to avoid re-submitting an already finished job (can + * happen when we receive the DONE interrupt while doing a GPU reset). + */ + job->jc = 0; + panfrost_mmu_as_put(pfdev, job->file_priv->mmu); + panfrost_devfreq_record_idle(&pfdev->pfdevfreq); + + dma_fence_signal_locked(job->done_fence); + pm_runtime_put_autosuspend(pfdev->dev); +} + +static void panfrost_job_handle_irq(struct panfrost_device *pfdev, u32 status) +{ + struct panfrost_job *done[NUM_JOB_SLOTS][2] = {}; + struct panfrost_job *failed[NUM_JOB_SLOTS] = {}; + u32 js_state = 0, js_events = 0; + unsigned int i, j; + + /* First we collect all failed/done jobs. */ + while (status) { + u32 js_state_mask = 0; + + for (j = 0; j < NUM_JOB_SLOTS; j++) { + if (status & MK_JS_MASK(j)) + js_state_mask |= MK_JS_MASK(j); + + if (status & JOB_INT_MASK_DONE(j)) { + if (done[j][0]) + done[j][1] = panfrost_dequeue_job(pfdev, j); + else + done[j][0] = panfrost_dequeue_job(pfdev, j); + } + + if (status & JOB_INT_MASK_ERR(j)) { + /* Cancel the next submission. Will be submitted + * after we're done handling this failure if + * there's no reset pending. + */ + job_write(pfdev, JS_COMMAND_NEXT(j), JS_COMMAND_NOP); + failed[j] = panfrost_dequeue_job(pfdev, j); + } + } + + /* JS_STATE is sampled when JOB_INT_CLEAR is written. + * For each BIT(slot) or BIT(slot + 16) bit written to + * JOB_INT_CLEAR, the corresponding bits in JS_STATE + * (BIT(slot) and BIT(slot + 16)) are updated, but this + * is racy. If we only have one job done at the time we + * read JOB_INT_RAWSTAT but the second job fails before we + * clear the status, we end up with a status containing + * only the DONE bit and consider both jobs as DONE since + * JS_STATE reports both NEXT and CURRENT as inactive. + * To prevent that, let's repeat this clear+read steps + * until status is 0. + */ + job_write(pfdev, JOB_INT_CLEAR, status); + js_state &= ~js_state_mask; + js_state |= job_read(pfdev, JOB_INT_JS_STATE) & js_state_mask; + js_events |= status; + status = job_read(pfdev, JOB_INT_RAWSTAT); + } + + /* Then we handle the dequeued jobs. */ + for (j = 0; j < NUM_JOB_SLOTS; j++) { + if (!(js_events & MK_JS_MASK(j))) + continue; + + if (failed[j]) { + panfrost_job_handle_err(pfdev, failed[j], j); + } else if (pfdev->jobs[j][0] && !(js_state & MK_JS_MASK(j))) { + /* When the current job doesn't fail, the JM dequeues + * the next job without waiting for an ACK, this means + * we can have 2 jobs dequeued and only catch the + * interrupt when the second one is done. If both slots + * are inactive, but one job remains in pfdev->jobs[j], + * consider it done. Of course that doesn't apply if a + * failure happened since we cancelled execution of the + * job in _NEXT (see above). + */ + if (WARN_ON(!done[j][0])) + done[j][0] = panfrost_dequeue_job(pfdev, j); + else + done[j][1] = panfrost_dequeue_job(pfdev, j); + } + + for (i = 0; i < ARRAY_SIZE(done[0]) && done[j][i]; i++) + panfrost_job_handle_done(pfdev, done[j][i]); + } + + /* And finally we requeue jobs that were waiting in the second slot + * and have been stopped if we detected a failure on the first slot. */ - queue->sched.timeout = MAX_SCHEDULE_TIMEOUT; + for (j = 0; j < NUM_JOB_SLOTS; j++) { + if (!(js_events & MK_JS_MASK(j))) + continue; + + if (!failed[j] || !pfdev->jobs[j][0]) + continue; + + if (pfdev->jobs[j][0]->jc == 0) { + /* The job was cancelled, signal the fence now */ + struct panfrost_job *canceled = panfrost_dequeue_job(pfdev, j); + + dma_fence_set_error(canceled->done_fence, -ECANCELED); + panfrost_job_handle_done(pfdev, canceled); + } else if (!atomic_read(&pfdev->reset.pending)) { + /* Requeue the job we removed if no reset is pending */ + job_write(pfdev, JS_COMMAND_NEXT(j), JS_COMMAND_START); + } + } +} -out: - mutex_unlock(&queue->lock); +static void panfrost_job_handle_irqs(struct panfrost_device *pfdev) +{ + u32 status = job_read(pfdev, JOB_INT_RAWSTAT); + + while (status) { + pm_runtime_mark_last_busy(pfdev->dev); - return stopped; + spin_lock(&pfdev->js->job_lock); + panfrost_job_handle_irq(pfdev, status); + spin_unlock(&pfdev->js->job_lock); + status = job_read(pfdev, JOB_INT_RAWSTAT); + } } -static void panfrost_scheduler_start(struct panfrost_queue_state *queue) +static u32 panfrost_active_slots(struct panfrost_device *pfdev, + u32 *js_state_mask, u32 js_state) { - enum panfrost_queue_status old_status; + u32 rawstat; - mutex_lock(&queue->lock); - old_status = atomic_xchg(&queue->status, - PANFROST_QUEUE_STATUS_STARTING); - WARN_ON(old_status != PANFROST_QUEUE_STATUS_STOPPED); + if (!(js_state & *js_state_mask)) + return 0; - /* Restore the original timeout before starting the scheduler. */ - queue->sched.timeout = msecs_to_jiffies(JOB_TIMEOUT_MS); - drm_sched_resubmit_jobs(&queue->sched); - drm_sched_start(&queue->sched, true); - old_status = atomic_xchg(&queue->status, - PANFROST_QUEUE_STATUS_ACTIVE); - if (old_status == PANFROST_QUEUE_STATUS_FAULT_PENDING) - drm_sched_fault(&queue->sched); + rawstat = job_read(pfdev, JOB_INT_RAWSTAT); + if (rawstat) { + unsigned int i; + + for (i = 0; i < NUM_JOB_SLOTS; i++) { + if (rawstat & MK_JS_MASK(i)) + *js_state_mask &= ~MK_JS_MASK(i); + } + } - mutex_unlock(&queue->lock); + return js_state & *js_state_mask; +} + +static void +panfrost_reset(struct panfrost_device *pfdev, + struct drm_sched_job *bad) +{ + u32 js_state, js_state_mask = 0xffffffff; + unsigned int i, j; + bool cookie; + int ret; + + if (!atomic_read(&pfdev->reset.pending)) + return; + + /* Stop the schedulers. + * + * FIXME: We temporarily get out of the dma_fence_signalling section + * because the cleanup path generate lockdep splats when taking locks + * to release job resources. We should rework the code to follow this + * pattern: + * + * try_lock + * if (locked) + * release + * else + * schedule_work_to_release_later + */ + for (i = 0; i < NUM_JOB_SLOTS; i++) + drm_sched_stop(&pfdev->js->queue[i].sched, bad); + + cookie = dma_fence_begin_signalling(); + + if (bad) + drm_sched_increase_karma(bad); + + /* Mask job interrupts and synchronize to make sure we won't be + * interrupted during our reset. + */ + job_write(pfdev, JOB_INT_MASK, 0); + synchronize_irq(pfdev->js->irq); + + for (i = 0; i < NUM_JOB_SLOTS; i++) { + /* Cancel the next job and soft-stop the running job. */ + job_write(pfdev, JS_COMMAND_NEXT(i), JS_COMMAND_NOP); + job_write(pfdev, JS_COMMAND(i), JS_COMMAND_SOFT_STOP); + } + + /* Wait at most 10ms for soft-stops to complete */ + ret = readl_poll_timeout(pfdev->iomem + JOB_INT_JS_STATE, js_state, + !panfrost_active_slots(pfdev, &js_state_mask, js_state), + 10, 10000); + + if (ret) + dev_err(pfdev->dev, "Soft-stop failed\n"); + + /* Handle the remaining interrupts before we reset. */ + panfrost_job_handle_irqs(pfdev); + + /* Remaining interrupts have been handled, but we might still have + * stuck jobs. Let's make sure the PM counters stay balanced by + * manually calling pm_runtime_put_noidle() and + * panfrost_devfreq_record_idle() for each stuck job. + */ + spin_lock(&pfdev->js->job_lock); + for (i = 0; i < NUM_JOB_SLOTS; i++) { + for (j = 0; j < ARRAY_SIZE(pfdev->jobs[0]) && pfdev->jobs[i][j]; j++) { + pm_runtime_put_noidle(pfdev->dev); + panfrost_devfreq_record_idle(&pfdev->pfdevfreq); + } + } + memset(pfdev->jobs, 0, sizeof(pfdev->jobs)); + spin_unlock(&pfdev->js->job_lock); + + /* Proceed with reset now. */ + panfrost_device_reset(pfdev); + + /* panfrost_device_reset() unmasks job interrupts, but we want to + * keep them masked a bit longer. + */ + job_write(pfdev, JOB_INT_MASK, 0); + + /* GPU has been reset, we can clear the reset pending bit. */ + atomic_set(&pfdev->reset.pending, 0); + + /* Now resubmit jobs that were previously queued but didn't have a + * chance to finish. + * FIXME: We temporarily get out of the DMA fence signalling section + * while resubmitting jobs because the job submission logic will + * allocate memory with the GFP_KERNEL flag which can trigger memory + * reclaim and exposes a lock ordering issue. + */ + dma_fence_end_signalling(cookie); + for (i = 0; i < NUM_JOB_SLOTS; i++) + drm_sched_resubmit_jobs(&pfdev->js->queue[i].sched); + cookie = dma_fence_begin_signalling(); + + /* Restart the schedulers */ + for (i = 0; i < NUM_JOB_SLOTS; i++) + drm_sched_start(&pfdev->js->queue[i].sched, true); + + /* Re-enable job interrupts now that everything has been restarted. */ + job_write(pfdev, JOB_INT_MASK, + GENMASK(16 + NUM_JOB_SLOTS - 1, 16) | + GENMASK(NUM_JOB_SLOTS - 1, 0)); + + dma_fence_end_signalling(cookie); } static enum drm_gpu_sched_stat panfrost_job_timedout(struct drm_sched_job @@ -454,17 +748,20 @@ static enum drm_gpu_sched_stat panfrost_job_timedout(struct drm_sched_job job_read(pfdev, JS_TAIL_LO(js)), sched_job); - /* Scheduler is already stopped, nothing to do. */ - if (!panfrost_scheduler_stop(&pfdev->js->queue[js], sched_job)) - return DRM_GPU_SCHED_STAT_NOMINAL; - - /* Schedule a reset if there's no reset in progress. */ - if (!atomic_xchg(&pfdev->reset.pending, 1)) - schedule_work(&pfdev->reset.work); + atomic_set(&pfdev->reset.pending, 1); + panfrost_reset(pfdev, sched_job); return DRM_GPU_SCHED_STAT_NOMINAL; } +static void panfrost_reset_work(struct work_struct *work) +{ + struct panfrost_device *pfdev; + + pfdev = container_of(work, struct panfrost_device, reset.work); + panfrost_reset(pfdev, NULL); +} + static const struct drm_sched_backend_ops panfrost_sched_ops = { .dependency = panfrost_job_dependency, .run_job = panfrost_job_run, @@ -472,161 +769,75 @@ static const struct drm_sched_backend_ops panfrost_sched_ops = { .free_job = panfrost_job_free }; -static irqreturn_t panfrost_job_irq_handler(int irq, void *data) +static irqreturn_t panfrost_job_irq_handler_thread(int irq, void *data) { struct panfrost_device *pfdev = data; - u32 status = job_read(pfdev, JOB_INT_STAT); - int j; - - dev_dbg(pfdev->dev, "jobslot irq status=%x\n", status); - - if (!status) - return IRQ_NONE; - - pm_runtime_mark_last_busy(pfdev->dev); - - for (j = 0; status; j++) { - u32 mask = MK_JS_MASK(j); - - if (!(status & mask)) - continue; - - job_write(pfdev, JOB_INT_CLEAR, mask); - - if (status & JOB_INT_MASK_ERR(j)) { - enum panfrost_queue_status old_status; - - job_write(pfdev, JS_COMMAND_NEXT(j), JS_COMMAND_NOP); - - dev_err(pfdev->dev, "js fault, js=%d, status=%s, head=0x%x, tail=0x%x", - j, - panfrost_exception_name(pfdev, job_read(pfdev, JS_STATUS(j))), - job_read(pfdev, JS_HEAD_LO(j)), - job_read(pfdev, JS_TAIL_LO(j))); - - /* - * When the queue is being restarted we don't report - * faults directly to avoid races between the timeout - * and reset handlers. panfrost_scheduler_start() will - * call drm_sched_fault() after the queue has been - * started if status == FAULT_PENDING. - */ - old_status = atomic_cmpxchg(&pfdev->js->queue[j].status, - PANFROST_QUEUE_STATUS_STARTING, - PANFROST_QUEUE_STATUS_FAULT_PENDING); - if (old_status == PANFROST_QUEUE_STATUS_ACTIVE) - drm_sched_fault(&pfdev->js->queue[j].sched); - } - - if (status & JOB_INT_MASK_DONE(j)) { - struct panfrost_job *job; - - spin_lock(&pfdev->js->job_lock); - job = pfdev->jobs[j]; - /* Only NULL if job timeout occurred */ - if (job) { - pfdev->jobs[j] = NULL; - - panfrost_mmu_as_put(pfdev, &job->file_priv->mmu); - panfrost_devfreq_record_idle(&pfdev->pfdevfreq); - - dma_fence_signal_locked(job->done_fence); - pm_runtime_put_autosuspend(pfdev->dev); - } - spin_unlock(&pfdev->js->job_lock); - } - - status &= ~mask; - } + panfrost_job_handle_irqs(pfdev); + job_write(pfdev, JOB_INT_MASK, + GENMASK(16 + NUM_JOB_SLOTS - 1, 16) | + GENMASK(NUM_JOB_SLOTS - 1, 0)); return IRQ_HANDLED; } -static void panfrost_reset(struct work_struct *work) +static irqreturn_t panfrost_job_irq_handler(int irq, void *data) { - struct panfrost_device *pfdev = container_of(work, - struct panfrost_device, - reset.work); - unsigned long flags; - unsigned int i; - bool cookie; - - cookie = dma_fence_begin_signalling(); - for (i = 0; i < NUM_JOB_SLOTS; i++) { - /* - * We want pending timeouts to be handled before we attempt - * to stop the scheduler. If we don't do that and the timeout - * handler is in flight, it might have removed the bad job - * from the list, and we'll lose this job if the reset handler - * enters the critical section in panfrost_scheduler_stop() - * before the timeout handler. - * - * Timeout is set to MAX_SCHEDULE_TIMEOUT - 1 because we need - * something big enough to make sure the timer will not expire - * before we manage to stop the scheduler, but we can't use - * MAX_SCHEDULE_TIMEOUT because drm_sched_get_cleanup_job() - * considers that as 'timer is not running' and will dequeue - * the job without making sure the timeout handler is not - * running. - */ - pfdev->js->queue[i].sched.timeout = MAX_SCHEDULE_TIMEOUT - 1; - cancel_delayed_work_sync(&pfdev->js->queue[i].sched.work_tdr); - panfrost_scheduler_stop(&pfdev->js->queue[i], NULL); - } - - /* All timers have been stopped, we can safely reset the pending state. */ - atomic_set(&pfdev->reset.pending, 0); - - spin_lock_irqsave(&pfdev->js->job_lock, flags); - for (i = 0; i < NUM_JOB_SLOTS; i++) { - if (pfdev->jobs[i]) { - pm_runtime_put_noidle(pfdev->dev); - panfrost_devfreq_record_idle(&pfdev->pfdevfreq); - pfdev->jobs[i] = NULL; - } - } - spin_unlock_irqrestore(&pfdev->js->job_lock, flags); - - panfrost_device_reset(pfdev); + struct panfrost_device *pfdev = data; + u32 status = job_read(pfdev, JOB_INT_STAT); - for (i = 0; i < NUM_JOB_SLOTS; i++) - panfrost_scheduler_start(&pfdev->js->queue[i]); + if (!status) + return IRQ_NONE; - dma_fence_end_signalling(cookie); + job_write(pfdev, JOB_INT_MASK, 0); + return IRQ_WAKE_THREAD; } int panfrost_job_init(struct panfrost_device *pfdev) { struct panfrost_job_slot *js; - int ret, j, irq; + unsigned int nentries = 2; + int ret, j; - INIT_WORK(&pfdev->reset.work, panfrost_reset); + /* All GPUs have two entries per queue, but without jobchain + * disambiguation stopping the right job in the close path is tricky, + * so let's just advertise one entry in that case. + */ + if (!panfrost_has_hw_feature(pfdev, HW_FEATURE_JOBCHAIN_DISAMBIGUATION)) + nentries = 1; pfdev->js = js = devm_kzalloc(pfdev->dev, sizeof(*js), GFP_KERNEL); if (!js) return -ENOMEM; + INIT_WORK(&pfdev->reset.work, panfrost_reset_work); spin_lock_init(&js->job_lock); - irq = platform_get_irq_byname(to_platform_device(pfdev->dev), "job"); - if (irq <= 0) + js->irq = platform_get_irq_byname(to_platform_device(pfdev->dev), "job"); + if (js->irq <= 0) return -ENODEV; - ret = devm_request_irq(pfdev->dev, irq, panfrost_job_irq_handler, - IRQF_SHARED, KBUILD_MODNAME "-job", pfdev); + ret = devm_request_threaded_irq(pfdev->dev, js->irq, + panfrost_job_irq_handler, + panfrost_job_irq_handler_thread, + IRQF_SHARED, KBUILD_MODNAME "-job", + pfdev); if (ret) { dev_err(pfdev->dev, "failed to request job irq"); return ret; } - for (j = 0; j < NUM_JOB_SLOTS; j++) { - mutex_init(&js->queue[j].lock); + pfdev->reset.wq = alloc_ordered_workqueue("panfrost-reset", 0); + if (!pfdev->reset.wq) + return -ENOMEM; + for (j = 0; j < NUM_JOB_SLOTS; j++) { js->queue[j].fence_context = dma_fence_context_alloc(1); ret = drm_sched_init(&js->queue[j].sched, &panfrost_sched_ops, - 1, 0, msecs_to_jiffies(JOB_TIMEOUT_MS), + nentries, 0, + msecs_to_jiffies(JOB_TIMEOUT_MS), + pfdev->reset.wq, NULL, "pan_js"); if (ret) { dev_err(pfdev->dev, "Failed to create scheduler: %d.", ret); @@ -642,6 +853,7 @@ err_sched: for (j--; j >= 0; j--) drm_sched_fini(&js->queue[j].sched); + destroy_workqueue(pfdev->reset.wq); return ret; } @@ -654,9 +866,10 @@ void panfrost_job_fini(struct panfrost_device *pfdev) for (j = 0; j < NUM_JOB_SLOTS; j++) { drm_sched_fini(&js->queue[j].sched); - mutex_destroy(&js->queue[j].lock); } + cancel_work_sync(&pfdev->reset.work); + destroy_workqueue(pfdev->reset.wq); } int panfrost_job_open(struct panfrost_file_priv *panfrost_priv) @@ -679,10 +892,46 @@ int panfrost_job_open(struct panfrost_file_priv *panfrost_priv) void panfrost_job_close(struct panfrost_file_priv *panfrost_priv) { + struct panfrost_device *pfdev = panfrost_priv->pfdev; int i; for (i = 0; i < NUM_JOB_SLOTS; i++) drm_sched_entity_destroy(&panfrost_priv->sched_entity[i]); + + /* Kill in-flight jobs */ + spin_lock(&pfdev->js->job_lock); + for (i = 0; i < NUM_JOB_SLOTS; i++) { + struct drm_sched_entity *entity = &panfrost_priv->sched_entity[i]; + int j; + + for (j = ARRAY_SIZE(pfdev->jobs[0]) - 1; j >= 0; j--) { + struct panfrost_job *job = pfdev->jobs[i][j]; + u32 cmd; + + if (!job || job->base.entity != entity) + continue; + + if (j == 1) { + /* Try to cancel the job before it starts */ + job_write(pfdev, JS_COMMAND_NEXT(i), JS_COMMAND_NOP); + /* Reset the job head so it doesn't get restarted if + * the job in the first slot failed. + */ + job->jc = 0; + } + + if (panfrost_has_hw_feature(pfdev, HW_FEATURE_JOBCHAIN_DISAMBIGUATION)) { + cmd = panfrost_get_job_chain_flag(job) ? + JS_COMMAND_HARD_STOP_1 : + JS_COMMAND_HARD_STOP_0; + } else { + cmd = JS_COMMAND_HARD_STOP; + } + + job_write(pfdev, JS_COMMAND(i), cmd); + } + } + spin_unlock(&pfdev->js->job_lock); } int panfrost_job_is_idle(struct panfrost_device *pfdev) diff --git a/drivers/gpu/drm/panfrost/panfrost_job.h b/drivers/gpu/drm/panfrost/panfrost_job.h index bbd3ba97ff67..82306a03b57e 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.h +++ b/drivers/gpu/drm/panfrost/panfrost_job.h @@ -19,9 +19,9 @@ struct panfrost_job { struct panfrost_device *pfdev; struct panfrost_file_priv *file_priv; - /* Optional fences userspace can pass in for the job to depend on. */ - struct dma_fence **in_fences; - u32 in_fence_count; + /* Contains both explicit and implicit fences */ + struct xarray deps; + unsigned long last_dep; /* Fence to be signaled by IRQ handler when the job is complete. */ struct dma_fence *done_fence; @@ -30,8 +30,6 @@ struct panfrost_job { __u32 requirements; __u32 flush_id; - /* Exclusive fences we have taken from the BOs to wait for */ - struct dma_fence **implicit_fences; struct panfrost_gem_mapping **mappings; struct drm_gem_object **bos; u32 bo_count; diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index 0581186ebfb3..0da5b3100ab1 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright 2019 Linaro, Ltd, Rob Herring <robh@kernel.org> */ + +#include <drm/panfrost_drm.h> + #include <linux/atomic.h> #include <linux/bitfield.h> #include <linux/delay.h> @@ -31,10 +34,13 @@ static int wait_ready(struct panfrost_device *pfdev, u32 as_nr) /* Wait for the MMU status to indicate there is no active command, in * case one is pending. */ ret = readl_relaxed_poll_timeout_atomic(pfdev->iomem + AS_STATUS(as_nr), - val, !(val & AS_STATUS_AS_ACTIVE), 10, 1000); + val, !(val & AS_STATUS_AS_ACTIVE), 10, 100000); - if (ret) + if (ret) { + /* The GPU hung, let's trigger a reset */ + panfrost_device_schedule_reset(pfdev); dev_err(pfdev->dev, "AS_ACTIVE bit stuck\n"); + } return ret; } @@ -151,6 +157,7 @@ u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu) as = mmu->as; if (as >= 0) { int en = atomic_inc_return(&mmu->as_count); + u32 mask = BIT(as) | BIT(16 + as); /* * AS can be retained by active jobs or a perfcnt context, @@ -159,6 +166,18 @@ u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu) WARN_ON(en >= (NUM_JOB_SLOTS + 1)); list_move(&mmu->list, &pfdev->as_lru_list); + + if (pfdev->as_faulty_mask & mask) { + /* Unhandled pagefault on this AS, the MMU was + * disabled. We need to re-enable the MMU after + * clearing+unmasking the AS interrupts. + */ + mmu_write(pfdev, MMU_INT_CLEAR, mask); + mmu_write(pfdev, MMU_INT_MASK, ~pfdev->as_faulty_mask); + pfdev->as_faulty_mask &= ~mask; + panfrost_mmu_enable(pfdev, mmu); + } + goto out; } @@ -208,6 +227,7 @@ void panfrost_mmu_reset(struct panfrost_device *pfdev) spin_lock(&pfdev->as_lock); pfdev->as_alloc_mask = 0; + pfdev->as_faulty_mask = 0; list_for_each_entry_safe(mmu, mmu_tmp, &pfdev->as_lru_list, list) { mmu->as = -1; @@ -337,7 +357,7 @@ static void mmu_tlb_inv_context_s1(void *cookie) static void mmu_tlb_sync_context(void *cookie) { - //struct panfrost_device *pfdev = cookie; + //struct panfrost_mmu *mmu = cookie; // TODO: Wait 1000 GPU cycles for HW_ISSUE_6367/T60X } @@ -352,57 +372,10 @@ static const struct iommu_flush_ops mmu_tlb_ops = { .tlb_flush_walk = mmu_tlb_flush_walk, }; -int panfrost_mmu_pgtable_alloc(struct panfrost_file_priv *priv) -{ - struct panfrost_mmu *mmu = &priv->mmu; - struct panfrost_device *pfdev = priv->pfdev; - - INIT_LIST_HEAD(&mmu->list); - mmu->as = -1; - - mmu->pgtbl_cfg = (struct io_pgtable_cfg) { - .pgsize_bitmap = SZ_4K | SZ_2M, - .ias = FIELD_GET(0xff, pfdev->features.mmu_features), - .oas = FIELD_GET(0xff00, pfdev->features.mmu_features), - .coherent_walk = pfdev->coherent, - .tlb = &mmu_tlb_ops, - .iommu_dev = pfdev->dev, - }; - - mmu->pgtbl_ops = alloc_io_pgtable_ops(ARM_MALI_LPAE, &mmu->pgtbl_cfg, - priv); - if (!mmu->pgtbl_ops) - return -EINVAL; - - return 0; -} - -void panfrost_mmu_pgtable_free(struct panfrost_file_priv *priv) -{ - struct panfrost_device *pfdev = priv->pfdev; - struct panfrost_mmu *mmu = &priv->mmu; - - spin_lock(&pfdev->as_lock); - if (mmu->as >= 0) { - pm_runtime_get_noresume(pfdev->dev); - if (pm_runtime_active(pfdev->dev)) - panfrost_mmu_disable(pfdev, mmu->as); - pm_runtime_put_autosuspend(pfdev->dev); - - clear_bit(mmu->as, &pfdev->as_alloc_mask); - clear_bit(mmu->as, &pfdev->as_in_use_mask); - list_del(&mmu->list); - } - spin_unlock(&pfdev->as_lock); - - free_io_pgtable_ops(mmu->pgtbl_ops); -} - static struct panfrost_gem_mapping * addr_to_mapping(struct panfrost_device *pfdev, int as, u64 addr) { struct panfrost_gem_mapping *mapping = NULL; - struct panfrost_file_priv *priv; struct drm_mm_node *node; u64 offset = addr >> PAGE_SHIFT; struct panfrost_mmu *mmu; @@ -415,11 +388,10 @@ addr_to_mapping(struct panfrost_device *pfdev, int as, u64 addr) goto out; found_mmu: - priv = container_of(mmu, struct panfrost_file_priv, mmu); - spin_lock(&priv->mm_lock); + spin_lock(&mmu->mm_lock); - drm_mm_for_each_node(node, &priv->mm) { + drm_mm_for_each_node(node, &mmu->mm) { if (offset >= node->start && offset < (node->start + node->size)) { mapping = drm_mm_node_to_panfrost_mapping(node); @@ -429,7 +401,7 @@ found_mmu: } } - spin_unlock(&priv->mm_lock); + spin_unlock(&mmu->mm_lock); out: spin_unlock(&pfdev->as_lock); return mapping; @@ -542,6 +514,107 @@ err_bo: return ret; } +static void panfrost_mmu_release_ctx(struct kref *kref) +{ + struct panfrost_mmu *mmu = container_of(kref, struct panfrost_mmu, + refcount); + struct panfrost_device *pfdev = mmu->pfdev; + + spin_lock(&pfdev->as_lock); + if (mmu->as >= 0) { + pm_runtime_get_noresume(pfdev->dev); + if (pm_runtime_active(pfdev->dev)) + panfrost_mmu_disable(pfdev, mmu->as); + pm_runtime_put_autosuspend(pfdev->dev); + + clear_bit(mmu->as, &pfdev->as_alloc_mask); + clear_bit(mmu->as, &pfdev->as_in_use_mask); + list_del(&mmu->list); + } + spin_unlock(&pfdev->as_lock); + + free_io_pgtable_ops(mmu->pgtbl_ops); + drm_mm_takedown(&mmu->mm); + kfree(mmu); +} + +void panfrost_mmu_ctx_put(struct panfrost_mmu *mmu) +{ + kref_put(&mmu->refcount, panfrost_mmu_release_ctx); +} + +struct panfrost_mmu *panfrost_mmu_ctx_get(struct panfrost_mmu *mmu) +{ + kref_get(&mmu->refcount); + + return mmu; +} + +#define PFN_4G (SZ_4G >> PAGE_SHIFT) +#define PFN_4G_MASK (PFN_4G - 1) +#define PFN_16M (SZ_16M >> PAGE_SHIFT) + +static void panfrost_drm_mm_color_adjust(const struct drm_mm_node *node, + unsigned long color, + u64 *start, u64 *end) +{ + /* Executable buffers can't start or end on a 4GB boundary */ + if (!(color & PANFROST_BO_NOEXEC)) { + u64 next_seg; + + if ((*start & PFN_4G_MASK) == 0) + (*start)++; + + if ((*end & PFN_4G_MASK) == 0) + (*end)--; + + next_seg = ALIGN(*start, PFN_4G); + if (next_seg - *start <= PFN_16M) + *start = next_seg + 1; + + *end = min(*end, ALIGN(*start, PFN_4G) - 1); + } +} + +struct panfrost_mmu *panfrost_mmu_ctx_create(struct panfrost_device *pfdev) +{ + struct panfrost_mmu *mmu; + + mmu = kzalloc(sizeof(*mmu), GFP_KERNEL); + if (!mmu) + return ERR_PTR(-ENOMEM); + + mmu->pfdev = pfdev; + spin_lock_init(&mmu->mm_lock); + + /* 4G enough for now. can be 48-bit */ + drm_mm_init(&mmu->mm, SZ_32M >> PAGE_SHIFT, (SZ_4G - SZ_32M) >> PAGE_SHIFT); + mmu->mm.color_adjust = panfrost_drm_mm_color_adjust; + + INIT_LIST_HEAD(&mmu->list); + mmu->as = -1; + + mmu->pgtbl_cfg = (struct io_pgtable_cfg) { + .pgsize_bitmap = SZ_4K | SZ_2M, + .ias = FIELD_GET(0xff, pfdev->features.mmu_features), + .oas = FIELD_GET(0xff00, pfdev->features.mmu_features), + .coherent_walk = pfdev->coherent, + .tlb = &mmu_tlb_ops, + .iommu_dev = pfdev->dev, + }; + + mmu->pgtbl_ops = alloc_io_pgtable_ops(ARM_MALI_LPAE, &mmu->pgtbl_cfg, + mmu); + if (!mmu->pgtbl_ops) { + kfree(mmu); + return ERR_PTR(-EINVAL); + } + + kref_init(&mmu->refcount); + + return mmu; +} + static const char *access_type_name(struct panfrost_device *pfdev, u32 fault_status) { @@ -605,7 +678,7 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data) if ((status & mask) == BIT(as) && (exception_type & 0xF8) == 0xC0) ret = panfrost_mmu_map_fault_addr(pfdev, as, addr); - if (ret) + if (ret) { /* terminal fault, print info about the fault */ dev_err(pfdev->dev, "Unhandled Page fault in AS%d at VA 0x%016llX\n" @@ -619,18 +692,32 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data) "TODO", fault_status, (fault_status & (1 << 10) ? "DECODER FAULT" : "SLAVE FAULT"), - exception_type, panfrost_exception_name(pfdev, exception_type), + exception_type, panfrost_exception_name(exception_type), access_type, access_type_name(pfdev, fault_status), source_id); + spin_lock(&pfdev->as_lock); + /* Ignore MMU interrupts on this AS until it's been + * re-enabled. + */ + pfdev->as_faulty_mask |= mask; + + /* Disable the MMU to kill jobs on this AS. */ + panfrost_mmu_disable(pfdev, as); + spin_unlock(&pfdev->as_lock); + } + status &= ~mask; /* If we received new MMU interrupts, process them before returning. */ if (!status) - status = mmu_read(pfdev, MMU_INT_RAWSTAT); + status = mmu_read(pfdev, MMU_INT_RAWSTAT) & ~pfdev->as_faulty_mask; } - mmu_write(pfdev, MMU_INT_MASK, ~0); + spin_lock(&pfdev->as_lock); + mmu_write(pfdev, MMU_INT_MASK, ~pfdev->as_faulty_mask); + spin_unlock(&pfdev->as_lock); + return IRQ_HANDLED; }; diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.h b/drivers/gpu/drm/panfrost/panfrost_mmu.h index 44fc2edf63ce..cc2a0d307feb 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.h +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.h @@ -18,7 +18,8 @@ void panfrost_mmu_reset(struct panfrost_device *pfdev); u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu); void panfrost_mmu_as_put(struct panfrost_device *pfdev, struct panfrost_mmu *mmu); -int panfrost_mmu_pgtable_alloc(struct panfrost_file_priv *priv); -void panfrost_mmu_pgtable_free(struct panfrost_file_priv *priv); +struct panfrost_mmu *panfrost_mmu_ctx_get(struct panfrost_mmu *mmu); +void panfrost_mmu_ctx_put(struct panfrost_mmu *mmu); +struct panfrost_mmu *panfrost_mmu_ctx_create(struct panfrost_device *pfdev); #endif diff --git a/drivers/gpu/drm/panfrost/panfrost_regs.h b/drivers/gpu/drm/panfrost/panfrost_regs.h index dc9df5457f1c..1940ff86e49a 100644 --- a/drivers/gpu/drm/panfrost/panfrost_regs.h +++ b/drivers/gpu/drm/panfrost/panfrost_regs.h @@ -262,9 +262,6 @@ #define JS_COMMAND_SOFT_STOP_1 0x06 /* Execute SOFT_STOP if JOB_CHAIN_FLAG is 1 */ #define JS_COMMAND_HARD_STOP_1 0x07 /* Execute HARD_STOP if JOB_CHAIN_FLAG is 1 */ -#define JS_STATUS_EVENT_ACTIVE 0x08 - - /* MMU regs */ #define MMU_INT_RAWSTAT 0x2000 #define MMU_INT_CLEAR 0x2004 diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c index 6fd7f13f1aca..b5a8859739a2 100644 --- a/drivers/gpu/drm/pl111/pl111_display.c +++ b/drivers/gpu/drm/pl111/pl111_display.c @@ -440,7 +440,6 @@ static struct drm_simple_display_pipe_funcs pl111_display_funcs = { .enable = pl111_display_enable, .disable = pl111_display_disable, .update = pl111_display_update, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, }; static int pl111_clk_div_choose_div(struct clk_hw *hw, unsigned long rate, diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c index 854e6c5a563f..fc47b0deb021 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.c +++ b/drivers/gpu/drm/qxl/qxl_drv.c @@ -95,7 +95,7 @@ qxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (ret) return ret; - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "qxl"); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &qxl_driver); if (ret) goto disable_pci; @@ -281,10 +281,8 @@ static struct drm_driver qxl_driver = { .prime_handle_to_fd = drm_gem_prime_handle_to_fd, .prime_fd_to_handle = drm_gem_prime_fd_to_handle, .gem_prime_import_sg_table = qxl_gem_prime_import_sg_table, - .gem_prime_mmap = qxl_gem_prime_mmap, .fops = &qxl_fops, .ioctls = qxl_ioctls, - .irq_handler = qxl_irq_handler, .name = DRIVER_NAME, .desc = DRIVER_DESC, .date = DRIVER_DATE, diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h index dd6abee55f56..359266d9e860 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.h +++ b/drivers/gpu/drm/qxl/qxl_drv.h @@ -434,12 +434,9 @@ struct drm_gem_object *qxl_gem_prime_import_sg_table( int qxl_gem_prime_vmap(struct drm_gem_object *obj, struct dma_buf_map *map); void qxl_gem_prime_vunmap(struct drm_gem_object *obj, struct dma_buf_map *map); -int qxl_gem_prime_mmap(struct drm_gem_object *obj, - struct vm_area_struct *vma); /* qxl_irq.c */ int qxl_irq_init(struct qxl_device *qdev); -irqreturn_t qxl_irq_handler(int irq, void *arg); void qxl_debugfs_add_files(struct qxl_device *qdev, struct drm_info_list *files, diff --git a/drivers/gpu/drm/qxl/qxl_irq.c b/drivers/gpu/drm/qxl/qxl_irq.c index d312322cacd1..665278ee3b6d 100644 --- a/drivers/gpu/drm/qxl/qxl_irq.c +++ b/drivers/gpu/drm/qxl/qxl_irq.c @@ -25,11 +25,11 @@ #include <linux/pci.h> -#include <drm/drm_irq.h> +#include <drm/drm_drv.h> #include "qxl_drv.h" -irqreturn_t qxl_irq_handler(int irq, void *arg) +static irqreturn_t qxl_irq_handler(int irq, void *arg) { struct drm_device *dev = (struct drm_device *) arg; struct qxl_device *qdev = to_qxl(dev); @@ -81,7 +81,8 @@ static void qxl_client_monitors_config_work_func(struct work_struct *work) int qxl_irq_init(struct qxl_device *qdev) { - struct pci_dev *pdev = to_pci_dev(qdev->ddev.dev); + struct drm_device *ddev = &qdev->ddev; + struct pci_dev *pdev = to_pci_dev(ddev->dev); int ret; init_waitqueue_head(&qdev->display_event); @@ -95,7 +96,7 @@ int qxl_irq_init(struct qxl_device *qdev) atomic_set(&qdev->irq_received_cursor, 0); atomic_set(&qdev->irq_received_io_cmd, 0); qdev->irq_received_error = 0; - ret = drm_irq_install(&qdev->ddev, pdev->irq); + ret = request_irq(pdev->irq, qxl_irq_handler, IRQF_SHARED, ddev->driver->name, ddev); qdev->ram_header->int_mask = QXL_INTERRUPT_MASK; if (unlikely(ret != 0)) { DRM_ERROR("Failed installing irq: %d\n", ret); diff --git a/drivers/gpu/drm/qxl/qxl_prime.c b/drivers/gpu/drm/qxl/qxl_prime.c index 0628d1cc91fe..4a10cb0a413b 100644 --- a/drivers/gpu/drm/qxl/qxl_prime.c +++ b/drivers/gpu/drm/qxl/qxl_prime.c @@ -73,9 +73,3 @@ void qxl_gem_prime_vunmap(struct drm_gem_object *obj, qxl_bo_vunmap(bo); } - -int qxl_gem_prime_mmap(struct drm_gem_object *obj, - struct vm_area_struct *area) -{ - return -ENOSYS; -} diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 5c23b77cb81a..c8dd68152d65 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -330,7 +330,7 @@ static int radeon_pci_probe(struct pci_dev *pdev, return -EPROBE_DEFER; /* Get rid of things like offb */ - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "radeondrmfb"); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &kms_driver); if (ret) return ret; diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c index b2ce642ca4fa..18f2c2e0dfb3 100644 --- a/drivers/gpu/drm/radeon/radeon_fence.c +++ b/drivers/gpu/drm/radeon/radeon_fence.c @@ -288,7 +288,7 @@ static void radeon_fence_check_lockup(struct work_struct *work) return; } - if (fence_drv->delayed_irq && rdev->ddev->irq_enabled) { + if (fence_drv->delayed_irq && rdev->irq.installed) { unsigned long irqflags; fence_drv->delayed_irq = false; diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c index 84d0b1a3355f..a36ce826d0c0 100644 --- a/drivers/gpu/drm/radeon/radeon_irq_kms.c +++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c @@ -357,7 +357,7 @@ void radeon_irq_kms_sw_irq_get(struct radeon_device *rdev, int ring) { unsigned long irqflags; - if (!rdev->ddev->irq_enabled) + if (!rdev->irq.installed) return; if (atomic_inc_return(&rdev->irq.ring_int[ring]) == 1) { @@ -396,7 +396,7 @@ void radeon_irq_kms_sw_irq_put(struct radeon_device *rdev, int ring) { unsigned long irqflags; - if (!rdev->ddev->irq_enabled) + if (!rdev->irq.installed) return; if (atomic_dec_and_test(&rdev->irq.ring_int[ring])) { @@ -422,7 +422,7 @@ void radeon_irq_kms_pflip_irq_get(struct radeon_device *rdev, int crtc) if (crtc < 0 || crtc >= rdev->num_crtc) return; - if (!rdev->ddev->irq_enabled) + if (!rdev->irq.installed) return; if (atomic_inc_return(&rdev->irq.pflip[crtc]) == 1) { @@ -448,7 +448,7 @@ void radeon_irq_kms_pflip_irq_put(struct radeon_device *rdev, int crtc) if (crtc < 0 || crtc >= rdev->num_crtc) return; - if (!rdev->ddev->irq_enabled) + if (!rdev->irq.installed) return; if (atomic_dec_and_test(&rdev->irq.pflip[crtc])) { @@ -470,7 +470,7 @@ void radeon_irq_kms_enable_afmt(struct radeon_device *rdev, int block) { unsigned long irqflags; - if (!rdev->ddev->irq_enabled) + if (!rdev->irq.installed) return; spin_lock_irqsave(&rdev->irq.lock, irqflags); @@ -492,7 +492,7 @@ void radeon_irq_kms_disable_afmt(struct radeon_device *rdev, int block) { unsigned long irqflags; - if (!rdev->ddev->irq_enabled) + if (!rdev->irq.installed) return; spin_lock_irqsave(&rdev->irq.lock, irqflags); @@ -514,7 +514,7 @@ void radeon_irq_kms_enable_hpd(struct radeon_device *rdev, unsigned hpd_mask) unsigned long irqflags; int i; - if (!rdev->ddev->irq_enabled) + if (!rdev->irq.installed) return; spin_lock_irqsave(&rdev->irq.lock, irqflags); @@ -537,7 +537,7 @@ void radeon_irq_kms_disable_hpd(struct radeon_device *rdev, unsigned hpd_mask) unsigned long irqflags; int i; - if (!rdev->ddev->irq_enabled) + if (!rdev->irq.installed) return; spin_lock_irqsave(&rdev->irq.lock, irqflags); diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c index bfbff90588cb..e289a66594a7 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c @@ -593,8 +593,6 @@ static int rcar_du_probe(struct platform_device *pdev) goto error; } - rcdu->ddev.irq_enabled = 1; - /* * Register the DRM device with the core and the connectors with * sysfs. diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index b730b8d5d949..bfba9793d238 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -116,7 +116,7 @@ static int rockchip_drm_bind(struct device *dev) int ret; /* Remove existing drivers that may own the framebuffer memory. */ - ret = drm_aperture_remove_framebuffers(false, "rockchip-drm-fb"); + ret = drm_aperture_remove_framebuffers(false, &rockchip_drm_driver); if (ret) { DRM_DEV_ERROR(dev, "Failed to remove existing framebuffers - %d.\n", @@ -162,12 +162,6 @@ static int rockchip_drm_bind(struct device *dev) drm_mode_config_reset(drm_dev); - /* - * enable drm irq mode. - * - with irq_enabled = true, we can use the vblank feature. - */ - drm_dev->irq_enabled = true; - ret = rockchip_drm_fbdev_init(drm_dev); if (ret) goto err_unbind_all; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index f5b9028a16a3..ba9e14da41b4 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -1110,7 +1110,6 @@ static const struct drm_plane_helper_funcs plane_helper_funcs = { .atomic_disable = vop_plane_atomic_disable, .atomic_async_check = vop_plane_atomic_async_check, .atomic_async_update = vop_plane_atomic_async_update, - .prepare_fb = drm_gem_plane_helper_prepare_fb, }; static const struct drm_plane_funcs vop_plane_funcs = { diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index a2a953693b45..67382621b429 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -232,7 +232,7 @@ static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched) { if (sched->timeout != MAX_SCHEDULE_TIMEOUT && !list_empty(&sched->pending_list)) - schedule_delayed_work(&sched->work_tdr, sched->timeout); + queue_delayed_work(sched->timeout_wq, &sched->work_tdr, sched->timeout); } /** @@ -244,7 +244,7 @@ static void drm_sched_start_timeout(struct drm_gpu_scheduler *sched) */ void drm_sched_fault(struct drm_gpu_scheduler *sched) { - mod_delayed_work(system_wq, &sched->work_tdr, 0); + mod_delayed_work(sched->timeout_wq, &sched->work_tdr, 0); } EXPORT_SYMBOL(drm_sched_fault); @@ -270,7 +270,7 @@ unsigned long drm_sched_suspend_timeout(struct drm_gpu_scheduler *sched) * Modify the timeout to an arbitrarily large value. This also prevents * the timeout to be restarted when new submissions arrive */ - if (mod_delayed_work(system_wq, &sched->work_tdr, MAX_SCHEDULE_TIMEOUT) + if (mod_delayed_work(sched->timeout_wq, &sched->work_tdr, MAX_SCHEDULE_TIMEOUT) && time_after(sched_timeout, now)) return sched_timeout - now; else @@ -294,7 +294,7 @@ void drm_sched_resume_timeout(struct drm_gpu_scheduler *sched, if (list_empty(&sched->pending_list)) cancel_delayed_work(&sched->work_tdr); else - mod_delayed_work(system_wq, &sched->work_tdr, remaining); + mod_delayed_work(sched->timeout_wq, &sched->work_tdr, remaining); spin_unlock(&sched->job_list_lock); } @@ -802,10 +802,10 @@ static int drm_sched_main(void *param) sched_job = drm_sched_entity_pop_job(entity); - complete(&entity->entity_idle); - - if (!sched_job) + if (!sched_job) { + complete(&entity->entity_idle); continue; + } s_fence = sched_job->s_fence; @@ -814,6 +814,7 @@ static int drm_sched_main(void *param) trace_drm_run_job(sched_job, entity); fence = sched->ops->run_job(sched_job); + complete(&entity->entity_idle); drm_sched_fence_scheduled(s_fence); if (!IS_ERR_OR_NULL(fence)) { @@ -846,6 +847,8 @@ static int drm_sched_main(void *param) * @hw_submission: number of hw submissions that can be in flight * @hang_limit: number of times to allow a job to hang before dropping it * @timeout: timeout value in jiffies for the scheduler + * @timeout_wq: workqueue to use for timeout work. If NULL, the system_wq is + * used * @score: optional score atomic shared with other schedulers * @name: name used for debugging * @@ -853,7 +856,8 @@ static int drm_sched_main(void *param) */ int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_backend_ops *ops, - unsigned hw_submission, unsigned hang_limit, long timeout, + unsigned hw_submission, unsigned hang_limit, + long timeout, struct workqueue_struct *timeout_wq, atomic_t *score, const char *name) { int i, ret; @@ -861,6 +865,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched, sched->hw_submission_limit = hw_submission; sched->name = name; sched->timeout = timeout; + sched->timeout_wq = timeout_wq ? : system_wq; sched->hang_limit = hang_limit; sched->score = score ? score : &sched->_score; for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_COUNT; i++) diff --git a/drivers/gpu/drm/sti/sti_compositor.c b/drivers/gpu/drm/sti/sti_compositor.c index 319962a2c17b..9caaf3ccfabe 100644 --- a/drivers/gpu/drm/sti/sti_compositor.c +++ b/drivers/gpu/drm/sti/sti_compositor.c @@ -145,8 +145,6 @@ static int sti_compositor_bind(struct device *dev, } drm_vblank_init(drm_dev, crtc_id); - /* Allow usage of vblank without having to call drm_irq_install */ - drm_dev->irq_enabled = 1; return 0; } diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c index 08b71248044d..1f9392fb58e1 100644 --- a/drivers/gpu/drm/stm/ltdc.c +++ b/drivers/gpu/drm/stm/ltdc.c @@ -947,7 +947,6 @@ static const struct drm_plane_funcs ltdc_plane_funcs = { }; static const struct drm_plane_helper_funcs ltdc_plane_helper_funcs = { - .prepare_fb = drm_gem_plane_helper_prepare_fb, .atomic_check = ltdc_plane_atomic_check, .atomic_update = ltdc_plane_atomic_update, .atomic_disable = ltdc_plane_atomic_disable, @@ -1339,9 +1338,6 @@ int ltdc_load(struct drm_device *ddev) goto err; } - /* Allow usage of vblank without having to call drm_irq_install */ - ddev->irq_enabled = 1; - clk_disable_unprepare(ldev->pixel_clk); pinctrl_pm_select_sleep_state(ddev->dev); diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index af335f58bdfc..54dd562e294c 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -97,10 +97,8 @@ static int sun4i_drv_bind(struct device *dev) if (ret) goto cleanup_mode_config; - drm->irq_enabled = true; - /* Remove early framebuffers (ie. simplefb) */ - ret = drm_aperture_remove_framebuffers(false, "sun4i-drm-fb"); + ret = drm_aperture_remove_framebuffers(false, &sun4i_drv_driver); if (ret) goto cleanup_mode_config; diff --git a/drivers/gpu/drm/sun4i/sun4i_layer.c b/drivers/gpu/drm/sun4i/sun4i_layer.c index 11771bdd6e7c..929e95f86b5b 100644 --- a/drivers/gpu/drm/sun4i/sun4i_layer.c +++ b/drivers/gpu/drm/sun4i/sun4i_layer.c @@ -127,7 +127,6 @@ static bool sun4i_layer_format_mod_supported(struct drm_plane *plane, } static const struct drm_plane_helper_funcs sun4i_backend_layer_helper_funcs = { - .prepare_fb = drm_gem_plane_helper_prepare_fb, .atomic_disable = sun4i_backend_layer_atomic_disable, .atomic_update = sun4i_backend_layer_atomic_update, }; diff --git a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c index e779855bcd6e..7845c2a53a7f 100644 --- a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c +++ b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c @@ -332,7 +332,6 @@ static void sun8i_ui_layer_atomic_update(struct drm_plane *plane, } static const struct drm_plane_helper_funcs sun8i_ui_layer_helper_funcs = { - .prepare_fb = drm_gem_plane_helper_prepare_fb, .atomic_check = sun8i_ui_layer_atomic_check, .atomic_disable = sun8i_ui_layer_atomic_disable, .atomic_update = sun8i_ui_layer_atomic_update, diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c index 1c86c2dd0bbf..bb7c43036dfa 100644 --- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c +++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c @@ -436,7 +436,6 @@ static void sun8i_vi_layer_atomic_update(struct drm_plane *plane, } static const struct drm_plane_helper_funcs sun8i_vi_layer_helper_funcs = { - .prepare_fb = drm_gem_plane_helper_prepare_fb, .atomic_check = sun8i_vi_layer_atomic_check, .atomic_disable = sun8i_vi_layer_atomic_disable, .atomic_update = sun8i_vi_layer_atomic_update, diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index f96c237b2242..8c6069b33160 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1188,13 +1188,6 @@ static int host1x_drm_probe(struct host1x_device *dev) goto device; } - /* - * We don't use the drm_irq_install() helpers provided by the DRM - * core, so we need to set this manually in order to allow the - * DRM_IOCTL_WAIT_VBLANK to operate correctly. - */ - drm->irq_enabled = true; - /* syncpoints are used for full 32-bit hardware VBLANK counters */ drm->max_vblank_count = 0xffffffff; @@ -1204,7 +1197,7 @@ static int host1x_drm_probe(struct host1x_device *dev) drm_mode_config_reset(drm); - err = drm_aperture_remove_framebuffers(false, "tegradrmfb"); + err = drm_aperture_remove_framebuffers(false, &tegra_drm_driver); if (err < 0) goto hub; diff --git a/drivers/gpu/drm/tidss/tidss_irq.c b/drivers/gpu/drm/tidss/tidss_irq.c index a5ec7931ef6b..2ed3e3296776 100644 --- a/drivers/gpu/drm/tidss/tidss_irq.c +++ b/drivers/gpu/drm/tidss/tidss_irq.c @@ -57,9 +57,6 @@ irqreturn_t tidss_irq_handler(int irq, void *arg) unsigned int id; dispc_irq_t irqstatus; - if (WARN_ON(!ddev->irq_enabled)) - return IRQ_NONE; - irqstatus = dispc_read_and_clear_irqstatus(tidss->dispc); for (id = 0; id < tidss->num_crtcs; id++) { diff --git a/drivers/gpu/drm/tidss/tidss_plane.c b/drivers/gpu/drm/tidss/tidss_plane.c index 1acd15aa4193..217415ec8eea 100644 --- a/drivers/gpu/drm/tidss/tidss_plane.c +++ b/drivers/gpu/drm/tidss/tidss_plane.c @@ -158,7 +158,6 @@ static void drm_plane_destroy(struct drm_plane *plane) } static const struct drm_plane_helper_funcs tidss_plane_helper_funcs = { - .prepare_fb = drm_gem_plane_helper_prepare_fb, .atomic_check = tidss_plane_atomic_check, .atomic_update = tidss_plane_atomic_update, .atomic_disable = tidss_plane_atomic_disable, diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig index d46f95d9196d..5593128eeff9 100644 --- a/drivers/gpu/drm/tiny/Kconfig +++ b/drivers/gpu/drm/tiny/Kconfig @@ -10,6 +10,19 @@ config DRM_ARCPGU If M is selected the module will be called arcpgu. +config DRM_BOCHS + tristate "DRM Support for bochs dispi vga interface (qemu stdvga)" + depends on DRM && PCI && MMU + select DRM_KMS_HELPER + select DRM_VRAM_HELPER + select DRM_TTM + select DRM_TTM_HELPER + help + This is a KMS driver for qemu's stdvga output. Choose this option + for qemu. + + If M is selected the module will be called bochs. + config DRM_CIRRUS_QEMU tristate "Cirrus driver for QEMU emulated device" depends on DRM && PCI && MMU diff --git a/drivers/gpu/drm/tiny/Makefile b/drivers/gpu/drm/tiny/Makefile index 9cc847e756da..e09942895c77 100644 --- a/drivers/gpu/drm/tiny/Makefile +++ b/drivers/gpu/drm/tiny/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_DRM_ARCPGU) += arcpgu.o +obj-$(CONFIG_DRM_BOCHS) += bochs.o obj-$(CONFIG_DRM_CIRRUS_QEMU) += cirrus.o obj-$(CONFIG_DRM_GM12U320) += gm12u320.o obj-$(CONFIG_DRM_SIMPLEDRM) += simpledrm.o diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c new file mode 100644 index 000000000000..a2cfecfa8556 --- /dev/null +++ b/drivers/gpu/drm/tiny/bochs.c @@ -0,0 +1,733 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/console.h> +#include <linux/pci.h> + +#include <drm/drm_aperture.h> +#include <drm/drm_atomic_helper.h> +#include <drm/drm_drv.h> +#include <drm/drm_fb_helper.h> +#include <drm/drm_fourcc.h> +#include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_gem_vram_helper.h> +#include <drm/drm_managed.h> +#include <drm/drm_probe_helper.h> +#include <drm/drm_simple_kms_helper.h> + +#include <video/vga.h> + +/* ---------------------------------------------------------------------- */ + +#define VBE_DISPI_IOPORT_INDEX 0x01CE +#define VBE_DISPI_IOPORT_DATA 0x01CF + +#define VBE_DISPI_INDEX_ID 0x0 +#define VBE_DISPI_INDEX_XRES 0x1 +#define VBE_DISPI_INDEX_YRES 0x2 +#define VBE_DISPI_INDEX_BPP 0x3 +#define VBE_DISPI_INDEX_ENABLE 0x4 +#define VBE_DISPI_INDEX_BANK 0x5 +#define VBE_DISPI_INDEX_VIRT_WIDTH 0x6 +#define VBE_DISPI_INDEX_VIRT_HEIGHT 0x7 +#define VBE_DISPI_INDEX_X_OFFSET 0x8 +#define VBE_DISPI_INDEX_Y_OFFSET 0x9 +#define VBE_DISPI_INDEX_VIDEO_MEMORY_64K 0xa + +#define VBE_DISPI_ID0 0xB0C0 +#define VBE_DISPI_ID1 0xB0C1 +#define VBE_DISPI_ID2 0xB0C2 +#define VBE_DISPI_ID3 0xB0C3 +#define VBE_DISPI_ID4 0xB0C4 +#define VBE_DISPI_ID5 0xB0C5 + +#define VBE_DISPI_DISABLED 0x00 +#define VBE_DISPI_ENABLED 0x01 +#define VBE_DISPI_GETCAPS 0x02 +#define VBE_DISPI_8BIT_DAC 0x20 +#define VBE_DISPI_LFB_ENABLED 0x40 +#define VBE_DISPI_NOCLEARMEM 0x80 + +static int bochs_modeset = -1; +static int defx = 1024; +static int defy = 768; + +module_param_named(modeset, bochs_modeset, int, 0444); +MODULE_PARM_DESC(modeset, "enable/disable kernel modesetting"); + +module_param(defx, int, 0444); +module_param(defy, int, 0444); +MODULE_PARM_DESC(defx, "default x resolution"); +MODULE_PARM_DESC(defy, "default y resolution"); + +/* ---------------------------------------------------------------------- */ + +enum bochs_types { + BOCHS_QEMU_STDVGA, + BOCHS_UNKNOWN, +}; + +struct bochs_device { + /* hw */ + void __iomem *mmio; + int ioports; + void __iomem *fb_map; + unsigned long fb_base; + unsigned long fb_size; + unsigned long qext_size; + + /* mode */ + u16 xres; + u16 yres; + u16 yres_virtual; + u32 stride; + u32 bpp; + struct edid *edid; + + /* drm */ + struct drm_device *dev; + struct drm_simple_display_pipe pipe; + struct drm_connector connector; +}; + +/* ---------------------------------------------------------------------- */ + +static void bochs_vga_writeb(struct bochs_device *bochs, u16 ioport, u8 val) +{ + if (WARN_ON(ioport < 0x3c0 || ioport > 0x3df)) + return; + + if (bochs->mmio) { + int offset = ioport - 0x3c0 + 0x400; + + writeb(val, bochs->mmio + offset); + } else { + outb(val, ioport); + } +} + +static u8 bochs_vga_readb(struct bochs_device *bochs, u16 ioport) +{ + if (WARN_ON(ioport < 0x3c0 || ioport > 0x3df)) + return 0xff; + + if (bochs->mmio) { + int offset = ioport - 0x3c0 + 0x400; + + return readb(bochs->mmio + offset); + } else { + return inb(ioport); + } +} + +static u16 bochs_dispi_read(struct bochs_device *bochs, u16 reg) +{ + u16 ret = 0; + + if (bochs->mmio) { + int offset = 0x500 + (reg << 1); + + ret = readw(bochs->mmio + offset); + } else { + outw(reg, VBE_DISPI_IOPORT_INDEX); + ret = inw(VBE_DISPI_IOPORT_DATA); + } + return ret; +} + +static void bochs_dispi_write(struct bochs_device *bochs, u16 reg, u16 val) +{ + if (bochs->mmio) { + int offset = 0x500 + (reg << 1); + + writew(val, bochs->mmio + offset); + } else { + outw(reg, VBE_DISPI_IOPORT_INDEX); + outw(val, VBE_DISPI_IOPORT_DATA); + } +} + +static void bochs_hw_set_big_endian(struct bochs_device *bochs) +{ + if (bochs->qext_size < 8) + return; + + writel(0xbebebebe, bochs->mmio + 0x604); +} + +static void bochs_hw_set_little_endian(struct bochs_device *bochs) +{ + if (bochs->qext_size < 8) + return; + + writel(0x1e1e1e1e, bochs->mmio + 0x604); +} + +#ifdef __BIG_ENDIAN +#define bochs_hw_set_native_endian(_b) bochs_hw_set_big_endian(_b) +#else +#define bochs_hw_set_native_endian(_b) bochs_hw_set_little_endian(_b) +#endif + +static int bochs_get_edid_block(void *data, u8 *buf, + unsigned int block, size_t len) +{ + struct bochs_device *bochs = data; + size_t i, start = block * EDID_LENGTH; + + if (start + len > 0x400 /* vga register offset */) + return -1; + + for (i = 0; i < len; i++) + buf[i] = readb(bochs->mmio + start + i); + + return 0; +} + +static int bochs_hw_load_edid(struct bochs_device *bochs) +{ + u8 header[8]; + + if (!bochs->mmio) + return -1; + + /* check header to detect whenever edid support is enabled in qemu */ + bochs_get_edid_block(bochs, header, 0, ARRAY_SIZE(header)); + if (drm_edid_header_is_valid(header) != 8) + return -1; + + kfree(bochs->edid); + bochs->edid = drm_do_get_edid(&bochs->connector, + bochs_get_edid_block, bochs); + if (bochs->edid == NULL) + return -1; + + return 0; +} + +static int bochs_hw_init(struct drm_device *dev) +{ + struct bochs_device *bochs = dev->dev_private; + struct pci_dev *pdev = to_pci_dev(dev->dev); + unsigned long addr, size, mem, ioaddr, iosize; + u16 id; + + if (pdev->resource[2].flags & IORESOURCE_MEM) { + /* mmio bar with vga and bochs registers present */ + if (pci_request_region(pdev, 2, "bochs-drm") != 0) { + DRM_ERROR("Cannot request mmio region\n"); + return -EBUSY; + } + ioaddr = pci_resource_start(pdev, 2); + iosize = pci_resource_len(pdev, 2); + bochs->mmio = ioremap(ioaddr, iosize); + if (bochs->mmio == NULL) { + DRM_ERROR("Cannot map mmio region\n"); + return -ENOMEM; + } + } else { + ioaddr = VBE_DISPI_IOPORT_INDEX; + iosize = 2; + if (!request_region(ioaddr, iosize, "bochs-drm")) { + DRM_ERROR("Cannot request ioports\n"); + return -EBUSY; + } + bochs->ioports = 1; + } + + id = bochs_dispi_read(bochs, VBE_DISPI_INDEX_ID); + mem = bochs_dispi_read(bochs, VBE_DISPI_INDEX_VIDEO_MEMORY_64K) + * 64 * 1024; + if ((id & 0xfff0) != VBE_DISPI_ID0) { + DRM_ERROR("ID mismatch\n"); + return -ENODEV; + } + + if ((pdev->resource[0].flags & IORESOURCE_MEM) == 0) + return -ENODEV; + addr = pci_resource_start(pdev, 0); + size = pci_resource_len(pdev, 0); + if (addr == 0) + return -ENODEV; + if (size != mem) { + DRM_ERROR("Size mismatch: pci=%ld, bochs=%ld\n", + size, mem); + size = min(size, mem); + } + + if (pci_request_region(pdev, 0, "bochs-drm") != 0) + DRM_WARN("Cannot request framebuffer, boot fb still active?\n"); + + bochs->fb_map = ioremap(addr, size); + if (bochs->fb_map == NULL) { + DRM_ERROR("Cannot map framebuffer\n"); + return -ENOMEM; + } + bochs->fb_base = addr; + bochs->fb_size = size; + + DRM_INFO("Found bochs VGA, ID 0x%x.\n", id); + DRM_INFO("Framebuffer size %ld kB @ 0x%lx, %s @ 0x%lx.\n", + size / 1024, addr, + bochs->ioports ? "ioports" : "mmio", + ioaddr); + + if (bochs->mmio && pdev->revision >= 2) { + bochs->qext_size = readl(bochs->mmio + 0x600); + if (bochs->qext_size < 4 || bochs->qext_size > iosize) { + bochs->qext_size = 0; + goto noext; + } + DRM_DEBUG("Found qemu ext regs, size %ld\n", + bochs->qext_size); + bochs_hw_set_native_endian(bochs); + } + +noext: + return 0; +} + +static void bochs_hw_fini(struct drm_device *dev) +{ + struct bochs_device *bochs = dev->dev_private; + + /* TODO: shot down existing vram mappings */ + + if (bochs->mmio) + iounmap(bochs->mmio); + if (bochs->ioports) + release_region(VBE_DISPI_IOPORT_INDEX, 2); + if (bochs->fb_map) + iounmap(bochs->fb_map); + pci_release_regions(to_pci_dev(dev->dev)); + kfree(bochs->edid); +} + +static void bochs_hw_blank(struct bochs_device *bochs, bool blank) +{ + DRM_DEBUG_DRIVER("hw_blank %d\n", blank); + /* discard ar_flip_flop */ + (void)bochs_vga_readb(bochs, VGA_IS1_RC); + /* blank or unblank; we need only update index and set 0x20 */ + bochs_vga_writeb(bochs, VGA_ATT_W, blank ? 0 : 0x20); +} + +static void bochs_hw_setmode(struct bochs_device *bochs, struct drm_display_mode *mode) +{ + int idx; + + if (!drm_dev_enter(bochs->dev, &idx)) + return; + + bochs->xres = mode->hdisplay; + bochs->yres = mode->vdisplay; + bochs->bpp = 32; + bochs->stride = mode->hdisplay * (bochs->bpp / 8); + bochs->yres_virtual = bochs->fb_size / bochs->stride; + + DRM_DEBUG_DRIVER("%dx%d @ %d bpp, vy %d\n", + bochs->xres, bochs->yres, bochs->bpp, + bochs->yres_virtual); + + bochs_hw_blank(bochs, false); + + bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE, 0); + bochs_dispi_write(bochs, VBE_DISPI_INDEX_BPP, bochs->bpp); + bochs_dispi_write(bochs, VBE_DISPI_INDEX_XRES, bochs->xres); + bochs_dispi_write(bochs, VBE_DISPI_INDEX_YRES, bochs->yres); + bochs_dispi_write(bochs, VBE_DISPI_INDEX_BANK, 0); + bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_WIDTH, bochs->xres); + bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_HEIGHT, + bochs->yres_virtual); + bochs_dispi_write(bochs, VBE_DISPI_INDEX_X_OFFSET, 0); + bochs_dispi_write(bochs, VBE_DISPI_INDEX_Y_OFFSET, 0); + + bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE, + VBE_DISPI_ENABLED | VBE_DISPI_LFB_ENABLED); + + drm_dev_exit(idx); +} + +static void bochs_hw_setformat(struct bochs_device *bochs, const struct drm_format_info *format) +{ + int idx; + + if (!drm_dev_enter(bochs->dev, &idx)) + return; + + DRM_DEBUG_DRIVER("format %c%c%c%c\n", + (format->format >> 0) & 0xff, + (format->format >> 8) & 0xff, + (format->format >> 16) & 0xff, + (format->format >> 24) & 0xff); + + switch (format->format) { + case DRM_FORMAT_XRGB8888: + bochs_hw_set_little_endian(bochs); + break; + case DRM_FORMAT_BGRX8888: + bochs_hw_set_big_endian(bochs); + break; + default: + /* should not happen */ + DRM_ERROR("%s: Huh? Got framebuffer format 0x%x", + __func__, format->format); + break; + } + + drm_dev_exit(idx); +} + +static void bochs_hw_setbase(struct bochs_device *bochs, int x, int y, int stride, u64 addr) +{ + unsigned long offset; + unsigned int vx, vy, vwidth, idx; + + if (!drm_dev_enter(bochs->dev, &idx)) + return; + + bochs->stride = stride; + offset = (unsigned long)addr + + y * bochs->stride + + x * (bochs->bpp / 8); + vy = offset / bochs->stride; + vx = (offset % bochs->stride) * 8 / bochs->bpp; + vwidth = stride * 8 / bochs->bpp; + + DRM_DEBUG_DRIVER("x %d, y %d, addr %llx -> offset %lx, vx %d, vy %d\n", + x, y, addr, offset, vx, vy); + bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_WIDTH, vwidth); + bochs_dispi_write(bochs, VBE_DISPI_INDEX_X_OFFSET, vx); + bochs_dispi_write(bochs, VBE_DISPI_INDEX_Y_OFFSET, vy); + + drm_dev_exit(idx); +} + +/* ---------------------------------------------------------------------- */ + +static const uint32_t bochs_formats[] = { + DRM_FORMAT_XRGB8888, + DRM_FORMAT_BGRX8888, +}; + +static void bochs_plane_update(struct bochs_device *bochs, struct drm_plane_state *state) +{ + struct drm_gem_vram_object *gbo; + s64 gpu_addr; + + if (!state->fb || !bochs->stride) + return; + + gbo = drm_gem_vram_of_gem(state->fb->obj[0]); + gpu_addr = drm_gem_vram_offset(gbo); + if (WARN_ON_ONCE(gpu_addr < 0)) + return; /* Bug: we didn't pin the BO to VRAM in prepare_fb. */ + + bochs_hw_setbase(bochs, + state->crtc_x, + state->crtc_y, + state->fb->pitches[0], + state->fb->offsets[0] + gpu_addr); + bochs_hw_setformat(bochs, state->fb->format); +} + +static void bochs_pipe_enable(struct drm_simple_display_pipe *pipe, + struct drm_crtc_state *crtc_state, + struct drm_plane_state *plane_state) +{ + struct bochs_device *bochs = pipe->crtc.dev->dev_private; + + bochs_hw_setmode(bochs, &crtc_state->mode); + bochs_plane_update(bochs, plane_state); +} + +static void bochs_pipe_disable(struct drm_simple_display_pipe *pipe) +{ + struct bochs_device *bochs = pipe->crtc.dev->dev_private; + + bochs_hw_blank(bochs, true); +} + +static void bochs_pipe_update(struct drm_simple_display_pipe *pipe, + struct drm_plane_state *old_state) +{ + struct bochs_device *bochs = pipe->crtc.dev->dev_private; + + bochs_plane_update(bochs, pipe->plane.state); +} + +static const struct drm_simple_display_pipe_funcs bochs_pipe_funcs = { + .enable = bochs_pipe_enable, + .disable = bochs_pipe_disable, + .update = bochs_pipe_update, + .prepare_fb = drm_gem_vram_simple_display_pipe_prepare_fb, + .cleanup_fb = drm_gem_vram_simple_display_pipe_cleanup_fb, +}; + +static int bochs_connector_get_modes(struct drm_connector *connector) +{ + struct bochs_device *bochs = + container_of(connector, struct bochs_device, connector); + int count = 0; + + if (bochs->edid) + count = drm_add_edid_modes(connector, bochs->edid); + + if (!count) { + count = drm_add_modes_noedid(connector, 8192, 8192); + drm_set_preferred_mode(connector, defx, defy); + } + return count; +} + +static const struct drm_connector_helper_funcs bochs_connector_connector_helper_funcs = { + .get_modes = bochs_connector_get_modes, +}; + +static const struct drm_connector_funcs bochs_connector_connector_funcs = { + .fill_modes = drm_helper_probe_single_connector_modes, + .destroy = drm_connector_cleanup, + .reset = drm_atomic_helper_connector_reset, + .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, +}; + +static void bochs_connector_init(struct drm_device *dev) +{ + struct bochs_device *bochs = dev->dev_private; + struct drm_connector *connector = &bochs->connector; + + drm_connector_init(dev, connector, &bochs_connector_connector_funcs, + DRM_MODE_CONNECTOR_VIRTUAL); + drm_connector_helper_add(connector, &bochs_connector_connector_helper_funcs); + + bochs_hw_load_edid(bochs); + if (bochs->edid) { + DRM_INFO("Found EDID data blob.\n"); + drm_connector_attach_edid_property(connector); + drm_connector_update_edid_property(connector, bochs->edid); + } +} + +static struct drm_framebuffer * +bochs_gem_fb_create(struct drm_device *dev, struct drm_file *file, + const struct drm_mode_fb_cmd2 *mode_cmd) +{ + if (mode_cmd->pixel_format != DRM_FORMAT_XRGB8888 && + mode_cmd->pixel_format != DRM_FORMAT_BGRX8888) + return ERR_PTR(-EINVAL); + + return drm_gem_fb_create(dev, file, mode_cmd); +} + +static const struct drm_mode_config_funcs bochs_mode_funcs = { + .fb_create = bochs_gem_fb_create, + .mode_valid = drm_vram_helper_mode_valid, + .atomic_check = drm_atomic_helper_check, + .atomic_commit = drm_atomic_helper_commit, +}; + +static int bochs_kms_init(struct bochs_device *bochs) +{ + int ret; + + ret = drmm_mode_config_init(bochs->dev); + if (ret) + return ret; + + bochs->dev->mode_config.max_width = 8192; + bochs->dev->mode_config.max_height = 8192; + + bochs->dev->mode_config.fb_base = bochs->fb_base; + bochs->dev->mode_config.preferred_depth = 24; + bochs->dev->mode_config.prefer_shadow = 0; + bochs->dev->mode_config.prefer_shadow_fbdev = 1; + bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true; + + bochs->dev->mode_config.funcs = &bochs_mode_funcs; + + bochs_connector_init(bochs->dev); + drm_simple_display_pipe_init(bochs->dev, + &bochs->pipe, + &bochs_pipe_funcs, + bochs_formats, + ARRAY_SIZE(bochs_formats), + NULL, + &bochs->connector); + + drm_mode_config_reset(bochs->dev); + + return 0; +} + +/* ---------------------------------------------------------------------- */ +/* drm interface */ + +static int bochs_load(struct drm_device *dev) +{ + struct bochs_device *bochs; + int ret; + + bochs = drmm_kzalloc(dev, sizeof(*bochs), GFP_KERNEL); + if (bochs == NULL) + return -ENOMEM; + dev->dev_private = bochs; + bochs->dev = dev; + + ret = bochs_hw_init(dev); + if (ret) + return ret; + + ret = drmm_vram_helper_init(dev, bochs->fb_base, bochs->fb_size); + if (ret) + return ret; + + ret = bochs_kms_init(bochs); + if (ret) + return ret; + + return 0; +} + +DEFINE_DRM_GEM_FOPS(bochs_fops); + +static const struct drm_driver bochs_driver = { + .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC, + .fops = &bochs_fops, + .name = "bochs-drm", + .desc = "bochs dispi vga interface (qemu stdvga)", + .date = "20130925", + .major = 1, + .minor = 0, + DRM_GEM_VRAM_DRIVER, +}; + +/* ---------------------------------------------------------------------- */ +/* pm interface */ + +#ifdef CONFIG_PM_SLEEP +static int bochs_pm_suspend(struct device *dev) +{ + struct drm_device *drm_dev = dev_get_drvdata(dev); + + return drm_mode_config_helper_suspend(drm_dev); +} + +static int bochs_pm_resume(struct device *dev) +{ + struct drm_device *drm_dev = dev_get_drvdata(dev); + + return drm_mode_config_helper_resume(drm_dev); +} +#endif + +static const struct dev_pm_ops bochs_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(bochs_pm_suspend, + bochs_pm_resume) +}; + +/* ---------------------------------------------------------------------- */ +/* pci interface */ + +static int bochs_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct drm_device *dev; + unsigned long fbsize; + int ret; + + fbsize = pci_resource_len(pdev, 0); + if (fbsize < 4 * 1024 * 1024) { + DRM_ERROR("less than 4 MB video memory, ignoring device\n"); + return -ENOMEM; + } + + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &bochs_driver); + if (ret) + return ret; + + dev = drm_dev_alloc(&bochs_driver, &pdev->dev); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + ret = pci_enable_device(pdev); + if (ret) + goto err_free_dev; + + pci_set_drvdata(pdev, dev); + + ret = bochs_load(dev); + if (ret) + goto err_free_dev; + + ret = drm_dev_register(dev, 0); + if (ret) + goto err_free_dev; + + drm_fbdev_generic_setup(dev, 32); + return ret; + +err_free_dev: + drm_dev_put(dev); + return ret; +} + +static void bochs_pci_remove(struct pci_dev *pdev) +{ + struct drm_device *dev = pci_get_drvdata(pdev); + + drm_dev_unplug(dev); + drm_atomic_helper_shutdown(dev); + bochs_hw_fini(dev); + drm_dev_put(dev); +} + +static const struct pci_device_id bochs_pci_tbl[] = { + { + .vendor = 0x1234, + .device = 0x1111, + .subvendor = PCI_SUBVENDOR_ID_REDHAT_QUMRANET, + .subdevice = PCI_SUBDEVICE_ID_QEMU, + .driver_data = BOCHS_QEMU_STDVGA, + }, + { + .vendor = 0x1234, + .device = 0x1111, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .driver_data = BOCHS_UNKNOWN, + }, + { /* end of list */ } +}; + +static struct pci_driver bochs_pci_driver = { + .name = "bochs-drm", + .id_table = bochs_pci_tbl, + .probe = bochs_pci_probe, + .remove = bochs_pci_remove, + .driver.pm = &bochs_pm_ops, +}; + +/* ---------------------------------------------------------------------- */ +/* module init/exit */ + +static int __init bochs_init(void) +{ + if (vgacon_text_force() && bochs_modeset == -1) + return -EINVAL; + + if (bochs_modeset == 0) + return -EINVAL; + + return pci_register_driver(&bochs_pci_driver); +} + +static void __exit bochs_exit(void) +{ + pci_unregister_driver(&bochs_pci_driver); +} + +module_init(bochs_init); +module_exit(bochs_exit); + +MODULE_DEVICE_TABLE(pci, bochs_pci_tbl); +MODULE_AUTHOR("Gerd Hoffmann <kraxel@redhat.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/gpu/drm/tiny/cirrus.c b/drivers/gpu/drm/tiny/cirrus.c index 42611dacde88..a8b476a59c0d 100644 --- a/drivers/gpu/drm/tiny/cirrus.c +++ b/drivers/gpu/drm/tiny/cirrus.c @@ -550,7 +550,7 @@ static int cirrus_pci_probe(struct pci_dev *pdev, struct cirrus_device *cirrus; int ret; - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "cirrusdrmfb"); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &cirrus_driver); if (ret) return ret; diff --git a/drivers/gpu/drm/tiny/hx8357d.c b/drivers/gpu/drm/tiny/hx8357d.c index da5df93450de..9b33c05732aa 100644 --- a/drivers/gpu/drm/tiny/hx8357d.c +++ b/drivers/gpu/drm/tiny/hx8357d.c @@ -184,7 +184,6 @@ static const struct drm_simple_display_pipe_funcs hx8357d_pipe_funcs = { .enable = yx240qv29_enable, .disable = mipi_dbi_pipe_disable, .update = mipi_dbi_pipe_update, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, }; static const struct drm_display_mode yx350hv15_mode = { diff --git a/drivers/gpu/drm/tiny/ili9225.c b/drivers/gpu/drm/tiny/ili9225.c index 69265d8a3beb..976d3209f164 100644 --- a/drivers/gpu/drm/tiny/ili9225.c +++ b/drivers/gpu/drm/tiny/ili9225.c @@ -328,7 +328,6 @@ static const struct drm_simple_display_pipe_funcs ili9225_pipe_funcs = { .enable = ili9225_pipe_enable, .disable = ili9225_pipe_disable, .update = ili9225_pipe_update, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, }; static const struct drm_display_mode ili9225_mode = { diff --git a/drivers/gpu/drm/tiny/ili9341.c b/drivers/gpu/drm/tiny/ili9341.c index ad9ce7b4f76f..37e0c33399c8 100644 --- a/drivers/gpu/drm/tiny/ili9341.c +++ b/drivers/gpu/drm/tiny/ili9341.c @@ -140,7 +140,6 @@ static const struct drm_simple_display_pipe_funcs ili9341_pipe_funcs = { .enable = yx240qv29_enable, .disable = mipi_dbi_pipe_disable, .update = mipi_dbi_pipe_update, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, }; static const struct drm_display_mode yx240qv29_mode = { diff --git a/drivers/gpu/drm/tiny/ili9486.c b/drivers/gpu/drm/tiny/ili9486.c index 75aa1476c66c..e9a63f4b2993 100644 --- a/drivers/gpu/drm/tiny/ili9486.c +++ b/drivers/gpu/drm/tiny/ili9486.c @@ -153,7 +153,6 @@ static const struct drm_simple_display_pipe_funcs waveshare_pipe_funcs = { .enable = waveshare_enable, .disable = mipi_dbi_pipe_disable, .update = mipi_dbi_pipe_update, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, }; static const struct drm_display_mode waveshare_mode = { diff --git a/drivers/gpu/drm/tiny/mi0283qt.c b/drivers/gpu/drm/tiny/mi0283qt.c index 82fd1ad3413f..023de49e7a8e 100644 --- a/drivers/gpu/drm/tiny/mi0283qt.c +++ b/drivers/gpu/drm/tiny/mi0283qt.c @@ -144,7 +144,6 @@ static const struct drm_simple_display_pipe_funcs mi0283qt_pipe_funcs = { .enable = mi0283qt_enable, .disable = mipi_dbi_pipe_disable, .update = mipi_dbi_pipe_update, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, }; static const struct drm_display_mode mi0283qt_mode = { diff --git a/drivers/gpu/drm/tiny/repaper.c b/drivers/gpu/drm/tiny/repaper.c index 2cee07a2e00b..007d9d59f01c 100644 --- a/drivers/gpu/drm/tiny/repaper.c +++ b/drivers/gpu/drm/tiny/repaper.c @@ -861,7 +861,6 @@ static const struct drm_simple_display_pipe_funcs repaper_pipe_funcs = { .enable = repaper_pipe_enable, .disable = repaper_pipe_disable, .update = repaper_pipe_update, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, }; static int repaper_connector_get_modes(struct drm_connector *connector) diff --git a/drivers/gpu/drm/tiny/st7586.c b/drivers/gpu/drm/tiny/st7586.c index 05db980cc047..1be55bed609a 100644 --- a/drivers/gpu/drm/tiny/st7586.c +++ b/drivers/gpu/drm/tiny/st7586.c @@ -268,7 +268,6 @@ static const struct drm_simple_display_pipe_funcs st7586_pipe_funcs = { .enable = st7586_pipe_enable, .disable = st7586_pipe_disable, .update = st7586_pipe_update, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, }; static const struct drm_display_mode st7586_mode = { diff --git a/drivers/gpu/drm/tiny/st7735r.c b/drivers/gpu/drm/tiny/st7735r.c index e8b7815d8cae..fc40dd10efa8 100644 --- a/drivers/gpu/drm/tiny/st7735r.c +++ b/drivers/gpu/drm/tiny/st7735r.c @@ -136,7 +136,6 @@ static const struct drm_simple_display_pipe_funcs st7735r_pipe_funcs = { .enable = st7735r_pipe_enable, .disable = mipi_dbi_pipe_disable, .update = mipi_dbi_pipe_update, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, }; static const struct st7735r_cfg jd_t18003_t01_cfg = { diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 1b950b45cf4b..20fbfd922266 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -485,6 +485,31 @@ void ttm_bo_unlock_delayed_workqueue(struct ttm_device *bdev, int resched) } EXPORT_SYMBOL(ttm_bo_unlock_delayed_workqueue); +static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo, + struct ttm_resource **mem, + struct ttm_operation_ctx *ctx, + struct ttm_place *hop) +{ + struct ttm_placement hop_placement; + struct ttm_resource *hop_mem; + int ret; + + hop_placement.num_placement = hop_placement.num_busy_placement = 1; + hop_placement.placement = hop_placement.busy_placement = hop; + + /* find space in the bounce domain */ + ret = ttm_bo_mem_space(bo, &hop_placement, &hop_mem, ctx); + if (ret) + return ret; + /* move to the bounce domain */ + ret = ttm_bo_handle_move_mem(bo, hop_mem, false, ctx, NULL); + if (ret) { + ttm_resource_free(bo, &hop_mem); + return ret; + } + return 0; +} + static int ttm_bo_evict(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx) { @@ -524,12 +549,17 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, goto out; } +bounce: ret = ttm_bo_handle_move_mem(bo, evict_mem, true, ctx, &hop); - if (unlikely(ret)) { - WARN(ret == -EMULTIHOP, "Unexpected multihop in eviction - likely driver bug\n"); - if (ret != -ERESTARTSYS) + if (ret == -EMULTIHOP) { + ret = ttm_bo_bounce_temp_buffer(bo, &evict_mem, ctx, &hop); + if (ret) { pr_err("Buffer eviction failed\n"); - ttm_resource_free(bo, &evict_mem); + ttm_resource_free(bo, &evict_mem); + goto out; + } + /* try and move to final place now. */ + goto bounce; } out: return ret; @@ -844,31 +874,6 @@ error: } EXPORT_SYMBOL(ttm_bo_mem_space); -static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo, - struct ttm_resource **mem, - struct ttm_operation_ctx *ctx, - struct ttm_place *hop) -{ - struct ttm_placement hop_placement; - struct ttm_resource *hop_mem; - int ret; - - hop_placement.num_placement = hop_placement.num_busy_placement = 1; - hop_placement.placement = hop_placement.busy_placement = hop; - - /* find space in the bounce domain */ - ret = ttm_bo_mem_space(bo, &hop_placement, &hop_mem, ctx); - if (ret) - return ret; - /* move to the bounce domain */ - ret = ttm_bo_handle_move_mem(bo, hop_mem, false, ctx, NULL); - if (ret) { - ttm_resource_free(bo, &hop_mem); - return ret; - } - return 0; -} - static int ttm_bo_move_buffer(struct ttm_buffer_object *bo, struct ttm_placement *placement, struct ttm_operation_ctx *ctx) @@ -913,6 +918,9 @@ static bool ttm_bo_places_compat(const struct ttm_place *places, { unsigned i; + if (mem->placement & TTM_PL_FLAG_TEMPORARY) + return false; + for (i = 0; i < num_placement; i++) { const struct ttm_place *heap = &places[i]; diff --git a/drivers/gpu/drm/tve200/tve200_display.c b/drivers/gpu/drm/tve200/tve200_display.c index 50e1fb71869f..17b8c8dd169d 100644 --- a/drivers/gpu/drm/tve200/tve200_display.c +++ b/drivers/gpu/drm/tve200/tve200_display.c @@ -316,7 +316,6 @@ static const struct drm_simple_display_pipe_funcs tve200_display_funcs = { .enable = tve200_display_enable, .disable = tve200_display_disable, .update = tve200_display_update, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, .enable_vblank = tve200_display_enable_vblank, .disable_vblank = tve200_display_disable_vblank, }; diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 8992480c88fa..a39bdd5cfc4f 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -402,7 +402,7 @@ v3d_sched_init(struct v3d_dev *v3d) ret = drm_sched_init(&v3d->queue[V3D_BIN].sched, &v3d_bin_sched_ops, hw_jobs_limit, job_hang_limit, - msecs_to_jiffies(hang_limit_ms), + msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_bin"); if (ret) { dev_err(v3d->drm.dev, "Failed to create bin scheduler: %d.", ret); @@ -412,7 +412,7 @@ v3d_sched_init(struct v3d_dev *v3d) ret = drm_sched_init(&v3d->queue[V3D_RENDER].sched, &v3d_render_sched_ops, hw_jobs_limit, job_hang_limit, - msecs_to_jiffies(hang_limit_ms), + msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_render"); if (ret) { dev_err(v3d->drm.dev, "Failed to create render scheduler: %d.", @@ -424,7 +424,7 @@ v3d_sched_init(struct v3d_dev *v3d) ret = drm_sched_init(&v3d->queue[V3D_TFU].sched, &v3d_tfu_sched_ops, hw_jobs_limit, job_hang_limit, - msecs_to_jiffies(hang_limit_ms), + msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_tfu"); if (ret) { dev_err(v3d->drm.dev, "Failed to create TFU scheduler: %d.", @@ -437,7 +437,7 @@ v3d_sched_init(struct v3d_dev *v3d) ret = drm_sched_init(&v3d->queue[V3D_CSD].sched, &v3d_csd_sched_ops, hw_jobs_limit, job_hang_limit, - msecs_to_jiffies(hang_limit_ms), + msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_csd"); if (ret) { dev_err(v3d->drm.dev, "Failed to create CSD scheduler: %d.", @@ -449,7 +449,7 @@ v3d_sched_init(struct v3d_dev *v3d) ret = drm_sched_init(&v3d->queue[V3D_CACHE_CLEAN].sched, &v3d_cache_clean_sched_ops, hw_jobs_limit, job_hang_limit, - msecs_to_jiffies(hang_limit_ms), + msecs_to_jiffies(hang_limit_ms), NULL, NULL, "v3d_cache_clean"); if (ret) { dev_err(v3d->drm.dev, "Failed to create CACHE_CLEAN scheduler: %d.", diff --git a/drivers/gpu/drm/vboxvideo/vbox_drv.c b/drivers/gpu/drm/vboxvideo/vbox_drv.c index 6d4b32da9866..2b81cb259d23 100644 --- a/drivers/gpu/drm/vboxvideo/vbox_drv.c +++ b/drivers/gpu/drm/vboxvideo/vbox_drv.c @@ -43,7 +43,7 @@ static int vbox_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!vbox_check_supported(VBE_DISPI_ID_HGSMI)) return -ENODEV; - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "vboxvideodrmfb"); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &driver); if (ret) return ret; @@ -184,7 +184,6 @@ static const struct drm_driver driver = { .lastclose = drm_fb_helper_lastclose, .fops = &vbox_fops, - .irq_handler = vbox_irq_handler, .name = DRIVER_NAME, .desc = DRIVER_DESC, .date = DRIVER_DATE, diff --git a/drivers/gpu/drm/vboxvideo/vbox_drv.h b/drivers/gpu/drm/vboxvideo/vbox_drv.h index ac7c2effc46f..4903b91d7fe4 100644 --- a/drivers/gpu/drm/vboxvideo/vbox_drv.h +++ b/drivers/gpu/drm/vboxvideo/vbox_drv.h @@ -145,7 +145,6 @@ void vbox_mm_fini(struct vbox_private *vbox); int vbox_irq_init(struct vbox_private *vbox); void vbox_irq_fini(struct vbox_private *vbox); void vbox_report_hotplug(struct vbox_private *vbox); -irqreturn_t vbox_irq_handler(int irq, void *arg); /* vbox_hgsmi.c */ void *hgsmi_buffer_alloc(struct gen_pool *guest_pool, size_t size, diff --git a/drivers/gpu/drm/vboxvideo/vbox_irq.c b/drivers/gpu/drm/vboxvideo/vbox_irq.c index b3ded68603ba..903a6c48ee8b 100644 --- a/drivers/gpu/drm/vboxvideo/vbox_irq.c +++ b/drivers/gpu/drm/vboxvideo/vbox_irq.c @@ -10,7 +10,8 @@ */ #include <linux/pci.h> -#include <drm/drm_irq.h> + +#include <drm/drm_drv.h> #include <drm/drm_probe_helper.h> #include "vbox_drv.h" @@ -31,7 +32,7 @@ void vbox_report_hotplug(struct vbox_private *vbox) schedule_work(&vbox->hotplug_work); } -irqreturn_t vbox_irq_handler(int irq, void *arg) +static irqreturn_t vbox_irq_handler(int irq, void *arg) { struct drm_device *dev = (struct drm_device *)arg; struct vbox_private *vbox = to_vbox_dev(dev); @@ -170,16 +171,21 @@ static void vbox_hotplug_worker(struct work_struct *work) int vbox_irq_init(struct vbox_private *vbox) { - struct pci_dev *pdev = to_pci_dev(vbox->ddev.dev); + struct drm_device *dev = &vbox->ddev; + struct pci_dev *pdev = to_pci_dev(dev->dev); INIT_WORK(&vbox->hotplug_work, vbox_hotplug_worker); vbox_update_mode_hints(vbox); - return drm_irq_install(&vbox->ddev, pdev->irq); + /* PCI devices require shared interrupts. */ + return request_irq(pdev->irq, vbox_irq_handler, IRQF_SHARED, dev->driver->name, dev); } void vbox_irq_fini(struct vbox_private *vbox) { - drm_irq_uninstall(&vbox->ddev); + struct drm_device *dev = &vbox->ddev; + struct pci_dev *pdev = to_pci_dev(dev->dev); + + free_irq(pdev->irq, dev); flush_work(&vbox->hotplug_work); } diff --git a/drivers/gpu/drm/vboxvideo/vbox_mode.c b/drivers/gpu/drm/vboxvideo/vbox_mode.c index 964381d55fc1..972c83b720aa 100644 --- a/drivers/gpu/drm/vboxvideo/vbox_mode.c +++ b/drivers/gpu/drm/vboxvideo/vbox_mode.c @@ -488,8 +488,7 @@ static const struct drm_plane_helper_funcs vbox_primary_helper_funcs = { .atomic_check = vbox_primary_atomic_check, .atomic_update = vbox_primary_atomic_update, .atomic_disable = vbox_primary_atomic_disable, - .prepare_fb = drm_gem_vram_plane_helper_prepare_fb, - .cleanup_fb = drm_gem_vram_plane_helper_cleanup_fb, + DRM_GEM_VRAM_PLANE_HELPER_FUNCS, }; static const struct drm_plane_funcs vbox_primary_plane_funcs = { diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig index 118e8a426b1a..345a5570a3da 100644 --- a/drivers/gpu/drm/vc4/Kconfig +++ b/drivers/gpu/drm/vc4/Kconfig @@ -12,6 +12,7 @@ config DRM_VC4 select SND_PCM select SND_PCM_ELD select SND_SOC_GENERIC_DMAENGINE_PCM + select SND_SOC_HDMI_CODEC select DRM_MIPI_DSI help Choose this option if you have a system that has a Broadcom diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index 8a60fb8ad370..73335feb712f 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -265,7 +265,7 @@ static int vc4_drm_bind(struct device *dev) if (ret) goto unbind_all; - ret = drm_aperture_remove_framebuffers(false, "vc4drmfb"); + ret = drm_aperture_remove_framebuffers(false, &vc4_drm_driver); if (ret) goto unbind_all; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index aab1b36ceb3c..d4833c878ca9 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -46,6 +46,7 @@ #include <linux/rational.h> #include <linux/reset.h> #include <sound/dmaengine_pcm.h> +#include <sound/hdmi-codec.h> #include <sound/pcm_drm_eld.h> #include <sound/pcm_params.h> #include <sound/soc.h> @@ -435,7 +436,7 @@ static void vc4_hdmi_set_avi_infoframe(struct drm_encoder *encoder) struct vc4_hdmi_encoder *vc4_encoder = to_vc4_hdmi_encoder(encoder); struct drm_connector *connector = &vc4_hdmi->connector; struct drm_connector_state *cstate = connector->state; - struct drm_crtc *crtc = encoder->crtc; + struct drm_crtc *crtc = cstate->crtc; const struct drm_display_mode *mode = &crtc->state->adjusted_mode; union hdmi_infoframe frame; int ret; @@ -477,15 +478,10 @@ static void vc4_hdmi_set_spd_infoframe(struct drm_encoder *encoder) static void vc4_hdmi_set_audio_infoframe(struct drm_encoder *encoder) { struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); + struct hdmi_audio_infoframe *audio = &vc4_hdmi->audio.infoframe; union hdmi_infoframe frame; - hdmi_audio_infoframe_init(&frame.audio); - - frame.audio.coding_type = HDMI_AUDIO_CODING_TYPE_STREAM; - frame.audio.sample_frequency = HDMI_AUDIO_SAMPLE_FREQUENCY_STREAM; - frame.audio.sample_size = HDMI_AUDIO_SAMPLE_SIZE_STREAM; - frame.audio.channels = vc4_hdmi->audio.channels; - + memcpy(&frame.audio, audio, sizeof(*audio)); vc4_hdmi_write_infoframe(encoder, &frame); } @@ -545,8 +541,11 @@ static bool vc4_hdmi_supports_scrambling(struct drm_encoder *encoder, static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder) { - struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); + struct drm_connector *connector = &vc4_hdmi->connector; + struct drm_connector_state *cstate = connector->state; + struct drm_crtc *crtc = cstate->crtc; + struct drm_display_mode *mode = &crtc->state->adjusted_mode; if (!vc4_hdmi_supports_scrambling(encoder, mode)) return; @@ -567,17 +566,18 @@ static void vc4_hdmi_enable_scrambling(struct drm_encoder *encoder) static void vc4_hdmi_disable_scrambling(struct drm_encoder *encoder) { struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); - struct drm_crtc *crtc = encoder->crtc; + struct drm_connector *connector = &vc4_hdmi->connector; + struct drm_connector_state *cstate = connector->state; /* - * At boot, encoder->crtc will be NULL. Since we don't know the + * At boot, connector->state will be NULL. Since we don't know the * state of the scrambler and in order to avoid any * inconsistency, let's disable it all the time. */ - if (crtc && !vc4_hdmi_supports_scrambling(encoder, &crtc->mode)) + if (cstate && !vc4_hdmi_supports_scrambling(encoder, &cstate->crtc->mode)) return; - if (crtc && !vc4_hdmi_mode_needs_scrambling(&crtc->mode)) + if (cstate && !vc4_hdmi_mode_needs_scrambling(&cstate->crtc->mode)) return; if (delayed_work_pending(&vc4_hdmi->scrambling_work)) @@ -613,12 +613,12 @@ static void vc4_hdmi_encoder_post_crtc_disable(struct drm_encoder *encoder, HDMI_WRITE(HDMI_RAM_PACKET_CONFIG, 0); - HDMI_WRITE(HDMI_VID_CTL, HDMI_READ(HDMI_VID_CTL) | - VC4_HD_VID_CTL_CLRRGB | VC4_HD_VID_CTL_CLRSYNC); + HDMI_WRITE(HDMI_VID_CTL, HDMI_READ(HDMI_VID_CTL) | VC4_HD_VID_CTL_CLRRGB); - HDMI_WRITE(HDMI_VID_CTL, - HDMI_READ(HDMI_VID_CTL) | VC4_HD_VID_CTL_BLANKPIX); + mdelay(1); + HDMI_WRITE(HDMI_VID_CTL, + HDMI_READ(HDMI_VID_CTL) & ~VC4_HD_VID_CTL_ENABLE); vc4_hdmi_disable_scrambling(encoder); } @@ -628,12 +628,12 @@ static void vc4_hdmi_encoder_post_crtc_powerdown(struct drm_encoder *encoder, struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); int ret; + HDMI_WRITE(HDMI_VID_CTL, + HDMI_READ(HDMI_VID_CTL) | VC4_HD_VID_CTL_BLANKPIX); + if (vc4_hdmi->variant->phy_disable) vc4_hdmi->variant->phy_disable(vc4_hdmi); - HDMI_WRITE(HDMI_VID_CTL, - HDMI_READ(HDMI_VID_CTL) & ~VC4_HD_VID_CTL_ENABLE); - clk_disable_unprepare(vc4_hdmi->pixel_bvb_clock); clk_disable_unprepare(vc4_hdmi->pixel_clock); @@ -898,7 +898,9 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder, vc4_hdmi_encoder_get_connector_state(encoder, state); struct vc4_hdmi_connector_state *vc4_conn_state = conn_state_to_vc4_hdmi_conn_state(conn_state); - struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; + struct drm_crtc_state *crtc_state = + drm_atomic_get_new_crtc_state(state, conn_state->crtc); + struct drm_display_mode *mode = &crtc_state->adjusted_mode; struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); unsigned long bvb_rate, pixel_rate, hsm_rate; int ret; @@ -983,7 +985,11 @@ static void vc4_hdmi_encoder_pre_crtc_configure(struct drm_encoder *encoder, static void vc4_hdmi_encoder_pre_crtc_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { - struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; + struct drm_connector_state *conn_state = + vc4_hdmi_encoder_get_connector_state(encoder, state); + struct drm_crtc_state *crtc_state = + drm_atomic_get_new_crtc_state(state, conn_state->crtc); + struct drm_display_mode *mode = &crtc_state->adjusted_mode; struct vc4_hdmi_encoder *vc4_encoder = to_vc4_hdmi_encoder(encoder); struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); @@ -1006,7 +1012,11 @@ static void vc4_hdmi_encoder_pre_crtc_enable(struct drm_encoder *encoder, static void vc4_hdmi_encoder_post_crtc_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { - struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; + struct drm_connector_state *conn_state = + vc4_hdmi_encoder_get_connector_state(encoder, state); + struct drm_crtc_state *crtc_state = + drm_atomic_get_new_crtc_state(state, conn_state->crtc); + struct drm_display_mode *mode = &crtc_state->adjusted_mode; struct vc4_hdmi *vc4_hdmi = encoder_to_vc4_hdmi(encoder); struct vc4_hdmi_encoder *vc4_encoder = to_vc4_hdmi_encoder(encoder); bool hsync_pos = mode->flags & DRM_MODE_FLAG_PHSYNC; @@ -1015,6 +1025,7 @@ static void vc4_hdmi_encoder_post_crtc_enable(struct drm_encoder *encoder, HDMI_WRITE(HDMI_VID_CTL, VC4_HD_VID_CTL_ENABLE | + VC4_HD_VID_CTL_CLRRGB | VC4_HD_VID_CTL_UNDERFLOW_ENABLE | VC4_HD_VID_CTL_FRAME_COUNTER_RESET | (vsync_pos ? 0 : VC4_HD_VID_CTL_VSYNC_LOW) | @@ -1192,8 +1203,8 @@ static void vc4_hdmi_audio_set_mai_clock(struct vc4_hdmi *vc4_hdmi) static void vc4_hdmi_set_n_cts(struct vc4_hdmi *vc4_hdmi) { - struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base; - struct drm_crtc *crtc = encoder->crtc; + struct drm_connector *connector = &vc4_hdmi->connector; + struct drm_crtc *crtc = connector->state->crtc; const struct drm_display_mode *mode = &crtc->state->adjusted_mode; u32 samplerate = vc4_hdmi->audio.samplerate; u32 n, cts; @@ -1224,36 +1235,31 @@ static inline struct vc4_hdmi *dai_to_hdmi(struct snd_soc_dai *dai) return snd_soc_card_get_drvdata(card); } -static int vc4_hdmi_audio_startup(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) +static int vc4_hdmi_audio_startup(struct device *dev, void *data) { - struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai); - struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base; + struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev); struct drm_connector *connector = &vc4_hdmi->connector; - int ret; - - if (vc4_hdmi->audio.substream && vc4_hdmi->audio.substream != substream) - return -EINVAL; - - vc4_hdmi->audio.substream = substream; /* * If the HDMI encoder hasn't probed, or the encoder is * currently in DVI mode, treat the codec dai as missing. */ - if (!encoder->crtc || !(HDMI_READ(HDMI_RAM_PACKET_CONFIG) & + if (!connector->state || !(HDMI_READ(HDMI_RAM_PACKET_CONFIG) & VC4_HDMI_RAM_PACKET_ENABLE)) return -ENODEV; - ret = snd_pcm_hw_constraint_eld(substream->runtime, connector->eld); - if (ret) - return ret; + vc4_hdmi->audio.streaming = true; - return 0; -} + HDMI_WRITE(HDMI_MAI_CTL, + VC4_HD_MAI_CTL_RESET | + VC4_HD_MAI_CTL_FLUSH | + VC4_HD_MAI_CTL_DLATE | + VC4_HD_MAI_CTL_ERRORE | + VC4_HD_MAI_CTL_ERRORF); + + if (vc4_hdmi->variant->phy_rng_enable) + vc4_hdmi->variant->phy_rng_enable(vc4_hdmi); -static int vc4_hdmi_audio_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) -{ return 0; } @@ -1273,49 +1279,99 @@ static void vc4_hdmi_audio_reset(struct vc4_hdmi *vc4_hdmi) HDMI_WRITE(HDMI_MAI_CTL, VC4_HD_MAI_CTL_FLUSH); } -static void vc4_hdmi_audio_shutdown(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) +static void vc4_hdmi_audio_shutdown(struct device *dev, void *data) { - struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai); + struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev); - if (substream != vc4_hdmi->audio.substream) - return; + HDMI_WRITE(HDMI_MAI_CTL, + VC4_HD_MAI_CTL_DLATE | + VC4_HD_MAI_CTL_ERRORE | + VC4_HD_MAI_CTL_ERRORF); + + if (vc4_hdmi->variant->phy_rng_disable) + vc4_hdmi->variant->phy_rng_disable(vc4_hdmi); + vc4_hdmi->audio.streaming = false; vc4_hdmi_audio_reset(vc4_hdmi); +} - vc4_hdmi->audio.substream = NULL; +static int sample_rate_to_mai_fmt(int samplerate) +{ + switch (samplerate) { + case 8000: + return VC4_HDMI_MAI_SAMPLE_RATE_8000; + case 11025: + return VC4_HDMI_MAI_SAMPLE_RATE_11025; + case 12000: + return VC4_HDMI_MAI_SAMPLE_RATE_12000; + case 16000: + return VC4_HDMI_MAI_SAMPLE_RATE_16000; + case 22050: + return VC4_HDMI_MAI_SAMPLE_RATE_22050; + case 24000: + return VC4_HDMI_MAI_SAMPLE_RATE_24000; + case 32000: + return VC4_HDMI_MAI_SAMPLE_RATE_32000; + case 44100: + return VC4_HDMI_MAI_SAMPLE_RATE_44100; + case 48000: + return VC4_HDMI_MAI_SAMPLE_RATE_48000; + case 64000: + return VC4_HDMI_MAI_SAMPLE_RATE_64000; + case 88200: + return VC4_HDMI_MAI_SAMPLE_RATE_88200; + case 96000: + return VC4_HDMI_MAI_SAMPLE_RATE_96000; + case 128000: + return VC4_HDMI_MAI_SAMPLE_RATE_128000; + case 176400: + return VC4_HDMI_MAI_SAMPLE_RATE_176400; + case 192000: + return VC4_HDMI_MAI_SAMPLE_RATE_192000; + default: + return VC4_HDMI_MAI_SAMPLE_RATE_NOT_INDICATED; + } } /* HDMI audio codec callbacks */ -static int vc4_hdmi_audio_hw_params(struct snd_pcm_substream *substream, - struct snd_pcm_hw_params *params, - struct snd_soc_dai *dai) +static int vc4_hdmi_audio_prepare(struct device *dev, void *data, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params) { - struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai); + struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev); struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base; - struct device *dev = &vc4_hdmi->pdev->dev; u32 audio_packet_config, channel_mask; u32 channel_map; - - if (substream != vc4_hdmi->audio.substream) - return -EINVAL; + u32 mai_audio_format; + u32 mai_sample_rate; dev_dbg(dev, "%s: %u Hz, %d bit, %d channels\n", __func__, - params_rate(params), params_width(params), - params_channels(params)); + params->sample_rate, params->sample_width, + params->channels); - vc4_hdmi->audio.channels = params_channels(params); - vc4_hdmi->audio.samplerate = params_rate(params); + vc4_hdmi->audio.channels = params->channels; + vc4_hdmi->audio.samplerate = params->sample_rate; HDMI_WRITE(HDMI_MAI_CTL, - VC4_HD_MAI_CTL_RESET | - VC4_HD_MAI_CTL_FLUSH | - VC4_HD_MAI_CTL_DLATE | - VC4_HD_MAI_CTL_ERRORE | - VC4_HD_MAI_CTL_ERRORF); + VC4_SET_FIELD(params->channels, VC4_HD_MAI_CTL_CHNUM) | + VC4_HD_MAI_CTL_WHOLSMP | + VC4_HD_MAI_CTL_CHALIGN | + VC4_HD_MAI_CTL_ENABLE); vc4_hdmi_audio_set_mai_clock(vc4_hdmi); + mai_sample_rate = sample_rate_to_mai_fmt(vc4_hdmi->audio.samplerate); + if (params->iec.status[0] & IEC958_AES0_NONAUDIO && + params->channels == 8) + mai_audio_format = VC4_HDMI_MAI_FORMAT_HBR; + else + mai_audio_format = VC4_HDMI_MAI_FORMAT_PCM; + HDMI_WRITE(HDMI_MAI_FMT, + VC4_SET_FIELD(mai_sample_rate, + VC4_HDMI_MAI_FORMAT_SAMPLE_RATE) | + VC4_SET_FIELD(mai_audio_format, + VC4_HDMI_MAI_FORMAT_AUDIO_FORMAT)); + /* The B frame identifier should match the value used by alsa-lib (8) */ audio_packet_config = VC4_HDMI_AUDIO_PACKET_ZERO_DATA_ON_SAMPLE_FLAT | @@ -1326,25 +1382,16 @@ static int vc4_hdmi_audio_hw_params(struct snd_pcm_substream *substream, audio_packet_config |= VC4_SET_FIELD(channel_mask, VC4_HDMI_AUDIO_PACKET_CEA_MASK); - /* Set the MAI threshold. This logic mimics the firmware's. */ - if (vc4_hdmi->audio.samplerate > 96000) { - HDMI_WRITE(HDMI_MAI_THR, - VC4_SET_FIELD(0x12, VC4_HD_MAI_THR_DREQHIGH) | - VC4_SET_FIELD(0x12, VC4_HD_MAI_THR_DREQLOW)); - } else if (vc4_hdmi->audio.samplerate > 48000) { - HDMI_WRITE(HDMI_MAI_THR, - VC4_SET_FIELD(0x14, VC4_HD_MAI_THR_DREQHIGH) | - VC4_SET_FIELD(0x12, VC4_HD_MAI_THR_DREQLOW)); - } else { - HDMI_WRITE(HDMI_MAI_THR, - VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_PANICHIGH) | - VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_PANICLOW) | - VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_DREQHIGH) | - VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_DREQLOW)); - } + /* Set the MAI threshold */ + HDMI_WRITE(HDMI_MAI_THR, + VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_PANICHIGH) | + VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_PANICLOW) | + VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_DREQHIGH) | + VC4_SET_FIELD(0x10, VC4_HD_MAI_THR_DREQLOW)); HDMI_WRITE(HDMI_MAI_CONFIG, VC4_HDMI_MAI_CONFIG_BIT_REVERSE | + VC4_HDMI_MAI_CONFIG_FORMAT_REVERSE | VC4_SET_FIELD(channel_mask, VC4_HDMI_MAI_CHANNEL_MASK)); channel_map = vc4_hdmi->variant->channel_map(vc4_hdmi, channel_mask); @@ -1352,92 +1399,12 @@ static int vc4_hdmi_audio_hw_params(struct snd_pcm_substream *substream, HDMI_WRITE(HDMI_AUDIO_PACKET_CONFIG, audio_packet_config); vc4_hdmi_set_n_cts(vc4_hdmi); + memcpy(&vc4_hdmi->audio.infoframe, ¶ms->cea, sizeof(params->cea)); vc4_hdmi_set_audio_infoframe(encoder); return 0; } -static int vc4_hdmi_audio_trigger(struct snd_pcm_substream *substream, int cmd, - struct snd_soc_dai *dai) -{ - struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai); - - switch (cmd) { - case SNDRV_PCM_TRIGGER_START: - vc4_hdmi->audio.streaming = true; - - if (vc4_hdmi->variant->phy_rng_enable) - vc4_hdmi->variant->phy_rng_enable(vc4_hdmi); - - HDMI_WRITE(HDMI_MAI_CTL, - VC4_SET_FIELD(vc4_hdmi->audio.channels, - VC4_HD_MAI_CTL_CHNUM) | - VC4_HD_MAI_CTL_ENABLE); - break; - case SNDRV_PCM_TRIGGER_STOP: - HDMI_WRITE(HDMI_MAI_CTL, - VC4_HD_MAI_CTL_DLATE | - VC4_HD_MAI_CTL_ERRORE | - VC4_HD_MAI_CTL_ERRORF); - - if (vc4_hdmi->variant->phy_rng_disable) - vc4_hdmi->variant->phy_rng_disable(vc4_hdmi); - - vc4_hdmi->audio.streaming = false; - - break; - default: - break; - } - - return 0; -} - -static inline struct vc4_hdmi * -snd_component_to_hdmi(struct snd_soc_component *component) -{ - struct snd_soc_card *card = snd_soc_component_get_drvdata(component); - - return snd_soc_card_get_drvdata(card); -} - -static int vc4_hdmi_audio_eld_ctl_info(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_info *uinfo) -{ - struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); - struct vc4_hdmi *vc4_hdmi = snd_component_to_hdmi(component); - struct drm_connector *connector = &vc4_hdmi->connector; - - uinfo->type = SNDRV_CTL_ELEM_TYPE_BYTES; - uinfo->count = sizeof(connector->eld); - - return 0; -} - -static int vc4_hdmi_audio_eld_ctl_get(struct snd_kcontrol *kcontrol, - struct snd_ctl_elem_value *ucontrol) -{ - struct snd_soc_component *component = snd_kcontrol_chip(kcontrol); - struct vc4_hdmi *vc4_hdmi = snd_component_to_hdmi(component); - struct drm_connector *connector = &vc4_hdmi->connector; - - memcpy(ucontrol->value.bytes.data, connector->eld, - sizeof(connector->eld)); - - return 0; -} - -static const struct snd_kcontrol_new vc4_hdmi_audio_controls[] = { - { - .access = SNDRV_CTL_ELEM_ACCESS_READ | - SNDRV_CTL_ELEM_ACCESS_VOLATILE, - .iface = SNDRV_CTL_ELEM_IFACE_PCM, - .name = "ELD", - .info = vc4_hdmi_audio_eld_ctl_info, - .get = vc4_hdmi_audio_eld_ctl_get, - }, -}; - static const struct snd_soc_dapm_widget vc4_hdmi_audio_widgets[] = { SND_SOC_DAPM_OUTPUT("TX"), }; @@ -1448,8 +1415,6 @@ static const struct snd_soc_dapm_route vc4_hdmi_audio_routes[] = { static const struct snd_soc_component_driver vc4_hdmi_audio_component_drv = { .name = "vc4-hdmi-codec-dai-component", - .controls = vc4_hdmi_audio_controls, - .num_controls = ARRAY_SIZE(vc4_hdmi_audio_controls), .dapm_widgets = vc4_hdmi_audio_widgets, .num_dapm_widgets = ARRAY_SIZE(vc4_hdmi_audio_widgets), .dapm_routes = vc4_hdmi_audio_routes, @@ -1460,28 +1425,6 @@ static const struct snd_soc_component_driver vc4_hdmi_audio_component_drv = { .non_legacy_dai_naming = 1, }; -static const struct snd_soc_dai_ops vc4_hdmi_audio_dai_ops = { - .startup = vc4_hdmi_audio_startup, - .shutdown = vc4_hdmi_audio_shutdown, - .hw_params = vc4_hdmi_audio_hw_params, - .set_fmt = vc4_hdmi_audio_set_fmt, - .trigger = vc4_hdmi_audio_trigger, -}; - -static struct snd_soc_dai_driver vc4_hdmi_audio_codec_dai_drv = { - .name = "vc4-hdmi-hifi", - .playback = { - .stream_name = "Playback", - .channels_min = 2, - .channels_max = 8, - .rates = SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_44100 | - SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_88200 | - SNDRV_PCM_RATE_96000 | SNDRV_PCM_RATE_176400 | - SNDRV_PCM_RATE_192000, - .formats = SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_LE, - }, -}; - static const struct snd_soc_component_driver vc4_hdmi_audio_cpu_dai_comp = { .name = "vc4-hdmi-cpu-dai-component", }; @@ -1508,7 +1451,6 @@ static struct snd_soc_dai_driver vc4_hdmi_audio_cpu_dai_drv = { SNDRV_PCM_RATE_192000, .formats = SNDRV_PCM_FMTBIT_IEC958_SUBFRAME_LE, }, - .ops = &vc4_hdmi_audio_dai_ops, }; static const struct snd_dmaengine_pcm_config pcm_conf = { @@ -1516,6 +1458,30 @@ static const struct snd_dmaengine_pcm_config pcm_conf = { .prepare_slave_config = snd_dmaengine_pcm_prepare_slave_config, }; +static int vc4_hdmi_audio_get_eld(struct device *dev, void *data, + uint8_t *buf, size_t len) +{ + struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev); + struct drm_connector *connector = &vc4_hdmi->connector; + + memcpy(buf, connector->eld, min(sizeof(connector->eld), len)); + + return 0; +} + +static const struct hdmi_codec_ops vc4_hdmi_codec_ops = { + .get_eld = vc4_hdmi_audio_get_eld, + .prepare = vc4_hdmi_audio_prepare, + .audio_shutdown = vc4_hdmi_audio_shutdown, + .audio_startup = vc4_hdmi_audio_startup, +}; + +struct hdmi_codec_pdata vc4_hdmi_codec_pdata = { + .ops = &vc4_hdmi_codec_ops, + .max_i2s_channels = 8, + .i2s = 1, +}; + static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) { const struct vc4_hdmi_register *mai_data = @@ -1523,6 +1489,7 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) struct snd_soc_dai_link *dai_link = &vc4_hdmi->audio.link; struct snd_soc_card *card = &vc4_hdmi->audio.card; struct device *dev = &vc4_hdmi->pdev->dev; + struct platform_device *codec_pdev; const __be32 *addr; int index; int ret; @@ -1569,12 +1536,13 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) return ret; } - /* register component and codec dai */ - ret = devm_snd_soc_register_component(dev, &vc4_hdmi_audio_component_drv, - &vc4_hdmi_audio_codec_dai_drv, 1); - if (ret) { - dev_err(dev, "Could not register component: %d\n", ret); - return ret; + codec_pdev = platform_device_register_data(dev, HDMI_CODEC_DRV_NAME, + PLATFORM_DEVID_AUTO, + &vc4_hdmi_codec_pdata, + sizeof(vc4_hdmi_codec_pdata)); + if (IS_ERR(codec_pdev)) { + dev_err(dev, "Couldn't register the HDMI codec: %ld\n", PTR_ERR(codec_pdev)); + return PTR_ERR(codec_pdev); } dai_link->cpus = &vc4_hdmi->audio.cpu; @@ -1587,9 +1555,9 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) dai_link->name = "MAI"; dai_link->stream_name = "MAI PCM"; - dai_link->codecs->dai_name = vc4_hdmi_audio_codec_dai_drv.name; + dai_link->codecs->dai_name = "i2s-hifi"; dai_link->cpus->dai_name = dev_name(dev); - dai_link->codecs->name = dev_name(dev); + dai_link->codecs->name = dev_name(&codec_pdev->dev); dai_link->platforms->name = dev_name(dev); card->dai_link = dai_link; @@ -1609,12 +1577,65 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) snd_soc_card_set_drvdata(card, vc4_hdmi); ret = devm_snd_soc_register_card(dev, card); if (ret) - dev_err(dev, "Could not register sound card: %d\n", ret); + dev_err_probe(dev, ret, "Could not register sound card\n"); return ret; } +static irqreturn_t vc4_hdmi_hpd_irq_thread(int irq, void *priv) +{ + struct vc4_hdmi *vc4_hdmi = priv; + struct drm_device *dev = vc4_hdmi->connector.dev; + + if (dev && dev->registered) + drm_kms_helper_hotplug_event(dev); + + return IRQ_HANDLED; +} + +static int vc4_hdmi_hotplug_init(struct vc4_hdmi *vc4_hdmi) +{ + struct drm_connector *connector = &vc4_hdmi->connector; + struct platform_device *pdev = vc4_hdmi->pdev; + int ret; + + if (vc4_hdmi->variant->external_irq_controller) { + unsigned int hpd_con = platform_get_irq_byname(pdev, "hpd-connected"); + unsigned int hpd_rm = platform_get_irq_byname(pdev, "hpd-removed"); + + ret = request_threaded_irq(hpd_con, + NULL, + vc4_hdmi_hpd_irq_thread, IRQF_ONESHOT, + "vc4 hdmi hpd connected", vc4_hdmi); + if (ret) + return ret; + + ret = request_threaded_irq(hpd_rm, + NULL, + vc4_hdmi_hpd_irq_thread, IRQF_ONESHOT, + "vc4 hdmi hpd disconnected", vc4_hdmi); + if (ret) { + free_irq(hpd_con, vc4_hdmi); + return ret; + } + + connector->polled = DRM_CONNECTOR_POLL_HPD; + } + + return 0; +} + +static void vc4_hdmi_hotplug_exit(struct vc4_hdmi *vc4_hdmi) +{ + struct platform_device *pdev = vc4_hdmi->pdev; + + if (vc4_hdmi->variant->external_irq_controller) { + free_irq(platform_get_irq_byname(pdev, "hpd-connected"), vc4_hdmi); + free_irq(platform_get_irq_byname(pdev, "hpd-removed"), vc4_hdmi); + } +} + #ifdef CONFIG_DRM_VC4_HDMI_CEC static irqreturn_t vc4_cec_irq_handler_rx_thread(int irq, void *priv) { @@ -2196,10 +2217,14 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) if (ret) goto err_destroy_encoder; - ret = vc4_hdmi_cec_init(vc4_hdmi); + ret = vc4_hdmi_hotplug_init(vc4_hdmi); if (ret) goto err_destroy_conn; + ret = vc4_hdmi_cec_init(vc4_hdmi); + if (ret) + goto err_free_hotplug; + ret = vc4_hdmi_audio_init(vc4_hdmi); if (ret) goto err_free_cec; @@ -2212,6 +2237,8 @@ static int vc4_hdmi_bind(struct device *dev, struct device *master, void *data) err_free_cec: vc4_hdmi_cec_exit(vc4_hdmi); +err_free_hotplug: + vc4_hdmi_hotplug_exit(vc4_hdmi); err_destroy_conn: vc4_hdmi_connector_destroy(&vc4_hdmi->connector); err_destroy_encoder: @@ -2253,6 +2280,7 @@ static void vc4_hdmi_unbind(struct device *dev, struct device *master, kfree(vc4_hdmi->hd_regset.regs); vc4_hdmi_cec_exit(vc4_hdmi); + vc4_hdmi_hotplug_exit(vc4_hdmi); vc4_hdmi_connector_destroy(&vc4_hdmi->connector); drm_encoder_cleanup(&vc4_hdmi->encoder.base.base); diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h index 884d245507a9..b6697b695f71 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.h +++ b/drivers/gpu/drm/vc4/vc4_hdmi.h @@ -114,8 +114,7 @@ struct vc4_hdmi_audio { int samplerate; int channels; struct snd_dmaengine_dai_dma_data dma_data; - struct snd_pcm_substream *substream; - + struct hdmi_audio_infoframe infoframe; bool streaming; }; diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index 6a1a9e1d72ce..f0b3e4cf5bce 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -880,7 +880,6 @@ int vc4_kms_load(struct drm_device *dev) /* Set support for vblank irq fast disable, before drm_vblank_init() */ dev->vblank_disable_immediate = true; - dev->irq_enabled = true; ret = drm_vblank_init(dev, dev->mode_config.num_crtc); if (ret < 0) { dev_err(dev->dev, "failed to initialize vblank\n"); diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h index be2c32a519b3..489f921ef44d 100644 --- a/drivers/gpu/drm/vc4/vc4_regs.h +++ b/drivers/gpu/drm/vc4/vc4_regs.h @@ -516,6 +516,36 @@ # define VC4_HDMI_AUDIO_PACKET_CEA_MASK_MASK VC4_MASK(7, 0) # define VC4_HDMI_AUDIO_PACKET_CEA_MASK_SHIFT 0 +# define VC4_HDMI_MAI_FORMAT_AUDIO_FORMAT_MASK VC4_MASK(23, 16) +# define VC4_HDMI_MAI_FORMAT_AUDIO_FORMAT_SHIFT 16 + +enum { + VC4_HDMI_MAI_FORMAT_PCM = 2, + VC4_HDMI_MAI_FORMAT_HBR = 200, +}; + +# define VC4_HDMI_MAI_FORMAT_SAMPLE_RATE_MASK VC4_MASK(15, 8) +# define VC4_HDMI_MAI_FORMAT_SAMPLE_RATE_SHIFT 8 + +enum { + VC4_HDMI_MAI_SAMPLE_RATE_NOT_INDICATED = 0, + VC4_HDMI_MAI_SAMPLE_RATE_8000 = 1, + VC4_HDMI_MAI_SAMPLE_RATE_11025 = 2, + VC4_HDMI_MAI_SAMPLE_RATE_12000 = 3, + VC4_HDMI_MAI_SAMPLE_RATE_16000 = 4, + VC4_HDMI_MAI_SAMPLE_RATE_22050 = 5, + VC4_HDMI_MAI_SAMPLE_RATE_24000 = 6, + VC4_HDMI_MAI_SAMPLE_RATE_32000 = 7, + VC4_HDMI_MAI_SAMPLE_RATE_44100 = 8, + VC4_HDMI_MAI_SAMPLE_RATE_48000 = 9, + VC4_HDMI_MAI_SAMPLE_RATE_64000 = 10, + VC4_HDMI_MAI_SAMPLE_RATE_88200 = 11, + VC4_HDMI_MAI_SAMPLE_RATE_96000 = 12, + VC4_HDMI_MAI_SAMPLE_RATE_128000 = 13, + VC4_HDMI_MAI_SAMPLE_RATE_176400 = 14, + VC4_HDMI_MAI_SAMPLE_RATE_192000 = 15, +}; + # define VC4_HDMI_RAM_PACKET_ENABLE BIT(16) /* When set, the CTS_PERIOD counts based on MAI bus sync pulse instead diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index ca77edbc5ea0..ed85a7863256 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -57,7 +57,7 @@ static int virtio_gpu_pci_quirk(struct drm_device *dev, struct virtio_device *vd vga ? "virtio-vga" : "virtio-gpu-pci", pname); if (vga) { - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "virtiodrmfb"); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &driver); if (ret) return ret; } diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index d9dbc4f258f3..d4e610a44e12 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -315,7 +315,9 @@ void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, void virtio_gpu_cmd_resource_flush(struct virtio_gpu_device *vgdev, uint32_t resource_id, uint32_t x, uint32_t y, - uint32_t width, uint32_t height); + uint32_t width, uint32_t height, + struct virtio_gpu_object_array *objs, + struct virtio_gpu_fence *fence); void virtio_gpu_cmd_set_scanout(struct virtio_gpu_device *vgdev, uint32_t scanout_id, uint32_t resource_id, uint32_t width, uint32_t height, diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c index 4e1b17548007..a49fd9480381 100644 --- a/drivers/gpu/drm/virtio/virtgpu_plane.c +++ b/drivers/gpu/drm/virtio/virtgpu_plane.c @@ -129,6 +129,40 @@ static void virtio_gpu_update_dumb_bo(struct virtio_gpu_device *vgdev, objs, NULL); } +static void virtio_gpu_resource_flush(struct drm_plane *plane, + uint32_t x, uint32_t y, + uint32_t width, uint32_t height) +{ + struct drm_device *dev = plane->dev; + struct virtio_gpu_device *vgdev = dev->dev_private; + struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_object *bo; + + vgfb = to_virtio_gpu_framebuffer(plane->state->fb); + bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]); + if (vgfb->fence) { + struct virtio_gpu_object_array *objs; + + objs = virtio_gpu_array_alloc(1); + if (!objs) + return; + virtio_gpu_array_add_obj(objs, vgfb->base.obj[0]); + virtio_gpu_array_lock_resv(objs); + virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y, + width, height, objs, vgfb->fence); + virtio_gpu_notify(vgdev); + + dma_fence_wait_timeout(&vgfb->fence->f, true, + msecs_to_jiffies(50)); + dma_fence_put(&vgfb->fence->f); + vgfb->fence = NULL; + } else { + virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y, + width, height, NULL, NULL); + virtio_gpu_notify(vgdev); + } +} + static void virtio_gpu_primary_plane_update(struct drm_plane *plane, struct drm_atomic_state *state) { @@ -198,16 +232,15 @@ static void virtio_gpu_primary_plane_update(struct drm_plane *plane, } } - virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, - rect.x1, - rect.y1, - rect.x2 - rect.x1, - rect.y2 - rect.y1); - virtio_gpu_notify(vgdev); + virtio_gpu_resource_flush(plane, + rect.x1, + rect.y1, + rect.x2 - rect.x1, + rect.y2 - rect.y1); } -static int virtio_gpu_cursor_prepare_fb(struct drm_plane *plane, - struct drm_plane_state *new_state) +static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane, + struct drm_plane_state *new_state) { struct drm_device *dev = plane->dev; struct virtio_gpu_device *vgdev = dev->dev_private; @@ -219,7 +252,10 @@ static int virtio_gpu_cursor_prepare_fb(struct drm_plane *plane, vgfb = to_virtio_gpu_framebuffer(new_state->fb); bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]); - if (bo && bo->dumb && (plane->state->fb != new_state->fb)) { + if (!bo || (plane->type == DRM_PLANE_TYPE_PRIMARY && !bo->guest_blob)) + return 0; + + if (bo->dumb && (plane->state->fb != new_state->fb)) { vgfb->fence = virtio_gpu_fence_alloc(vgdev); if (!vgfb->fence) return -ENOMEM; @@ -228,8 +264,8 @@ static int virtio_gpu_cursor_prepare_fb(struct drm_plane *plane, return 0; } -static void virtio_gpu_cursor_cleanup_fb(struct drm_plane *plane, - struct drm_plane_state *old_state) +static void virtio_gpu_plane_cleanup_fb(struct drm_plane *plane, + struct drm_plane_state *old_state) { struct virtio_gpu_framebuffer *vgfb; @@ -321,13 +357,15 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, } static const struct drm_plane_helper_funcs virtio_gpu_primary_helper_funcs = { + .prepare_fb = virtio_gpu_plane_prepare_fb, + .cleanup_fb = virtio_gpu_plane_cleanup_fb, .atomic_check = virtio_gpu_plane_atomic_check, .atomic_update = virtio_gpu_primary_plane_update, }; static const struct drm_plane_helper_funcs virtio_gpu_cursor_helper_funcs = { - .prepare_fb = virtio_gpu_cursor_prepare_fb, - .cleanup_fb = virtio_gpu_cursor_cleanup_fb, + .prepare_fb = virtio_gpu_plane_prepare_fb, + .cleanup_fb = virtio_gpu_plane_cleanup_fb, .atomic_check = virtio_gpu_plane_atomic_check, .atomic_update = virtio_gpu_cursor_plane_update, }; diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index cf84d382dd41..2e71e91278b4 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -576,13 +576,16 @@ void virtio_gpu_cmd_set_scanout(struct virtio_gpu_device *vgdev, void virtio_gpu_cmd_resource_flush(struct virtio_gpu_device *vgdev, uint32_t resource_id, uint32_t x, uint32_t y, - uint32_t width, uint32_t height) + uint32_t width, uint32_t height, + struct virtio_gpu_object_array *objs, + struct virtio_gpu_fence *fence) { struct virtio_gpu_resource_flush *cmd_p; struct virtio_gpu_vbuffer *vbuf; cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); memset(cmd_p, 0, sizeof(*cmd_p)); + vbuf->objs = objs; cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_RESOURCE_FLUSH); cmd_p->resource_id = cpu_to_le32(resource_id); @@ -591,7 +594,7 @@ void virtio_gpu_cmd_resource_flush(struct virtio_gpu_device *vgdev, cmd_p->r.x = cpu_to_le32(x); cmd_p->r.y = cpu_to_le32(y); - virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); + virtio_gpu_queue_fenced_ctrl_buffer(vgdev, vbuf, fence); } void virtio_gpu_cmd_transfer_to_host_2d(struct virtio_gpu_device *vgdev, diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c index e49523866e1d..ead8fff81f30 100644 --- a/drivers/gpu/drm/vkms/vkms_composer.c +++ b/drivers/gpu/drm/vkms/vkms_composer.c @@ -6,7 +6,6 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_gem_framebuffer_helper.h> -#include <drm/drm_gem_shmem_helper.h> #include <drm/drm_vblank.h> #include "vkms_drv.h" @@ -154,24 +153,21 @@ static void compose_plane(struct vkms_composer *primary_composer, struct vkms_composer *plane_composer, void *vaddr_out) { - struct drm_gem_object *plane_obj; - struct drm_gem_shmem_object *plane_shmem_obj; struct drm_framebuffer *fb = &plane_composer->fb; + void *vaddr; void (*pixel_blend)(const u8 *p_src, u8 *p_dst); - plane_obj = drm_gem_fb_get_obj(&plane_composer->fb, 0); - plane_shmem_obj = to_drm_gem_shmem_obj(plane_obj); - - if (WARN_ON(!plane_shmem_obj->vaddr)) + if (WARN_ON(dma_buf_map_is_null(&primary_composer->map[0]))) return; + vaddr = plane_composer->map[0].vaddr; + if (fb->format->format == DRM_FORMAT_ARGB8888) pixel_blend = &alpha_blend; else pixel_blend = &x_blend; - blend(vaddr_out, plane_shmem_obj->vaddr, primary_composer, - plane_composer, pixel_blend); + blend(vaddr_out, vaddr, primary_composer, plane_composer, pixel_blend); } static int compose_active_planes(void **vaddr_out, @@ -180,21 +176,23 @@ static int compose_active_planes(void **vaddr_out, { struct drm_framebuffer *fb = &primary_composer->fb; struct drm_gem_object *gem_obj = drm_gem_fb_get_obj(fb, 0); - struct drm_gem_shmem_object *shmem_obj = to_drm_gem_shmem_obj(gem_obj); + const void *vaddr; int i; if (!*vaddr_out) { - *vaddr_out = kzalloc(shmem_obj->base.size, GFP_KERNEL); + *vaddr_out = kzalloc(gem_obj->size, GFP_KERNEL); if (!*vaddr_out) { DRM_ERROR("Cannot allocate memory for output frame."); return -ENOMEM; } } - if (WARN_ON(!shmem_obj->vaddr)) + if (WARN_ON(dma_buf_map_is_null(&primary_composer->map[0]))) return -EINVAL; - memcpy(*vaddr_out, shmem_obj->vaddr, shmem_obj->base.size); + vaddr = primary_composer->map[0].vaddr; + + memcpy(*vaddr_out, vaddr, gem_obj->size); /* If there are other planes besides primary, we consider the active * planes should be in z-order and compose them associatively: @@ -251,7 +249,7 @@ void vkms_composer_worker(struct work_struct *work) if (crtc_state->num_active_planes >= 1) { act_plane = crtc_state->active_planes[0]; - if (act_plane->base.plane->type == DRM_PLANE_TYPE_PRIMARY) + if (act_plane->base.base.plane->type == DRM_PLANE_TYPE_PRIMARY) primary_composer = act_plane->composer; } diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c index 027ffe759440..0ffe5f0e33f7 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.c +++ b/drivers/gpu/drm/vkms/vkms_drv.c @@ -28,6 +28,9 @@ #include "vkms_drv.h" +#include <drm/drm_print.h> +#include <drm/drm_debugfs.h> + #define DRIVER_NAME "vkms" #define DRIVER_DESC "Virtual Kernel Mode Setting" #define DRIVER_DATE "20180514" @@ -52,7 +55,7 @@ DEFINE_DRM_GEM_FOPS(vkms_driver_fops); static void vkms_release(struct drm_device *dev) { - struct vkms_device *vkms = container_of(dev, struct vkms_device, drm); + struct vkms_device *vkms = drm_device_to_vkms_device(dev); destroy_workqueue(vkms->output.composer_workq); } @@ -86,12 +89,37 @@ static void vkms_atomic_commit_tail(struct drm_atomic_state *old_state) drm_atomic_helper_cleanup_planes(dev, old_state); } +static int vkms_config_show(struct seq_file *m, void *data) +{ + struct drm_info_node *node = (struct drm_info_node *)m->private; + struct drm_device *dev = node->minor->dev; + struct vkms_device *vkmsdev = drm_device_to_vkms_device(dev); + + seq_printf(m, "writeback=%d\n", vkmsdev->config->writeback); + seq_printf(m, "cursor=%d\n", vkmsdev->config->cursor); + seq_printf(m, "overlay=%d\n", vkmsdev->config->overlay); + + return 0; +} + +static const struct drm_info_list vkms_config_debugfs_list[] = { + { "vkms_config", vkms_config_show, 0 }, +}; + +static void vkms_config_debugfs_init(struct drm_minor *minor) +{ + drm_debugfs_create_files(vkms_config_debugfs_list, ARRAY_SIZE(vkms_config_debugfs_list), + minor->debugfs_root, minor); +} + static const struct drm_driver vkms_driver = { .driver_features = DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_GEM, .release = vkms_release, .fops = &vkms_driver_fops, DRM_GEM_SHMEM_DRIVER_OPS, + .debugfs_init = vkms_config_debugfs_init, + .name = DRIVER_NAME, .desc = DRIVER_DESC, .date = DRIVER_DATE, @@ -163,8 +191,6 @@ static int vkms_create(struct vkms_config *config) goto out_devres; } - vkms_device->drm.irq_enabled = true; - ret = drm_vblank_init(&vkms_device->drm, 1); if (ret) { DRM_ERROR("Failed to vblank\n"); diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h index ac8c9c2fa4ed..8c731b6dcba7 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.h +++ b/drivers/gpu/drm/vkms/vkms_drv.h @@ -7,6 +7,7 @@ #include <drm/drm.h> #include <drm/drm_gem.h> +#include <drm/drm_gem_atomic_helper.h> #include <drm/drm_encoder.h> #include <drm/drm_writeback.h> @@ -22,6 +23,7 @@ struct vkms_composer { struct drm_framebuffer fb; struct drm_rect src, dst; + struct dma_buf_map map[4]; unsigned int offset; unsigned int pitch; unsigned int cpp; @@ -33,7 +35,7 @@ struct vkms_composer { * @composer: data required for composing computation */ struct vkms_plane_state { - struct drm_plane_state base; + struct drm_shadow_plane_state base; struct vkms_composer *composer; }; @@ -111,7 +113,7 @@ struct vkms_device { container_of(target, struct vkms_crtc_state, base) #define to_vkms_plane_state(target)\ - container_of(target, struct vkms_plane_state, base) + container_of(target, struct vkms_plane_state, base.base) /* CRTC */ int vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc, diff --git a/drivers/gpu/drm/vkms/vkms_plane.c b/drivers/gpu/drm/vkms/vkms_plane.c index 107521ace597..8a56fbf572b0 100644 --- a/drivers/gpu/drm/vkms/vkms_plane.c +++ b/drivers/gpu/drm/vkms/vkms_plane.c @@ -8,7 +8,6 @@ #include <drm/drm_gem_atomic_helper.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_plane_helper.h> -#include <drm/drm_gem_shmem_helper.h> #include "vkms_drv.h" @@ -40,17 +39,16 @@ vkms_plane_duplicate_state(struct drm_plane *plane) vkms_state->composer = composer; - __drm_atomic_helper_plane_duplicate_state(plane, - &vkms_state->base); + __drm_gem_duplicate_shadow_plane_state(plane, &vkms_state->base); - return &vkms_state->base; + return &vkms_state->base.base; } static void vkms_plane_destroy_state(struct drm_plane *plane, struct drm_plane_state *old_state) { struct vkms_plane_state *vkms_state = to_vkms_plane_state(old_state); - struct drm_crtc *crtc = vkms_state->base.crtc; + struct drm_crtc *crtc = vkms_state->base.base.crtc; if (crtc) { /* dropping the reference we acquired in @@ -63,7 +61,7 @@ static void vkms_plane_destroy_state(struct drm_plane *plane, kfree(vkms_state->composer); vkms_state->composer = NULL; - __drm_atomic_helper_plane_destroy_state(old_state); + __drm_gem_destroy_shadow_plane_state(&vkms_state->base); kfree(vkms_state); } @@ -71,8 +69,10 @@ static void vkms_plane_reset(struct drm_plane *plane) { struct vkms_plane_state *vkms_state; - if (plane->state) + if (plane->state) { vkms_plane_destroy_state(plane, plane->state); + plane->state = NULL; /* must be set to NULL here */ + } vkms_state = kzalloc(sizeof(*vkms_state), GFP_KERNEL); if (!vkms_state) { @@ -80,8 +80,7 @@ static void vkms_plane_reset(struct drm_plane *plane) return; } - plane->state = &vkms_state->base; - plane->state->plane = plane; + __drm_gem_reset_shadow_plane(plane, &vkms_state->base); } static const struct drm_plane_funcs vkms_plane_funcs = { @@ -98,6 +97,7 @@ static void vkms_plane_atomic_update(struct drm_plane *plane, struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane); struct vkms_plane_state *vkms_plane_state; + struct drm_shadow_plane_state *shadow_plane_state; struct drm_framebuffer *fb = new_state->fb; struct vkms_composer *composer; @@ -105,11 +105,13 @@ static void vkms_plane_atomic_update(struct drm_plane *plane, return; vkms_plane_state = to_vkms_plane_state(new_state); + shadow_plane_state = &vkms_plane_state->base; composer = vkms_plane_state->composer; memcpy(&composer->src, &new_state->src, sizeof(struct drm_rect)); memcpy(&composer->dst, &new_state->dst, sizeof(struct drm_rect)); memcpy(&composer->fb, fb, sizeof(struct drm_framebuffer)); + memcpy(&composer->map, &shadow_plane_state->map, sizeof(composer->map)); drm_framebuffer_get(&composer->fb); composer->offset = fb->offsets[0]; composer->pitch = fb->pitches[0]; @@ -150,45 +152,10 @@ static int vkms_plane_atomic_check(struct drm_plane *plane, return 0; } -static int vkms_prepare_fb(struct drm_plane *plane, - struct drm_plane_state *state) -{ - struct drm_gem_object *gem_obj; - struct dma_buf_map map; - int ret; - - if (!state->fb) - return 0; - - gem_obj = drm_gem_fb_get_obj(state->fb, 0); - ret = drm_gem_shmem_vmap(gem_obj, &map); - if (ret) - DRM_ERROR("vmap failed: %d\n", ret); - - return drm_gem_plane_helper_prepare_fb(plane, state); -} - -static void vkms_cleanup_fb(struct drm_plane *plane, - struct drm_plane_state *old_state) -{ - struct drm_gem_object *gem_obj; - struct drm_gem_shmem_object *shmem_obj; - struct dma_buf_map map; - - if (!old_state->fb) - return; - - gem_obj = drm_gem_fb_get_obj(old_state->fb, 0); - shmem_obj = to_drm_gem_shmem_obj(drm_gem_fb_get_obj(old_state->fb, 0)); - dma_buf_map_set_vaddr(&map, shmem_obj->vaddr); - drm_gem_shmem_vunmap(gem_obj, &map); -} - static const struct drm_plane_helper_funcs vkms_primary_helper_funcs = { .atomic_update = vkms_plane_atomic_update, .atomic_check = vkms_plane_atomic_check, - .prepare_fb = vkms_prepare_fb, - .cleanup_fb = vkms_cleanup_fb, + DRM_GEM_SHADOW_PLANE_HELPER_FUNCS, }; struct vkms_plane *vkms_plane_init(struct vkms_device *vkmsdev, diff --git a/drivers/gpu/drm/vmwgfx/Kconfig b/drivers/gpu/drm/vmwgfx/Kconfig index 0060ef842b5a..c9ce47c448e0 100644 --- a/drivers/gpu/drm/vmwgfx/Kconfig +++ b/drivers/gpu/drm/vmwgfx/Kconfig @@ -22,3 +22,11 @@ config DRM_VMWGFX_FBCON Choose this option if you are shipping a new vmwgfx userspace driver that supports using the kernel driver. +config DRM_VMWGFX_MKSSTATS + bool "Enable mksGuestStats instrumentation of vmwgfx by default" + depends on DRM_VMWGFX + depends on X86 + default n + help + Choose this option to instrument the kernel driver for mksGuestStats. + diff --git a/drivers/gpu/drm/vmwgfx/Makefile b/drivers/gpu/drm/vmwgfx/Makefile index 09f6dcac768b..bc323f7d4032 100644 --- a/drivers/gpu/drm/vmwgfx/Makefile +++ b/drivers/gpu/drm/vmwgfx/Makefile @@ -9,7 +9,7 @@ vmwgfx-y := vmwgfx_execbuf.o vmwgfx_gmr.o vmwgfx_kms.o vmwgfx_drv.o \ vmwgfx_cotable.o vmwgfx_so.o vmwgfx_binding.o vmwgfx_msg.o \ vmwgfx_simple_resource.o vmwgfx_va.o vmwgfx_blit.o \ vmwgfx_validation.o vmwgfx_page_dirty.o vmwgfx_streamoutput.o \ - ttm_object.o ttm_memory.o + vmwgfx_devcaps.o ttm_object.o ttm_memory.o vmwgfx-$(CONFIG_DRM_FBDEV_EMULATION) += vmwgfx_fb.o vmwgfx-$(CONFIG_TRANSPARENT_HUGEPAGE) += vmwgfx_thp.o diff --git a/drivers/gpu/drm/vmwgfx/device_include/includeCheck.h b/drivers/gpu/drm/vmwgfx/device_include/includeCheck.h deleted file mode 100644 index 8cce7f15b6eb..000000000000 --- a/drivers/gpu/drm/vmwgfx/device_include/includeCheck.h +++ /dev/null @@ -1,3 +0,0 @@ -/* - * Intentionally empty file. - */ diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_caps.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_caps.h deleted file mode 100644 index 69c4253fbfbb..000000000000 --- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_caps.h +++ /dev/null @@ -1,111 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT */ -/********************************************************** - * Copyright 2007-2015 VMware, Inc. - * - * Permission is hereby granted, free of charge, to any person - * obtaining a copy of this software and associated documentation - * files (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, - * modify, merge, publish, distribute, sublicense, and/or sell copies - * of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be - * included in all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - * - **********************************************************/ - -/* - * svga3d_caps.h -- - * - * Definitions for SVGA3D hardware capabilities. Capabilities - * are used to query for optional rendering features during - * driver initialization. The capability data is stored as very - * basic key/value dictionary within the "FIFO register" memory - * area at the beginning of BAR2. - * - * Note that these definitions are only for 3D capabilities. - * The SVGA device also has "device capabilities" and "FIFO - * capabilities", which are non-3D-specific and are stored as - * bitfields rather than key/value pairs. - */ - -#ifndef _SVGA3D_CAPS_H_ -#define _SVGA3D_CAPS_H_ - -#define INCLUDE_ALLOW_MODULE -#define INCLUDE_ALLOW_USERLEVEL - -#include "includeCheck.h" - -#include "svga_reg.h" - -#define SVGA_FIFO_3D_CAPS_SIZE (SVGA_FIFO_3D_CAPS_LAST - \ - SVGA_FIFO_3D_CAPS + 1) - - -/* - * SVGA3dCapsRecordType - * - * Record types that can be found in the caps block. - * Related record types are grouped together numerically so that - * SVGA3dCaps_FindRecord() can be applied on a range of record - * types. - */ - -typedef enum { - SVGA3DCAPS_RECORD_UNKNOWN = 0, - SVGA3DCAPS_RECORD_DEVCAPS_MIN = 0x100, - SVGA3DCAPS_RECORD_DEVCAPS = 0x100, - SVGA3DCAPS_RECORD_DEVCAPS_MAX = 0x1ff, -} SVGA3dCapsRecordType; - - -/* - * SVGA3dCapsRecordHeader - * - * Header field leading each caps block record. Contains the offset (in - * register words, NOT bytes) to the next caps block record (or the end - * of caps block records which will be a zero word) and the record type - * as defined above. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCapsRecordHeader { - uint32 length; - SVGA3dCapsRecordType type; -} -#include "vmware_pack_end.h" -SVGA3dCapsRecordHeader; - - -/* - * SVGA3dCapsRecord - * - * Caps block record; "data" is a placeholder for the actual data structure - * contained within the record; - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCapsRecord { - SVGA3dCapsRecordHeader header; - uint32 data[1]; -} -#include "vmware_pack_end.h" -SVGA3dCapsRecord; - - -typedef uint32 SVGA3dCapPair[2]; - -#endif diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h index 799bc0963f7a..945c84b27e81 100644 --- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h +++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h @@ -1,6 +1,6 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT */ /********************************************************** - * Copyright 1998-2020 VMware, Inc. + * Copyright 2012-2021 VMware, Inc. + * SPDX-License-Identifier: GPL-2.0 OR MIT * * Permission is hereby granted, free of charge, to any person * obtaining a copy of this software and associated documentation @@ -27,2249 +27,1487 @@ /* * svga3d_cmd.h -- * - * SVGA 3d hardware cmd definitions + * SVGA 3d hardware cmd definitions */ + + #ifndef _SVGA3D_CMD_H_ #define _SVGA3D_CMD_H_ -#define INCLUDE_ALLOW_MODULE -#define INCLUDE_ALLOW_USERLEVEL -#define INCLUDE_ALLOW_VMCORE - -#include "includeCheck.h" #include "svga3d_types.h" - -/* - * Identifiers for commands in the command FIFO. - * - * IDs between 1000 and 1039 (inclusive) were used by obsolete versions of - * the SVGA3D protocol and remain reserved; they should not be used in the - * future. - * - * IDs between 1040 and 2999 (inclusive) are available for use by the - * current SVGA3D protocol. - * - * FIFO clients other than SVGA3D should stay below 1000, or at 3000 - * and up. - */ - -typedef enum { - SVGA_3D_CMD_LEGACY_BASE = 1000, - SVGA_3D_CMD_BASE = 1040, - - SVGA_3D_CMD_SURFACE_DEFINE = 1040, - SVGA_3D_CMD_SURFACE_DESTROY = 1041, - SVGA_3D_CMD_SURFACE_COPY = 1042, - SVGA_3D_CMD_SURFACE_STRETCHBLT = 1043, - SVGA_3D_CMD_SURFACE_DMA = 1044, - SVGA_3D_CMD_CONTEXT_DEFINE = 1045, - SVGA_3D_CMD_CONTEXT_DESTROY = 1046, - SVGA_3D_CMD_SETTRANSFORM = 1047, - SVGA_3D_CMD_SETZRANGE = 1048, - SVGA_3D_CMD_SETRENDERSTATE = 1049, - SVGA_3D_CMD_SETRENDERTARGET = 1050, - SVGA_3D_CMD_SETTEXTURESTATE = 1051, - SVGA_3D_CMD_SETMATERIAL = 1052, - SVGA_3D_CMD_SETLIGHTDATA = 1053, - SVGA_3D_CMD_SETLIGHTENABLED = 1054, - SVGA_3D_CMD_SETVIEWPORT = 1055, - SVGA_3D_CMD_SETCLIPPLANE = 1056, - SVGA_3D_CMD_CLEAR = 1057, - SVGA_3D_CMD_PRESENT = 1058, - SVGA_3D_CMD_SHADER_DEFINE = 1059, - SVGA_3D_CMD_SHADER_DESTROY = 1060, - SVGA_3D_CMD_SET_SHADER = 1061, - SVGA_3D_CMD_SET_SHADER_CONST = 1062, - SVGA_3D_CMD_DRAW_PRIMITIVES = 1063, - SVGA_3D_CMD_SETSCISSORRECT = 1064, - SVGA_3D_CMD_BEGIN_QUERY = 1065, - SVGA_3D_CMD_END_QUERY = 1066, - SVGA_3D_CMD_WAIT_FOR_QUERY = 1067, - SVGA_3D_CMD_PRESENT_READBACK = 1068, - SVGA_3D_CMD_BLIT_SURFACE_TO_SCREEN = 1069, - SVGA_3D_CMD_SURFACE_DEFINE_V2 = 1070, - SVGA_3D_CMD_GENERATE_MIPMAPS = 1071, - SVGA_3D_CMD_DEAD4 = 1072, - SVGA_3D_CMD_DEAD5 = 1073, - SVGA_3D_CMD_DEAD6 = 1074, - SVGA_3D_CMD_DEAD7 = 1075, - SVGA_3D_CMD_DEAD8 = 1076, - SVGA_3D_CMD_DEAD9 = 1077, - SVGA_3D_CMD_DEAD10 = 1078, - SVGA_3D_CMD_DEAD11 = 1079, - SVGA_3D_CMD_ACTIVATE_SURFACE = 1080, - SVGA_3D_CMD_DEACTIVATE_SURFACE = 1081, - SVGA_3D_CMD_SCREEN_DMA = 1082, - SVGA_3D_CMD_DEAD1 = 1083, - SVGA_3D_CMD_DEAD2 = 1084, - - SVGA_3D_CMD_DEAD12 = 1085, - SVGA_3D_CMD_DEAD13 = 1086, - SVGA_3D_CMD_DEAD14 = 1087, - SVGA_3D_CMD_DEAD15 = 1088, - SVGA_3D_CMD_DEAD16 = 1089, - SVGA_3D_CMD_DEAD17 = 1090, - - SVGA_3D_CMD_SET_OTABLE_BASE = 1091, - SVGA_3D_CMD_READBACK_OTABLE = 1092, - - SVGA_3D_CMD_DEFINE_GB_MOB = 1093, - SVGA_3D_CMD_DESTROY_GB_MOB = 1094, - SVGA_3D_CMD_DEAD3 = 1095, - SVGA_3D_CMD_UPDATE_GB_MOB_MAPPING = 1096, - - SVGA_3D_CMD_DEFINE_GB_SURFACE = 1097, - SVGA_3D_CMD_DESTROY_GB_SURFACE = 1098, - SVGA_3D_CMD_BIND_GB_SURFACE = 1099, - SVGA_3D_CMD_COND_BIND_GB_SURFACE = 1100, - SVGA_3D_CMD_UPDATE_GB_IMAGE = 1101, - SVGA_3D_CMD_UPDATE_GB_SURFACE = 1102, - SVGA_3D_CMD_READBACK_GB_IMAGE = 1103, - SVGA_3D_CMD_READBACK_GB_SURFACE = 1104, - SVGA_3D_CMD_INVALIDATE_GB_IMAGE = 1105, - SVGA_3D_CMD_INVALIDATE_GB_SURFACE = 1106, - - SVGA_3D_CMD_DEFINE_GB_CONTEXT = 1107, - SVGA_3D_CMD_DESTROY_GB_CONTEXT = 1108, - SVGA_3D_CMD_BIND_GB_CONTEXT = 1109, - SVGA_3D_CMD_READBACK_GB_CONTEXT = 1110, - SVGA_3D_CMD_INVALIDATE_GB_CONTEXT = 1111, - - SVGA_3D_CMD_DEFINE_GB_SHADER = 1112, - SVGA_3D_CMD_DESTROY_GB_SHADER = 1113, - SVGA_3D_CMD_BIND_GB_SHADER = 1114, - - SVGA_3D_CMD_SET_OTABLE_BASE64 = 1115, - - SVGA_3D_CMD_BEGIN_GB_QUERY = 1116, - SVGA_3D_CMD_END_GB_QUERY = 1117, - SVGA_3D_CMD_WAIT_FOR_GB_QUERY = 1118, - - SVGA_3D_CMD_NOP = 1119, - - SVGA_3D_CMD_ENABLE_GART = 1120, - SVGA_3D_CMD_DISABLE_GART = 1121, - SVGA_3D_CMD_MAP_MOB_INTO_GART = 1122, - SVGA_3D_CMD_UNMAP_GART_RANGE = 1123, - - SVGA_3D_CMD_DEFINE_GB_SCREENTARGET = 1124, - SVGA_3D_CMD_DESTROY_GB_SCREENTARGET = 1125, - SVGA_3D_CMD_BIND_GB_SCREENTARGET = 1126, - SVGA_3D_CMD_UPDATE_GB_SCREENTARGET = 1127, - - SVGA_3D_CMD_READBACK_GB_IMAGE_PARTIAL = 1128, - SVGA_3D_CMD_INVALIDATE_GB_IMAGE_PARTIAL = 1129, - - SVGA_3D_CMD_SET_GB_SHADERCONSTS_INLINE = 1130, - - SVGA_3D_CMD_GB_SCREEN_DMA = 1131, - SVGA_3D_CMD_BIND_GB_SURFACE_WITH_PITCH = 1132, - SVGA_3D_CMD_GB_MOB_FENCE = 1133, - SVGA_3D_CMD_DEFINE_GB_SURFACE_V2 = 1134, - SVGA_3D_CMD_DEFINE_GB_MOB64 = 1135, - SVGA_3D_CMD_REDEFINE_GB_MOB64 = 1136, - SVGA_3D_CMD_NOP_ERROR = 1137, - - SVGA_3D_CMD_SET_VERTEX_STREAMS = 1138, - SVGA_3D_CMD_SET_VERTEX_DECLS = 1139, - SVGA_3D_CMD_SET_VERTEX_DIVISORS = 1140, - SVGA_3D_CMD_DRAW = 1141, - SVGA_3D_CMD_DRAW_INDEXED = 1142, - - /* - * DX10 Commands - */ - SVGA_3D_CMD_DX_MIN = 1143, - SVGA_3D_CMD_DX_DEFINE_CONTEXT = 1143, - SVGA_3D_CMD_DX_DESTROY_CONTEXT = 1144, - SVGA_3D_CMD_DX_BIND_CONTEXT = 1145, - SVGA_3D_CMD_DX_READBACK_CONTEXT = 1146, - SVGA_3D_CMD_DX_INVALIDATE_CONTEXT = 1147, - SVGA_3D_CMD_DX_SET_SINGLE_CONSTANT_BUFFER = 1148, - SVGA_3D_CMD_DX_SET_SHADER_RESOURCES = 1149, - SVGA_3D_CMD_DX_SET_SHADER = 1150, - SVGA_3D_CMD_DX_SET_SAMPLERS = 1151, - SVGA_3D_CMD_DX_DRAW = 1152, - SVGA_3D_CMD_DX_DRAW_INDEXED = 1153, - SVGA_3D_CMD_DX_DRAW_INSTANCED = 1154, - SVGA_3D_CMD_DX_DRAW_INDEXED_INSTANCED = 1155, - SVGA_3D_CMD_DX_DRAW_AUTO = 1156, - SVGA_3D_CMD_DX_SET_INPUT_LAYOUT = 1157, - SVGA_3D_CMD_DX_SET_VERTEX_BUFFERS = 1158, - SVGA_3D_CMD_DX_SET_INDEX_BUFFER = 1159, - SVGA_3D_CMD_DX_SET_TOPOLOGY = 1160, - SVGA_3D_CMD_DX_SET_RENDERTARGETS = 1161, - SVGA_3D_CMD_DX_SET_BLEND_STATE = 1162, - SVGA_3D_CMD_DX_SET_DEPTHSTENCIL_STATE = 1163, - SVGA_3D_CMD_DX_SET_RASTERIZER_STATE = 1164, - SVGA_3D_CMD_DX_DEFINE_QUERY = 1165, - SVGA_3D_CMD_DX_DESTROY_QUERY = 1166, - SVGA_3D_CMD_DX_BIND_QUERY = 1167, - SVGA_3D_CMD_DX_SET_QUERY_OFFSET = 1168, - SVGA_3D_CMD_DX_BEGIN_QUERY = 1169, - SVGA_3D_CMD_DX_END_QUERY = 1170, - SVGA_3D_CMD_DX_READBACK_QUERY = 1171, - SVGA_3D_CMD_DX_SET_PREDICATION = 1172, - SVGA_3D_CMD_DX_SET_SOTARGETS = 1173, - SVGA_3D_CMD_DX_SET_VIEWPORTS = 1174, - SVGA_3D_CMD_DX_SET_SCISSORRECTS = 1175, - SVGA_3D_CMD_DX_CLEAR_RENDERTARGET_VIEW = 1176, - SVGA_3D_CMD_DX_CLEAR_DEPTHSTENCIL_VIEW = 1177, - SVGA_3D_CMD_DX_PRED_COPY_REGION = 1178, - SVGA_3D_CMD_DX_PRED_COPY = 1179, - SVGA_3D_CMD_DX_PRESENTBLT = 1180, - SVGA_3D_CMD_DX_GENMIPS = 1181, - SVGA_3D_CMD_DX_UPDATE_SUBRESOURCE = 1182, - SVGA_3D_CMD_DX_READBACK_SUBRESOURCE = 1183, - SVGA_3D_CMD_DX_INVALIDATE_SUBRESOURCE = 1184, - SVGA_3D_CMD_DX_DEFINE_SHADERRESOURCE_VIEW = 1185, - SVGA_3D_CMD_DX_DESTROY_SHADERRESOURCE_VIEW = 1186, - SVGA_3D_CMD_DX_DEFINE_RENDERTARGET_VIEW = 1187, - SVGA_3D_CMD_DX_DESTROY_RENDERTARGET_VIEW = 1188, - SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_VIEW = 1189, - SVGA_3D_CMD_DX_DESTROY_DEPTHSTENCIL_VIEW = 1190, - SVGA_3D_CMD_DX_DEFINE_ELEMENTLAYOUT = 1191, - SVGA_3D_CMD_DX_DESTROY_ELEMENTLAYOUT = 1192, - SVGA_3D_CMD_DX_DEFINE_BLEND_STATE = 1193, - SVGA_3D_CMD_DX_DESTROY_BLEND_STATE = 1194, - SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_STATE = 1195, - SVGA_3D_CMD_DX_DESTROY_DEPTHSTENCIL_STATE = 1196, - SVGA_3D_CMD_DX_DEFINE_RASTERIZER_STATE = 1197, - SVGA_3D_CMD_DX_DESTROY_RASTERIZER_STATE = 1198, - SVGA_3D_CMD_DX_DEFINE_SAMPLER_STATE = 1199, - SVGA_3D_CMD_DX_DESTROY_SAMPLER_STATE = 1200, - SVGA_3D_CMD_DX_DEFINE_SHADER = 1201, - SVGA_3D_CMD_DX_DESTROY_SHADER = 1202, - SVGA_3D_CMD_DX_BIND_SHADER = 1203, - SVGA_3D_CMD_DX_DEFINE_STREAMOUTPUT = 1204, - SVGA_3D_CMD_DX_DESTROY_STREAMOUTPUT = 1205, - SVGA_3D_CMD_DX_SET_STREAMOUTPUT = 1206, - SVGA_3D_CMD_DX_SET_COTABLE = 1207, - SVGA_3D_CMD_DX_READBACK_COTABLE = 1208, - SVGA_3D_CMD_DX_BUFFER_COPY = 1209, - SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER = 1210, - SVGA_3D_CMD_DX_SURFACE_COPY_AND_READBACK = 1211, - SVGA_3D_CMD_DX_MOVE_QUERY = 1212, - SVGA_3D_CMD_DX_BIND_ALL_QUERY = 1213, - SVGA_3D_CMD_DX_READBACK_ALL_QUERY = 1214, - SVGA_3D_CMD_DX_PRED_TRANSFER_FROM_BUFFER = 1215, - SVGA_3D_CMD_DX_MOB_FENCE_64 = 1216, - SVGA_3D_CMD_DX_BIND_ALL_SHADER = 1217, - SVGA_3D_CMD_DX_HINT = 1218, - SVGA_3D_CMD_DX_BUFFER_UPDATE = 1219, - SVGA_3D_CMD_DX_SET_VS_CONSTANT_BUFFER_OFFSET = 1220, - SVGA_3D_CMD_DX_SET_PS_CONSTANT_BUFFER_OFFSET = 1221, - SVGA_3D_CMD_DX_SET_GS_CONSTANT_BUFFER_OFFSET = 1222, - SVGA_3D_CMD_DX_SET_HS_CONSTANT_BUFFER_OFFSET = 1223, - SVGA_3D_CMD_DX_SET_DS_CONSTANT_BUFFER_OFFSET = 1224, - SVGA_3D_CMD_DX_SET_CS_CONSTANT_BUFFER_OFFSET = 1225, - - SVGA_3D_CMD_DX_COND_BIND_ALL_SHADER = 1226, - SVGA_3D_CMD_DX_MAX = 1227, - - SVGA_3D_CMD_SCREEN_COPY = 1227, - - SVGA_3D_CMD_RESERVED1 = 1228, - SVGA_3D_CMD_RESERVED2 = 1229, - SVGA_3D_CMD_RESERVED3 = 1230, - SVGA_3D_CMD_RESERVED4 = 1231, - SVGA_3D_CMD_RESERVED5 = 1232, - SVGA_3D_CMD_RESERVED6 = 1233, - SVGA_3D_CMD_RESERVED7 = 1234, - SVGA_3D_CMD_RESERVED8 = 1235, - - SVGA_3D_CMD_GROW_OTABLE = 1236, - SVGA_3D_CMD_DX_GROW_COTABLE = 1237, - SVGA_3D_CMD_INTRA_SURFACE_COPY = 1238, - - SVGA_3D_CMD_DEFINE_GB_SURFACE_V3 = 1239, - - SVGA_3D_CMD_DX_RESOLVE_COPY = 1240, - SVGA_3D_CMD_DX_PRED_RESOLVE_COPY = 1241, - SVGA_3D_CMD_DX_PRED_CONVERT_REGION = 1242, - SVGA_3D_CMD_DX_PRED_CONVERT = 1243, - SVGA_3D_CMD_WHOLE_SURFACE_COPY = 1244, - - SVGA_3D_CMD_DX_DEFINE_UA_VIEW = 1245, - SVGA_3D_CMD_DX_DESTROY_UA_VIEW = 1246, - SVGA_3D_CMD_DX_CLEAR_UA_VIEW_UINT = 1247, - SVGA_3D_CMD_DX_CLEAR_UA_VIEW_FLOAT = 1248, - SVGA_3D_CMD_DX_COPY_STRUCTURE_COUNT = 1249, - SVGA_3D_CMD_DX_SET_UA_VIEWS = 1250, - - SVGA_3D_CMD_DX_DRAW_INDEXED_INSTANCED_INDIRECT = 1251, - SVGA_3D_CMD_DX_DRAW_INSTANCED_INDIRECT = 1252, - SVGA_3D_CMD_DX_DISPATCH = 1253, - SVGA_3D_CMD_DX_DISPATCH_INDIRECT = 1254, - - SVGA_3D_CMD_WRITE_ZERO_SURFACE = 1255, - SVGA_3D_CMD_HINT_ZERO_SURFACE = 1256, - SVGA_3D_CMD_DX_TRANSFER_TO_BUFFER = 1257, - SVGA_3D_CMD_DX_SET_STRUCTURE_COUNT = 1258, - - SVGA_3D_CMD_LOGICOPS_BITBLT = 1259, - SVGA_3D_CMD_LOGICOPS_TRANSBLT = 1260, - SVGA_3D_CMD_LOGICOPS_STRETCHBLT = 1261, - SVGA_3D_CMD_LOGICOPS_COLORFILL = 1262, - SVGA_3D_CMD_LOGICOPS_ALPHABLEND = 1263, - SVGA_3D_CMD_LOGICOPS_CLEARTYPEBLEND = 1264, - - SVGA_3D_CMD_RESERVED2_1 = 1265, - - SVGA_3D_CMD_RESERVED2_2 = 1266, - SVGA_3D_CMD_DEFINE_GB_SURFACE_V4 = 1267, - SVGA_3D_CMD_DX_SET_CS_UA_VIEWS = 1268, - SVGA_3D_CMD_DX_SET_MIN_LOD = 1269, - SVGA_3D_CMD_RESERVED2_3 = 1270, - SVGA_3D_CMD_RESERVED2_4 = 1271, - SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_VIEW_V2 = 1272, - SVGA_3D_CMD_DX_DEFINE_STREAMOUTPUT_WITH_MOB = 1273, - SVGA_3D_CMD_DX_SET_SHADER_IFACE = 1274, - SVGA_3D_CMD_DX_BIND_STREAMOUTPUT = 1275, - SVGA_3D_CMD_SURFACE_STRETCHBLT_NON_MS_TO_MS = 1276, - SVGA_3D_CMD_DX_BIND_SHADER_IFACE = 1277, - - SVGA_3D_CMD_MAX = 1278, - SVGA_3D_CMD_FUTURE_MAX = 3000 +#include "svga3d_limits.h" +#include "svga_reg.h" + +typedef enum SVGAFifo3dCmdId { + SVGA_3D_CMD_LEGACY_BASE = 1000, + SVGA_3D_CMD_BASE = 1040, + + SVGA_3D_CMD_SURFACE_DEFINE = 1040, + SVGA_3D_CMD_SURFACE_DESTROY = 1041, + SVGA_3D_CMD_SURFACE_COPY = 1042, + SVGA_3D_CMD_SURFACE_STRETCHBLT = 1043, + SVGA_3D_CMD_SURFACE_DMA = 1044, + SVGA_3D_CMD_CONTEXT_DEFINE = 1045, + SVGA_3D_CMD_CONTEXT_DESTROY = 1046, + SVGA_3D_CMD_SETTRANSFORM = 1047, + SVGA_3D_CMD_SETZRANGE = 1048, + SVGA_3D_CMD_SETRENDERSTATE = 1049, + SVGA_3D_CMD_SETRENDERTARGET = 1050, + SVGA_3D_CMD_SETTEXTURESTATE = 1051, + SVGA_3D_CMD_SETMATERIAL = 1052, + SVGA_3D_CMD_SETLIGHTDATA = 1053, + SVGA_3D_CMD_SETLIGHTENABLED = 1054, + SVGA_3D_CMD_SETVIEWPORT = 1055, + SVGA_3D_CMD_SETCLIPPLANE = 1056, + SVGA_3D_CMD_CLEAR = 1057, + SVGA_3D_CMD_PRESENT = 1058, + SVGA_3D_CMD_SHADER_DEFINE = 1059, + SVGA_3D_CMD_SHADER_DESTROY = 1060, + SVGA_3D_CMD_SET_SHADER = 1061, + SVGA_3D_CMD_SET_SHADER_CONST = 1062, + SVGA_3D_CMD_DRAW_PRIMITIVES = 1063, + SVGA_3D_CMD_SETSCISSORRECT = 1064, + SVGA_3D_CMD_BEGIN_QUERY = 1065, + SVGA_3D_CMD_END_QUERY = 1066, + SVGA_3D_CMD_WAIT_FOR_QUERY = 1067, + SVGA_3D_CMD_PRESENT_READBACK = 1068, + SVGA_3D_CMD_BLIT_SURFACE_TO_SCREEN = 1069, + SVGA_3D_CMD_SURFACE_DEFINE_V2 = 1070, + SVGA_3D_CMD_GENERATE_MIPMAPS = 1071, + SVGA_3D_CMD_DEAD4 = 1072, + SVGA_3D_CMD_DEAD5 = 1073, + SVGA_3D_CMD_DEAD6 = 1074, + SVGA_3D_CMD_DEAD7 = 1075, + SVGA_3D_CMD_DEAD8 = 1076, + SVGA_3D_CMD_DEAD9 = 1077, + SVGA_3D_CMD_DEAD10 = 1078, + SVGA_3D_CMD_DEAD11 = 1079, + SVGA_3D_CMD_ACTIVATE_SURFACE = 1080, + SVGA_3D_CMD_DEACTIVATE_SURFACE = 1081, + SVGA_3D_CMD_SCREEN_DMA = 1082, + SVGA_3D_CMD_DEAD1 = 1083, + SVGA_3D_CMD_DEAD2 = 1084, + + SVGA_3D_CMD_DEAD12 = 1085, + SVGA_3D_CMD_DEAD13 = 1086, + SVGA_3D_CMD_DEAD14 = 1087, + SVGA_3D_CMD_DEAD15 = 1088, + SVGA_3D_CMD_DEAD16 = 1089, + SVGA_3D_CMD_DEAD17 = 1090, + + SVGA_3D_CMD_SET_OTABLE_BASE = 1091, + SVGA_3D_CMD_READBACK_OTABLE = 1092, + + SVGA_3D_CMD_DEFINE_GB_MOB = 1093, + SVGA_3D_CMD_DESTROY_GB_MOB = 1094, + SVGA_3D_CMD_DEAD3 = 1095, + SVGA_3D_CMD_UPDATE_GB_MOB_MAPPING = 1096, + + SVGA_3D_CMD_DEFINE_GB_SURFACE = 1097, + SVGA_3D_CMD_DESTROY_GB_SURFACE = 1098, + SVGA_3D_CMD_BIND_GB_SURFACE = 1099, + SVGA_3D_CMD_COND_BIND_GB_SURFACE = 1100, + SVGA_3D_CMD_UPDATE_GB_IMAGE = 1101, + SVGA_3D_CMD_UPDATE_GB_SURFACE = 1102, + SVGA_3D_CMD_READBACK_GB_IMAGE = 1103, + SVGA_3D_CMD_READBACK_GB_SURFACE = 1104, + SVGA_3D_CMD_INVALIDATE_GB_IMAGE = 1105, + SVGA_3D_CMD_INVALIDATE_GB_SURFACE = 1106, + + SVGA_3D_CMD_DEFINE_GB_CONTEXT = 1107, + SVGA_3D_CMD_DESTROY_GB_CONTEXT = 1108, + SVGA_3D_CMD_BIND_GB_CONTEXT = 1109, + SVGA_3D_CMD_READBACK_GB_CONTEXT = 1110, + SVGA_3D_CMD_INVALIDATE_GB_CONTEXT = 1111, + + SVGA_3D_CMD_DEFINE_GB_SHADER = 1112, + SVGA_3D_CMD_DESTROY_GB_SHADER = 1113, + SVGA_3D_CMD_BIND_GB_SHADER = 1114, + + SVGA_3D_CMD_SET_OTABLE_BASE64 = 1115, + + SVGA_3D_CMD_BEGIN_GB_QUERY = 1116, + SVGA_3D_CMD_END_GB_QUERY = 1117, + SVGA_3D_CMD_WAIT_FOR_GB_QUERY = 1118, + + SVGA_3D_CMD_NOP = 1119, + + SVGA_3D_CMD_ENABLE_GART = 1120, + SVGA_3D_CMD_DISABLE_GART = 1121, + SVGA_3D_CMD_MAP_MOB_INTO_GART = 1122, + SVGA_3D_CMD_UNMAP_GART_RANGE = 1123, + + SVGA_3D_CMD_DEFINE_GB_SCREENTARGET = 1124, + SVGA_3D_CMD_DESTROY_GB_SCREENTARGET = 1125, + SVGA_3D_CMD_BIND_GB_SCREENTARGET = 1126, + SVGA_3D_CMD_UPDATE_GB_SCREENTARGET = 1127, + + SVGA_3D_CMD_READBACK_GB_IMAGE_PARTIAL = 1128, + SVGA_3D_CMD_INVALIDATE_GB_IMAGE_PARTIAL = 1129, + + SVGA_3D_CMD_SET_GB_SHADERCONSTS_INLINE = 1130, + + SVGA_3D_CMD_GB_SCREEN_DMA = 1131, + SVGA_3D_CMD_BIND_GB_SURFACE_WITH_PITCH = 1132, + SVGA_3D_CMD_GB_MOB_FENCE = 1133, + SVGA_3D_CMD_DEFINE_GB_SURFACE_V2 = 1134, + SVGA_3D_CMD_DEFINE_GB_MOB64 = 1135, + SVGA_3D_CMD_REDEFINE_GB_MOB64 = 1136, + SVGA_3D_CMD_NOP_ERROR = 1137, + + SVGA_3D_CMD_SET_VERTEX_STREAMS = 1138, + SVGA_3D_CMD_SET_VERTEX_DECLS = 1139, + SVGA_3D_CMD_SET_VERTEX_DIVISORS = 1140, + SVGA_3D_CMD_DRAW = 1141, + SVGA_3D_CMD_DRAW_INDEXED = 1142, + + SVGA_3D_CMD_DX_MIN = 1143, + SVGA_3D_CMD_DX_DEFINE_CONTEXT = 1143, + SVGA_3D_CMD_DX_DESTROY_CONTEXT = 1144, + SVGA_3D_CMD_DX_BIND_CONTEXT = 1145, + SVGA_3D_CMD_DX_READBACK_CONTEXT = 1146, + SVGA_3D_CMD_DX_INVALIDATE_CONTEXT = 1147, + SVGA_3D_CMD_DX_SET_SINGLE_CONSTANT_BUFFER = 1148, + SVGA_3D_CMD_DX_SET_SHADER_RESOURCES = 1149, + SVGA_3D_CMD_DX_SET_SHADER = 1150, + SVGA_3D_CMD_DX_SET_SAMPLERS = 1151, + SVGA_3D_CMD_DX_DRAW = 1152, + SVGA_3D_CMD_DX_DRAW_INDEXED = 1153, + SVGA_3D_CMD_DX_DRAW_INSTANCED = 1154, + SVGA_3D_CMD_DX_DRAW_INDEXED_INSTANCED = 1155, + SVGA_3D_CMD_DX_DRAW_AUTO = 1156, + SVGA_3D_CMD_DX_SET_INPUT_LAYOUT = 1157, + SVGA_3D_CMD_DX_SET_VERTEX_BUFFERS = 1158, + SVGA_3D_CMD_DX_SET_INDEX_BUFFER = 1159, + SVGA_3D_CMD_DX_SET_TOPOLOGY = 1160, + SVGA_3D_CMD_DX_SET_RENDERTARGETS = 1161, + SVGA_3D_CMD_DX_SET_BLEND_STATE = 1162, + SVGA_3D_CMD_DX_SET_DEPTHSTENCIL_STATE = 1163, + SVGA_3D_CMD_DX_SET_RASTERIZER_STATE = 1164, + SVGA_3D_CMD_DX_DEFINE_QUERY = 1165, + SVGA_3D_CMD_DX_DESTROY_QUERY = 1166, + SVGA_3D_CMD_DX_BIND_QUERY = 1167, + SVGA_3D_CMD_DX_SET_QUERY_OFFSET = 1168, + SVGA_3D_CMD_DX_BEGIN_QUERY = 1169, + SVGA_3D_CMD_DX_END_QUERY = 1170, + SVGA_3D_CMD_DX_READBACK_QUERY = 1171, + SVGA_3D_CMD_DX_SET_PREDICATION = 1172, + SVGA_3D_CMD_DX_SET_SOTARGETS = 1173, + SVGA_3D_CMD_DX_SET_VIEWPORTS = 1174, + SVGA_3D_CMD_DX_SET_SCISSORRECTS = 1175, + SVGA_3D_CMD_DX_CLEAR_RENDERTARGET_VIEW = 1176, + SVGA_3D_CMD_DX_CLEAR_DEPTHSTENCIL_VIEW = 1177, + SVGA_3D_CMD_DX_PRED_COPY_REGION = 1178, + SVGA_3D_CMD_DX_PRED_COPY = 1179, + SVGA_3D_CMD_DX_PRESENTBLT = 1180, + SVGA_3D_CMD_DX_GENMIPS = 1181, + SVGA_3D_CMD_DX_UPDATE_SUBRESOURCE = 1182, + SVGA_3D_CMD_DX_READBACK_SUBRESOURCE = 1183, + SVGA_3D_CMD_DX_INVALIDATE_SUBRESOURCE = 1184, + SVGA_3D_CMD_DX_DEFINE_SHADERRESOURCE_VIEW = 1185, + SVGA_3D_CMD_DX_DESTROY_SHADERRESOURCE_VIEW = 1186, + SVGA_3D_CMD_DX_DEFINE_RENDERTARGET_VIEW = 1187, + SVGA_3D_CMD_DX_DESTROY_RENDERTARGET_VIEW = 1188, + SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_VIEW = 1189, + SVGA_3D_CMD_DX_DESTROY_DEPTHSTENCIL_VIEW = 1190, + SVGA_3D_CMD_DX_DEFINE_ELEMENTLAYOUT = 1191, + SVGA_3D_CMD_DX_DESTROY_ELEMENTLAYOUT = 1192, + SVGA_3D_CMD_DX_DEFINE_BLEND_STATE = 1193, + SVGA_3D_CMD_DX_DESTROY_BLEND_STATE = 1194, + SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_STATE = 1195, + SVGA_3D_CMD_DX_DESTROY_DEPTHSTENCIL_STATE = 1196, + SVGA_3D_CMD_DX_DEFINE_RASTERIZER_STATE = 1197, + SVGA_3D_CMD_DX_DESTROY_RASTERIZER_STATE = 1198, + SVGA_3D_CMD_DX_DEFINE_SAMPLER_STATE = 1199, + SVGA_3D_CMD_DX_DESTROY_SAMPLER_STATE = 1200, + SVGA_3D_CMD_DX_DEFINE_SHADER = 1201, + SVGA_3D_CMD_DX_DESTROY_SHADER = 1202, + SVGA_3D_CMD_DX_BIND_SHADER = 1203, + SVGA_3D_CMD_DX_DEFINE_STREAMOUTPUT = 1204, + SVGA_3D_CMD_DX_DESTROY_STREAMOUTPUT = 1205, + SVGA_3D_CMD_DX_SET_STREAMOUTPUT = 1206, + SVGA_3D_CMD_DX_SET_COTABLE = 1207, + SVGA_3D_CMD_DX_READBACK_COTABLE = 1208, + SVGA_3D_CMD_DX_BUFFER_COPY = 1209, + SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER = 1210, + SVGA_3D_CMD_DX_SURFACE_COPY_AND_READBACK = 1211, + SVGA_3D_CMD_DX_MOVE_QUERY = 1212, + SVGA_3D_CMD_DX_BIND_ALL_QUERY = 1213, + SVGA_3D_CMD_DX_READBACK_ALL_QUERY = 1214, + SVGA_3D_CMD_DX_PRED_TRANSFER_FROM_BUFFER = 1215, + SVGA_3D_CMD_DX_MOB_FENCE_64 = 1216, + SVGA_3D_CMD_DX_BIND_ALL_SHADER = 1217, + SVGA_3D_CMD_DX_HINT = 1218, + SVGA_3D_CMD_DX_BUFFER_UPDATE = 1219, + SVGA_3D_CMD_DX_SET_VS_CONSTANT_BUFFER_OFFSET = 1220, + SVGA_3D_CMD_DX_SET_PS_CONSTANT_BUFFER_OFFSET = 1221, + SVGA_3D_CMD_DX_SET_GS_CONSTANT_BUFFER_OFFSET = 1222, + SVGA_3D_CMD_DX_SET_HS_CONSTANT_BUFFER_OFFSET = 1223, + SVGA_3D_CMD_DX_SET_DS_CONSTANT_BUFFER_OFFSET = 1224, + SVGA_3D_CMD_DX_SET_CS_CONSTANT_BUFFER_OFFSET = 1225, + + SVGA_3D_CMD_DX_COND_BIND_ALL_SHADER = 1226, + SVGA_3D_CMD_DX_MAX = 1227, + + SVGA_3D_CMD_SCREEN_COPY = 1227, + + SVGA_3D_CMD_RESERVED1 = 1228, + SVGA_3D_CMD_RESERVED2 = 1229, + SVGA_3D_CMD_RESERVED3 = 1230, + SVGA_3D_CMD_RESERVED4 = 1231, + SVGA_3D_CMD_RESERVED5 = 1232, + SVGA_3D_CMD_RESERVED6 = 1233, + SVGA_3D_CMD_RESERVED7 = 1234, + SVGA_3D_CMD_RESERVED8 = 1235, + + SVGA_3D_CMD_GROW_OTABLE = 1236, + SVGA_3D_CMD_DX_GROW_COTABLE = 1237, + SVGA_3D_CMD_INTRA_SURFACE_COPY = 1238, + + SVGA_3D_CMD_DEFINE_GB_SURFACE_V3 = 1239, + + SVGA_3D_CMD_DX_RESOLVE_COPY = 1240, + SVGA_3D_CMD_DX_PRED_RESOLVE_COPY = 1241, + SVGA_3D_CMD_DX_PRED_CONVERT_REGION = 1242, + SVGA_3D_CMD_DX_PRED_CONVERT = 1243, + SVGA_3D_CMD_WHOLE_SURFACE_COPY = 1244, + + SVGA_3D_CMD_DX_DEFINE_UA_VIEW = 1245, + SVGA_3D_CMD_DX_DESTROY_UA_VIEW = 1246, + SVGA_3D_CMD_DX_CLEAR_UA_VIEW_UINT = 1247, + SVGA_3D_CMD_DX_CLEAR_UA_VIEW_FLOAT = 1248, + SVGA_3D_CMD_DX_COPY_STRUCTURE_COUNT = 1249, + SVGA_3D_CMD_DX_SET_UA_VIEWS = 1250, + + SVGA_3D_CMD_DX_DRAW_INDEXED_INSTANCED_INDIRECT = 1251, + SVGA_3D_CMD_DX_DRAW_INSTANCED_INDIRECT = 1252, + SVGA_3D_CMD_DX_DISPATCH = 1253, + SVGA_3D_CMD_DX_DISPATCH_INDIRECT = 1254, + + SVGA_3D_CMD_WRITE_ZERO_SURFACE = 1255, + SVGA_3D_CMD_UPDATE_ZERO_SURFACE = 1256, + SVGA_3D_CMD_DX_TRANSFER_TO_BUFFER = 1257, + SVGA_3D_CMD_DX_SET_STRUCTURE_COUNT = 1258, + + SVGA_3D_CMD_LOGICOPS_BITBLT = 1259, + SVGA_3D_CMD_LOGICOPS_TRANSBLT = 1260, + SVGA_3D_CMD_LOGICOPS_STRETCHBLT = 1261, + SVGA_3D_CMD_LOGICOPS_COLORFILL = 1262, + SVGA_3D_CMD_LOGICOPS_ALPHABLEND = 1263, + SVGA_3D_CMD_LOGICOPS_CLEARTYPEBLEND = 1264, + + SVGA_3D_CMD_DX_COPY_COTABLE_INTO_MOB = 1265, + + SVGA_3D_CMD_UPDATE_GB_SCREENTARGET_V2 = 1266, + + SVGA_3D_CMD_DEFINE_GB_SURFACE_V4 = 1267, + SVGA_3D_CMD_DX_SET_CS_UA_VIEWS = 1268, + SVGA_3D_CMD_DX_SET_MIN_LOD = 1269, + + SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_VIEW_V2 = 1272, + SVGA_3D_CMD_DX_DEFINE_STREAMOUTPUT_WITH_MOB = 1273, + SVGA_3D_CMD_DX_SET_SHADER_IFACE = 1274, + SVGA_3D_CMD_DX_BIND_STREAMOUTPUT = 1275, + SVGA_3D_CMD_SURFACE_STRETCHBLT_NON_MS_TO_MS = 1276, + SVGA_3D_CMD_DX_BIND_SHADER_IFACE = 1277, + + SVGA_3D_CMD_UPDATE_GB_SCREENTARGET_MOVE = 1278, + + SVGA_3D_CMD_DX_PRED_STAGING_COPY = 1281, + SVGA_3D_CMD_DX_STAGING_COPY = 1282, + SVGA_3D_CMD_DX_PRED_STAGING_COPY_REGION = 1283, + SVGA_3D_CMD_DX_SET_VERTEX_BUFFERS_V2 = 1284, + SVGA_3D_CMD_DX_SET_INDEX_BUFFER_V2 = 1285, + SVGA_3D_CMD_DX_SET_VERTEX_BUFFERS_OFFSET_AND_SIZE = 1286, + SVGA_3D_CMD_DX_SET_INDEX_BUFFER_OFFSET_AND_SIZE = 1287, + SVGA_3D_CMD_DX_DEFINE_RASTERIZER_STATE_V2 = 1288, + SVGA_3D_CMD_DX_PRED_STAGING_CONVERT_REGION = 1289, + SVGA_3D_CMD_DX_PRED_STAGING_CONVERT = 1290, + SVGA_3D_CMD_DX_STAGING_BUFFER_COPY = 1291, + + SVGA_3D_CMD_MAX = 1303, + SVGA_3D_CMD_FUTURE_MAX = 3000 } SVGAFifo3dCmdId; #define SVGA_NUM_3D_CMD (SVGA_3D_CMD_MAX - SVGA_3D_CMD_BASE) -/* - * FIFO command format definitions: - */ - -/* - * The data size header following cmdNum for every 3d command - */ -typedef -#include "vmware_pack_begin.h" -struct { - uint32 id; - uint32 size; -} -#include "vmware_pack_end.h" -SVGA3dCmdHeader; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 numMipLevels; -} -#include "vmware_pack_end.h" -SVGA3dSurfaceFace; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 sid; - SVGA3dSurface1Flags surfaceFlags; - SVGA3dSurfaceFormat format; - - /* - * If surfaceFlags has SVGA3D_SURFACE_CUBEMAP bit set, all SVGA3dSurfaceFace - * structures must have the same value of numMipLevels field. - * Otherwise, all but the first SVGA3dSurfaceFace structures must have the - * numMipLevels set to 0. - */ - SVGA3dSurfaceFace face[SVGA3D_MAX_SURFACE_FACES]; - - /* - * Followed by an SVGA3dSize structure for each mip level in each face. - * - * A note on surface sizes: Sizes are always specified in pixels, - * even if the true surface size is not a multiple of the minimum - * block size of the surface's format. For example, a 3x3x1 DXT1 - * compressed texture would actually be stored as a 4x4x1 image in - * memory. - */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDefineSurface; /* SVGA_3D_CMD_SURFACE_DEFINE */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 sid; - SVGA3dSurface1Flags surfaceFlags; - SVGA3dSurfaceFormat format; - - /* - * If surfaceFlags has SVGA3D_SURFACE_CUBEMAP bit set, all SVGA3dSurfaceFace - * structures must have the same value of numMipLevels field. - * Otherwise, all but the first SVGA3dSurfaceFace structures must have the - * numMipLevels set to 0. - */ - SVGA3dSurfaceFace face[SVGA3D_MAX_SURFACE_FACES]; - uint32 multisampleCount; - SVGA3dTextureFilter autogenFilter; - - /* - * Followed by an SVGA3dSize structure for each mip level in each face. - * - * A note on surface sizes: Sizes are always specified in pixels, - * even if the true surface size is not a multiple of the minimum - * block size of the surface's format. For example, a 3x3x1 DXT1 - * compressed texture would actually be stored as a 4x4x1 image in - * memory. - */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDefineSurface_v2; /* SVGA_3D_CMD_SURFACE_DEFINE_V2 */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 sid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDestroySurface; /* SVGA_3D_CMD_SURFACE_DESTROY */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDefineContext; /* SVGA_3D_CMD_CONTEXT_DEFINE */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDestroyContext; /* SVGA_3D_CMD_CONTEXT_DESTROY */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGA3dClearFlag clearFlag; - uint32 color; - float depth; - uint32 stencil; - /* Followed by variable number of SVGA3dRect structures */ -} -#include "vmware_pack_end.h" -SVGA3dCmdClear; /* SVGA_3D_CMD_CLEAR */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dLightType type; - SVGA3dBool inWorldSpace; - float diffuse[4]; - float specular[4]; - float ambient[4]; - float position[4]; - float direction[4]; - float range; - float falloff; - float attenuation0; - float attenuation1; - float attenuation2; - float theta; - float phi; -} -#include "vmware_pack_end.h" -SVGA3dLightData; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 sid; - /* Followed by variable number of SVGA3dCopyRect structures */ -} -#include "vmware_pack_end.h" -SVGA3dCmdPresent; /* SVGA_3D_CMD_PRESENT */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dRenderStateName state; - union { - uint32 uintValue; - float floatValue; - }; -} -#include "vmware_pack_end.h" -SVGA3dRenderState; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - /* Followed by variable number of SVGA3dRenderState structures */ -} -#include "vmware_pack_end.h" -SVGA3dCmdSetRenderState; /* SVGA_3D_CMD_SETRENDERSTATE */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGA3dRenderTargetType type; - SVGA3dSurfaceImageId target; -} -#include "vmware_pack_end.h" -SVGA3dCmdSetRenderTarget; /* SVGA_3D_CMD_SETRENDERTARGET */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dSurfaceImageId src; - SVGA3dSurfaceImageId dest; - /* Followed by variable number of SVGA3dCopyBox structures */ -} -#include "vmware_pack_end.h" -SVGA3dCmdSurfaceCopy; /* SVGA_3D_CMD_SURFACE_COPY */ +#pragma pack(push, 1) +typedef struct { + uint32 id; + uint32 size; +} SVGA3dCmdHeader; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 numMipLevels; +} SVGA3dSurfaceFace; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 sid; + SVGA3dSurface1Flags surfaceFlags; + SVGA3dSurfaceFormat format; + + SVGA3dSurfaceFace face[SVGA3D_MAX_SURFACE_FACES]; + +} SVGA3dCmdDefineSurface; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 sid; + SVGA3dSurface1Flags surfaceFlags; + SVGA3dSurfaceFormat format; + + SVGA3dSurfaceFace face[SVGA3D_MAX_SURFACE_FACES]; + uint32 multisampleCount; + SVGA3dTextureFilter autogenFilter; + +} SVGA3dCmdDefineSurface_v2; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 sid; +} SVGA3dCmdDestroySurface; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; +} SVGA3dCmdDefineContext; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; +} SVGA3dCmdDestroyContext; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGA3dClearFlag clearFlag; + uint32 color; + float depth; + uint32 stencil; + +} SVGA3dCmdClear; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dLightType type; + SVGA3dBool inWorldSpace; + float diffuse[4]; + float specular[4]; + float ambient[4]; + float position[4]; + float direction[4]; + float range; + float falloff; + float attenuation0; + float attenuation1; + float attenuation2; + float theta; + float phi; +} SVGA3dLightData; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 sid; + +} SVGA3dCmdPresent; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dRenderStateName state; + union { + uint32 uintValue; + float floatValue; + }; +} SVGA3dRenderState; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + +} SVGA3dCmdSetRenderState; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGA3dRenderTargetType type; + SVGA3dSurfaceImageId target; +} SVGA3dCmdSetRenderTarget; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dSurfaceImageId src; + SVGA3dSurfaceImageId dest; + +} SVGA3dCmdSurfaceCopy; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dSurfaceImageId surface; + SVGA3dCopyBox box; +} SVGA3dCmdIntraSurfaceCopy; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 srcSid; + uint32 destSid; +} SVGA3dCmdWholeSurfaceCopy; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dSurfaceImageId src; + SVGA3dSurfaceImageId dest; + SVGA3dBox boxSrc; + SVGA3dBox boxDest; +} SVGA3dCmdSurfaceStretchBltNonMSToMS; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dSurfaceImageId src; + SVGA3dSurfaceImageId dest; + SVGA3dBox boxSrc; + SVGA3dBox boxDest; + SVGA3dStretchBltMode mode; +} SVGA3dCmdSurfaceStretchBlt; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 discard : 1; + + uint32 unsynchronized : 1; + + uint32 reserved : 30; +} SVGA3dSurfaceDMAFlags; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGAGuestImage guest; + SVGA3dSurfaceImageId host; + SVGA3dTransferType transfer; + +} SVGA3dCmdSurfaceDMA; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 suffixSize; + + uint32 maximumOffset; + + SVGA3dSurfaceDMAFlags flags; +} SVGA3dCmdSurfaceDMASuffix; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 first; + uint32 last; +} SVGA3dArrayRangeHint; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 surfaceId; + uint32 offset; + uint32 stride; +} SVGA3dArray; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dDeclType type; + SVGA3dDeclMethod method; + SVGA3dDeclUsage usage; + uint32 usageIndex; +} SVGA3dVertexArrayIdentity; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dVertexDecl { + SVGA3dVertexArrayIdentity identity; + SVGA3dArray array; + SVGA3dArrayRangeHint rangeHint; +} SVGA3dVertexDecl; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dPrimitiveRange { + SVGA3dPrimitiveType primType; + uint32 primitiveCount; + + SVGA3dArray indexArray; + uint32 indexWidth; + + int32 indexBias; +} SVGA3dPrimitiveRange; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + uint32 numVertexDecls; + uint32 numRanges; + +} SVGA3dCmdDrawPrimitives; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + + uint32 primitiveCount; + uint32 startVertexLocation; + + uint8 primitiveType; + uint8 padding[3]; +} SVGA3dCmdDraw; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + + uint8 primitiveType; + + uint32 indexBufferSid; + uint32 indexBufferOffset; + + uint8 indexBufferStride; + + int32 baseVertexLocation; + + uint32 primitiveCount; + uint32 pad0; + uint16 pad1; +} SVGA3dCmdDrawIndexed; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint16 streamOffset; + uint8 stream; + uint8 type; + uint8 method; + uint8 usage; + uint8 usageIndex; + uint8 padding; + +} SVGA3dVertexElement; +#pragma pack(pop) -/* - * Perform a surface copy within the same image. - * The src/dest boxes are allowed to overlap. - */ -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dSurfaceImageId surface; - SVGA3dCopyBox box; -} -#include "vmware_pack_end.h" -SVGA3dCmdIntraSurfaceCopy; /* SVGA_3D_CMD_INTRA_SURFACE_COPY */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 srcSid; - uint32 destSid; -} -#include "vmware_pack_end.h" -SVGA3dCmdWholeSurfaceCopy; /* SVGA_3D_CMD_WHOLE_SURFACE_COPY */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dSurfaceImageId src; - SVGA3dSurfaceImageId dest; - SVGA3dBox boxSrc; - SVGA3dBox boxDest; -} -#include "vmware_pack_end.h" -SVGA3dCmdSurfaceStretchBltNonMSToMS; -/* SVGA_3D_CMD_SURFACE_STRETCHBLT_NON_MS_TO_MS */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dSurfaceImageId src; - SVGA3dSurfaceImageId dest; - SVGA3dBox boxSrc; - SVGA3dBox boxDest; - SVGA3dStretchBltMode mode; -} -#include "vmware_pack_end.h" -SVGA3dCmdSurfaceStretchBlt; /* SVGA_3D_CMD_SURFACE_STRETCHBLT */ - -typedef -#include "vmware_pack_begin.h" -struct { - /* - * If the discard flag is present in a surface DMA operation, the host may - * discard the contents of the current mipmap level and face of the target - * surface before applying the surface DMA contents. - */ - uint32 discard : 1; - - /* - * If the unsynchronized flag is present, the host may perform this upload - * without syncing to pending reads on this surface. - */ - uint32 unsynchronized : 1; - - /* - * Guests *MUST* set the reserved bits to 0 before submitting the command - * suffix as future flags may occupy these bits. - */ - uint32 reserved : 30; -} -#include "vmware_pack_end.h" -SVGA3dSurfaceDMAFlags; - -typedef -#include "vmware_pack_begin.h" -struct { - SVGAGuestImage guest; - SVGA3dSurfaceImageId host; - SVGA3dTransferType transfer; - - /* - * Followed by variable number of SVGA3dCopyBox structures. For consistency - * in all clipping logic and coordinate translation, we define the - * "source" in each copyBox as the guest image and the - * "destination" as the host image, regardless of transfer - * direction. - * - * For efficiency, the SVGA3D device is free to copy more data than - * specified. For example, it may round copy boxes outwards such - * that they lie on particular alignment boundaries. - */ -} -#include "vmware_pack_end.h" -SVGA3dCmdSurfaceDMA; /* SVGA_3D_CMD_SURFACE_DMA */ - -/* - * SVGA3dCmdSurfaceDMASuffix -- - * - * This is a command suffix that will appear after a SurfaceDMA command in - * the FIFO. It contains some extra information that hosts may use to - * optimize performance or protect the guest. This suffix exists to preserve - * backwards compatibility while also allowing for new functionality to be - * implemented. - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 suffixSize; - - /* - * The maximum offset is used to determine the maximum offset from the - * guestPtr base address that will be accessed or written to during this - * surfaceDMA. If the suffix is supported, the host will respect this - * boundary while performing surface DMAs. - * - * Defaults to MAX_UINT32 - */ - uint32 maximumOffset; - - /* - * A set of flags that describes optimizations that the host may perform - * while performing this surface DMA operation. The guest should never rely - * on behaviour that is different when these flags are set for correctness. - * - * Defaults to 0 - */ - SVGA3dSurfaceDMAFlags flags; -} -#include "vmware_pack_end.h" -SVGA3dCmdSurfaceDMASuffix; - -/* - * SVGA_3D_CMD_DRAW_PRIMITIVES -- - * - * This command is the SVGA3D device's generic drawing entry point. - * It can draw multiple ranges of primitives, optionally using an - * index buffer, using an arbitrary collection of vertex buffers. - * - * Each SVGA3dVertexDecl defines a distinct vertex array to bind - * during this draw call. The declarations specify which surface - * the vertex data lives in, what that vertex data is used for, - * and how to interpret it. - * - * Each SVGA3dPrimitiveRange defines a collection of primitives - * to render using the same vertex arrays. An index buffer is - * optional. - */ - -typedef -#include "vmware_pack_begin.h" -struct { - /* - * A range hint is an optional specification for the range of indices - * in an SVGA3dArray that will be used. If 'last' is zero, it is assumed - * that the entire array will be used. - * - * These are only hints. The SVGA3D device may use them for - * performance optimization if possible, but it's also allowed to - * ignore these values. - */ - uint32 first; - uint32 last; -} -#include "vmware_pack_end.h" -SVGA3dArrayRangeHint; - -typedef -#include "vmware_pack_begin.h" -struct { - /* - * Define the origin and shape of a vertex or index array. Both - * 'offset' and 'stride' are in bytes. The provided surface will be - * reinterpreted as a flat array of bytes in the same format used - * by surface DMA operations. To avoid unnecessary conversions, the - * surface should be created with the SVGA3D_BUFFER format. - * - * Index 0 in the array starts 'offset' bytes into the surface. - * Index 1 begins at byte 'offset + stride', etc. Array indices may - * not be negative. - */ - uint32 surfaceId; - uint32 offset; - uint32 stride; -} -#include "vmware_pack_end.h" -SVGA3dArray; - -typedef -#include "vmware_pack_begin.h" -struct { - /* - * Describe a vertex array's data type, and define how it is to be - * used by the fixed function pipeline or the vertex shader. It - * isn't useful to have two VertexDecls with the same - * VertexArrayIdentity in one draw call. - */ - SVGA3dDeclType type; - SVGA3dDeclMethod method; - SVGA3dDeclUsage usage; - uint32 usageIndex; -} -#include "vmware_pack_end.h" -SVGA3dVertexArrayIdentity; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dVertexDecl { - SVGA3dVertexArrayIdentity identity; - SVGA3dArray array; - SVGA3dArrayRangeHint rangeHint; -} -#include "vmware_pack_end.h" -SVGA3dVertexDecl; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dPrimitiveRange { - /* - * Define a group of primitives to render, from sequential indices. - * - * The value of 'primitiveType' and 'primitiveCount' imply the - * total number of vertices that will be rendered. - */ - SVGA3dPrimitiveType primType; - uint32 primitiveCount; - - /* - * Optional index buffer. If indexArray.surfaceId is - * SVGA3D_INVALID_ID, we render without an index buffer. Rendering - * without an index buffer is identical to rendering with an index - * buffer containing the sequence [0, 1, 2, 3, ...]. - * - * If an index buffer is in use, indexWidth specifies the width in - * bytes of each index value. It must be less than or equal to - * indexArray.stride. - * - * (Currently, the SVGA3D device requires index buffers to be tightly - * packed. In other words, indexWidth == indexArray.stride) - */ - SVGA3dArray indexArray; - uint32 indexWidth; - - /* - * Optional index bias. This number is added to all indices from - * indexArray before they are used as vertex array indices. This - * can be used in multiple ways: - * - * - When not using an indexArray, this bias can be used to - * specify where in the vertex arrays to begin rendering. - * - * - A positive number here is equivalent to increasing the - * offset in each vertex array. - * - * - A negative number can be used to render using a small - * vertex array and an index buffer that contains large - * values. This may be used by some applications that - * crop a vertex buffer without modifying their index - * buffer. - * - * Note that rendering with a negative bias value may be slower and - * use more memory than rendering with a positive or zero bias. - */ - int32 indexBias; -} -#include "vmware_pack_end.h" -SVGA3dPrimitiveRange; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - uint32 numVertexDecls; - uint32 numRanges; - - /* - * There are two variable size arrays after the - * SVGA3dCmdDrawPrimitives structure. In order, - * they are: - * - * 1. SVGA3dVertexDecl, quantity 'numVertexDecls', but no more than - * SVGA3D_MAX_VERTEX_ARRAYS; - * 2. SVGA3dPrimitiveRange, quantity 'numRanges', but no more than - * SVGA3D_MAX_DRAW_PRIMITIVE_RANGES; - * 3. Optionally, SVGA3dVertexDivisor, quantity 'numVertexDecls' (contains - * the frequency divisor for the corresponding vertex decl). - */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDrawPrimitives; /* SVGA_3D_CMD_DRAWPRIMITIVES */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - - uint32 primitiveCount; /* How many primitives to render */ - uint32 startVertexLocation; /* Which vertex do we start rendering at. */ - - uint8 primitiveType; /* SVGA3dPrimitiveType */ - uint8 padding[3]; -} -#include "vmware_pack_end.h" -SVGA3dCmdDraw; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - - uint8 primitiveType; /* SVGA3dPrimitiveType */ - - uint32 indexBufferSid; /* Valid index buffer sid. */ - uint32 indexBufferOffset; /* Byte offset into the vertex buffer, almost */ - /* always 0 for pre SM guests, non-zero for OpenGL */ - /* guests. We can't represent non-multiple of */ - /* stride offsets in D3D9Renderer... */ - uint8 indexBufferStride; /* Allowable values = 1, 2, or 4 */ - - int32 baseVertexLocation; /* Bias applied to the index when selecting a */ - /* vertex from the streams, may be negative */ - - uint32 primitiveCount; /* How many primitives to render */ - uint32 pad0; - uint16 pad1; -} -#include "vmware_pack_end.h" -SVGA3dCmdDrawIndexed; - -typedef -#include "vmware_pack_begin.h" -struct { - /* - * Describe a vertex array's data type, and define how it is to be - * used by the fixed function pipeline or the vertex shader. It - * isn't useful to have two VertexDecls with the same - * VertexArrayIdentity in one draw call. - */ - uint16 streamOffset; - uint8 stream; - uint8 type; /* SVGA3dDeclType */ - uint8 method; /* SVGA3dDeclMethod */ - uint8 usage; /* SVGA3dDeclUsage */ - uint8 usageIndex; - uint8 padding; - -} -#include "vmware_pack_end.h" -SVGA3dVertexElement; - -/* - * Should the vertex element respect the stream value? The high bit of the - * stream should be set to indicate that the stream should be respected. If - * the high bit is not set, the stream will be ignored and replaced by the index - * of the position of the currently considered vertex element. - * - * All guests should set this bit and correctly specify the stream going - * forward. - */ #define SVGA3D_VERTEX_ELEMENT_RESPECT_STREAM (1 << 7) -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - - uint32 numElements; - - /* - * Followed by numElements SVGA3dVertexElement structures. - * - * If numElements < SVGA3D_MAX_VERTEX_ARRAYS, the remaining elements - * are cleared and will not be used by following draws. - */ -} -#include "vmware_pack_end.h" -SVGA3dCmdSetVertexDecls; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 sid; - uint32 stride; - uint32 offset; -} -#include "vmware_pack_end.h" -SVGA3dVertexStream; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - - uint32 numStreams; - /* - * Followed by numStream SVGA3dVertexStream structures. - * - * If numStreams < SVGA3D_MAX_VERTEX_ARRAYS, the remaining streams - * are cleared and will not be used by following draws. - */ -} -#include "vmware_pack_end.h" -SVGA3dCmdSetVertexStreams; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - uint32 numDivisors; -} -#include "vmware_pack_end.h" -SVGA3dCmdSetVertexDivisors; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 stage; - SVGA3dTextureStateName name; - union { - uint32 value; - float floatValue; - }; -} -#include "vmware_pack_end.h" -SVGA3dTextureState; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - /* Followed by variable number of SVGA3dTextureState structures */ -} -#include "vmware_pack_end.h" -SVGA3dCmdSetTextureState; /* SVGA_3D_CMD_SETTEXTURESTATE */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGA3dTransformType type; - float matrix[16]; -} -#include "vmware_pack_end.h" -SVGA3dCmdSetTransform; /* SVGA_3D_CMD_SETTRANSFORM */ - -typedef -#include "vmware_pack_begin.h" -struct { - float min; - float max; -} -#include "vmware_pack_end.h" -SVGA3dZRange; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGA3dZRange zRange; -} -#include "vmware_pack_end.h" -SVGA3dCmdSetZRange; /* SVGA_3D_CMD_SETZRANGE */ - -typedef -#include "vmware_pack_begin.h" -struct { - float diffuse[4]; - float ambient[4]; - float specular[4]; - float emissive[4]; - float shininess; -} -#include "vmware_pack_end.h" -SVGA3dMaterial; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGA3dFace face; - SVGA3dMaterial material; -} -#include "vmware_pack_end.h" -SVGA3dCmdSetMaterial; /* SVGA_3D_CMD_SETMATERIAL */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - uint32 index; - SVGA3dLightData data; -} -#include "vmware_pack_end.h" -SVGA3dCmdSetLightData; /* SVGA_3D_CMD_SETLIGHTDATA */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - uint32 index; - uint32 enabled; -} -#include "vmware_pack_end.h" -SVGA3dCmdSetLightEnabled; /* SVGA_3D_CMD_SETLIGHTENABLED */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGA3dRect rect; -} -#include "vmware_pack_end.h" -SVGA3dCmdSetViewport; /* SVGA_3D_CMD_SETVIEWPORT */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGA3dRect rect; -} -#include "vmware_pack_end.h" -SVGA3dCmdSetScissorRect; /* SVGA_3D_CMD_SETSCISSORRECT */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - uint32 index; - float plane[4]; -} -#include "vmware_pack_end.h" -SVGA3dCmdSetClipPlane; /* SVGA_3D_CMD_SETCLIPPLANE */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - uint32 shid; - SVGA3dShaderType type; - /* Followed by variable number of DWORDs for shader bycode */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDefineShader; /* SVGA_3D_CMD_SHADER_DEFINE */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - uint32 shid; - SVGA3dShaderType type; -} -#include "vmware_pack_end.h" -SVGA3dCmdDestroyShader; /* SVGA_3D_CMD_SHADER_DESTROY */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - uint32 reg; /* register number */ - SVGA3dShaderType type; - SVGA3dShaderConstType ctype; - uint32 values[4]; - - /* - * Followed by a variable number of additional values. - */ -} -#include "vmware_pack_end.h" -SVGA3dCmdSetShaderConst; /* SVGA_3D_CMD_SET_SHADER_CONST */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGA3dShaderType type; - uint32 shid; -} -#include "vmware_pack_end.h" -SVGA3dCmdSetShader; /* SVGA_3D_CMD_SET_SHADER */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGA3dQueryType type; -} -#include "vmware_pack_end.h" -SVGA3dCmdBeginQuery; /* SVGA_3D_CMD_BEGIN_QUERY */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGA3dQueryType type; - SVGAGuestPtr guestResult; /* Points to an SVGA3dQueryResult structure */ -} -#include "vmware_pack_end.h" -SVGA3dCmdEndQuery; /* SVGA_3D_CMD_END_QUERY */ - - -/* - * SVGA3D_CMD_WAIT_FOR_QUERY -- - * - * Will read the SVGA3dQueryResult structure pointed to by guestResult, - * and if the state member is set to anything else than - * SVGA3D_QUERYSTATE_PENDING, this command will always be a no-op. - * - * Otherwise, in addition to the query explicitly waited for, - * All queries with the same type and issued with the same cid, for which - * an SVGA_3D_CMD_END_QUERY command has previously been sent, will - * be finished after execution of this command. - * - * A query will be identified by the gmrId and offset of the guestResult - * member. If the device can't find an SVGA_3D_CMD_END_QUERY that has - * been sent previously with an indentical gmrId and offset, it will - * effectively end all queries with an identical type issued with the - * same cid, and the SVGA3dQueryResult structure pointed to by - * guestResult will not be written to. This property can be used to - * implement a query barrier for a given cid and query type. - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; /* Same parameters passed to END_QUERY */ - SVGA3dQueryType type; - SVGAGuestPtr guestResult; -} -#include "vmware_pack_end.h" -SVGA3dCmdWaitForQuery; /* SVGA_3D_CMD_WAIT_FOR_QUERY */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 totalSize; /* Set by guest before query is ended. */ - SVGA3dQueryState state; /* Set by host or guest. See SVGA3dQueryState. */ - union { /* Set by host on exit from PENDING state */ - uint32 result32; - uint32 queryCookie; /* May be used to identify which QueryGetData this - result corresponds to. */ - }; -} -#include "vmware_pack_end.h" -SVGA3dQueryResult; - - -/* - * SVGA_3D_CMD_BLIT_SURFACE_TO_SCREEN -- - * - * This is a blit from an SVGA3D surface to a Screen Object. - * This blit must be directed at a specific screen. - * - * The blit copies from a rectangular region of an SVGA3D surface - * image to a rectangular region of a screen. - * - * This command takes an optional variable-length list of clipping - * rectangles after the body of the command. If no rectangles are - * specified, there is no clipping region. The entire destRect is - * drawn to. If one or more rectangles are included, they describe - * a clipping region. The clip rectangle coordinates are measured - * relative to the top-left corner of destRect. - * - * The srcImage must be from mip=0 face=0. - * - * This supports scaling if the src and dest are of different sizes. - * - * Availability: - * SVGA_FIFO_CAP_SCREEN_OBJECT - */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dSurfaceImageId srcImage; - SVGASignedRect srcRect; - uint32 destScreenId; /* Screen Object ID */ - SVGASignedRect destRect; - /* Clipping: zero or more SVGASignedRects follow */ -} -#include "vmware_pack_end.h" -SVGA3dCmdBlitSurfaceToScreen; /* SVGA_3D_CMD_BLIT_SURFACE_TO_SCREEN */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 sid; - SVGA3dTextureFilter filter; -} -#include "vmware_pack_end.h" -SVGA3dCmdGenerateMipmaps; /* SVGA_3D_CMD_GENERATE_MIPMAPS */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 sid; -} -#include "vmware_pack_end.h" -SVGA3dCmdActivateSurface; /* SVGA_3D_CMD_ACTIVATE_SURFACE */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 sid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDeactivateSurface; /* SVGA_3D_CMD_DEACTIVATE_SURFACE */ - -/* - * Screen DMA command - * - * Available with SVGA_FIFO_CAP_SCREEN_OBJECT_2. The SVGA_CAP_3D device - * cap bit is not required. - * - * - refBuffer and destBuffer are 32bit BGRX; refBuffer and destBuffer could - * be different, but it is required that guest makes sure refBuffer has - * exactly the same contents that were written to when last time screen DMA - * command is received by host. - * - * - changemap is generated by lib/blit, and it has the changes from last - * received screen DMA or more. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdScreenDMA { - uint32 screenId; - SVGAGuestImage refBuffer; - SVGAGuestImage destBuffer; - SVGAGuestImage changeMap; -} -#include "vmware_pack_end.h" -SVGA3dCmdScreenDMA; /* SVGA_3D_CMD_SCREEN_DMA */ - -/* - * Logic ops - */ - -#define SVGA3D_LOTRANSBLT_HONORALPHA (0x01) -#define SVGA3D_LOSTRETCHBLT_MIRRORX (0x01) -#define SVGA3D_LOSTRETCHBLT_MIRRORY (0x02) -#define SVGA3D_LOALPHABLEND_SRCHASALPHA (0x01) - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdLogicOpsBitBlt { - /* - * All LogicOps surfaces are one-level - * surfaces so mipmap & face should always - * be zero. - */ - SVGA3dSurfaceImageId src; - SVGA3dSurfaceImageId dst; - SVGA3dLogicOp logicOp; - SVGA3dLogicOpRop3 logicOpRop3; - /* Followed by variable number of SVGA3dCopyBox structures */ -} -#include "vmware_pack_end.h" -SVGA3dCmdLogicOpsBitBlt; /* SVGA_3D_CMD_LOGICOPS_BITBLT */ - - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdLogicOpsTransBlt { - /* - * All LogicOps surfaces are one-level - * surfaces so mipmap & face should always - * be zero. - */ - SVGA3dSurfaceImageId src; - SVGA3dSurfaceImageId dst; - uint32 color; - uint32 flags; - SVGA3dBox srcBox; - SVGA3dSignedBox dstBox; - SVGA3dBox clipBox; -} -#include "vmware_pack_end.h" -SVGA3dCmdLogicOpsTransBlt; /* SVGA_3D_CMD_LOGICOPS_TRANSBLT */ - - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdLogicOpsStretchBlt { - /* - * All LogicOps surfaces are one-level - * surfaces so mipmap & face should always - * be zero. - */ - SVGA3dSurfaceImageId src; - SVGA3dSurfaceImageId dst; - uint16 mode; - uint16 flags; - SVGA3dBox srcBox; - SVGA3dSignedBox dstBox; - SVGA3dBox clipBox; -} -#include "vmware_pack_end.h" -SVGA3dCmdLogicOpsStretchBlt; /* SVGA_3D_CMD_LOGICOPS_STRETCHBLT */ - - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdLogicOpsColorFill { - /* - * All LogicOps surfaces are one-level - * surfaces so mipmap & face should always - * be zero. - */ - SVGA3dSurfaceImageId dst; - uint32 color; - SVGA3dLogicOp logicOp; - SVGA3dLogicOpRop3 logicOpRop3; - /* Followed by variable number of SVGA3dRect structures. */ -} -#include "vmware_pack_end.h" -SVGA3dCmdLogicOpsColorFill; /* SVGA_3D_CMD_LOGICOPS_COLORFILL */ - - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdLogicOpsAlphaBlend { - /* - * All LogicOps surfaces are one-level - * surfaces so mipmap & face should always - * be zero. - */ - SVGA3dSurfaceImageId src; - SVGA3dSurfaceImageId dst; - uint32 alphaVal; - uint32 flags; - SVGA3dBox srcBox; - SVGA3dSignedBox dstBox; - SVGA3dBox clipBox; -} -#include "vmware_pack_end.h" -SVGA3dCmdLogicOpsAlphaBlend; /* SVGA_3D_CMD_LOGICOPS_ALPHABLEND */ +#pragma pack(push, 1) +typedef struct { + uint32 cid; + + uint32 numElements; + +} SVGA3dCmdSetVertexDecls; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 sid; + uint32 stride; + uint32 offset; +} SVGA3dVertexStream; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + + uint32 numStreams; + +} SVGA3dCmdSetVertexStreams; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + uint32 numDivisors; +} SVGA3dCmdSetVertexDivisors; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 stage; + SVGA3dTextureStateName name; + union { + uint32 value; + float floatValue; + }; +} SVGA3dTextureState; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + +} SVGA3dCmdSetTextureState; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGA3dTransformType type; + float matrix[16]; +} SVGA3dCmdSetTransform; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + float min; + float max; +} SVGA3dZRange; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGA3dZRange zRange; +} SVGA3dCmdSetZRange; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + float diffuse[4]; + float ambient[4]; + float specular[4]; + float emissive[4]; + float shininess; +} SVGA3dMaterial; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGA3dFace face; + SVGA3dMaterial material; +} SVGA3dCmdSetMaterial; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + uint32 index; + SVGA3dLightData data; +} SVGA3dCmdSetLightData; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + uint32 index; + uint32 enabled; +} SVGA3dCmdSetLightEnabled; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGA3dRect rect; +} SVGA3dCmdSetViewport; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGA3dRect rect; +} SVGA3dCmdSetScissorRect; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + uint32 index; + float plane[4]; +} SVGA3dCmdSetClipPlane; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + uint32 shid; + SVGA3dShaderType type; + +} SVGA3dCmdDefineShader; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + uint32 shid; + SVGA3dShaderType type; +} SVGA3dCmdDestroyShader; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + uint32 reg; + SVGA3dShaderType type; + SVGA3dShaderConstType ctype; + uint32 values[4]; + +} SVGA3dCmdSetShaderConst; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGA3dShaderType type; + uint32 shid; +} SVGA3dCmdSetShader; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGA3dQueryType type; +} SVGA3dCmdBeginQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGA3dQueryType type; + SVGAGuestPtr guestResult; +} SVGA3dCmdEndQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGA3dQueryType type; + SVGAGuestPtr guestResult; +} SVGA3dCmdWaitForQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 totalSize; + SVGA3dQueryState state; + union { + uint32 result32; + uint32 queryCookie; + }; +} SVGA3dQueryResult; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dSurfaceImageId srcImage; + SVGASignedRect srcRect; + uint32 destScreenId; + SVGASignedRect destRect; + +} SVGA3dCmdBlitSurfaceToScreen; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 sid; + SVGA3dTextureFilter filter; +} SVGA3dCmdGenerateMipmaps; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 sid; +} SVGA3dCmdActivateSurface; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 sid; +} SVGA3dCmdDeactivateSurface; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdScreenDMA { + uint32 screenId; + SVGAGuestImage refBuffer; + SVGAGuestImage destBuffer; + SVGAGuestImage changeMap; +} SVGA3dCmdScreenDMA; +#pragma pack(pop) + +#define SVGA3D_LOTRANSBLT_HONORALPHA (0x01) +#define SVGA3D_LOSTRETCHBLT_MIRRORX (0x01) +#define SVGA3D_LOSTRETCHBLT_MIRRORY (0x02) +#define SVGA3D_LOALPHABLEND_SRCHASALPHA (0x01) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdLogicOpsBitBlt { + SVGA3dSurfaceImageId src; + SVGA3dSurfaceImageId dst; + SVGA3dLogicOp logicOp; + SVGA3dLogicOpRop3 logicOpRop3; + +} SVGA3dCmdLogicOpsBitBlt; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdLogicOpsTransBlt { + SVGA3dSurfaceImageId src; + SVGA3dSurfaceImageId dst; + uint32 color; + uint32 flags; + SVGA3dBox srcBox; + SVGA3dSignedBox dstBox; + SVGA3dBox clipBox; +} SVGA3dCmdLogicOpsTransBlt; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdLogicOpsStretchBlt { + SVGA3dSurfaceImageId src; + SVGA3dSurfaceImageId dst; + uint16 mode; + uint16 flags; + SVGA3dBox srcBox; + SVGA3dSignedBox dstBox; + SVGA3dBox clipBox; +} SVGA3dCmdLogicOpsStretchBlt; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdLogicOpsColorFill { + SVGA3dSurfaceImageId dst; + uint32 color; + SVGA3dLogicOp logicOp; + SVGA3dLogicOpRop3 logicOpRop3; + +} SVGA3dCmdLogicOpsColorFill; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdLogicOpsAlphaBlend { + SVGA3dSurfaceImageId src; + SVGA3dSurfaceImageId dst; + uint32 alphaVal; + uint32 flags; + SVGA3dBox srcBox; + SVGA3dSignedBox dstBox; + SVGA3dBox clipBox; +} SVGA3dCmdLogicOpsAlphaBlend; +#pragma pack(pop) #define SVGA3D_CLEARTYPE_INVALID_GAMMA_INDEX 0xFFFFFFFF -#define SVGA3D_CLEARTYPE_GAMMA_WIDTH 512 +#define SVGA3D_CLEARTYPE_GAMMA_WIDTH 512 #define SVGA3D_CLEARTYPE_GAMMA_HEIGHT 16 -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdLogicOpsClearTypeBlend { - /* - * All LogicOps surfaces are one-level - * surfaces so mipmap & face should always - * be zero. - */ - SVGA3dSurfaceImageId tmp; - SVGA3dSurfaceImageId dst; - SVGA3dSurfaceImageId gammaSurf; - SVGA3dSurfaceImageId alphaSurf; - uint32 gamma; - uint32 color; - uint32 color2; - int32 alphaOffsetX; - int32 alphaOffsetY; - /* Followed by variable number of SVGA3dBox structures */ -} -#include "vmware_pack_end.h" -SVGA3dCmdLogicOpsClearTypeBlend; /* SVGA_3D_CMD_LOGICOPS_CLEARTYPEBLEND */ - - -/* - * Guest-backed objects definitions. - */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGAMobFormat ptDepth; - uint32 sizeInBytes; - PPN64 base; -} -#include "vmware_pack_end.h" -SVGAOTableMobEntry; -#define SVGA3D_OTABLE_MOB_ENTRY_SIZE (sizeof(SVGAOTableMobEntry)) - -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dSurfaceFormat format; - SVGA3dSurface1Flags surface1Flags; - uint32 numMipLevels; - uint32 multisampleCount; - SVGA3dTextureFilter autogenFilter; - SVGA3dSize size; - SVGAMobId mobid; - uint32 arraySize; - uint32 mobPitch; - SVGA3dSurface2Flags surface2Flags; - uint8 multisamplePattern; - uint8 qualityLevel; - uint16 bufferByteStride; - float minLOD; - uint32 pad0[2]; -} -#include "vmware_pack_end.h" -SVGAOTableSurfaceEntry; -#define SVGA3D_OTABLE_SURFACE_ENTRY_SIZE (sizeof(SVGAOTableSurfaceEntry)) - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGAMobId mobid; -} -#include "vmware_pack_end.h" -SVGAOTableContextEntry; -#define SVGA3D_OTABLE_CONTEXT_ENTRY_SIZE (sizeof(SVGAOTableContextEntry)) - -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dShaderType type; - uint32 sizeInBytes; - uint32 offsetInBytes; - SVGAMobId mobid; -} -#include "vmware_pack_end.h" -SVGAOTableShaderEntry; -#define SVGA3D_OTABLE_SHADER_ENTRY_SIZE (sizeof(SVGAOTableShaderEntry)) - -#define SVGA_STFLAG_PRIMARY (1 << 0) -#define SVGA_STFLAG_RESERVED (1 << 1) /* Added with cap SVGA_CAP_HP_CMD_QUEUE */ +#pragma pack(push, 1) +typedef struct SVGA3dCmdLogicOpsClearTypeBlend { + SVGA3dSurfaceImageId tmp; + SVGA3dSurfaceImageId dst; + SVGA3dSurfaceImageId gammaSurf; + SVGA3dSurfaceImageId alphaSurf; + uint32 gamma; + uint32 color; + uint32 color2; + int32 alphaOffsetX; + int32 alphaOffsetY; + +} SVGA3dCmdLogicOpsClearTypeBlend; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGAMobFormat ptDepth; + uint32 sizeInBytes; + PPN64 base; +} SVGAOTableMobEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dSurfaceFormat format; + SVGA3dSurface1Flags surface1Flags; + uint32 numMipLevels; + uint32 multisampleCount; + SVGA3dTextureFilter autogenFilter; + SVGA3dSize size; + SVGAMobId mobid; + uint32 arraySize; + uint32 mobPitch; + SVGA3dSurface2Flags surface2Flags; + uint8 multisamplePattern; + uint8 qualityLevel; + uint16 bufferByteStride; + float minLOD; + uint32 pad0[2]; +} SVGAOTableSurfaceEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGAMobId mobid; +} SVGAOTableContextEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dShaderType type; + uint32 sizeInBytes; + uint32 offsetInBytes; + SVGAMobId mobid; +} SVGAOTableShaderEntry; +#pragma pack(pop) + +#define SVGA_STFLAG_PRIMARY (1 << 0) +#define SVGA_STFLAG_RESERVED (1 << 1) typedef uint32 SVGAScreenTargetFlags; -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dSurfaceImageId image; - uint32 width; - uint32 height; - int32 xRoot; - int32 yRoot; - SVGAScreenTargetFlags flags; - uint32 dpi; - uint32 pad[7]; -} -#include "vmware_pack_end.h" -SVGAOTableScreenTargetEntry; -#define SVGA3D_OTABLE_SCREEN_TARGET_ENTRY_SIZE \ - (sizeof(SVGAOTableScreenTargetEntry)) - -typedef -#include "vmware_pack_begin.h" -struct { - float value[4]; -} -#include "vmware_pack_end.h" -SVGA3dShaderConstFloat; - -typedef -#include "vmware_pack_begin.h" -struct { - int32 value[4]; -} -#include "vmware_pack_end.h" -SVGA3dShaderConstInt; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 value; -} -#include "vmware_pack_end.h" -SVGA3dShaderConstBool; - -typedef -#include "vmware_pack_begin.h" -struct { - uint16 streamOffset; - uint8 stream; - uint8 type; - uint8 methodUsage; - uint8 usageIndex; -} -#include "vmware_pack_end.h" -SVGAGBVertexElement; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 sid; - uint16 stride; - uint32 offset; -} -#include "vmware_pack_end.h" -SVGAGBVertexStream; -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dRect viewport; - SVGA3dRect scissorRect; - SVGA3dZRange zRange; - - SVGA3dSurfaceImageId renderTargets[SVGA3D_RT_MAX]; - SVGAGBVertexElement decl1[4]; - - uint32 renderStates[SVGA3D_RS_MAX]; - SVGAGBVertexElement decl2[18]; - uint32 pad0[2]; - - struct { - SVGA3dFace face; - SVGA3dMaterial material; - } material; - - float clipPlanes[SVGA3D_NUM_CLIPPLANES][4]; - float matrices[SVGA3D_TRANSFORM_MAX][16]; - - SVGA3dBool lightEnabled[SVGA3D_NUM_LIGHTS]; - SVGA3dLightData lightData[SVGA3D_NUM_LIGHTS]; - - /* - * Shaders currently bound - */ - uint32 shaders[SVGA3D_NUM_SHADERTYPE_PREDX]; - SVGAGBVertexElement decl3[10]; - uint32 pad1[3]; - - uint32 occQueryActive; - uint32 occQueryValue; - - /* - * Int/Bool Shader constants - */ - SVGA3dShaderConstInt pShaderIValues[SVGA3D_CONSTINTREG_MAX]; - SVGA3dShaderConstInt vShaderIValues[SVGA3D_CONSTINTREG_MAX]; - uint16 pShaderBValues; - uint16 vShaderBValues; - - - SVGAGBVertexStream streams[SVGA3D_MAX_VERTEX_ARRAYS]; - SVGA3dVertexDivisor divisors[SVGA3D_MAX_VERTEX_ARRAYS]; - uint32 numVertexDecls; - uint32 numVertexStreams; - uint32 numVertexDivisors; - uint32 pad2[30]; - - /* - * Texture Stages - * - * SVGA3D_TS_INVALID through SVGA3D_TS_CONSTANT are in the - * textureStages array. - * SVGA3D_TS_COLOR_KEY is in tsColorKey. - */ - uint32 tsColorKey[SVGA3D_NUM_TEXTURE_UNITS]; - uint32 textureStages[SVGA3D_NUM_TEXTURE_UNITS][SVGA3D_TS_CONSTANT + 1]; - uint32 tsColorKeyEnable[SVGA3D_NUM_TEXTURE_UNITS]; - - /* - * Float Shader constants. - */ - SVGA3dShaderConstFloat pShaderFValues[SVGA3D_CONSTREG_MAX]; - SVGA3dShaderConstFloat vShaderFValues[SVGA3D_CONSTREG_MAX]; -} -#include "vmware_pack_end.h" -SVGAGBContextData; -#define SVGA3D_CONTEXT_DATA_SIZE (sizeof(SVGAGBContextData)) - -/* - * SVGA3dCmdSetOTableBase -- - * - * This command allows the guest to specify the base PPN of the - * specified object table. - */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGAOTableType type; - PPN32 baseAddress; - uint32 sizeInBytes; - uint32 validSizeInBytes; - SVGAMobFormat ptDepth; -} -#include "vmware_pack_end.h" -SVGA3dCmdSetOTableBase; /* SVGA_3D_CMD_SET_OTABLE_BASE */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGAOTableType type; - PPN64 baseAddress; - uint32 sizeInBytes; - uint32 validSizeInBytes; - SVGAMobFormat ptDepth; -} -#include "vmware_pack_end.h" -SVGA3dCmdSetOTableBase64; /* SVGA_3D_CMD_SET_OTABLE_BASE64 */ - -/* - * Guests using SVGA_3D_CMD_GROW_OTABLE are promising that - * the new OTable contains the same contents as the old one, except possibly - * for some new invalid entries at the end. - * - * (Otherwise, guests should use one of the SetOTableBase commands.) - */ -typedef -#include "vmware_pack_begin.h" -struct { - SVGAOTableType type; - PPN64 baseAddress; - uint32 sizeInBytes; - uint32 validSizeInBytes; - SVGAMobFormat ptDepth; -} -#include "vmware_pack_end.h" -SVGA3dCmdGrowOTable; /* SVGA_3D_CMD_GROW_OTABLE */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGAOTableType type; -} -#include "vmware_pack_end.h" -SVGA3dCmdReadbackOTable; /* SVGA_3D_CMD_READBACK_OTABLE */ - -/* - * Define a memory object (Mob) in the OTable. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDefineGBMob { - SVGAMobId mobid; - SVGAMobFormat ptDepth; - PPN32 base; - uint32 sizeInBytes; -} -#include "vmware_pack_end.h" -SVGA3dCmdDefineGBMob; /* SVGA_3D_CMD_DEFINE_GB_MOB */ - - -/* - * Destroys an object in the OTable. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDestroyGBMob { - SVGAMobId mobid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDestroyGBMob; /* SVGA_3D_CMD_DESTROY_GB_MOB */ - -/* - * Define a memory object (Mob) in the OTable with a PPN64 base. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDefineGBMob64 { - SVGAMobId mobid; - SVGAMobFormat ptDepth; - PPN64 base; - uint32 sizeInBytes; -} -#include "vmware_pack_end.h" -SVGA3dCmdDefineGBMob64; /* SVGA_3D_CMD_DEFINE_GB_MOB64 */ - -/* - * Redefine an object in the OTable with PPN64 base. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdRedefineGBMob64 { - SVGAMobId mobid; - SVGAMobFormat ptDepth; - PPN64 base; - uint32 sizeInBytes; -} -#include "vmware_pack_end.h" -SVGA3dCmdRedefineGBMob64; /* SVGA_3D_CMD_REDEFINE_GB_MOB64 */ - -/* - * Notification that the page tables have been modified. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdUpdateGBMobMapping { - SVGAMobId mobid; -} -#include "vmware_pack_end.h" -SVGA3dCmdUpdateGBMobMapping; /* SVGA_3D_CMD_UPDATE_GB_MOB_MAPPING */ - -/* - * Define a guest-backed surface. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDefineGBSurface { - uint32 sid; - SVGA3dSurface1Flags surfaceFlags; - SVGA3dSurfaceFormat format; - uint32 numMipLevels; - uint32 multisampleCount; - SVGA3dTextureFilter autogenFilter; - SVGA3dSize size; -} -#include "vmware_pack_end.h" -SVGA3dCmdDefineGBSurface; /* SVGA_3D_CMD_DEFINE_GB_SURFACE */ - -/* - * Defines a guest-backed surface, adding the arraySize field. - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDefineGBSurface_v2 { - uint32 sid; - SVGA3dSurface1Flags surfaceFlags; - SVGA3dSurfaceFormat format; - uint32 numMipLevels; - uint32 multisampleCount; - SVGA3dTextureFilter autogenFilter; - SVGA3dSize size; - uint32 arraySize; - uint32 pad; -} -#include "vmware_pack_end.h" -SVGA3dCmdDefineGBSurface_v2; /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V2 */ - -/* - * Defines a guest-backed surface, adding the larger flags. - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDefineGBSurface_v3 { - uint32 sid; - SVGA3dSurfaceAllFlags surfaceFlags; - SVGA3dSurfaceFormat format; - uint32 numMipLevels; - uint32 multisampleCount; - SVGA3dMSPattern multisamplePattern; - SVGA3dMSQualityLevel qualityLevel; - SVGA3dTextureFilter autogenFilter; - SVGA3dSize size; - uint32 arraySize; -} -#include "vmware_pack_end.h" -SVGA3dCmdDefineGBSurface_v3; /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V3 */ - -/* - * Defines a guest-backed surface, adding buffer byte stride. - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDefineGBSurface_v4 { - uint32 sid; - SVGA3dSurfaceAllFlags surfaceFlags; - SVGA3dSurfaceFormat format; - uint32 numMipLevels; - uint32 multisampleCount; - SVGA3dMSPattern multisamplePattern; - SVGA3dMSQualityLevel qualityLevel; - SVGA3dTextureFilter autogenFilter; - SVGA3dSize size; - uint32 arraySize; - uint32 bufferByteStride; -} -#include "vmware_pack_end.h" -SVGA3dCmdDefineGBSurface_v4; /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V4 */ - -/* - * Destroy a guest-backed surface. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDestroyGBSurface { - uint32 sid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDestroyGBSurface; /* SVGA_3D_CMD_DESTROY_GB_SURFACE */ - -/* - * Bind a guest-backed surface to a mob. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdBindGBSurface { - uint32 sid; - SVGAMobId mobid; -} -#include "vmware_pack_end.h" -SVGA3dCmdBindGBSurface; /* SVGA_3D_CMD_BIND_GB_SURFACE */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdBindGBSurfaceWithPitch { - uint32 sid; - SVGAMobId mobid; - uint32 baseLevelPitch; -} -#include "vmware_pack_end.h" -SVGA3dCmdBindGBSurfaceWithPitch; /* SVGA_3D_CMD_BIND_GB_SURFACE_WITH_PITCH */ - -/* - * Conditionally bind a mob to a guest-backed surface if testMobid - * matches the currently bound mob. Optionally issue a - * readback/update on the surface while it is still bound to the old - * mobid if the mobid is changed by this command. - */ +#pragma pack(push, 1) +typedef struct { + SVGA3dSurfaceImageId image; + uint32 width; + uint32 height; + int32 xRoot; + int32 yRoot; + SVGAScreenTargetFlags flags; + uint32 dpi; + uint32 pad[7]; +} SVGAOTableScreenTargetEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + float value[4]; +} SVGA3dShaderConstFloat; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + int32 value[4]; +} SVGA3dShaderConstInt; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 value; +} SVGA3dShaderConstBool; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint16 streamOffset; + uint8 stream; + uint8 type; + uint8 methodUsage; + uint8 usageIndex; +} SVGAGBVertexElement; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 sid; + uint16 stride; + uint32 offset; +} SVGAGBVertexStream; +#pragma pack(pop) +#pragma pack(push, 1) +typedef struct { + SVGA3dRect viewport; + SVGA3dRect scissorRect; + SVGA3dZRange zRange; + + SVGA3dSurfaceImageId renderTargets[SVGA3D_RT_MAX]; + SVGAGBVertexElement decl1[4]; + + uint32 renderStates[SVGA3D_RS_MAX]; + SVGAGBVertexElement decl2[18]; + uint32 pad0[2]; + + struct { + SVGA3dFace face; + SVGA3dMaterial material; + } material; + + float clipPlanes[SVGA3D_MAX_CLIP_PLANES][4]; + float matrices[SVGA3D_TRANSFORM_MAX][16]; + + SVGA3dBool lightEnabled[SVGA3D_NUM_LIGHTS]; + SVGA3dLightData lightData[SVGA3D_NUM_LIGHTS]; + + uint32 shaders[SVGA3D_NUM_SHADERTYPE_PREDX]; + SVGAGBVertexElement decl3[10]; + uint32 pad1[3]; + + uint32 occQueryActive; + uint32 occQueryValue; + + SVGA3dShaderConstInt pShaderIValues[SVGA3D_CONSTINTREG_MAX]; + SVGA3dShaderConstInt vShaderIValues[SVGA3D_CONSTINTREG_MAX]; + uint16 pShaderBValues; + uint16 vShaderBValues; + + SVGAGBVertexStream streams[SVGA3D_MAX_VERTEX_ARRAYS]; + SVGA3dVertexDivisor divisors[SVGA3D_MAX_VERTEX_ARRAYS]; + uint32 numVertexDecls; + uint32 numVertexStreams; + uint32 numVertexDivisors; + uint32 pad2[30]; + + uint32 tsColorKey[SVGA3D_NUM_TEXTURE_UNITS]; + uint32 textureStages[SVGA3D_NUM_TEXTURE_UNITS][SVGA3D_TS_CONSTANT + 1]; + uint32 tsColorKeyEnable[SVGA3D_NUM_TEXTURE_UNITS]; + + SVGA3dShaderConstFloat pShaderFValues[SVGA3D_CONSTREG_MAX]; + SVGA3dShaderConstFloat vShaderFValues[SVGA3D_CONSTREG_MAX]; +} SVGAGBContextData; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGAOTableType type; + PPN32 baseAddress; + uint32 sizeInBytes; + uint32 validSizeInBytes; + SVGAMobFormat ptDepth; +} SVGA3dCmdSetOTableBase; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGAOTableType type; + PPN64 baseAddress; + uint32 sizeInBytes; + uint32 validSizeInBytes; + SVGAMobFormat ptDepth; +} SVGA3dCmdSetOTableBase64; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGAOTableType type; + PPN64 baseAddress; + uint32 sizeInBytes; + uint32 validSizeInBytes; + SVGAMobFormat ptDepth; +} SVGA3dCmdGrowOTable; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGAOTableType type; +} SVGA3dCmdReadbackOTable; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDefineGBMob { + SVGAMobId mobid; + SVGAMobFormat ptDepth; + PPN32 base; + uint32 sizeInBytes; +} SVGA3dCmdDefineGBMob; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDestroyGBMob { + SVGAMobId mobid; +} SVGA3dCmdDestroyGBMob; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDefineGBMob64 { + SVGAMobId mobid; + SVGAMobFormat ptDepth; + PPN64 base; + uint32 sizeInBytes; +} SVGA3dCmdDefineGBMob64; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdRedefineGBMob64 { + SVGAMobId mobid; + SVGAMobFormat ptDepth; + PPN64 base; + uint32 sizeInBytes; +} SVGA3dCmdRedefineGBMob64; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdUpdateGBMobMapping { + SVGAMobId mobid; +} SVGA3dCmdUpdateGBMobMapping; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDefineGBSurface { + uint32 sid; + SVGA3dSurface1Flags surfaceFlags; + SVGA3dSurfaceFormat format; + uint32 numMipLevels; + uint32 multisampleCount; + SVGA3dTextureFilter autogenFilter; + SVGA3dSize size; +} SVGA3dCmdDefineGBSurface; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDefineGBSurface_v2 { + uint32 sid; + SVGA3dSurface1Flags surfaceFlags; + SVGA3dSurfaceFormat format; + uint32 numMipLevels; + uint32 multisampleCount; + SVGA3dTextureFilter autogenFilter; + SVGA3dSize size; + uint32 arraySize; + uint32 pad; +} SVGA3dCmdDefineGBSurface_v2; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDefineGBSurface_v3 { + uint32 sid; + SVGA3dSurfaceAllFlags surfaceFlags; + SVGA3dSurfaceFormat format; + uint32 numMipLevels; + uint32 multisampleCount; + SVGA3dMSPattern multisamplePattern; + SVGA3dMSQualityLevel qualityLevel; + SVGA3dTextureFilter autogenFilter; + SVGA3dSize size; + uint32 arraySize; +} SVGA3dCmdDefineGBSurface_v3; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDefineGBSurface_v4 { + uint32 sid; + SVGA3dSurfaceAllFlags surfaceFlags; + SVGA3dSurfaceFormat format; + uint32 numMipLevels; + uint32 multisampleCount; + SVGA3dMSPattern multisamplePattern; + SVGA3dMSQualityLevel qualityLevel; + SVGA3dTextureFilter autogenFilter; + SVGA3dSize size; + uint32 arraySize; + uint32 bufferByteStride; +} SVGA3dCmdDefineGBSurface_v4; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDestroyGBSurface { + uint32 sid; +} SVGA3dCmdDestroyGBSurface; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdBindGBSurface { + uint32 sid; + SVGAMobId mobid; +} SVGA3dCmdBindGBSurface; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdBindGBSurfaceWithPitch { + uint32 sid; + SVGAMobId mobid; + uint32 baseLevelPitch; +} SVGA3dCmdBindGBSurfaceWithPitch; +#pragma pack(pop) #define SVGA3D_COND_BIND_GB_SURFACE_FLAG_READBACK (1 << 0) -#define SVGA3D_COND_BIND_GB_SURFACE_FLAG_UPDATE (1 << 1) - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdCondBindGBSurface { - uint32 sid; - SVGAMobId testMobid; - SVGAMobId mobid; - uint32 flags; -} -#include "vmware_pack_end.h" -SVGA3dCmdCondBindGBSurface; /* SVGA_3D_CMD_COND_BIND_GB_SURFACE */ - -/* - * Update an image in a guest-backed surface. - * (Inform the device that the guest-contents have been updated.) - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdUpdateGBImage { - SVGA3dSurfaceImageId image; - SVGA3dBox box; -} -#include "vmware_pack_end.h" -SVGA3dCmdUpdateGBImage; /* SVGA_3D_CMD_UPDATE_GB_IMAGE */ - -/* - * Update an entire guest-backed surface. - * (Inform the device that the guest-contents have been updated.) - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdUpdateGBSurface { - uint32 sid; -} -#include "vmware_pack_end.h" -SVGA3dCmdUpdateGBSurface; /* SVGA_3D_CMD_UPDATE_GB_SURFACE */ - -/* - * Readback an image in a guest-backed surface. - * (Request the device to flush the dirty contents into the guest.) - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdReadbackGBImage { - SVGA3dSurfaceImageId image; -} -#include "vmware_pack_end.h" -SVGA3dCmdReadbackGBImage; /* SVGA_3D_CMD_READBACK_GB_IMAGE */ - -/* - * Readback an entire guest-backed surface. - * (Request the device to flush the dirty contents into the guest.) - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdReadbackGBSurface { - uint32 sid; -} -#include "vmware_pack_end.h" -SVGA3dCmdReadbackGBSurface; /* SVGA_3D_CMD_READBACK_GB_SURFACE */ - -/* - * Readback a sub rect of an image in a guest-backed surface. After - * issuing this command the driver is required to issue an update call - * of the same region before issuing any other commands that reference - * this surface or rendering is not guaranteed. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdReadbackGBImagePartial { - SVGA3dSurfaceImageId image; - SVGA3dBox box; - uint32 invertBox; -} -#include "vmware_pack_end.h" -SVGA3dCmdReadbackGBImagePartial; /* SVGA_3D_CMD_READBACK_GB_IMAGE_PARTIAL */ - - -/* - * Invalidate an image in a guest-backed surface. - * (Notify the device that the contents can be lost.) - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdInvalidateGBImage { - SVGA3dSurfaceImageId image; -} -#include "vmware_pack_end.h" -SVGA3dCmdInvalidateGBImage; /* SVGA_3D_CMD_INVALIDATE_GB_IMAGE */ - -/* - * Invalidate an entire guest-backed surface. - * (Notify the device that the contents if all images can be lost.) - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdInvalidateGBSurface { - uint32 sid; -} -#include "vmware_pack_end.h" -SVGA3dCmdInvalidateGBSurface; /* SVGA_3D_CMD_INVALIDATE_GB_SURFACE */ - -/* - * Invalidate a sub rect of an image in a guest-backed surface. After - * issuing this command the driver is required to issue an update call - * of the same region before issuing any other commands that reference - * this surface or rendering is not guaranteed. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdInvalidateGBImagePartial { - SVGA3dSurfaceImageId image; - SVGA3dBox box; - uint32 invertBox; -} -#include "vmware_pack_end.h" -SVGA3dCmdInvalidateGBImagePartial; /* SVGA_3D_CMD_INVALIDATE_GB_IMAGE_PARTIAL */ - - -/* - * Define a guest-backed context. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDefineGBContext { - uint32 cid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDefineGBContext; /* SVGA_3D_CMD_DEFINE_GB_CONTEXT */ - -/* - * Destroy a guest-backed context. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDestroyGBContext { - uint32 cid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDestroyGBContext; /* SVGA_3D_CMD_DESTROY_GB_CONTEXT */ - -/* - * Bind a guest-backed context. - * - * validContents should be set to 0 for new contexts, - * and 1 if this is an old context which is getting paged - * back on to the device. - * - * For new contexts, it is recommended that the driver - * issue commands to initialize all interesting state - * prior to rendering. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdBindGBContext { - uint32 cid; - SVGAMobId mobid; - uint32 validContents; -} -#include "vmware_pack_end.h" -SVGA3dCmdBindGBContext; /* SVGA_3D_CMD_BIND_GB_CONTEXT */ - -/* - * Readback a guest-backed context. - * (Request that the device flush the contents back into guest memory.) - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdReadbackGBContext { - uint32 cid; -} -#include "vmware_pack_end.h" -SVGA3dCmdReadbackGBContext; /* SVGA_3D_CMD_READBACK_GB_CONTEXT */ - -/* - * Invalidate a guest-backed context. - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdInvalidateGBContext { - uint32 cid; -} -#include "vmware_pack_end.h" -SVGA3dCmdInvalidateGBContext; /* SVGA_3D_CMD_INVALIDATE_GB_CONTEXT */ - -/* - * Define a guest-backed shader. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDefineGBShader { - uint32 shid; - SVGA3dShaderType type; - uint32 sizeInBytes; -} -#include "vmware_pack_end.h" -SVGA3dCmdDefineGBShader; /* SVGA_3D_CMD_DEFINE_GB_SHADER */ - -/* - * Bind a guest-backed shader. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdBindGBShader { - uint32 shid; - SVGAMobId mobid; - uint32 offsetInBytes; -} -#include "vmware_pack_end.h" -SVGA3dCmdBindGBShader; /* SVGA_3D_CMD_BIND_GB_SHADER */ - -/* - * Destroy a guest-backed shader. - */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDestroyGBShader { - uint32 shid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDestroyGBShader; /* SVGA_3D_CMD_DESTROY_GB_SHADER */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - uint32 regStart; - SVGA3dShaderType shaderType; - SVGA3dShaderConstType constType; - - /* - * Followed by a variable number of shader constants. - * - * Note that FLOAT and INT constants are 4-dwords in length, while - * BOOL constants are 1-dword in length. - */ -} -#include "vmware_pack_end.h" -SVGA3dCmdSetGBShaderConstInline; /* SVGA_3D_CMD_SET_GB_SHADERCONSTS_INLINE */ - - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGA3dQueryType type; -} -#include "vmware_pack_end.h" -SVGA3dCmdBeginGBQuery; /* SVGA_3D_CMD_BEGIN_GB_QUERY */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGA3dQueryType type; - SVGAMobId mobid; - uint32 offset; -} -#include "vmware_pack_end.h" -SVGA3dCmdEndGBQuery; /* SVGA_3D_CMD_END_GB_QUERY */ - - -/* - * SVGA_3D_CMD_WAIT_FOR_GB_QUERY -- - * - * The semantics of this command are identical to the - * SVGA_3D_CMD_WAIT_FOR_QUERY except that the results are written - * to a Mob instead of a GMR. - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGA3dQueryType type; - SVGAMobId mobid; - uint32 offset; -} -#include "vmware_pack_end.h" -SVGA3dCmdWaitForGBQuery; /* SVGA_3D_CMD_WAIT_FOR_GB_QUERY */ - - -typedef -#include "vmware_pack_begin.h" -struct { - SVGAMobId mobid; - uint32 mustBeZero; - uint32 initialized; -} -#include "vmware_pack_end.h" -SVGA3dCmdEnableGart; /* SVGA_3D_CMD_ENABLE_GART */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGAMobId mobid; - uint32 gartOffset; -} -#include "vmware_pack_end.h" -SVGA3dCmdMapMobIntoGart; /* SVGA_3D_CMD_MAP_MOB_INTO_GART */ - - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 gartOffset; - uint32 numPages; -} -#include "vmware_pack_end.h" -SVGA3dCmdUnmapGartRange; /* SVGA_3D_CMD_UNMAP_GART_RANGE */ - - -/* - * Screen Targets - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 stid; - uint32 width; - uint32 height; - int32 xRoot; - int32 yRoot; - SVGAScreenTargetFlags flags; - - /* - * The physical DPI that the guest expects this screen displayed at. - * - * Guests which are not DPI-aware should set this to zero. - */ - uint32 dpi; -} -#include "vmware_pack_end.h" -SVGA3dCmdDefineGBScreenTarget; /* SVGA_3D_CMD_DEFINE_GB_SCREENTARGET */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 stid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDestroyGBScreenTarget; /* SVGA_3D_CMD_DESTROY_GB_SCREENTARGET */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 stid; - SVGA3dSurfaceImageId image; -} -#include "vmware_pack_end.h" -SVGA3dCmdBindGBScreenTarget; /* SVGA_3D_CMD_BIND_GB_SCREENTARGET */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 stid; - SVGA3dRect rect; -} -#include "vmware_pack_end.h" -SVGA3dCmdUpdateGBScreenTarget; /* SVGA_3D_CMD_UPDATE_GB_SCREENTARGET */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdGBScreenDMA { - uint32 screenId; - uint32 dead; - SVGAMobId destMobID; - uint32 destPitch; - SVGAMobId changeMapMobID; -} -#include "vmware_pack_end.h" -SVGA3dCmdGBScreenDMA; /* SVGA_3D_CMD_GB_SCREEN_DMA */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 value; - uint32 mobId; - uint32 mobOffset; -} -#include "vmware_pack_end.h" -SVGA3dCmdGBMobFence; /* SVGA_3D_CMD_GB_MOB_FENCE */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 stid; - SVGA3dSurfaceImageId dest; - - uint32 statusMobId; - uint32 statusMobOffset; - - /* Reserved fields */ - uint32 mustBeInvalidId; - uint32 mustBeZero; -} -#include "vmware_pack_end.h" -SVGA3dCmdScreenCopy; /* SVGA_3D_CMD_SCREEN_COPY */ +#define SVGA3D_COND_BIND_GB_SURFACE_FLAG_UPDATE (1 << 1) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdCondBindGBSurface { + uint32 sid; + SVGAMobId testMobid; + SVGAMobId mobid; + uint32 flags; +} SVGA3dCmdCondBindGBSurface; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdUpdateGBImage { + SVGA3dSurfaceImageId image; + SVGA3dBox box; +} SVGA3dCmdUpdateGBImage; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdUpdateGBSurface { + uint32 sid; +} SVGA3dCmdUpdateGBSurface; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdReadbackGBImage { + SVGA3dSurfaceImageId image; +} SVGA3dCmdReadbackGBImage; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdReadbackGBSurface { + uint32 sid; +} SVGA3dCmdReadbackGBSurface; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdReadbackGBImagePartial { + SVGA3dSurfaceImageId image; + SVGA3dBox box; + uint32 invertBox; +} SVGA3dCmdReadbackGBImagePartial; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdInvalidateGBImage { + SVGA3dSurfaceImageId image; +} SVGA3dCmdInvalidateGBImage; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdInvalidateGBSurface { + uint32 sid; +} SVGA3dCmdInvalidateGBSurface; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdInvalidateGBImagePartial { + SVGA3dSurfaceImageId image; + SVGA3dBox box; + uint32 invertBox; +} SVGA3dCmdInvalidateGBImagePartial; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDefineGBContext { + uint32 cid; +} SVGA3dCmdDefineGBContext; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDestroyGBContext { + uint32 cid; +} SVGA3dCmdDestroyGBContext; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdBindGBContext { + uint32 cid; + SVGAMobId mobid; + uint32 validContents; +} SVGA3dCmdBindGBContext; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdReadbackGBContext { + uint32 cid; +} SVGA3dCmdReadbackGBContext; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdInvalidateGBContext { + uint32 cid; +} SVGA3dCmdInvalidateGBContext; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDefineGBShader { + uint32 shid; + SVGA3dShaderType type; + uint32 sizeInBytes; +} SVGA3dCmdDefineGBShader; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdBindGBShader { + uint32 shid; + SVGAMobId mobid; + uint32 offsetInBytes; +} SVGA3dCmdBindGBShader; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDestroyGBShader { + uint32 shid; +} SVGA3dCmdDestroyGBShader; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + uint32 regStart; + SVGA3dShaderType shaderType; + SVGA3dShaderConstType constType; + +} SVGA3dCmdSetGBShaderConstInline; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGA3dQueryType type; +} SVGA3dCmdBeginGBQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGA3dQueryType type; + SVGAMobId mobid; + uint32 offset; +} SVGA3dCmdEndGBQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGA3dQueryType type; + SVGAMobId mobid; + uint32 offset; +} SVGA3dCmdWaitForGBQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGAMobId mobid; + uint32 mustBeZero; + uint32 initialized; +} SVGA3dCmdEnableGart; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGAMobId mobid; + uint32 gartOffset; +} SVGA3dCmdMapMobIntoGart; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 gartOffset; + uint32 numPages; +} SVGA3dCmdUnmapGartRange; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 stid; + uint32 width; + uint32 height; + int32 xRoot; + int32 yRoot; + SVGAScreenTargetFlags flags; + + uint32 dpi; +} SVGA3dCmdDefineGBScreenTarget; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 stid; +} SVGA3dCmdDestroyGBScreenTarget; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 stid; + SVGA3dSurfaceImageId image; +} SVGA3dCmdBindGBScreenTarget; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 stid; + SVGA3dRect rect; +} SVGA3dCmdUpdateGBScreenTarget; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 stid; + SVGA3dRect rect; + SVGA3dFrameUpdateType type; +} SVGA3dCmdUpdateGBScreenTarget_v2; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 stid; + SVGA3dRect rect; + SVGA3dFrameUpdateType type; + SVGAUnsignedPoint srcPoint; +} SVGA3dCmdUpdateGBScreenTargetMove; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdGBScreenDMA { + uint32 screenId; + uint32 dead; + SVGAMobId destMobID; + uint32 destPitch; + SVGAMobId changeMapMobID; +} SVGA3dCmdGBScreenDMA; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 value; + uint32 mobId; + uint32 mobOffset; +} SVGA3dCmdGBMobFence; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 stid; + SVGA3dSurfaceImageId dest; + + uint32 statusMobId; + uint32 statusMobOffset; + + uint32 mustBeInvalidId; + uint32 mustBeZero; +} SVGA3dCmdScreenCopy; +#pragma pack(pop) #define SVGA_SCREEN_COPY_STATUS_FAILURE 0x00 #define SVGA_SCREEN_COPY_STATUS_SUCCESS 0x01 #define SVGA_SCREEN_COPY_STATUS_INVALID 0xFFFFFFFF -typedef -#include "vmware_pack_begin.h" -struct { - uint32 sid; -} -#include "vmware_pack_end.h" -SVGA3dCmdWriteZeroSurface; /* SVGA_3D_CMD_WRITE_ZERO_SURFACE */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 sid; -} -#include "vmware_pack_end.h" -SVGA3dCmdHintZeroSurface; /* SVGA_3D_CMD_HINT_ZERO_SURFACE */ - -#endif /* _SVGA3D_CMD_H_ */ +#pragma pack(push, 1) +typedef struct { + uint32 sid; +} SVGA3dCmdWriteZeroSurface; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 sid; +} SVGA3dCmdUpdateZeroSurface; +#pragma pack(pop) + +#endif diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h index 617b468c626c..379ec15c7758 100644 --- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h +++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h @@ -1,6 +1,6 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT */ /********************************************************** - * Copyright 1998-2019 VMware, Inc. + * Copyright 1998-2021 VMware, Inc. + * SPDX-License-Identifier: GPL-2.0 OR MIT * * Permission is hereby granted, free of charge, to any person * obtaining a copy of this software and associated documentation @@ -27,484 +27,345 @@ /* * svga3d_devcaps.h -- * - * SVGA 3d caps definitions + * SVGA 3d caps definitions */ -#ifndef _SVGA3D_DEVCAPS_H_ -#define _SVGA3D_DEVCAPS_H_ -#define INCLUDE_ALLOW_MODULE -#define INCLUDE_ALLOW_USERLEVEL -#define INCLUDE_ALLOW_VMCORE -#include "includeCheck.h" +#ifndef _SVGA3D_DEVCAPS_H_ +#define _SVGA3D_DEVCAPS_H_ #include "svga3d_types.h" -/* - * 3D Hardware Version - * - * The hardware version is stored in the SVGA_FIFO_3D_HWVERSION fifo - * register. Is set by the host and read by the guest. This lets - * us make new guest drivers which are backwards-compatible with old - * SVGA hardware revisions. It does not let us support old guest - * drivers. Good enough for now. - * - */ - -#define SVGA3D_MAKE_HWVERSION(major, minor) (((major) << 16) | ((minor) & 0xFF)) -#define SVGA3D_MAJOR_HWVERSION(version) ((version) >> 16) -#define SVGA3D_MINOR_HWVERSION(version) ((version) & 0xFF) +#define SVGA3D_MAKE_HWVERSION(major, minor) (((major) << 16) | ((minor)&0xFF)) +#define SVGA3D_MAJOR_HWVERSION(version) ((version) >> 16) +#define SVGA3D_MINOR_HWVERSION(version) ((version)&0xFF) typedef enum { - SVGA3D_HWVERSION_WS5_RC1 = SVGA3D_MAKE_HWVERSION(0, 1), - SVGA3D_HWVERSION_WS5_RC2 = SVGA3D_MAKE_HWVERSION(0, 2), - SVGA3D_HWVERSION_WS51_RC1 = SVGA3D_MAKE_HWVERSION(0, 3), - SVGA3D_HWVERSION_WS6_B1 = SVGA3D_MAKE_HWVERSION(1, 1), - SVGA3D_HWVERSION_FUSION_11 = SVGA3D_MAKE_HWVERSION(1, 4), - SVGA3D_HWVERSION_WS65_B1 = SVGA3D_MAKE_HWVERSION(2, 0), - SVGA3D_HWVERSION_WS8_B1 = SVGA3D_MAKE_HWVERSION(2, 1), - SVGA3D_HWVERSION_CURRENT = SVGA3D_HWVERSION_WS8_B1, + SVGA3D_HWVERSION_WS5_RC1 = SVGA3D_MAKE_HWVERSION(0, 1), + SVGA3D_HWVERSION_WS5_RC2 = SVGA3D_MAKE_HWVERSION(0, 2), + SVGA3D_HWVERSION_WS51_RC1 = SVGA3D_MAKE_HWVERSION(0, 3), + SVGA3D_HWVERSION_WS6_B1 = SVGA3D_MAKE_HWVERSION(1, 1), + SVGA3D_HWVERSION_FUSION_11 = SVGA3D_MAKE_HWVERSION(1, 4), + SVGA3D_HWVERSION_WS65_B1 = SVGA3D_MAKE_HWVERSION(2, 0), + SVGA3D_HWVERSION_WS8_B1 = SVGA3D_MAKE_HWVERSION(2, 1), + SVGA3D_HWVERSION_CURRENT = SVGA3D_HWVERSION_WS8_B1, } SVGA3dHardwareVersion; -/* - * DevCap indexes. - */ - typedef uint32 SVGA3dDevCapIndex; -#define SVGA3D_DEVCAP_INVALID ((uint32)-1) -#define SVGA3D_DEVCAP_3D 0 -#define SVGA3D_DEVCAP_MAX_LIGHTS 1 - -/* - * SVGA3D_DEVCAP_MAX_TEXTURES reflects the maximum number of - * fixed-function texture units available. Each of these units - * work in both FFP and Shader modes, and they support texture - * transforms and texture coordinates. The host may have additional - * texture image units that are only usable with shaders. - */ -#define SVGA3D_DEVCAP_MAX_TEXTURES 2 -#define SVGA3D_DEVCAP_MAX_CLIP_PLANES 3 -#define SVGA3D_DEVCAP_VERTEX_SHADER_VERSION 4 -#define SVGA3D_DEVCAP_VERTEX_SHADER 5 -#define SVGA3D_DEVCAP_FRAGMENT_SHADER_VERSION 6 -#define SVGA3D_DEVCAP_FRAGMENT_SHADER 7 -#define SVGA3D_DEVCAP_MAX_RENDER_TARGETS 8 -#define SVGA3D_DEVCAP_S23E8_TEXTURES 9 -#define SVGA3D_DEVCAP_S10E5_TEXTURES 10 -#define SVGA3D_DEVCAP_MAX_FIXED_VERTEXBLEND 11 -#define SVGA3D_DEVCAP_D16_BUFFER_FORMAT 12 -#define SVGA3D_DEVCAP_D24S8_BUFFER_FORMAT 13 -#define SVGA3D_DEVCAP_D24X8_BUFFER_FORMAT 14 -#define SVGA3D_DEVCAP_QUERY_TYPES 15 -#define SVGA3D_DEVCAP_TEXTURE_GRADIENT_SAMPLING 16 -#define SVGA3D_DEVCAP_MAX_POINT_SIZE 17 -#define SVGA3D_DEVCAP_MAX_SHADER_TEXTURES 18 -#define SVGA3D_DEVCAP_MAX_TEXTURE_WIDTH 19 -#define SVGA3D_DEVCAP_MAX_TEXTURE_HEIGHT 20 -#define SVGA3D_DEVCAP_MAX_VOLUME_EXTENT 21 -#define SVGA3D_DEVCAP_MAX_TEXTURE_REPEAT 22 -#define SVGA3D_DEVCAP_MAX_TEXTURE_ASPECT_RATIO 23 -#define SVGA3D_DEVCAP_MAX_TEXTURE_ANISOTROPY 24 -#define SVGA3D_DEVCAP_MAX_PRIMITIVE_COUNT 25 -#define SVGA3D_DEVCAP_MAX_VERTEX_INDEX 26 -#define SVGA3D_DEVCAP_MAX_VERTEX_SHADER_INSTRUCTIONS 27 -#define SVGA3D_DEVCAP_MAX_FRAGMENT_SHADER_INSTRUCTIONS 28 -#define SVGA3D_DEVCAP_MAX_VERTEX_SHADER_TEMPS 29 -#define SVGA3D_DEVCAP_MAX_FRAGMENT_SHADER_TEMPS 30 -#define SVGA3D_DEVCAP_TEXTURE_OPS 31 -#define SVGA3D_DEVCAP_SURFACEFMT_X8R8G8B8 32 -#define SVGA3D_DEVCAP_SURFACEFMT_A8R8G8B8 33 -#define SVGA3D_DEVCAP_SURFACEFMT_A2R10G10B10 34 -#define SVGA3D_DEVCAP_SURFACEFMT_X1R5G5B5 35 -#define SVGA3D_DEVCAP_SURFACEFMT_A1R5G5B5 36 -#define SVGA3D_DEVCAP_SURFACEFMT_A4R4G4B4 37 -#define SVGA3D_DEVCAP_SURFACEFMT_R5G6B5 38 -#define SVGA3D_DEVCAP_SURFACEFMT_LUMINANCE16 39 -#define SVGA3D_DEVCAP_SURFACEFMT_LUMINANCE8_ALPHA8 40 -#define SVGA3D_DEVCAP_SURFACEFMT_ALPHA8 41 -#define SVGA3D_DEVCAP_SURFACEFMT_LUMINANCE8 42 -#define SVGA3D_DEVCAP_SURFACEFMT_Z_D16 43 -#define SVGA3D_DEVCAP_SURFACEFMT_Z_D24S8 44 -#define SVGA3D_DEVCAP_SURFACEFMT_Z_D24X8 45 -#define SVGA3D_DEVCAP_SURFACEFMT_DXT1 46 -#define SVGA3D_DEVCAP_SURFACEFMT_DXT2 47 -#define SVGA3D_DEVCAP_SURFACEFMT_DXT3 48 -#define SVGA3D_DEVCAP_SURFACEFMT_DXT4 49 -#define SVGA3D_DEVCAP_SURFACEFMT_DXT5 50 -#define SVGA3D_DEVCAP_SURFACEFMT_BUMPX8L8V8U8 51 -#define SVGA3D_DEVCAP_SURFACEFMT_A2W10V10U10 52 -#define SVGA3D_DEVCAP_SURFACEFMT_BUMPU8V8 53 -#define SVGA3D_DEVCAP_SURFACEFMT_Q8W8V8U8 54 -#define SVGA3D_DEVCAP_SURFACEFMT_CxV8U8 55 -#define SVGA3D_DEVCAP_SURFACEFMT_R_S10E5 56 -#define SVGA3D_DEVCAP_SURFACEFMT_R_S23E8 57 -#define SVGA3D_DEVCAP_SURFACEFMT_RG_S10E5 58 -#define SVGA3D_DEVCAP_SURFACEFMT_RG_S23E8 59 -#define SVGA3D_DEVCAP_SURFACEFMT_ARGB_S10E5 60 -#define SVGA3D_DEVCAP_SURFACEFMT_ARGB_S23E8 61 - -/* - * There is a hole in our devcap definitions for - * historical reasons. - * - * Define a constant just for completeness. - */ -#define SVGA3D_DEVCAP_MISSING62 62 - -#define SVGA3D_DEVCAP_MAX_VERTEX_SHADER_TEXTURES 63 - -/* - * Note that MAX_SIMULTANEOUS_RENDER_TARGETS is a maximum count of color - * render targets. This does not include the depth or stencil targets. - */ -#define SVGA3D_DEVCAP_MAX_SIMULTANEOUS_RENDER_TARGETS 64 - -#define SVGA3D_DEVCAP_SURFACEFMT_V16U16 65 -#define SVGA3D_DEVCAP_SURFACEFMT_G16R16 66 -#define SVGA3D_DEVCAP_SURFACEFMT_A16B16G16R16 67 -#define SVGA3D_DEVCAP_SURFACEFMT_UYVY 68 -#define SVGA3D_DEVCAP_SURFACEFMT_YUY2 69 - -/* - * Deprecated. - */ -#define SVGA3D_DEVCAP_DEAD4 70 -#define SVGA3D_DEVCAP_DEAD5 71 -#define SVGA3D_DEVCAP_DEAD7 72 -#define SVGA3D_DEVCAP_DEAD6 73 - -#define SVGA3D_DEVCAP_AUTOGENMIPMAPS 74 -#define SVGA3D_DEVCAP_SURFACEFMT_NV12 75 -#define SVGA3D_DEVCAP_DEAD10 76 - -/* - * This is the maximum number of SVGA context IDs that the guest - * can define using SVGA_3D_CMD_CONTEXT_DEFINE. - */ -#define SVGA3D_DEVCAP_MAX_CONTEXT_IDS 77 - -/* - * This is the maximum number of SVGA surface IDs that the guest - * can define using SVGA_3D_CMD_SURFACE_DEFINE*. - */ -#define SVGA3D_DEVCAP_MAX_SURFACE_IDS 78 - -#define SVGA3D_DEVCAP_SURFACEFMT_Z_DF16 79 -#define SVGA3D_DEVCAP_SURFACEFMT_Z_DF24 80 -#define SVGA3D_DEVCAP_SURFACEFMT_Z_D24S8_INT 81 - -#define SVGA3D_DEVCAP_SURFACEFMT_ATI1 82 -#define SVGA3D_DEVCAP_SURFACEFMT_ATI2 83 - -/* - * Deprecated. - */ -#define SVGA3D_DEVCAP_DEAD1 84 -#define SVGA3D_DEVCAP_DEAD8 85 -#define SVGA3D_DEVCAP_DEAD9 86 - -#define SVGA3D_DEVCAP_LINE_AA 87 /* boolean */ -#define SVGA3D_DEVCAP_LINE_STIPPLE 88 /* boolean */ -#define SVGA3D_DEVCAP_MAX_LINE_WIDTH 89 /* float */ -#define SVGA3D_DEVCAP_MAX_AA_LINE_WIDTH 90 /* float */ - -#define SVGA3D_DEVCAP_SURFACEFMT_YV12 91 - -/* - * Deprecated. - */ -#define SVGA3D_DEVCAP_DEAD3 92 - -/* - * Are TS_CONSTANT, TS_COLOR_KEY, and TS_COLOR_KEY_ENABLE supported? - */ -#define SVGA3D_DEVCAP_TS_COLOR_KEY 93 /* boolean */ - -/* - * Deprecated. - */ -#define SVGA3D_DEVCAP_DEAD2 94 - -/* - * Does the device support DXContexts? - */ -#define SVGA3D_DEVCAP_DXCONTEXT 95 - -/* - * Deprecated. - */ -#define SVGA3D_DEVCAP_DEAD11 96 - -/* - * What is the maximum number of vertex buffers or vertex input registers - * that can be expected to work correctly with a DXContext? - * - * The guest is allowed to set up to SVGA3D_DX_MAX_VERTEXBUFFERS, but - * anything in excess of this cap is not guaranteed to render correctly. - * - * Similarly, the guest can set up to SVGA3D_DX_MAX_VERTEXINPUTREGISTERS - * input registers without the SVGA3D_DEVCAP_SM4_1 cap, or - * SVGA3D_DX_SM41_MAX_VERTEXINPUTREGISTERS with the SVGA3D_DEVCAP_SM4_1, - * but only the registers up to this cap value are guaranteed to render - * correctly. - * - * If guest-drivers are able to expose a lower-limit, it's recommended - * that they clamp to this value. Otherwise, the host will make a - * best-effort on case-by-case basis if guests exceed this. - */ -#define SVGA3D_DEVCAP_DX_MAX_VERTEXBUFFERS 97 - -/* - * What is the maximum number of constant buffers that can be expected to - * work correctly with a DX context? - * - * The guest is allowed to set up to SVGA3D_DX_MAX_CONSTBUFFERS, but - * anything in excess of this cap is not guaranteed to render correctly. - * - * If guest-drivers are able to expose a lower-limit, it's recommended - * that they clamp to this value. Otherwise, the host will make a - * best-effort on case-by-case basis if guests exceed this. - */ -#define SVGA3D_DEVCAP_DX_MAX_CONSTANT_BUFFERS 98 - -/* - * Does the device support provoking vertex control? - * - * If this cap is present, the provokingVertexLast field in the - * rasterizer state is enabled. (Guests can then set it to FALSE, - * meaning that the first vertex is the provoking vertex, or TRUE, - * meaning that the last verteix is the provoking vertex.) - * - * If this cap is FALSE, then guests should set the provokingVertexLast - * to FALSE, otherwise rendering behavior is undefined. - */ -#define SVGA3D_DEVCAP_DX_PROVOKING_VERTEX 99 - -#define SVGA3D_DEVCAP_DXFMT_X8R8G8B8 100 -#define SVGA3D_DEVCAP_DXFMT_A8R8G8B8 101 -#define SVGA3D_DEVCAP_DXFMT_R5G6B5 102 -#define SVGA3D_DEVCAP_DXFMT_X1R5G5B5 103 -#define SVGA3D_DEVCAP_DXFMT_A1R5G5B5 104 -#define SVGA3D_DEVCAP_DXFMT_A4R4G4B4 105 -#define SVGA3D_DEVCAP_DXFMT_Z_D32 106 -#define SVGA3D_DEVCAP_DXFMT_Z_D16 107 -#define SVGA3D_DEVCAP_DXFMT_Z_D24S8 108 -#define SVGA3D_DEVCAP_DXFMT_Z_D15S1 109 -#define SVGA3D_DEVCAP_DXFMT_LUMINANCE8 110 -#define SVGA3D_DEVCAP_DXFMT_LUMINANCE4_ALPHA4 111 -#define SVGA3D_DEVCAP_DXFMT_LUMINANCE16 112 -#define SVGA3D_DEVCAP_DXFMT_LUMINANCE8_ALPHA8 113 -#define SVGA3D_DEVCAP_DXFMT_DXT1 114 -#define SVGA3D_DEVCAP_DXFMT_DXT2 115 -#define SVGA3D_DEVCAP_DXFMT_DXT3 116 -#define SVGA3D_DEVCAP_DXFMT_DXT4 117 -#define SVGA3D_DEVCAP_DXFMT_DXT5 118 -#define SVGA3D_DEVCAP_DXFMT_BUMPU8V8 119 -#define SVGA3D_DEVCAP_DXFMT_BUMPL6V5U5 120 -#define SVGA3D_DEVCAP_DXFMT_BUMPX8L8V8U8 121 -#define SVGA3D_DEVCAP_DXFMT_FORMAT_DEAD1 122 -#define SVGA3D_DEVCAP_DXFMT_ARGB_S10E5 123 -#define SVGA3D_DEVCAP_DXFMT_ARGB_S23E8 124 -#define SVGA3D_DEVCAP_DXFMT_A2R10G10B10 125 -#define SVGA3D_DEVCAP_DXFMT_V8U8 126 -#define SVGA3D_DEVCAP_DXFMT_Q8W8V8U8 127 -#define SVGA3D_DEVCAP_DXFMT_CxV8U8 128 -#define SVGA3D_DEVCAP_DXFMT_X8L8V8U8 129 -#define SVGA3D_DEVCAP_DXFMT_A2W10V10U10 130 -#define SVGA3D_DEVCAP_DXFMT_ALPHA8 131 -#define SVGA3D_DEVCAP_DXFMT_R_S10E5 132 -#define SVGA3D_DEVCAP_DXFMT_R_S23E8 133 -#define SVGA3D_DEVCAP_DXFMT_RG_S10E5 134 -#define SVGA3D_DEVCAP_DXFMT_RG_S23E8 135 -#define SVGA3D_DEVCAP_DXFMT_BUFFER 136 -#define SVGA3D_DEVCAP_DXFMT_Z_D24X8 137 -#define SVGA3D_DEVCAP_DXFMT_V16U16 138 -#define SVGA3D_DEVCAP_DXFMT_G16R16 139 -#define SVGA3D_DEVCAP_DXFMT_A16B16G16R16 140 -#define SVGA3D_DEVCAP_DXFMT_UYVY 141 -#define SVGA3D_DEVCAP_DXFMT_YUY2 142 -#define SVGA3D_DEVCAP_DXFMT_NV12 143 -#define SVGA3D_DEVCAP_DXFMT_FORMAT_DEAD2 144 -#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_TYPELESS 145 -#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_UINT 146 -#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_SINT 147 -#define SVGA3D_DEVCAP_DXFMT_R32G32B32_TYPELESS 148 -#define SVGA3D_DEVCAP_DXFMT_R32G32B32_FLOAT 149 -#define SVGA3D_DEVCAP_DXFMT_R32G32B32_UINT 150 -#define SVGA3D_DEVCAP_DXFMT_R32G32B32_SINT 151 -#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_TYPELESS 152 -#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_UINT 153 -#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_SNORM 154 -#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_SINT 155 -#define SVGA3D_DEVCAP_DXFMT_R32G32_TYPELESS 156 -#define SVGA3D_DEVCAP_DXFMT_R32G32_UINT 157 -#define SVGA3D_DEVCAP_DXFMT_R32G32_SINT 158 -#define SVGA3D_DEVCAP_DXFMT_R32G8X24_TYPELESS 159 -#define SVGA3D_DEVCAP_DXFMT_D32_FLOAT_S8X24_UINT 160 -#define SVGA3D_DEVCAP_DXFMT_R32_FLOAT_X8X24 161 -#define SVGA3D_DEVCAP_DXFMT_X32_G8X24_UINT 162 -#define SVGA3D_DEVCAP_DXFMT_R10G10B10A2_TYPELESS 163 -#define SVGA3D_DEVCAP_DXFMT_R10G10B10A2_UINT 164 -#define SVGA3D_DEVCAP_DXFMT_R11G11B10_FLOAT 165 -#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_TYPELESS 166 -#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_UNORM 167 -#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_UNORM_SRGB 168 -#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_UINT 169 -#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_SINT 170 -#define SVGA3D_DEVCAP_DXFMT_R16G16_TYPELESS 171 -#define SVGA3D_DEVCAP_DXFMT_R16G16_UINT 172 -#define SVGA3D_DEVCAP_DXFMT_R16G16_SINT 173 -#define SVGA3D_DEVCAP_DXFMT_R32_TYPELESS 174 -#define SVGA3D_DEVCAP_DXFMT_D32_FLOAT 175 -#define SVGA3D_DEVCAP_DXFMT_R32_UINT 176 -#define SVGA3D_DEVCAP_DXFMT_R32_SINT 177 -#define SVGA3D_DEVCAP_DXFMT_R24G8_TYPELESS 178 -#define SVGA3D_DEVCAP_DXFMT_D24_UNORM_S8_UINT 179 -#define SVGA3D_DEVCAP_DXFMT_R24_UNORM_X8 180 -#define SVGA3D_DEVCAP_DXFMT_X24_G8_UINT 181 -#define SVGA3D_DEVCAP_DXFMT_R8G8_TYPELESS 182 -#define SVGA3D_DEVCAP_DXFMT_R8G8_UNORM 183 -#define SVGA3D_DEVCAP_DXFMT_R8G8_UINT 184 -#define SVGA3D_DEVCAP_DXFMT_R8G8_SINT 185 -#define SVGA3D_DEVCAP_DXFMT_R16_TYPELESS 186 -#define SVGA3D_DEVCAP_DXFMT_R16_UNORM 187 -#define SVGA3D_DEVCAP_DXFMT_R16_UINT 188 -#define SVGA3D_DEVCAP_DXFMT_R16_SNORM 189 -#define SVGA3D_DEVCAP_DXFMT_R16_SINT 190 -#define SVGA3D_DEVCAP_DXFMT_R8_TYPELESS 191 -#define SVGA3D_DEVCAP_DXFMT_R8_UNORM 192 -#define SVGA3D_DEVCAP_DXFMT_R8_UINT 193 -#define SVGA3D_DEVCAP_DXFMT_R8_SNORM 194 -#define SVGA3D_DEVCAP_DXFMT_R8_SINT 195 -#define SVGA3D_DEVCAP_DXFMT_P8 196 -#define SVGA3D_DEVCAP_DXFMT_R9G9B9E5_SHAREDEXP 197 -#define SVGA3D_DEVCAP_DXFMT_R8G8_B8G8_UNORM 198 -#define SVGA3D_DEVCAP_DXFMT_G8R8_G8B8_UNORM 199 -#define SVGA3D_DEVCAP_DXFMT_BC1_TYPELESS 200 -#define SVGA3D_DEVCAP_DXFMT_BC1_UNORM_SRGB 201 -#define SVGA3D_DEVCAP_DXFMT_BC2_TYPELESS 202 -#define SVGA3D_DEVCAP_DXFMT_BC2_UNORM_SRGB 203 -#define SVGA3D_DEVCAP_DXFMT_BC3_TYPELESS 204 -#define SVGA3D_DEVCAP_DXFMT_BC3_UNORM_SRGB 205 -#define SVGA3D_DEVCAP_DXFMT_BC4_TYPELESS 206 -#define SVGA3D_DEVCAP_DXFMT_ATI1 207 -#define SVGA3D_DEVCAP_DXFMT_BC4_SNORM 208 -#define SVGA3D_DEVCAP_DXFMT_BC5_TYPELESS 209 -#define SVGA3D_DEVCAP_DXFMT_ATI2 210 -#define SVGA3D_DEVCAP_DXFMT_BC5_SNORM 211 -#define SVGA3D_DEVCAP_DXFMT_R10G10B10_XR_BIAS_A2_UNORM 212 -#define SVGA3D_DEVCAP_DXFMT_B8G8R8A8_TYPELESS 213 -#define SVGA3D_DEVCAP_DXFMT_B8G8R8A8_UNORM_SRGB 214 -#define SVGA3D_DEVCAP_DXFMT_B8G8R8X8_TYPELESS 215 -#define SVGA3D_DEVCAP_DXFMT_B8G8R8X8_UNORM_SRGB 216 -#define SVGA3D_DEVCAP_DXFMT_Z_DF16 217 -#define SVGA3D_DEVCAP_DXFMT_Z_DF24 218 -#define SVGA3D_DEVCAP_DXFMT_Z_D24S8_INT 219 -#define SVGA3D_DEVCAP_DXFMT_YV12 220 -#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_FLOAT 221 -#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_FLOAT 222 -#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_UNORM 223 -#define SVGA3D_DEVCAP_DXFMT_R32G32_FLOAT 224 -#define SVGA3D_DEVCAP_DXFMT_R10G10B10A2_UNORM 225 -#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_SNORM 226 -#define SVGA3D_DEVCAP_DXFMT_R16G16_FLOAT 227 -#define SVGA3D_DEVCAP_DXFMT_R16G16_UNORM 228 -#define SVGA3D_DEVCAP_DXFMT_R16G16_SNORM 229 -#define SVGA3D_DEVCAP_DXFMT_R32_FLOAT 230 -#define SVGA3D_DEVCAP_DXFMT_R8G8_SNORM 231 -#define SVGA3D_DEVCAP_DXFMT_R16_FLOAT 232 -#define SVGA3D_DEVCAP_DXFMT_D16_UNORM 233 -#define SVGA3D_DEVCAP_DXFMT_A8_UNORM 234 -#define SVGA3D_DEVCAP_DXFMT_BC1_UNORM 235 -#define SVGA3D_DEVCAP_DXFMT_BC2_UNORM 236 -#define SVGA3D_DEVCAP_DXFMT_BC3_UNORM 237 -#define SVGA3D_DEVCAP_DXFMT_B5G6R5_UNORM 238 -#define SVGA3D_DEVCAP_DXFMT_B5G5R5A1_UNORM 239 -#define SVGA3D_DEVCAP_DXFMT_B8G8R8A8_UNORM 240 -#define SVGA3D_DEVCAP_DXFMT_B8G8R8X8_UNORM 241 -#define SVGA3D_DEVCAP_DXFMT_BC4_UNORM 242 -#define SVGA3D_DEVCAP_DXFMT_BC5_UNORM 243 - -/* - * Advertises shaderModel 4.1 support, independent blend-states, - * cube-map arrays, and a higher vertex input registers limit. - * - * (See documentation on SVGA3D_DEVCAP_DX_MAX_VERTEXBUFFERS.) - */ -#define SVGA3D_DEVCAP_SM41 244 -#define SVGA3D_DEVCAP_MULTISAMPLE_2X 245 -#define SVGA3D_DEVCAP_MULTISAMPLE_4X 246 - -/* - * Indicates that the device has rendering support for - * the full multisample quality. If this cap is not present, - * the host may or may not support full quality rendering. - * - * See also SVGA_REG_MS_HINT_RESOLVED. - */ -#define SVGA3D_DEVCAP_MS_FULL_QUALITY 247 - -/* - * Advertises support for the SVGA3D LogicOps commands. - */ -#define SVGA3D_DEVCAP_LOGICOPS 248 - -/* - * Advertises support for using logicOps in the DXBlendStates. - */ -#define SVGA3D_DEVCAP_LOGIC_BLENDOPS 249 - -/* -* Note DXFMT range is now non-contiguous. -*/ -#define SVGA3D_DEVCAP_RESERVED_1 250 -#define SVGA3D_DEVCAP_DXFMT_BC6H_TYPELESS 251 -#define SVGA3D_DEVCAP_DXFMT_BC6H_UF16 252 -#define SVGA3D_DEVCAP_DXFMT_BC6H_SF16 253 -#define SVGA3D_DEVCAP_DXFMT_BC7_TYPELESS 254 -#define SVGA3D_DEVCAP_DXFMT_BC7_UNORM 255 -#define SVGA3D_DEVCAP_DXFMT_BC7_UNORM_SRGB 256 -#define SVGA3D_DEVCAP_RESERVED_2 257 - -#define SVGA3D_DEVCAP_SM5 258 -#define SVGA3D_DEVCAP_MULTISAMPLE_8X 259 - -/* This must be the last index. */ -#define SVGA3D_DEVCAP_MAX 260 - -/* - * Bit definitions for DXFMT devcaps - * - * - * SUPPORTED: Can the format be defined? - * SHADER_SAMPLE: Can the format be sampled from a shader? - * COLOR_RENDERTARGET: Can the format be a color render target? - * DEPTH_RENDERTARGET: Can the format be a depth render target? - * BLENDABLE: Is the format blendable? - * MIPS: Does the format support mip levels? - * ARRAY: Does the format support texture arrays? - * VOLUME: Does the format support having volume? - * MULTISAMPLE: Does the format support multisample? - */ -#define SVGA3D_DXFMT_SUPPORTED (1 << 0) -#define SVGA3D_DXFMT_SHADER_SAMPLE (1 << 1) -#define SVGA3D_DXFMT_COLOR_RENDERTARGET (1 << 2) -#define SVGA3D_DXFMT_DEPTH_RENDERTARGET (1 << 3) -#define SVGA3D_DXFMT_BLENDABLE (1 << 4) -#define SVGA3D_DXFMT_MIPS (1 << 5) -#define SVGA3D_DXFMT_ARRAY (1 << 6) -#define SVGA3D_DXFMT_VOLUME (1 << 7) -#define SVGA3D_DXFMT_DX_VERTEX_BUFFER (1 << 8) -#define SVGA3D_DXFMT_MULTISAMPLE (1 << 9) -#define SVGA3D_DXFMT_MAX (1 << 10) +#define SVGA3D_DEVCAP_INVALID ((uint32)-1) +#define SVGA3D_DEVCAP_3D 0 +#define SVGA3D_DEVCAP_MAX_LIGHTS 1 + +#define SVGA3D_DEVCAP_MAX_TEXTURES 2 +#define SVGA3D_DEVCAP_MAX_CLIP_PLANES 3 +#define SVGA3D_DEVCAP_VERTEX_SHADER_VERSION 4 +#define SVGA3D_DEVCAP_VERTEX_SHADER 5 +#define SVGA3D_DEVCAP_FRAGMENT_SHADER_VERSION 6 +#define SVGA3D_DEVCAP_FRAGMENT_SHADER 7 +#define SVGA3D_DEVCAP_MAX_RENDER_TARGETS 8 +#define SVGA3D_DEVCAP_S23E8_TEXTURES 9 +#define SVGA3D_DEVCAP_S10E5_TEXTURES 10 +#define SVGA3D_DEVCAP_MAX_FIXED_VERTEXBLEND 11 +#define SVGA3D_DEVCAP_D16_BUFFER_FORMAT 12 +#define SVGA3D_DEVCAP_D24S8_BUFFER_FORMAT 13 +#define SVGA3D_DEVCAP_D24X8_BUFFER_FORMAT 14 +#define SVGA3D_DEVCAP_QUERY_TYPES 15 +#define SVGA3D_DEVCAP_TEXTURE_GRADIENT_SAMPLING 16 +#define SVGA3D_DEVCAP_MAX_POINT_SIZE 17 +#define SVGA3D_DEVCAP_MAX_SHADER_TEXTURES 18 +#define SVGA3D_DEVCAP_MAX_TEXTURE_WIDTH 19 +#define SVGA3D_DEVCAP_MAX_TEXTURE_HEIGHT 20 +#define SVGA3D_DEVCAP_MAX_VOLUME_EXTENT 21 +#define SVGA3D_DEVCAP_MAX_TEXTURE_REPEAT 22 +#define SVGA3D_DEVCAP_MAX_TEXTURE_ASPECT_RATIO 23 +#define SVGA3D_DEVCAP_MAX_TEXTURE_ANISOTROPY 24 +#define SVGA3D_DEVCAP_MAX_PRIMITIVE_COUNT 25 +#define SVGA3D_DEVCAP_MAX_VERTEX_INDEX 26 +#define SVGA3D_DEVCAP_MAX_VERTEX_SHADER_INSTRUCTIONS 27 +#define SVGA3D_DEVCAP_MAX_FRAGMENT_SHADER_INSTRUCTIONS 28 +#define SVGA3D_DEVCAP_MAX_VERTEX_SHADER_TEMPS 29 +#define SVGA3D_DEVCAP_MAX_FRAGMENT_SHADER_TEMPS 30 +#define SVGA3D_DEVCAP_TEXTURE_OPS 31 +#define SVGA3D_DEVCAP_SURFACEFMT_X8R8G8B8 32 +#define SVGA3D_DEVCAP_SURFACEFMT_A8R8G8B8 33 +#define SVGA3D_DEVCAP_SURFACEFMT_A2R10G10B10 34 +#define SVGA3D_DEVCAP_SURFACEFMT_X1R5G5B5 35 +#define SVGA3D_DEVCAP_SURFACEFMT_A1R5G5B5 36 +#define SVGA3D_DEVCAP_SURFACEFMT_A4R4G4B4 37 +#define SVGA3D_DEVCAP_SURFACEFMT_R5G6B5 38 +#define SVGA3D_DEVCAP_SURFACEFMT_LUMINANCE16 39 +#define SVGA3D_DEVCAP_SURFACEFMT_LUMINANCE8_ALPHA8 40 +#define SVGA3D_DEVCAP_SURFACEFMT_ALPHA8 41 +#define SVGA3D_DEVCAP_SURFACEFMT_LUMINANCE8 42 +#define SVGA3D_DEVCAP_SURFACEFMT_Z_D16 43 +#define SVGA3D_DEVCAP_SURFACEFMT_Z_D24S8 44 +#define SVGA3D_DEVCAP_SURFACEFMT_Z_D24X8 45 +#define SVGA3D_DEVCAP_SURFACEFMT_DXT1 46 +#define SVGA3D_DEVCAP_SURFACEFMT_DXT2 47 +#define SVGA3D_DEVCAP_SURFACEFMT_DXT3 48 +#define SVGA3D_DEVCAP_SURFACEFMT_DXT4 49 +#define SVGA3D_DEVCAP_SURFACEFMT_DXT5 50 +#define SVGA3D_DEVCAP_SURFACEFMT_BUMPX8L8V8U8 51 +#define SVGA3D_DEVCAP_SURFACEFMT_A2W10V10U10 52 +#define SVGA3D_DEVCAP_SURFACEFMT_BUMPU8V8 53 +#define SVGA3D_DEVCAP_SURFACEFMT_Q8W8V8U8 54 +#define SVGA3D_DEVCAP_SURFACEFMT_CxV8U8 55 +#define SVGA3D_DEVCAP_SURFACEFMT_R_S10E5 56 +#define SVGA3D_DEVCAP_SURFACEFMT_R_S23E8 57 +#define SVGA3D_DEVCAP_SURFACEFMT_RG_S10E5 58 +#define SVGA3D_DEVCAP_SURFACEFMT_RG_S23E8 59 +#define SVGA3D_DEVCAP_SURFACEFMT_ARGB_S10E5 60 +#define SVGA3D_DEVCAP_SURFACEFMT_ARGB_S23E8 61 + +#define SVGA3D_DEVCAP_MISSING62 62 + +#define SVGA3D_DEVCAP_MAX_VERTEX_SHADER_TEXTURES 63 + +#define SVGA3D_DEVCAP_MAX_SIMULTANEOUS_RENDER_TARGETS 64 + +#define SVGA3D_DEVCAP_SURFACEFMT_V16U16 65 +#define SVGA3D_DEVCAP_SURFACEFMT_G16R16 66 +#define SVGA3D_DEVCAP_SURFACEFMT_A16B16G16R16 67 +#define SVGA3D_DEVCAP_SURFACEFMT_UYVY 68 +#define SVGA3D_DEVCAP_SURFACEFMT_YUY2 69 + +#define SVGA3D_DEVCAP_DEAD4 70 +#define SVGA3D_DEVCAP_DEAD5 71 +#define SVGA3D_DEVCAP_DEAD7 72 +#define SVGA3D_DEVCAP_DEAD6 73 + +#define SVGA3D_DEVCAP_AUTOGENMIPMAPS 74 +#define SVGA3D_DEVCAP_SURFACEFMT_NV12 75 +#define SVGA3D_DEVCAP_DEAD10 76 + +#define SVGA3D_DEVCAP_MAX_CONTEXT_IDS 77 + +#define SVGA3D_DEVCAP_MAX_SURFACE_IDS 78 + +#define SVGA3D_DEVCAP_SURFACEFMT_Z_DF16 79 +#define SVGA3D_DEVCAP_SURFACEFMT_Z_DF24 80 +#define SVGA3D_DEVCAP_SURFACEFMT_Z_D24S8_INT 81 + +#define SVGA3D_DEVCAP_SURFACEFMT_ATI1 82 +#define SVGA3D_DEVCAP_SURFACEFMT_ATI2 83 + +#define SVGA3D_DEVCAP_DEAD1 84 +#define SVGA3D_DEVCAP_DEAD8 85 +#define SVGA3D_DEVCAP_DEAD9 86 + +#define SVGA3D_DEVCAP_LINE_AA 87 +#define SVGA3D_DEVCAP_LINE_STIPPLE 88 +#define SVGA3D_DEVCAP_MAX_LINE_WIDTH 89 +#define SVGA3D_DEVCAP_MAX_AA_LINE_WIDTH 90 + +#define SVGA3D_DEVCAP_SURFACEFMT_YV12 91 + +#define SVGA3D_DEVCAP_DEAD3 92 + +#define SVGA3D_DEVCAP_TS_COLOR_KEY 93 + +#define SVGA3D_DEVCAP_DEAD2 94 + +#define SVGA3D_DEVCAP_DXCONTEXT 95 + +#define SVGA3D_DEVCAP_DEAD11 96 + +#define SVGA3D_DEVCAP_DX_MAX_VERTEXBUFFERS 97 + +#define SVGA3D_DEVCAP_DX_MAX_CONSTANT_BUFFERS 98 + +#define SVGA3D_DEVCAP_DX_PROVOKING_VERTEX 99 + +#define SVGA3D_DEVCAP_DXFMT_X8R8G8B8 100 +#define SVGA3D_DEVCAP_DXFMT_A8R8G8B8 101 +#define SVGA3D_DEVCAP_DXFMT_R5G6B5 102 +#define SVGA3D_DEVCAP_DXFMT_X1R5G5B5 103 +#define SVGA3D_DEVCAP_DXFMT_A1R5G5B5 104 +#define SVGA3D_DEVCAP_DXFMT_A4R4G4B4 105 +#define SVGA3D_DEVCAP_DXFMT_Z_D32 106 +#define SVGA3D_DEVCAP_DXFMT_Z_D16 107 +#define SVGA3D_DEVCAP_DXFMT_Z_D24S8 108 +#define SVGA3D_DEVCAP_DXFMT_Z_D15S1 109 +#define SVGA3D_DEVCAP_DXFMT_LUMINANCE8 110 +#define SVGA3D_DEVCAP_DXFMT_LUMINANCE4_ALPHA4 111 +#define SVGA3D_DEVCAP_DXFMT_LUMINANCE16 112 +#define SVGA3D_DEVCAP_DXFMT_LUMINANCE8_ALPHA8 113 +#define SVGA3D_DEVCAP_DXFMT_DXT1 114 +#define SVGA3D_DEVCAP_DXFMT_DXT2 115 +#define SVGA3D_DEVCAP_DXFMT_DXT3 116 +#define SVGA3D_DEVCAP_DXFMT_DXT4 117 +#define SVGA3D_DEVCAP_DXFMT_DXT5 118 +#define SVGA3D_DEVCAP_DXFMT_BUMPU8V8 119 +#define SVGA3D_DEVCAP_DXFMT_BUMPL6V5U5 120 +#define SVGA3D_DEVCAP_DXFMT_BUMPX8L8V8U8 121 +#define SVGA3D_DEVCAP_DXFMT_FORMAT_DEAD1 122 +#define SVGA3D_DEVCAP_DXFMT_ARGB_S10E5 123 +#define SVGA3D_DEVCAP_DXFMT_ARGB_S23E8 124 +#define SVGA3D_DEVCAP_DXFMT_A2R10G10B10 125 +#define SVGA3D_DEVCAP_DXFMT_V8U8 126 +#define SVGA3D_DEVCAP_DXFMT_Q8W8V8U8 127 +#define SVGA3D_DEVCAP_DXFMT_CxV8U8 128 +#define SVGA3D_DEVCAP_DXFMT_X8L8V8U8 129 +#define SVGA3D_DEVCAP_DXFMT_A2W10V10U10 130 +#define SVGA3D_DEVCAP_DXFMT_ALPHA8 131 +#define SVGA3D_DEVCAP_DXFMT_R_S10E5 132 +#define SVGA3D_DEVCAP_DXFMT_R_S23E8 133 +#define SVGA3D_DEVCAP_DXFMT_RG_S10E5 134 +#define SVGA3D_DEVCAP_DXFMT_RG_S23E8 135 +#define SVGA3D_DEVCAP_DXFMT_BUFFER 136 +#define SVGA3D_DEVCAP_DXFMT_Z_D24X8 137 +#define SVGA3D_DEVCAP_DXFMT_V16U16 138 +#define SVGA3D_DEVCAP_DXFMT_G16R16 139 +#define SVGA3D_DEVCAP_DXFMT_A16B16G16R16 140 +#define SVGA3D_DEVCAP_DXFMT_UYVY 141 +#define SVGA3D_DEVCAP_DXFMT_YUY2 142 +#define SVGA3D_DEVCAP_DXFMT_NV12 143 +#define SVGA3D_DEVCAP_DXFMT_FORMAT_DEAD2 144 +#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_TYPELESS 145 +#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_UINT 146 +#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_SINT 147 +#define SVGA3D_DEVCAP_DXFMT_R32G32B32_TYPELESS 148 +#define SVGA3D_DEVCAP_DXFMT_R32G32B32_FLOAT 149 +#define SVGA3D_DEVCAP_DXFMT_R32G32B32_UINT 150 +#define SVGA3D_DEVCAP_DXFMT_R32G32B32_SINT 151 +#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_TYPELESS 152 +#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_UINT 153 +#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_SNORM 154 +#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_SINT 155 +#define SVGA3D_DEVCAP_DXFMT_R32G32_TYPELESS 156 +#define SVGA3D_DEVCAP_DXFMT_R32G32_UINT 157 +#define SVGA3D_DEVCAP_DXFMT_R32G32_SINT 158 +#define SVGA3D_DEVCAP_DXFMT_R32G8X24_TYPELESS 159 +#define SVGA3D_DEVCAP_DXFMT_D32_FLOAT_S8X24_UINT 160 +#define SVGA3D_DEVCAP_DXFMT_R32_FLOAT_X8X24 161 +#define SVGA3D_DEVCAP_DXFMT_X32_G8X24_UINT 162 +#define SVGA3D_DEVCAP_DXFMT_R10G10B10A2_TYPELESS 163 +#define SVGA3D_DEVCAP_DXFMT_R10G10B10A2_UINT 164 +#define SVGA3D_DEVCAP_DXFMT_R11G11B10_FLOAT 165 +#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_TYPELESS 166 +#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_UNORM 167 +#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_UNORM_SRGB 168 +#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_UINT 169 +#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_SINT 170 +#define SVGA3D_DEVCAP_DXFMT_R16G16_TYPELESS 171 +#define SVGA3D_DEVCAP_DXFMT_R16G16_UINT 172 +#define SVGA3D_DEVCAP_DXFMT_R16G16_SINT 173 +#define SVGA3D_DEVCAP_DXFMT_R32_TYPELESS 174 +#define SVGA3D_DEVCAP_DXFMT_D32_FLOAT 175 +#define SVGA3D_DEVCAP_DXFMT_R32_UINT 176 +#define SVGA3D_DEVCAP_DXFMT_R32_SINT 177 +#define SVGA3D_DEVCAP_DXFMT_R24G8_TYPELESS 178 +#define SVGA3D_DEVCAP_DXFMT_D24_UNORM_S8_UINT 179 +#define SVGA3D_DEVCAP_DXFMT_R24_UNORM_X8 180 +#define SVGA3D_DEVCAP_DXFMT_X24_G8_UINT 181 +#define SVGA3D_DEVCAP_DXFMT_R8G8_TYPELESS 182 +#define SVGA3D_DEVCAP_DXFMT_R8G8_UNORM 183 +#define SVGA3D_DEVCAP_DXFMT_R8G8_UINT 184 +#define SVGA3D_DEVCAP_DXFMT_R8G8_SINT 185 +#define SVGA3D_DEVCAP_DXFMT_R16_TYPELESS 186 +#define SVGA3D_DEVCAP_DXFMT_R16_UNORM 187 +#define SVGA3D_DEVCAP_DXFMT_R16_UINT 188 +#define SVGA3D_DEVCAP_DXFMT_R16_SNORM 189 +#define SVGA3D_DEVCAP_DXFMT_R16_SINT 190 +#define SVGA3D_DEVCAP_DXFMT_R8_TYPELESS 191 +#define SVGA3D_DEVCAP_DXFMT_R8_UNORM 192 +#define SVGA3D_DEVCAP_DXFMT_R8_UINT 193 +#define SVGA3D_DEVCAP_DXFMT_R8_SNORM 194 +#define SVGA3D_DEVCAP_DXFMT_R8_SINT 195 +#define SVGA3D_DEVCAP_DXFMT_P8 196 +#define SVGA3D_DEVCAP_DXFMT_R9G9B9E5_SHAREDEXP 197 +#define SVGA3D_DEVCAP_DXFMT_R8G8_B8G8_UNORM 198 +#define SVGA3D_DEVCAP_DXFMT_G8R8_G8B8_UNORM 199 +#define SVGA3D_DEVCAP_DXFMT_BC1_TYPELESS 200 +#define SVGA3D_DEVCAP_DXFMT_BC1_UNORM_SRGB 201 +#define SVGA3D_DEVCAP_DXFMT_BC2_TYPELESS 202 +#define SVGA3D_DEVCAP_DXFMT_BC2_UNORM_SRGB 203 +#define SVGA3D_DEVCAP_DXFMT_BC3_TYPELESS 204 +#define SVGA3D_DEVCAP_DXFMT_BC3_UNORM_SRGB 205 +#define SVGA3D_DEVCAP_DXFMT_BC4_TYPELESS 206 +#define SVGA3D_DEVCAP_DXFMT_ATI1 207 +#define SVGA3D_DEVCAP_DXFMT_BC4_SNORM 208 +#define SVGA3D_DEVCAP_DXFMT_BC5_TYPELESS 209 +#define SVGA3D_DEVCAP_DXFMT_ATI2 210 +#define SVGA3D_DEVCAP_DXFMT_BC5_SNORM 211 +#define SVGA3D_DEVCAP_DXFMT_R10G10B10_XR_BIAS_A2_UNORM 212 +#define SVGA3D_DEVCAP_DXFMT_B8G8R8A8_TYPELESS 213 +#define SVGA3D_DEVCAP_DXFMT_B8G8R8A8_UNORM_SRGB 214 +#define SVGA3D_DEVCAP_DXFMT_B8G8R8X8_TYPELESS 215 +#define SVGA3D_DEVCAP_DXFMT_B8G8R8X8_UNORM_SRGB 216 +#define SVGA3D_DEVCAP_DXFMT_Z_DF16 217 +#define SVGA3D_DEVCAP_DXFMT_Z_DF24 218 +#define SVGA3D_DEVCAP_DXFMT_Z_D24S8_INT 219 +#define SVGA3D_DEVCAP_DXFMT_YV12 220 +#define SVGA3D_DEVCAP_DXFMT_R32G32B32A32_FLOAT 221 +#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_FLOAT 222 +#define SVGA3D_DEVCAP_DXFMT_R16G16B16A16_UNORM 223 +#define SVGA3D_DEVCAP_DXFMT_R32G32_FLOAT 224 +#define SVGA3D_DEVCAP_DXFMT_R10G10B10A2_UNORM 225 +#define SVGA3D_DEVCAP_DXFMT_R8G8B8A8_SNORM 226 +#define SVGA3D_DEVCAP_DXFMT_R16G16_FLOAT 227 +#define SVGA3D_DEVCAP_DXFMT_R16G16_UNORM 228 +#define SVGA3D_DEVCAP_DXFMT_R16G16_SNORM 229 +#define SVGA3D_DEVCAP_DXFMT_R32_FLOAT 230 +#define SVGA3D_DEVCAP_DXFMT_R8G8_SNORM 231 +#define SVGA3D_DEVCAP_DXFMT_R16_FLOAT 232 +#define SVGA3D_DEVCAP_DXFMT_D16_UNORM 233 +#define SVGA3D_DEVCAP_DXFMT_A8_UNORM 234 +#define SVGA3D_DEVCAP_DXFMT_BC1_UNORM 235 +#define SVGA3D_DEVCAP_DXFMT_BC2_UNORM 236 +#define SVGA3D_DEVCAP_DXFMT_BC3_UNORM 237 +#define SVGA3D_DEVCAP_DXFMT_B5G6R5_UNORM 238 +#define SVGA3D_DEVCAP_DXFMT_B5G5R5A1_UNORM 239 +#define SVGA3D_DEVCAP_DXFMT_B8G8R8A8_UNORM 240 +#define SVGA3D_DEVCAP_DXFMT_B8G8R8X8_UNORM 241 +#define SVGA3D_DEVCAP_DXFMT_BC4_UNORM 242 +#define SVGA3D_DEVCAP_DXFMT_BC5_UNORM 243 + +#define SVGA3D_DEVCAP_SM41 244 +#define SVGA3D_DEVCAP_MULTISAMPLE_2X 245 +#define SVGA3D_DEVCAP_MULTISAMPLE_4X 246 + +#define SVGA3D_DEVCAP_MS_FULL_QUALITY 247 + +#define SVGA3D_DEVCAP_LOGICOPS 248 + +#define SVGA3D_DEVCAP_LOGIC_BLENDOPS 249 + +#define SVGA3D_DEVCAP_DEAD12 250 + +#define SVGA3D_DEVCAP_DXFMT_BC6H_TYPELESS 251 +#define SVGA3D_DEVCAP_DXFMT_BC6H_UF16 252 +#define SVGA3D_DEVCAP_DXFMT_BC6H_SF16 253 +#define SVGA3D_DEVCAP_DXFMT_BC7_TYPELESS 254 +#define SVGA3D_DEVCAP_DXFMT_BC7_UNORM 255 +#define SVGA3D_DEVCAP_DXFMT_BC7_UNORM_SRGB 256 + +#define SVGA3D_DEVCAP_DEAD13 257 + +#define SVGA3D_DEVCAP_SM5 258 +#define SVGA3D_DEVCAP_MULTISAMPLE_8X 259 + +#define SVGA3D_DEVCAP_MAX 262 + +#define SVGA3D_DXFMT_SUPPORTED (1 << 0) +#define SVGA3D_DXFMT_SHADER_SAMPLE (1 << 1) +#define SVGA3D_DXFMT_COLOR_RENDERTARGET (1 << 2) +#define SVGA3D_DXFMT_DEPTH_RENDERTARGET (1 << 3) +#define SVGA3D_DXFMT_BLENDABLE (1 << 4) +#define SVGA3D_DXFMT_MIPS (1 << 5) +#define SVGA3D_DXFMT_ARRAY (1 << 6) +#define SVGA3D_DXFMT_VOLUME (1 << 7) +#define SVGA3D_DXFMT_DX_VERTEX_BUFFER (1 << 8) +#define SVGA3D_DXFMT_MULTISAMPLE (1 << 9) +#define SVGA3D_DXFMT_MAX (1 << 10) typedef union { - SVGA3dBool b; - uint32 u; - int32 i; - float f; + SVGA3dBool b; + uint32 u; + int32 i; + float f; } SVGA3dDevCapResult; -#endif /* _SVGA3D_DEVCAPS_H_ */ +#endif diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h index f703ac2b1768..5af442dad542 100644 --- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h +++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h @@ -1,6 +1,6 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT */ /********************************************************** - * Copyright 2012-2019 VMware, Inc. + * Copyright 2012-2021 VMware, Inc. + * SPDX-License-Identifier: GPL-2.0 OR MIT * * Permission is hereby granted, free of charge, to any person * obtaining a copy of this software and associated documentation @@ -27,88 +27,70 @@ /* * svga3d_dx.h -- * - * SVGA 3d hardware definitions for DX10 support. + * SVGA 3d hardware definitions for DX10 support. */ + + #ifndef _SVGA3D_DX_H_ #define _SVGA3D_DX_H_ -#define INCLUDE_ALLOW_MODULE -#define INCLUDE_ALLOW_USERLEVEL -#define INCLUDE_ALLOW_VMCORE -#include "includeCheck.h" - +#include "svga_reg.h" #include "svga3d_limits.h" +#include "svga3d_types.h" -#define SVGA3D_INPUT_MIN 0 -#define SVGA3D_INPUT_PER_VERTEX_DATA 0 +#define SVGA3D_INPUT_MIN 0 +#define SVGA3D_INPUT_PER_VERTEX_DATA 0 #define SVGA3D_INPUT_PER_INSTANCE_DATA 1 -#define SVGA3D_INPUT_MAX 2 +#define SVGA3D_INPUT_MAX 2 typedef uint32 SVGA3dInputClassification; -#define SVGA3D_RESOURCE_TYPE_MIN 1 -#define SVGA3D_RESOURCE_BUFFER 1 -#define SVGA3D_RESOURCE_TEXTURE1D 2 -#define SVGA3D_RESOURCE_TEXTURE2D 3 -#define SVGA3D_RESOURCE_TEXTURE3D 4 -#define SVGA3D_RESOURCE_TEXTURECUBE 5 -#define SVGA3D_RESOURCE_TYPE_DX10_MAX 6 -#define SVGA3D_RESOURCE_BUFFEREX 6 -#define SVGA3D_RESOURCE_TYPE_MAX 7 -typedef uint32 SVGA3dResourceType; - -#define SVGA3D_COLOR_WRITE_ENABLE_RED (1 << 0) -#define SVGA3D_COLOR_WRITE_ENABLE_GREEN (1 << 1) -#define SVGA3D_COLOR_WRITE_ENABLE_BLUE (1 << 2) -#define SVGA3D_COLOR_WRITE_ENABLE_ALPHA (1 << 3) -#define SVGA3D_COLOR_WRITE_ENABLE_ALL (SVGA3D_COLOR_WRITE_ENABLE_RED | \ - SVGA3D_COLOR_WRITE_ENABLE_GREEN | \ - SVGA3D_COLOR_WRITE_ENABLE_BLUE | \ - SVGA3D_COLOR_WRITE_ENABLE_ALPHA) +#define SVGA3D_COLOR_WRITE_ENABLE_RED (1 << 0) +#define SVGA3D_COLOR_WRITE_ENABLE_GREEN (1 << 1) +#define SVGA3D_COLOR_WRITE_ENABLE_BLUE (1 << 2) +#define SVGA3D_COLOR_WRITE_ENABLE_ALPHA (1 << 3) +#define SVGA3D_COLOR_WRITE_ENABLE_ALL \ + (SVGA3D_COLOR_WRITE_ENABLE_RED | SVGA3D_COLOR_WRITE_ENABLE_GREEN | \ + SVGA3D_COLOR_WRITE_ENABLE_BLUE | SVGA3D_COLOR_WRITE_ENABLE_ALPHA) typedef uint8 SVGA3dColorWriteEnable; -#define SVGA3D_DEPTH_WRITE_MASK_ZERO 0 -#define SVGA3D_DEPTH_WRITE_MASK_ALL 1 +#define SVGA3D_DEPTH_WRITE_MASK_ZERO 0 +#define SVGA3D_DEPTH_WRITE_MASK_ALL 1 typedef uint8 SVGA3dDepthWriteMask; -#define SVGA3D_FILTER_MIP_LINEAR (1 << 0) -#define SVGA3D_FILTER_MAG_LINEAR (1 << 2) -#define SVGA3D_FILTER_MIN_LINEAR (1 << 4) +#define SVGA3D_FILTER_MIP_LINEAR (1 << 0) +#define SVGA3D_FILTER_MAG_LINEAR (1 << 2) +#define SVGA3D_FILTER_MIN_LINEAR (1 << 4) #define SVGA3D_FILTER_ANISOTROPIC (1 << 6) -#define SVGA3D_FILTER_COMPARE (1 << 7) +#define SVGA3D_FILTER_COMPARE (1 << 7) typedef uint32 SVGA3dFilter; #define SVGA3D_CULL_INVALID 0 -#define SVGA3D_CULL_MIN 1 -#define SVGA3D_CULL_NONE 1 -#define SVGA3D_CULL_FRONT 2 -#define SVGA3D_CULL_BACK 3 -#define SVGA3D_CULL_MAX 4 +#define SVGA3D_CULL_MIN 1 +#define SVGA3D_CULL_NONE 1 +#define SVGA3D_CULL_FRONT 2 +#define SVGA3D_CULL_BACK 3 +#define SVGA3D_CULL_MAX 4 typedef uint8 SVGA3dCullMode; -#define SVGA3D_COMPARISON_INVALID 0 -#define SVGA3D_COMPARISON_MIN 1 -#define SVGA3D_COMPARISON_NEVER 1 -#define SVGA3D_COMPARISON_LESS 2 -#define SVGA3D_COMPARISON_EQUAL 3 -#define SVGA3D_COMPARISON_LESS_EQUAL 4 -#define SVGA3D_COMPARISON_GREATER 5 -#define SVGA3D_COMPARISON_NOT_EQUAL 6 -#define SVGA3D_COMPARISON_GREATER_EQUAL 7 -#define SVGA3D_COMPARISON_ALWAYS 8 -#define SVGA3D_COMPARISON_MAX 9 +#define SVGA3D_COMPARISON_INVALID 0 +#define SVGA3D_COMPARISON_MIN 1 +#define SVGA3D_COMPARISON_NEVER 1 +#define SVGA3D_COMPARISON_LESS 2 +#define SVGA3D_COMPARISON_EQUAL 3 +#define SVGA3D_COMPARISON_LESS_EQUAL 4 +#define SVGA3D_COMPARISON_GREATER 5 +#define SVGA3D_COMPARISON_NOT_EQUAL 6 +#define SVGA3D_COMPARISON_GREATER_EQUAL 7 +#define SVGA3D_COMPARISON_ALWAYS 8 +#define SVGA3D_COMPARISON_MAX 9 typedef uint8 SVGA3dComparisonFunc; -/* - * SVGA3D_MULTISAMPLE_RAST_DISABLE disables MSAA for all primitives. - * SVGA3D_MULTISAMPLE_RAST_DISABLE_LINE, which is supported in SM41, - * disables MSAA for lines only. - */ -#define SVGA3D_MULTISAMPLE_RAST_DISABLE 0 -#define SVGA3D_MULTISAMPLE_RAST_ENABLE 1 -#define SVGA3D_MULTISAMPLE_RAST_DX_MAX 1 -#define SVGA3D_MULTISAMPLE_RAST_DISABLE_LINE 2 -#define SVGA3D_MULTISAMPLE_RAST_MAX 2 +#define SVGA3D_MULTISAMPLE_RAST_DISABLE 0 +#define SVGA3D_MULTISAMPLE_RAST_ENABLE 1 +#define SVGA3D_MULTISAMPLE_RAST_DX_MAX 1 +#define SVGA3D_MULTISAMPLE_RAST_DISABLE_LINE 2 +#define SVGA3D_MULTISAMPLE_RAST_MAX 2 typedef uint8 SVGA3dMultisampleRastEnable; #define SVGA3D_DX_MAX_VERTEXBUFFERS 32 @@ -137,1531 +119,1273 @@ typedef uint32 SVGA3dQueryId; typedef uint32 SVGA3dStreamOutputId; typedef union { - struct { - float r; - float g; - float b; - float a; - }; - - float value[4]; -} SVGA3dRGBAFloat; - -typedef union { - struct { - uint32 r; - uint32 g; - uint32 b; - uint32 a; - }; - - uint32 value[4]; + struct { + uint32 r; + uint32 g; + uint32 b; + uint32 a; + }; + + uint32 value[4]; } SVGA3dRGBAUint32; -typedef -#include "vmware_pack_begin.h" -struct { - uint32 cid; - SVGAMobId mobid; -} -#include "vmware_pack_end.h" -SVGAOTableDXContextEntry; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineContext { - uint32 cid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineContext; /* SVGA_3D_CMD_DX_DEFINE_CONTEXT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDestroyContext { - uint32 cid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDestroyContext; /* SVGA_3D_CMD_DX_DESTROY_CONTEXT */ - -/* - * Bind a DX context. - * - * validContents should be set to 0 for new contexts, - * and 1 if this is an old context which is getting paged - * back on to the device. - * - * For new contexts, it is recommended that the driver - * issue commands to initialize all interesting state - * prior to rendering. - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXBindContext { - uint32 cid; - SVGAMobId mobid; - uint32 validContents; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXBindContext; /* SVGA_3D_CMD_DX_BIND_CONTEXT */ - -/* - * Readback a DX context. - * (Request that the device flush the contents back into guest memory.) - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXReadbackContext { - uint32 cid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXReadbackContext; /* SVGA_3D_CMD_DX_READBACK_CONTEXT */ - -/* - * Invalidate a guest-backed context. - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXInvalidateContext { - uint32 cid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXInvalidateContext; /* SVGA_3D_CMD_DX_INVALIDATE_CONTEXT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetSingleConstantBuffer { - uint32 slot; - SVGA3dShaderType type; - SVGA3dSurfaceId sid; - uint32 offsetInBytes; - uint32 sizeInBytes; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetSingleConstantBuffer; -/* SVGA_3D_CMD_DX_SET_SINGLE_CONSTANT_BUFFER */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetShaderResources { - uint32 startView; - SVGA3dShaderType type; - - /* - * Followed by a variable number of SVGA3dShaderResourceViewId's. - */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetShaderResources; /* SVGA_3D_CMD_DX_SET_SHADER_RESOURCES */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetShader { - SVGA3dShaderId shaderId; - SVGA3dShaderType type; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetShader; /* SVGA_3D_CMD_DX_SET_SHADER */ +#pragma pack(push, 1) +typedef struct { + uint32 cid; + SVGAMobId mobid; +} SVGAOTableDXContextEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineContext { + uint32 cid; +} SVGA3dCmdDXDefineContext; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDestroyContext { + uint32 cid; +} SVGA3dCmdDXDestroyContext; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXBindContext { + uint32 cid; + SVGAMobId mobid; + uint32 validContents; +} SVGA3dCmdDXBindContext; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXReadbackContext { + uint32 cid; +} SVGA3dCmdDXReadbackContext; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXInvalidateContext { + uint32 cid; +} SVGA3dCmdDXInvalidateContext; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetSingleConstantBuffer { + uint32 slot; + SVGA3dShaderType type; + SVGA3dSurfaceId sid; + uint32 offsetInBytes; + uint32 sizeInBytes; +} SVGA3dCmdDXSetSingleConstantBuffer; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetShaderResources { + uint32 startView; + SVGA3dShaderType type; + +} SVGA3dCmdDXSetShaderResources; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetShader { + SVGA3dShaderId shaderId; + SVGA3dShaderType type; +} SVGA3dCmdDXSetShader; +#pragma pack(pop) typedef union { - struct { - uint32 cbOffset : 12; - uint32 cbId : 4; - uint32 baseSamp : 4; - uint32 baseTex : 7; - uint32 reserved : 5; - }; - uint32 value; + struct { + uint32 cbOffset : 12; + uint32 cbId : 4; + uint32 baseSamp : 4; + uint32 baseTex : 7; + uint32 reserved : 5; + }; + uint32 value; } SVGA3dIfaceData; -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetShaderIface { - SVGA3dShaderType type; - uint32 numClassInstances; - uint32 index; - uint32 iface; - SVGA3dIfaceData data; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetShaderIface; /* SVGA_3D_CMD_DX_SET_SHADER_IFACE */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXBindShaderIface { - uint32 cid; - SVGAMobId mobid; - uint32 offsetInBytes; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXBindShaderIface; /* SVGA_3D_CMD_DX_BIND_SHADER_IFACE */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetSamplers { - uint32 startSampler; - SVGA3dShaderType type; - - /* - * Followed by a variable number of SVGA3dSamplerId's. - */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetSamplers; /* SVGA_3D_CMD_DX_SET_SAMPLERS */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDraw { - uint32 vertexCount; - uint32 startVertexLocation; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDraw; /* SVGA_3D_CMD_DX_DRAW */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDrawIndexed { - uint32 indexCount; - uint32 startIndexLocation; - int32 baseVertexLocation; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDrawIndexed; /* SVGA_3D_CMD_DX_DRAW_INDEXED */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDrawInstanced { - uint32 vertexCountPerInstance; - uint32 instanceCount; - uint32 startVertexLocation; - uint32 startInstanceLocation; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDrawInstanced; /* SVGA_3D_CMD_DX_DRAW_INSTANCED */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDrawIndexedInstanced { - uint32 indexCountPerInstance; - uint32 instanceCount; - uint32 startIndexLocation; - int32 baseVertexLocation; - uint32 startInstanceLocation; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDrawIndexedInstanced; /* SVGA_3D_CMD_DX_DRAW_INDEXED_INSTANCED */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDrawIndexedInstancedIndirect { - SVGA3dSurfaceId argsBufferSid; - uint32 byteOffsetForArgs; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDrawIndexedInstancedIndirect; -/* SVGA_3D_CMD_DX_DRAW_INDEXED_INSTANCED_INDIRECT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDrawInstancedIndirect { - SVGA3dSurfaceId argsBufferSid; - uint32 byteOffsetForArgs; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDrawInstancedIndirect; -/* SVGA_3D_CMD_DX_DRAW_INSTANCED_INDIRECT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDrawAuto { - uint32 pad0; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDrawAuto; /* SVGA_3D_CMD_DX_DRAW_AUTO */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDispatch { - uint32 threadGroupCountX; - uint32 threadGroupCountY; - uint32 threadGroupCountZ; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDispatch; -/* SVGA_3D_CMD_DX_DISPATCH */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDispatchIndirect { - SVGA3dSurfaceId argsBufferSid; - uint32 byteOffsetForArgs; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDispatchIndirect; -/* SVGA_3D_CMD_DX_DISPATCH_INDIRECT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetInputLayout { - SVGA3dElementLayoutId elementLayoutId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetInputLayout; /* SVGA_3D_CMD_DX_SET_INPUT_LAYOUT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dVertexBuffer { - SVGA3dSurfaceId sid; - uint32 stride; - uint32 offset; -} -#include "vmware_pack_end.h" -SVGA3dVertexBuffer; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetVertexBuffers { - uint32 startBuffer; - /* Followed by a variable number of SVGA3dVertexBuffer's. */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetVertexBuffers; /* SVGA_3D_CMD_DX_SET_VERTEX_BUFFERS */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetIndexBuffer { - SVGA3dSurfaceId sid; - SVGA3dSurfaceFormat format; - uint32 offset; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetIndexBuffer; /* SVGA_3D_CMD_DX_SET_INDEX_BUFFER */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetTopology { - SVGA3dPrimitiveType topology; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetTopology; /* SVGA_3D_CMD_DX_SET_TOPOLOGY */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetRenderTargets { - SVGA3dDepthStencilViewId depthStencilViewId; - /* Followed by a variable number of SVGA3dRenderTargetViewId's. */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetRenderTargets; /* SVGA_3D_CMD_DX_SET_RENDERTARGETS */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetBlendState { - SVGA3dBlendStateId blendId; - float blendFactor[4]; - uint32 sampleMask; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetBlendState; /* SVGA_3D_CMD_DX_SET_BLEND_STATE */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetDepthStencilState { - SVGA3dDepthStencilStateId depthStencilId; - uint32 stencilRef; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetDepthStencilState; /* SVGA_3D_CMD_DX_SET_DEPTHSTENCIL_STATE */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetRasterizerState { - SVGA3dRasterizerStateId rasterizerId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetRasterizerState; /* SVGA_3D_CMD_DX_SET_RASTERIZER_STATE */ +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetShaderIface { + SVGA3dShaderType type; + uint32 numClassInstances; + uint32 index; + uint32 iface; + SVGA3dIfaceData data; +} SVGA3dCmdDXSetShaderIface; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXBindShaderIface { + uint32 cid; + SVGAMobId mobid; + uint32 offsetInBytes; +} SVGA3dCmdDXBindShaderIface; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetSamplers { + uint32 startSampler; + SVGA3dShaderType type; + +} SVGA3dCmdDXSetSamplers; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDraw { + uint32 vertexCount; + uint32 startVertexLocation; +} SVGA3dCmdDXDraw; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDrawIndexed { + uint32 indexCount; + uint32 startIndexLocation; + int32 baseVertexLocation; +} SVGA3dCmdDXDrawIndexed; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDrawInstanced { + uint32 vertexCountPerInstance; + uint32 instanceCount; + uint32 startVertexLocation; + uint32 startInstanceLocation; +} SVGA3dCmdDXDrawInstanced; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDrawIndexedInstanced { + uint32 indexCountPerInstance; + uint32 instanceCount; + uint32 startIndexLocation; + int32 baseVertexLocation; + uint32 startInstanceLocation; +} SVGA3dCmdDXDrawIndexedInstanced; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDrawIndexedInstancedIndirect { + SVGA3dSurfaceId argsBufferSid; + uint32 byteOffsetForArgs; +} SVGA3dCmdDXDrawIndexedInstancedIndirect; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDrawInstancedIndirect { + SVGA3dSurfaceId argsBufferSid; + uint32 byteOffsetForArgs; +} SVGA3dCmdDXDrawInstancedIndirect; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDrawAuto { + uint32 pad0; +} SVGA3dCmdDXDrawAuto; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDispatch { + uint32 threadGroupCountX; + uint32 threadGroupCountY; + uint32 threadGroupCountZ; +} SVGA3dCmdDXDispatch; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDispatchIndirect { + SVGA3dSurfaceId argsBufferSid; + uint32 byteOffsetForArgs; +} SVGA3dCmdDXDispatchIndirect; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetInputLayout { + SVGA3dElementLayoutId elementLayoutId; +} SVGA3dCmdDXSetInputLayout; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dVertexBuffer { + SVGA3dSurfaceId sid; + uint32 stride; + uint32 offset; +} SVGA3dVertexBuffer; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetVertexBuffers { + uint32 startBuffer; + +} SVGA3dCmdDXSetVertexBuffers; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dVertexBuffer_v2 { + SVGA3dSurfaceId sid; + uint32 stride; + uint32 offset; + uint32 sizeInBytes; +} SVGA3dVertexBuffer_v2; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetVertexBuffers_v2 { + uint32 startBuffer; + +} SVGA3dCmdDXSetVertexBuffers_v2; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dVertexBufferOffsetAndSize { + uint32 stride; + uint32 offset; + uint32 sizeInBytes; +} SVGA3dVertexBufferOffsetAndSize; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetVertexBuffersOffsetAndSize { + uint32 startBuffer; + +} SVGA3dCmdDXSetVertexBuffersOffsetAndSize; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetIndexBuffer { + SVGA3dSurfaceId sid; + SVGA3dSurfaceFormat format; + uint32 offset; +} SVGA3dCmdDXSetIndexBuffer; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetIndexBuffer_v2 { + SVGA3dSurfaceId sid; + SVGA3dSurfaceFormat format; + uint32 offset; + uint32 sizeInBytes; +} SVGA3dCmdDXSetIndexBuffer_v2; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetIndexBufferOffsetAndSize { + SVGA3dSurfaceFormat format; + uint32 offset; + uint32 sizeInBytes; +} SVGA3dCmdDXSetIndexBufferOffsetAndSize; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetTopology { + SVGA3dPrimitiveType topology; +} SVGA3dCmdDXSetTopology; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetRenderTargets { + SVGA3dDepthStencilViewId depthStencilViewId; + +} SVGA3dCmdDXSetRenderTargets; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetBlendState { + SVGA3dBlendStateId blendId; + float blendFactor[4]; + uint32 sampleMask; +} SVGA3dCmdDXSetBlendState; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetDepthStencilState { + SVGA3dDepthStencilStateId depthStencilId; + uint32 stencilRef; +} SVGA3dCmdDXSetDepthStencilState; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetRasterizerState { + SVGA3dRasterizerStateId rasterizerId; +} SVGA3dCmdDXSetRasterizerState; +#pragma pack(pop) #define SVGA3D_DXQUERY_FLAG_PREDICATEHINT (1 << 0) typedef uint32 SVGA3dDXQueryFlags; -/* - * The SVGADXQueryDeviceState and SVGADXQueryDeviceBits are used by the device - * to track query state transitions, but are not intended to be used by the - * driver. - */ -#define SVGADX_QDSTATE_INVALID ((uint8)-1) /* Query has no state */ -#define SVGADX_QDSTATE_MIN 0 -#define SVGADX_QDSTATE_IDLE 0 /* Query hasn't started yet */ -#define SVGADX_QDSTATE_ACTIVE 1 /* Query is actively gathering data */ -#define SVGADX_QDSTATE_PENDING 2 /* Query is waiting for results */ -#define SVGADX_QDSTATE_FINISHED 3 /* Query has completed */ -#define SVGADX_QDSTATE_MAX 4 +#define SVGADX_QDSTATE_INVALID ((uint8)-1) +#define SVGADX_QDSTATE_MIN 0 +#define SVGADX_QDSTATE_IDLE 0 +#define SVGADX_QDSTATE_ACTIVE 1 +#define SVGADX_QDSTATE_PENDING 2 +#define SVGADX_QDSTATE_FINISHED 3 +#define SVGADX_QDSTATE_MAX 4 typedef uint8 SVGADXQueryDeviceState; -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dQueryTypeUint8 type; - uint16 pad0; - SVGADXQueryDeviceState state; - SVGA3dDXQueryFlags flags; - SVGAMobId mobid; - uint32 offset; -} -#include "vmware_pack_end.h" -SVGACOTableDXQueryEntry; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineQuery { - SVGA3dQueryId queryId; - SVGA3dQueryType type; - SVGA3dDXQueryFlags flags; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineQuery; /* SVGA_3D_CMD_DX_DEFINE_QUERY */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDestroyQuery { - SVGA3dQueryId queryId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDestroyQuery; /* SVGA_3D_CMD_DX_DESTROY_QUERY */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXBindQuery { - SVGA3dQueryId queryId; - SVGAMobId mobid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXBindQuery; /* SVGA_3D_CMD_DX_BIND_QUERY */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetQueryOffset { - SVGA3dQueryId queryId; - uint32 mobOffset; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetQueryOffset; /* SVGA_3D_CMD_DX_SET_QUERY_OFFSET */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXBeginQuery { - SVGA3dQueryId queryId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXBeginQuery; /* SVGA_3D_CMD_DX_QUERY_BEGIN */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXEndQuery { - SVGA3dQueryId queryId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXEndQuery; /* SVGA_3D_CMD_DX_QUERY_END */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXReadbackQuery { - SVGA3dQueryId queryId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXReadbackQuery; /* SVGA_3D_CMD_DX_READBACK_QUERY */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXMoveQuery { - SVGA3dQueryId queryId; - SVGAMobId mobid; - uint32 mobOffset; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXMoveQuery; /* SVGA_3D_CMD_DX_MOVE_QUERY */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXBindAllQuery { - uint32 cid; - SVGAMobId mobid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXBindAllQuery; /* SVGA_3D_CMD_DX_BIND_ALL_QUERY */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXReadbackAllQuery { - uint32 cid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXReadbackAllQuery; /* SVGA_3D_CMD_DX_READBACK_ALL_QUERY */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetPredication { - SVGA3dQueryId queryId; - uint32 predicateValue; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetPredication; /* SVGA_3D_CMD_DX_SET_PREDICATION */ - -typedef -#include "vmware_pack_begin.h" -struct MKS3dDXSOState { - uint32 offset; /* Starting offset */ - uint32 intOffset; /* Internal offset */ - uint32 vertexCount; /* vertices written */ - uint32 dead; -} -#include "vmware_pack_end.h" -SVGA3dDXSOState; - -/* Set the offset field to this value to append SO values to the buffer */ -#define SVGA3D_DX_SO_OFFSET_APPEND ((uint32) ~0u) - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dSoTarget { - SVGA3dSurfaceId sid; - uint32 offset; - uint32 sizeInBytes; -} -#include "vmware_pack_end.h" -SVGA3dSoTarget; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetSOTargets { - uint32 pad0; - /* Followed by a variable number of SVGA3dSOTarget's. */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetSOTargets; /* SVGA_3D_CMD_DX_SET_SOTARGETS */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dViewport -{ - float x; - float y; - float width; - float height; - float minDepth; - float maxDepth; -} -#include "vmware_pack_end.h" -SVGA3dViewport; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetViewports { - uint32 pad0; - /* Followed by a variable number of SVGA3dViewport's. */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetViewports; /* SVGA_3D_CMD_DX_SET_VIEWPORTS */ - -#define SVGA3D_DX_MAX_VIEWPORTS 16 - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetScissorRects { - uint32 pad0; - /* Followed by a variable number of SVGASignedRect's. */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetScissorRects; /* SVGA_3D_CMD_DX_SET_SCISSORRECTS */ - -#define SVGA3D_DX_MAX_SCISSORRECTS 16 - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXClearRenderTargetView { - SVGA3dRenderTargetViewId renderTargetViewId; - SVGA3dRGBAFloat rgba; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXClearRenderTargetView; /* SVGA_3D_CMD_DX_CLEAR_RENDERTARGET_VIEW */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXClearDepthStencilView { - uint16 flags; - uint16 stencil; - SVGA3dDepthStencilViewId depthStencilViewId; - float depth; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXClearDepthStencilView; /* SVGA_3D_CMD_DX_CLEAR_DEPTHSTENCIL_VIEW */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXPredCopyRegion { - SVGA3dSurfaceId dstSid; - uint32 dstSubResource; - SVGA3dSurfaceId srcSid; - uint32 srcSubResource; - SVGA3dCopyBox box; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXPredCopyRegion; -/* SVGA_3D_CMD_DX_PRED_COPY_REGION */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXPredCopy { - SVGA3dSurfaceId dstSid; - SVGA3dSurfaceId srcSid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXPredCopy; /* SVGA_3D_CMD_DX_PRED_COPY */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXPredConvertRegion { - SVGA3dSurfaceId dstSid; - uint32 dstSubResource; - SVGA3dBox destBox; - SVGA3dSurfaceId srcSid; - uint32 srcSubResource; - SVGA3dBox srcBox; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXPredConvertRegion; /* SVGA_3D_CMD_DX_PRED_CONVERT_REGION */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXPredConvert { - SVGA3dSurfaceId dstSid; - SVGA3dSurfaceId srcSid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXPredConvert; /* SVGA_3D_CMD_DX_PRED_CONVERT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXBufferCopy { - SVGA3dSurfaceId dest; - SVGA3dSurfaceId src; - uint32 destX; - uint32 srcX; - uint32 width; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXBufferCopy; -/* SVGA_3D_CMD_DX_BUFFER_COPY */ - -/* - * Perform a surface copy between a multisample, and a non-multisampled - * surface. - */ -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dSurfaceId dstSid; - uint32 dstSubResource; - SVGA3dSurfaceId srcSid; - uint32 srcSubResource; - SVGA3dSurfaceFormat copyFormat; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXResolveCopy; /* SVGA_3D_CMD_DX_RESOLVE_COPY */ - -/* - * Perform a predicated surface copy between a multisample, and a - * non-multisampled surface. - */ -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dSurfaceId dstSid; - uint32 dstSubResource; - SVGA3dSurfaceId srcSid; - uint32 srcSubResource; - SVGA3dSurfaceFormat copyFormat; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXPredResolveCopy; /* SVGA_3D_CMD_DX_PRED_RESOLVE_COPY */ +#pragma pack(push, 1) +typedef struct { + SVGA3dQueryTypeUint8 type; + uint16 pad0; + SVGADXQueryDeviceState state; + SVGA3dDXQueryFlags flags; + SVGAMobId mobid; + uint32 offset; +} SVGACOTableDXQueryEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineQuery { + SVGA3dQueryId queryId; + SVGA3dQueryType type; + SVGA3dDXQueryFlags flags; +} SVGA3dCmdDXDefineQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDestroyQuery { + SVGA3dQueryId queryId; +} SVGA3dCmdDXDestroyQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXBindQuery { + SVGA3dQueryId queryId; + SVGAMobId mobid; +} SVGA3dCmdDXBindQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetQueryOffset { + SVGA3dQueryId queryId; + uint32 mobOffset; +} SVGA3dCmdDXSetQueryOffset; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXBeginQuery { + SVGA3dQueryId queryId; +} SVGA3dCmdDXBeginQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXEndQuery { + SVGA3dQueryId queryId; +} SVGA3dCmdDXEndQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXReadbackQuery { + SVGA3dQueryId queryId; +} SVGA3dCmdDXReadbackQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXMoveQuery { + SVGA3dQueryId queryId; + SVGAMobId mobid; + uint32 mobOffset; +} SVGA3dCmdDXMoveQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXBindAllQuery { + uint32 cid; + SVGAMobId mobid; +} SVGA3dCmdDXBindAllQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXReadbackAllQuery { + uint32 cid; +} SVGA3dCmdDXReadbackAllQuery; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetPredication { + SVGA3dQueryId queryId; + uint32 predicateValue; +} SVGA3dCmdDXSetPredication; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct MKS3dDXSOState { + uint32 offset; + uint32 intOffset; + uint32 vertexCount; + uint32 dead; +} SVGA3dDXSOState; +#pragma pack(pop) + +#define SVGA3D_DX_SO_OFFSET_APPEND ((uint32)~0u) + +#pragma pack(push, 1) +typedef struct SVGA3dSoTarget { + SVGA3dSurfaceId sid; + uint32 offset; + uint32 sizeInBytes; +} SVGA3dSoTarget; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetSOTargets { + uint32 pad0; + +} SVGA3dCmdDXSetSOTargets; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dViewport { + float x; + float y; + float width; + float height; + float minDepth; + float maxDepth; +} SVGA3dViewport; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetViewports { + uint32 pad0; + +} SVGA3dCmdDXSetViewports; +#pragma pack(pop) + +#define SVGA3D_DX_MAX_VIEWPORTS 16 + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetScissorRects { + uint32 pad0; + +} SVGA3dCmdDXSetScissorRects; +#pragma pack(pop) + +#define SVGA3D_DX_MAX_SCISSORRECTS 16 + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXClearRenderTargetView { + SVGA3dRenderTargetViewId renderTargetViewId; + SVGA3dRGBAFloat rgba; +} SVGA3dCmdDXClearRenderTargetView; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXClearDepthStencilView { + uint16 flags; + uint16 stencil; + SVGA3dDepthStencilViewId depthStencilViewId; + float depth; +} SVGA3dCmdDXClearDepthStencilView; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXPredCopyRegion { + SVGA3dSurfaceId dstSid; + uint32 dstSubResource; + SVGA3dSurfaceId srcSid; + uint32 srcSubResource; + SVGA3dCopyBox box; +} SVGA3dCmdDXPredCopyRegion; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXPredStagingCopyRegion { + SVGA3dSurfaceId dstSid; + uint32 dstSubResource; + SVGA3dSurfaceId srcSid; + uint32 srcSubResource; + SVGA3dCopyBox box; + uint8 readback; + uint8 unsynchronized; + uint8 mustBeZero[2]; +} SVGA3dCmdDXPredStagingCopyRegion; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXPredCopy { + SVGA3dSurfaceId dstSid; + SVGA3dSurfaceId srcSid; +} SVGA3dCmdDXPredCopy; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXPredConvertRegion { + SVGA3dSurfaceId dstSid; + uint32 dstSubResource; + SVGA3dBox destBox; + SVGA3dSurfaceId srcSid; + uint32 srcSubResource; + SVGA3dBox srcBox; +} SVGA3dCmdDXPredConvertRegion; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXPredStagingConvertRegion { + SVGA3dSurfaceId dstSid; + uint32 dstSubResource; + SVGA3dBox destBox; + SVGA3dSurfaceId srcSid; + uint32 srcSubResource; + SVGA3dBox srcBox; + uint8 readback; + uint8 unsynchronized; + uint8 mustBeZero[2]; +} SVGA3dCmdDXPredStagingConvertRegion; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXPredConvert { + SVGA3dSurfaceId dstSid; + SVGA3dSurfaceId srcSid; +} SVGA3dCmdDXPredConvert; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXPredStagingConvert { + SVGA3dSurfaceId dstSid; + SVGA3dSurfaceId srcSid; + uint8 readback; + uint8 unsynchronized; + uint8 mustBeZero[2]; +} SVGA3dCmdDXPredStagingConvert; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXBufferCopy { + SVGA3dSurfaceId dest; + SVGA3dSurfaceId src; + uint32 destX; + uint32 srcX; + uint32 width; +} SVGA3dCmdDXBufferCopy; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXStagingBufferCopy { + SVGA3dSurfaceId dest; + SVGA3dSurfaceId src; + uint32 destX; + uint32 srcX; + uint32 width; + uint8 readback; + uint8 unsynchronized; + uint8 mustBeZero[2]; +} SVGA3dCmdDXStagingBufferCopy; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dSurfaceId dstSid; + uint32 dstSubResource; + SVGA3dSurfaceId srcSid; + uint32 srcSubResource; + SVGA3dSurfaceFormat copyFormat; +} SVGA3dCmdDXResolveCopy; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dSurfaceId dstSid; + uint32 dstSubResource; + SVGA3dSurfaceId srcSid; + uint32 srcSubResource; + SVGA3dSurfaceFormat copyFormat; +} SVGA3dCmdDXPredResolveCopy; +#pragma pack(pop) typedef uint32 SVGA3dDXPresentBltMode; -#define SVGADX_PRESENTBLT_LINEAR (1 << 0) -#define SVGADX_PRESENTBLT_FORCE_SRC_SRGB (1 << 1) +#define SVGADX_PRESENTBLT_LINEAR (1 << 0) +#define SVGADX_PRESENTBLT_FORCE_SRC_SRGB (1 << 1) #define SVGADX_PRESENTBLT_FORCE_SRC_XRBIAS (1 << 2) -#define SVGADX_PRESENTBLT_MODE_MAX (1 << 3) - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXPresentBlt { - SVGA3dSurfaceId srcSid; - uint32 srcSubResource; - SVGA3dSurfaceId dstSid; - uint32 destSubResource; - SVGA3dBox boxSrc; - SVGA3dBox boxDest; - SVGA3dDXPresentBltMode mode; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXPresentBlt; /* SVGA_3D_CMD_DX_PRESENTBLT*/ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXGenMips { - SVGA3dShaderResourceViewId shaderResourceViewId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXGenMips; /* SVGA_3D_CMD_DX_GENMIPS */ - -/* - * Update a sub-resource in a guest-backed resource. - * (Inform the device that the guest-contents have been updated.) - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXUpdateSubResource { - SVGA3dSurfaceId sid; - uint32 subResource; - SVGA3dBox box; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXUpdateSubResource; /* SVGA_3D_CMD_DX_UPDATE_SUBRESOURCE */ - -/* - * Readback a subresource in a guest-backed resource. - * (Request the device to flush the dirty contents into the guest.) - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXReadbackSubResource { - SVGA3dSurfaceId sid; - uint32 subResource; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXReadbackSubResource; /* SVGA_3D_CMD_DX_READBACK_SUBRESOURCE */ - -/* - * Invalidate an image in a guest-backed surface. - * (Notify the device that the contents can be lost.) - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXInvalidateSubResource { - SVGA3dSurfaceId sid; - uint32 subResource; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXInvalidateSubResource; /* SVGA_3D_CMD_DX_INVALIDATE_SUBRESOURCE */ - - -/* - * Raw byte wise transfer from a buffer surface into another surface - * of the requested box. Supported if 3d is enabled and SVGA_CAP_DX - * is set. This command does not take a context. - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXTransferFromBuffer { - SVGA3dSurfaceId srcSid; - uint32 srcOffset; - uint32 srcPitch; - uint32 srcSlicePitch; - SVGA3dSurfaceId destSid; - uint32 destSubResource; - SVGA3dBox destBox; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXTransferFromBuffer; /* SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER */ - - -#define SVGA3D_TRANSFER_TO_BUFFER_READBACK (1 << 0) +#define SVGADX_PRESENTBLT_MODE_MAX (1 << 3) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXPresentBlt { + SVGA3dSurfaceId srcSid; + uint32 srcSubResource; + SVGA3dSurfaceId dstSid; + uint32 destSubResource; + SVGA3dBox boxSrc; + SVGA3dBox boxDest; + SVGA3dDXPresentBltMode mode; +} SVGA3dCmdDXPresentBlt; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXGenMips { + SVGA3dShaderResourceViewId shaderResourceViewId; +} SVGA3dCmdDXGenMips; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXUpdateSubResource { + SVGA3dSurfaceId sid; + uint32 subResource; + SVGA3dBox box; +} SVGA3dCmdDXUpdateSubResource; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXReadbackSubResource { + SVGA3dSurfaceId sid; + uint32 subResource; +} SVGA3dCmdDXReadbackSubResource; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXInvalidateSubResource { + SVGA3dSurfaceId sid; + uint32 subResource; +} SVGA3dCmdDXInvalidateSubResource; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXTransferFromBuffer { + SVGA3dSurfaceId srcSid; + uint32 srcOffset; + uint32 srcPitch; + uint32 srcSlicePitch; + SVGA3dSurfaceId destSid; + uint32 destSubResource; + SVGA3dBox destBox; +} SVGA3dCmdDXTransferFromBuffer; +#pragma pack(pop) + +#define SVGA3D_TRANSFER_TO_BUFFER_READBACK (1 << 0) #define SVGA3D_TRANSFER_TO_BUFFER_FLAGS_MASK (1 << 0) typedef uint32 SVGA3dTransferToBufferFlags; -/* - * Raw byte wise transfer to a buffer surface from another surface - * of the requested box. Supported if SVGA_CAP_DX2 is set. This - * command does not take a context. - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXTransferToBuffer { - SVGA3dSurfaceId srcSid; - uint32 srcSubResource; - SVGA3dBox srcBox; - SVGA3dSurfaceId destSid; - uint32 destOffset; - uint32 destPitch; - uint32 destSlicePitch; - SVGA3dTransferToBufferFlags flags; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXTransferToBuffer; /* SVGA_3D_CMD_DX_TRANSFER_TO_BUFFER */ - +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXTransferToBuffer { + SVGA3dSurfaceId srcSid; + uint32 srcSubResource; + SVGA3dBox srcBox; + SVGA3dSurfaceId destSid; + uint32 destOffset; + uint32 destPitch; + uint32 destSlicePitch; + SVGA3dTransferToBufferFlags flags; +} SVGA3dCmdDXTransferToBuffer; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXPredTransferFromBuffer { + SVGA3dSurfaceId srcSid; + uint32 srcOffset; + uint32 srcPitch; + uint32 srcSlicePitch; + SVGA3dSurfaceId destSid; + uint32 destSubResource; + SVGA3dBox destBox; +} SVGA3dCmdDXPredTransferFromBuffer; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSurfaceCopyAndReadback { + SVGA3dSurfaceId srcSid; + SVGA3dSurfaceId destSid; + SVGA3dCopyBox box; +} SVGA3dCmdDXSurfaceCopyAndReadback; +#pragma pack(pop) -/* - * Raw byte wise transfer from a buffer surface into another surface - * of the requested box. Supported if SVGA3D_DEVCAP_DXCONTEXT is set. - * The context is implied from the command buffer header. - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXPredTransferFromBuffer { - SVGA3dSurfaceId srcSid; - uint32 srcOffset; - uint32 srcPitch; - uint32 srcSlicePitch; - SVGA3dSurfaceId destSid; - uint32 destSubResource; - SVGA3dBox destBox; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXPredTransferFromBuffer; -/* SVGA_3D_CMD_DX_PRED_TRANSFER_FROM_BUFFER */ - - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSurfaceCopyAndReadback { - SVGA3dSurfaceId srcSid; - SVGA3dSurfaceId destSid; - SVGA3dCopyBox box; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSurfaceCopyAndReadback; -/* SVGA_3D_CMD_DX_SURFACE_COPY_AND_READBACK */ - -/* - * SVGA_DX_HINT_NONE: Does nothing. - * - * SVGA_DX_HINT_PREFETCH_OBJECT: - * SVGA_DX_HINT_PREEVICT_OBJECT: - * Consumes a SVGAObjectRef, and hints that the host should consider - * fetching/evicting the specified object. - * - * An id of SVGA3D_INVALID_ID can be used if the guest isn't sure - * what object was affected. (For instance, if the guest knows that - * it is about to evict a DXShader, but doesn't know precisely which one, - * the device can still use this to help limit it's search, or track - * how many page-outs have happened.) - * - * SVGA_DX_HINT_PREFETCH_COBJECT: - * SVGA_DX_HINT_PREEVICT_COBJECT: - * Same as the above, except they consume an SVGACObjectRef. - */ typedef uint32 SVGADXHintId; -#define SVGA_DX_HINT_NONE 0 -#define SVGA_DX_HINT_PREFETCH_OBJECT 1 -#define SVGA_DX_HINT_PREEVICT_OBJECT 2 -#define SVGA_DX_HINT_PREFETCH_COBJECT 3 -#define SVGA_DX_HINT_PREEVICT_COBJECT 4 -#define SVGA_DX_HINT_MAX 5 - -typedef -#include "vmware_pack_begin.h" -struct SVGAObjectRef { - SVGAOTableType type; - uint32 id; -} -#include "vmware_pack_end.h" -SVGAObjectRef; - -typedef -#include "vmware_pack_begin.h" -struct SVGACObjectRef { - SVGACOTableType type; - uint32 cid; - uint32 id; -} -#include "vmware_pack_end.h" -SVGACObjectRef; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXHint { - SVGADXHintId hintId; - - /* - * Followed by variable sized data depending on the hintId. - */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDXHint; -/* SVGA_3D_CMD_DX_HINT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXBufferUpdate { - SVGA3dSurfaceId sid; - uint32 x; - uint32 width; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXBufferUpdate; -/* SVGA_3D_CMD_DX_BUFFER_UPDATE */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetConstantBufferOffset { - uint32 slot; - uint32 offsetInBytes; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetConstantBufferOffset; +#define SVGA_DX_HINT_NONE 0 +#define SVGA_DX_HINT_PREFETCH_OBJECT 1 +#define SVGA_DX_HINT_PREEVICT_OBJECT 2 +#define SVGA_DX_HINT_PREFETCH_COBJECT 3 +#define SVGA_DX_HINT_PREEVICT_COBJECT 4 +#define SVGA_DX_HINT_MAX 5 + +#pragma pack(push, 1) +typedef struct SVGAObjectRef { + SVGAOTableType type; + uint32 id; +} SVGAObjectRef; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGACObjectRef { + SVGACOTableType type; + uint32 cid; + uint32 id; +} SVGACObjectRef; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXHint { + SVGADXHintId hintId; + +} SVGA3dCmdDXHint; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXBufferUpdate { + SVGA3dSurfaceId sid; + uint32 x; + uint32 width; +} SVGA3dCmdDXBufferUpdate; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetConstantBufferOffset { + uint32 slot; + uint32 offsetInBytes; +} SVGA3dCmdDXSetConstantBufferOffset; +#pragma pack(pop) typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetVSConstantBufferOffset; -/* SVGA_3D_CMD_DX_SET_VS_CONSTANT_BUFFER_OFFSET */ typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetPSConstantBufferOffset; -/* SVGA_3D_CMD_DX_SET_PS_CONSTANT_BUFFER_OFFSET */ typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetGSConstantBufferOffset; -/* SVGA_3D_CMD_DX_SET_GS_CONSTANT_BUFFER_OFFSET */ typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetHSConstantBufferOffset; -/* SVGA_3D_CMD_DX_SET_HS_CONSTANT_BUFFER_OFFSET */ typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetDSConstantBufferOffset; -/* SVGA_3D_CMD_DX_SET_DS_CONSTANT_BUFFER_OFFSET */ typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetCSConstantBufferOffset; -/* SVGA_3D_CMD_DX_SET_CS_CONSTANT_BUFFER_OFFSET */ - -#define SVGA3D_BUFFEREX_SRV_RAW (1 << 0) -#define SVGA3D_BUFFEREX_SRV_FLAGS_MAX (1 << 1) +#define SVGA3D_BUFFEREX_SRV_RAW (1 << 0) +#define SVGA3D_BUFFEREX_SRV_FLAGS_MAX (1 << 1) #define SVGA3D_BUFFEREX_SRV_FLAGS_MASK (SVGA3D_BUFFEREX_SRV_FLAGS_MAX - 1) typedef uint32 SVGA3dBufferExFlags; -typedef -#include "vmware_pack_begin.h" -struct { - union { - struct { - uint32 firstElement; - uint32 numElements; - uint32 pad0; - uint32 pad1; - } buffer; - struct { - uint32 mostDetailedMip; - uint32 firstArraySlice; - uint32 mipLevels; - uint32 arraySize; - } tex; /* 1d, 2d, 3d, cube */ - struct { - uint32 firstElement; - uint32 numElements; - SVGA3dBufferExFlags flags; - uint32 pad0; - } bufferex; - }; -} -#include "vmware_pack_end.h" -SVGA3dShaderResourceViewDesc; - -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dSurfaceId sid; - SVGA3dSurfaceFormat format; - SVGA3dResourceType resourceDimension; - SVGA3dShaderResourceViewDesc desc; - uint32 pad; -} -#include "vmware_pack_end.h" -SVGACOTableDXSRViewEntry; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineShaderResourceView { - SVGA3dShaderResourceViewId shaderResourceViewId; - - SVGA3dSurfaceId sid; - SVGA3dSurfaceFormat format; - SVGA3dResourceType resourceDimension; - - SVGA3dShaderResourceViewDesc desc; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineShaderResourceView; -/* SVGA_3D_CMD_DX_DEFINE_SHADERRESOURCE_VIEW */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDestroyShaderResourceView { - SVGA3dShaderResourceViewId shaderResourceViewId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDestroyShaderResourceView; -/* SVGA_3D_CMD_DX_DESTROY_SHADERRESOURCE_VIEW */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dRenderTargetViewDesc { - union { - struct { - uint32 firstElement; - uint32 numElements; - uint32 padding0; - } buffer; - struct { - uint32 mipSlice; - uint32 firstArraySlice; - uint32 arraySize; - } tex; /* 1d, 2d, cube */ - struct { - uint32 mipSlice; - uint32 firstW; - uint32 wSize; - } tex3D; - }; -} -#include "vmware_pack_end.h" -SVGA3dRenderTargetViewDesc; - -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dSurfaceId sid; - SVGA3dSurfaceFormat format; - SVGA3dResourceType resourceDimension; - SVGA3dRenderTargetViewDesc desc; - uint32 pad[2]; -} -#include "vmware_pack_end.h" -SVGACOTableDXRTViewEntry; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineRenderTargetView { - SVGA3dRenderTargetViewId renderTargetViewId; - - SVGA3dSurfaceId sid; - SVGA3dSurfaceFormat format; - SVGA3dResourceType resourceDimension; - - SVGA3dRenderTargetViewDesc desc; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineRenderTargetView; -/* SVGA_3D_CMD_DX_DEFINE_RENDERTARGET_VIEW */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDestroyRenderTargetView { - SVGA3dRenderTargetViewId renderTargetViewId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDestroyRenderTargetView; -/* SVGA_3D_CMD_DX_DESTROY_RENDERTARGET_VIEW */ - -/* - */ -#define SVGA3D_DXDSVIEW_CREATE_READ_ONLY_DEPTH 0x01 +#pragma pack(push, 1) +typedef struct { + union { + struct { + uint32 firstElement; + uint32 numElements; + uint32 pad0; + uint32 pad1; + } buffer; + struct { + uint32 mostDetailedMip; + uint32 firstArraySlice; + uint32 mipLevels; + uint32 arraySize; + } tex; + struct { + uint32 firstElement; + uint32 numElements; + SVGA3dBufferExFlags flags; + uint32 pad0; + } bufferex; + }; +} SVGA3dShaderResourceViewDesc; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dSurfaceId sid; + SVGA3dSurfaceFormat format; + SVGA3dResourceType resourceDimension; + SVGA3dShaderResourceViewDesc desc; + uint32 pad; +} SVGACOTableDXSRViewEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineShaderResourceView { + SVGA3dShaderResourceViewId shaderResourceViewId; + + SVGA3dSurfaceId sid; + SVGA3dSurfaceFormat format; + SVGA3dResourceType resourceDimension; + + SVGA3dShaderResourceViewDesc desc; +} SVGA3dCmdDXDefineShaderResourceView; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDestroyShaderResourceView { + SVGA3dShaderResourceViewId shaderResourceViewId; +} SVGA3dCmdDXDestroyShaderResourceView; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dRenderTargetViewDesc { + union { + struct { + uint32 firstElement; + uint32 numElements; + uint32 padding0; + } buffer; + struct { + uint32 mipSlice; + uint32 firstArraySlice; + uint32 arraySize; + } tex; + struct { + uint32 mipSlice; + uint32 firstW; + uint32 wSize; + } tex3D; + }; +} SVGA3dRenderTargetViewDesc; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dSurfaceId sid; + SVGA3dSurfaceFormat format; + SVGA3dResourceType resourceDimension; + SVGA3dRenderTargetViewDesc desc; + uint32 pad[2]; +} SVGACOTableDXRTViewEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineRenderTargetView { + SVGA3dRenderTargetViewId renderTargetViewId; + + SVGA3dSurfaceId sid; + SVGA3dSurfaceFormat format; + SVGA3dResourceType resourceDimension; + + SVGA3dRenderTargetViewDesc desc; +} SVGA3dCmdDXDefineRenderTargetView; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDestroyRenderTargetView { + SVGA3dRenderTargetViewId renderTargetViewId; +} SVGA3dCmdDXDestroyRenderTargetView; +#pragma pack(pop) + +#define SVGA3D_DXDSVIEW_CREATE_READ_ONLY_DEPTH 0x01 #define SVGA3D_DXDSVIEW_CREATE_READ_ONLY_STENCIL 0x02 -#define SVGA3D_DXDSVIEW_CREATE_FLAG_MASK 0x03 +#define SVGA3D_DXDSVIEW_CREATE_FLAG_MASK 0x03 typedef uint8 SVGA3DCreateDSViewFlags; -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dSurfaceId sid; - SVGA3dSurfaceFormat format; - SVGA3dResourceType resourceDimension; - uint32 mipSlice; - uint32 firstArraySlice; - uint32 arraySize; - SVGA3DCreateDSViewFlags flags; - uint8 pad0; - uint16 pad1; - uint32 pad2; -} -#include "vmware_pack_end.h" -SVGACOTableDXDSViewEntry; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineDepthStencilView { - SVGA3dDepthStencilViewId depthStencilViewId; - - SVGA3dSurfaceId sid; - SVGA3dSurfaceFormat format; - SVGA3dResourceType resourceDimension; - uint32 mipSlice; - uint32 firstArraySlice; - uint32 arraySize; - SVGA3DCreateDSViewFlags flags; - uint8 pad0; - uint16 pad1; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineDepthStencilView; -/* SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_VIEW */ - -/* - * Version 2 needed in order to start validating and using the flags - * field. Unfortunately the device wasn't validating or using the - * flags field and the driver wasn't initializing it in shipped code, - * so a new version of the command is needed to allow that code to - * continue to work. - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineDepthStencilView_v2 { - SVGA3dDepthStencilViewId depthStencilViewId; - - SVGA3dSurfaceId sid; - SVGA3dSurfaceFormat format; - SVGA3dResourceType resourceDimension; - uint32 mipSlice; - uint32 firstArraySlice; - uint32 arraySize; - SVGA3DCreateDSViewFlags flags; - uint8 pad0; - uint16 pad1; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineDepthStencilView_v2; -/* SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_VIEW_V2 */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDestroyDepthStencilView { - SVGA3dDepthStencilViewId depthStencilViewId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDestroyDepthStencilView; -/* SVGA_3D_CMD_DX_DESTROY_DEPTHSTENCIL_VIEW */ - - -#define SVGA3D_UABUFFER_RAW (1 << 0) -#define SVGA3D_UABUFFER_APPEND (1 << 1) +#pragma pack(push, 1) +typedef struct { + SVGA3dSurfaceId sid; + SVGA3dSurfaceFormat format; + SVGA3dResourceType resourceDimension; + uint32 mipSlice; + uint32 firstArraySlice; + uint32 arraySize; + SVGA3DCreateDSViewFlags flags; + uint8 pad0; + uint16 pad1; + uint32 pad2; +} SVGACOTableDXDSViewEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineDepthStencilView { + SVGA3dDepthStencilViewId depthStencilViewId; + + SVGA3dSurfaceId sid; + SVGA3dSurfaceFormat format; + SVGA3dResourceType resourceDimension; + uint32 mipSlice; + uint32 firstArraySlice; + uint32 arraySize; + SVGA3DCreateDSViewFlags flags; + uint8 pad0; + uint16 pad1; +} SVGA3dCmdDXDefineDepthStencilView; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineDepthStencilView_v2 { + SVGA3dDepthStencilViewId depthStencilViewId; + + SVGA3dSurfaceId sid; + SVGA3dSurfaceFormat format; + SVGA3dResourceType resourceDimension; + uint32 mipSlice; + uint32 firstArraySlice; + uint32 arraySize; + SVGA3DCreateDSViewFlags flags; + uint8 pad0; + uint16 pad1; +} SVGA3dCmdDXDefineDepthStencilView_v2; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDestroyDepthStencilView { + SVGA3dDepthStencilViewId depthStencilViewId; +} SVGA3dCmdDXDestroyDepthStencilView; +#pragma pack(pop) + +#define SVGA3D_UABUFFER_RAW (1 << 0) +#define SVGA3D_UABUFFER_APPEND (1 << 1) #define SVGA3D_UABUFFER_COUNTER (1 << 2) typedef uint32 SVGA3dUABufferFlags; -typedef -#include "vmware_pack_begin.h" -struct { - union { - struct { - uint32 firstElement; - uint32 numElements; - SVGA3dUABufferFlags flags; - uint32 padding0; - uint32 padding1; - } buffer; - struct { - uint32 mipSlice; - uint32 firstArraySlice; - uint32 arraySize; - uint32 padding0; - uint32 padding1; - } tex; /* 1d, 2d */ - struct { - uint32 mipSlice; - uint32 firstW; - uint32 wSize; - uint32 padding0; - uint32 padding1; - } tex3D; - }; -} -#include "vmware_pack_end.h" -SVGA3dUAViewDesc; - -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dSurfaceId sid; - SVGA3dSurfaceFormat format; - SVGA3dResourceType resourceDimension; - SVGA3dUAViewDesc desc; - uint32 structureCount; - uint32 pad[7]; -} -#include "vmware_pack_end.h" -SVGACOTableDXUAViewEntry; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineUAView { - SVGA3dUAViewId uaViewId; - - SVGA3dSurfaceId sid; - SVGA3dSurfaceFormat format; - SVGA3dResourceType resourceDimension; - - SVGA3dUAViewDesc desc; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineUAView; -/* SVGA_3D_CMD_DX_DEFINE_UA_VIEW */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDestroyUAView { - SVGA3dUAViewId uaViewId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDestroyUAView; -/* SVGA_3D_CMD_DX_DESTROY_UA_VIEW */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXClearUAViewUint { - SVGA3dUAViewId uaViewId; - SVGA3dRGBAUint32 value; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXClearUAViewUint; -/* SVGA_3D_CMD_DX_CLEAR_UA_VIEW_UINT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXClearUAViewFloat { - SVGA3dUAViewId uaViewId; - SVGA3dRGBAFloat value; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXClearUAViewFloat; -/* SVGA_3D_CMD_DX_CLEAR_UA_VIEW_FLOAT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXCopyStructureCount { - SVGA3dUAViewId srcUAViewId; - SVGA3dSurfaceId destSid; - uint32 destByteOffset; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXCopyStructureCount; -/* SVGA_3D_CMD_DX_COPY_STRUCTURE_COUNT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetStructureCount { - SVGA3dUAViewId uaViewId; - uint32 structureCount; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetStructureCount; -/* SVGA_3D_CMD_DX_SET_STRUCTURE_COUNT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetUAViews { - uint32 uavSpliceIndex; - /* Followed by a variable number of SVGA3dUAViewId's. */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetUAViews; /* SVGA_3D_CMD_DX_SET_UA_VIEWS */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetCSUAViews { - uint32 startIndex; - /* Followed by a variable number of SVGA3dUAViewId's. */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetCSUAViews; /* SVGA_3D_CMD_DX_SET_CS_UA_VIEWS */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dInputElementDesc { - uint32 inputSlot; - uint32 alignedByteOffset; - SVGA3dSurfaceFormat format; - SVGA3dInputClassification inputSlotClass; - uint32 instanceDataStepRate; - uint32 inputRegister; -} -#include "vmware_pack_end.h" -SVGA3dInputElementDesc; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 elid; - uint32 numDescs; - SVGA3dInputElementDesc descs[32]; - uint32 pad[62]; -} -#include "vmware_pack_end.h" -SVGACOTableDXElementLayoutEntry; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineElementLayout { - SVGA3dElementLayoutId elementLayoutId; - /* Followed by a variable number of SVGA3dInputElementDesc's. */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineElementLayout; -/* SVGA_3D_CMD_DX_DEFINE_ELEMENTLAYOUT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDestroyElementLayout { - SVGA3dElementLayoutId elementLayoutId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDestroyElementLayout; -/* SVGA_3D_CMD_DX_DESTROY_ELEMENTLAYOUT */ - +#pragma pack(push, 1) +typedef struct { + union { + struct { + uint32 firstElement; + uint32 numElements; + SVGA3dUABufferFlags flags; + uint32 padding0; + uint32 padding1; + } buffer; + struct { + uint32 mipSlice; + uint32 firstArraySlice; + uint32 arraySize; + uint32 padding0; + uint32 padding1; + } tex; + struct { + uint32 mipSlice; + uint32 firstW; + uint32 wSize; + uint32 padding0; + uint32 padding1; + } tex3D; + }; +} SVGA3dUAViewDesc; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dSurfaceId sid; + SVGA3dSurfaceFormat format; + SVGA3dResourceType resourceDimension; + SVGA3dUAViewDesc desc; + uint32 structureCount; + uint32 pad[7]; +} SVGACOTableDXUAViewEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineUAView { + SVGA3dUAViewId uaViewId; + + SVGA3dSurfaceId sid; + SVGA3dSurfaceFormat format; + SVGA3dResourceType resourceDimension; + + SVGA3dUAViewDesc desc; +} SVGA3dCmdDXDefineUAView; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDestroyUAView { + SVGA3dUAViewId uaViewId; +} SVGA3dCmdDXDestroyUAView; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXClearUAViewUint { + SVGA3dUAViewId uaViewId; + SVGA3dRGBAUint32 value; +} SVGA3dCmdDXClearUAViewUint; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXClearUAViewFloat { + SVGA3dUAViewId uaViewId; + SVGA3dRGBAFloat value; +} SVGA3dCmdDXClearUAViewFloat; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXCopyStructureCount { + SVGA3dUAViewId srcUAViewId; + SVGA3dSurfaceId destSid; + uint32 destByteOffset; +} SVGA3dCmdDXCopyStructureCount; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetStructureCount { + SVGA3dUAViewId uaViewId; + uint32 structureCount; +} SVGA3dCmdDXSetStructureCount; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetUAViews { + uint32 uavSpliceIndex; + +} SVGA3dCmdDXSetUAViews; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetCSUAViews { + uint32 startIndex; + +} SVGA3dCmdDXSetCSUAViews; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dInputElementDesc { + uint32 inputSlot; + uint32 alignedByteOffset; + SVGA3dSurfaceFormat format; + SVGA3dInputClassification inputSlotClass; + uint32 instanceDataStepRate; + uint32 inputRegister; +} SVGA3dInputElementDesc; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 elid; + uint32 numDescs; + SVGA3dInputElementDesc descs[32]; + uint32 pad[62]; +} SVGACOTableDXElementLayoutEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineElementLayout { + SVGA3dElementLayoutId elementLayoutId; + +} SVGA3dCmdDXDefineElementLayout; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDestroyElementLayout { + SVGA3dElementLayoutId elementLayoutId; +} SVGA3dCmdDXDestroyElementLayout; +#pragma pack(pop) #define SVGA3D_DX_MAX_RENDER_TARGETS 8 -typedef -#include "vmware_pack_begin.h" -struct SVGA3dDXBlendStatePerRT { - uint8 blendEnable; - uint8 srcBlend; - uint8 destBlend; - uint8 blendOp; - uint8 srcBlendAlpha; - uint8 destBlendAlpha; - uint8 blendOpAlpha; - SVGA3dColorWriteEnable renderTargetWriteMask; - uint8 logicOpEnable; - uint8 logicOp; - uint16 pad0; -} -#include "vmware_pack_end.h" -SVGA3dDXBlendStatePerRT; - -typedef -#include "vmware_pack_begin.h" -struct { - uint8 alphaToCoverageEnable; - uint8 independentBlendEnable; - uint16 pad0; - SVGA3dDXBlendStatePerRT perRT[SVGA3D_MAX_RENDER_TARGETS]; - uint32 pad1[7]; -} -#include "vmware_pack_end.h" -SVGACOTableDXBlendStateEntry; - -/* - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineBlendState { - SVGA3dBlendStateId blendId; - uint8 alphaToCoverageEnable; - uint8 independentBlendEnable; - uint16 pad0; - SVGA3dDXBlendStatePerRT perRT[SVGA3D_MAX_RENDER_TARGETS]; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineBlendState; /* SVGA_3D_CMD_DX_DEFINE_BLEND_STATE */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDestroyBlendState { - SVGA3dBlendStateId blendId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDestroyBlendState; /* SVGA_3D_CMD_DX_DESTROY_BLEND_STATE */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint8 depthEnable; - SVGA3dDepthWriteMask depthWriteMask; - SVGA3dComparisonFunc depthFunc; - uint8 stencilEnable; - uint8 frontEnable; - uint8 backEnable; - uint8 stencilReadMask; - uint8 stencilWriteMask; - - uint8 frontStencilFailOp; - uint8 frontStencilDepthFailOp; - uint8 frontStencilPassOp; - SVGA3dComparisonFunc frontStencilFunc; - - uint8 backStencilFailOp; - uint8 backStencilDepthFailOp; - uint8 backStencilPassOp; - SVGA3dComparisonFunc backStencilFunc; -} -#include "vmware_pack_end.h" -SVGACOTableDXDepthStencilEntry; - -/* - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineDepthStencilState { - SVGA3dDepthStencilStateId depthStencilId; - - uint8 depthEnable; - SVGA3dDepthWriteMask depthWriteMask; - SVGA3dComparisonFunc depthFunc; - uint8 stencilEnable; - uint8 frontEnable; - uint8 backEnable; - uint8 stencilReadMask; - uint8 stencilWriteMask; - - uint8 frontStencilFailOp; - uint8 frontStencilDepthFailOp; - uint8 frontStencilPassOp; - SVGA3dComparisonFunc frontStencilFunc; - - uint8 backStencilFailOp; - uint8 backStencilDepthFailOp; - uint8 backStencilPassOp; - SVGA3dComparisonFunc backStencilFunc; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineDepthStencilState; -/* SVGA_3D_CMD_DX_DEFINE_DEPTHSTENCIL_STATE */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDestroyDepthStencilState { - SVGA3dDepthStencilStateId depthStencilId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDestroyDepthStencilState; -/* SVGA_3D_CMD_DX_DESTROY_DEPTHSTENCIL_STATE */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint8 fillMode; - SVGA3dCullMode cullMode; - uint8 frontCounterClockwise; - uint8 provokingVertexLast; - int32 depthBias; - float depthBiasClamp; - float slopeScaledDepthBias; - uint8 depthClipEnable; - uint8 scissorEnable; - SVGA3dMultisampleRastEnable multisampleEnable; - uint8 antialiasedLineEnable; - float lineWidth; - uint8 lineStippleEnable; - uint8 lineStippleFactor; - uint16 lineStipplePattern; - uint8 forcedSampleCount; - uint8 mustBeZero[3]; -} -#include "vmware_pack_end.h" -SVGACOTableDXRasterizerStateEntry; - -/* - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineRasterizerState { - SVGA3dRasterizerStateId rasterizerId; - - uint8 fillMode; - SVGA3dCullMode cullMode; - uint8 frontCounterClockwise; - uint8 provokingVertexLast; - int32 depthBias; - float depthBiasClamp; - float slopeScaledDepthBias; - uint8 depthClipEnable; - uint8 scissorEnable; - SVGA3dMultisampleRastEnable multisampleEnable; - uint8 antialiasedLineEnable; - float lineWidth; - uint8 lineStippleEnable; - uint8 lineStippleFactor; - uint16 lineStipplePattern; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineRasterizerState; -/* SVGA_3D_CMD_DX_DEFINE_RASTERIZER_STATE */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDestroyRasterizerState { - SVGA3dRasterizerStateId rasterizerId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDestroyRasterizerState; -/* SVGA_3D_CMD_DX_DESTROY_RASTERIZER_STATE */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGA3dFilter filter; - uint8 addressU; - uint8 addressV; - uint8 addressW; - uint8 pad0; - float mipLODBias; - uint8 maxAnisotropy; - SVGA3dComparisonFunc comparisonFunc; - uint16 pad1; - SVGA3dRGBAFloat borderColor; - float minLOD; - float maxLOD; - uint32 pad2[6]; -} -#include "vmware_pack_end.h" -SVGACOTableDXSamplerEntry; - -/* - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineSamplerState { - SVGA3dSamplerId samplerId; - SVGA3dFilter filter; - uint8 addressU; - uint8 addressV; - uint8 addressW; - uint8 pad0; - float mipLODBias; - uint8 maxAnisotropy; - SVGA3dComparisonFunc comparisonFunc; - uint16 pad1; - SVGA3dRGBAFloat borderColor; - float minLOD; - float maxLOD; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineSamplerState; /* SVGA_3D_CMD_DX_DEFINE_SAMPLER_STATE */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDestroySamplerState { - SVGA3dSamplerId samplerId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDestroySamplerState; /* SVGA_3D_CMD_DX_DESTROY_SAMPLER_STATE */ - - -#define SVGADX_SIGNATURE_SEMANTIC_NAME_UNDEFINED 0 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_POSITION 1 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_CLIP_DISTANCE 2 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_CULL_DISTANCE 3 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_RENDER_TARGET_ARRAY_INDEX 4 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_VIEWPORT_ARRAY_INDEX 5 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_VERTEX_ID 6 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_PRIMITIVE_ID 7 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_INSTANCE_ID 8 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_IS_FRONT_FACE 9 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_SAMPLE_INDEX 10 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_U_EQ_0_EDGE_TESSFACTOR 11 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_V_EQ_0_EDGE_TESSFACTOR 12 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_U_EQ_1_EDGE_TESSFACTOR 13 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_V_EQ_1_EDGE_TESSFACTOR 14 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_U_INSIDE_TESSFACTOR 15 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_V_INSIDE_TESSFACTOR 16 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_U_EQ_0_EDGE_TESSFACTOR 17 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_V_EQ_0_EDGE_TESSFACTOR 18 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_W_EQ_0_EDGE_TESSFACTOR 19 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_INSIDE_TESSFACTOR 20 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_LINE_DETAIL_TESSFACTOR 21 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_LINE_DENSITY_TESSFACTOR 22 -#define SVGADX_SIGNATURE_SEMANTIC_NAME_MAX 23 +#pragma pack(push, 1) +typedef struct SVGA3dDXBlendStatePerRT { + uint8 blendEnable; + uint8 srcBlend; + uint8 destBlend; + uint8 blendOp; + uint8 srcBlendAlpha; + uint8 destBlendAlpha; + uint8 blendOpAlpha; + SVGA3dColorWriteEnable renderTargetWriteMask; + uint8 logicOpEnable; + uint8 logicOp; + uint16 pad0; +} SVGA3dDXBlendStatePerRT; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint8 alphaToCoverageEnable; + uint8 independentBlendEnable; + uint16 pad0; + SVGA3dDXBlendStatePerRT perRT[SVGA3D_DX_MAX_RENDER_TARGETS]; + uint32 pad1[7]; +} SVGACOTableDXBlendStateEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineBlendState { + SVGA3dBlendStateId blendId; + uint8 alphaToCoverageEnable; + uint8 independentBlendEnable; + uint16 pad0; + SVGA3dDXBlendStatePerRT perRT[SVGA3D_DX_MAX_RENDER_TARGETS]; +} SVGA3dCmdDXDefineBlendState; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDestroyBlendState { + SVGA3dBlendStateId blendId; +} SVGA3dCmdDXDestroyBlendState; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint8 depthEnable; + SVGA3dDepthWriteMask depthWriteMask; + SVGA3dComparisonFunc depthFunc; + uint8 stencilEnable; + uint8 frontEnable; + uint8 backEnable; + uint8 stencilReadMask; + uint8 stencilWriteMask; + + uint8 frontStencilFailOp; + uint8 frontStencilDepthFailOp; + uint8 frontStencilPassOp; + SVGA3dComparisonFunc frontStencilFunc; + + uint8 backStencilFailOp; + uint8 backStencilDepthFailOp; + uint8 backStencilPassOp; + SVGA3dComparisonFunc backStencilFunc; +} SVGACOTableDXDepthStencilEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineDepthStencilState { + SVGA3dDepthStencilStateId depthStencilId; + + uint8 depthEnable; + SVGA3dDepthWriteMask depthWriteMask; + SVGA3dComparisonFunc depthFunc; + uint8 stencilEnable; + uint8 frontEnable; + uint8 backEnable; + uint8 stencilReadMask; + uint8 stencilWriteMask; + + uint8 frontStencilFailOp; + uint8 frontStencilDepthFailOp; + uint8 frontStencilPassOp; + SVGA3dComparisonFunc frontStencilFunc; + + uint8 backStencilFailOp; + uint8 backStencilDepthFailOp; + uint8 backStencilPassOp; + SVGA3dComparisonFunc backStencilFunc; +} SVGA3dCmdDXDefineDepthStencilState; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDestroyDepthStencilState { + SVGA3dDepthStencilStateId depthStencilId; +} SVGA3dCmdDXDestroyDepthStencilState; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint8 fillMode; + SVGA3dCullMode cullMode; + uint8 frontCounterClockwise; + uint8 provokingVertexLast; + int32 depthBias; + float depthBiasClamp; + float slopeScaledDepthBias; + uint8 depthClipEnable; + uint8 scissorEnable; + SVGA3dMultisampleRastEnable multisampleEnable; + uint8 antialiasedLineEnable; + float lineWidth; + uint8 lineStippleEnable; + uint8 lineStippleFactor; + uint16 lineStipplePattern; + uint8 forcedSampleCount; + uint8 mustBeZero[3]; +} SVGACOTableDXRasterizerStateEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineRasterizerState { + SVGA3dRasterizerStateId rasterizerId; + + uint8 fillMode; + SVGA3dCullMode cullMode; + uint8 frontCounterClockwise; + uint8 provokingVertexLast; + int32 depthBias; + float depthBiasClamp; + float slopeScaledDepthBias; + uint8 depthClipEnable; + uint8 scissorEnable; + SVGA3dMultisampleRastEnable multisampleEnable; + uint8 antialiasedLineEnable; + float lineWidth; + uint8 lineStippleEnable; + uint8 lineStippleFactor; + uint16 lineStipplePattern; +} SVGA3dCmdDXDefineRasterizerState; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineRasterizerState_v2 { + SVGA3dRasterizerStateId rasterizerId; + + uint8 fillMode; + SVGA3dCullMode cullMode; + uint8 frontCounterClockwise; + uint8 provokingVertexLast; + int32 depthBias; + float depthBiasClamp; + float slopeScaledDepthBias; + uint8 depthClipEnable; + uint8 scissorEnable; + SVGA3dMultisampleRastEnable multisampleEnable; + uint8 antialiasedLineEnable; + float lineWidth; + uint8 lineStippleEnable; + uint8 lineStippleFactor; + uint16 lineStipplePattern; + uint32 forcedSampleCount; +} SVGA3dCmdDXDefineRasterizerState_v2; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDestroyRasterizerState { + SVGA3dRasterizerStateId rasterizerId; +} SVGA3dCmdDXDestroyRasterizerState; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGA3dFilter filter; + uint8 addressU; + uint8 addressV; + uint8 addressW; + uint8 pad0; + float mipLODBias; + uint8 maxAnisotropy; + SVGA3dComparisonFunc comparisonFunc; + uint16 pad1; + SVGA3dRGBAFloat borderColor; + float minLOD; + float maxLOD; + uint32 pad2[6]; +} SVGACOTableDXSamplerEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineSamplerState { + SVGA3dSamplerId samplerId; + SVGA3dFilter filter; + uint8 addressU; + uint8 addressV; + uint8 addressW; + uint8 pad0; + float mipLODBias; + uint8 maxAnisotropy; + SVGA3dComparisonFunc comparisonFunc; + uint16 pad1; + SVGA3dRGBAFloat borderColor; + float minLOD; + float maxLOD; +} SVGA3dCmdDXDefineSamplerState; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDestroySamplerState { + SVGA3dSamplerId samplerId; +} SVGA3dCmdDXDestroySamplerState; +#pragma pack(pop) + +#define SVGADX_SIGNATURE_SEMANTIC_NAME_UNDEFINED 0 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_POSITION 1 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_CLIP_DISTANCE 2 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_CULL_DISTANCE 3 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_RENDER_TARGET_ARRAY_INDEX 4 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_VIEWPORT_ARRAY_INDEX 5 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_VERTEX_ID 6 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_PRIMITIVE_ID 7 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_INSTANCE_ID 8 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_IS_FRONT_FACE 9 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_SAMPLE_INDEX 10 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_U_EQ_0_EDGE_TESSFACTOR 11 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_V_EQ_0_EDGE_TESSFACTOR 12 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_U_EQ_1_EDGE_TESSFACTOR 13 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_V_EQ_1_EDGE_TESSFACTOR 14 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_U_INSIDE_TESSFACTOR 15 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_QUAD_V_INSIDE_TESSFACTOR 16 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_U_EQ_0_EDGE_TESSFACTOR 17 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_V_EQ_0_EDGE_TESSFACTOR 18 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_W_EQ_0_EDGE_TESSFACTOR 19 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_TRI_INSIDE_TESSFACTOR 20 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_LINE_DETAIL_TESSFACTOR 21 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_FINAL_LINE_DENSITY_TESSFACTOR 22 +#define SVGADX_SIGNATURE_SEMANTIC_NAME_MAX 23 typedef uint32 SVGA3dDXSignatureSemanticName; #define SVGADX_SIGNATURE_REGISTER_COMPONENT_UNKNOWN 0 @@ -1670,398 +1394,331 @@ typedef uint32 SVGA3dDXSignatureRegisterComponentType; #define SVGADX_SIGNATURE_MIN_PRECISION_DEFAULT 0 typedef uint32 SVGA3dDXSignatureMinPrecision; -typedef -#include "vmware_pack_begin.h" -struct SVGA3dDXSignatureEntry { - uint32 registerIndex; - SVGA3dDXSignatureSemanticName semanticName; - uint32 mask; /* Lower 4 bits represent X, Y, Z, W channels */ - SVGA3dDXSignatureRegisterComponentType componentType; - SVGA3dDXSignatureMinPrecision minPrecision; -} -#include "vmware_pack_end.h" -SVGA3dDXShaderSignatureEntry; +#pragma pack(push, 1) +typedef struct SVGA3dDXSignatureEntry { + uint32 registerIndex; + SVGA3dDXSignatureSemanticName semanticName; + uint32 mask; + SVGA3dDXSignatureRegisterComponentType componentType; + SVGA3dDXSignatureMinPrecision minPrecision; +} SVGA3dDXShaderSignatureEntry; +#pragma pack(pop) #define SVGADX_SIGNATURE_HEADER_VERSION_0 0x08a92d12 -/* - * The SVGA3dDXSignatureHeader structure is added after the shader - * body in the mob that is bound to the shader. It is followed by the - * specified number of SVGA3dDXSignatureEntry structures for each of - * the three types of signatures in the order (input, output, patch - * constants). - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dDXSignatureHeader { - uint32 headerVersion; - uint32 numInputSignatures; - uint32 numOutputSignatures; - uint32 numPatchConstantSignatures; -} -#include "vmware_pack_end.h" -SVGA3dDXShaderSignatureHeader; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineShader { - SVGA3dShaderId shaderId; - SVGA3dShaderType type; - uint32 sizeInBytes; /* Number of bytes of shader text. */ -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineShader; /* SVGA_3D_CMD_DX_DEFINE_SHADER */ - -typedef -#include "vmware_pack_begin.h" -struct SVGACOTableDXShaderEntry { - SVGA3dShaderType type; - uint32 sizeInBytes; - uint32 offsetInBytes; - SVGAMobId mobid; - uint32 pad[4]; -} -#include "vmware_pack_end.h" -SVGACOTableDXShaderEntry; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDestroyShader { - SVGA3dShaderId shaderId; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDestroyShader; /* SVGA_3D_CMD_DX_DESTROY_SHADER */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXBindShader { - uint32 cid; - uint32 shid; - SVGAMobId mobid; - uint32 offsetInBytes; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXBindShader; /* SVGA_3D_CMD_DX_BIND_SHADER */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXBindAllShader { - uint32 cid; - SVGAMobId mobid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXBindAllShader; /* SVGA_3D_CMD_DX_BIND_ALL_SHADER */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXCondBindAllShader { - uint32 cid; - SVGAMobId testMobid; - SVGAMobId mobid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXCondBindAllShader; /* SVGA_3D_CMD_DX_COND_BIND_ALL_SHADER */ +#pragma pack(push, 1) +typedef struct SVGA3dDXSignatureHeader { + uint32 headerVersion; + uint32 numInputSignatures; + uint32 numOutputSignatures; + uint32 numPatchConstantSignatures; +} SVGA3dDXShaderSignatureHeader; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineShader { + SVGA3dShaderId shaderId; + SVGA3dShaderType type; + uint32 sizeInBytes; +} SVGA3dCmdDXDefineShader; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGACOTableDXShaderEntry { + SVGA3dShaderType type; + uint32 sizeInBytes; + uint32 offsetInBytes; + SVGAMobId mobid; + uint32 pad[4]; +} SVGACOTableDXShaderEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDestroyShader { + SVGA3dShaderId shaderId; +} SVGA3dCmdDXDestroyShader; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXBindShader { + uint32 cid; + uint32 shid; + SVGAMobId mobid; + uint32 offsetInBytes; +} SVGA3dCmdDXBindShader; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXBindAllShader { + uint32 cid; + SVGAMobId mobid; +} SVGA3dCmdDXBindAllShader; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXCondBindAllShader { + uint32 cid; + SVGAMobId testMobid; + SVGAMobId mobid; +} SVGA3dCmdDXCondBindAllShader; +#pragma pack(pop) -/* - * The maximum number of streamout decl's in each streamout entry. - */ #define SVGA3D_MAX_DX10_STREAMOUT_DECLS 64 #define SVGA3D_MAX_STREAMOUT_DECLS 512 -typedef -#include "vmware_pack_begin.h" -struct SVGA3dStreamOutputDeclarationEntry { - uint32 outputSlot; - uint32 registerIndex; - uint8 registerMask; - uint8 pad0; - uint16 pad1; - uint32 stream; -} -#include "vmware_pack_end.h" -SVGA3dStreamOutputDeclarationEntry; - -typedef -#include "vmware_pack_begin.h" -struct SVGAOTableStreamOutputEntry { - uint32 numOutputStreamEntries; - SVGA3dStreamOutputDeclarationEntry decl[SVGA3D_MAX_DX10_STREAMOUT_DECLS]; - uint32 streamOutputStrideInBytes[SVGA3D_DX_MAX_SOTARGETS]; - uint32 rasterizedStream; - uint32 numOutputStreamStrides; - uint32 mobid; - uint32 offsetInBytes; - uint8 usesMob; - uint8 pad0; - uint16 pad1; - uint32 pad2[246]; -} -#include "vmware_pack_end.h" -SVGACOTableDXStreamOutputEntry; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineStreamOutput { - SVGA3dStreamOutputId soid; - uint32 numOutputStreamEntries; - SVGA3dStreamOutputDeclarationEntry decl[SVGA3D_MAX_DX10_STREAMOUT_DECLS]; - uint32 streamOutputStrideInBytes[SVGA3D_DX_MAX_SOTARGETS]; - uint32 rasterizedStream; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineStreamOutput; /* SVGA_3D_CMD_DX_DEFINE_STREAMOUTPUT */ - -/* - * Version 2 needed in order to start validating and using the - * rasterizedStream field. Unfortunately the device wasn't validating - * or using this field and the driver wasn't initializing it in shipped - * code, so a new version of the command is needed to allow that code - * to continue to work. Also added new numOutputStreamStrides field. - */ +#pragma pack(push, 1) +typedef struct SVGA3dStreamOutputDeclarationEntry { + uint32 outputSlot; + uint32 registerIndex; + uint8 registerMask; + uint8 pad0; + uint16 pad1; + uint32 stream; +} SVGA3dStreamOutputDeclarationEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGAOTableStreamOutputEntry { + uint32 numOutputStreamEntries; + SVGA3dStreamOutputDeclarationEntry decl[SVGA3D_MAX_DX10_STREAMOUT_DECLS]; + uint32 streamOutputStrideInBytes[SVGA3D_DX_MAX_SOTARGETS]; + uint32 rasterizedStream; + uint32 numOutputStreamStrides; + uint32 mobid; + uint32 offsetInBytes; + uint8 usesMob; + uint8 pad0; + uint16 pad1; + uint32 pad2[246]; +} SVGACOTableDXStreamOutputEntry; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineStreamOutput { + SVGA3dStreamOutputId soid; + uint32 numOutputStreamEntries; + SVGA3dStreamOutputDeclarationEntry decl[SVGA3D_MAX_DX10_STREAMOUT_DECLS]; + uint32 streamOutputStrideInBytes[SVGA3D_DX_MAX_SOTARGETS]; + uint32 rasterizedStream; +} SVGA3dCmdDXDefineStreamOutput; +#pragma pack(pop) #define SVGA3D_DX_SO_NO_RASTERIZED_STREAM 0xFFFFFFFF -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDefineStreamOutputWithMob { - SVGA3dStreamOutputId soid; - uint32 numOutputStreamEntries; - uint32 numOutputStreamStrides; - uint32 streamOutputStrideInBytes[SVGA3D_DX_MAX_SOTARGETS]; - uint32 rasterizedStream; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDefineStreamOutputWithMob; -/* SVGA_3D_CMD_DX_DEFINE_STREAMOUTPUT_WITH_MOB */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXBindStreamOutput { - SVGA3dStreamOutputId soid; - uint32 mobid; - uint32 offsetInBytes; - uint32 sizeInBytes; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXBindStreamOutput; /* SVGA_3D_CMD_DX_BIND_STREAMOUTPUT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXDestroyStreamOutput { - SVGA3dStreamOutputId soid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXDestroyStreamOutput; /* SVGA_3D_CMD_DX_DESTROY_STREAMOUTPUT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetStreamOutput { - SVGA3dStreamOutputId soid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetStreamOutput; /* SVGA_3D_CMD_DX_SET_STREAMOUTPUT */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetMinLOD { - SVGA3dSurfaceId sid; - float minLOD; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetMinLOD; /* SVGA_3D_CMD_DX_SET_MIN_LOD */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint64 value; - uint32 mobId; - uint32 mobOffset; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXMobFence64; /* SVGA_3D_CMD_DX_MOB_FENCE_64 */ +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDefineStreamOutputWithMob { + SVGA3dStreamOutputId soid; + uint32 numOutputStreamEntries; + uint32 numOutputStreamStrides; + uint32 streamOutputStrideInBytes[SVGA3D_DX_MAX_SOTARGETS]; + uint32 rasterizedStream; +} SVGA3dCmdDXDefineStreamOutputWithMob; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXBindStreamOutput { + SVGA3dStreamOutputId soid; + uint32 mobid; + uint32 offsetInBytes; + uint32 sizeInBytes; +} SVGA3dCmdDXBindStreamOutput; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXDestroyStreamOutput { + SVGA3dStreamOutputId soid; +} SVGA3dCmdDXDestroyStreamOutput; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetStreamOutput { + SVGA3dStreamOutputId soid; +} SVGA3dCmdDXSetStreamOutput; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetMinLOD { + SVGA3dSurfaceId sid; + float minLOD; +} SVGA3dCmdDXSetMinLOD; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint64 value; + uint32 mobId; + uint32 mobOffset; +} SVGA3dCmdDXMobFence64; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXSetCOTable { + uint32 cid; + uint32 mobid; + SVGACOTableType type; + uint32 validSizeInBytes; +} SVGA3dCmdDXSetCOTable; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXGrowCOTable { + uint32 cid; + uint32 mobid; + SVGACOTableType type; + uint32 validSizeInBytes; +} SVGA3dCmdDXGrowCOTable; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXReadbackCOTable { + uint32 cid; + SVGACOTableType type; +} SVGA3dCmdDXReadbackCOTable; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXCopyCOTableIntoMob { + uint32 cid; + SVGACOTableType type; + uint32 mobid; +} SVGA3dCmdDXCopyCOTableIntoMob; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXPredStagingCopy { + SVGA3dSurfaceId dstSid; + SVGA3dSurfaceId srcSid; + uint8 readback; + uint8 unsynchronized; + uint8 mustBeZero[2]; + +} SVGA3dCmdDXPredStagingCopy; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCmdDXStagingCopy { + SVGA3dSurfaceId dstSid; + SVGA3dSurfaceId srcSid; + uint8 readback; + uint8 unsynchronized; + uint8 mustBeZero[2]; + +} SVGA3dCmdDXStagingCopy; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCOTableData { + uint32 mobid; +} SVGA3dCOTableData; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dBufferBinding { + uint32 bufferId; + uint32 stride; + uint32 offset; +} SVGA3dBufferBinding; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dConstantBufferBinding { + uint32 sid; + uint32 offsetInBytes; + uint32 sizeInBytes; +} SVGA3dConstantBufferBinding; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGADXInputAssemblyMobFormat { + uint32 layoutId; + SVGA3dBufferBinding vertexBuffers[SVGA3D_DX_MAX_VERTEXBUFFERS]; + uint32 indexBufferSid; + uint32 pad; + uint32 indexBufferOffset; + uint32 indexBufferFormat; + uint32 topology; +} SVGADXInputAssemblyMobFormat; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGADXContextMobFormat { + SVGADXInputAssemblyMobFormat inputAssembly; + + struct { + uint32 blendStateId; + uint32 blendFactor[4]; + uint32 sampleMask; + uint32 depthStencilStateId; + uint32 stencilRef; + uint32 rasterizerStateId; + uint32 depthStencilViewId; + uint32 renderTargetViewIds[SVGA3D_DX_MAX_RENDER_TARGETS]; + } renderState; + + uint32 pad0[8]; + + struct { + uint32 targets[SVGA3D_DX_MAX_SOTARGETS]; + uint32 soid; + } streamOut; + + uint32 pad1[10]; + + uint32 uavSpliceIndex; + + uint8 numViewports; + uint8 numScissorRects; + uint16 pad2[1]; + + uint32 pad3[3]; + + SVGA3dViewport viewports[SVGA3D_DX_MAX_VIEWPORTS]; + uint32 pad4[32]; + + SVGASignedRect scissorRects[SVGA3D_DX_MAX_SCISSORRECTS]; + uint32 pad5[64]; + + struct { + uint32 queryID; + uint32 value; + } predication; + + SVGAMobId shaderIfaceMobid; + uint32 shaderIfaceOffset; + struct { + uint32 shaderId; + SVGA3dConstantBufferBinding + constantBuffers[SVGA3D_DX_MAX_CONSTBUFFERS]; + uint32 shaderResources[SVGA3D_DX_MAX_SRVIEWS]; + uint32 samplers[SVGA3D_DX_MAX_SAMPLERS]; + } shaderState[SVGA3D_NUM_SHADERTYPE]; + uint32 pad6[26]; + + SVGA3dQueryId queryID[SVGA3D_MAX_QUERY]; + + SVGA3dCOTableData cotables[SVGA_COTABLE_MAX]; + + uint32 pad7[64]; + + uint32 uaViewIds[SVGA3D_DX11_1_MAX_UAVIEWS]; + uint32 csuaViewIds[SVGA3D_DX11_1_MAX_UAVIEWS]; + + uint32 pad8[188]; +} SVGADXContextMobFormat; +#pragma pack(pop) -/* - * SVGA3dCmdSetCOTable -- - * - * This command allows the guest to bind a mob to a context-object table. - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXSetCOTable { - uint32 cid; - uint32 mobid; - SVGACOTableType type; - uint32 validSizeInBytes; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXSetCOTable; /* SVGA_3D_CMD_DX_SET_COTABLE */ +#define SVGA3D_DX_MAX_CLASS_INSTANCES_PADDED 256 -/* - * Guests using SVGA_3D_CMD_DX_GROW_COTABLE are promising that - * the new COTable contains the same contents as the old one, except possibly - * for some new invalid entries at the end. - * - * If there is an old cotable mob bound, it also has to still be valid. - * - * (Otherwise, guests should use the DXSetCOTableBase command.) - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXGrowCOTable { - uint32 cid; - uint32 mobid; - SVGACOTableType type; - uint32 validSizeInBytes; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXGrowCOTable; /* SVGA_3D_CMD_DX_GROW_COTABLE */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXReadbackCOTable { - uint32 cid; - SVGACOTableType type; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXReadbackCOTable; /* SVGA_3D_CMD_DX_READBACK_COTABLE */ - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCOTableData { - uint32 mobid; -} -#include "vmware_pack_end.h" -SVGA3dCOTableData; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dBufferBinding { - uint32 bufferId; - uint32 stride; - uint32 offset; -} -#include "vmware_pack_end.h" -SVGA3dBufferBinding; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dConstantBufferBinding { - uint32 sid; - uint32 offsetInBytes; - uint32 sizeInBytes; -} -#include "vmware_pack_end.h" -SVGA3dConstantBufferBinding; - -typedef -#include "vmware_pack_begin.h" -struct SVGADXInputAssemblyMobFormat { - uint32 layoutId; - SVGA3dBufferBinding vertexBuffers[SVGA3D_DX_MAX_VERTEXBUFFERS]; - uint32 indexBufferSid; - uint32 pad; - uint32 indexBufferOffset; - uint32 indexBufferFormat; - uint32 topology; -} -#include "vmware_pack_end.h" -SVGADXInputAssemblyMobFormat; - -typedef -#include "vmware_pack_begin.h" -struct SVGADXContextMobFormat { - SVGADXInputAssemblyMobFormat inputAssembly; - - struct { - uint32 blendStateId; - uint32 blendFactor[4]; - uint32 sampleMask; - uint32 depthStencilStateId; - uint32 stencilRef; - uint32 rasterizerStateId; - uint32 depthStencilViewId; - uint32 renderTargetViewIds[SVGA3D_MAX_SIMULTANEOUS_RENDER_TARGETS]; - } renderState; - - uint32 pad0[8]; - - struct { - uint32 targets[SVGA3D_DX_MAX_SOTARGETS]; - uint32 soid; - } streamOut; - - uint32 pad1[10]; - - uint32 uavSpliceIndex; - - uint8 numViewports; - uint8 numScissorRects; - uint16 pad2[1]; - - uint32 pad3[3]; - - SVGA3dViewport viewports[SVGA3D_DX_MAX_VIEWPORTS]; - uint32 pad4[32]; - - SVGASignedRect scissorRects[SVGA3D_DX_MAX_SCISSORRECTS]; - uint32 pad5[64]; - - struct { - uint32 queryID; - uint32 value; - } predication; - - SVGAMobId shaderIfaceMobid; - uint32 shaderIfaceOffset; - struct { - uint32 shaderId; - SVGA3dConstantBufferBinding constantBuffers[SVGA3D_DX_MAX_CONSTBUFFERS]; - uint32 shaderResources[SVGA3D_DX_MAX_SRVIEWS]; - uint32 samplers[SVGA3D_DX_MAX_SAMPLERS]; - } shaderState[SVGA3D_NUM_SHADERTYPE]; - uint32 pad6[26]; - - SVGA3dQueryId queryID[SVGA3D_MAX_QUERY]; - - SVGA3dCOTableData cotables[SVGA_COTABLE_MAX]; - - uint32 pad7[64]; - - uint32 uaViewIds[SVGA3D_DX11_1_MAX_UAVIEWS]; - uint32 csuaViewIds[SVGA3D_DX11_1_MAX_UAVIEWS]; - - uint32 pad8[188]; -} -#include "vmware_pack_end.h" -SVGADXContextMobFormat; +#pragma pack(push, 1) +typedef struct SVGADXShaderIfaceMobFormat { + struct { + uint32 numClassInstances; + uint32 iface[SVGA3D_DX_MAX_CLASS_INSTANCES_PADDED]; + SVGA3dIfaceData data[SVGA3D_DX_MAX_CLASS_INSTANCES_PADDED]; + } shaderIfaceState[SVGA3D_NUM_SHADERTYPE]; -/* - * There is conflicting documentation on max class instances (253 vs 256). The - * lower value is the one used throughout the device, but since mob format is - * more involved to increase if needed, conservatively use the higher one here. - */ -#define SVGA3D_DX_MAX_CLASS_INSTANCES_PADDED 256 + uint32 pad0[1018]; +} SVGADXShaderIfaceMobFormat; +#pragma pack(pop) -typedef -#include "vmware_pack_begin.h" -struct SVGADXShaderIfaceMobFormat { - struct { - uint32 numClassInstances; - uint32 iface[SVGA3D_DX_MAX_CLASS_INSTANCES_PADDED]; - SVGA3dIfaceData data[SVGA3D_DX_MAX_CLASS_INSTANCES_PADDED]; - } shaderIfaceState[SVGA3D_NUM_SHADERTYPE]; - - uint32 pad0[1018]; -} -#include "vmware_pack_end.h" -SVGADXShaderIfaceMobFormat; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCmdDXTempSetContext { - uint32 dxcid; -} -#include "vmware_pack_end.h" -SVGA3dCmdDXTempSetContext; /* SVGA_3D_CMD_DX_TEMP_SET_CONTEXT */ - -#endif /* _SVGA3D_DX_H_ */ +#endif diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h index f4375a41b3aa..35494a728c7a 100644 --- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h +++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h @@ -1,6 +1,6 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT */ /********************************************************** - * Copyright 2007-2019 VMware, Inc. + * Copyright 2012-2021 VMware, Inc. + * SPDX-License-Identifier: GPL-2.0 OR MIT * * Permission is hereby granted, free of charge, to any person * obtaining a copy of this software and associated documentation @@ -27,104 +27,59 @@ /* * svga3d_limits.h -- * - * SVGA 3d hardware limits + * SVGA 3d hardware limits */ -#ifndef _SVGA3D_LIMITS_H_ -#define _SVGA3D_LIMITS_H_ -#define INCLUDE_ALLOW_MODULE -#define INCLUDE_ALLOW_USERLEVEL -#define INCLUDE_ALLOW_VMCORE -#include "includeCheck.h" +#ifndef _SVGA3D_LIMITS_H_ +#define _SVGA3D_LIMITS_H_ -#define SVGA3D_NUM_CLIPPLANES 6 -#define SVGA3D_MAX_CONTEXT_IDS 256 -#define SVGA3D_MAX_SURFACE_IDS (32 * 1024) +#define SVGA3D_HB_MAX_CONTEXT_IDS 256 +#define SVGA3D_HB_MAX_SURFACE_IDS (32 * 1024) -/* - * While there are separate bind-points for RenderTargetViews and - * UnorderedAccessViews in a DXContext, there is in fact one shared - * semantic space that the guest-driver can use on any given draw call. - * So there are really only 8 slots that can be spilt up between them, with the - * spliceIndex controlling where the UAV's sit in the collapsed array. - */ -#define SVGA3D_MAX_RENDER_TARGETS 8 -#define SVGA3D_MAX_SIMULTANEOUS_RENDER_TARGETS (SVGA3D_MAX_RENDER_TARGETS) -#define SVGA3D_MAX_UAVIEWS 8 -#define SVGA3D_DX11_1_MAX_UAVIEWS 64 +#define SVGA3D_DX_MAX_RENDER_TARGETS 8 +#define SVGA3D_DX11_MAX_UAVIEWS 8 +#define SVGA3D_DX11_1_MAX_UAVIEWS 64 +#define SVGA3D_MAX_UAVIEWS (SVGA3D_DX11_1_MAX_UAVIEWS) +#define SVGA3D_DX11_MAX_SIMULTANEOUS_RTUAV (SVGA3D_DX11_MAX_UAVIEWS) +#define SVGA3D_DX11_1_MAX_SIMULTANEOUS_RTUAV (SVGA3D_DX11_1_MAX_UAVIEWS) +#define SVGA3D_MAX_SIMULTANEOUS_RTUAV (SVGA3D_MAX_UAVIEWS) -/* - * Maximum canonical size of a surface in host-backed mode (pre-GBObjects). - */ #define SVGA3D_HB_MAX_SURFACE_SIZE MBYTES_2_BYTES(128) -/* - * Maximum ID a shader can be assigned on a given context. - */ -#define SVGA3D_MAX_SHADERIDS 5000 -/* - * Maximum number of shaders of a given type that can be defined - * (including all contexts). - */ -#define SVGA3D_MAX_SIMULTANEOUS_SHADERS 20000 +#define SVGA3D_MAX_SHADERIDS 5000 -#define SVGA3D_NUM_TEXTURE_UNITS 32 -#define SVGA3D_NUM_LIGHTS 8 +#define SVGA3D_MAX_SIMULTANEOUS_SHADERS 20000 -#define SVGA3D_MAX_VIDEOPROCESSOR_SAMPLERS 32 +#define SVGA3D_NUM_TEXTURE_UNITS 32 +#define SVGA3D_NUM_LIGHTS 8 + +#define SVGA3D_MAX_VIDEOPROCESSOR_SAMPLERS 32 -/* - * Maximum size in dwords of shader text the SVGA device will allow. - * Currently 8 MB. - */ #define SVGA3D_MAX_SHADER_MEMORY_BYTES (8 * 1024 * 1024) -#define SVGA3D_MAX_SHADER_MEMORY (SVGA3D_MAX_SHADER_MEMORY_BYTES / \ - sizeof(uint32)) +#define SVGA3D_MAX_SHADER_MEMORY \ + (SVGA3D_MAX_SHADER_MEMORY_BYTES / sizeof(uint32)) -/* - * The maximum value of threadGroupCount in each dimension - */ #define SVGA3D_MAX_SHADER_THREAD_GROUPS 65535 -#define SVGA3D_MAX_CLIP_PLANES 6 +#define SVGA3D_MAX_CLIP_PLANES 6 -/* - * This is the limit to the number of fixed-function texture - * transforms and texture coordinates we can support. It does *not* - * correspond to the number of texture image units (samplers) we - * support! - */ #define SVGA3D_MAX_TEXTURE_COORDS 8 -/* - * Number of faces in a cubemap. - */ #define SVGA3D_MAX_SURFACE_FACES 6 -/* - * Maximum number of array indexes in a GB surface (with DX enabled). - */ #define SVGA3D_SM4_MAX_SURFACE_ARRAYSIZE 512 #define SVGA3D_SM5_MAX_SURFACE_ARRAYSIZE 2048 #define SVGA3D_MAX_SURFACE_ARRAYSIZE SVGA3D_SM5_MAX_SURFACE_ARRAYSIZE -/* - * The maximum number of vertex arrays we're guaranteed to support in - * SVGA_3D_CMD_DRAWPRIMITIVES. - */ -#define SVGA3D_MAX_VERTEX_ARRAYS 32 +#define SVGA3D_MAX_VERTEX_ARRAYS 32 -/* - * The maximum number of primitive ranges we're guaranteed to support - * in SVGA_3D_CMD_DRAWPRIMITIVES. - */ #define SVGA3D_MAX_DRAW_PRIMITIVE_RANGES 32 -/* - * The maximum number of samples that can be contained in a surface. - */ #define SVGA3D_MAX_SAMPLES 8 -#endif /* _SVGA3D_LIMITS_H_ */ +#define SVGA3D_MIN_SBX_DATA_SIZE (GBYTES_2_BYTES(1)) +#define SVGA3D_MAX_SBX_DATA_SIZE (GBYTES_2_BYTES(4)) + +#endif diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h index bdfc404c91e3..988d8509c472 100644 --- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h +++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h @@ -1,6 +1,6 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT */ /********************************************************** * Copyright 1998-2015 VMware, Inc. + * SPDX-License-Identifier: GPL-2.0 OR MIT * * Permission is hereby granted, free of charge, to any person * obtaining a copy of this software and associated documentation @@ -27,17 +27,13 @@ /* * svga3d_reg.h -- * - * SVGA 3d hardware definitions + * SVGA 3d hardware definitions */ -#ifndef _SVGA3D_REG_H_ -#define _SVGA3D_REG_H_ -#define INCLUDE_ALLOW_MODULE -#define INCLUDE_ALLOW_USERLEVEL -#define INCLUDE_ALLOW_VMCORE -#include "includeCheck.h" +#ifndef _SVGA3D_REG_H_ +#define _SVGA3D_REG_H_ #include "svga_reg.h" @@ -47,5 +43,4 @@ #include "svga3d_dx.h" #include "svga3d_devcaps.h" - -#endif /* _SVGA3D_REG_H_ */ +#endif diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h index 127eaf0a0a58..7d98fc48414e 100644 --- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h +++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h @@ -1,1667 +1,1561 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT */ -/************************************************************************** +/********************************************************** + * Copyright 2008-2021 VMware, Inc. + * SPDX-License-Identifier: GPL-2.0 OR MIT * - * Copyright 2008-2015 VMware, Inc., Palo Alto, CA., USA + * Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, + * modify, merge, publish, distribute, sublicense, and/or sell copies + * of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the - * "Software"), to deal in the Software without restriction, including - * without limitation the rights to use, copy, modify, merge, publish, - * distribute, sub license, and/or sell copies of the Software, and to - * permit persons to whom the Software is furnished to do so, subject to - * the following conditions: + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. * - * The above copyright notice and this permission notice (including the - * next paragraph) shall be included in all copies or substantial portions - * of the Software. + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, - * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR - * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE - * USE OR OTHER DEALINGS IN THE SOFTWARE. - * - **************************************************************************/ + **********************************************************/ /* * svga3d_surfacedefs.h -- * - * Surface definitions and inlineable utilities for SVGA3d. + * Surface definitions for SVGA3d. */ + + #ifndef _SVGA3D_SURFACEDEFS_H_ #define _SVGA3D_SURFACEDEFS_H_ -#define INCLUDE_ALLOW_USERLEVEL -#define INCLUDE_ALLOW_MODULE -#include "includeCheck.h" +#include "svga3d_types.h" -#include <linux/kernel.h> -#include <drm/vmwgfx_drm.h> +#ifdef __cplusplus +extern "C" { +#endif -#include "svga3d_reg.h" +struct SVGAUseCaps; -#define surf_size_struct struct drm_vmw_size +#if defined(_WIN32) && !defined(__GNUC__) -/* - * enum svga3d_block_desc - describes generic properties about formats. - */ -enum svga3d_block_desc { - /* Nothing special can be said about this format. */ - SVGA3DBLOCKDESC_NONE = 0, +#define STATIC_CONST __declspec(selectany) extern const +#else +#define STATIC_CONST static const +#endif + +typedef enum SVGA3dBlockDesc { - /* Format contains Blue/U data */ - SVGA3DBLOCKDESC_BLUE = 1 << 0, - SVGA3DBLOCKDESC_W = 1 << 0, - SVGA3DBLOCKDESC_BUMP_L = 1 << 0, + SVGA3DBLOCKDESC_NONE = 0, - /* Format contains Green/V data */ - SVGA3DBLOCKDESC_GREEN = 1 << 1, - SVGA3DBLOCKDESC_V = 1 << 1, + SVGA3DBLOCKDESC_BLUE = 1 << 0, + SVGA3DBLOCKDESC_W = 1 << 0, + SVGA3DBLOCKDESC_BUMP_L = 1 << 0, - /* Format contains Red/W/Luminance data */ - SVGA3DBLOCKDESC_RED = 1 << 2, - SVGA3DBLOCKDESC_U = 1 << 2, - SVGA3DBLOCKDESC_LUMINANCE = 1 << 2, + SVGA3DBLOCKDESC_GREEN = 1 << 1, + SVGA3DBLOCKDESC_V = 1 << 1, - /* Format contains Alpha/Q data */ - SVGA3DBLOCKDESC_ALPHA = 1 << 3, - SVGA3DBLOCKDESC_Q = 1 << 3, + SVGA3DBLOCKDESC_RED = 1 << 2, + SVGA3DBLOCKDESC_U = 1 << 2, + SVGA3DBLOCKDESC_LUMINANCE = 1 << 2, - /* Format is a buffer */ - SVGA3DBLOCKDESC_BUFFER = 1 << 4, + SVGA3DBLOCKDESC_ALPHA = 1 << 3, + SVGA3DBLOCKDESC_Q = 1 << 3, - /* Format is compressed */ - SVGA3DBLOCKDESC_COMPRESSED = 1 << 5, + SVGA3DBLOCKDESC_BUFFER = 1 << 4, - /* Format uses IEEE floating point */ - SVGA3DBLOCKDESC_FP = 1 << 6, + SVGA3DBLOCKDESC_COMPRESSED = 1 << 5, - /* Three separate blocks store data. */ - SVGA3DBLOCKDESC_PLANAR_YUV = 1 << 7, + SVGA3DBLOCKDESC_FP = 1 << 6, + + SVGA3DBLOCKDESC_PLANAR_YUV = 1 << 7, - /* 2 planes of Y, UV, e.g., NV12. */ SVGA3DBLOCKDESC_2PLANAR_YUV = 1 << 8, - /* 3 planes of separate Y, U, V, e.g., YV12. */ SVGA3DBLOCKDESC_3PLANAR_YUV = 1 << 9, - /* Block with a stencil channel */ - SVGA3DBLOCKDESC_STENCIL = 1 << 11, - - /* Typeless format */ - SVGA3DBLOCKDESC_TYPELESS = 1 << 12, - - /* Channels are signed integers */ - SVGA3DBLOCKDESC_SINT = 1 << 13, - - /* Channels are unsigned integers */ - SVGA3DBLOCKDESC_UINT = 1 << 14, - - /* Channels are normalized (when sampling) */ - SVGA3DBLOCKDESC_NORM = 1 << 15, - - /* Channels are in SRGB */ - SVGA3DBLOCKDESC_SRGB = 1 << 16, - - /* Shared exponent */ - SVGA3DBLOCKDESC_EXP = 1 << 17, - - /* Format contains color data. */ - SVGA3DBLOCKDESC_COLOR = 1 << 18, - /* Format contains depth data. */ - SVGA3DBLOCKDESC_DEPTH = 1 << 19, - /* Format contains bump data. */ - SVGA3DBLOCKDESC_BUMP = 1 << 20, - - /* Format contains YUV video data. */ - SVGA3DBLOCKDESC_YUV_VIDEO = 1 << 21, - - /* For mixed unsigned/signed formats. */ - SVGA3DBLOCKDESC_MIXED = 1 << 22, - - /* For distingushing CxV8U8. */ - SVGA3DBLOCKDESC_CX = 1 << 23, - - /* Different compressed format groups. */ - SVGA3DBLOCKDESC_BC1 = 1 << 24, - SVGA3DBLOCKDESC_BC2 = 1 << 25, - SVGA3DBLOCKDESC_BC3 = 1 << 26, - SVGA3DBLOCKDESC_BC4 = 1 << 27, - SVGA3DBLOCKDESC_BC5 = 1 << 28, - SVGA3DBLOCKDESC_BC6H = 1 << 29, - SVGA3DBLOCKDESC_BC7 = 1 << 30, - - SVGA3DBLOCKDESC_A_UINT = SVGA3DBLOCKDESC_ALPHA | - SVGA3DBLOCKDESC_UINT | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_A_UNORM = SVGA3DBLOCKDESC_A_UINT | - SVGA3DBLOCKDESC_NORM, - SVGA3DBLOCKDESC_R_UINT = SVGA3DBLOCKDESC_RED | - SVGA3DBLOCKDESC_UINT | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_R_UNORM = SVGA3DBLOCKDESC_R_UINT | - SVGA3DBLOCKDESC_NORM, - SVGA3DBLOCKDESC_R_SINT = SVGA3DBLOCKDESC_RED | - SVGA3DBLOCKDESC_SINT | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_R_SNORM = SVGA3DBLOCKDESC_R_SINT | - SVGA3DBLOCKDESC_NORM, - SVGA3DBLOCKDESC_G_UINT = SVGA3DBLOCKDESC_GREEN | - SVGA3DBLOCKDESC_UINT | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_RG_UINT = SVGA3DBLOCKDESC_RED | - SVGA3DBLOCKDESC_GREEN | - SVGA3DBLOCKDESC_UINT | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_RG_UNORM = SVGA3DBLOCKDESC_RG_UINT | - SVGA3DBLOCKDESC_NORM, - SVGA3DBLOCKDESC_RG_SINT = SVGA3DBLOCKDESC_RED | - SVGA3DBLOCKDESC_GREEN | - SVGA3DBLOCKDESC_SINT | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_RG_SNORM = SVGA3DBLOCKDESC_RG_SINT | - SVGA3DBLOCKDESC_NORM, - SVGA3DBLOCKDESC_RGB_UINT = SVGA3DBLOCKDESC_RED | - SVGA3DBLOCKDESC_GREEN | - SVGA3DBLOCKDESC_BLUE | - SVGA3DBLOCKDESC_UINT | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_RGB_SINT = SVGA3DBLOCKDESC_RED | - SVGA3DBLOCKDESC_GREEN | - SVGA3DBLOCKDESC_BLUE | - SVGA3DBLOCKDESC_SINT | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_RGB_UNORM = SVGA3DBLOCKDESC_RGB_UINT | - SVGA3DBLOCKDESC_NORM, - SVGA3DBLOCKDESC_RGB_UNORM_SRGB = SVGA3DBLOCKDESC_RGB_UNORM | - SVGA3DBLOCKDESC_SRGB, - SVGA3DBLOCKDESC_RGBA_UINT = SVGA3DBLOCKDESC_RED | - SVGA3DBLOCKDESC_GREEN | - SVGA3DBLOCKDESC_BLUE | - SVGA3DBLOCKDESC_ALPHA | - SVGA3DBLOCKDESC_UINT | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_RGBA_UNORM = SVGA3DBLOCKDESC_RGBA_UINT | - SVGA3DBLOCKDESC_NORM, - SVGA3DBLOCKDESC_RGBA_UNORM_SRGB = SVGA3DBLOCKDESC_RGBA_UNORM | - SVGA3DBLOCKDESC_SRGB, - SVGA3DBLOCKDESC_RGBA_SINT = SVGA3DBLOCKDESC_RED | - SVGA3DBLOCKDESC_GREEN | - SVGA3DBLOCKDESC_BLUE | - SVGA3DBLOCKDESC_ALPHA | - SVGA3DBLOCKDESC_SINT | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_RGBA_SNORM = SVGA3DBLOCKDESC_RGBA_SINT | - SVGA3DBLOCKDESC_NORM, - SVGA3DBLOCKDESC_RGBA_FP = SVGA3DBLOCKDESC_RED | - SVGA3DBLOCKDESC_GREEN | - SVGA3DBLOCKDESC_BLUE | - SVGA3DBLOCKDESC_ALPHA | - SVGA3DBLOCKDESC_FP | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_UV = SVGA3DBLOCKDESC_U | - SVGA3DBLOCKDESC_V | - SVGA3DBLOCKDESC_BUMP, - SVGA3DBLOCKDESC_UVL = SVGA3DBLOCKDESC_UV | - SVGA3DBLOCKDESC_BUMP_L | - SVGA3DBLOCKDESC_MIXED | - SVGA3DBLOCKDESC_BUMP, - SVGA3DBLOCKDESC_UVW = SVGA3DBLOCKDESC_UV | - SVGA3DBLOCKDESC_W | - SVGA3DBLOCKDESC_BUMP, - SVGA3DBLOCKDESC_UVWA = SVGA3DBLOCKDESC_UVW | - SVGA3DBLOCKDESC_ALPHA | - SVGA3DBLOCKDESC_MIXED | - SVGA3DBLOCKDESC_BUMP, - SVGA3DBLOCKDESC_UVWQ = SVGA3DBLOCKDESC_U | - SVGA3DBLOCKDESC_V | - SVGA3DBLOCKDESC_W | - SVGA3DBLOCKDESC_Q | - SVGA3DBLOCKDESC_BUMP, - SVGA3DBLOCKDESC_L_UNORM = SVGA3DBLOCKDESC_LUMINANCE | - SVGA3DBLOCKDESC_UINT | - SVGA3DBLOCKDESC_NORM | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_LA_UNORM = SVGA3DBLOCKDESC_LUMINANCE | - SVGA3DBLOCKDESC_ALPHA | - SVGA3DBLOCKDESC_UINT | - SVGA3DBLOCKDESC_NORM | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_R_FP = SVGA3DBLOCKDESC_RED | - SVGA3DBLOCKDESC_FP | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_RG_FP = SVGA3DBLOCKDESC_R_FP | - SVGA3DBLOCKDESC_GREEN | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_RGB_FP = SVGA3DBLOCKDESC_RG_FP | - SVGA3DBLOCKDESC_BLUE | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_YUV = SVGA3DBLOCKDESC_YUV_VIDEO | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_AYUV = SVGA3DBLOCKDESC_ALPHA | - SVGA3DBLOCKDESC_YUV_VIDEO | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_RGB_EXP = SVGA3DBLOCKDESC_RED | - SVGA3DBLOCKDESC_GREEN | - SVGA3DBLOCKDESC_BLUE | - SVGA3DBLOCKDESC_EXP | - SVGA3DBLOCKDESC_COLOR, - - SVGA3DBLOCKDESC_COMP_TYPELESS = SVGA3DBLOCKDESC_COMPRESSED | - SVGA3DBLOCKDESC_TYPELESS, - SVGA3DBLOCKDESC_COMP_UNORM = SVGA3DBLOCKDESC_COMPRESSED | - SVGA3DBLOCKDESC_UINT | - SVGA3DBLOCKDESC_NORM | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_COMP_SNORM = SVGA3DBLOCKDESC_COMPRESSED | - SVGA3DBLOCKDESC_SINT | - SVGA3DBLOCKDESC_NORM | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_COMP_UNORM | - SVGA3DBLOCKDESC_SRGB, - SVGA3DBLOCKDESC_BC1_COMP_TYPELESS = SVGA3DBLOCKDESC_BC1 | - SVGA3DBLOCKDESC_COMP_TYPELESS, - SVGA3DBLOCKDESC_BC1_COMP_UNORM = SVGA3DBLOCKDESC_BC1 | - SVGA3DBLOCKDESC_COMP_UNORM, - SVGA3DBLOCKDESC_BC1_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC1_COMP_UNORM | - SVGA3DBLOCKDESC_SRGB, - SVGA3DBLOCKDESC_BC2_COMP_TYPELESS = SVGA3DBLOCKDESC_BC2 | - SVGA3DBLOCKDESC_COMP_TYPELESS, - SVGA3DBLOCKDESC_BC2_COMP_UNORM = SVGA3DBLOCKDESC_BC2 | - SVGA3DBLOCKDESC_COMP_UNORM, - SVGA3DBLOCKDESC_BC2_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC2_COMP_UNORM | - SVGA3DBLOCKDESC_SRGB, - SVGA3DBLOCKDESC_BC3_COMP_TYPELESS = SVGA3DBLOCKDESC_BC3 | - SVGA3DBLOCKDESC_COMP_TYPELESS, - SVGA3DBLOCKDESC_BC3_COMP_UNORM = SVGA3DBLOCKDESC_BC3 | - SVGA3DBLOCKDESC_COMP_UNORM, - SVGA3DBLOCKDESC_BC3_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC3_COMP_UNORM | - SVGA3DBLOCKDESC_SRGB, - SVGA3DBLOCKDESC_BC4_COMP_TYPELESS = SVGA3DBLOCKDESC_BC4 | - SVGA3DBLOCKDESC_COMP_TYPELESS, - SVGA3DBLOCKDESC_BC4_COMP_UNORM = SVGA3DBLOCKDESC_BC4 | - SVGA3DBLOCKDESC_COMP_UNORM, - SVGA3DBLOCKDESC_BC4_COMP_SNORM = SVGA3DBLOCKDESC_BC4 | - SVGA3DBLOCKDESC_COMP_SNORM, - SVGA3DBLOCKDESC_BC5_COMP_TYPELESS = SVGA3DBLOCKDESC_BC5 | - SVGA3DBLOCKDESC_COMP_TYPELESS, - SVGA3DBLOCKDESC_BC5_COMP_UNORM = SVGA3DBLOCKDESC_BC5 | - SVGA3DBLOCKDESC_COMP_UNORM, - SVGA3DBLOCKDESC_BC5_COMP_SNORM = SVGA3DBLOCKDESC_BC5 | - SVGA3DBLOCKDESC_COMP_SNORM, - SVGA3DBLOCKDESC_BC6H_COMP_TYPELESS = SVGA3DBLOCKDESC_BC6H | - SVGA3DBLOCKDESC_COMP_TYPELESS, - SVGA3DBLOCKDESC_BC6H_COMP_UF16 = SVGA3DBLOCKDESC_BC6H | - SVGA3DBLOCKDESC_COMPRESSED, - SVGA3DBLOCKDESC_BC6H_COMP_SF16 = SVGA3DBLOCKDESC_BC6H | - SVGA3DBLOCKDESC_COMPRESSED, - SVGA3DBLOCKDESC_BC7_COMP_TYPELESS = SVGA3DBLOCKDESC_BC7 | - SVGA3DBLOCKDESC_COMP_TYPELESS, - SVGA3DBLOCKDESC_BC7_COMP_UNORM = SVGA3DBLOCKDESC_BC7 | - SVGA3DBLOCKDESC_COMP_UNORM, - SVGA3DBLOCKDESC_BC7_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC7_COMP_UNORM | - SVGA3DBLOCKDESC_SRGB, - - SVGA3DBLOCKDESC_NV12 = SVGA3DBLOCKDESC_YUV_VIDEO | - SVGA3DBLOCKDESC_PLANAR_YUV | - SVGA3DBLOCKDESC_2PLANAR_YUV | - SVGA3DBLOCKDESC_COLOR, - SVGA3DBLOCKDESC_YV12 = SVGA3DBLOCKDESC_YUV_VIDEO | - SVGA3DBLOCKDESC_PLANAR_YUV | - SVGA3DBLOCKDESC_3PLANAR_YUV | - SVGA3DBLOCKDESC_COLOR, - - SVGA3DBLOCKDESC_DEPTH_UINT = SVGA3DBLOCKDESC_DEPTH | - SVGA3DBLOCKDESC_UINT, - SVGA3DBLOCKDESC_DEPTH_UNORM = SVGA3DBLOCKDESC_DEPTH_UINT | - SVGA3DBLOCKDESC_NORM, - SVGA3DBLOCKDESC_DS = SVGA3DBLOCKDESC_DEPTH | - SVGA3DBLOCKDESC_STENCIL, - SVGA3DBLOCKDESC_DS_UINT = SVGA3DBLOCKDESC_DEPTH | - SVGA3DBLOCKDESC_STENCIL | - SVGA3DBLOCKDESC_UINT, - SVGA3DBLOCKDESC_DS_UNORM = SVGA3DBLOCKDESC_DS_UINT | - SVGA3DBLOCKDESC_NORM, - SVGA3DBLOCKDESC_DEPTH_FP = SVGA3DBLOCKDESC_DEPTH | - SVGA3DBLOCKDESC_FP, - - SVGA3DBLOCKDESC_UV_UINT = SVGA3DBLOCKDESC_UV | - SVGA3DBLOCKDESC_UINT, - SVGA3DBLOCKDESC_UV_SNORM = SVGA3DBLOCKDESC_UV | - SVGA3DBLOCKDESC_SINT | - SVGA3DBLOCKDESC_NORM, - SVGA3DBLOCKDESC_UVCX_SNORM = SVGA3DBLOCKDESC_UV_SNORM | - SVGA3DBLOCKDESC_CX, + SVGA3DBLOCKDESC_STENCIL = 1 << 11, + + SVGA3DBLOCKDESC_TYPELESS = 1 << 12, + + SVGA3DBLOCKDESC_SINT = 1 << 13, + + SVGA3DBLOCKDESC_UINT = 1 << 14, + + SVGA3DBLOCKDESC_NORM = 1 << 15, + + SVGA3DBLOCKDESC_SRGB = 1 << 16, + + SVGA3DBLOCKDESC_EXP = 1 << 17, + + SVGA3DBLOCKDESC_COLOR = 1 << 18, + + SVGA3DBLOCKDESC_DEPTH = 1 << 19, + + SVGA3DBLOCKDESC_BUMP = 1 << 20, + + SVGA3DBLOCKDESC_YUV_VIDEO = 1 << 21, + + SVGA3DBLOCKDESC_MIXED = 1 << 22, + + SVGA3DBLOCKDESC_CX = 1 << 23, + + SVGA3DBLOCKDESC_BC1 = 1 << 24, + SVGA3DBLOCKDESC_BC2 = 1 << 25, + SVGA3DBLOCKDESC_BC3 = 1 << 26, + SVGA3DBLOCKDESC_BC4 = 1 << 27, + SVGA3DBLOCKDESC_BC5 = 1 << 28, + SVGA3DBLOCKDESC_BC6H = 1 << 29, + SVGA3DBLOCKDESC_BC7 = 1 << 30, + SVGA3DBLOCKDESC_COMPRESSED_MASK = + SVGA3DBLOCKDESC_BC1 | SVGA3DBLOCKDESC_BC2 | + SVGA3DBLOCKDESC_BC3 | SVGA3DBLOCKDESC_BC4 | + SVGA3DBLOCKDESC_BC5 | SVGA3DBLOCKDESC_BC6H | + SVGA3DBLOCKDESC_BC7, + + SVGA3DBLOCKDESC_A_UINT = SVGA3DBLOCKDESC_ALPHA | SVGA3DBLOCKDESC_UINT | + SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_A_UNORM = SVGA3DBLOCKDESC_A_UINT | SVGA3DBLOCKDESC_NORM, + SVGA3DBLOCKDESC_R_UINT = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_UINT | + SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_R_UNORM = SVGA3DBLOCKDESC_R_UINT | SVGA3DBLOCKDESC_NORM, + SVGA3DBLOCKDESC_R_SINT = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_SINT | + SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_R_SNORM = SVGA3DBLOCKDESC_R_SINT | SVGA3DBLOCKDESC_NORM, + SVGA3DBLOCKDESC_G_UINT = SVGA3DBLOCKDESC_GREEN | SVGA3DBLOCKDESC_UINT | + SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_RG_UINT = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN | + SVGA3DBLOCKDESC_UINT | SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_RG_UNORM = + SVGA3DBLOCKDESC_RG_UINT | SVGA3DBLOCKDESC_NORM, + SVGA3DBLOCKDESC_RG_SINT = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN | + SVGA3DBLOCKDESC_SINT | SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_RG_SNORM = + SVGA3DBLOCKDESC_RG_SINT | SVGA3DBLOCKDESC_NORM, + SVGA3DBLOCKDESC_RGB_UINT = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN | + SVGA3DBLOCKDESC_BLUE | SVGA3DBLOCKDESC_UINT | + SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_RGB_SINT = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN | + SVGA3DBLOCKDESC_BLUE | SVGA3DBLOCKDESC_SINT | + SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_RGB_UNORM = + SVGA3DBLOCKDESC_RGB_UINT | SVGA3DBLOCKDESC_NORM, + SVGA3DBLOCKDESC_RGB_UNORM_SRGB = + SVGA3DBLOCKDESC_RGB_UNORM | SVGA3DBLOCKDESC_SRGB, + SVGA3DBLOCKDESC_RGBA_UINT = + SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN | + SVGA3DBLOCKDESC_BLUE | SVGA3DBLOCKDESC_ALPHA | + SVGA3DBLOCKDESC_UINT | SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_RGBA_UNORM = + SVGA3DBLOCKDESC_RGBA_UINT | SVGA3DBLOCKDESC_NORM, + SVGA3DBLOCKDESC_RGBA_UNORM_SRGB = + SVGA3DBLOCKDESC_RGBA_UNORM | SVGA3DBLOCKDESC_SRGB, + SVGA3DBLOCKDESC_RGBA_SINT = + SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN | + SVGA3DBLOCKDESC_BLUE | SVGA3DBLOCKDESC_ALPHA | + SVGA3DBLOCKDESC_SINT | SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_RGBA_SNORM = + SVGA3DBLOCKDESC_RGBA_SINT | SVGA3DBLOCKDESC_NORM, + SVGA3DBLOCKDESC_RGBA_FP = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN | + SVGA3DBLOCKDESC_BLUE | SVGA3DBLOCKDESC_ALPHA | + SVGA3DBLOCKDESC_FP | SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_UV = + SVGA3DBLOCKDESC_U | SVGA3DBLOCKDESC_V | SVGA3DBLOCKDESC_BUMP, + SVGA3DBLOCKDESC_UVL = SVGA3DBLOCKDESC_UV | SVGA3DBLOCKDESC_BUMP_L | + SVGA3DBLOCKDESC_MIXED | SVGA3DBLOCKDESC_BUMP, + SVGA3DBLOCKDESC_UVW = + SVGA3DBLOCKDESC_UV | SVGA3DBLOCKDESC_W | SVGA3DBLOCKDESC_BUMP, + SVGA3DBLOCKDESC_UVWA = SVGA3DBLOCKDESC_UVW | SVGA3DBLOCKDESC_ALPHA | + SVGA3DBLOCKDESC_MIXED | SVGA3DBLOCKDESC_BUMP, + SVGA3DBLOCKDESC_UVWQ = SVGA3DBLOCKDESC_U | SVGA3DBLOCKDESC_V | + SVGA3DBLOCKDESC_W | SVGA3DBLOCKDESC_Q | + SVGA3DBLOCKDESC_BUMP, + SVGA3DBLOCKDESC_L_UNORM = SVGA3DBLOCKDESC_LUMINANCE | + SVGA3DBLOCKDESC_UINT | SVGA3DBLOCKDESC_NORM | + SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_LA_UNORM = SVGA3DBLOCKDESC_LUMINANCE | + SVGA3DBLOCKDESC_ALPHA | + SVGA3DBLOCKDESC_UINT | SVGA3DBLOCKDESC_NORM | + SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_R_FP = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_FP | + SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_RG_FP = SVGA3DBLOCKDESC_R_FP | SVGA3DBLOCKDESC_GREEN | + SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_RGB_FP = SVGA3DBLOCKDESC_RG_FP | SVGA3DBLOCKDESC_BLUE | + SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_YUV = SVGA3DBLOCKDESC_YUV_VIDEO | SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_AYUV = SVGA3DBLOCKDESC_ALPHA | + SVGA3DBLOCKDESC_YUV_VIDEO | + SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_RGB_EXP = SVGA3DBLOCKDESC_RED | SVGA3DBLOCKDESC_GREEN | + SVGA3DBLOCKDESC_BLUE | SVGA3DBLOCKDESC_EXP | + SVGA3DBLOCKDESC_COLOR, + + SVGA3DBLOCKDESC_COMP_TYPELESS = + SVGA3DBLOCKDESC_COMPRESSED | SVGA3DBLOCKDESC_TYPELESS, + SVGA3DBLOCKDESC_COMP_UNORM = + SVGA3DBLOCKDESC_COMPRESSED | SVGA3DBLOCKDESC_UINT | + SVGA3DBLOCKDESC_NORM | SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_COMP_SNORM = + SVGA3DBLOCKDESC_COMPRESSED | SVGA3DBLOCKDESC_SINT | + SVGA3DBLOCKDESC_NORM | SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_COMP_UNORM_SRGB = + SVGA3DBLOCKDESC_COMP_UNORM | SVGA3DBLOCKDESC_SRGB, + SVGA3DBLOCKDESC_BC1_COMP_TYPELESS = + SVGA3DBLOCKDESC_BC1 | SVGA3DBLOCKDESC_COMP_TYPELESS, + SVGA3DBLOCKDESC_BC1_COMP_UNORM = + SVGA3DBLOCKDESC_BC1 | SVGA3DBLOCKDESC_COMP_UNORM, + SVGA3DBLOCKDESC_BC1_COMP_UNORM_SRGB = + SVGA3DBLOCKDESC_BC1_COMP_UNORM | SVGA3DBLOCKDESC_SRGB, + SVGA3DBLOCKDESC_BC2_COMP_TYPELESS = + SVGA3DBLOCKDESC_BC2 | SVGA3DBLOCKDESC_COMP_TYPELESS, + SVGA3DBLOCKDESC_BC2_COMP_UNORM = + SVGA3DBLOCKDESC_BC2 | SVGA3DBLOCKDESC_COMP_UNORM, + SVGA3DBLOCKDESC_BC2_COMP_UNORM_SRGB = + SVGA3DBLOCKDESC_BC2_COMP_UNORM | SVGA3DBLOCKDESC_SRGB, + SVGA3DBLOCKDESC_BC3_COMP_TYPELESS = + SVGA3DBLOCKDESC_BC3 | SVGA3DBLOCKDESC_COMP_TYPELESS, + SVGA3DBLOCKDESC_BC3_COMP_UNORM = + SVGA3DBLOCKDESC_BC3 | SVGA3DBLOCKDESC_COMP_UNORM, + SVGA3DBLOCKDESC_BC3_COMP_UNORM_SRGB = + SVGA3DBLOCKDESC_BC3_COMP_UNORM | SVGA3DBLOCKDESC_SRGB, + SVGA3DBLOCKDESC_BC4_COMP_TYPELESS = + SVGA3DBLOCKDESC_BC4 | SVGA3DBLOCKDESC_COMP_TYPELESS, + SVGA3DBLOCKDESC_BC4_COMP_UNORM = + SVGA3DBLOCKDESC_BC4 | SVGA3DBLOCKDESC_COMP_UNORM, + SVGA3DBLOCKDESC_BC4_COMP_SNORM = + SVGA3DBLOCKDESC_BC4 | SVGA3DBLOCKDESC_COMP_SNORM, + SVGA3DBLOCKDESC_BC5_COMP_TYPELESS = + SVGA3DBLOCKDESC_BC5 | SVGA3DBLOCKDESC_COMP_TYPELESS, + SVGA3DBLOCKDESC_BC5_COMP_UNORM = + SVGA3DBLOCKDESC_BC5 | SVGA3DBLOCKDESC_COMP_UNORM, + SVGA3DBLOCKDESC_BC5_COMP_SNORM = + SVGA3DBLOCKDESC_BC5 | SVGA3DBLOCKDESC_COMP_SNORM, + SVGA3DBLOCKDESC_BC6H_COMP_TYPELESS = + SVGA3DBLOCKDESC_BC6H | SVGA3DBLOCKDESC_COMP_TYPELESS, + SVGA3DBLOCKDESC_BC6H_COMP_UF16 = + SVGA3DBLOCKDESC_BC6H | SVGA3DBLOCKDESC_COMPRESSED, + SVGA3DBLOCKDESC_BC6H_COMP_SF16 = + SVGA3DBLOCKDESC_BC6H | SVGA3DBLOCKDESC_COMPRESSED, + SVGA3DBLOCKDESC_BC7_COMP_TYPELESS = + SVGA3DBLOCKDESC_BC7 | SVGA3DBLOCKDESC_COMP_TYPELESS, + SVGA3DBLOCKDESC_BC7_COMP_UNORM = + SVGA3DBLOCKDESC_BC7 | SVGA3DBLOCKDESC_COMP_UNORM, + SVGA3DBLOCKDESC_BC7_COMP_UNORM_SRGB = + SVGA3DBLOCKDESC_BC7_COMP_UNORM | SVGA3DBLOCKDESC_SRGB, + + SVGA3DBLOCKDESC_NV12 = + SVGA3DBLOCKDESC_YUV_VIDEO | SVGA3DBLOCKDESC_PLANAR_YUV | + SVGA3DBLOCKDESC_2PLANAR_YUV | SVGA3DBLOCKDESC_COLOR, + SVGA3DBLOCKDESC_YV12 = + SVGA3DBLOCKDESC_YUV_VIDEO | SVGA3DBLOCKDESC_PLANAR_YUV | + SVGA3DBLOCKDESC_3PLANAR_YUV | SVGA3DBLOCKDESC_COLOR, + + SVGA3DBLOCKDESC_DEPTH_UINT = + SVGA3DBLOCKDESC_DEPTH | SVGA3DBLOCKDESC_UINT, + SVGA3DBLOCKDESC_DEPTH_UNORM = + SVGA3DBLOCKDESC_DEPTH_UINT | SVGA3DBLOCKDESC_NORM, + SVGA3DBLOCKDESC_DS = SVGA3DBLOCKDESC_DEPTH | SVGA3DBLOCKDESC_STENCIL, + SVGA3DBLOCKDESC_DS_UINT = SVGA3DBLOCKDESC_DEPTH | + SVGA3DBLOCKDESC_STENCIL | + SVGA3DBLOCKDESC_UINT, + SVGA3DBLOCKDESC_DS_UNORM = + SVGA3DBLOCKDESC_DS_UINT | SVGA3DBLOCKDESC_NORM, + SVGA3DBLOCKDESC_DEPTH_FP = SVGA3DBLOCKDESC_DEPTH | SVGA3DBLOCKDESC_FP, + + SVGA3DBLOCKDESC_UV_UINT = SVGA3DBLOCKDESC_UV | SVGA3DBLOCKDESC_UINT, + SVGA3DBLOCKDESC_UV_SNORM = SVGA3DBLOCKDESC_UV | SVGA3DBLOCKDESC_SINT | + SVGA3DBLOCKDESC_NORM, + SVGA3DBLOCKDESC_UVCX_SNORM = + SVGA3DBLOCKDESC_UV_SNORM | SVGA3DBLOCKDESC_CX, SVGA3DBLOCKDESC_UVWQ_SNORM = SVGA3DBLOCKDESC_UVWQ | SVGA3DBLOCKDESC_SINT | SVGA3DBLOCKDESC_NORM, -}; +} SVGA3dBlockDesc; -struct svga3d_channel_def { +typedef struct SVGA3dChannelDef { union { - u8 blue; - u8 w_bump; - u8 l_bump; - u8 uv_video; - u8 u_video; + uint8 blue; + uint8 w_bump; + uint8 l_bump; + uint8 uv_video; + uint8 u_video; }; union { - u8 green; - u8 stencil; - u8 v_bump; - u8 v_video; + uint8 green; + uint8 stencil; + uint8 v_bump; + uint8 v_video; }; union { - u8 red; - u8 u_bump; - u8 luminance; - u8 y_video; - u8 depth; - u8 data; + uint8 red; + uint8 u_bump; + uint8 luminance; + uint8 y_video; + uint8 depth; + uint8 data; }; union { - u8 alpha; - u8 q_bump; - u8 exp; + uint8 alpha; + uint8 q_bump; + uint8 exp; }; -}; +} SVGA3dChannelDef; -/* - * struct svga3d_surface_desc - describes the actual pixel data. - * - * @format: Format - * @block_desc: Block description - * @block_size: Dimensions in pixels of a block - * @bytes_per_block: Size of block in bytes - * @pitch_bytes_per_block: Size of a block in bytes for purposes of pitch - * @bit_depth: Channel bit depths - * @bit_offset: Channel bit masks (in bits offset from the start of the pointer) - */ -struct svga3d_surface_desc { +typedef struct SVGA3dSurfaceDesc { SVGA3dSurfaceFormat format; - enum svga3d_block_desc block_desc; - - surf_size_struct block_size; - u32 bytes_per_block; - u32 pitch_bytes_per_block; - - struct svga3d_channel_def bit_depth; - struct svga3d_channel_def bit_offset; -}; - -static const struct svga3d_surface_desc svga3d_surface_descs[] = { - {SVGA3D_FORMAT_INVALID, SVGA3DBLOCKDESC_NONE, - {1, 1, 1}, 0, 0, - {{0}, {0}, {0}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_X8R8G8B8, SVGA3DBLOCKDESC_RGB_UNORM, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {0}}, - {{0}, {8}, {16}, {24}}}, - - {SVGA3D_A8R8G8B8, SVGA3DBLOCKDESC_RGBA_UNORM, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {8}}, - {{0}, {8}, {16}, {24}}}, - - {SVGA3D_R5G6B5, SVGA3DBLOCKDESC_RGB_UNORM, - {1, 1, 1}, 2, 2, - {{5}, {6}, {5}, {0}}, - {{0}, {5}, {11}, {0}}}, - - {SVGA3D_X1R5G5B5, SVGA3DBLOCKDESC_RGB_UNORM, - {1, 1, 1}, 2, 2, - {{5}, {5}, {5}, {0}}, - {{0}, {5}, {10}, {0}}}, - - {SVGA3D_A1R5G5B5, SVGA3DBLOCKDESC_RGBA_UNORM, - {1, 1, 1}, 2, 2, - {{5}, {5}, {5}, {1}}, - {{0}, {5}, {10}, {15}}}, - - {SVGA3D_A4R4G4B4, SVGA3DBLOCKDESC_RGBA_UNORM, - {1, 1, 1}, 2, 2, - {{4}, {4}, {4}, {4}}, - {{0}, {4}, {8}, {12}}}, - - {SVGA3D_Z_D32, SVGA3DBLOCKDESC_DEPTH_UNORM, - {1, 1, 1}, 4, 4, - {{0}, {0}, {32}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_Z_D16, SVGA3DBLOCKDESC_DEPTH_UNORM, - {1, 1, 1}, 2, 2, - {{0}, {0}, {16}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_Z_D24S8, SVGA3DBLOCKDESC_DS_UNORM, - {1, 1, 1}, 4, 4, - {{0}, {8}, {24}, {0}}, - {{0}, {0}, {8}, {0}}}, - - {SVGA3D_Z_D15S1, SVGA3DBLOCKDESC_DS_UNORM, - {1, 1, 1}, 2, 2, - {{0}, {1}, {15}, {0}}, - {{0}, {0}, {1}, {0}}}, - - {SVGA3D_LUMINANCE8, SVGA3DBLOCKDESC_L_UNORM, - {1, 1, 1}, 1, 1, - {{0}, {0}, {8}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_LUMINANCE4_ALPHA4, SVGA3DBLOCKDESC_LA_UNORM, - {1, 1, 1}, 1, 1, - {{0}, {0}, {4}, {4}}, - {{0}, {0}, {0}, {4}}}, - - {SVGA3D_LUMINANCE16, SVGA3DBLOCKDESC_L_UNORM, - {1, 1, 1}, 2, 2, - {{0}, {0}, {16}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_LUMINANCE8_ALPHA8, SVGA3DBLOCKDESC_LA_UNORM, - {1, 1, 1}, 2, 2, - {{0}, {0}, {8}, {8}}, - {{0}, {0}, {0}, {8}}}, - - {SVGA3D_DXT1, SVGA3DBLOCKDESC_BC1_COMP_UNORM, - {4, 4, 1}, 8, 8, - {{0}, {0}, {64}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_DXT2, SVGA3DBLOCKDESC_BC2_COMP_UNORM, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_DXT3, SVGA3DBLOCKDESC_BC2_COMP_UNORM, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_DXT4, SVGA3DBLOCKDESC_BC3_COMP_UNORM, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_DXT5, SVGA3DBLOCKDESC_BC3_COMP_UNORM, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BUMPU8V8, SVGA3DBLOCKDESC_UV_SNORM, - {1, 1, 1}, 2, 2, - {{0}, {8}, {8}, {0}}, - {{0}, {8}, {0}, {0}}}, - - {SVGA3D_BUMPL6V5U5, SVGA3DBLOCKDESC_UVL, - {1, 1, 1}, 2, 2, - {{6}, {5}, {5}, {0}}, - {{10}, {5}, {0}, {0}}}, - - {SVGA3D_BUMPX8L8V8U8, SVGA3DBLOCKDESC_UVL, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {0}}, - {{16}, {8}, {0}, {0}}}, - - {SVGA3D_FORMAT_DEAD1, SVGA3DBLOCKDESC_NONE, - {1, 1, 1}, 3, 3, - {{8}, {8}, {8}, {0}}, - {{16}, {8}, {0}, {0}}}, - - {SVGA3D_ARGB_S10E5, SVGA3DBLOCKDESC_RGBA_FP, - {1, 1, 1}, 8, 8, - {{16}, {16}, {16}, {16}}, - {{32}, {16}, {0}, {48}}}, - - {SVGA3D_ARGB_S23E8, SVGA3DBLOCKDESC_RGBA_FP, - {1, 1, 1}, 16, 16, - {{32}, {32}, {32}, {32}}, - {{64}, {32}, {0}, {96}}}, - - {SVGA3D_A2R10G10B10, SVGA3DBLOCKDESC_RGBA_UNORM, - {1, 1, 1}, 4, 4, - {{10}, {10}, {10}, {2}}, - {{0}, {10}, {20}, {30}}}, - - {SVGA3D_V8U8, SVGA3DBLOCKDESC_UV_SNORM, - {1, 1, 1}, 2, 2, - {{0}, {8}, {8}, {0}}, - {{0}, {8}, {0}, {0}}}, - - {SVGA3D_Q8W8V8U8, SVGA3DBLOCKDESC_UVWQ_SNORM, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {8}}, - {{16}, {8}, {0}, {24}}}, - - {SVGA3D_CxV8U8, SVGA3DBLOCKDESC_UVCX_SNORM, - {1, 1, 1}, 2, 2, - {{0}, {8}, {8}, {0}}, - {{0}, {8}, {0}, {0}}}, - - {SVGA3D_X8L8V8U8, SVGA3DBLOCKDESC_UVL, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {0}}, - {{16}, {8}, {0}, {0}}}, - - {SVGA3D_A2W10V10U10, SVGA3DBLOCKDESC_UVWA, - {1, 1, 1}, 4, 4, - {{10}, {10}, {10}, {2}}, - {{20}, {10}, {0}, {30}}}, - - {SVGA3D_ALPHA8, SVGA3DBLOCKDESC_A_UNORM, - {1, 1, 1}, 1, 1, - {{0}, {0}, {0}, {8}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R_S10E5, SVGA3DBLOCKDESC_R_FP, - {1, 1, 1}, 2, 2, - {{0}, {0}, {16}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R_S23E8, SVGA3DBLOCKDESC_R_FP, - {1, 1, 1}, 4, 4, - {{0}, {0}, {32}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_RG_S10E5, SVGA3DBLOCKDESC_RG_FP, - {1, 1, 1}, 4, 4, - {{0}, {16}, {16}, {0}}, - {{0}, {16}, {0}, {0}}}, - - {SVGA3D_RG_S23E8, SVGA3DBLOCKDESC_RG_FP, - {1, 1, 1}, 8, 8, - {{0}, {32}, {32}, {0}}, - {{0}, {32}, {0}, {0}}}, - - {SVGA3D_BUFFER, SVGA3DBLOCKDESC_BUFFER, - {1, 1, 1}, 1, 1, - {{0}, {0}, {8}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_Z_D24X8, SVGA3DBLOCKDESC_DEPTH_UNORM, - {1, 1, 1}, 4, 4, - {{0}, {0}, {24}, {0}}, - {{0}, {0}, {8}, {0}}}, - - {SVGA3D_V16U16, SVGA3DBLOCKDESC_UV_SNORM, - {1, 1, 1}, 4, 4, - {{0}, {16}, {16}, {0}}, - {{0}, {16}, {0}, {0}}}, - - {SVGA3D_G16R16, SVGA3DBLOCKDESC_RG_UNORM, - {1, 1, 1}, 4, 4, - {{0}, {16}, {16}, {0}}, - {{0}, {16}, {0}, {0}}}, - - {SVGA3D_A16B16G16R16, SVGA3DBLOCKDESC_RGBA_UNORM, - {1, 1, 1}, 8, 8, - {{16}, {16}, {16}, {16}}, - {{32}, {16}, {0}, {48}}}, - - {SVGA3D_UYVY, SVGA3DBLOCKDESC_YUV, - {2, 1, 1}, 4, 4, - {{8}, {0}, {8}, {0}}, - {{0}, {0}, {8}, {0}}}, - - {SVGA3D_YUY2, SVGA3DBLOCKDESC_YUV, - {2, 1, 1}, 4, 4, - {{8}, {0}, {8}, {0}}, - {{8}, {0}, {0}, {0}}}, - - {SVGA3D_NV12, SVGA3DBLOCKDESC_NV12, - {2, 2, 1}, 6, 2, - {{0}, {0}, {48}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_FORMAT_DEAD2, SVGA3DBLOCKDESC_NONE, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {8}}, - {{0}, {8}, {16}, {24}}}, - - {SVGA3D_R32G32B32A32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 16, 16, - {{32}, {32}, {32}, {32}}, - {{64}, {32}, {0}, {96}}}, - - {SVGA3D_R32G32B32A32_UINT, SVGA3DBLOCKDESC_RGBA_UINT, - {1, 1, 1}, 16, 16, - {{32}, {32}, {32}, {32}}, - {{64}, {32}, {0}, {96}}}, - - {SVGA3D_R32G32B32A32_SINT, SVGA3DBLOCKDESC_RGBA_SINT, - {1, 1, 1}, 16, 16, - {{32}, {32}, {32}, {32}}, - {{64}, {32}, {0}, {96}}}, - - {SVGA3D_R32G32B32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 12, 12, - {{32}, {32}, {32}, {0}}, - {{64}, {32}, {0}, {0}}}, - - {SVGA3D_R32G32B32_FLOAT, SVGA3DBLOCKDESC_RGB_FP, - {1, 1, 1}, 12, 12, - {{32}, {32}, {32}, {0}}, - {{64}, {32}, {0}, {0}}}, - - {SVGA3D_R32G32B32_UINT, SVGA3DBLOCKDESC_RGB_UINT, - {1, 1, 1}, 12, 12, - {{32}, {32}, {32}, {0}}, - {{64}, {32}, {0}, {0}}}, - - {SVGA3D_R32G32B32_SINT, SVGA3DBLOCKDESC_RGB_SINT, - {1, 1, 1}, 12, 12, - {{32}, {32}, {32}, {0}}, - {{64}, {32}, {0}, {0}}}, - - {SVGA3D_R16G16B16A16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 8, 8, - {{16}, {16}, {16}, {16}}, - {{32}, {16}, {0}, {48}}}, - - {SVGA3D_R16G16B16A16_UINT, SVGA3DBLOCKDESC_RGBA_UINT, - {1, 1, 1}, 8, 8, - {{16}, {16}, {16}, {16}}, - {{32}, {16}, {0}, {48}}}, - - {SVGA3D_R16G16B16A16_SNORM, SVGA3DBLOCKDESC_RGBA_SNORM, - {1, 1, 1}, 8, 8, - {{16}, {16}, {16}, {16}}, - {{32}, {16}, {0}, {48}}}, - - {SVGA3D_R16G16B16A16_SINT, SVGA3DBLOCKDESC_RGBA_SINT, - {1, 1, 1}, 8, 8, - {{16}, {16}, {16}, {16}}, - {{32}, {16}, {0}, {48}}}, - - {SVGA3D_R32G32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 8, 8, - {{0}, {32}, {32}, {0}}, - {{0}, {32}, {0}, {0}}}, - - {SVGA3D_R32G32_UINT, SVGA3DBLOCKDESC_RG_UINT, - {1, 1, 1}, 8, 8, - {{0}, {32}, {32}, {0}}, - {{0}, {32}, {0}, {0}}}, - - {SVGA3D_R32G32_SINT, SVGA3DBLOCKDESC_RG_SINT, - {1, 1, 1}, 8, 8, - {{0}, {32}, {32}, {0}}, - {{0}, {32}, {0}, {0}}}, - - {SVGA3D_R32G8X24_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 8, 8, - {{0}, {8}, {32}, {0}}, - {{0}, {32}, {0}, {0}}}, - - {SVGA3D_D32_FLOAT_S8X24_UINT, SVGA3DBLOCKDESC_DS, - {1, 1, 1}, 8, 8, - {{0}, {8}, {32}, {0}}, - {{0}, {32}, {0}, {0}}}, - - {SVGA3D_R32_FLOAT_X8X24, SVGA3DBLOCKDESC_R_FP, - {1, 1, 1}, 8, 8, - {{0}, {0}, {32}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_X32_G8X24_UINT, SVGA3DBLOCKDESC_G_UINT, - {1, 1, 1}, 8, 8, - {{0}, {8}, {0}, {0}}, - {{0}, {32}, {0}, {0}}}, - - {SVGA3D_R10G10B10A2_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 4, 4, - {{10}, {10}, {10}, {2}}, - {{20}, {10}, {0}, {30}}}, - - {SVGA3D_R10G10B10A2_UINT, SVGA3DBLOCKDESC_RGBA_UINT, - {1, 1, 1}, 4, 4, - {{10}, {10}, {10}, {2}}, - {{20}, {10}, {0}, {30}}}, - - {SVGA3D_R11G11B10_FLOAT, SVGA3DBLOCKDESC_RGB_FP, - {1, 1, 1}, 4, 4, - {{10}, {11}, {11}, {0}}, - {{22}, {11}, {0}, {0}}}, - - {SVGA3D_R8G8B8A8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {8}}, - {{16}, {8}, {0}, {24}}}, - - {SVGA3D_R8G8B8A8_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {8}}, - {{16}, {8}, {0}, {24}}}, - - {SVGA3D_R8G8B8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_UNORM_SRGB, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {8}}, - {{16}, {8}, {0}, {24}}}, - - {SVGA3D_R8G8B8A8_UINT, SVGA3DBLOCKDESC_RGBA_UINT, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {8}}, - {{16}, {8}, {0}, {24}}}, - - {SVGA3D_R8G8B8A8_SINT, SVGA3DBLOCKDESC_RGBA_SINT, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {8}}, - {{16}, {8}, {0}, {24}}}, - - {SVGA3D_R16G16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 4, 4, - {{0}, {16}, {16}, {0}}, - {{0}, {16}, {0}, {0}}}, - - {SVGA3D_R16G16_UINT, SVGA3DBLOCKDESC_RG_UINT, - {1, 1, 1}, 4, 4, - {{0}, {16}, {16}, {0}}, - {{0}, {16}, {0}, {0}}}, - - {SVGA3D_R16G16_SINT, SVGA3DBLOCKDESC_RG_SINT, - {1, 1, 1}, 4, 4, - {{0}, {16}, {16}, {0}}, - {{0}, {16}, {0}, {0}}}, - - {SVGA3D_R32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 4, 4, - {{0}, {0}, {32}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_D32_FLOAT, SVGA3DBLOCKDESC_DEPTH_FP, - {1, 1, 1}, 4, 4, - {{0}, {0}, {32}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R32_UINT, SVGA3DBLOCKDESC_R_UINT, - {1, 1, 1}, 4, 4, - {{0}, {0}, {32}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R32_SINT, SVGA3DBLOCKDESC_R_SINT, - {1, 1, 1}, 4, 4, - {{0}, {0}, {32}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R24G8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 4, 4, - {{0}, {8}, {24}, {0}}, - {{0}, {24}, {0}, {0}}}, - - {SVGA3D_D24_UNORM_S8_UINT, SVGA3DBLOCKDESC_DS_UNORM, - {1, 1, 1}, 4, 4, - {{0}, {8}, {24}, {0}}, - {{0}, {24}, {0}, {0}}}, - - {SVGA3D_R24_UNORM_X8, SVGA3DBLOCKDESC_R_UNORM, - {1, 1, 1}, 4, 4, - {{0}, {0}, {24}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_X24_G8_UINT, SVGA3DBLOCKDESC_G_UINT, - {1, 1, 1}, 4, 4, - {{0}, {8}, {0}, {0}}, - {{0}, {24}, {0}, {0}}}, - - {SVGA3D_R8G8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 2, 2, - {{0}, {8}, {8}, {0}}, - {{0}, {8}, {0}, {0}}}, - - {SVGA3D_R8G8_UNORM, SVGA3DBLOCKDESC_RG_UNORM, - {1, 1, 1}, 2, 2, - {{0}, {8}, {8}, {0}}, - {{0}, {8}, {0}, {0}}}, - - {SVGA3D_R8G8_UINT, SVGA3DBLOCKDESC_RG_UINT, - {1, 1, 1}, 2, 2, - {{0}, {8}, {8}, {0}}, - {{0}, {8}, {0}, {0}}}, - - {SVGA3D_R8G8_SINT, SVGA3DBLOCKDESC_RG_SINT, - {1, 1, 1}, 2, 2, - {{0}, {8}, {8}, {0}}, - {{0}, {8}, {0}, {0}}}, - - {SVGA3D_R16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 2, 2, - {{0}, {0}, {16}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R16_UNORM, SVGA3DBLOCKDESC_R_UNORM, - {1, 1, 1}, 2, 2, - {{0}, {0}, {16}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R16_UINT, SVGA3DBLOCKDESC_R_UINT, - {1, 1, 1}, 2, 2, - {{0}, {0}, {16}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R16_SNORM, SVGA3DBLOCKDESC_R_SNORM, - {1, 1, 1}, 2, 2, - {{0}, {0}, {16}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R16_SINT, SVGA3DBLOCKDESC_R_SINT, - {1, 1, 1}, 2, 2, - {{0}, {0}, {16}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 1, 1, - {{0}, {0}, {8}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R8_UNORM, SVGA3DBLOCKDESC_R_UNORM, - {1, 1, 1}, 1, 1, - {{0}, {0}, {8}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R8_UINT, SVGA3DBLOCKDESC_R_UINT, - {1, 1, 1}, 1, 1, - {{0}, {0}, {8}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R8_SNORM, SVGA3DBLOCKDESC_R_SNORM, - {1, 1, 1}, 1, 1, - {{0}, {0}, {8}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R8_SINT, SVGA3DBLOCKDESC_R_SINT, - {1, 1, 1}, 1, 1, - {{0}, {0}, {8}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_P8, SVGA3DBLOCKDESC_NONE, - {1, 1, 1}, 1, 1, - {{0}, {0}, {8}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R9G9B9E5_SHAREDEXP, SVGA3DBLOCKDESC_RGB_EXP, - {1, 1, 1}, 4, 4, - {{9}, {9}, {9}, {5}}, - {{18}, {9}, {0}, {27}}}, - - {SVGA3D_R8G8_B8G8_UNORM, SVGA3DBLOCKDESC_NONE, - {2, 1, 1}, 4, 4, - {{0}, {8}, {8}, {0}}, - {{0}, {0}, {8}, {0}}}, - - {SVGA3D_G8R8_G8B8_UNORM, SVGA3DBLOCKDESC_NONE, - {2, 1, 1}, 4, 4, - {{0}, {8}, {8}, {0}}, - {{0}, {8}, {0}, {0}}}, - - {SVGA3D_BC1_TYPELESS, SVGA3DBLOCKDESC_BC1_COMP_TYPELESS, - {4, 4, 1}, 8, 8, - {{0}, {0}, {64}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC1_UNORM_SRGB, SVGA3DBLOCKDESC_BC1_COMP_UNORM_SRGB, - {4, 4, 1}, 8, 8, - {{0}, {0}, {64}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC2_TYPELESS, SVGA3DBLOCKDESC_BC2_COMP_TYPELESS, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC2_UNORM_SRGB, SVGA3DBLOCKDESC_BC2_COMP_UNORM_SRGB, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC3_TYPELESS, SVGA3DBLOCKDESC_BC3_COMP_TYPELESS, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC3_UNORM_SRGB, SVGA3DBLOCKDESC_BC3_COMP_UNORM_SRGB, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC4_TYPELESS, SVGA3DBLOCKDESC_BC4_COMP_TYPELESS, - {4, 4, 1}, 8, 8, - {{0}, {0}, {64}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_ATI1, SVGA3DBLOCKDESC_BC4_COMP_UNORM, - {4, 4, 1}, 8, 8, - {{0}, {0}, {64}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC4_SNORM, SVGA3DBLOCKDESC_BC4_COMP_SNORM, - {4, 4, 1}, 8, 8, - {{0}, {0}, {64}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC5_TYPELESS, SVGA3DBLOCKDESC_BC5_COMP_TYPELESS, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_ATI2, SVGA3DBLOCKDESC_BC5_COMP_UNORM, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC5_SNORM, SVGA3DBLOCKDESC_BC5_COMP_SNORM, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R10G10B10_XR_BIAS_A2_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM, - {1, 1, 1}, 4, 4, - {{10}, {10}, {10}, {2}}, - {{20}, {10}, {0}, {30}}}, - - {SVGA3D_B8G8R8A8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {8}}, - {{0}, {8}, {16}, {24}}}, - - {SVGA3D_B8G8R8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_UNORM_SRGB, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {8}}, - {{0}, {8}, {16}, {24}}}, - - {SVGA3D_B8G8R8X8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {0}}, - {{0}, {8}, {16}, {24}}}, - - {SVGA3D_B8G8R8X8_UNORM_SRGB, SVGA3DBLOCKDESC_RGB_UNORM_SRGB, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {0}}, - {{0}, {8}, {16}, {24}}}, - - {SVGA3D_Z_DF16, SVGA3DBLOCKDESC_DEPTH_UNORM, - {1, 1, 1}, 2, 2, - {{0}, {0}, {16}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_Z_DF24, SVGA3DBLOCKDESC_DEPTH_UNORM, - {1, 1, 1}, 4, 4, - {{0}, {0}, {24}, {0}}, - {{0}, {0}, {8}, {0}}}, - - {SVGA3D_Z_D24S8_INT, SVGA3DBLOCKDESC_DS_UNORM, - {1, 1, 1}, 4, 4, - {{0}, {8}, {24}, {0}}, - {{0}, {0}, {8}, {0}}}, - - {SVGA3D_YV12, SVGA3DBLOCKDESC_YV12, - {2, 2, 1}, 6, 2, - {{0}, {0}, {48}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R32G32B32A32_FLOAT, SVGA3DBLOCKDESC_RGBA_FP, - {1, 1, 1}, 16, 16, - {{32}, {32}, {32}, {32}}, - {{64}, {32}, {0}, {96}}}, - - {SVGA3D_R16G16B16A16_FLOAT, SVGA3DBLOCKDESC_RGBA_FP, - {1, 1, 1}, 8, 8, - {{16}, {16}, {16}, {16}}, - {{32}, {16}, {0}, {48}}}, - - {SVGA3D_R16G16B16A16_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM, - {1, 1, 1}, 8, 8, - {{16}, {16}, {16}, {16}}, - {{32}, {16}, {0}, {48}}}, - - {SVGA3D_R32G32_FLOAT, SVGA3DBLOCKDESC_RG_FP, - {1, 1, 1}, 8, 8, - {{0}, {32}, {32}, {0}}, - {{0}, {32}, {0}, {0}}}, - - {SVGA3D_R10G10B10A2_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM, - {1, 1, 1}, 4, 4, - {{10}, {10}, {10}, {2}}, - {{20}, {10}, {0}, {30}}}, - - {SVGA3D_R8G8B8A8_SNORM, SVGA3DBLOCKDESC_RGBA_SNORM, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {8}}, - {{16}, {8}, {0}, {24}}}, - - {SVGA3D_R16G16_FLOAT, SVGA3DBLOCKDESC_RG_FP, - {1, 1, 1}, 4, 4, - {{0}, {16}, {16}, {0}}, - {{0}, {16}, {0}, {0}}}, - - {SVGA3D_R16G16_UNORM, SVGA3DBLOCKDESC_RG_UNORM, - {1, 1, 1}, 4, 4, - {{0}, {16}, {16}, {0}}, - {{0}, {16}, {0}, {0}}}, - - {SVGA3D_R16G16_SNORM, SVGA3DBLOCKDESC_RG_SNORM, - {1, 1, 1}, 4, 4, - {{0}, {16}, {16}, {0}}, - {{0}, {16}, {0}, {0}}}, - - {SVGA3D_R32_FLOAT, SVGA3DBLOCKDESC_R_FP, - {1, 1, 1}, 4, 4, - {{0}, {0}, {32}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_R8G8_SNORM, SVGA3DBLOCKDESC_RG_SNORM, - {1, 1, 1}, 2, 2, - {{0}, {8}, {8}, {0}}, - {{0}, {8}, {0}, {0}}}, - - {SVGA3D_R16_FLOAT, SVGA3DBLOCKDESC_R_FP, - {1, 1, 1}, 2, 2, - {{0}, {0}, {16}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_D16_UNORM, SVGA3DBLOCKDESC_DEPTH_UNORM, - {1, 1, 1}, 2, 2, - {{0}, {0}, {16}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_A8_UNORM, SVGA3DBLOCKDESC_A_UNORM, - {1, 1, 1}, 1, 1, - {{0}, {0}, {0}, {8}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC1_UNORM, SVGA3DBLOCKDESC_BC1_COMP_UNORM, - {4, 4, 1}, 8, 8, - {{0}, {0}, {64}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC2_UNORM, SVGA3DBLOCKDESC_BC2_COMP_UNORM, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC3_UNORM, SVGA3DBLOCKDESC_BC3_COMP_UNORM, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_B5G6R5_UNORM, SVGA3DBLOCKDESC_RGB_UNORM, - {1, 1, 1}, 2, 2, - {{5}, {6}, {5}, {0}}, - {{0}, {5}, {11}, {0}}}, - - {SVGA3D_B5G5R5A1_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM, - {1, 1, 1}, 2, 2, - {{5}, {5}, {5}, {1}}, - {{0}, {5}, {10}, {15}}}, - - {SVGA3D_B8G8R8A8_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {8}}, - {{0}, {8}, {16}, {24}}}, - - {SVGA3D_B8G8R8X8_UNORM, SVGA3DBLOCKDESC_RGB_UNORM, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {0}}, - {{0}, {8}, {16}, {24}}}, - - {SVGA3D_BC4_UNORM, SVGA3DBLOCKDESC_BC4_COMP_UNORM, - {4, 4, 1}, 8, 8, - {{0}, {0}, {64}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC5_UNORM, SVGA3DBLOCKDESC_BC5_COMP_UNORM, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_B4G4R4A4_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM, - {1, 1, 1}, 2, 2, - {{4}, {4}, {4}, {4}}, - {{0}, {4}, {8}, {12}}}, - - {SVGA3D_BC6H_TYPELESS, SVGA3DBLOCKDESC_BC6H_COMP_TYPELESS, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC6H_UF16, SVGA3DBLOCKDESC_BC6H_COMP_UF16, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC6H_SF16, SVGA3DBLOCKDESC_BC6H_COMP_SF16, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC7_TYPELESS, SVGA3DBLOCKDESC_BC7_COMP_TYPELESS, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC7_UNORM, SVGA3DBLOCKDESC_BC7_COMP_UNORM, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_BC7_UNORM_SRGB, SVGA3DBLOCKDESC_BC7_COMP_UNORM_SRGB, - {4, 4, 1}, 16, 16, - {{0}, {0}, {128}, {0}}, - {{0}, {0}, {0}, {0}}}, - - {SVGA3D_AYUV, SVGA3DBLOCKDESC_AYUV, - {1, 1, 1}, 4, 4, - {{8}, {8}, {8}, {8}}, - {{0}, {8}, {16}, {24}}}, -}; - -static inline u32 clamped_umul32(u32 a, u32 b) -{ - uint64_t tmp = (uint64_t) a*b; - return (tmp > (uint64_t) ((u32) -1)) ? (u32) -1 : tmp; -} - -/** - * svga3dsurface_get_desc - Look up the appropriate SVGA3dSurfaceDesc for the - * given format. - */ -static inline const struct svga3d_surface_desc * -svga3dsurface_get_desc(SVGA3dSurfaceFormat format) -{ - if (format < ARRAY_SIZE(svga3d_surface_descs)) - return &svga3d_surface_descs[format]; - - return &svga3d_surface_descs[SVGA3D_FORMAT_INVALID]; -} - -/** - * svga3dsurface_get_mip_size - Given a base level size and the mip level, - * compute the size of the mip level. - */ -static inline surf_size_struct -svga3dsurface_get_mip_size(surf_size_struct base_level, u32 mip_level) -{ - surf_size_struct size; - - size.width = max_t(u32, base_level.width >> mip_level, 1); - size.height = max_t(u32, base_level.height >> mip_level, 1); - size.depth = max_t(u32, base_level.depth >> mip_level, 1); - size.pad64 = 0; - - return size; -} - -static inline void -svga3dsurface_get_size_in_blocks(const struct svga3d_surface_desc *desc, - const surf_size_struct *pixel_size, - surf_size_struct *block_size) -{ - block_size->width = __KERNEL_DIV_ROUND_UP(pixel_size->width, - desc->block_size.width); - block_size->height = __KERNEL_DIV_ROUND_UP(pixel_size->height, - desc->block_size.height); - block_size->depth = __KERNEL_DIV_ROUND_UP(pixel_size->depth, - desc->block_size.depth); -} - -static inline bool -svga3dsurface_is_planar_surface(const struct svga3d_surface_desc *desc) -{ - return (desc->block_desc & SVGA3DBLOCKDESC_PLANAR_YUV) != 0; -} - -static inline u32 -svga3dsurface_calculate_pitch(const struct svga3d_surface_desc *desc, - const surf_size_struct *size) -{ - u32 pitch; - surf_size_struct blocks; - - svga3dsurface_get_size_in_blocks(desc, size, &blocks); - - pitch = blocks.width * desc->pitch_bytes_per_block; - - return pitch; -} - -/** - * svga3dsurface_get_image_buffer_size - Calculates image buffer size. - * - * Return the number of bytes of buffer space required to store one image of a - * surface, optionally using the specified pitch. - * - * If pitch is zero, it is assumed that rows are tightly packed. - * - * This function is overflow-safe. If the result would have overflowed, instead - * we return MAX_UINT32. - */ -static inline u32 -svga3dsurface_get_image_buffer_size(const struct svga3d_surface_desc *desc, - const surf_size_struct *size, - u32 pitch) -{ - surf_size_struct image_blocks; - u32 slice_size, total_size; - - svga3dsurface_get_size_in_blocks(desc, size, &image_blocks); - - if (svga3dsurface_is_planar_surface(desc)) { - total_size = clamped_umul32(image_blocks.width, - image_blocks.height); - total_size = clamped_umul32(total_size, image_blocks.depth); - total_size = clamped_umul32(total_size, desc->bytes_per_block); - return total_size; - } - - if (pitch == 0) - pitch = svga3dsurface_calculate_pitch(desc, size); - - slice_size = clamped_umul32(image_blocks.height, pitch); - total_size = clamped_umul32(slice_size, image_blocks.depth); - - return total_size; -} - -/** - * svga3dsurface_get_serialized_size - Get the serialized size for the image. - */ -static inline u32 -svga3dsurface_get_serialized_size(SVGA3dSurfaceFormat format, - surf_size_struct base_level_size, - u32 num_mip_levels, - u32 num_layers) -{ - const struct svga3d_surface_desc *desc = svga3dsurface_get_desc(format); - u32 total_size = 0; - u32 mip; - - for (mip = 0; mip < num_mip_levels; mip++) { - surf_size_struct size = - svga3dsurface_get_mip_size(base_level_size, mip); - total_size += svga3dsurface_get_image_buffer_size(desc, - &size, 0); - } - - return total_size * num_layers; -} - -/** - * svga3dsurface_get_serialized_size_extended - Returns the number of bytes - * required for a surface with given parameters. Support for sample count. - */ -static inline u32 -svga3dsurface_get_serialized_size_extended(SVGA3dSurfaceFormat format, - surf_size_struct base_level_size, - u32 num_mip_levels, - u32 num_layers, - u32 num_samples) -{ - uint64_t total_size = - svga3dsurface_get_serialized_size(format, - base_level_size, - num_mip_levels, - num_layers); - total_size *= max_t(u32, 1, num_samples); - - return min_t(uint64_t, total_size, (uint64_t)U32_MAX); -} - -/** - * svga3dsurface_get_pixel_offset - Compute the offset (in bytes) to a pixel - * in an image (or volume). - * - * @width: The image width in pixels. - * @height: The image height in pixels - */ -static inline u32 -svga3dsurface_get_pixel_offset(SVGA3dSurfaceFormat format, - u32 width, u32 height, - u32 x, u32 y, u32 z) -{ - const struct svga3d_surface_desc *desc = svga3dsurface_get_desc(format); - const u32 bw = desc->block_size.width, bh = desc->block_size.height; - const u32 bd = desc->block_size.depth; - const u32 rowstride = __KERNEL_DIV_ROUND_UP(width, bw) * - desc->bytes_per_block; - const u32 imgstride = __KERNEL_DIV_ROUND_UP(height, bh) * rowstride; - const u32 offset = (z / bd * imgstride + - y / bh * rowstride + - x / bw * desc->bytes_per_block); - return offset; -} - -static inline u32 -svga3dsurface_get_image_offset(SVGA3dSurfaceFormat format, - surf_size_struct baseLevelSize, - u32 numMipLevels, - u32 face, - u32 mip) - -{ - u32 offset; - u32 mipChainBytes; - u32 mipChainBytesToLevel; - u32 i; - const struct svga3d_surface_desc *desc; - surf_size_struct mipSize; - u32 bytes; - - desc = svga3dsurface_get_desc(format); - - mipChainBytes = 0; - mipChainBytesToLevel = 0; - for (i = 0; i < numMipLevels; i++) { - mipSize = svga3dsurface_get_mip_size(baseLevelSize, i); - bytes = svga3dsurface_get_image_buffer_size(desc, &mipSize, 0); - mipChainBytes += bytes; - if (i < mip) - mipChainBytesToLevel += bytes; - } - - offset = mipChainBytes * face + mipChainBytesToLevel; - - return offset; -} - - -/** - * svga3dsurface_is_gb_screen_target_format - Is the specified format usable as - * a ScreenTarget? - * (with just the GBObjects cap-bit - * set) - * @format: format to queried - * - * RETURNS: - * true if queried format is valid for screen targets - */ -static inline bool -svga3dsurface_is_gb_screen_target_format(SVGA3dSurfaceFormat format) -{ - return (format == SVGA3D_X8R8G8B8 || - format == SVGA3D_A8R8G8B8 || - format == SVGA3D_R5G6B5 || - format == SVGA3D_X1R5G5B5 || - format == SVGA3D_A1R5G5B5 || - format == SVGA3D_P8); -} - - -/** - * svga3dsurface_is_dx_screen_target_format - Is the specified format usable as - * a ScreenTarget? - * (with DX10 enabled) - * - * @format: format to queried - * - * Results: - * true if queried format is valid for screen targets - */ -static inline bool -svga3dsurface_is_dx_screen_target_format(SVGA3dSurfaceFormat format) -{ - return (format == SVGA3D_R8G8B8A8_UNORM || - format == SVGA3D_B8G8R8A8_UNORM || - format == SVGA3D_B8G8R8X8_UNORM); -} - - -/** - * svga3dsurface_is_screen_target_format - Is the specified format usable as a - * ScreenTarget? - * (for some combination of caps) - * - * @format: format to queried - * - * Results: - * true if queried format is valid for screen targets - */ -static inline bool -svga3dsurface_is_screen_target_format(SVGA3dSurfaceFormat format) -{ - if (svga3dsurface_is_gb_screen_target_format(format)) { - return true; - } - return svga3dsurface_is_dx_screen_target_format(format); -} - -/** - * struct svga3dsurface_mip - Mimpmap level information - * @bytes: Bytes required in the backing store of this mipmap level. - * @img_stride: Byte stride per image. - * @row_stride: Byte stride per block row. - * @size: The size of the mipmap. - */ -struct svga3dsurface_mip { - size_t bytes; - size_t img_stride; - size_t row_stride; - struct drm_vmw_size size; - -}; - -/** - * struct svga3dsurface_cache - Cached surface information - * @desc: Pointer to the surface descriptor - * @mip: Array of mipmap level information. Valid size is @num_mip_levels. - * @mip_chain_bytes: Bytes required in the backing store for the whole chain - * of mip levels. - * @sheet_bytes: Bytes required in the backing store for a sheet - * representing a single sample. - * @num_mip_levels: Valid size of the @mip array. Number of mipmap levels in - * a chain. - * @num_layers: Number of slices in an array texture or number of faces in - * a cubemap texture. - */ -struct svga3dsurface_cache { - const struct svga3d_surface_desc *desc; - struct svga3dsurface_mip mip[DRM_VMW_MAX_MIP_LEVELS]; - size_t mip_chain_bytes; - size_t sheet_bytes; - u32 num_mip_levels; - u32 num_layers; -}; - -/** - * struct svga3dsurface_loc - Surface location - * @sheet: The multisample sheet. - * @sub_resource: Surface subresource. Defined as layer * num_mip_levels + - * mip_level. - * @x: X coordinate. - * @y: Y coordinate. - * @z: Z coordinate. - */ -struct svga3dsurface_loc { - u32 sheet; - u32 sub_resource; - u32 x, y, z; + SVGA3dBlockDesc blockDesc; + + SVGA3dSize blockSize; + uint32 bytesPerBlock; + uint32 pitchBytesPerBlock; + + SVGA3dChannelDef bitDepth; + SVGA3dChannelDef bitOffset; +} SVGA3dSurfaceDesc; + +STATIC_CONST SVGA3dSurfaceDesc g_SVGA3dSurfaceDescs[] = { + { SVGA3D_FORMAT_INVALID, + SVGA3DBLOCKDESC_NONE, + { 1, 1, 1 }, + 0, + 0, + { { 0 }, { 0 }, { 0 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_X8R8G8B8, + SVGA3DBLOCKDESC_RGB_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 0 } }, + { { 0 }, { 8 }, { 16 }, { 24 } } }, + + { SVGA3D_A8R8G8B8, + SVGA3DBLOCKDESC_RGBA_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 8 } }, + { { 0 }, { 8 }, { 16 }, { 24 } } }, + + { SVGA3D_R5G6B5, + SVGA3DBLOCKDESC_RGB_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 5 }, { 6 }, { 5 }, { 0 } }, + { { 0 }, { 5 }, { 11 }, { 0 } } }, + + { SVGA3D_X1R5G5B5, + SVGA3DBLOCKDESC_RGB_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 5 }, { 5 }, { 5 }, { 0 } }, + { { 0 }, { 5 }, { 10 }, { 0 } } }, + + { SVGA3D_A1R5G5B5, + SVGA3DBLOCKDESC_RGBA_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 5 }, { 5 }, { 5 }, { 1 } }, + { { 0 }, { 5 }, { 10 }, { 15 } } }, + + { SVGA3D_A4R4G4B4, + SVGA3DBLOCKDESC_RGBA_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 4 }, { 4 }, { 4 }, { 4 } }, + { { 0 }, { 4 }, { 8 }, { 12 } } }, + + { SVGA3D_Z_D32, + SVGA3DBLOCKDESC_DEPTH_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 0 }, { 32 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_Z_D16, + SVGA3DBLOCKDESC_DEPTH_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 0 }, { 16 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_Z_D24S8, + SVGA3DBLOCKDESC_DS_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 8 }, { 24 }, { 0 } }, + { { 0 }, { 0 }, { 8 }, { 0 } } }, + + { SVGA3D_Z_D15S1, + SVGA3DBLOCKDESC_DS_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 1 }, { 15 }, { 0 } }, + { { 0 }, { 0 }, { 1 }, { 0 } } }, + + { SVGA3D_LUMINANCE8, + SVGA3DBLOCKDESC_L_UNORM, + { 1, 1, 1 }, + 1, + 1, + { { 0 }, { 0 }, { 8 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_LUMINANCE4_ALPHA4, + SVGA3DBLOCKDESC_LA_UNORM, + { 1, 1, 1 }, + 1, + 1, + { { 0 }, { 0 }, { 4 }, { 4 } }, + { { 0 }, { 0 }, { 0 }, { 4 } } }, + + { SVGA3D_LUMINANCE16, + SVGA3DBLOCKDESC_L_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 0 }, { 16 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_LUMINANCE8_ALPHA8, + SVGA3DBLOCKDESC_LA_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 0 }, { 8 }, { 8 } }, + { { 0 }, { 0 }, { 0 }, { 8 } } }, + + { SVGA3D_DXT1, + SVGA3DBLOCKDESC_BC1_COMP_UNORM, + { 4, 4, 1 }, + 8, + 8, + { { 0 }, { 0 }, { 64 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_DXT2, + SVGA3DBLOCKDESC_BC2_COMP_UNORM, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_DXT3, + SVGA3DBLOCKDESC_BC2_COMP_UNORM, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_DXT4, + SVGA3DBLOCKDESC_BC3_COMP_UNORM, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_DXT5, + SVGA3DBLOCKDESC_BC3_COMP_UNORM, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BUMPU8V8, + SVGA3DBLOCKDESC_UV_SNORM, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 8 }, { 8 }, { 0 } }, + { { 0 }, { 8 }, { 0 }, { 0 } } }, + + { SVGA3D_BUMPL6V5U5, + SVGA3DBLOCKDESC_UVL, + { 1, 1, 1 }, + 2, + 2, + { { 6 }, { 5 }, { 5 }, { 0 } }, + { { 10 }, { 5 }, { 0 }, { 0 } } }, + + { SVGA3D_BUMPX8L8V8U8, + SVGA3DBLOCKDESC_UVL, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 0 } }, + { { 16 }, { 8 }, { 0 }, { 0 } } }, + + { SVGA3D_FORMAT_DEAD1, + SVGA3DBLOCKDESC_NONE, + { 1, 1, 1 }, + 3, + 3, + { { 8 }, { 8 }, { 8 }, { 0 } }, + { { 16 }, { 8 }, { 0 }, { 0 } } }, + + { SVGA3D_ARGB_S10E5, + SVGA3DBLOCKDESC_RGBA_FP, + { 1, 1, 1 }, + 8, + 8, + { { 16 }, { 16 }, { 16 }, { 16 } }, + { { 32 }, { 16 }, { 0 }, { 48 } } }, + + { SVGA3D_ARGB_S23E8, + SVGA3DBLOCKDESC_RGBA_FP, + { 1, 1, 1 }, + 16, + 16, + { { 32 }, { 32 }, { 32 }, { 32 } }, + { { 64 }, { 32 }, { 0 }, { 96 } } }, + + { SVGA3D_A2R10G10B10, + SVGA3DBLOCKDESC_RGBA_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 10 }, { 10 }, { 10 }, { 2 } }, + { { 0 }, { 10 }, { 20 }, { 30 } } }, + + { SVGA3D_V8U8, + SVGA3DBLOCKDESC_UV_SNORM, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 8 }, { 8 }, { 0 } }, + { { 0 }, { 8 }, { 0 }, { 0 } } }, + + { SVGA3D_Q8W8V8U8, + SVGA3DBLOCKDESC_UVWQ_SNORM, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 8 } }, + { { 16 }, { 8 }, { 0 }, { 24 } } }, + + { SVGA3D_CxV8U8, + SVGA3DBLOCKDESC_UVCX_SNORM, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 8 }, { 8 }, { 0 } }, + { { 0 }, { 8 }, { 0 }, { 0 } } }, + + { SVGA3D_X8L8V8U8, + SVGA3DBLOCKDESC_UVL, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 0 } }, + { { 16 }, { 8 }, { 0 }, { 0 } } }, + + { SVGA3D_A2W10V10U10, + SVGA3DBLOCKDESC_UVWA, + { 1, 1, 1 }, + 4, + 4, + { { 10 }, { 10 }, { 10 }, { 2 } }, + { { 20 }, { 10 }, { 0 }, { 30 } } }, + + { SVGA3D_ALPHA8, + SVGA3DBLOCKDESC_A_UNORM, + { 1, 1, 1 }, + 1, + 1, + { { 0 }, { 0 }, { 0 }, { 8 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R_S10E5, + SVGA3DBLOCKDESC_R_FP, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 0 }, { 16 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R_S23E8, + SVGA3DBLOCKDESC_R_FP, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 0 }, { 32 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_RG_S10E5, + SVGA3DBLOCKDESC_RG_FP, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 16 }, { 16 }, { 0 } }, + { { 0 }, { 16 }, { 0 }, { 0 } } }, + + { SVGA3D_RG_S23E8, + SVGA3DBLOCKDESC_RG_FP, + { 1, 1, 1 }, + 8, + 8, + { { 0 }, { 32 }, { 32 }, { 0 } }, + { { 0 }, { 32 }, { 0 }, { 0 } } }, + + { SVGA3D_BUFFER, + SVGA3DBLOCKDESC_BUFFER, + { 1, 1, 1 }, + 1, + 1, + { { 0 }, { 0 }, { 8 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_Z_D24X8, + SVGA3DBLOCKDESC_DEPTH_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 0 }, { 24 }, { 0 } }, + { { 0 }, { 0 }, { 8 }, { 0 } } }, + + { SVGA3D_V16U16, + SVGA3DBLOCKDESC_UV_SNORM, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 16 }, { 16 }, { 0 } }, + { { 0 }, { 16 }, { 0 }, { 0 } } }, + + { SVGA3D_G16R16, + SVGA3DBLOCKDESC_RG_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 16 }, { 16 }, { 0 } }, + { { 0 }, { 16 }, { 0 }, { 0 } } }, + + { SVGA3D_A16B16G16R16, + SVGA3DBLOCKDESC_RGBA_UNORM, + { 1, 1, 1 }, + 8, + 8, + { { 16 }, { 16 }, { 16 }, { 16 } }, + { { 32 }, { 16 }, { 0 }, { 48 } } }, + + { SVGA3D_UYVY, + SVGA3DBLOCKDESC_YUV, + { 2, 1, 1 }, + 4, + 4, + { { 8 }, { 0 }, { 8 }, { 0 } }, + { { 0 }, { 0 }, { 8 }, { 0 } } }, + + { SVGA3D_YUY2, + SVGA3DBLOCKDESC_YUV, + { 2, 1, 1 }, + 4, + 4, + { { 8 }, { 0 }, { 8 }, { 0 } }, + { { 8 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_NV12, + SVGA3DBLOCKDESC_NV12, + { 2, 2, 1 }, + 6, + 2, + { { 0 }, { 0 }, { 48 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_FORMAT_DEAD2, + SVGA3DBLOCKDESC_NONE, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 8 } }, + { { 0 }, { 8 }, { 16 }, { 24 } } }, + + { SVGA3D_R32G32B32A32_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 16, + 16, + { { 32 }, { 32 }, { 32 }, { 32 } }, + { { 64 }, { 32 }, { 0 }, { 96 } } }, + + { SVGA3D_R32G32B32A32_UINT, + SVGA3DBLOCKDESC_RGBA_UINT, + { 1, 1, 1 }, + 16, + 16, + { { 32 }, { 32 }, { 32 }, { 32 } }, + { { 64 }, { 32 }, { 0 }, { 96 } } }, + + { SVGA3D_R32G32B32A32_SINT, + SVGA3DBLOCKDESC_RGBA_SINT, + { 1, 1, 1 }, + 16, + 16, + { { 32 }, { 32 }, { 32 }, { 32 } }, + { { 64 }, { 32 }, { 0 }, { 96 } } }, + + { SVGA3D_R32G32B32_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 12, + 12, + { { 32 }, { 32 }, { 32 }, { 0 } }, + { { 64 }, { 32 }, { 0 }, { 0 } } }, + + { SVGA3D_R32G32B32_FLOAT, + SVGA3DBLOCKDESC_RGB_FP, + { 1, 1, 1 }, + 12, + 12, + { { 32 }, { 32 }, { 32 }, { 0 } }, + { { 64 }, { 32 }, { 0 }, { 0 } } }, + + { SVGA3D_R32G32B32_UINT, + SVGA3DBLOCKDESC_RGB_UINT, + { 1, 1, 1 }, + 12, + 12, + { { 32 }, { 32 }, { 32 }, { 0 } }, + { { 64 }, { 32 }, { 0 }, { 0 } } }, + + { SVGA3D_R32G32B32_SINT, + SVGA3DBLOCKDESC_RGB_SINT, + { 1, 1, 1 }, + 12, + 12, + { { 32 }, { 32 }, { 32 }, { 0 } }, + { { 64 }, { 32 }, { 0 }, { 0 } } }, + + { SVGA3D_R16G16B16A16_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 8, + 8, + { { 16 }, { 16 }, { 16 }, { 16 } }, + { { 32 }, { 16 }, { 0 }, { 48 } } }, + + { SVGA3D_R16G16B16A16_UINT, + SVGA3DBLOCKDESC_RGBA_UINT, + { 1, 1, 1 }, + 8, + 8, + { { 16 }, { 16 }, { 16 }, { 16 } }, + { { 32 }, { 16 }, { 0 }, { 48 } } }, + + { SVGA3D_R16G16B16A16_SNORM, + SVGA3DBLOCKDESC_RGBA_SNORM, + { 1, 1, 1 }, + 8, + 8, + { { 16 }, { 16 }, { 16 }, { 16 } }, + { { 32 }, { 16 }, { 0 }, { 48 } } }, + + { SVGA3D_R16G16B16A16_SINT, + SVGA3DBLOCKDESC_RGBA_SINT, + { 1, 1, 1 }, + 8, + 8, + { { 16 }, { 16 }, { 16 }, { 16 } }, + { { 32 }, { 16 }, { 0 }, { 48 } } }, + + { SVGA3D_R32G32_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 8, + 8, + { { 0 }, { 32 }, { 32 }, { 0 } }, + { { 0 }, { 32 }, { 0 }, { 0 } } }, + + { SVGA3D_R32G32_UINT, + SVGA3DBLOCKDESC_RG_UINT, + { 1, 1, 1 }, + 8, + 8, + { { 0 }, { 32 }, { 32 }, { 0 } }, + { { 0 }, { 32 }, { 0 }, { 0 } } }, + + { SVGA3D_R32G32_SINT, + SVGA3DBLOCKDESC_RG_SINT, + { 1, 1, 1 }, + 8, + 8, + { { 0 }, { 32 }, { 32 }, { 0 } }, + { { 0 }, { 32 }, { 0 }, { 0 } } }, + + { SVGA3D_R32G8X24_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 8, + 8, + { { 0 }, { 8 }, { 32 }, { 0 } }, + { { 0 }, { 32 }, { 0 }, { 0 } } }, + + { SVGA3D_D32_FLOAT_S8X24_UINT, + SVGA3DBLOCKDESC_DS, + { 1, 1, 1 }, + 8, + 8, + { { 0 }, { 8 }, { 32 }, { 0 } }, + { { 0 }, { 32 }, { 0 }, { 0 } } }, + + { SVGA3D_R32_FLOAT_X8X24, + SVGA3DBLOCKDESC_R_FP, + { 1, 1, 1 }, + 8, + 8, + { { 0 }, { 0 }, { 32 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_X32_G8X24_UINT, + SVGA3DBLOCKDESC_G_UINT, + { 1, 1, 1 }, + 8, + 8, + { { 0 }, { 8 }, { 0 }, { 0 } }, + { { 0 }, { 32 }, { 0 }, { 0 } } }, + + { SVGA3D_R10G10B10A2_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 4, + 4, + { { 10 }, { 10 }, { 10 }, { 2 } }, + { { 20 }, { 10 }, { 0 }, { 30 } } }, + + { SVGA3D_R10G10B10A2_UINT, + SVGA3DBLOCKDESC_RGBA_UINT, + { 1, 1, 1 }, + 4, + 4, + { { 10 }, { 10 }, { 10 }, { 2 } }, + { { 20 }, { 10 }, { 0 }, { 30 } } }, + + { SVGA3D_R11G11B10_FLOAT, + SVGA3DBLOCKDESC_RGB_FP, + { 1, 1, 1 }, + 4, + 4, + { { 10 }, { 11 }, { 11 }, { 0 } }, + { { 22 }, { 11 }, { 0 }, { 0 } } }, + + { SVGA3D_R8G8B8A8_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 8 } }, + { { 16 }, { 8 }, { 0 }, { 24 } } }, + + { SVGA3D_R8G8B8A8_UNORM, + SVGA3DBLOCKDESC_RGBA_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 8 } }, + { { 16 }, { 8 }, { 0 }, { 24 } } }, + + { SVGA3D_R8G8B8A8_UNORM_SRGB, + SVGA3DBLOCKDESC_RGBA_UNORM_SRGB, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 8 } }, + { { 16 }, { 8 }, { 0 }, { 24 } } }, + + { SVGA3D_R8G8B8A8_UINT, + SVGA3DBLOCKDESC_RGBA_UINT, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 8 } }, + { { 16 }, { 8 }, { 0 }, { 24 } } }, + + { SVGA3D_R8G8B8A8_SINT, + SVGA3DBLOCKDESC_RGBA_SINT, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 8 } }, + { { 16 }, { 8 }, { 0 }, { 24 } } }, + + { SVGA3D_R16G16_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 16 }, { 16 }, { 0 } }, + { { 0 }, { 16 }, { 0 }, { 0 } } }, + + { SVGA3D_R16G16_UINT, + SVGA3DBLOCKDESC_RG_UINT, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 16 }, { 16 }, { 0 } }, + { { 0 }, { 16 }, { 0 }, { 0 } } }, + + { SVGA3D_R16G16_SINT, + SVGA3DBLOCKDESC_RG_SINT, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 16 }, { 16 }, { 0 } }, + { { 0 }, { 16 }, { 0 }, { 0 } } }, + + { SVGA3D_R32_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 0 }, { 32 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_D32_FLOAT, + SVGA3DBLOCKDESC_DEPTH_FP, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 0 }, { 32 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R32_UINT, + SVGA3DBLOCKDESC_R_UINT, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 0 }, { 32 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R32_SINT, + SVGA3DBLOCKDESC_R_SINT, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 0 }, { 32 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R24G8_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 8 }, { 24 }, { 0 } }, + { { 0 }, { 24 }, { 0 }, { 0 } } }, + + { SVGA3D_D24_UNORM_S8_UINT, + SVGA3DBLOCKDESC_DS_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 8 }, { 24 }, { 0 } }, + { { 0 }, { 24 }, { 0 }, { 0 } } }, + + { SVGA3D_R24_UNORM_X8, + SVGA3DBLOCKDESC_R_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 0 }, { 24 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_X24_G8_UINT, + SVGA3DBLOCKDESC_G_UINT, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 8 }, { 0 }, { 0 } }, + { { 0 }, { 24 }, { 0 }, { 0 } } }, + + { SVGA3D_R8G8_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 8 }, { 8 }, { 0 } }, + { { 0 }, { 8 }, { 0 }, { 0 } } }, + + { SVGA3D_R8G8_UNORM, + SVGA3DBLOCKDESC_RG_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 8 }, { 8 }, { 0 } }, + { { 0 }, { 8 }, { 0 }, { 0 } } }, + + { SVGA3D_R8G8_UINT, + SVGA3DBLOCKDESC_RG_UINT, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 8 }, { 8 }, { 0 } }, + { { 0 }, { 8 }, { 0 }, { 0 } } }, + + { SVGA3D_R8G8_SINT, + SVGA3DBLOCKDESC_RG_SINT, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 8 }, { 8 }, { 0 } }, + { { 0 }, { 8 }, { 0 }, { 0 } } }, + + { SVGA3D_R16_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 0 }, { 16 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R16_UNORM, + SVGA3DBLOCKDESC_R_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 0 }, { 16 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R16_UINT, + SVGA3DBLOCKDESC_R_UINT, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 0 }, { 16 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R16_SNORM, + SVGA3DBLOCKDESC_R_SNORM, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 0 }, { 16 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R16_SINT, + SVGA3DBLOCKDESC_R_SINT, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 0 }, { 16 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R8_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 1, + 1, + { { 0 }, { 0 }, { 8 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R8_UNORM, + SVGA3DBLOCKDESC_R_UNORM, + { 1, 1, 1 }, + 1, + 1, + { { 0 }, { 0 }, { 8 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R8_UINT, + SVGA3DBLOCKDESC_R_UINT, + { 1, 1, 1 }, + 1, + 1, + { { 0 }, { 0 }, { 8 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R8_SNORM, + SVGA3DBLOCKDESC_R_SNORM, + { 1, 1, 1 }, + 1, + 1, + { { 0 }, { 0 }, { 8 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R8_SINT, + SVGA3DBLOCKDESC_R_SINT, + { 1, 1, 1 }, + 1, + 1, + { { 0 }, { 0 }, { 8 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_P8, + SVGA3DBLOCKDESC_NONE, + { 1, 1, 1 }, + 1, + 1, + { { 0 }, { 0 }, { 8 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R9G9B9E5_SHAREDEXP, + SVGA3DBLOCKDESC_RGB_EXP, + { 1, 1, 1 }, + 4, + 4, + { { 9 }, { 9 }, { 9 }, { 5 } }, + { { 18 }, { 9 }, { 0 }, { 27 } } }, + + { SVGA3D_R8G8_B8G8_UNORM, + SVGA3DBLOCKDESC_NONE, + { 2, 1, 1 }, + 4, + 4, + { { 0 }, { 8 }, { 8 }, { 0 } }, + { { 0 }, { 0 }, { 8 }, { 0 } } }, + + { SVGA3D_G8R8_G8B8_UNORM, + SVGA3DBLOCKDESC_NONE, + { 2, 1, 1 }, + 4, + 4, + { { 0 }, { 8 }, { 8 }, { 0 } }, + { { 0 }, { 8 }, { 0 }, { 0 } } }, + + { SVGA3D_BC1_TYPELESS, + SVGA3DBLOCKDESC_BC1_COMP_TYPELESS, + { 4, 4, 1 }, + 8, + 8, + { { 0 }, { 0 }, { 64 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC1_UNORM_SRGB, + SVGA3DBLOCKDESC_BC1_COMP_UNORM_SRGB, + { 4, 4, 1 }, + 8, + 8, + { { 0 }, { 0 }, { 64 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC2_TYPELESS, + SVGA3DBLOCKDESC_BC2_COMP_TYPELESS, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC2_UNORM_SRGB, + SVGA3DBLOCKDESC_BC2_COMP_UNORM_SRGB, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC3_TYPELESS, + SVGA3DBLOCKDESC_BC3_COMP_TYPELESS, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC3_UNORM_SRGB, + SVGA3DBLOCKDESC_BC3_COMP_UNORM_SRGB, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC4_TYPELESS, + SVGA3DBLOCKDESC_BC4_COMP_TYPELESS, + { 4, 4, 1 }, + 8, + 8, + { { 0 }, { 0 }, { 64 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_ATI1, + SVGA3DBLOCKDESC_BC4_COMP_UNORM, + { 4, 4, 1 }, + 8, + 8, + { { 0 }, { 0 }, { 64 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC4_SNORM, + SVGA3DBLOCKDESC_BC4_COMP_SNORM, + { 4, 4, 1 }, + 8, + 8, + { { 0 }, { 0 }, { 64 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC5_TYPELESS, + SVGA3DBLOCKDESC_BC5_COMP_TYPELESS, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_ATI2, + SVGA3DBLOCKDESC_BC5_COMP_UNORM, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC5_SNORM, + SVGA3DBLOCKDESC_BC5_COMP_SNORM, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R10G10B10_XR_BIAS_A2_UNORM, + SVGA3DBLOCKDESC_RGBA_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 10 }, { 10 }, { 10 }, { 2 } }, + { { 20 }, { 10 }, { 0 }, { 30 } } }, + + { SVGA3D_B8G8R8A8_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 8 } }, + { { 0 }, { 8 }, { 16 }, { 24 } } }, + + { SVGA3D_B8G8R8A8_UNORM_SRGB, + SVGA3DBLOCKDESC_RGBA_UNORM_SRGB, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 8 } }, + { { 0 }, { 8 }, { 16 }, { 24 } } }, + + { SVGA3D_B8G8R8X8_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 0 } }, + { { 0 }, { 8 }, { 16 }, { 24 } } }, + + { SVGA3D_B8G8R8X8_UNORM_SRGB, + SVGA3DBLOCKDESC_RGB_UNORM_SRGB, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 0 } }, + { { 0 }, { 8 }, { 16 }, { 24 } } }, + + { SVGA3D_Z_DF16, + SVGA3DBLOCKDESC_DEPTH_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 0 }, { 16 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_Z_DF24, + SVGA3DBLOCKDESC_DEPTH_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 0 }, { 24 }, { 0 } }, + { { 0 }, { 0 }, { 8 }, { 0 } } }, + + { SVGA3D_Z_D24S8_INT, + SVGA3DBLOCKDESC_DS_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 8 }, { 24 }, { 0 } }, + { { 0 }, { 0 }, { 8 }, { 0 } } }, + + { SVGA3D_YV12, + SVGA3DBLOCKDESC_YV12, + { 2, 2, 1 }, + 6, + 2, + { { 0 }, { 0 }, { 48 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R32G32B32A32_FLOAT, + SVGA3DBLOCKDESC_RGBA_FP, + { 1, 1, 1 }, + 16, + 16, + { { 32 }, { 32 }, { 32 }, { 32 } }, + { { 64 }, { 32 }, { 0 }, { 96 } } }, + + { SVGA3D_R16G16B16A16_FLOAT, + SVGA3DBLOCKDESC_RGBA_FP, + { 1, 1, 1 }, + 8, + 8, + { { 16 }, { 16 }, { 16 }, { 16 } }, + { { 32 }, { 16 }, { 0 }, { 48 } } }, + + { SVGA3D_R16G16B16A16_UNORM, + SVGA3DBLOCKDESC_RGBA_UNORM, + { 1, 1, 1 }, + 8, + 8, + { { 16 }, { 16 }, { 16 }, { 16 } }, + { { 32 }, { 16 }, { 0 }, { 48 } } }, + + { SVGA3D_R32G32_FLOAT, + SVGA3DBLOCKDESC_RG_FP, + { 1, 1, 1 }, + 8, + 8, + { { 0 }, { 32 }, { 32 }, { 0 } }, + { { 0 }, { 32 }, { 0 }, { 0 } } }, + + { SVGA3D_R10G10B10A2_UNORM, + SVGA3DBLOCKDESC_RGBA_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 10 }, { 10 }, { 10 }, { 2 } }, + { { 20 }, { 10 }, { 0 }, { 30 } } }, + + { SVGA3D_R8G8B8A8_SNORM, + SVGA3DBLOCKDESC_RGBA_SNORM, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 8 } }, + { { 16 }, { 8 }, { 0 }, { 24 } } }, + + { SVGA3D_R16G16_FLOAT, + SVGA3DBLOCKDESC_RG_FP, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 16 }, { 16 }, { 0 } }, + { { 0 }, { 16 }, { 0 }, { 0 } } }, + + { SVGA3D_R16G16_UNORM, + SVGA3DBLOCKDESC_RG_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 16 }, { 16 }, { 0 } }, + { { 0 }, { 16 }, { 0 }, { 0 } } }, + + { SVGA3D_R16G16_SNORM, + SVGA3DBLOCKDESC_RG_SNORM, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 16 }, { 16 }, { 0 } }, + { { 0 }, { 16 }, { 0 }, { 0 } } }, + + { SVGA3D_R32_FLOAT, + SVGA3DBLOCKDESC_R_FP, + { 1, 1, 1 }, + 4, + 4, + { { 0 }, { 0 }, { 32 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_R8G8_SNORM, + SVGA3DBLOCKDESC_RG_SNORM, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 8 }, { 8 }, { 0 } }, + { { 0 }, { 8 }, { 0 }, { 0 } } }, + + { SVGA3D_R16_FLOAT, + SVGA3DBLOCKDESC_R_FP, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 0 }, { 16 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_D16_UNORM, + SVGA3DBLOCKDESC_DEPTH_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 0 }, { 0 }, { 16 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_A8_UNORM, + SVGA3DBLOCKDESC_A_UNORM, + { 1, 1, 1 }, + 1, + 1, + { { 0 }, { 0 }, { 0 }, { 8 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC1_UNORM, + SVGA3DBLOCKDESC_BC1_COMP_UNORM, + { 4, 4, 1 }, + 8, + 8, + { { 0 }, { 0 }, { 64 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC2_UNORM, + SVGA3DBLOCKDESC_BC2_COMP_UNORM, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC3_UNORM, + SVGA3DBLOCKDESC_BC3_COMP_UNORM, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_B5G6R5_UNORM, + SVGA3DBLOCKDESC_RGB_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 5 }, { 6 }, { 5 }, { 0 } }, + { { 0 }, { 5 }, { 11 }, { 0 } } }, + + { SVGA3D_B5G5R5A1_UNORM, + SVGA3DBLOCKDESC_RGBA_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 5 }, { 5 }, { 5 }, { 1 } }, + { { 0 }, { 5 }, { 10 }, { 15 } } }, + + { SVGA3D_B8G8R8A8_UNORM, + SVGA3DBLOCKDESC_RGBA_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 8 } }, + { { 0 }, { 8 }, { 16 }, { 24 } } }, + + { SVGA3D_B8G8R8X8_UNORM, + SVGA3DBLOCKDESC_RGB_UNORM, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 0 } }, + { { 0 }, { 8 }, { 16 }, { 24 } } }, + + { SVGA3D_BC4_UNORM, + SVGA3DBLOCKDESC_BC4_COMP_UNORM, + { 4, 4, 1 }, + 8, + 8, + { { 0 }, { 0 }, { 64 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC5_UNORM, + SVGA3DBLOCKDESC_BC5_COMP_UNORM, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_B4G4R4A4_UNORM, + SVGA3DBLOCKDESC_RGBA_UNORM, + { 1, 1, 1 }, + 2, + 2, + { { 4 }, { 4 }, { 4 }, { 4 } }, + { { 0 }, { 4 }, { 8 }, { 12 } } }, + + { SVGA3D_BC6H_TYPELESS, + SVGA3DBLOCKDESC_BC6H_COMP_TYPELESS, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC6H_UF16, + SVGA3DBLOCKDESC_BC6H_COMP_UF16, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC6H_SF16, + SVGA3DBLOCKDESC_BC6H_COMP_SF16, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC7_TYPELESS, + SVGA3DBLOCKDESC_BC7_COMP_TYPELESS, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC7_UNORM, + SVGA3DBLOCKDESC_BC7_COMP_UNORM, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_BC7_UNORM_SRGB, + SVGA3DBLOCKDESC_BC7_COMP_UNORM_SRGB, + { 4, 4, 1 }, + 16, + 16, + { { 0 }, { 0 }, { 128 }, { 0 } }, + { { 0 }, { 0 }, { 0 }, { 0 } } }, + + { SVGA3D_AYUV, + SVGA3DBLOCKDESC_AYUV, + { 1, 1, 1 }, + 4, + 4, + { { 8 }, { 8 }, { 8 }, { 8 } }, + { { 0 }, { 8 }, { 16 }, { 24 } } }, + + { SVGA3D_R11G11B10_TYPELESS, + SVGA3DBLOCKDESC_TYPELESS, + { 1, 1, 1 }, + 4, + 4, + { { 10 }, { 11 }, { 11 }, { 0 } }, + { { 22 }, { 11 }, { 0 }, { 0 } } }, }; -/** - * svga3dsurface_subres - Compute the subresource from layer and mipmap. - * @cache: Surface layout data. - * @mip_level: The mipmap level. - * @layer: The surface layer (face or array slice). - * - * Return: The subresource. - */ -static inline u32 svga3dsurface_subres(const struct svga3dsurface_cache *cache, - u32 mip_level, u32 layer) -{ - return cache->num_mip_levels * layer + mip_level; -} - -/** - * svga3dsurface_setup_cache - Build a surface cache entry - * @size: The surface base level dimensions. - * @format: The surface format. - * @num_mip_levels: Number of mipmap levels. - * @num_layers: Number of layers. - * @cache: Pointer to a struct svga3dsurface_cach object to be filled in. - * - * Return: Zero on success, -EINVAL on invalid surface layout. - */ -static inline int svga3dsurface_setup_cache(const struct drm_vmw_size *size, - SVGA3dSurfaceFormat format, - u32 num_mip_levels, - u32 num_layers, - u32 num_samples, - struct svga3dsurface_cache *cache) -{ - const struct svga3d_surface_desc *desc; - u32 i; - - memset(cache, 0, sizeof(*cache)); - cache->desc = desc = svga3dsurface_get_desc(format); - cache->num_mip_levels = num_mip_levels; - cache->num_layers = num_layers; - for (i = 0; i < cache->num_mip_levels; i++) { - struct svga3dsurface_mip *mip = &cache->mip[i]; - - mip->size = svga3dsurface_get_mip_size(*size, i); - mip->bytes = svga3dsurface_get_image_buffer_size - (desc, &mip->size, 0); - mip->row_stride = - __KERNEL_DIV_ROUND_UP(mip->size.width, - desc->block_size.width) * - desc->bytes_per_block * num_samples; - if (!mip->row_stride) - goto invalid_dim; - - mip->img_stride = - __KERNEL_DIV_ROUND_UP(mip->size.height, - desc->block_size.height) * - mip->row_stride; - if (!mip->img_stride) - goto invalid_dim; - - cache->mip_chain_bytes += mip->bytes; - } - cache->sheet_bytes = cache->mip_chain_bytes * num_layers; - if (!cache->sheet_bytes) - goto invalid_dim; - - return 0; - -invalid_dim: - VMW_DEBUG_USER("Invalid surface layout for dirty tracking.\n"); - return -EINVAL; -} - -/** - * svga3dsurface_get_loc - Get a surface location from an offset into the - * backing store - * @cache: Surface layout data. - * @loc: Pointer to a struct svga3dsurface_loc to be filled in. - * @offset: Offset into the surface backing store. - */ -static inline void -svga3dsurface_get_loc(const struct svga3dsurface_cache *cache, - struct svga3dsurface_loc *loc, - size_t offset) -{ - const struct svga3dsurface_mip *mip = &cache->mip[0]; - const struct svga3d_surface_desc *desc = cache->desc; - u32 layer; - int i; - - loc->sheet = offset / cache->sheet_bytes; - offset -= loc->sheet * cache->sheet_bytes; - - layer = offset / cache->mip_chain_bytes; - offset -= layer * cache->mip_chain_bytes; - for (i = 0; i < cache->num_mip_levels; ++i, ++mip) { - if (mip->bytes > offset) - break; - offset -= mip->bytes; - } - - loc->sub_resource = svga3dsurface_subres(cache, i, layer); - loc->z = offset / mip->img_stride; - offset -= loc->z * mip->img_stride; - loc->z *= desc->block_size.depth; - loc->y = offset / mip->row_stride; - offset -= loc->y * mip->row_stride; - loc->y *= desc->block_size.height; - loc->x = offset / desc->bytes_per_block; - loc->x *= desc->block_size.width; -} - -/** - * svga3dsurface_inc_loc - Clamp increment a surface location with one block - * size - * in each dimension. - * @loc: Pointer to a struct svga3dsurface_loc to be incremented. - * - * When computing the size of a range as size = end - start, the range does not - * include the end element. However a location representing the last byte - * of a touched region in the backing store *is* included in the range. - * This function modifies such a location to match the end definition - * given as start + size which is the one used in a SVGA3dBox. - */ -static inline void -svga3dsurface_inc_loc(const struct svga3dsurface_cache *cache, - struct svga3dsurface_loc *loc) -{ - const struct svga3d_surface_desc *desc = cache->desc; - u32 mip = loc->sub_resource % cache->num_mip_levels; - const struct drm_vmw_size *size = &cache->mip[mip].size; - - loc->sub_resource++; - loc->x += desc->block_size.width; - if (loc->x > size->width) - loc->x = size->width; - loc->y += desc->block_size.height; - if (loc->y > size->height) - loc->y = size->height; - loc->z += desc->block_size.depth; - if (loc->z > size->depth) - loc->z = size->depth; -} - -/** - * svga3dsurface_min_loc - The start location in a subresource - * @cache: Surface layout data. - * @sub_resource: The subresource. - * @loc: Pointer to a struct svga3dsurface_loc to be filled in. - */ -static inline void -svga3dsurface_min_loc(const struct svga3dsurface_cache *cache, - u32 sub_resource, - struct svga3dsurface_loc *loc) -{ - loc->sheet = 0; - loc->sub_resource = sub_resource; - loc->x = loc->y = loc->z = 0; -} - -/** - * svga3dsurface_min_loc - The end location in a subresource - * @cache: Surface layout data. - * @sub_resource: The subresource. - * @loc: Pointer to a struct svga3dsurface_loc to be filled in. - * - * Following the end definition given in svga3dsurface_inc_loc(), - * Compute the end location of a surface subresource. - */ -static inline void -svga3dsurface_max_loc(const struct svga3dsurface_cache *cache, - u32 sub_resource, - struct svga3dsurface_loc *loc) -{ - const struct drm_vmw_size *size; - u32 mip; - - loc->sheet = 0; - loc->sub_resource = sub_resource + 1; - mip = sub_resource % cache->num_mip_levels; - size = &cache->mip[mip].size; - loc->x = size->width; - loc->y = size->height; - loc->z = size->depth; +#ifdef __cplusplus } +#endif -#endif /* _SVGA3D_SURFACEDEFS_H_ */ +#endif diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h index 77e338a65791..70b88ee16cf6 100644 --- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h +++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h @@ -1,6 +1,6 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT */ /********************************************************** - * Copyright 2012-2015 VMware, Inc. + * Copyright 2012-2021 VMware, Inc. + * SPDX-License-Identifier: GPL-2.0 OR MIT * * Permission is hereby granted, free of charge, to any person * obtaining a copy of this software and associated documentation @@ -27,1974 +27,1530 @@ /* * svga3d_types.h -- * - * SVGA 3d hardware definitions for basic types + * SVGA 3d hardware definitions for basic types */ + + #ifndef _SVGA3D_TYPES_H_ #define _SVGA3D_TYPES_H_ -#define INCLUDE_ALLOW_MODULE -#define INCLUDE_ALLOW_USERLEVEL -#define INCLUDE_ALLOW_VMCORE - -#include "includeCheck.h" +#include "vm_basic_types.h" -/* - * Generic Types - */ +#define SVGA3D_INVALID_ID ((uint32)-1) -#define SVGA3D_INVALID_ID ((uint32)-1) +#define SVGA3D_RESOURCE_TYPE_MIN 1 +#define SVGA3D_RESOURCE_BUFFER 1 +#define SVGA3D_RESOURCE_TEXTURE1D 2 +#define SVGA3D_RESOURCE_TEXTURE2D 3 +#define SVGA3D_RESOURCE_TEXTURE3D 4 +#define SVGA3D_RESOURCE_TEXTURECUBE 5 +#define SVGA3D_RESOURCE_TYPE_DX10_MAX 6 +#define SVGA3D_RESOURCE_BUFFEREX 6 +#define SVGA3D_RESOURCE_TYPE_MAX 7 +typedef uint32 SVGA3dResourceType; -typedef uint8 SVGABool8; /* 8-bit Bool definition */ -typedef uint32 SVGA3dBool; /* 32-bit Bool definition */ -typedef uint32 SVGA3dColor; /* a, r, g, b */ +typedef uint8 SVGABool8; +typedef uint32 SVGA3dBool; +typedef uint32 SVGA3dColor; typedef uint32 SVGA3dSurfaceId; -typedef -#include "vmware_pack_begin.h" -struct { - uint32 numerator; - uint32 denominator; -} -#include "vmware_pack_end.h" -SVGA3dFraction64; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCopyRect { - uint32 x; - uint32 y; - uint32 w; - uint32 h; - uint32 srcx; - uint32 srcy; -} -#include "vmware_pack_end.h" -SVGA3dCopyRect; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dCopyBox { - uint32 x; - uint32 y; - uint32 z; - uint32 w; - uint32 h; - uint32 d; - uint32 srcx; - uint32 srcy; - uint32 srcz; -} -#include "vmware_pack_end.h" -SVGA3dCopyBox; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dRect { - uint32 x; - uint32 y; - uint32 w; - uint32 h; -} -#include "vmware_pack_end.h" -SVGA3dRect; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 x; - uint32 y; - uint32 z; - uint32 w; - uint32 h; - uint32 d; -} -#include "vmware_pack_end.h" -SVGA3dBox; - -typedef -#include "vmware_pack_begin.h" -struct { - int32 x; - int32 y; - int32 z; - int32 w; - int32 h; - int32 d; -} -#include "vmware_pack_end.h" -SVGA3dSignedBox; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 x; - uint32 y; - uint32 z; -} -#include "vmware_pack_end.h" -SVGA3dPoint; +#pragma pack(push, 1) +typedef struct { + uint32 numerator; + uint32 denominator; +} SVGA3dFraction64; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCopyRect { + uint32 x; + uint32 y; + uint32 w; + uint32 h; + uint32 srcx; + uint32 srcy; +} SVGA3dCopyRect; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dCopyBox { + uint32 x; + uint32 y; + uint32 z; + uint32 w; + uint32 h; + uint32 d; + uint32 srcx; + uint32 srcy; + uint32 srcz; +} SVGA3dCopyBox; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dRect { + uint32 x; + uint32 y; + uint32 w; + uint32 h; +} SVGA3dRect; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 x; + uint32 y; + uint32 z; + uint32 w; + uint32 h; + uint32 d; +} SVGA3dBox; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + int32 x; + int32 y; + int32 z; + int32 w; + int32 h; + int32 d; +} SVGA3dSignedBox; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 x; + uint32 y; + uint32 z; +} SVGA3dPoint; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef union { + struct { + float r; + float g; + float b; + float a; + }; + + float value[4]; +} SVGA3dRGBAFloat; +#pragma pack(pop) -/* - * Surface formats. - */ typedef enum SVGA3dSurfaceFormat { - SVGA3D_FORMAT_INVALID = 0, - - SVGA3D_X8R8G8B8 = 1, - SVGA3D_FORMAT_MIN = 1, - - SVGA3D_A8R8G8B8 = 2, - - SVGA3D_R5G6B5 = 3, - SVGA3D_X1R5G5B5 = 4, - SVGA3D_A1R5G5B5 = 5, - SVGA3D_A4R4G4B4 = 6, - - SVGA3D_Z_D32 = 7, - SVGA3D_Z_D16 = 8, - SVGA3D_Z_D24S8 = 9, - SVGA3D_Z_D15S1 = 10, - - SVGA3D_LUMINANCE8 = 11, - SVGA3D_LUMINANCE4_ALPHA4 = 12, - SVGA3D_LUMINANCE16 = 13, - SVGA3D_LUMINANCE8_ALPHA8 = 14, - - SVGA3D_DXT1 = 15, - SVGA3D_DXT2 = 16, - SVGA3D_DXT3 = 17, - SVGA3D_DXT4 = 18, - SVGA3D_DXT5 = 19, - - SVGA3D_BUMPU8V8 = 20, - SVGA3D_BUMPL6V5U5 = 21, - SVGA3D_BUMPX8L8V8U8 = 22, - SVGA3D_FORMAT_DEAD1 = 23, - - SVGA3D_ARGB_S10E5 = 24, /* 16-bit floating-point ARGB */ - SVGA3D_ARGB_S23E8 = 25, /* 32-bit floating-point ARGB */ - - SVGA3D_A2R10G10B10 = 26, - - /* signed formats */ - SVGA3D_V8U8 = 27, - SVGA3D_Q8W8V8U8 = 28, - SVGA3D_CxV8U8 = 29, - - /* mixed formats */ - SVGA3D_X8L8V8U8 = 30, - SVGA3D_A2W10V10U10 = 31, - - SVGA3D_ALPHA8 = 32, - - /* Single- and dual-component floating point formats */ - SVGA3D_R_S10E5 = 33, - SVGA3D_R_S23E8 = 34, - SVGA3D_RG_S10E5 = 35, - SVGA3D_RG_S23E8 = 36, - - SVGA3D_BUFFER = 37, - - SVGA3D_Z_D24X8 = 38, - - SVGA3D_V16U16 = 39, - - SVGA3D_G16R16 = 40, - SVGA3D_A16B16G16R16 = 41, - - /* Packed Video formats */ - SVGA3D_UYVY = 42, - SVGA3D_YUY2 = 43, - - /* Planar video formats */ - SVGA3D_NV12 = 44, - - SVGA3D_FORMAT_DEAD2 = 45, - - SVGA3D_R32G32B32A32_TYPELESS = 46, - SVGA3D_R32G32B32A32_UINT = 47, - SVGA3D_R32G32B32A32_SINT = 48, - SVGA3D_R32G32B32_TYPELESS = 49, - SVGA3D_R32G32B32_FLOAT = 50, - SVGA3D_R32G32B32_UINT = 51, - SVGA3D_R32G32B32_SINT = 52, - SVGA3D_R16G16B16A16_TYPELESS = 53, - SVGA3D_R16G16B16A16_UINT = 54, - SVGA3D_R16G16B16A16_SNORM = 55, - SVGA3D_R16G16B16A16_SINT = 56, - SVGA3D_R32G32_TYPELESS = 57, - SVGA3D_R32G32_UINT = 58, - SVGA3D_R32G32_SINT = 59, - SVGA3D_R32G8X24_TYPELESS = 60, - SVGA3D_D32_FLOAT_S8X24_UINT = 61, - SVGA3D_R32_FLOAT_X8X24 = 62, - SVGA3D_X32_G8X24_UINT = 63, - SVGA3D_R10G10B10A2_TYPELESS = 64, - SVGA3D_R10G10B10A2_UINT = 65, - SVGA3D_R11G11B10_FLOAT = 66, - SVGA3D_R8G8B8A8_TYPELESS = 67, - SVGA3D_R8G8B8A8_UNORM = 68, - SVGA3D_R8G8B8A8_UNORM_SRGB = 69, - SVGA3D_R8G8B8A8_UINT = 70, - SVGA3D_R8G8B8A8_SINT = 71, - SVGA3D_R16G16_TYPELESS = 72, - SVGA3D_R16G16_UINT = 73, - SVGA3D_R16G16_SINT = 74, - SVGA3D_R32_TYPELESS = 75, - SVGA3D_D32_FLOAT = 76, - SVGA3D_R32_UINT = 77, - SVGA3D_R32_SINT = 78, - SVGA3D_R24G8_TYPELESS = 79, - SVGA3D_D24_UNORM_S8_UINT = 80, - SVGA3D_R24_UNORM_X8 = 81, - SVGA3D_X24_G8_UINT = 82, - SVGA3D_R8G8_TYPELESS = 83, - SVGA3D_R8G8_UNORM = 84, - SVGA3D_R8G8_UINT = 85, - SVGA3D_R8G8_SINT = 86, - SVGA3D_R16_TYPELESS = 87, - SVGA3D_R16_UNORM = 88, - SVGA3D_R16_UINT = 89, - SVGA3D_R16_SNORM = 90, - SVGA3D_R16_SINT = 91, - SVGA3D_R8_TYPELESS = 92, - SVGA3D_R8_UNORM = 93, - SVGA3D_R8_UINT = 94, - SVGA3D_R8_SNORM = 95, - SVGA3D_R8_SINT = 96, - SVGA3D_P8 = 97, - SVGA3D_R9G9B9E5_SHAREDEXP = 98, - SVGA3D_R8G8_B8G8_UNORM = 99, - SVGA3D_G8R8_G8B8_UNORM = 100, - SVGA3D_BC1_TYPELESS = 101, - SVGA3D_BC1_UNORM_SRGB = 102, - SVGA3D_BC2_TYPELESS = 103, - SVGA3D_BC2_UNORM_SRGB = 104, - SVGA3D_BC3_TYPELESS = 105, - SVGA3D_BC3_UNORM_SRGB = 106, - SVGA3D_BC4_TYPELESS = 107, - SVGA3D_ATI1 = 108, /* DX9-specific BC4_UNORM */ - SVGA3D_BC4_SNORM = 109, - SVGA3D_BC5_TYPELESS = 110, - SVGA3D_ATI2 = 111, /* DX9-specific BC5_UNORM */ - SVGA3D_BC5_SNORM = 112, - SVGA3D_R10G10B10_XR_BIAS_A2_UNORM = 113, - SVGA3D_B8G8R8A8_TYPELESS = 114, - SVGA3D_B8G8R8A8_UNORM_SRGB = 115, - SVGA3D_B8G8R8X8_TYPELESS = 116, - SVGA3D_B8G8R8X8_UNORM_SRGB = 117, - - /* Advanced depth formats. */ - SVGA3D_Z_DF16 = 118, - SVGA3D_Z_DF24 = 119, - SVGA3D_Z_D24S8_INT = 120, - - /* Planar video formats. */ - SVGA3D_YV12 = 121, - - SVGA3D_R32G32B32A32_FLOAT = 122, - SVGA3D_R16G16B16A16_FLOAT = 123, - SVGA3D_R16G16B16A16_UNORM = 124, - SVGA3D_R32G32_FLOAT = 125, - SVGA3D_R10G10B10A2_UNORM = 126, - SVGA3D_R8G8B8A8_SNORM = 127, - SVGA3D_R16G16_FLOAT = 128, - SVGA3D_R16G16_UNORM = 129, - SVGA3D_R16G16_SNORM = 130, - SVGA3D_R32_FLOAT = 131, - SVGA3D_R8G8_SNORM = 132, - SVGA3D_R16_FLOAT = 133, - SVGA3D_D16_UNORM = 134, - SVGA3D_A8_UNORM = 135, - SVGA3D_BC1_UNORM = 136, - SVGA3D_BC2_UNORM = 137, - SVGA3D_BC3_UNORM = 138, - SVGA3D_B5G6R5_UNORM = 139, - SVGA3D_B5G5R5A1_UNORM = 140, - SVGA3D_B8G8R8A8_UNORM = 141, - SVGA3D_B8G8R8X8_UNORM = 142, - SVGA3D_BC4_UNORM = 143, - SVGA3D_BC5_UNORM = 144, - SVGA3D_B4G4R4A4_UNORM = 145, - - /* DX11 compressed formats */ - SVGA3D_BC6H_TYPELESS = 146, - SVGA3D_BC6H_UF16 = 147, - SVGA3D_BC6H_SF16 = 148, - SVGA3D_BC7_TYPELESS = 149, - SVGA3D_BC7_UNORM = 150, - SVGA3D_BC7_UNORM_SRGB = 151, - - /* Video format with alpha */ - SVGA3D_AYUV = 152, - - SVGA3D_FORMAT_MAX + SVGA3D_FORMAT_INVALID = 0, + + SVGA3D_X8R8G8B8 = 1, + SVGA3D_FORMAT_MIN = 1, + + SVGA3D_A8R8G8B8 = 2, + + SVGA3D_R5G6B5 = 3, + SVGA3D_X1R5G5B5 = 4, + SVGA3D_A1R5G5B5 = 5, + SVGA3D_A4R4G4B4 = 6, + + SVGA3D_Z_D32 = 7, + SVGA3D_Z_D16 = 8, + SVGA3D_Z_D24S8 = 9, + SVGA3D_Z_D15S1 = 10, + + SVGA3D_LUMINANCE8 = 11, + SVGA3D_LUMINANCE4_ALPHA4 = 12, + SVGA3D_LUMINANCE16 = 13, + SVGA3D_LUMINANCE8_ALPHA8 = 14, + + SVGA3D_DXT1 = 15, + SVGA3D_DXT2 = 16, + SVGA3D_DXT3 = 17, + SVGA3D_DXT4 = 18, + SVGA3D_DXT5 = 19, + + SVGA3D_BUMPU8V8 = 20, + SVGA3D_BUMPL6V5U5 = 21, + SVGA3D_BUMPX8L8V8U8 = 22, + SVGA3D_FORMAT_DEAD1 = 23, + + SVGA3D_ARGB_S10E5 = 24, + SVGA3D_ARGB_S23E8 = 25, + + SVGA3D_A2R10G10B10 = 26, + + SVGA3D_V8U8 = 27, + SVGA3D_Q8W8V8U8 = 28, + SVGA3D_CxV8U8 = 29, + + SVGA3D_X8L8V8U8 = 30, + SVGA3D_A2W10V10U10 = 31, + + SVGA3D_ALPHA8 = 32, + + SVGA3D_R_S10E5 = 33, + SVGA3D_R_S23E8 = 34, + SVGA3D_RG_S10E5 = 35, + SVGA3D_RG_S23E8 = 36, + + SVGA3D_BUFFER = 37, + + SVGA3D_Z_D24X8 = 38, + + SVGA3D_V16U16 = 39, + + SVGA3D_G16R16 = 40, + SVGA3D_A16B16G16R16 = 41, + + SVGA3D_UYVY = 42, + SVGA3D_YUY2 = 43, + + SVGA3D_NV12 = 44, + + SVGA3D_FORMAT_DEAD2 = 45, + + SVGA3D_R32G32B32A32_TYPELESS = 46, + SVGA3D_R32G32B32A32_UINT = 47, + SVGA3D_R32G32B32A32_SINT = 48, + SVGA3D_R32G32B32_TYPELESS = 49, + SVGA3D_R32G32B32_FLOAT = 50, + SVGA3D_R32G32B32_UINT = 51, + SVGA3D_R32G32B32_SINT = 52, + SVGA3D_R16G16B16A16_TYPELESS = 53, + SVGA3D_R16G16B16A16_UINT = 54, + SVGA3D_R16G16B16A16_SNORM = 55, + SVGA3D_R16G16B16A16_SINT = 56, + SVGA3D_R32G32_TYPELESS = 57, + SVGA3D_R32G32_UINT = 58, + SVGA3D_R32G32_SINT = 59, + SVGA3D_R32G8X24_TYPELESS = 60, + SVGA3D_D32_FLOAT_S8X24_UINT = 61, + SVGA3D_R32_FLOAT_X8X24 = 62, + SVGA3D_X32_G8X24_UINT = 63, + SVGA3D_R10G10B10A2_TYPELESS = 64, + SVGA3D_R10G10B10A2_UINT = 65, + SVGA3D_R11G11B10_FLOAT = 66, + SVGA3D_R8G8B8A8_TYPELESS = 67, + SVGA3D_R8G8B8A8_UNORM = 68, + SVGA3D_R8G8B8A8_UNORM_SRGB = 69, + SVGA3D_R8G8B8A8_UINT = 70, + SVGA3D_R8G8B8A8_SINT = 71, + SVGA3D_R16G16_TYPELESS = 72, + SVGA3D_R16G16_UINT = 73, + SVGA3D_R16G16_SINT = 74, + SVGA3D_R32_TYPELESS = 75, + SVGA3D_D32_FLOAT = 76, + SVGA3D_R32_UINT = 77, + SVGA3D_R32_SINT = 78, + SVGA3D_R24G8_TYPELESS = 79, + SVGA3D_D24_UNORM_S8_UINT = 80, + SVGA3D_R24_UNORM_X8 = 81, + SVGA3D_X24_G8_UINT = 82, + SVGA3D_R8G8_TYPELESS = 83, + SVGA3D_R8G8_UNORM = 84, + SVGA3D_R8G8_UINT = 85, + SVGA3D_R8G8_SINT = 86, + SVGA3D_R16_TYPELESS = 87, + SVGA3D_R16_UNORM = 88, + SVGA3D_R16_UINT = 89, + SVGA3D_R16_SNORM = 90, + SVGA3D_R16_SINT = 91, + SVGA3D_R8_TYPELESS = 92, + SVGA3D_R8_UNORM = 93, + SVGA3D_R8_UINT = 94, + SVGA3D_R8_SNORM = 95, + SVGA3D_R8_SINT = 96, + SVGA3D_P8 = 97, + SVGA3D_R9G9B9E5_SHAREDEXP = 98, + SVGA3D_R8G8_B8G8_UNORM = 99, + SVGA3D_G8R8_G8B8_UNORM = 100, + SVGA3D_BC1_TYPELESS = 101, + SVGA3D_BC1_UNORM_SRGB = 102, + SVGA3D_BC2_TYPELESS = 103, + SVGA3D_BC2_UNORM_SRGB = 104, + SVGA3D_BC3_TYPELESS = 105, + SVGA3D_BC3_UNORM_SRGB = 106, + SVGA3D_BC4_TYPELESS = 107, + SVGA3D_ATI1 = 108, + SVGA3D_BC4_SNORM = 109, + SVGA3D_BC5_TYPELESS = 110, + SVGA3D_ATI2 = 111, + SVGA3D_BC5_SNORM = 112, + SVGA3D_R10G10B10_XR_BIAS_A2_UNORM = 113, + SVGA3D_B8G8R8A8_TYPELESS = 114, + SVGA3D_B8G8R8A8_UNORM_SRGB = 115, + SVGA3D_B8G8R8X8_TYPELESS = 116, + SVGA3D_B8G8R8X8_UNORM_SRGB = 117, + + SVGA3D_Z_DF16 = 118, + SVGA3D_Z_DF24 = 119, + SVGA3D_Z_D24S8_INT = 120, + + SVGA3D_YV12 = 121, + + SVGA3D_R32G32B32A32_FLOAT = 122, + SVGA3D_R16G16B16A16_FLOAT = 123, + SVGA3D_R16G16B16A16_UNORM = 124, + SVGA3D_R32G32_FLOAT = 125, + SVGA3D_R10G10B10A2_UNORM = 126, + SVGA3D_R8G8B8A8_SNORM = 127, + SVGA3D_R16G16_FLOAT = 128, + SVGA3D_R16G16_UNORM = 129, + SVGA3D_R16G16_SNORM = 130, + SVGA3D_R32_FLOAT = 131, + SVGA3D_R8G8_SNORM = 132, + SVGA3D_R16_FLOAT = 133, + SVGA3D_D16_UNORM = 134, + SVGA3D_A8_UNORM = 135, + SVGA3D_BC1_UNORM = 136, + SVGA3D_BC2_UNORM = 137, + SVGA3D_BC3_UNORM = 138, + SVGA3D_B5G6R5_UNORM = 139, + SVGA3D_B5G5R5A1_UNORM = 140, + SVGA3D_B8G8R8A8_UNORM = 141, + SVGA3D_B8G8R8X8_UNORM = 142, + SVGA3D_BC4_UNORM = 143, + SVGA3D_BC5_UNORM = 144, + SVGA3D_B4G4R4A4_UNORM = 145, + + SVGA3D_BC6H_TYPELESS = 146, + SVGA3D_BC6H_UF16 = 147, + SVGA3D_BC6H_SF16 = 148, + SVGA3D_BC7_TYPELESS = 149, + SVGA3D_BC7_UNORM = 150, + SVGA3D_BC7_UNORM_SRGB = 151, + + SVGA3D_AYUV = 152, + + SVGA3D_R11G11B10_TYPELESS = 153, + + SVGA3D_FORMAT_MAX } SVGA3dSurfaceFormat; -/* - * SVGA3d Surface Flags -- - */ -#define SVGA3D_SURFACE_CUBEMAP (1 << 0) +#define SVGA3D_SURFACE_CUBEMAP (1 << 0) -/* - * HINT flags are not enforced by the device but are useful for - * performance. - */ -#define SVGA3D_SURFACE_HINT_STATIC (CONST64U(1) << 1) -#define SVGA3D_SURFACE_HINT_DYNAMIC (CONST64U(1) << 2) -#define SVGA3D_SURFACE_HINT_INDEXBUFFER (CONST64U(1) << 3) -#define SVGA3D_SURFACE_HINT_VERTEXBUFFER (CONST64U(1) << 4) -#define SVGA3D_SURFACE_HINT_TEXTURE (CONST64U(1) << 5) -#define SVGA3D_SURFACE_HINT_RENDERTARGET (CONST64U(1) << 6) -#define SVGA3D_SURFACE_HINT_DEPTHSTENCIL (CONST64U(1) << 7) -#define SVGA3D_SURFACE_HINT_WRITEONLY (CONST64U(1) << 8) -#define SVGA3D_SURFACE_DEAD2 (CONST64U(1) << 9) -#define SVGA3D_SURFACE_AUTOGENMIPMAPS (CONST64U(1) << 10) - -#define SVGA3D_SURFACE_DEAD1 (CONST64U(1) << 11) +#define SVGA3D_SURFACE_HINT_STATIC (CONST64U(1) << 1) +#define SVGA3D_SURFACE_HINT_DYNAMIC (CONST64U(1) << 2) +#define SVGA3D_SURFACE_HINT_INDEXBUFFER (CONST64U(1) << 3) +#define SVGA3D_SURFACE_HINT_VERTEXBUFFER (CONST64U(1) << 4) +#define SVGA3D_SURFACE_HINT_TEXTURE (CONST64U(1) << 5) +#define SVGA3D_SURFACE_HINT_RENDERTARGET (CONST64U(1) << 6) +#define SVGA3D_SURFACE_HINT_DEPTHSTENCIL (CONST64U(1) << 7) +#define SVGA3D_SURFACE_HINT_WRITEONLY (CONST64U(1) << 8) +#define SVGA3D_SURFACE_DEAD2 (CONST64U(1) << 9) +#define SVGA3D_SURFACE_AUTOGENMIPMAPS (CONST64U(1) << 10) -/* - * Is this surface using a base-level pitch for it's mob backing? - * - * This flag is not intended to be set by guest-drivers, but is instead - * set by the device when the surface is bound to a mob with a specified - * pitch. - */ -#define SVGA3D_SURFACE_MOB_PITCH (CONST64U(1) << 12) +#define SVGA3D_SURFACE_DEAD1 (CONST64U(1) << 11) -#define SVGA3D_SURFACE_INACTIVE (CONST64U(1) << 13) -#define SVGA3D_SURFACE_HINT_RT_LOCKABLE (CONST64U(1) << 14) -#define SVGA3D_SURFACE_VOLUME (CONST64U(1) << 15) +#define SVGA3D_SURFACE_MOB_PITCH (CONST64U(1) << 12) -/* - * Required to be set on a surface to bind it to a screen target. - */ -#define SVGA3D_SURFACE_SCREENTARGET (CONST64U(1) << 16) +#define SVGA3D_SURFACE_INACTIVE (CONST64U(1) << 13) +#define SVGA3D_SURFACE_HINT_RT_LOCKABLE (CONST64U(1) << 14) +#define SVGA3D_SURFACE_VOLUME (CONST64U(1) << 15) -/* - * Align images in the guest-backing mob to 16-bytes. - */ -#define SVGA3D_SURFACE_ALIGN16 (CONST64U(1) << 17) +#define SVGA3D_SURFACE_SCREENTARGET (CONST64U(1) << 16) -#define SVGA3D_SURFACE_1D (CONST64U(1) << 18) -#define SVGA3D_SURFACE_ARRAY (CONST64U(1) << 19) +#define SVGA3D_SURFACE_ALIGN16 (CONST64U(1) << 17) -/* - * Bind flags. - * These are enforced for any surface defined with DefineGBSurface_v2. - */ -#define SVGA3D_SURFACE_BIND_VERTEX_BUFFER (CONST64U(1) << 20) -#define SVGA3D_SURFACE_BIND_INDEX_BUFFER (CONST64U(1) << 21) -#define SVGA3D_SURFACE_BIND_CONSTANT_BUFFER (CONST64U(1) << 22) -#define SVGA3D_SURFACE_BIND_SHADER_RESOURCE (CONST64U(1) << 23) -#define SVGA3D_SURFACE_BIND_RENDER_TARGET (CONST64U(1) << 24) -#define SVGA3D_SURFACE_BIND_DEPTH_STENCIL (CONST64U(1) << 25) -#define SVGA3D_SURFACE_BIND_STREAM_OUTPUT (CONST64U(1) << 26) +#define SVGA3D_SURFACE_1D (CONST64U(1) << 18) +#define SVGA3D_SURFACE_ARRAY (CONST64U(1) << 19) -/* - * The STAGING flags notes that the surface will not be used directly by the - * drawing pipeline, i.e. that it will not be bound to any bind point. - * Staging surfaces may be used by copy operations to move data in and out - * of other surfaces. No bind flags may be set on surfaces with this flag. - * - * The HINT_INDIRECT_UPDATE flag suggests that the surface will receive - * updates indirectly, i.e. the surface will not be updated directly, but - * will receive copies from staging surfaces. - */ -#define SVGA3D_SURFACE_STAGING_UPLOAD (CONST64U(1) << 27) -#define SVGA3D_SURFACE_STAGING_DOWNLOAD (CONST64U(1) << 28) -#define SVGA3D_SURFACE_HINT_INDIRECT_UPDATE (CONST64U(1) << 29) +#define SVGA3D_SURFACE_BIND_VERTEX_BUFFER (CONST64U(1) << 20) +#define SVGA3D_SURFACE_BIND_INDEX_BUFFER (CONST64U(1) << 21) +#define SVGA3D_SURFACE_BIND_CONSTANT_BUFFER (CONST64U(1) << 22) +#define SVGA3D_SURFACE_BIND_SHADER_RESOURCE (CONST64U(1) << 23) +#define SVGA3D_SURFACE_BIND_RENDER_TARGET (CONST64U(1) << 24) +#define SVGA3D_SURFACE_BIND_DEPTH_STENCIL (CONST64U(1) << 25) +#define SVGA3D_SURFACE_BIND_STREAM_OUTPUT (CONST64U(1) << 26) -/* - * Setting this flag allow this surface to be used with the - * SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER command. It is only valid for - * buffer surfaces, and no bind flags are allowed to be set on surfaces - * with this flag except SVGA3D_SURFACE_TRANSFER_TO_BUFFER. - */ -#define SVGA3D_SURFACE_TRANSFER_FROM_BUFFER (CONST64U(1) << 30) +#define SVGA3D_SURFACE_STAGING_UPLOAD (CONST64U(1) << 27) +#define SVGA3D_SURFACE_STAGING_DOWNLOAD (CONST64U(1) << 28) +#define SVGA3D_SURFACE_HINT_INDIRECT_UPDATE (CONST64U(1) << 29) -/* - * Reserved for video operations. - */ -#define SVGA3D_SURFACE_RESERVED1 (CONST64U(1) << 31) +#define SVGA3D_SURFACE_TRANSFER_FROM_BUFFER (CONST64U(1) << 30) -/* - * Specifies that a surface is multisample, and therefore requires the full - * mob-backing to store all the samples. - */ -#define SVGA3D_SURFACE_MULTISAMPLE (CONST64U(1) << 32) +#define SVGA3D_SURFACE_RESERVED1 (CONST64U(1) << 31) +#define SVGA3D_SURFACE_VADECODE SVGA3D_SURFACE_RESERVED1 -/* - * Specified that the surface is allowed to be bound to a UAView. - */ -#define SVGA3D_SURFACE_BIND_UAVIEW (CONST64U(1) << 33) +#define SVGA3D_SURFACE_MULTISAMPLE (CONST64U(1) << 32) -/* - * Setting this flag allow this surface to be used with the - * SVGA_3D_CMD_DX_TRANSFER_TO_BUFFER command. It is only valid for - * buffer surfaces, and no bind flags are allowed to be set on surfaces - * with this flag except SVGA3D_SURFACE_TRANSFER_FROM_BUFFER. - */ -#define SVGA3D_SURFACE_TRANSFER_TO_BUFFER (CONST64U(1) << 34) +#define SVGA3D_SURFACE_BIND_UAVIEW (CONST64U(1) << 33) -#define SVGA3D_SURFACE_BIND_LOGICOPS (CONST64U(1) << 35) +#define SVGA3D_SURFACE_TRANSFER_TO_BUFFER (CONST64U(1) << 34) -/* - * Optional flags for use with SVGA3D_SURFACE_BIND_UAVIEW - */ -#define SVGA3D_SURFACE_BIND_RAW_VIEWS (CONST64U(1) << 36) -#define SVGA3D_SURFACE_BUFFER_STRUCTURED (CONST64U(1) << 37) +#define SVGA3D_SURFACE_BIND_LOGICOPS (CONST64U(1) << 35) -#define SVGA3D_SURFACE_DRAWINDIRECT_ARGS (CONST64U(1) << 38) -#define SVGA3D_SURFACE_RESOURCE_CLAMP (CONST64U(1) << 39) +#define SVGA3D_SURFACE_BIND_RAW_VIEWS (CONST64U(1) << 36) +#define SVGA3D_SURFACE_BUFFER_STRUCTURED (CONST64U(1) << 37) -#define SVGA3D_SURFACE_FLAG_MAX (CONST64U(1) << 40) +#define SVGA3D_SURFACE_DRAWINDIRECT_ARGS (CONST64U(1) << 38) +#define SVGA3D_SURFACE_RESOURCE_CLAMP (CONST64U(1) << 39) + +#define SVGA3D_SURFACE_STAGING_COPY (CONST64U(1) << 40) + +#define SVGA3D_SURFACE_FLAG_MAX (CONST64U(1) << 44) -/* - * Surface flags types: - * - * SVGA3dSurface1Flags: Lower 32-bits of flags. - * SVGA3dSurface2Flags: Upper 32-bits of flags. - * SVGA3dSurfaceAllFlags: Full 64-bits of flags. - */ typedef uint32 SVGA3dSurface1Flags; typedef uint32 SVGA3dSurface2Flags; typedef uint64 SVGA3dSurfaceAllFlags; -#define SVGA3D_SURFACE_FLAGS1_MASK ((uint64_t)MAX_UINT32) +#define SVGA3D_SURFACE_FLAGS1_MASK ((uint64)MAX_UINT32) #define SVGA3D_SURFACE_FLAGS2_MASK (MAX_UINT64 & ~SVGA3D_SURFACE_FLAGS1_MASK) -#define SVGA3D_SURFACE_HB_DISALLOWED_MASK \ - ( SVGA3D_SURFACE_MOB_PITCH | \ - SVGA3D_SURFACE_SCREENTARGET | \ - SVGA3D_SURFACE_ALIGN16 | \ - SVGA3D_SURFACE_BIND_CONSTANT_BUFFER | \ - SVGA3D_SURFACE_BIND_STREAM_OUTPUT | \ - SVGA3D_SURFACE_STAGING_UPLOAD | \ - SVGA3D_SURFACE_STAGING_DOWNLOAD | \ - SVGA3D_SURFACE_HINT_INDIRECT_UPDATE | \ - SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \ - SVGA3D_SURFACE_RESERVED1 | \ - SVGA3D_SURFACE_MULTISAMPLE | \ - SVGA3D_SURFACE_BIND_UAVIEW | \ - SVGA3D_SURFACE_TRANSFER_TO_BUFFER | \ - SVGA3D_SURFACE_BIND_LOGICOPS | \ - SVGA3D_SURFACE_BIND_RAW_VIEWS | \ - SVGA3D_SURFACE_BUFFER_STRUCTURED | \ - SVGA3D_SURFACE_DRAWINDIRECT_ARGS | \ - SVGA3D_SURFACE_RESOURCE_CLAMP \ - ) - -#define SVGA3D_SURFACE_HB_PRESENT_DISALLOWED_MASK \ - ( SVGA3D_SURFACE_1D | \ - SVGA3D_SURFACE_RESERVED1 | \ - SVGA3D_SURFACE_MULTISAMPLE \ - ) - -#define SVGA3D_SURFACE_2D_DISALLOWED_MASK \ - ( SVGA3D_SURFACE_CUBEMAP | \ - SVGA3D_SURFACE_AUTOGENMIPMAPS | \ - SVGA3D_SURFACE_VOLUME | \ - SVGA3D_SURFACE_1D | \ - SVGA3D_SURFACE_BIND_VERTEX_BUFFER | \ - SVGA3D_SURFACE_BIND_INDEX_BUFFER | \ - SVGA3D_SURFACE_BIND_CONSTANT_BUFFER | \ - SVGA3D_SURFACE_BIND_DEPTH_STENCIL | \ - SVGA3D_SURFACE_BIND_STREAM_OUTPUT | \ - SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \ - SVGA3D_SURFACE_RESERVED1 | \ - SVGA3D_SURFACE_MULTISAMPLE | \ - SVGA3D_SURFACE_BIND_UAVIEW | \ - SVGA3D_SURFACE_TRANSFER_TO_BUFFER | \ - SVGA3D_SURFACE_BIND_RAW_VIEWS | \ - SVGA3D_SURFACE_BUFFER_STRUCTURED | \ - SVGA3D_SURFACE_DRAWINDIRECT_ARGS | \ - SVGA3D_SURFACE_RESOURCE_CLAMP \ - ) - -#define SVGA3D_SURFACE_BASICOPS_DISALLOWED_MASK \ - ( SVGA3D_SURFACE_CUBEMAP | \ - SVGA3D_SURFACE_AUTOGENMIPMAPS | \ - SVGA3D_SURFACE_VOLUME | \ - SVGA3D_SURFACE_1D | \ - SVGA3D_SURFACE_RESERVED1 | \ - SVGA3D_SURFACE_MULTISAMPLE \ - ) - -#define SVGA3D_SURFACE_SCREENTARGET_DISALLOWED_MASK \ - ( SVGA3D_SURFACE_CUBEMAP | \ - SVGA3D_SURFACE_AUTOGENMIPMAPS | \ - SVGA3D_SURFACE_VOLUME | \ - SVGA3D_SURFACE_1D | \ - SVGA3D_SURFACE_BIND_VERTEX_BUFFER | \ - SVGA3D_SURFACE_BIND_INDEX_BUFFER | \ - SVGA3D_SURFACE_BIND_CONSTANT_BUFFER | \ - SVGA3D_SURFACE_BIND_DEPTH_STENCIL | \ - SVGA3D_SURFACE_BIND_STREAM_OUTPUT | \ - SVGA3D_SURFACE_INACTIVE | \ - SVGA3D_SURFACE_STAGING_UPLOAD | \ - SVGA3D_SURFACE_STAGING_DOWNLOAD | \ - SVGA3D_SURFACE_HINT_INDIRECT_UPDATE | \ - SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \ - SVGA3D_SURFACE_RESERVED1 | \ - SVGA3D_SURFACE_MULTISAMPLE | \ - SVGA3D_SURFACE_BIND_UAVIEW | \ - SVGA3D_SURFACE_TRANSFER_TO_BUFFER | \ - SVGA3D_SURFACE_BIND_RAW_VIEWS | \ - SVGA3D_SURFACE_BUFFER_STRUCTURED | \ - SVGA3D_SURFACE_DRAWINDIRECT_ARGS | \ - SVGA3D_SURFACE_RESOURCE_CLAMP \ - ) - -#define SVGA3D_SURFACE_BUFFER_DISALLOWED_MASK \ - ( SVGA3D_SURFACE_CUBEMAP | \ - SVGA3D_SURFACE_AUTOGENMIPMAPS | \ - SVGA3D_SURFACE_VOLUME | \ - SVGA3D_SURFACE_1D | \ - SVGA3D_SURFACE_DEAD2 | \ - SVGA3D_SURFACE_ARRAY | \ - SVGA3D_SURFACE_MULTISAMPLE | \ - SVGA3D_SURFACE_MOB_PITCH | \ - SVGA3D_SURFACE_RESOURCE_CLAMP \ - ) - -#define SVGA3D_SURFACE_MULTISAMPLE_DISALLOWED_MASK \ - ( SVGA3D_SURFACE_CUBEMAP | \ - SVGA3D_SURFACE_AUTOGENMIPMAPS | \ - SVGA3D_SURFACE_VOLUME | \ - SVGA3D_SURFACE_1D | \ - SVGA3D_SURFACE_SCREENTARGET | \ - SVGA3D_SURFACE_MOB_PITCH | \ - SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \ - SVGA3D_SURFACE_RESERVED1 | \ - SVGA3D_SURFACE_BIND_UAVIEW | \ - SVGA3D_SURFACE_TRANSFER_TO_BUFFER | \ - SVGA3D_SURFACE_BIND_LOGICOPS | \ - SVGA3D_SURFACE_BIND_RAW_VIEWS | \ - SVGA3D_SURFACE_BUFFER_STRUCTURED | \ - SVGA3D_SURFACE_DRAWINDIRECT_ARGS \ - ) - -#define SVGA3D_SURFACE_DX_ONLY_MASK \ - ( SVGA3D_SURFACE_BIND_STREAM_OUTPUT | \ - SVGA3D_SURFACE_STAGING_UPLOAD | \ - SVGA3D_SURFACE_STAGING_DOWNLOAD | \ - SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \ - SVGA3D_SURFACE_TRANSFER_TO_BUFFER \ - ) - -#define SVGA3D_SURFACE_STAGING_MASK \ - ( SVGA3D_SURFACE_STAGING_UPLOAD | \ - SVGA3D_SURFACE_STAGING_DOWNLOAD \ - ) - -#define SVGA3D_SURFACE_BIND_MASK \ - ( SVGA3D_SURFACE_BIND_VERTEX_BUFFER | \ - SVGA3D_SURFACE_BIND_INDEX_BUFFER | \ - SVGA3D_SURFACE_BIND_CONSTANT_BUFFER | \ - SVGA3D_SURFACE_BIND_SHADER_RESOURCE | \ - SVGA3D_SURFACE_BIND_RENDER_TARGET | \ - SVGA3D_SURFACE_BIND_DEPTH_STENCIL | \ - SVGA3D_SURFACE_BIND_STREAM_OUTPUT | \ - SVGA3D_SURFACE_BIND_UAVIEW | \ - SVGA3D_SURFACE_BIND_LOGICOPS | \ - SVGA3D_SURFACE_BIND_RAW_VIEWS \ - ) - -#define SVGA3D_SURFACE_VADECODE_DISALLOWED_MASK \ - ( SVGA3D_SURFACE_CUBEMAP | \ - SVGA3D_SURFACE_HINT_STATIC | \ - SVGA3D_SURFACE_HINT_DYNAMIC | \ - SVGA3D_SURFACE_HINT_INDEXBUFFER | \ - SVGA3D_SURFACE_HINT_VERTEXBUFFER | \ - SVGA3D_SURFACE_HINT_TEXTURE | \ - SVGA3D_SURFACE_HINT_RENDERTARGET | \ - SVGA3D_SURFACE_HINT_DEPTHSTENCIL | \ - SVGA3D_SURFACE_HINT_WRITEONLY | \ - SVGA3D_SURFACE_DEAD2 | \ - SVGA3D_SURFACE_AUTOGENMIPMAPS | \ - SVGA3D_SURFACE_HINT_RT_LOCKABLE | \ - SVGA3D_SURFACE_VOLUME | \ - SVGA3D_SURFACE_SCREENTARGET | \ - SVGA3D_SURFACE_1D | \ - SVGA3D_SURFACE_BIND_VERTEX_BUFFER | \ - SVGA3D_SURFACE_BIND_INDEX_BUFFER | \ - SVGA3D_SURFACE_BIND_CONSTANT_BUFFER | \ - SVGA3D_SURFACE_BIND_RENDER_TARGET | \ - SVGA3D_SURFACE_BIND_SHADER_RESOURCE | \ - SVGA3D_SURFACE_BIND_DEPTH_STENCIL | \ - SVGA3D_SURFACE_BIND_STREAM_OUTPUT | \ - SVGA3D_SURFACE_INACTIVE | \ - SVGA3D_SURFACE_STAGING_UPLOAD | \ - SVGA3D_SURFACE_STAGING_DOWNLOAD | \ - SVGA3D_SURFACE_HINT_INDIRECT_UPDATE | \ - SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \ - SVGA3D_SURFACE_MULTISAMPLE | \ - SVGA3D_SURFACE_BIND_UAVIEW | \ - SVGA3D_SURFACE_TRANSFER_TO_BUFFER | \ - SVGA3D_SURFACE_BIND_LOGICOPS | \ - SVGA3D_SURFACE_BIND_RAW_VIEWS | \ - SVGA3D_SURFACE_BUFFER_STRUCTURED | \ - SVGA3D_SURFACE_DRAWINDIRECT_ARGS | \ - SVGA3D_SURFACE_RESOURCE_CLAMP \ - ) - -#define SVGA3D_SURFACE_VAPROCESSFRAME_OUTPUT_DISALLOWED_MASK \ - ( SVGA3D_SURFACE_HINT_INDEXBUFFER | \ - SVGA3D_SURFACE_HINT_VERTEXBUFFER | \ - SVGA3D_SURFACE_HINT_DEPTHSTENCIL | \ - SVGA3D_SURFACE_DEAD2 | \ - SVGA3D_SURFACE_VOLUME | \ - SVGA3D_SURFACE_1D | \ - SVGA3D_SURFACE_BIND_VERTEX_BUFFER | \ - SVGA3D_SURFACE_BIND_INDEX_BUFFER | \ - SVGA3D_SURFACE_BIND_CONSTANT_BUFFER | \ - SVGA3D_SURFACE_BIND_DEPTH_STENCIL | \ - SVGA3D_SURFACE_BIND_STREAM_OUTPUT | \ - SVGA3D_SURFACE_INACTIVE | \ - SVGA3D_SURFACE_STAGING_UPLOAD | \ - SVGA3D_SURFACE_STAGING_DOWNLOAD | \ - SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \ - SVGA3D_SURFACE_VADECODE | \ - SVGA3D_SURFACE_MULTISAMPLE | \ - SVGA3D_SURFACE_BIND_UAVIEW | \ - SVGA3D_SURFACE_TRANSFER_TO_BUFFER | \ - SVGA3D_SURFACE_BIND_LOGICOPS | \ - SVGA3D_SURFACE_BIND_RAW_VIEWS | \ - SVGA3D_SURFACE_BUFFER_STRUCTURED | \ - SVGA3D_SURFACE_DRAWINDIRECT_ARGS | \ - SVGA3D_SURFACE_RESOURCE_CLAMP \ - ) - -#define SVGA3D_SURFACE_VAPROCESSFRAME_INPUT_DISALLOWED_MASK \ - ( SVGA3D_SURFACE_CUBEMAP | \ - SVGA3D_SURFACE_HINT_INDEXBUFFER | \ - SVGA3D_SURFACE_HINT_VERTEXBUFFER | \ - SVGA3D_SURFACE_HINT_DEPTHSTENCIL | \ - SVGA3D_SURFACE_DEAD2 | \ - SVGA3D_SURFACE_VOLUME | \ - SVGA3D_SURFACE_SCREENTARGET | \ - SVGA3D_SURFACE_1D | \ - SVGA3D_SURFACE_BIND_VERTEX_BUFFER | \ - SVGA3D_SURFACE_BIND_INDEX_BUFFER | \ - SVGA3D_SURFACE_BIND_CONSTANT_BUFFER | \ - SVGA3D_SURFACE_BIND_DEPTH_STENCIL | \ - SVGA3D_SURFACE_BIND_STREAM_OUTPUT | \ - SVGA3D_SURFACE_STAGING_UPLOAD | \ - SVGA3D_SURFACE_STAGING_DOWNLOAD | \ - SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \ - SVGA3D_SURFACE_MULTISAMPLE | \ - SVGA3D_SURFACE_BIND_UAVIEW | \ - SVGA3D_SURFACE_TRANSFER_TO_BUFFER | \ - SVGA3D_SURFACE_BIND_LOGICOPS | \ - SVGA3D_SURFACE_BIND_RAW_VIEWS | \ - SVGA3D_SURFACE_BUFFER_STRUCTURED | \ - SVGA3D_SURFACE_DRAWINDIRECT_ARGS | \ - SVGA3D_SURFACE_RESOURCE_CLAMP \ - ) - -#define SVGA3D_SURFACE_LOGICOPS_DISALLOWED_MASK \ - ( SVGA3D_SURFACE_CUBEMAP | \ - SVGA3D_SURFACE_DEAD2 | \ - SVGA3D_SURFACE_AUTOGENMIPMAPS | \ - SVGA3D_SURFACE_VOLUME | \ - SVGA3D_SURFACE_1D | \ - SVGA3D_SURFACE_BIND_VERTEX_BUFFER | \ - SVGA3D_SURFACE_BIND_INDEX_BUFFER | \ - SVGA3D_SURFACE_BIND_CONSTANT_BUFFER | \ - SVGA3D_SURFACE_BIND_DEPTH_STENCIL | \ - SVGA3D_SURFACE_BIND_STREAM_OUTPUT | \ - SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \ - SVGA3D_SURFACE_VADECODE | \ - SVGA3D_SURFACE_MULTISAMPLE | \ - SVGA3D_SURFACE_BIND_UAVIEW | \ - SVGA3D_SURFACE_TRANSFER_TO_BUFFER | \ - SVGA3D_SURFACE_BIND_RAW_VIEWS | \ - SVGA3D_SURFACE_BUFFER_STRUCTURED | \ - SVGA3D_SURFACE_DRAWINDIRECT_ARGS | \ - SVGA3D_SURFACE_RESOURCE_CLAMP \ - ) +#define SVGA3D_SURFACE_HB_DISALLOWED_MASK \ + (SVGA3D_SURFACE_MOB_PITCH | SVGA3D_SURFACE_SCREENTARGET | \ + SVGA3D_SURFACE_ALIGN16 | SVGA3D_SURFACE_BIND_CONSTANT_BUFFER | \ + SVGA3D_SURFACE_BIND_STREAM_OUTPUT | SVGA3D_SURFACE_STAGING_UPLOAD | \ + SVGA3D_SURFACE_STAGING_DOWNLOAD | \ + SVGA3D_SURFACE_HINT_INDIRECT_UPDATE | \ + SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | SVGA3D_SURFACE_MULTISAMPLE | \ + SVGA3D_SURFACE_BIND_UAVIEW | SVGA3D_SURFACE_TRANSFER_TO_BUFFER | \ + SVGA3D_SURFACE_BIND_LOGICOPS | SVGA3D_SURFACE_BIND_RAW_VIEWS | \ + SVGA3D_SURFACE_BUFFER_STRUCTURED | SVGA3D_SURFACE_DRAWINDIRECT_ARGS | \ + SVGA3D_SURFACE_RESOURCE_CLAMP | SVGA3D_SURFACE_STAGING_COPY | \ + SVGA3D_SURFACE_RESTRICT_UPDATE | SVGA3D_SURFACE_BIND_TENSOR | \ + SVGA3D_SURFACE_LO_STAGING) + +#define SVGA3D_SURFACE_HB_PRESENT_DISALLOWED_MASK \ + (SVGA3D_SURFACE_1D | SVGA3D_SURFACE_MULTISAMPLE | \ + SVGA3D_SURFACE_STAGING_COPY) + +#define SVGA3D_SURFACE_2D_DISALLOWED_MASK \ + (SVGA3D_SURFACE_CUBEMAP | SVGA3D_SURFACE_AUTOGENMIPMAPS | \ + SVGA3D_SURFACE_VOLUME | SVGA3D_SURFACE_1D | \ + SVGA3D_SURFACE_BIND_VERTEX_BUFFER | \ + SVGA3D_SURFACE_BIND_INDEX_BUFFER | \ + SVGA3D_SURFACE_BIND_CONSTANT_BUFFER | \ + SVGA3D_SURFACE_BIND_DEPTH_STENCIL | \ + SVGA3D_SURFACE_BIND_STREAM_OUTPUT | \ + SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | SVGA3D_SURFACE_MULTISAMPLE | \ + SVGA3D_SURFACE_BIND_UAVIEW | SVGA3D_SURFACE_TRANSFER_TO_BUFFER | \ + SVGA3D_SURFACE_BIND_RAW_VIEWS | SVGA3D_SURFACE_BUFFER_STRUCTURED | \ + SVGA3D_SURFACE_DRAWINDIRECT_ARGS | SVGA3D_SURFACE_RESOURCE_CLAMP | \ + SVGA3D_SURFACE_BIND_TENSOR) + +#define SVGA3D_SURFACE_BASICOPS_DISALLOWED_MASK \ + (SVGA3D_SURFACE_CUBEMAP | SVGA3D_SURFACE_AUTOGENMIPMAPS | \ + SVGA3D_SURFACE_VOLUME | SVGA3D_SURFACE_1D | \ + SVGA3D_SURFACE_MULTISAMPLE) + +#define SVGA3D_SURFACE_SCREENTARGET_DISALLOWED_MASK \ + (SVGA3D_SURFACE_CUBEMAP | SVGA3D_SURFACE_AUTOGENMIPMAPS | \ + SVGA3D_SURFACE_VOLUME | SVGA3D_SURFACE_1D | \ + SVGA3D_SURFACE_BIND_VERTEX_BUFFER | \ + SVGA3D_SURFACE_BIND_INDEX_BUFFER | \ + SVGA3D_SURFACE_BIND_CONSTANT_BUFFER | \ + SVGA3D_SURFACE_BIND_DEPTH_STENCIL | \ + SVGA3D_SURFACE_BIND_STREAM_OUTPUT | SVGA3D_SURFACE_INACTIVE | \ + SVGA3D_SURFACE_STAGING_UPLOAD | SVGA3D_SURFACE_STAGING_DOWNLOAD | \ + SVGA3D_SURFACE_HINT_INDIRECT_UPDATE | \ + SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | SVGA3D_SURFACE_MULTISAMPLE | \ + SVGA3D_SURFACE_TRANSFER_TO_BUFFER | SVGA3D_SURFACE_BIND_RAW_VIEWS | \ + SVGA3D_SURFACE_BUFFER_STRUCTURED | SVGA3D_SURFACE_DRAWINDIRECT_ARGS | \ + SVGA3D_SURFACE_RESOURCE_CLAMP | SVGA3D_SURFACE_STAGING_COPY | \ + SVGA3D_SURFACE_BIND_TENSOR | SVGA3D_SURFACE_LO_STAGING) + +#define SVGA3D_SURFACE_BUFFER_DISALLOWED_MASK \ + (SVGA3D_SURFACE_CUBEMAP | SVGA3D_SURFACE_AUTOGENMIPMAPS | \ + SVGA3D_SURFACE_VOLUME | SVGA3D_SURFACE_1D | SVGA3D_SURFACE_DEAD2 | \ + SVGA3D_SURFACE_ARRAY | SVGA3D_SURFACE_MULTISAMPLE | \ + SVGA3D_SURFACE_MOB_PITCH | SVGA3D_SURFACE_RESOURCE_CLAMP) + +#define SVGA3D_SURFACE_MULTISAMPLE_DISALLOWED_MASK \ + (SVGA3D_SURFACE_CUBEMAP | SVGA3D_SURFACE_AUTOGENMIPMAPS | \ + SVGA3D_SURFACE_VOLUME | SVGA3D_SURFACE_1D | \ + SVGA3D_SURFACE_SCREENTARGET | SVGA3D_SURFACE_MOB_PITCH | \ + SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | SVGA3D_SURFACE_BIND_UAVIEW | \ + SVGA3D_SURFACE_TRANSFER_TO_BUFFER | SVGA3D_SURFACE_BIND_LOGICOPS | \ + SVGA3D_SURFACE_BIND_RAW_VIEWS | SVGA3D_SURFACE_BUFFER_STRUCTURED | \ + SVGA3D_SURFACE_DRAWINDIRECT_ARGS | SVGA3D_SURFACE_STAGING_COPY) + +#define SVGA3D_SURFACE_DX_ONLY_MASK \ + (SVGA3D_SURFACE_BIND_STREAM_OUTPUT | SVGA3D_SURFACE_STAGING_UPLOAD | \ + SVGA3D_SURFACE_STAGING_DOWNLOAD | \ + SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \ + SVGA3D_SURFACE_TRANSFER_TO_BUFFER) + +#define SVGA3D_SURFACE_ANY_STAGING_MASK \ + (SVGA3D_SURFACE_STAGING_UPLOAD | SVGA3D_SURFACE_STAGING_DOWNLOAD | \ + SVGA3D_SURFACE_STAGING_COPY | SVGA3D_SURFACE_LO_STAGING) + +#define SVGA3D_SURFACE_ANY_NONHINT_STAGING_MASK \ + (SVGA3D_SURFACE_ANY_STAGING_MASK & ~(SVGA3D_SURFACE_LO_STAGING)) + +#define SVGA3D_SURFACE_BIND_MASK \ + (SVGA3D_SURFACE_BIND_VERTEX_BUFFER | \ + SVGA3D_SURFACE_BIND_INDEX_BUFFER | \ + SVGA3D_SURFACE_BIND_CONSTANT_BUFFER | \ + SVGA3D_SURFACE_BIND_SHADER_RESOURCE | \ + SVGA3D_SURFACE_BIND_RENDER_TARGET | \ + SVGA3D_SURFACE_BIND_DEPTH_STENCIL | \ + SVGA3D_SURFACE_BIND_STREAM_OUTPUT | SVGA3D_SURFACE_BIND_UAVIEW | \ + SVGA3D_SURFACE_BIND_LOGICOPS | SVGA3D_SURFACE_BIND_RAW_VIEWS | \ + SVGA3D_SURFACE_BIND_TENSOR) + +#define SVGA3D_SURFACE_STAGING_DISALLOWED_MASK \ + (SVGA3D_SURFACE_BIND_MASK | SVGA3D_SURFACE_AUTOGENMIPMAPS | \ + SVGA3D_SURFACE_SCREENTARGET | SVGA3D_SURFACE_HINT_RENDERTARGET | \ + SVGA3D_SURFACE_HINT_INDIRECT_UPDATE | SVGA3D_SURFACE_MULTISAMPLE | \ + SVGA3D_SURFACE_DRAWINDIRECT_ARGS | SVGA3D_SURFACE_RESOURCE_CLAMP | \ + SVGA3D_SURFACE_BIND_TENSOR) + +#define SVGA3D_SURFACE_STAGING_COPY_DISALLOWED_MASK \ + (SVGA3D_SURFACE_STAGING_DISALLOWED_MASK | \ + SVGA3D_SURFACE_TRANSFER_TO_BUFFER | \ + SVGA3D_SURFACE_TRANSFER_FROM_BUFFER) + +#define SVGA3D_SURFACE_LOGICOPS_DISALLOWED_MASK \ + (SVGA3D_SURFACE_CUBEMAP | SVGA3D_SURFACE_DEAD2 | \ + SVGA3D_SURFACE_AUTOGENMIPMAPS | SVGA3D_SURFACE_VOLUME | \ + SVGA3D_SURFACE_1D | SVGA3D_SURFACE_BIND_VERTEX_BUFFER | \ + SVGA3D_SURFACE_BIND_INDEX_BUFFER | \ + SVGA3D_SURFACE_BIND_CONSTANT_BUFFER | \ + SVGA3D_SURFACE_BIND_DEPTH_STENCIL | \ + SVGA3D_SURFACE_BIND_STREAM_OUTPUT | \ + SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | SVGA3D_SURFACE_MULTISAMPLE | \ + SVGA3D_SURFACE_BIND_UAVIEW | SVGA3D_SURFACE_TRANSFER_TO_BUFFER | \ + SVGA3D_SURFACE_BIND_RAW_VIEWS | SVGA3D_SURFACE_BUFFER_STRUCTURED | \ + SVGA3D_SURFACE_DRAWINDIRECT_ARGS | SVGA3D_SURFACE_RESOURCE_CLAMP | \ + SVGA3D_SURFACE_STAGING_COPY) + +#define SVGA3D_SURFACE_SM5_MASK \ + (SVGA3D_SURFACE_DRAWINDIRECT_ARGS | SVGA3D_SURFACE_BUFFER_STRUCTURED | \ + SVGA3D_SURFACE_BIND_RAW_VIEWS | SVGA3D_SURFACE_BIND_UAVIEW | \ + SVGA3D_SURFACE_RESOURCE_CLAMP) #define SVGA3D_BUFFER_STRUCTURED_STRIDE_MAX 2048 - -/* - * These are really the D3DFORMAT_OP defines from the wdk. We need - * them so that we can query the host for what the supported surface - * operations are (when we're using the D3D backend, in particular), - * and so we can send those operations to the guest. - */ typedef enum { - SVGA3DFORMAT_OP_TEXTURE = 0x00000001, - SVGA3DFORMAT_OP_VOLUMETEXTURE = 0x00000002, - SVGA3DFORMAT_OP_CUBETEXTURE = 0x00000004, - SVGA3DFORMAT_OP_OFFSCREEN_RENDERTARGET = 0x00000008, - SVGA3DFORMAT_OP_SAME_FORMAT_RENDERTARGET = 0x00000010, - SVGA3DFORMAT_OP_ZSTENCIL = 0x00000040, - SVGA3DFORMAT_OP_ZSTENCIL_WITH_ARBITRARY_COLOR_DEPTH = 0x00000080, + SVGA3DFORMAT_OP_TEXTURE = 0x00000001, + SVGA3DFORMAT_OP_VOLUMETEXTURE = 0x00000002, + SVGA3DFORMAT_OP_CUBETEXTURE = 0x00000004, + SVGA3DFORMAT_OP_OFFSCREEN_RENDERTARGET = 0x00000008, + SVGA3DFORMAT_OP_SAME_FORMAT_RENDERTARGET = 0x00000010, + SVGA3DFORMAT_OP_ZSTENCIL = 0x00000040, + SVGA3DFORMAT_OP_ZSTENCIL_WITH_ARBITRARY_COLOR_DEPTH = 0x00000080, -/* - * This format can be used as a render target if the current display mode - * is the same depth if the alpha channel is ignored. e.g. if the device - * can render to A8R8G8B8 when the display mode is X8R8G8B8, then the - * format op list entry for A8R8G8B8 should have this cap. - */ - SVGA3DFORMAT_OP_SAME_FORMAT_UP_TO_ALPHA_RENDERTARGET = 0x00000100, + SVGA3DFORMAT_OP_SAME_FORMAT_UP_TO_ALPHA_RENDERTARGET = 0x00000100, -/* - * This format contains DirectDraw support (including Flip). This flag - * should not to be set on alpha formats. - */ - SVGA3DFORMAT_OP_DISPLAYMODE = 0x00000400, + SVGA3DFORMAT_OP_DISPLAYMODE = 0x00000400, -/* - * The rasterizer can support some level of Direct3D support in this format - * and implies that the driver can create a Context in this mode (for some - * render target format). When this flag is set, the SVGA3DFORMAT_OP_DISPLAYMODE - * flag must also be set. - */ - SVGA3DFORMAT_OP_3DACCELERATION = 0x00000800, + SVGA3DFORMAT_OP_3DACCELERATION = 0x00000800, -/* - * This is set for a private format when the driver has put the bpp in - * the structure. - */ - SVGA3DFORMAT_OP_PIXELSIZE = 0x00001000, + SVGA3DFORMAT_OP_PIXELSIZE = 0x00001000, -/* - * Indicates that this format can be converted to any RGB format for which - * SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB is specified. - */ - SVGA3DFORMAT_OP_CONVERT_TO_ARGB = 0x00002000, + SVGA3DFORMAT_OP_CONVERT_TO_ARGB = 0x00002000, -/* - * Indicates that this format can be used to create offscreen plain surfaces. - */ - SVGA3DFORMAT_OP_OFFSCREENPLAIN = 0x00004000, + SVGA3DFORMAT_OP_OFFSCREENPLAIN = 0x00004000, -/* - * Indicated that this format can be read as an SRGB texture (meaning that the - * sampler will linearize the looked up data). - */ - SVGA3DFORMAT_OP_SRGBREAD = 0x00008000, + SVGA3DFORMAT_OP_SRGBREAD = 0x00008000, -/* - * Indicates that this format can be used in the bumpmap instructions. - */ - SVGA3DFORMAT_OP_BUMPMAP = 0x00010000, + SVGA3DFORMAT_OP_BUMPMAP = 0x00010000, -/* - * Indicates that this format can be sampled by the displacement map sampler. - */ - SVGA3DFORMAT_OP_DMAP = 0x00020000, + SVGA3DFORMAT_OP_DMAP = 0x00020000, -/* - * Indicates that this format cannot be used with texture filtering. - */ - SVGA3DFORMAT_OP_NOFILTER = 0x00040000, + SVGA3DFORMAT_OP_NOFILTER = 0x00040000, -/* - * Indicates that format conversions are supported to this RGB format if - * SVGA3DFORMAT_OP_CONVERT_TO_ARGB is specified in the source format. - */ - SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB = 0x00080000, + SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB = 0x00080000, -/* - * Indicated that this format can be written as an SRGB target - * (meaning that the pixel pipe will DE-linearize data on output to format) - */ - SVGA3DFORMAT_OP_SRGBWRITE = 0x00100000, + SVGA3DFORMAT_OP_SRGBWRITE = 0x00100000, -/* - * Indicates that this format cannot be used with alpha blending. - */ - SVGA3DFORMAT_OP_NOALPHABLEND = 0x00200000, + SVGA3DFORMAT_OP_NOALPHABLEND = 0x00200000, -/* - * Indicates that the device can auto-generated sublevels for resources - * of this format. - */ - SVGA3DFORMAT_OP_AUTOGENMIPMAP = 0x00400000, + SVGA3DFORMAT_OP_AUTOGENMIPMAP = 0x00400000, -/* - * Indicates that this format can be used by vertex texture sampler. - */ - SVGA3DFORMAT_OP_VERTEXTEXTURE = 0x00800000, + SVGA3DFORMAT_OP_VERTEXTEXTURE = 0x00800000, -/* - * Indicates that this format supports neither texture coordinate - * wrap modes, nor mipmapping. - */ - SVGA3DFORMAT_OP_NOTEXCOORDWRAPNORMIP = 0x01000000 + SVGA3DFORMAT_OP_NOTEXCOORDWRAPNORMIP = 0x01000000 } SVGA3dFormatOp; -#define SVGA3D_FORMAT_POSITIVE \ - (SVGA3DFORMAT_OP_TEXTURE | \ - SVGA3DFORMAT_OP_VOLUMETEXTURE | \ - SVGA3DFORMAT_OP_CUBETEXTURE | \ - SVGA3DFORMAT_OP_OFFSCREEN_RENDERTARGET | \ - SVGA3DFORMAT_OP_SAME_FORMAT_RENDERTARGET | \ - SVGA3DFORMAT_OP_ZSTENCIL | \ - SVGA3DFORMAT_OP_ZSTENCIL_WITH_ARBITRARY_COLOR_DEPTH | \ - SVGA3DFORMAT_OP_SAME_FORMAT_UP_TO_ALPHA_RENDERTARGET | \ - SVGA3DFORMAT_OP_DISPLAYMODE | \ - SVGA3DFORMAT_OP_3DACCELERATION | \ - SVGA3DFORMAT_OP_PIXELSIZE | \ - SVGA3DFORMAT_OP_CONVERT_TO_ARGB | \ - SVGA3DFORMAT_OP_OFFSCREENPLAIN | \ - SVGA3DFORMAT_OP_SRGBREAD | \ - SVGA3DFORMAT_OP_BUMPMAP | \ - SVGA3DFORMAT_OP_DMAP | \ - SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB | \ - SVGA3DFORMAT_OP_SRGBWRITE | \ - SVGA3DFORMAT_OP_AUTOGENMIPMAP | \ - SVGA3DFORMAT_OP_VERTEXTEXTURE) - -#define SVGA3D_FORMAT_NEGATIVE \ - (SVGA3DFORMAT_OP_NOFILTER | \ - SVGA3DFORMAT_OP_NOALPHABLEND | \ - SVGA3DFORMAT_OP_NOTEXCOORDWRAPNORMIP) +#define SVGA3D_FORMAT_POSITIVE \ + (SVGA3DFORMAT_OP_TEXTURE | SVGA3DFORMAT_OP_VOLUMETEXTURE | \ + SVGA3DFORMAT_OP_CUBETEXTURE | \ + SVGA3DFORMAT_OP_OFFSCREEN_RENDERTARGET | \ + SVGA3DFORMAT_OP_SAME_FORMAT_RENDERTARGET | SVGA3DFORMAT_OP_ZSTENCIL | \ + SVGA3DFORMAT_OP_ZSTENCIL_WITH_ARBITRARY_COLOR_DEPTH | \ + SVGA3DFORMAT_OP_SAME_FORMAT_UP_TO_ALPHA_RENDERTARGET | \ + SVGA3DFORMAT_OP_DISPLAYMODE | SVGA3DFORMAT_OP_3DACCELERATION | \ + SVGA3DFORMAT_OP_PIXELSIZE | SVGA3DFORMAT_OP_CONVERT_TO_ARGB | \ + SVGA3DFORMAT_OP_OFFSCREENPLAIN | SVGA3DFORMAT_OP_SRGBREAD | \ + SVGA3DFORMAT_OP_BUMPMAP | SVGA3DFORMAT_OP_DMAP | \ + SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB | SVGA3DFORMAT_OP_SRGBWRITE | \ + SVGA3DFORMAT_OP_AUTOGENMIPMAP | SVGA3DFORMAT_OP_VERTEXTEXTURE) + +#define SVGA3D_FORMAT_NEGATIVE \ + (SVGA3DFORMAT_OP_NOFILTER | SVGA3DFORMAT_OP_NOALPHABLEND | \ + SVGA3DFORMAT_OP_NOTEXCOORDWRAPNORMIP) -/* - * This structure is a conversion of SVGA3DFORMAT_OP_* - * Entries must be located at the same position. - */ typedef union { - uint32 value; - struct { - uint32 texture : 1; - uint32 volumeTexture : 1; - uint32 cubeTexture : 1; - uint32 offscreenRenderTarget : 1; - uint32 sameFormatRenderTarget : 1; - uint32 unknown1 : 1; - uint32 zStencil : 1; - uint32 zStencilArbitraryDepth : 1; - uint32 sameFormatUpToAlpha : 1; - uint32 unknown2 : 1; - uint32 displayMode : 1; - uint32 acceleration3d : 1; - uint32 pixelSize : 1; - uint32 convertToARGB : 1; - uint32 offscreenPlain : 1; - uint32 sRGBRead : 1; - uint32 bumpMap : 1; - uint32 dmap : 1; - uint32 noFilter : 1; - uint32 memberOfGroupARGB : 1; - uint32 sRGBWrite : 1; - uint32 noAlphaBlend : 1; - uint32 autoGenMipMap : 1; - uint32 vertexTexture : 1; - uint32 noTexCoordWrapNorMip : 1; - }; + uint32 value; + struct { + uint32 texture : 1; + uint32 volumeTexture : 1; + uint32 cubeTexture : 1; + uint32 offscreenRenderTarget : 1; + uint32 sameFormatRenderTarget : 1; + uint32 unknown1 : 1; + uint32 zStencil : 1; + uint32 zStencilArbitraryDepth : 1; + uint32 sameFormatUpToAlpha : 1; + uint32 unknown2 : 1; + uint32 displayMode : 1; + uint32 acceleration3d : 1; + uint32 pixelSize : 1; + uint32 convertToARGB : 1; + uint32 offscreenPlain : 1; + uint32 sRGBRead : 1; + uint32 bumpMap : 1; + uint32 dmap : 1; + uint32 noFilter : 1; + uint32 memberOfGroupARGB : 1; + uint32 sRGBWrite : 1; + uint32 noAlphaBlend : 1; + uint32 autoGenMipMap : 1; + uint32 vertexTexture : 1; + uint32 noTexCoordWrapNorMip : 1; + }; } SVGA3dSurfaceFormatCaps; -/* - * SVGA_3D_CMD_SETRENDERSTATE Types. All value types - * must fit in a uint32. - */ - typedef enum { - SVGA3D_RS_INVALID = 0, - SVGA3D_RS_MIN = 1, - SVGA3D_RS_ZENABLE = 1, /* SVGA3dBool */ - SVGA3D_RS_ZWRITEENABLE = 2, /* SVGA3dBool */ - SVGA3D_RS_ALPHATESTENABLE = 3, /* SVGA3dBool */ - SVGA3D_RS_DITHERENABLE = 4, /* SVGA3dBool */ - SVGA3D_RS_BLENDENABLE = 5, /* SVGA3dBool */ - SVGA3D_RS_FOGENABLE = 6, /* SVGA3dBool */ - SVGA3D_RS_SPECULARENABLE = 7, /* SVGA3dBool */ - SVGA3D_RS_STENCILENABLE = 8, /* SVGA3dBool */ - SVGA3D_RS_LIGHTINGENABLE = 9, /* SVGA3dBool */ - SVGA3D_RS_NORMALIZENORMALS = 10, /* SVGA3dBool */ - SVGA3D_RS_POINTSPRITEENABLE = 11, /* SVGA3dBool */ - SVGA3D_RS_POINTSCALEENABLE = 12, /* SVGA3dBool */ - SVGA3D_RS_STENCILREF = 13, /* uint32 */ - SVGA3D_RS_STENCILMASK = 14, /* uint32 */ - SVGA3D_RS_STENCILWRITEMASK = 15, /* uint32 */ - SVGA3D_RS_FOGSTART = 16, /* float */ - SVGA3D_RS_FOGEND = 17, /* float */ - SVGA3D_RS_FOGDENSITY = 18, /* float */ - SVGA3D_RS_POINTSIZE = 19, /* float */ - SVGA3D_RS_POINTSIZEMIN = 20, /* float */ - SVGA3D_RS_POINTSIZEMAX = 21, /* float */ - SVGA3D_RS_POINTSCALE_A = 22, /* float */ - SVGA3D_RS_POINTSCALE_B = 23, /* float */ - SVGA3D_RS_POINTSCALE_C = 24, /* float */ - SVGA3D_RS_FOGCOLOR = 25, /* SVGA3dColor */ - SVGA3D_RS_AMBIENT = 26, /* SVGA3dColor */ - SVGA3D_RS_CLIPPLANEENABLE = 27, /* SVGA3dClipPlanes */ - SVGA3D_RS_FOGMODE = 28, /* SVGA3dFogMode */ - SVGA3D_RS_FILLMODE = 29, /* SVGA3dFillMode */ - SVGA3D_RS_SHADEMODE = 30, /* SVGA3dShadeMode */ - SVGA3D_RS_LINEPATTERN = 31, /* SVGA3dLinePattern */ - SVGA3D_RS_SRCBLEND = 32, /* SVGA3dBlendOp */ - SVGA3D_RS_DSTBLEND = 33, /* SVGA3dBlendOp */ - SVGA3D_RS_BLENDEQUATION = 34, /* SVGA3dBlendEquation */ - SVGA3D_RS_CULLMODE = 35, /* SVGA3dFace */ - SVGA3D_RS_ZFUNC = 36, /* SVGA3dCmpFunc */ - SVGA3D_RS_ALPHAFUNC = 37, /* SVGA3dCmpFunc */ - SVGA3D_RS_STENCILFUNC = 38, /* SVGA3dCmpFunc */ - SVGA3D_RS_STENCILFAIL = 39, /* SVGA3dStencilOp */ - SVGA3D_RS_STENCILZFAIL = 40, /* SVGA3dStencilOp */ - SVGA3D_RS_STENCILPASS = 41, /* SVGA3dStencilOp */ - SVGA3D_RS_ALPHAREF = 42, /* float (0.0 .. 1.0) */ - SVGA3D_RS_FRONTWINDING = 43, /* SVGA3dFrontWinding */ - SVGA3D_RS_COORDINATETYPE = 44, /* SVGA3dCoordinateType */ - SVGA3D_RS_ZBIAS = 45, /* float */ - SVGA3D_RS_RANGEFOGENABLE = 46, /* SVGA3dBool */ - SVGA3D_RS_COLORWRITEENABLE = 47, /* SVGA3dColorMask */ - SVGA3D_RS_VERTEXMATERIALENABLE = 48, /* SVGA3dBool */ - SVGA3D_RS_DIFFUSEMATERIALSOURCE = 49, /* SVGA3dVertexMaterial */ - SVGA3D_RS_SPECULARMATERIALSOURCE = 50, /* SVGA3dVertexMaterial */ - SVGA3D_RS_AMBIENTMATERIALSOURCE = 51, /* SVGA3dVertexMaterial */ - SVGA3D_RS_EMISSIVEMATERIALSOURCE = 52, /* SVGA3dVertexMaterial */ - SVGA3D_RS_TEXTUREFACTOR = 53, /* SVGA3dColor */ - SVGA3D_RS_LOCALVIEWER = 54, /* SVGA3dBool */ - SVGA3D_RS_SCISSORTESTENABLE = 55, /* SVGA3dBool */ - SVGA3D_RS_BLENDCOLOR = 56, /* SVGA3dColor */ - SVGA3D_RS_STENCILENABLE2SIDED = 57, /* SVGA3dBool */ - SVGA3D_RS_CCWSTENCILFUNC = 58, /* SVGA3dCmpFunc */ - SVGA3D_RS_CCWSTENCILFAIL = 59, /* SVGA3dStencilOp */ - SVGA3D_RS_CCWSTENCILZFAIL = 60, /* SVGA3dStencilOp */ - SVGA3D_RS_CCWSTENCILPASS = 61, /* SVGA3dStencilOp */ - SVGA3D_RS_VERTEXBLEND = 62, /* SVGA3dVertexBlendFlags */ - SVGA3D_RS_SLOPESCALEDEPTHBIAS = 63, /* float */ - SVGA3D_RS_DEPTHBIAS = 64, /* float */ - - - /* - * Output Gamma Level - * - * Output gamma effects the gamma curve of colors that are output from the - * rendering pipeline. A value of 1.0 specifies a linear color space. If the - * value is <= 0.0, gamma correction is ignored and linear color space is - * used. - */ - - SVGA3D_RS_OUTPUTGAMMA = 65, /* float */ - SVGA3D_RS_ZVISIBLE = 66, /* SVGA3dBool */ - SVGA3D_RS_LASTPIXEL = 67, /* SVGA3dBool */ - SVGA3D_RS_CLIPPING = 68, /* SVGA3dBool */ - SVGA3D_RS_WRAP0 = 69, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP1 = 70, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP2 = 71, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP3 = 72, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP4 = 73, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP5 = 74, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP6 = 75, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP7 = 76, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP8 = 77, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP9 = 78, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP10 = 79, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP11 = 80, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP12 = 81, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP13 = 82, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP14 = 83, /* SVGA3dWrapFlags */ - SVGA3D_RS_WRAP15 = 84, /* SVGA3dWrapFlags */ - SVGA3D_RS_MULTISAMPLEANTIALIAS = 85, /* SVGA3dBool */ - SVGA3D_RS_MULTISAMPLEMASK = 86, /* uint32 */ - SVGA3D_RS_INDEXEDVERTEXBLENDENABLE = 87, /* SVGA3dBool */ - SVGA3D_RS_TWEENFACTOR = 88, /* float */ - SVGA3D_RS_ANTIALIASEDLINEENABLE = 89, /* SVGA3dBool */ - SVGA3D_RS_COLORWRITEENABLE1 = 90, /* SVGA3dColorMask */ - SVGA3D_RS_COLORWRITEENABLE2 = 91, /* SVGA3dColorMask */ - SVGA3D_RS_COLORWRITEENABLE3 = 92, /* SVGA3dColorMask */ - SVGA3D_RS_SEPARATEALPHABLENDENABLE = 93, /* SVGA3dBool */ - SVGA3D_RS_SRCBLENDALPHA = 94, /* SVGA3dBlendOp */ - SVGA3D_RS_DSTBLENDALPHA = 95, /* SVGA3dBlendOp */ - SVGA3D_RS_BLENDEQUATIONALPHA = 96, /* SVGA3dBlendEquation */ - SVGA3D_RS_TRANSPARENCYANTIALIAS = 97, /* SVGA3dTransparencyAntialiasType */ - SVGA3D_RS_LINEWIDTH = 98, /* float */ - SVGA3D_RS_MAX + SVGA3D_RS_INVALID = 0, + SVGA3D_RS_MIN = 1, + SVGA3D_RS_ZENABLE = 1, + SVGA3D_RS_ZWRITEENABLE = 2, + SVGA3D_RS_ALPHATESTENABLE = 3, + SVGA3D_RS_DITHERENABLE = 4, + SVGA3D_RS_BLENDENABLE = 5, + SVGA3D_RS_FOGENABLE = 6, + SVGA3D_RS_SPECULARENABLE = 7, + SVGA3D_RS_STENCILENABLE = 8, + SVGA3D_RS_LIGHTINGENABLE = 9, + SVGA3D_RS_NORMALIZENORMALS = 10, + SVGA3D_RS_POINTSPRITEENABLE = 11, + SVGA3D_RS_POINTSCALEENABLE = 12, + SVGA3D_RS_STENCILREF = 13, + SVGA3D_RS_STENCILMASK = 14, + SVGA3D_RS_STENCILWRITEMASK = 15, + SVGA3D_RS_FOGSTART = 16, + SVGA3D_RS_FOGEND = 17, + SVGA3D_RS_FOGDENSITY = 18, + SVGA3D_RS_POINTSIZE = 19, + SVGA3D_RS_POINTSIZEMIN = 20, + SVGA3D_RS_POINTSIZEMAX = 21, + SVGA3D_RS_POINTSCALE_A = 22, + SVGA3D_RS_POINTSCALE_B = 23, + SVGA3D_RS_POINTSCALE_C = 24, + SVGA3D_RS_FOGCOLOR = 25, + SVGA3D_RS_AMBIENT = 26, + SVGA3D_RS_CLIPPLANEENABLE = 27, + SVGA3D_RS_FOGMODE = 28, + SVGA3D_RS_FILLMODE = 29, + SVGA3D_RS_SHADEMODE = 30, + SVGA3D_RS_LINEPATTERN = 31, + SVGA3D_RS_SRCBLEND = 32, + SVGA3D_RS_DSTBLEND = 33, + SVGA3D_RS_BLENDEQUATION = 34, + SVGA3D_RS_CULLMODE = 35, + SVGA3D_RS_ZFUNC = 36, + SVGA3D_RS_ALPHAFUNC = 37, + SVGA3D_RS_STENCILFUNC = 38, + SVGA3D_RS_STENCILFAIL = 39, + SVGA3D_RS_STENCILZFAIL = 40, + SVGA3D_RS_STENCILPASS = 41, + SVGA3D_RS_ALPHAREF = 42, + SVGA3D_RS_FRONTWINDING = 43, + SVGA3D_RS_COORDINATETYPE = 44, + SVGA3D_RS_ZBIAS = 45, + SVGA3D_RS_RANGEFOGENABLE = 46, + SVGA3D_RS_COLORWRITEENABLE = 47, + SVGA3D_RS_VERTEXMATERIALENABLE = 48, + SVGA3D_RS_DIFFUSEMATERIALSOURCE = 49, + SVGA3D_RS_SPECULARMATERIALSOURCE = 50, + SVGA3D_RS_AMBIENTMATERIALSOURCE = 51, + SVGA3D_RS_EMISSIVEMATERIALSOURCE = 52, + SVGA3D_RS_TEXTUREFACTOR = 53, + SVGA3D_RS_LOCALVIEWER = 54, + SVGA3D_RS_SCISSORTESTENABLE = 55, + SVGA3D_RS_BLENDCOLOR = 56, + SVGA3D_RS_STENCILENABLE2SIDED = 57, + SVGA3D_RS_CCWSTENCILFUNC = 58, + SVGA3D_RS_CCWSTENCILFAIL = 59, + SVGA3D_RS_CCWSTENCILZFAIL = 60, + SVGA3D_RS_CCWSTENCILPASS = 61, + SVGA3D_RS_VERTEXBLEND = 62, + SVGA3D_RS_SLOPESCALEDEPTHBIAS = 63, + SVGA3D_RS_DEPTHBIAS = 64, + + SVGA3D_RS_OUTPUTGAMMA = 65, + SVGA3D_RS_ZVISIBLE = 66, + SVGA3D_RS_LASTPIXEL = 67, + SVGA3D_RS_CLIPPING = 68, + SVGA3D_RS_WRAP0 = 69, + SVGA3D_RS_WRAP1 = 70, + SVGA3D_RS_WRAP2 = 71, + SVGA3D_RS_WRAP3 = 72, + SVGA3D_RS_WRAP4 = 73, + SVGA3D_RS_WRAP5 = 74, + SVGA3D_RS_WRAP6 = 75, + SVGA3D_RS_WRAP7 = 76, + SVGA3D_RS_WRAP8 = 77, + SVGA3D_RS_WRAP9 = 78, + SVGA3D_RS_WRAP10 = 79, + SVGA3D_RS_WRAP11 = 80, + SVGA3D_RS_WRAP12 = 81, + SVGA3D_RS_WRAP13 = 82, + SVGA3D_RS_WRAP14 = 83, + SVGA3D_RS_WRAP15 = 84, + SVGA3D_RS_MULTISAMPLEANTIALIAS = 85, + SVGA3D_RS_MULTISAMPLEMASK = 86, + SVGA3D_RS_INDEXEDVERTEXBLENDENABLE = 87, + SVGA3D_RS_TWEENFACTOR = 88, + SVGA3D_RS_ANTIALIASEDLINEENABLE = 89, + SVGA3D_RS_COLORWRITEENABLE1 = 90, + SVGA3D_RS_COLORWRITEENABLE2 = 91, + SVGA3D_RS_COLORWRITEENABLE3 = 92, + SVGA3D_RS_SEPARATEALPHABLENDENABLE = 93, + SVGA3D_RS_SRCBLENDALPHA = 94, + SVGA3D_RS_DSTBLENDALPHA = 95, + SVGA3D_RS_BLENDEQUATIONALPHA = 96, + SVGA3D_RS_TRANSPARENCYANTIALIAS = 97, + SVGA3D_RS_LINEWIDTH = 98, + SVGA3D_RS_MAX } SVGA3dRenderStateName; typedef enum { - SVGA3D_TRANSPARENCYANTIALIAS_NORMAL = 0, - SVGA3D_TRANSPARENCYANTIALIAS_ALPHATOCOVERAGE = 1, - SVGA3D_TRANSPARENCYANTIALIAS_SUPERSAMPLE = 2, - SVGA3D_TRANSPARENCYANTIALIAS_MAX + SVGA3D_TRANSPARENCYANTIALIAS_NORMAL = 0, + SVGA3D_TRANSPARENCYANTIALIAS_ALPHATOCOVERAGE = 1, + SVGA3D_TRANSPARENCYANTIALIAS_SUPERSAMPLE = 2, + SVGA3D_TRANSPARENCYANTIALIAS_MAX } SVGA3dTransparencyAntialiasType; typedef enum { - SVGA3D_VERTEXMATERIAL_NONE = 0, /* Use the value in the current material */ - SVGA3D_VERTEXMATERIAL_DIFFUSE = 1, /* Use the value in the diffuse component */ - SVGA3D_VERTEXMATERIAL_SPECULAR = 2, /* Use the value in the specular component */ - SVGA3D_VERTEXMATERIAL_MAX = 3, + SVGA3D_VERTEXMATERIAL_NONE = 0, + SVGA3D_VERTEXMATERIAL_DIFFUSE = 1, + SVGA3D_VERTEXMATERIAL_SPECULAR = 2, + SVGA3D_VERTEXMATERIAL_MAX = 3, } SVGA3dVertexMaterial; typedef enum { - SVGA3D_FILLMODE_INVALID = 0, - SVGA3D_FILLMODE_MIN = 1, - SVGA3D_FILLMODE_POINT = 1, - SVGA3D_FILLMODE_LINE = 2, - SVGA3D_FILLMODE_FILL = 3, - SVGA3D_FILLMODE_MAX + SVGA3D_FILLMODE_INVALID = 0, + SVGA3D_FILLMODE_MIN = 1, + SVGA3D_FILLMODE_POINT = 1, + SVGA3D_FILLMODE_LINE = 2, + SVGA3D_FILLMODE_FILL = 3, + SVGA3D_FILLMODE_MAX } SVGA3dFillModeType; - -typedef -#include "vmware_pack_begin.h" -union { - struct { - uint16 mode; /* SVGA3dFillModeType */ - uint16 face; /* SVGA3dFace */ - }; - uint32 uintValue; -} -#include "vmware_pack_end.h" -SVGA3dFillMode; +#pragma pack(push, 1) +typedef union { + struct { + uint16 mode; + uint16 face; + }; + uint32 uintValue; +} SVGA3dFillMode; +#pragma pack(pop) typedef enum { - SVGA3D_SHADEMODE_INVALID = 0, - SVGA3D_SHADEMODE_FLAT = 1, - SVGA3D_SHADEMODE_SMOOTH = 2, - SVGA3D_SHADEMODE_PHONG = 3, /* Not supported */ - SVGA3D_SHADEMODE_MAX + SVGA3D_SHADEMODE_INVALID = 0, + SVGA3D_SHADEMODE_FLAT = 1, + SVGA3D_SHADEMODE_SMOOTH = 2, + SVGA3D_SHADEMODE_PHONG = 3, + SVGA3D_SHADEMODE_MAX } SVGA3dShadeMode; -typedef -#include "vmware_pack_begin.h" -union { - struct { - uint16 repeat; - uint16 pattern; - }; - uint32 uintValue; -} -#include "vmware_pack_end.h" -SVGA3dLinePattern; +#pragma pack(push, 1) +typedef union { + struct { + uint16 repeat; + uint16 pattern; + }; + uint32 uintValue; +} SVGA3dLinePattern; +#pragma pack(pop) typedef enum { - SVGA3D_BLENDOP_INVALID = 0, - SVGA3D_BLENDOP_MIN = 1, - SVGA3D_BLENDOP_ZERO = 1, - SVGA3D_BLENDOP_ONE = 2, - SVGA3D_BLENDOP_SRCCOLOR = 3, - SVGA3D_BLENDOP_INVSRCCOLOR = 4, - SVGA3D_BLENDOP_SRCALPHA = 5, - SVGA3D_BLENDOP_INVSRCALPHA = 6, - SVGA3D_BLENDOP_DESTALPHA = 7, - SVGA3D_BLENDOP_INVDESTALPHA = 8, - SVGA3D_BLENDOP_DESTCOLOR = 9, - SVGA3D_BLENDOP_INVDESTCOLOR = 10, - SVGA3D_BLENDOP_SRCALPHASAT = 11, - SVGA3D_BLENDOP_BLENDFACTOR = 12, - SVGA3D_BLENDOP_INVBLENDFACTOR = 13, - SVGA3D_BLENDOP_SRC1COLOR = 14, - SVGA3D_BLENDOP_INVSRC1COLOR = 15, - SVGA3D_BLENDOP_SRC1ALPHA = 16, - SVGA3D_BLENDOP_INVSRC1ALPHA = 17, - SVGA3D_BLENDOP_BLENDFACTORALPHA = 18, - SVGA3D_BLENDOP_INVBLENDFACTORALPHA = 19, - SVGA3D_BLENDOP_MAX + SVGA3D_BLENDOP_INVALID = 0, + SVGA3D_BLENDOP_MIN = 1, + SVGA3D_BLENDOP_ZERO = 1, + SVGA3D_BLENDOP_ONE = 2, + SVGA3D_BLENDOP_SRCCOLOR = 3, + SVGA3D_BLENDOP_INVSRCCOLOR = 4, + SVGA3D_BLENDOP_SRCALPHA = 5, + SVGA3D_BLENDOP_INVSRCALPHA = 6, + SVGA3D_BLENDOP_DESTALPHA = 7, + SVGA3D_BLENDOP_INVDESTALPHA = 8, + SVGA3D_BLENDOP_DESTCOLOR = 9, + SVGA3D_BLENDOP_INVDESTCOLOR = 10, + SVGA3D_BLENDOP_SRCALPHASAT = 11, + SVGA3D_BLENDOP_BLENDFACTOR = 12, + SVGA3D_BLENDOP_INVBLENDFACTOR = 13, + SVGA3D_BLENDOP_SRC1COLOR = 14, + SVGA3D_BLENDOP_INVSRC1COLOR = 15, + SVGA3D_BLENDOP_SRC1ALPHA = 16, + SVGA3D_BLENDOP_INVSRC1ALPHA = 17, + SVGA3D_BLENDOP_BLENDFACTORALPHA = 18, + SVGA3D_BLENDOP_INVBLENDFACTORALPHA = 19, + SVGA3D_BLENDOP_MAX } SVGA3dBlendOp; typedef enum { - SVGA3D_BLENDEQ_INVALID = 0, - SVGA3D_BLENDEQ_MIN = 1, - SVGA3D_BLENDEQ_ADD = 1, - SVGA3D_BLENDEQ_SUBTRACT = 2, - SVGA3D_BLENDEQ_REVSUBTRACT = 3, - SVGA3D_BLENDEQ_MINIMUM = 4, - SVGA3D_BLENDEQ_MAXIMUM = 5, - SVGA3D_BLENDEQ_MAX + SVGA3D_BLENDEQ_INVALID = 0, + SVGA3D_BLENDEQ_MIN = 1, + SVGA3D_BLENDEQ_ADD = 1, + SVGA3D_BLENDEQ_SUBTRACT = 2, + SVGA3D_BLENDEQ_REVSUBTRACT = 3, + SVGA3D_BLENDEQ_MINIMUM = 4, + SVGA3D_BLENDEQ_MAXIMUM = 5, + SVGA3D_BLENDEQ_MAX } SVGA3dBlendEquation; typedef enum { - SVGA3D_DX11_LOGICOP_MIN = 0, - SVGA3D_DX11_LOGICOP_CLEAR = 0, - SVGA3D_DX11_LOGICOP_SET = 1, - SVGA3D_DX11_LOGICOP_COPY = 2, - SVGA3D_DX11_LOGICOP_COPY_INVERTED = 3, - SVGA3D_DX11_LOGICOP_NOOP = 4, - SVGA3D_DX11_LOGICOP_INVERT = 5, - SVGA3D_DX11_LOGICOP_AND = 6, - SVGA3D_DX11_LOGICOP_NAND = 7, - SVGA3D_DX11_LOGICOP_OR = 8, - SVGA3D_DX11_LOGICOP_NOR = 9, - SVGA3D_DX11_LOGICOP_XOR = 10, - SVGA3D_DX11_LOGICOP_EQUIV = 11, - SVGA3D_DX11_LOGICOP_AND_REVERSE = 12, - SVGA3D_DX11_LOGICOP_AND_INVERTED = 13, - SVGA3D_DX11_LOGICOP_OR_REVERSE = 14, - SVGA3D_DX11_LOGICOP_OR_INVERTED = 15, - SVGA3D_DX11_LOGICOP_MAX + SVGA3D_DX11_LOGICOP_MIN = 0, + SVGA3D_DX11_LOGICOP_CLEAR = 0, + SVGA3D_DX11_LOGICOP_SET = 1, + SVGA3D_DX11_LOGICOP_COPY = 2, + SVGA3D_DX11_LOGICOP_COPY_INVERTED = 3, + SVGA3D_DX11_LOGICOP_NOOP = 4, + SVGA3D_DX11_LOGICOP_INVERT = 5, + SVGA3D_DX11_LOGICOP_AND = 6, + SVGA3D_DX11_LOGICOP_NAND = 7, + SVGA3D_DX11_LOGICOP_OR = 8, + SVGA3D_DX11_LOGICOP_NOR = 9, + SVGA3D_DX11_LOGICOP_XOR = 10, + SVGA3D_DX11_LOGICOP_EQUIV = 11, + SVGA3D_DX11_LOGICOP_AND_REVERSE = 12, + SVGA3D_DX11_LOGICOP_AND_INVERTED = 13, + SVGA3D_DX11_LOGICOP_OR_REVERSE = 14, + SVGA3D_DX11_LOGICOP_OR_INVERTED = 15, + SVGA3D_DX11_LOGICOP_MAX } SVGA3dDX11LogicOp; typedef enum { - SVGA3D_FRONTWINDING_INVALID = 0, - SVGA3D_FRONTWINDING_CW = 1, - SVGA3D_FRONTWINDING_CCW = 2, - SVGA3D_FRONTWINDING_MAX + SVGA3D_FRONTWINDING_INVALID = 0, + SVGA3D_FRONTWINDING_CW = 1, + SVGA3D_FRONTWINDING_MIN = 1, + SVGA3D_FRONTWINDING_CCW = 2, + SVGA3D_FRONTWINDING_MAX } SVGA3dFrontWinding; typedef enum { - SVGA3D_FACE_INVALID = 0, - SVGA3D_FACE_NONE = 1, - SVGA3D_FACE_MIN = 1, - SVGA3D_FACE_FRONT = 2, - SVGA3D_FACE_BACK = 3, - SVGA3D_FACE_FRONT_BACK = 4, - SVGA3D_FACE_MAX + SVGA3D_FACE_INVALID = 0, + SVGA3D_FACE_NONE = 1, + SVGA3D_FACE_MIN = 1, + SVGA3D_FACE_FRONT = 2, + SVGA3D_FACE_BACK = 3, + SVGA3D_FACE_FRONT_BACK = 4, + SVGA3D_FACE_MAX } SVGA3dFace; -/* - * The order and the values should not be changed - */ - typedef enum { - SVGA3D_CMP_INVALID = 0, - SVGA3D_CMP_NEVER = 1, - SVGA3D_CMP_LESS = 2, - SVGA3D_CMP_EQUAL = 3, - SVGA3D_CMP_LESSEQUAL = 4, - SVGA3D_CMP_GREATER = 5, - SVGA3D_CMP_NOTEQUAL = 6, - SVGA3D_CMP_GREATEREQUAL = 7, - SVGA3D_CMP_ALWAYS = 8, - SVGA3D_CMP_MAX + SVGA3D_CMP_INVALID = 0, + SVGA3D_CMP_NEVER = 1, + SVGA3D_CMP_LESS = 2, + SVGA3D_CMP_EQUAL = 3, + SVGA3D_CMP_LESSEQUAL = 4, + SVGA3D_CMP_GREATER = 5, + SVGA3D_CMP_NOTEQUAL = 6, + SVGA3D_CMP_GREATEREQUAL = 7, + SVGA3D_CMP_ALWAYS = 8, + SVGA3D_CMP_MAX } SVGA3dCmpFunc; -/* - * SVGA3D_FOGFUNC_* specifies the fog equation, or PER_VERTEX which allows - * the fog factor to be specified in the alpha component of the specular - * (a.k.a. secondary) vertex color. - */ typedef enum { - SVGA3D_FOGFUNC_INVALID = 0, - SVGA3D_FOGFUNC_EXP = 1, - SVGA3D_FOGFUNC_EXP2 = 2, - SVGA3D_FOGFUNC_LINEAR = 3, - SVGA3D_FOGFUNC_PER_VERTEX = 4 + SVGA3D_FOGFUNC_INVALID = 0, + SVGA3D_FOGFUNC_EXP = 1, + SVGA3D_FOGFUNC_EXP2 = 2, + SVGA3D_FOGFUNC_LINEAR = 3, + SVGA3D_FOGFUNC_PER_VERTEX = 4 } SVGA3dFogFunction; -/* - * SVGA3D_FOGTYPE_* specifies if fog factors are computed on a per-vertex - * or per-pixel basis. - */ typedef enum { - SVGA3D_FOGTYPE_INVALID = 0, - SVGA3D_FOGTYPE_VERTEX = 1, - SVGA3D_FOGTYPE_PIXEL = 2, - SVGA3D_FOGTYPE_MAX = 3 + SVGA3D_FOGTYPE_INVALID = 0, + SVGA3D_FOGTYPE_VERTEX = 1, + SVGA3D_FOGTYPE_PIXEL = 2, + SVGA3D_FOGTYPE_MAX = 3 } SVGA3dFogType; -/* - * SVGA3D_FOGBASE_* selects depth or range-based fog. Depth-based fog is - * computed using the eye Z value of each pixel (or vertex), whereas range- - * based fog is computed using the actual distance (range) to the eye. - */ typedef enum { - SVGA3D_FOGBASE_INVALID = 0, - SVGA3D_FOGBASE_DEPTHBASED = 1, - SVGA3D_FOGBASE_RANGEBASED = 2, - SVGA3D_FOGBASE_MAX = 3 + SVGA3D_FOGBASE_INVALID = 0, + SVGA3D_FOGBASE_DEPTHBASED = 1, + SVGA3D_FOGBASE_RANGEBASED = 2, + SVGA3D_FOGBASE_MAX = 3 } SVGA3dFogBase; typedef enum { - SVGA3D_STENCILOP_INVALID = 0, - SVGA3D_STENCILOP_MIN = 1, - SVGA3D_STENCILOP_KEEP = 1, - SVGA3D_STENCILOP_ZERO = 2, - SVGA3D_STENCILOP_REPLACE = 3, - SVGA3D_STENCILOP_INCRSAT = 4, - SVGA3D_STENCILOP_DECRSAT = 5, - SVGA3D_STENCILOP_INVERT = 6, - SVGA3D_STENCILOP_INCR = 7, - SVGA3D_STENCILOP_DECR = 8, - SVGA3D_STENCILOP_MAX + SVGA3D_STENCILOP_INVALID = 0, + SVGA3D_STENCILOP_MIN = 1, + SVGA3D_STENCILOP_KEEP = 1, + SVGA3D_STENCILOP_ZERO = 2, + SVGA3D_STENCILOP_REPLACE = 3, + SVGA3D_STENCILOP_INCRSAT = 4, + SVGA3D_STENCILOP_DECRSAT = 5, + SVGA3D_STENCILOP_INVERT = 6, + SVGA3D_STENCILOP_INCR = 7, + SVGA3D_STENCILOP_DECR = 8, + SVGA3D_STENCILOP_MAX } SVGA3dStencilOp; typedef enum { - SVGA3D_CLIPPLANE_0 = (1 << 0), - SVGA3D_CLIPPLANE_1 = (1 << 1), - SVGA3D_CLIPPLANE_2 = (1 << 2), - SVGA3D_CLIPPLANE_3 = (1 << 3), - SVGA3D_CLIPPLANE_4 = (1 << 4), - SVGA3D_CLIPPLANE_5 = (1 << 5), + SVGA3D_CLIPPLANE_0 = (1 << 0), + SVGA3D_CLIPPLANE_1 = (1 << 1), + SVGA3D_CLIPPLANE_2 = (1 << 2), + SVGA3D_CLIPPLANE_3 = (1 << 3), + SVGA3D_CLIPPLANE_4 = (1 << 4), + SVGA3D_CLIPPLANE_5 = (1 << 5), } SVGA3dClipPlanes; typedef enum { - SVGA3D_CLEAR_COLOR = 0x1, - SVGA3D_CLEAR_DEPTH = 0x2, - SVGA3D_CLEAR_STENCIL = 0x4, - - /* - * Hint only, must be used together with SVGA3D_CLEAR_COLOR. If - * SVGA3D_CLEAR_DEPTH or SVGA3D_CLEAR_STENCIL bit is set, this - * bit will be ignored. - */ - SVGA3D_CLEAR_COLORFILL = 0x8 + SVGA3D_CLEAR_COLOR = 0x1, + SVGA3D_CLEAR_DEPTH = 0x2, + SVGA3D_CLEAR_STENCIL = 0x4, + + SVGA3D_CLEAR_COLORFILL = 0x8 } SVGA3dClearFlag; typedef enum { - SVGA3D_RT_DEPTH = 0, - SVGA3D_RT_MIN = 0, - SVGA3D_RT_STENCIL = 1, - SVGA3D_RT_COLOR0 = 2, - SVGA3D_RT_COLOR1 = 3, - SVGA3D_RT_COLOR2 = 4, - SVGA3D_RT_COLOR3 = 5, - SVGA3D_RT_COLOR4 = 6, - SVGA3D_RT_COLOR5 = 7, - SVGA3D_RT_COLOR6 = 8, - SVGA3D_RT_COLOR7 = 9, - SVGA3D_RT_MAX, - SVGA3D_RT_INVALID = ((uint32)-1), + SVGA3D_RT_DEPTH = 0, + SVGA3D_RT_MIN = 0, + SVGA3D_RT_STENCIL = 1, + SVGA3D_RT_COLOR0 = 2, + SVGA3D_RT_COLOR1 = 3, + SVGA3D_RT_COLOR2 = 4, + SVGA3D_RT_COLOR3 = 5, + SVGA3D_RT_COLOR4 = 6, + SVGA3D_RT_COLOR5 = 7, + SVGA3D_RT_COLOR6 = 8, + SVGA3D_RT_COLOR7 = 9, + SVGA3D_RT_MAX, + SVGA3D_RT_INVALID = ((uint32)-1), } SVGA3dRenderTargetType; #define SVGA3D_MAX_RT_COLOR (SVGA3D_RT_COLOR7 - SVGA3D_RT_COLOR0 + 1) -typedef -#include "vmware_pack_begin.h" -union { - struct { - uint32 red : 1; - uint32 green : 1; - uint32 blue : 1; - uint32 alpha : 1; - }; - uint32 uintValue; -} -#include "vmware_pack_end.h" -SVGA3dColorMask; +#pragma pack(push, 1) +typedef union { + struct { + uint32 red : 1; + uint32 green : 1; + uint32 blue : 1; + uint32 alpha : 1; + }; + uint32 uintValue; +} SVGA3dColorMask; +#pragma pack(pop) typedef enum { - SVGA3D_VBLEND_DISABLE = 0, - SVGA3D_VBLEND_1WEIGHT = 1, - SVGA3D_VBLEND_2WEIGHT = 2, - SVGA3D_VBLEND_3WEIGHT = 3, - SVGA3D_VBLEND_MAX = 4, + SVGA3D_VBLEND_DISABLE = 0, + SVGA3D_VBLEND_1WEIGHT = 1, + SVGA3D_VBLEND_2WEIGHT = 2, + SVGA3D_VBLEND_3WEIGHT = 3, + SVGA3D_VBLEND_MAX = 4, } SVGA3dVertexBlendFlags; typedef enum { - SVGA3D_WRAPCOORD_0 = 1 << 0, - SVGA3D_WRAPCOORD_1 = 1 << 1, - SVGA3D_WRAPCOORD_2 = 1 << 2, - SVGA3D_WRAPCOORD_3 = 1 << 3, - SVGA3D_WRAPCOORD_ALL = 0xF, + SVGA3D_WRAPCOORD_0 = 1 << 0, + SVGA3D_WRAPCOORD_1 = 1 << 1, + SVGA3D_WRAPCOORD_2 = 1 << 2, + SVGA3D_WRAPCOORD_3 = 1 << 3, + SVGA3D_WRAPCOORD_ALL = 0xF, } SVGA3dWrapFlags; -/* - * SVGA_3D_CMD_TEXTURESTATE Types. All value types - * must fit in a uint32. - */ - typedef enum { - SVGA3D_TS_INVALID = 0, - SVGA3D_TS_MIN = 1, - SVGA3D_TS_BIND_TEXTURE = 1, /* SVGA3dSurfaceId */ - SVGA3D_TS_COLOROP = 2, /* SVGA3dTextureCombiner */ - SVGA3D_TS_COLORARG1 = 3, /* SVGA3dTextureArgData */ - SVGA3D_TS_COLORARG2 = 4, /* SVGA3dTextureArgData */ - SVGA3D_TS_ALPHAOP = 5, /* SVGA3dTextureCombiner */ - SVGA3D_TS_ALPHAARG1 = 6, /* SVGA3dTextureArgData */ - SVGA3D_TS_ALPHAARG2 = 7, /* SVGA3dTextureArgData */ - SVGA3D_TS_ADDRESSU = 8, /* SVGA3dTextureAddress */ - SVGA3D_TS_ADDRESSV = 9, /* SVGA3dTextureAddress */ - SVGA3D_TS_MIPFILTER = 10, /* SVGA3dTextureFilter */ - SVGA3D_TS_MAGFILTER = 11, /* SVGA3dTextureFilter */ - SVGA3D_TS_MINFILTER = 12, /* SVGA3dTextureFilter */ - SVGA3D_TS_BORDERCOLOR = 13, /* SVGA3dColor */ - SVGA3D_TS_TEXCOORDINDEX = 14, /* uint32 */ - SVGA3D_TS_TEXTURETRANSFORMFLAGS = 15, /* SVGA3dTexTransformFlags */ - SVGA3D_TS_TEXCOORDGEN = 16, /* SVGA3dTextureCoordGen */ - SVGA3D_TS_BUMPENVMAT00 = 17, /* float */ - SVGA3D_TS_BUMPENVMAT01 = 18, /* float */ - SVGA3D_TS_BUMPENVMAT10 = 19, /* float */ - SVGA3D_TS_BUMPENVMAT11 = 20, /* float */ - SVGA3D_TS_TEXTURE_MIPMAP_LEVEL = 21, /* uint32 */ - SVGA3D_TS_TEXTURE_LOD_BIAS = 22, /* float */ - SVGA3D_TS_TEXTURE_ANISOTROPIC_LEVEL = 23, /* uint32 */ - SVGA3D_TS_ADDRESSW = 24, /* SVGA3dTextureAddress */ - - - /* - * Sampler Gamma Level - * - * Sampler gamma effects the color of samples taken from the sampler. A - * value of 1.0 will produce linear samples. If the value is <= 0.0 the - * gamma value is ignored and a linear space is used. - */ - - SVGA3D_TS_GAMMA = 25, /* float */ - SVGA3D_TS_BUMPENVLSCALE = 26, /* float */ - SVGA3D_TS_BUMPENVLOFFSET = 27, /* float */ - SVGA3D_TS_COLORARG0 = 28, /* SVGA3dTextureArgData */ - SVGA3D_TS_ALPHAARG0 = 29, /* SVGA3dTextureArgData */ - SVGA3D_TS_PREGB_MAX = 30, /* Max value before GBObjects */ - SVGA3D_TS_CONSTANT = 30, /* SVGA3dColor */ - SVGA3D_TS_COLOR_KEY_ENABLE = 31, /* SVGA3dBool */ - SVGA3D_TS_COLOR_KEY = 32, /* SVGA3dColor */ - SVGA3D_TS_MAX + SVGA3D_TS_INVALID = 0, + SVGA3D_TS_MIN = 1, + SVGA3D_TS_BIND_TEXTURE = 1, + SVGA3D_TS_COLOROP = 2, + SVGA3D_TS_COLORARG1 = 3, + SVGA3D_TS_COLORARG2 = 4, + SVGA3D_TS_ALPHAOP = 5, + SVGA3D_TS_ALPHAARG1 = 6, + SVGA3D_TS_ALPHAARG2 = 7, + SVGA3D_TS_ADDRESSU = 8, + SVGA3D_TS_ADDRESSV = 9, + SVGA3D_TS_MIPFILTER = 10, + SVGA3D_TS_MAGFILTER = 11, + SVGA3D_TS_MINFILTER = 12, + SVGA3D_TS_BORDERCOLOR = 13, + SVGA3D_TS_TEXCOORDINDEX = 14, + SVGA3D_TS_TEXTURETRANSFORMFLAGS = 15, + SVGA3D_TS_TEXCOORDGEN = 16, + SVGA3D_TS_BUMPENVMAT00 = 17, + SVGA3D_TS_BUMPENVMAT01 = 18, + SVGA3D_TS_BUMPENVMAT10 = 19, + SVGA3D_TS_BUMPENVMAT11 = 20, + SVGA3D_TS_TEXTURE_MIPMAP_LEVEL = 21, + SVGA3D_TS_TEXTURE_LOD_BIAS = 22, + SVGA3D_TS_TEXTURE_ANISOTROPIC_LEVEL = 23, + SVGA3D_TS_ADDRESSW = 24, + + SVGA3D_TS_GAMMA = 25, + SVGA3D_TS_BUMPENVLSCALE = 26, + SVGA3D_TS_BUMPENVLOFFSET = 27, + SVGA3D_TS_COLORARG0 = 28, + SVGA3D_TS_ALPHAARG0 = 29, + SVGA3D_TS_PREGB_MAX = 30, + SVGA3D_TS_CONSTANT = 30, + SVGA3D_TS_COLOR_KEY_ENABLE = 31, + SVGA3D_TS_COLOR_KEY = 32, + SVGA3D_TS_MAX } SVGA3dTextureStateName; typedef enum { - SVGA3D_TC_INVALID = 0, - SVGA3D_TC_DISABLE = 1, - SVGA3D_TC_SELECTARG1 = 2, - SVGA3D_TC_SELECTARG2 = 3, - SVGA3D_TC_MODULATE = 4, - SVGA3D_TC_ADD = 5, - SVGA3D_TC_ADDSIGNED = 6, - SVGA3D_TC_SUBTRACT = 7, - SVGA3D_TC_BLENDTEXTUREALPHA = 8, - SVGA3D_TC_BLENDDIFFUSEALPHA = 9, - SVGA3D_TC_BLENDCURRENTALPHA = 10, - SVGA3D_TC_BLENDFACTORALPHA = 11, - SVGA3D_TC_MODULATE2X = 12, - SVGA3D_TC_MODULATE4X = 13, - SVGA3D_TC_DSDT = 14, - SVGA3D_TC_DOTPRODUCT3 = 15, - SVGA3D_TC_BLENDTEXTUREALPHAPM = 16, - SVGA3D_TC_ADDSIGNED2X = 17, - SVGA3D_TC_ADDSMOOTH = 18, - SVGA3D_TC_PREMODULATE = 19, - SVGA3D_TC_MODULATEALPHA_ADDCOLOR = 20, - SVGA3D_TC_MODULATECOLOR_ADDALPHA = 21, - SVGA3D_TC_MODULATEINVALPHA_ADDCOLOR = 22, - SVGA3D_TC_MODULATEINVCOLOR_ADDALPHA = 23, - SVGA3D_TC_BUMPENVMAPLUMINANCE = 24, - SVGA3D_TC_MULTIPLYADD = 25, - SVGA3D_TC_LERP = 26, - SVGA3D_TC_MAX + SVGA3D_TC_INVALID = 0, + SVGA3D_TC_DISABLE = 1, + SVGA3D_TC_SELECTARG1 = 2, + SVGA3D_TC_SELECTARG2 = 3, + SVGA3D_TC_MODULATE = 4, + SVGA3D_TC_ADD = 5, + SVGA3D_TC_ADDSIGNED = 6, + SVGA3D_TC_SUBTRACT = 7, + SVGA3D_TC_BLENDTEXTUREALPHA = 8, + SVGA3D_TC_BLENDDIFFUSEALPHA = 9, + SVGA3D_TC_BLENDCURRENTALPHA = 10, + SVGA3D_TC_BLENDFACTORALPHA = 11, + SVGA3D_TC_MODULATE2X = 12, + SVGA3D_TC_MODULATE4X = 13, + SVGA3D_TC_DSDT = 14, + SVGA3D_TC_DOTPRODUCT3 = 15, + SVGA3D_TC_BLENDTEXTUREALPHAPM = 16, + SVGA3D_TC_ADDSIGNED2X = 17, + SVGA3D_TC_ADDSMOOTH = 18, + SVGA3D_TC_PREMODULATE = 19, + SVGA3D_TC_MODULATEALPHA_ADDCOLOR = 20, + SVGA3D_TC_MODULATECOLOR_ADDALPHA = 21, + SVGA3D_TC_MODULATEINVALPHA_ADDCOLOR = 22, + SVGA3D_TC_MODULATEINVCOLOR_ADDALPHA = 23, + SVGA3D_TC_BUMPENVMAPLUMINANCE = 24, + SVGA3D_TC_MULTIPLYADD = 25, + SVGA3D_TC_LERP = 26, + SVGA3D_TC_MAX } SVGA3dTextureCombiner; -#define SVGA3D_TC_CAP_BIT(svga3d_tc_op) (svga3d_tc_op ? (1 << (svga3d_tc_op - 1)) : 0) +#define SVGA3D_TC_CAP_BIT(svga3d_tc_op) \ + (svga3d_tc_op ? (1 << (svga3d_tc_op - 1)) : 0) typedef enum { - SVGA3D_TEX_ADDRESS_INVALID = 0, - SVGA3D_TEX_ADDRESS_MIN = 1, - SVGA3D_TEX_ADDRESS_WRAP = 1, - SVGA3D_TEX_ADDRESS_MIRROR = 2, - SVGA3D_TEX_ADDRESS_CLAMP = 3, - SVGA3D_TEX_ADDRESS_BORDER = 4, - SVGA3D_TEX_ADDRESS_MIRRORONCE = 5, - SVGA3D_TEX_ADDRESS_EDGE = 6, - SVGA3D_TEX_ADDRESS_MAX + SVGA3D_TEX_ADDRESS_INVALID = 0, + SVGA3D_TEX_ADDRESS_MIN = 1, + SVGA3D_TEX_ADDRESS_WRAP = 1, + SVGA3D_TEX_ADDRESS_MIRROR = 2, + SVGA3D_TEX_ADDRESS_CLAMP = 3, + SVGA3D_TEX_ADDRESS_BORDER = 4, + SVGA3D_TEX_ADDRESS_MIRRORONCE = 5, + SVGA3D_TEX_ADDRESS_EDGE = 6, + SVGA3D_TEX_ADDRESS_MAX } SVGA3dTextureAddress; -/* - * SVGA3D_TEX_FILTER_NONE as the minification filter means mipmapping is - * disabled, and the rasterizer should use the magnification filter instead. - */ typedef enum { - SVGA3D_TEX_FILTER_NONE = 0, - SVGA3D_TEX_FILTER_MIN = 0, - SVGA3D_TEX_FILTER_NEAREST = 1, - SVGA3D_TEX_FILTER_LINEAR = 2, - SVGA3D_TEX_FILTER_ANISOTROPIC = 3, - SVGA3D_TEX_FILTER_FLATCUBIC = 4, /* Deprecated, not implemented */ - SVGA3D_TEX_FILTER_GAUSSIANCUBIC = 5, /* Deprecated, not implemented */ - SVGA3D_TEX_FILTER_PYRAMIDALQUAD = 6, /* Not currently implemented */ - SVGA3D_TEX_FILTER_GAUSSIANQUAD = 7, /* Not currently implemented */ - SVGA3D_TEX_FILTER_MAX + SVGA3D_TEX_FILTER_NONE = 0, + SVGA3D_TEX_FILTER_MIN = 0, + SVGA3D_TEX_FILTER_NEAREST = 1, + SVGA3D_TEX_FILTER_LINEAR = 2, + SVGA3D_TEX_FILTER_ANISOTROPIC = 3, + SVGA3D_TEX_FILTER_FLATCUBIC = 4, + SVGA3D_TEX_FILTER_GAUSSIANCUBIC = 5, + SVGA3D_TEX_FILTER_PYRAMIDALQUAD = 6, + SVGA3D_TEX_FILTER_GAUSSIANQUAD = 7, + SVGA3D_TEX_FILTER_MAX } SVGA3dTextureFilter; typedef enum { - SVGA3D_TEX_TRANSFORM_OFF = 0, - SVGA3D_TEX_TRANSFORM_S = (1 << 0), - SVGA3D_TEX_TRANSFORM_T = (1 << 1), - SVGA3D_TEX_TRANSFORM_R = (1 << 2), - SVGA3D_TEX_TRANSFORM_Q = (1 << 3), - SVGA3D_TEX_PROJECTED = (1 << 15), + SVGA3D_TEX_TRANSFORM_OFF = 0, + SVGA3D_TEX_TRANSFORM_S = (1 << 0), + SVGA3D_TEX_TRANSFORM_T = (1 << 1), + SVGA3D_TEX_TRANSFORM_R = (1 << 2), + SVGA3D_TEX_TRANSFORM_Q = (1 << 3), + SVGA3D_TEX_PROJECTED = (1 << 15), } SVGA3dTexTransformFlags; typedef enum { - SVGA3D_TEXCOORD_GEN_OFF = 0, - SVGA3D_TEXCOORD_GEN_EYE_POSITION = 1, - SVGA3D_TEXCOORD_GEN_EYE_NORMAL = 2, - SVGA3D_TEXCOORD_GEN_REFLECTIONVECTOR = 3, - SVGA3D_TEXCOORD_GEN_SPHERE = 4, - SVGA3D_TEXCOORD_GEN_MAX + SVGA3D_TEXCOORD_GEN_OFF = 0, + SVGA3D_TEXCOORD_GEN_EYE_POSITION = 1, + SVGA3D_TEXCOORD_GEN_EYE_NORMAL = 2, + SVGA3D_TEXCOORD_GEN_REFLECTIONVECTOR = 3, + SVGA3D_TEXCOORD_GEN_SPHERE = 4, + SVGA3D_TEXCOORD_GEN_MAX } SVGA3dTextureCoordGen; -/* - * Texture argument constants for texture combiner - */ typedef enum { - SVGA3D_TA_INVALID = 0, - SVGA3D_TA_TFACTOR = 1, - SVGA3D_TA_PREVIOUS = 2, - SVGA3D_TA_DIFFUSE = 3, - SVGA3D_TA_TEXTURE = 4, - SVGA3D_TA_SPECULAR = 5, - SVGA3D_TA_CONSTANT = 6, - SVGA3D_TA_MAX + SVGA3D_TA_INVALID = 0, + SVGA3D_TA_TFACTOR = 1, + SVGA3D_TA_PREVIOUS = 2, + SVGA3D_TA_DIFFUSE = 3, + SVGA3D_TA_TEXTURE = 4, + SVGA3D_TA_SPECULAR = 5, + SVGA3D_TA_CONSTANT = 6, + SVGA3D_TA_MAX } SVGA3dTextureArgData; #define SVGA3D_TM_MASK_LEN 4 -/* Modifiers for texture argument constants defined above. */ typedef enum { - SVGA3D_TM_NONE = 0, - SVGA3D_TM_ALPHA = (1 << SVGA3D_TM_MASK_LEN), - SVGA3D_TM_ONE_MINUS = (2 << SVGA3D_TM_MASK_LEN), + SVGA3D_TM_NONE = 0, + SVGA3D_TM_ALPHA = (1 << SVGA3D_TM_MASK_LEN), + SVGA3D_TM_ONE_MINUS = (2 << SVGA3D_TM_MASK_LEN), } SVGA3dTextureArgModifier; -/* - * Vertex declarations - * - * Notes: - * - * SVGA3D_DECLUSAGE_POSITIONT is for pre-transformed vertices. If you - * draw with any POSITIONT vertex arrays, the programmable vertex - * pipeline will be implicitly disabled. Drawing will take place as if - * no vertex shader was bound. - */ - typedef enum { - SVGA3D_DECLUSAGE_POSITION = 0, - SVGA3D_DECLUSAGE_BLENDWEIGHT, - SVGA3D_DECLUSAGE_BLENDINDICES, - SVGA3D_DECLUSAGE_NORMAL, - SVGA3D_DECLUSAGE_PSIZE, - SVGA3D_DECLUSAGE_TEXCOORD, - SVGA3D_DECLUSAGE_TANGENT, - SVGA3D_DECLUSAGE_BINORMAL, - SVGA3D_DECLUSAGE_TESSFACTOR, - SVGA3D_DECLUSAGE_POSITIONT, - SVGA3D_DECLUSAGE_COLOR, - SVGA3D_DECLUSAGE_FOG, - SVGA3D_DECLUSAGE_DEPTH, - SVGA3D_DECLUSAGE_SAMPLE, - SVGA3D_DECLUSAGE_MAX + SVGA3D_DECLUSAGE_POSITION = 0, + SVGA3D_DECLUSAGE_BLENDWEIGHT, + SVGA3D_DECLUSAGE_BLENDINDICES, + SVGA3D_DECLUSAGE_NORMAL, + SVGA3D_DECLUSAGE_PSIZE, + SVGA3D_DECLUSAGE_TEXCOORD, + SVGA3D_DECLUSAGE_TANGENT, + SVGA3D_DECLUSAGE_BINORMAL, + SVGA3D_DECLUSAGE_TESSFACTOR, + SVGA3D_DECLUSAGE_POSITIONT, + SVGA3D_DECLUSAGE_COLOR, + SVGA3D_DECLUSAGE_FOG, + SVGA3D_DECLUSAGE_DEPTH, + SVGA3D_DECLUSAGE_SAMPLE, + SVGA3D_DECLUSAGE_MAX } SVGA3dDeclUsage; typedef enum { - SVGA3D_DECLMETHOD_DEFAULT = 0, - SVGA3D_DECLMETHOD_PARTIALU, - SVGA3D_DECLMETHOD_PARTIALV, - SVGA3D_DECLMETHOD_CROSSUV, /* Normal */ - SVGA3D_DECLMETHOD_UV, - SVGA3D_DECLMETHOD_LOOKUP, /* Lookup a displacement map */ - SVGA3D_DECLMETHOD_LOOKUPPRESAMPLED, /* Lookup a pre-sampled displacement */ - /* map */ + SVGA3D_DECLMETHOD_DEFAULT = 0, + SVGA3D_DECLMETHOD_PARTIALU, + SVGA3D_DECLMETHOD_PARTIALV, + SVGA3D_DECLMETHOD_CROSSUV, + SVGA3D_DECLMETHOD_UV, + SVGA3D_DECLMETHOD_LOOKUP, + SVGA3D_DECLMETHOD_LOOKUPPRESAMPLED, } SVGA3dDeclMethod; typedef enum { - SVGA3D_DECLTYPE_FLOAT1 = 0, - SVGA3D_DECLTYPE_FLOAT2 = 1, - SVGA3D_DECLTYPE_FLOAT3 = 2, - SVGA3D_DECLTYPE_FLOAT4 = 3, - SVGA3D_DECLTYPE_D3DCOLOR = 4, - SVGA3D_DECLTYPE_UBYTE4 = 5, - SVGA3D_DECLTYPE_SHORT2 = 6, - SVGA3D_DECLTYPE_SHORT4 = 7, - SVGA3D_DECLTYPE_UBYTE4N = 8, - SVGA3D_DECLTYPE_SHORT2N = 9, - SVGA3D_DECLTYPE_SHORT4N = 10, - SVGA3D_DECLTYPE_USHORT2N = 11, - SVGA3D_DECLTYPE_USHORT4N = 12, - SVGA3D_DECLTYPE_UDEC3 = 13, - SVGA3D_DECLTYPE_DEC3N = 14, - SVGA3D_DECLTYPE_FLOAT16_2 = 15, - SVGA3D_DECLTYPE_FLOAT16_4 = 16, - SVGA3D_DECLTYPE_MAX, + SVGA3D_DECLTYPE_FLOAT1 = 0, + SVGA3D_DECLTYPE_FLOAT2 = 1, + SVGA3D_DECLTYPE_FLOAT3 = 2, + SVGA3D_DECLTYPE_FLOAT4 = 3, + SVGA3D_DECLTYPE_D3DCOLOR = 4, + SVGA3D_DECLTYPE_UBYTE4 = 5, + SVGA3D_DECLTYPE_SHORT2 = 6, + SVGA3D_DECLTYPE_SHORT4 = 7, + SVGA3D_DECLTYPE_UBYTE4N = 8, + SVGA3D_DECLTYPE_SHORT2N = 9, + SVGA3D_DECLTYPE_SHORT4N = 10, + SVGA3D_DECLTYPE_USHORT2N = 11, + SVGA3D_DECLTYPE_USHORT4N = 12, + SVGA3D_DECLTYPE_UDEC3 = 13, + SVGA3D_DECLTYPE_DEC3N = 14, + SVGA3D_DECLTYPE_FLOAT16_2 = 15, + SVGA3D_DECLTYPE_FLOAT16_4 = 16, + SVGA3D_DECLTYPE_MAX, } SVGA3dDeclType; -/* - * This structure is used for the divisor for geometry instancing; - * it's a direct translation of the Direct3D equivalent. - */ typedef union { - struct { - /* - * For index data, this number represents the number of instances to draw. - * For instance data, this number represents the number of - * instances/vertex in this stream - */ - uint32 count : 30; - - /* - * This is 1 if this is supposed to be the data that is repeated for - * every instance. - */ - uint32 indexedData : 1; - - /* - * This is 1 if this is supposed to be the per-instance data. - */ - uint32 instanceData : 1; - }; - - uint32 value; + struct { + uint32 count : 30; + + uint32 indexedData : 1; + + uint32 instanceData : 1; + }; + + uint32 value; } SVGA3dVertexDivisor; typedef enum { - /* - * SVGA3D_PRIMITIVE_INVALID is a valid primitive type. - * - * List MIN second so debuggers will think INVALID is - * the correct name. - */ - SVGA3D_PRIMITIVE_INVALID = 0, - SVGA3D_PRIMITIVE_MIN = 0, - SVGA3D_PRIMITIVE_TRIANGLELIST = 1, - SVGA3D_PRIMITIVE_POINTLIST = 2, - SVGA3D_PRIMITIVE_LINELIST = 3, - SVGA3D_PRIMITIVE_LINESTRIP = 4, - SVGA3D_PRIMITIVE_TRIANGLESTRIP = 5, - SVGA3D_PRIMITIVE_TRIANGLEFAN = 6, - SVGA3D_PRIMITIVE_LINELIST_ADJ = 7, - SVGA3D_PRIMITIVE_PREDX_MAX = 7, - SVGA3D_PRIMITIVE_LINESTRIP_ADJ = 8, - SVGA3D_PRIMITIVE_TRIANGLELIST_ADJ = 9, - SVGA3D_PRIMITIVE_TRIANGLESTRIP_ADJ = 10, - SVGA3D_PRIMITIVE_DX10_MAX = 11, - SVGA3D_PRIMITIVE_1_CONTROL_POINT_PATCH = 11, - SVGA3D_PRIMITIVE_2_CONTROL_POINT_PATCH = 12, - SVGA3D_PRIMITIVE_3_CONTROL_POINT_PATCH = 13, - SVGA3D_PRIMITIVE_4_CONTROL_POINT_PATCH = 14, - SVGA3D_PRIMITIVE_5_CONTROL_POINT_PATCH = 15, - SVGA3D_PRIMITIVE_6_CONTROL_POINT_PATCH = 16, - SVGA3D_PRIMITIVE_7_CONTROL_POINT_PATCH = 17, - SVGA3D_PRIMITIVE_8_CONTROL_POINT_PATCH = 18, - SVGA3D_PRIMITIVE_9_CONTROL_POINT_PATCH = 19, - SVGA3D_PRIMITIVE_10_CONTROL_POINT_PATCH = 20, - SVGA3D_PRIMITIVE_11_CONTROL_POINT_PATCH = 21, - SVGA3D_PRIMITIVE_12_CONTROL_POINT_PATCH = 22, - SVGA3D_PRIMITIVE_13_CONTROL_POINT_PATCH = 23, - SVGA3D_PRIMITIVE_14_CONTROL_POINT_PATCH = 24, - SVGA3D_PRIMITIVE_15_CONTROL_POINT_PATCH = 25, - SVGA3D_PRIMITIVE_16_CONTROL_POINT_PATCH = 26, - SVGA3D_PRIMITIVE_17_CONTROL_POINT_PATCH = 27, - SVGA3D_PRIMITIVE_18_CONTROL_POINT_PATCH = 28, - SVGA3D_PRIMITIVE_19_CONTROL_POINT_PATCH = 29, - SVGA3D_PRIMITIVE_20_CONTROL_POINT_PATCH = 30, - SVGA3D_PRIMITIVE_21_CONTROL_POINT_PATCH = 31, - SVGA3D_PRIMITIVE_22_CONTROL_POINT_PATCH = 32, - SVGA3D_PRIMITIVE_23_CONTROL_POINT_PATCH = 33, - SVGA3D_PRIMITIVE_24_CONTROL_POINT_PATCH = 34, - SVGA3D_PRIMITIVE_25_CONTROL_POINT_PATCH = 35, - SVGA3D_PRIMITIVE_26_CONTROL_POINT_PATCH = 36, - SVGA3D_PRIMITIVE_27_CONTROL_POINT_PATCH = 37, - SVGA3D_PRIMITIVE_28_CONTROL_POINT_PATCH = 38, - SVGA3D_PRIMITIVE_29_CONTROL_POINT_PATCH = 39, - SVGA3D_PRIMITIVE_30_CONTROL_POINT_PATCH = 40, - SVGA3D_PRIMITIVE_31_CONTROL_POINT_PATCH = 41, - SVGA3D_PRIMITIVE_32_CONTROL_POINT_PATCH = 42, - SVGA3D_PRIMITIVE_MAX = 43 + + SVGA3D_PRIMITIVE_INVALID = 0, + SVGA3D_PRIMITIVE_MIN = 0, + SVGA3D_PRIMITIVE_TRIANGLELIST = 1, + SVGA3D_PRIMITIVE_POINTLIST = 2, + SVGA3D_PRIMITIVE_LINELIST = 3, + SVGA3D_PRIMITIVE_LINESTRIP = 4, + SVGA3D_PRIMITIVE_TRIANGLESTRIP = 5, + SVGA3D_PRIMITIVE_TRIANGLEFAN = 6, + SVGA3D_PRIMITIVE_LINELIST_ADJ = 7, + SVGA3D_PRIMITIVE_PREDX_MAX = 7, + SVGA3D_PRIMITIVE_LINESTRIP_ADJ = 8, + SVGA3D_PRIMITIVE_TRIANGLELIST_ADJ = 9, + SVGA3D_PRIMITIVE_TRIANGLESTRIP_ADJ = 10, + SVGA3D_PRIMITIVE_DX10_MAX = 11, + SVGA3D_PRIMITIVE_1_CONTROL_POINT_PATCH = 11, + SVGA3D_PRIMITIVE_2_CONTROL_POINT_PATCH = 12, + SVGA3D_PRIMITIVE_3_CONTROL_POINT_PATCH = 13, + SVGA3D_PRIMITIVE_4_CONTROL_POINT_PATCH = 14, + SVGA3D_PRIMITIVE_5_CONTROL_POINT_PATCH = 15, + SVGA3D_PRIMITIVE_6_CONTROL_POINT_PATCH = 16, + SVGA3D_PRIMITIVE_7_CONTROL_POINT_PATCH = 17, + SVGA3D_PRIMITIVE_8_CONTROL_POINT_PATCH = 18, + SVGA3D_PRIMITIVE_9_CONTROL_POINT_PATCH = 19, + SVGA3D_PRIMITIVE_10_CONTROL_POINT_PATCH = 20, + SVGA3D_PRIMITIVE_11_CONTROL_POINT_PATCH = 21, + SVGA3D_PRIMITIVE_12_CONTROL_POINT_PATCH = 22, + SVGA3D_PRIMITIVE_13_CONTROL_POINT_PATCH = 23, + SVGA3D_PRIMITIVE_14_CONTROL_POINT_PATCH = 24, + SVGA3D_PRIMITIVE_15_CONTROL_POINT_PATCH = 25, + SVGA3D_PRIMITIVE_16_CONTROL_POINT_PATCH = 26, + SVGA3D_PRIMITIVE_17_CONTROL_POINT_PATCH = 27, + SVGA3D_PRIMITIVE_18_CONTROL_POINT_PATCH = 28, + SVGA3D_PRIMITIVE_19_CONTROL_POINT_PATCH = 29, + SVGA3D_PRIMITIVE_20_CONTROL_POINT_PATCH = 30, + SVGA3D_PRIMITIVE_21_CONTROL_POINT_PATCH = 31, + SVGA3D_PRIMITIVE_22_CONTROL_POINT_PATCH = 32, + SVGA3D_PRIMITIVE_23_CONTROL_POINT_PATCH = 33, + SVGA3D_PRIMITIVE_24_CONTROL_POINT_PATCH = 34, + SVGA3D_PRIMITIVE_25_CONTROL_POINT_PATCH = 35, + SVGA3D_PRIMITIVE_26_CONTROL_POINT_PATCH = 36, + SVGA3D_PRIMITIVE_27_CONTROL_POINT_PATCH = 37, + SVGA3D_PRIMITIVE_28_CONTROL_POINT_PATCH = 38, + SVGA3D_PRIMITIVE_29_CONTROL_POINT_PATCH = 39, + SVGA3D_PRIMITIVE_30_CONTROL_POINT_PATCH = 40, + SVGA3D_PRIMITIVE_31_CONTROL_POINT_PATCH = 41, + SVGA3D_PRIMITIVE_32_CONTROL_POINT_PATCH = 42, + SVGA3D_PRIMITIVE_MAX = 43 } SVGA3dPrimitiveType; typedef enum { - SVGA3D_COORDINATE_INVALID = 0, - SVGA3D_COORDINATE_LEFTHANDED = 1, - SVGA3D_COORDINATE_RIGHTHANDED = 2, - SVGA3D_COORDINATE_MAX + SVGA3D_COORDINATE_INVALID = 0, + SVGA3D_COORDINATE_LEFTHANDED = 1, + SVGA3D_COORDINATE_RIGHTHANDED = 2, + SVGA3D_COORDINATE_MAX } SVGA3dCoordinateType; typedef enum { - SVGA3D_TRANSFORM_INVALID = 0, - SVGA3D_TRANSFORM_WORLD = 1, - SVGA3D_TRANSFORM_MIN = 1, - SVGA3D_TRANSFORM_VIEW = 2, - SVGA3D_TRANSFORM_PROJECTION = 3, - SVGA3D_TRANSFORM_TEXTURE0 = 4, - SVGA3D_TRANSFORM_TEXTURE1 = 5, - SVGA3D_TRANSFORM_TEXTURE2 = 6, - SVGA3D_TRANSFORM_TEXTURE3 = 7, - SVGA3D_TRANSFORM_TEXTURE4 = 8, - SVGA3D_TRANSFORM_TEXTURE5 = 9, - SVGA3D_TRANSFORM_TEXTURE6 = 10, - SVGA3D_TRANSFORM_TEXTURE7 = 11, - SVGA3D_TRANSFORM_WORLD1 = 12, - SVGA3D_TRANSFORM_WORLD2 = 13, - SVGA3D_TRANSFORM_WORLD3 = 14, - SVGA3D_TRANSFORM_MAX + SVGA3D_TRANSFORM_INVALID = 0, + SVGA3D_TRANSFORM_WORLD = 1, + SVGA3D_TRANSFORM_MIN = 1, + SVGA3D_TRANSFORM_VIEW = 2, + SVGA3D_TRANSFORM_PROJECTION = 3, + SVGA3D_TRANSFORM_TEXTURE0 = 4, + SVGA3D_TRANSFORM_TEXTURE1 = 5, + SVGA3D_TRANSFORM_TEXTURE2 = 6, + SVGA3D_TRANSFORM_TEXTURE3 = 7, + SVGA3D_TRANSFORM_TEXTURE4 = 8, + SVGA3D_TRANSFORM_TEXTURE5 = 9, + SVGA3D_TRANSFORM_TEXTURE6 = 10, + SVGA3D_TRANSFORM_TEXTURE7 = 11, + SVGA3D_TRANSFORM_WORLD1 = 12, + SVGA3D_TRANSFORM_WORLD2 = 13, + SVGA3D_TRANSFORM_WORLD3 = 14, + SVGA3D_TRANSFORM_MAX } SVGA3dTransformType; typedef enum { - SVGA3D_LIGHTTYPE_INVALID = 0, - SVGA3D_LIGHTTYPE_MIN = 1, - SVGA3D_LIGHTTYPE_POINT = 1, - SVGA3D_LIGHTTYPE_SPOT1 = 2, /* 1-cone, in degrees */ - SVGA3D_LIGHTTYPE_SPOT2 = 3, /* 2-cone, in radians */ - SVGA3D_LIGHTTYPE_DIRECTIONAL = 4, - SVGA3D_LIGHTTYPE_MAX + SVGA3D_LIGHTTYPE_INVALID = 0, + SVGA3D_LIGHTTYPE_MIN = 1, + SVGA3D_LIGHTTYPE_POINT = 1, + SVGA3D_LIGHTTYPE_SPOT1 = 2, + SVGA3D_LIGHTTYPE_SPOT2 = 3, + SVGA3D_LIGHTTYPE_DIRECTIONAL = 4, + SVGA3D_LIGHTTYPE_MAX } SVGA3dLightType; typedef enum { - SVGA3D_CUBEFACE_POSX = 0, - SVGA3D_CUBEFACE_NEGX = 1, - SVGA3D_CUBEFACE_POSY = 2, - SVGA3D_CUBEFACE_NEGY = 3, - SVGA3D_CUBEFACE_POSZ = 4, - SVGA3D_CUBEFACE_NEGZ = 5, + SVGA3D_CUBEFACE_POSX = 0, + SVGA3D_CUBEFACE_NEGX = 1, + SVGA3D_CUBEFACE_POSY = 2, + SVGA3D_CUBEFACE_NEGY = 3, + SVGA3D_CUBEFACE_POSZ = 4, + SVGA3D_CUBEFACE_NEGZ = 5, } SVGA3dCubeFace; typedef enum { - SVGA3D_SHADERTYPE_INVALID = 0, - SVGA3D_SHADERTYPE_MIN = 1, - SVGA3D_SHADERTYPE_VS = 1, - SVGA3D_SHADERTYPE_PS = 2, - SVGA3D_SHADERTYPE_PREDX_MAX = 3, - SVGA3D_SHADERTYPE_GS = 3, - SVGA3D_SHADERTYPE_DX10_MAX = 4, - SVGA3D_SHADERTYPE_HS = 4, - SVGA3D_SHADERTYPE_DS = 5, - SVGA3D_SHADERTYPE_CS = 6, - SVGA3D_SHADERTYPE_MAX = 7 + SVGA3D_SHADERTYPE_INVALID = 0, + SVGA3D_SHADERTYPE_MIN = 1, + SVGA3D_SHADERTYPE_VS = 1, + SVGA3D_SHADERTYPE_PS = 2, + SVGA3D_SHADERTYPE_PREDX_MAX = 3, + SVGA3D_SHADERTYPE_GS = 3, + SVGA3D_SHADERTYPE_DX10_MAX = 4, + SVGA3D_SHADERTYPE_HS = 4, + SVGA3D_SHADERTYPE_DS = 5, + SVGA3D_SHADERTYPE_CS = 6, + SVGA3D_SHADERTYPE_MAX = 7 } SVGA3dShaderType; -#define SVGA3D_NUM_SHADERTYPE_PREDX \ - (SVGA3D_SHADERTYPE_PREDX_MAX - SVGA3D_SHADERTYPE_MIN) +#define SVGA3D_NUM_SHADERTYPE_PREDX \ + (SVGA3D_SHADERTYPE_PREDX_MAX - SVGA3D_SHADERTYPE_MIN) -#define SVGA3D_NUM_SHADERTYPE_DX10 \ - (SVGA3D_SHADERTYPE_DX10_MAX - SVGA3D_SHADERTYPE_MIN) +#define SVGA3D_NUM_SHADERTYPE_DX10 \ + (SVGA3D_SHADERTYPE_DX10_MAX - SVGA3D_SHADERTYPE_MIN) -#define SVGA3D_NUM_SHADERTYPE \ - (SVGA3D_SHADERTYPE_MAX - SVGA3D_SHADERTYPE_MIN) +#define SVGA3D_NUM_SHADERTYPE (SVGA3D_SHADERTYPE_MAX - SVGA3D_SHADERTYPE_MIN) typedef enum { - SVGA3D_CONST_TYPE_MIN = 0, - SVGA3D_CONST_TYPE_FLOAT = 0, - SVGA3D_CONST_TYPE_INT = 1, - SVGA3D_CONST_TYPE_BOOL = 2, - SVGA3D_CONST_TYPE_MAX = 3, + SVGA3D_CONST_TYPE_MIN = 0, + SVGA3D_CONST_TYPE_FLOAT = 0, + SVGA3D_CONST_TYPE_INT = 1, + SVGA3D_CONST_TYPE_BOOL = 2, + SVGA3D_CONST_TYPE_MAX = 3, } SVGA3dShaderConstType; -/* - * Register limits for shader consts. - */ -#define SVGA3D_CONSTREG_MAX 256 -#define SVGA3D_CONSTINTREG_MAX 16 -#define SVGA3D_CONSTBOOLREG_MAX 16 +#define SVGA3D_CONSTREG_MAX 256 +#define SVGA3D_CONSTINTREG_MAX 16 +#define SVGA3D_CONSTBOOLREG_MAX 16 typedef enum { - SVGA3D_STRETCH_BLT_POINT = 0, - SVGA3D_STRETCH_BLT_LINEAR = 1, - SVGA3D_STRETCH_BLT_MAX + SVGA3D_STRETCH_BLT_POINT = 0, + SVGA3D_STRETCH_BLT_LINEAR = 1, + SVGA3D_STRETCH_BLT_MAX } SVGA3dStretchBltMode; typedef enum { - SVGA3D_QUERYTYPE_INVALID = ((uint8)-1), - SVGA3D_QUERYTYPE_MIN = 0, - SVGA3D_QUERYTYPE_OCCLUSION = 0, - SVGA3D_QUERYTYPE_TIMESTAMP = 1, - SVGA3D_QUERYTYPE_TIMESTAMPDISJOINT = 2, - SVGA3D_QUERYTYPE_PIPELINESTATS = 3, - SVGA3D_QUERYTYPE_OCCLUSIONPREDICATE = 4, - SVGA3D_QUERYTYPE_STREAMOUTPUTSTATS = 5, - SVGA3D_QUERYTYPE_STREAMOVERFLOWPREDICATE = 6, - SVGA3D_QUERYTYPE_OCCLUSION64 = 7, - SVGA3D_QUERYTYPE_DX10_MAX = 8, - SVGA3D_QUERYTYPE_SOSTATS_STREAM0 = 8, - SVGA3D_QUERYTYPE_SOSTATS_STREAM1 = 9, - SVGA3D_QUERYTYPE_SOSTATS_STREAM2 = 10, - SVGA3D_QUERYTYPE_SOSTATS_STREAM3 = 11, - SVGA3D_QUERYTYPE_SOP_STREAM0 = 12, - SVGA3D_QUERYTYPE_SOP_STREAM1 = 13, - SVGA3D_QUERYTYPE_SOP_STREAM2 = 14, - SVGA3D_QUERYTYPE_SOP_STREAM3 = 15, - SVGA3D_QUERYTYPE_MAX + SVGA3D_QUERYTYPE_INVALID = ((uint8)-1), + SVGA3D_QUERYTYPE_MIN = 0, + SVGA3D_QUERYTYPE_OCCLUSION = 0, + SVGA3D_QUERYTYPE_TIMESTAMP = 1, + SVGA3D_QUERYTYPE_TIMESTAMPDISJOINT = 2, + SVGA3D_QUERYTYPE_PIPELINESTATS = 3, + SVGA3D_QUERYTYPE_OCCLUSIONPREDICATE = 4, + SVGA3D_QUERYTYPE_STREAMOUTPUTSTATS = 5, + SVGA3D_QUERYTYPE_STREAMOVERFLOWPREDICATE = 6, + SVGA3D_QUERYTYPE_OCCLUSION64 = 7, + SVGA3D_QUERYTYPE_DX10_MAX = 8, + SVGA3D_QUERYTYPE_SOSTATS_STREAM0 = 8, + SVGA3D_QUERYTYPE_SOSTATS_STREAM1 = 9, + SVGA3D_QUERYTYPE_SOSTATS_STREAM2 = 10, + SVGA3D_QUERYTYPE_SOSTATS_STREAM3 = 11, + SVGA3D_QUERYTYPE_SOP_STREAM0 = 12, + SVGA3D_QUERYTYPE_SOP_STREAM1 = 13, + SVGA3D_QUERYTYPE_SOP_STREAM2 = 14, + SVGA3D_QUERYTYPE_SOP_STREAM3 = 15, + SVGA3D_QUERYTYPE_MAX } SVGA3dQueryType; typedef uint8 SVGA3dQueryTypeUint8; -#define SVGA3D_NUM_QUERYTYPE (SVGA3D_QUERYTYPE_MAX - SVGA3D_QUERYTYPE_MIN) +#define SVGA3D_NUM_QUERYTYPE (SVGA3D_QUERYTYPE_MAX - SVGA3D_QUERYTYPE_MIN) -/* - * This is the maximum number of queries per context that can be active - * simultaneously between a beginQuery and endQuery. - */ #define SVGA3D_MAX_QUERY 64 -/* - * Query result buffer formats - */ -typedef -#include "vmware_pack_begin.h" -struct { - uint32 samplesRendered; -} -#include "vmware_pack_end.h" -SVGADXOcclusionQueryResult; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 passed; -} -#include "vmware_pack_end.h" -SVGADXEventQueryResult; - -typedef -#include "vmware_pack_begin.h" -struct { - uint64 timestamp; -} -#include "vmware_pack_end.h" -SVGADXTimestampQueryResult; - -typedef -#include "vmware_pack_begin.h" -struct { - uint64 realFrequency; - uint32 disjoint; -} -#include "vmware_pack_end.h" -SVGADXTimestampDisjointQueryResult; - -typedef -#include "vmware_pack_begin.h" -struct { - uint64 inputAssemblyVertices; - uint64 inputAssemblyPrimitives; - uint64 vertexShaderInvocations; - uint64 geometryShaderInvocations; - uint64 geometryShaderPrimitives; - uint64 clipperInvocations; - uint64 clipperPrimitives; - uint64 pixelShaderInvocations; - uint64 hullShaderInvocations; - uint64 domainShaderInvocations; - uint64 computeShaderInvocations; -} -#include "vmware_pack_end.h" -SVGADXPipelineStatisticsQueryResult; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 anySamplesRendered; -} -#include "vmware_pack_end.h" -SVGADXOcclusionPredicateQueryResult; - -typedef -#include "vmware_pack_begin.h" -struct { - uint64 numPrimitivesWritten; - uint64 numPrimitivesRequired; -} -#include "vmware_pack_end.h" -SVGADXStreamOutStatisticsQueryResult; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 overflowed; -} -#include "vmware_pack_end.h" -SVGADXStreamOutPredicateQueryResult; - -typedef -#include "vmware_pack_begin.h" -struct { - uint64 samplesRendered; -} -#include "vmware_pack_end.h" -SVGADXOcclusion64QueryResult; - -/* - * SVGADXQueryResultUnion is not intended for use in the protocol, but is - * very helpful when working with queries generically. - */ -typedef -#include "vmware_pack_begin.h" -union SVGADXQueryResultUnion { - SVGADXOcclusionQueryResult occ; - SVGADXEventQueryResult event; - SVGADXTimestampQueryResult ts; - SVGADXTimestampDisjointQueryResult tsDisjoint; - SVGADXPipelineStatisticsQueryResult pipelineStats; - SVGADXOcclusionPredicateQueryResult occPred; - SVGADXStreamOutStatisticsQueryResult soStats; - SVGADXStreamOutPredicateQueryResult soPred; - SVGADXOcclusion64QueryResult occ64; -} -#include "vmware_pack_end.h" -SVGADXQueryResultUnion; +#pragma pack(push, 1) +typedef struct { + uint32 samplesRendered; +} SVGADXOcclusionQueryResult; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 passed; +} SVGADXEventQueryResult; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint64 timestamp; +} SVGADXTimestampQueryResult; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint64 realFrequency; + uint32 disjoint; +} SVGADXTimestampDisjointQueryResult; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint64 inputAssemblyVertices; + uint64 inputAssemblyPrimitives; + uint64 vertexShaderInvocations; + uint64 geometryShaderInvocations; + uint64 geometryShaderPrimitives; + uint64 clipperInvocations; + uint64 clipperPrimitives; + uint64 pixelShaderInvocations; + uint64 hullShaderInvocations; + uint64 domainShaderInvocations; + uint64 computeShaderInvocations; +} SVGADXPipelineStatisticsQueryResult; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 anySamplesRendered; +} SVGADXOcclusionPredicateQueryResult; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint64 numPrimitivesWritten; + uint64 numPrimitivesRequired; +} SVGADXStreamOutStatisticsQueryResult; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 overflowed; +} SVGADXStreamOutPredicateQueryResult; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint64 samplesRendered; +} SVGADXOcclusion64QueryResult; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef union SVGADXQueryResultUnion { + SVGADXOcclusionQueryResult occ; + SVGADXEventQueryResult event; + SVGADXTimestampQueryResult ts; + SVGADXTimestampDisjointQueryResult tsDisjoint; + SVGADXPipelineStatisticsQueryResult pipelineStats; + SVGADXOcclusionPredicateQueryResult occPred; + SVGADXStreamOutStatisticsQueryResult soStats; + SVGADXStreamOutPredicateQueryResult soPred; + SVGADXOcclusion64QueryResult occ64; +} SVGADXQueryResultUnion; +#pragma pack(pop) typedef enum { - SVGA3D_QUERYSTATE_PENDING = 0, /* Query is not finished yet */ - SVGA3D_QUERYSTATE_SUCCEEDED = 1, /* Completed successfully */ - SVGA3D_QUERYSTATE_FAILED = 2, /* Completed unsuccessfully */ - SVGA3D_QUERYSTATE_NEW = 3, /* Never submitted (guest only) */ + SVGA3D_QUERYSTATE_PENDING = 0, + SVGA3D_QUERYSTATE_SUCCEEDED = 1, + SVGA3D_QUERYSTATE_FAILED = 2, + SVGA3D_QUERYSTATE_NEW = 3, } SVGA3dQueryState; typedef enum { - SVGA3D_WRITE_HOST_VRAM = 1, - SVGA3D_READ_HOST_VRAM = 2, + SVGA3D_WRITE_HOST_VRAM = 1, + SVGA3D_READ_HOST_VRAM = 2, } SVGA3dTransferType; -#define SVGA3D_LOGICOP_INVALID 0 -#define SVGA3D_LOGICOP_MIN 1 -#define SVGA3D_LOGICOP_COPY 1 -#define SVGA3D_LOGICOP_NOT 2 -#define SVGA3D_LOGICOP_AND 3 -#define SVGA3D_LOGICOP_OR 4 -#define SVGA3D_LOGICOP_XOR 5 -#define SVGA3D_LOGICOP_NXOR 6 -#define SVGA3D_LOGICOP_ROP3 7 -#define SVGA3D_LOGICOP_MAX 8 +#define SVGA3D_LOGICOP_INVALID 0 +#define SVGA3D_LOGICOP_COPY 1 + +#define SVGA3D_LOGICOP_MIN 1 +#define SVGA3D_LOGICOP_NOT 2 +#define SVGA3D_LOGICOP_AND 3 +#define SVGA3D_LOGICOP_OR 4 +#define SVGA3D_LOGICOP_XOR 5 +#define SVGA3D_LOGICOP_NXOR 6 +#define SVGA3D_LOGICOP_ROP3 7 + +#define SVGA3D_LOGICOP_MAX 8 typedef uint16 SVGA3dLogicOp; -#define SVGA3D_LOGICOP_ROP3_INVALID ((uint16) -1) -#define SVGA3D_LOGICOP_ROP3_MIN 0 -#define SVGA3D_LOGICOP_ROP3_MAX 256 +#define SVGA3D_LOGICOP_ROP3_INVALID ((uint16)-1) +#define SVGA3D_LOGICOP_ROP3_MIN 0 +#define SVGA3D_LOGICOP_ROP3_MAX 256 typedef uint16 SVGA3dLogicOpRop3; -typedef -#include "vmware_pack_begin.h" -struct { - union { - struct { - uint16 function; // SVGA3dFogFunction - uint8 type; // SVGA3dFogType - uint8 base; // SVGA3dFogBase - }; - uint32 uintValue; - }; -} -#include "vmware_pack_end.h" -SVGA3dFogMode; - -/* - * Uniquely identify one image (a 1D/2D/3D array) from a surface. This - * is a surface ID as well as face/mipmap indices. - */ -typedef -#include "vmware_pack_begin.h" -struct SVGA3dSurfaceImageId { - uint32 sid; - uint32 face; - uint32 mipmap; -} -#include "vmware_pack_end.h" -SVGA3dSurfaceImageId; - -typedef -#include "vmware_pack_begin.h" -struct SVGA3dSubSurfaceId { - uint32 sid; - uint32 subResourceId; -} -#include "vmware_pack_end.h" -SVGA3dSubSurfaceId; - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 width; - uint32 height; - uint32 depth; -} -#include "vmware_pack_end.h" -SVGA3dSize; +#pragma pack(push, 1) +typedef struct { + union { + struct { + uint16 function; + uint8 type; + uint8 base; + }; + uint32 uintValue; + }; +} SVGA3dFogMode; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dSurfaceImageId { + uint32 sid; + uint32 face; + uint32 mipmap; +} SVGA3dSurfaceImageId; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGA3dSubSurfaceId { + uint32 sid; + uint32 subResourceId; +} SVGA3dSubSurfaceId; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 width; + uint32 height; + uint32 depth; +} SVGA3dSize; +#pragma pack(pop) -/* - * Guest-backed objects definitions. - */ typedef enum { - SVGA_OTABLE_MOB = 0, - SVGA_OTABLE_MIN = 0, - SVGA_OTABLE_SURFACE = 1, - SVGA_OTABLE_CONTEXT = 2, - SVGA_OTABLE_SHADER = 3, - SVGA_OTABLE_SCREENTARGET = 4, - - SVGA_OTABLE_DX9_MAX = 5, - - SVGA_OTABLE_DXCONTEXT = 5, - SVGA_OTABLE_DX_MAX = 6, - - SVGA_OTABLE_RESERVED1 = 6, - SVGA_OTABLE_RESERVED2 = 7, - - /* - * Additions to this table need to be tied to HW-version features and - * checkpointed accordingly. - */ - SVGA_OTABLE_DEVEL_MAX = 8, - SVGA_OTABLE_MAX = 8 + SVGA_OTABLE_MOB = 0, + SVGA_OTABLE_MIN = 0, + SVGA_OTABLE_SURFACE = 1, + SVGA_OTABLE_CONTEXT = 2, + SVGA_OTABLE_SHADER = 3, + SVGA_OTABLE_SCREENTARGET = 4, + + SVGA_OTABLE_DX9_MAX = 5, + + SVGA_OTABLE_DXCONTEXT = 5, + SVGA_OTABLE_DX_MAX = 6, + + SVGA_OTABLE_DEVEL_MAX = 6, + SVGA_OTABLE_MAX = 6, + + SVGA_OTABLE_RESERVED1 = 6, + SVGA_OTABLE_RESERVED2 = 7, + SVGA_OTABLE_BUG_1952836_MAX = 8, } SVGAOTableType; typedef enum { - SVGA_COTABLE_MIN = 0, - SVGA_COTABLE_RTVIEW = 0, - SVGA_COTABLE_DSVIEW = 1, - SVGA_COTABLE_SRVIEW = 2, - SVGA_COTABLE_ELEMENTLAYOUT = 3, - SVGA_COTABLE_BLENDSTATE = 4, - SVGA_COTABLE_DEPTHSTENCIL = 5, - SVGA_COTABLE_RASTERIZERSTATE = 6, - SVGA_COTABLE_SAMPLER = 7, - SVGA_COTABLE_STREAMOUTPUT = 8, - SVGA_COTABLE_DXQUERY = 9, - SVGA_COTABLE_DXSHADER = 10, - SVGA_COTABLE_DX10_MAX = 11, - SVGA_COTABLE_UAVIEW = 11, - SVGA_COTABLE_MAX = 12, + SVGA_COTABLE_MIN = 0, + SVGA_COTABLE_RTVIEW = 0, + SVGA_COTABLE_DSVIEW = 1, + SVGA_COTABLE_SRVIEW = 2, + SVGA_COTABLE_ELEMENTLAYOUT = 3, + SVGA_COTABLE_BLENDSTATE = 4, + SVGA_COTABLE_DEPTHSTENCIL = 5, + SVGA_COTABLE_RASTERIZERSTATE = 6, + SVGA_COTABLE_SAMPLER = 7, + SVGA_COTABLE_STREAMOUTPUT = 8, + SVGA_COTABLE_DXQUERY = 9, + SVGA_COTABLE_DXSHADER = 10, + SVGA_COTABLE_DX10_MAX = 11, + SVGA_COTABLE_UAVIEW = 11, + SVGA_COTABLE_MAX = 12, } SVGACOTableType; -/* - * The largest size (number of entries) allowed in a COTable. - */ #define SVGA_COTABLE_MAX_IDS (MAX_UINT16 - 2) typedef enum SVGAMobFormat { - SVGA3D_MOBFMT_INVALID = SVGA3D_INVALID_ID, - SVGA3D_MOBFMT_PTDEPTH_0 = 0, - SVGA3D_MOBFMT_MIN = 0, - SVGA3D_MOBFMT_PTDEPTH_1 = 1, - SVGA3D_MOBFMT_PTDEPTH_2 = 2, - SVGA3D_MOBFMT_RANGE = 3, - SVGA3D_MOBFMT_PTDEPTH64_0 = 4, - SVGA3D_MOBFMT_PTDEPTH64_1 = 5, - SVGA3D_MOBFMT_PTDEPTH64_2 = 6, - SVGA3D_MOBFMT_PREDX_MAX = 7, - SVGA3D_MOBFMT_EMPTY = 7, - SVGA3D_MOBFMT_MAX, - - /* - * This isn't actually used by the guest, but is a mob-format used - * internally by the SVGA device (and is therefore not binary compatible). - */ - SVGA3D_MOBFMT_HB, + SVGA3D_MOBFMT_INVALID = SVGA3D_INVALID_ID, + SVGA3D_MOBFMT_PT_0 = 0, + SVGA3D_MOBFMT_MIN = 0, + SVGA3D_MOBFMT_PT_1 = 1, + SVGA3D_MOBFMT_PT_2 = 2, + SVGA3D_MOBFMT_RANGE = 3, + SVGA3D_MOBFMT_PT64_0 = 4, + SVGA3D_MOBFMT_PT64_1 = 5, + SVGA3D_MOBFMT_PT64_2 = 6, + SVGA3D_MOBFMT_PREDX_MAX = 7, + SVGA3D_MOBFMT_EMPTY = 7, + + SVGA3D_MOBFMT_MAX, + + SVGA3D_MOBFMT_HB, } SVGAMobFormat; #define SVGA3D_MOB_EMPTY_BASE 1 -/* - * Multisample pattern types. - */ - typedef enum SVGA3dMSPattern { - SVGA3D_MS_PATTERN_NONE = 0, - SVGA3D_MS_PATTERN_MIN = 0, - SVGA3D_MS_PATTERN_STANDARD = 1, - SVGA3D_MS_PATTERN_CENTER = 2, - SVGA3D_MS_PATTERN_MAX = 3, + SVGA3D_MS_PATTERN_NONE = 0, + SVGA3D_MS_PATTERN_MIN = 0, + SVGA3D_MS_PATTERN_STANDARD = 1, + SVGA3D_MS_PATTERN_CENTER = 2, + SVGA3D_MS_PATTERN_MAX = 3, } SVGA3dMSPattern; -/* - * Precision settings for each sample. - */ - typedef enum SVGA3dMSQualityLevel { - SVGA3D_MS_QUALITY_NONE = 0, - SVGA3D_MS_QUALITY_MIN = 0, - SVGA3D_MS_QUALITY_FULL = 1, - SVGA3D_MS_QUALITY_MAX = 2, + SVGA3D_MS_QUALITY_NONE = 0, + SVGA3D_MS_QUALITY_MIN = 0, + SVGA3D_MS_QUALITY_FULL = 1, + SVGA3D_MS_QUALITY_RESOLVED = 2, + SVGA3D_MS_QUALITY_MAX = 3, } SVGA3dMSQualityLevel; -/* - * Screen Target Update Flags - */ - typedef enum SVGA3dFrameUpdateType { - SVGA3D_FRAME_END = 0, - SVGA3D_FRAME_PARTIAL = 1, - SVGA3D_FRAME_UNKNOWN = 2, - SVGA3D_FRAME_MAX = 3, + SVGA3D_FRAME_END = 0, + SVGA3D_FRAME_MIN = 0, + SVGA3D_FRAME_PARTIAL = 1, + SVGA3D_FRAME_UNKNOWN = 2, + SVGA3D_FRAME_MAX = 3, } SVGA3dFrameUpdateType; -#endif /* _SVGA3D_TYPES_H_ */ +#endif diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h b/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h index acb41e28e46f..bf242c21f352 100644 --- a/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h +++ b/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h @@ -1,6 +1,6 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT */ /********************************************************** - * Copyright 2007-2015 VMware, Inc. + * Copyright 2007,2020 VMware, Inc. + * SPDX-License-Identifier: GPL-2.0 OR MIT * * Permission is hereby granted, free of charge, to any person * obtaining a copy of this software and associated documentation @@ -30,61 +30,27 @@ * Definitions for our own (vendor-specific) SVGA Escape commands. */ -#ifndef _SVGA_ESCAPE_H_ -#define _SVGA_ESCAPE_H_ -/* - * Namespace IDs for the escape command - */ +#ifndef _SVGA_ESCAPE_H_ +#define _SVGA_ESCAPE_H_ #define SVGA_ESCAPE_NSID_VMWARE 0x00000000 -#define SVGA_ESCAPE_NSID_DEVEL 0xFFFFFFFF - +#define SVGA_ESCAPE_NSID_DEVEL 0xFFFFFFFF -/* - * Within SVGA_ESCAPE_NSID_VMWARE, we multiplex commands according to - * the first DWORD of escape data (after the nsID and size). As a - * guideline we're using the high word and low word as a major and - * minor command number, respectively. - * - * Major command number allocation: - * - * 0000: Reserved - * 0001: SVGA_ESCAPE_VMWARE_LOG (svga_binary_logger.h) - * 0002: SVGA_ESCAPE_VMWARE_VIDEO (svga_overlay.h) - * 0003: SVGA_ESCAPE_VMWARE_HINT (svga_escape.h) - */ - -#define SVGA_ESCAPE_VMWARE_MAJOR_MASK 0xFFFF0000 - - -/* - * SVGA Hint commands. - * - * These escapes let the SVGA driver provide optional information to - * he host about the state of the guest or guest applications. The - * host can use these hints to make user interface or performance - * decisions. - * - * Notes: - * - * - SVGA_ESCAPE_VMWARE_HINT_FULLSCREEN is deprecated for guests - * that use the SVGA Screen Object extension. Instead of sending - * this escape, use the SVGA_SCREEN_FULLSCREEN_HINT flag on your - * Screen Object. - */ +#define SVGA_ESCAPE_VMWARE_MAJOR_MASK 0xFFFF0000 -#define SVGA_ESCAPE_VMWARE_HINT 0x00030000 -#define SVGA_ESCAPE_VMWARE_HINT_FULLSCREEN 0x00030001 /* Deprecated */ +#define SVGA_ESCAPE_VMWARE_HINT 0x00030000 +#define SVGA_ESCAPE_VMWARE_HINT_FULLSCREEN 0x00030001 -typedef -struct { - uint32 command; - uint32 fullscreen; - struct { - int32 x, y; - } monitorPosition; +#pragma pack(push, 1) +typedef struct { + uint32 command; + uint32 fullscreen; + struct { + int32 x, y; + } monitorPosition; } SVGAEscapeHintFullscreen; +#pragma pack(pop) -#endif /* _SVGA_ESCAPE_H_ */ +#endif diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h b/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h index e5385146e7fc..aec17c3c6c29 100644 --- a/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h +++ b/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h @@ -1,6 +1,6 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT */ /********************************************************** - * Copyright 2007-2015 VMware, Inc. + * Copyright 2007-2021 VMware, Inc. + * SPDX-License-Identifier: GPL-2.0 OR MIT * * Permission is hereby granted, free of charge, to any person * obtaining a copy of this software and associated documentation @@ -30,171 +30,88 @@ * Definitions for video-overlay support. */ + + #ifndef _SVGA_OVERLAY_H_ #define _SVGA_OVERLAY_H_ #include "svga_reg.h" -/* - * Video formats we support - */ +#if defined __cplusplus +extern "C" { +#endif -#define VMWARE_FOURCC_YV12 0x32315659 /* 'Y' 'V' '1' '2' */ -#define VMWARE_FOURCC_YUY2 0x32595559 /* 'Y' 'U' 'Y' '2' */ -#define VMWARE_FOURCC_UYVY 0x59565955 /* 'U' 'Y' 'V' 'Y' */ +#define VMWARE_FOURCC_YV12 0x32315659 +#define VMWARE_FOURCC_YUY2 0x32595559 +#define VMWARE_FOURCC_UYVY 0x59565955 typedef enum { - SVGA_OVERLAY_FORMAT_INVALID = 0, - SVGA_OVERLAY_FORMAT_YV12 = VMWARE_FOURCC_YV12, - SVGA_OVERLAY_FORMAT_YUY2 = VMWARE_FOURCC_YUY2, - SVGA_OVERLAY_FORMAT_UYVY = VMWARE_FOURCC_UYVY, + SVGA_OVERLAY_FORMAT_INVALID = 0, + SVGA_OVERLAY_FORMAT_YV12 = VMWARE_FOURCC_YV12, + SVGA_OVERLAY_FORMAT_YUY2 = VMWARE_FOURCC_YUY2, + SVGA_OVERLAY_FORMAT_UYVY = VMWARE_FOURCC_UYVY, } SVGAOverlayFormat; -#define SVGA_VIDEO_COLORKEY_MASK 0x00ffffff +#define SVGA_VIDEO_COLORKEY_MASK 0x00ffffff -#define SVGA_ESCAPE_VMWARE_VIDEO 0x00020000 +#define SVGA_ESCAPE_VMWARE_VIDEO 0x00020000 -#define SVGA_ESCAPE_VMWARE_VIDEO_SET_REGS 0x00020001 - /* FIFO escape layout: - * Type, Stream Id, (Register Id, Value) pairs */ +#define SVGA_ESCAPE_VMWARE_VIDEO_SET_REGS 0x00020001 -#define SVGA_ESCAPE_VMWARE_VIDEO_FLUSH 0x00020002 - /* FIFO escape layout: - * Type, Stream Id */ +#define SVGA_ESCAPE_VMWARE_VIDEO_FLUSH 0x00020002 -typedef -struct SVGAEscapeVideoSetRegs { - struct { - uint32 cmdType; - uint32 streamId; - } header; +typedef struct SVGAEscapeVideoSetRegs { + struct { + uint32 cmdType; + uint32 streamId; + } header; - /* May include zero or more items. */ - struct { - uint32 registerId; - uint32 value; - } items[1]; + struct { + uint32 registerId; + uint32 value; + } items[1]; } SVGAEscapeVideoSetRegs; -typedef -struct SVGAEscapeVideoFlush { - uint32 cmdType; - uint32 streamId; +typedef struct SVGAEscapeVideoFlush { + uint32 cmdType; + uint32 streamId; } SVGAEscapeVideoFlush; - -/* - * Struct definitions for the video overlay commands built on - * SVGAFifoCmdEscape. - */ -typedef -struct { - uint32 command; - uint32 overlay; +#pragma pack(push, 1) +typedef struct { + uint32 command; + uint32 overlay; } SVGAFifoEscapeCmdVideoBase; +#pragma pack(pop) -typedef -struct { - SVGAFifoEscapeCmdVideoBase videoCmd; +#pragma pack(push, 1) +typedef struct { + SVGAFifoEscapeCmdVideoBase videoCmd; } SVGAFifoEscapeCmdVideoFlush; - -typedef -struct { - SVGAFifoEscapeCmdVideoBase videoCmd; - struct { - uint32 regId; - uint32 value; - } items[1]; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGAFifoEscapeCmdVideoBase videoCmd; + struct { + uint32 regId; + uint32 value; + } items[1]; } SVGAFifoEscapeCmdVideoSetRegs; - -typedef -struct { - SVGAFifoEscapeCmdVideoBase videoCmd; - struct { - uint32 regId; - uint32 value; - } items[SVGA_VIDEO_NUM_REGS]; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGAFifoEscapeCmdVideoBase videoCmd; + struct { + uint32 regId; + uint32 value; + } items[SVGA_VIDEO_NUM_REGS]; } SVGAFifoEscapeCmdVideoSetAllRegs; +#pragma pack(pop) - -/* - *---------------------------------------------------------------------- - * - * VMwareVideoGetAttributes -- - * - * Computes the size, pitches and offsets for YUV frames. - * - * Results: - * TRUE on success; otherwise FALSE on failure. - * - * Side effects: - * Pitches and offsets for the given YUV frame are put in 'pitches' - * and 'offsets' respectively. They are both optional though. - * - *---------------------------------------------------------------------- - */ - -static inline bool -VMwareVideoGetAttributes(const SVGAOverlayFormat format, /* IN */ - uint32 *width, /* IN / OUT */ - uint32 *height, /* IN / OUT */ - uint32 *size, /* OUT */ - uint32 *pitches, /* OUT (optional) */ - uint32 *offsets) /* OUT (optional) */ -{ - int tmp; - - *width = (*width + 1) & ~1; - - if (offsets) { - offsets[0] = 0; - } - - switch (format) { - case VMWARE_FOURCC_YV12: - *height = (*height + 1) & ~1; - *size = (*width) * (*height); - - if (pitches) { - pitches[0] = *width; - } - - if (offsets) { - offsets[1] = *size; - } - - tmp = *width >> 1; - - if (pitches) { - pitches[1] = pitches[2] = tmp; - } - - tmp *= (*height >> 1); - *size += tmp; - - if (offsets) { - offsets[2] = *size; - } - - *size += tmp; - break; - - case VMWARE_FOURCC_YUY2: - case VMWARE_FOURCC_UYVY: - *size = *width * 2; - - if (pitches) { - pitches[0] = *size; - } - - *size *= *height; - break; - - default: - return false; - } - - return true; +#if defined __cplusplus } +#endif -#endif /* _SVGA_OVERLAY_H_ */ +#endif diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h b/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h index 193a57f6aae5..b3602557de2e 100644 --- a/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h +++ b/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h @@ -1,6 +1,6 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT */ /********************************************************** * Copyright 1998-2021 VMware, Inc. + * SPDX-License-Identifier: GPL-2.0 OR MIT * * Permission is hereby granted, free of charge, to any person * obtaining a copy of this software and associated documentation @@ -30,2277 +30,870 @@ * Virtual hardware definitions for the VMware SVGA II device. */ -#ifndef _SVGA_REG_H_ -#define _SVGA_REG_H_ -#include <linux/pci_ids.h> -#define INCLUDE_ALLOW_MODULE -#define INCLUDE_ALLOW_USERLEVEL -#define INCLUDE_ALLOW_VMCORE -#include "includeCheck.h" +#ifndef _SVGA_REG_H_ +#define _SVGA_REG_H_ -#include "svga_types.h" +#include "vm_basic_types.h" -/* - * SVGA_REG_ENABLE bit definitions. - */ typedef enum { - SVGA_REG_ENABLE_DISABLE = 0, - SVGA_REG_ENABLE_ENABLE = (1 << 0), - SVGA_REG_ENABLE_HIDE = (1 << 1), + SVGA_REG_ENABLE_DISABLE = 0, + SVGA_REG_ENABLE_ENABLE = (1 << 0), + SVGA_REG_ENABLE_HIDE = (1 << 1), } SvgaRegEnable; typedef uint32 SVGAMobId; -/* - * Arbitrary and meaningless limits. Please ignore these when writing - * new drivers. - */ -#define SVGA_MAX_WIDTH 2560 -#define SVGA_MAX_HEIGHT 1600 - +#define SVGA_MAX_WIDTH 2560 +#define SVGA_MAX_HEIGHT 1600 -#define SVGA_MAX_BITS_PER_PIXEL 32 -#define SVGA_MAX_DEPTH 24 -#define SVGA_MAX_DISPLAYS 10 -#define SVGA_MAX_SCREEN_SIZE 8192 +#define SVGA_MAX_BITS_PER_PIXEL 32 +#define SVGA_MAX_DEPTH 24 +#define SVGA_MAX_DISPLAYS 10 +#define SVGA_MAX_SCREEN_SIZE 8192 #define SVGA_SCREEN_ROOT_LIMIT (SVGA_MAX_SCREEN_SIZE * SVGA_MAX_DISPLAYS) +#define SVGA_CURSOR_ON_HIDE 0x0 +#define SVGA_CURSOR_ON_SHOW 0x1 -/* - * Legal values for the SVGA_REG_CURSOR_ON register in old-fashioned - * cursor bypass mode. - */ -#define SVGA_CURSOR_ON_HIDE 0x0 -#define SVGA_CURSOR_ON_SHOW 0x1 - -/* - * Remove the cursor from the framebuffer - * because we need to see what's under it - */ -#define SVGA_CURSOR_ON_REMOVE_FROM_FB 0x2 +#define SVGA_CURSOR_ON_REMOVE_FROM_FB 0x2 -/* Put the cursor back in the framebuffer so the user can see it */ -#define SVGA_CURSOR_ON_RESTORE_TO_FB 0x3 +#define SVGA_CURSOR_ON_RESTORE_TO_FB 0x3 -/* - * The maximum framebuffer size that can traced for guests unless the - * SVGA_CAP_GBOBJECTS is set in SVGA_REG_CAPABILITIES. In that case - * the full framebuffer can be traced independent of this limit. - */ -#define SVGA_FB_MAX_TRACEABLE_SIZE 0x1000000 +#define SVGA_FB_MAX_TRACEABLE_SIZE 0x1000000 -#define SVGA_MAX_PSEUDOCOLOR_DEPTH 8 -#define SVGA_MAX_PSEUDOCOLORS (1 << SVGA_MAX_PSEUDOCOLOR_DEPTH) -#define SVGA_NUM_PALETTE_REGS (3 * SVGA_MAX_PSEUDOCOLORS) +#define SVGA_MAX_PSEUDOCOLOR_DEPTH 8 +#define SVGA_MAX_PSEUDOCOLORS (1 << SVGA_MAX_PSEUDOCOLOR_DEPTH) +#define SVGA_NUM_PALETTE_REGS (3 * SVGA_MAX_PSEUDOCOLORS) -#define SVGA_MAGIC 0x900000UL -#define SVGA_MAKE_ID(ver) (SVGA_MAGIC << 8 | (ver)) +#define SVGA_MAGIC 0x900000UL +#define SVGA_MAKE_ID(ver) (SVGA_MAGIC << 8 | (ver)) -/* Version 3 has the control bar instead of the FIFO */ -#define SVGA_VERSION_3 3 -#define SVGA_ID_3 SVGA_MAKE_ID(SVGA_VERSION_3) +#define SVGA_VERSION_3 3 +#define SVGA_ID_3 SVGA_MAKE_ID(SVGA_VERSION_3) -/* Version 2 let the address of the frame buffer be unsigned on Win32 */ -#define SVGA_VERSION_2 2 -#define SVGA_ID_2 SVGA_MAKE_ID(SVGA_VERSION_2) +#define SVGA_VERSION_2 2 +#define SVGA_ID_2 SVGA_MAKE_ID(SVGA_VERSION_2) -/* Version 1 has new registers starting with SVGA_REG_CAPABILITIES so - PALETTE_BASE has moved */ -#define SVGA_VERSION_1 1 -#define SVGA_ID_1 SVGA_MAKE_ID(SVGA_VERSION_1) +#define SVGA_VERSION_1 1 +#define SVGA_ID_1 SVGA_MAKE_ID(SVGA_VERSION_1) -/* Version 0 is the initial version */ -#define SVGA_VERSION_0 0 -#define SVGA_ID_0 SVGA_MAKE_ID(SVGA_VERSION_0) +#define SVGA_VERSION_0 0 +#define SVGA_ID_0 SVGA_MAKE_ID(SVGA_VERSION_0) -/* - * "Invalid" value for all SVGA IDs. - * (Version ID, screen object ID, surface ID...) - */ -#define SVGA_ID_INVALID 0xFFFFFFFF +#define SVGA_ID_INVALID 0xFFFFFFFF -/* Port offsets, relative to BAR0 */ -#define SVGA_INDEX_PORT 0x0 -#define SVGA_VALUE_PORT 0x1 -#define SVGA_BIOS_PORT 0x2 -#define SVGA_IRQSTATUS_PORT 0x8 +#define SVGA_INDEX_PORT 0x0 +#define SVGA_VALUE_PORT 0x1 +#define SVGA_BIOS_PORT 0x2 +#define SVGA_IRQSTATUS_PORT 0x8 -/* - * Interrupt source flags for IRQSTATUS_PORT and IRQMASK. - * - * Interrupts are only supported when the - * SVGA_CAP_IRQMASK capability is present. - */ -#define SVGA_IRQFLAG_ANY_FENCE (1 << 0) /* Any fence was passed */ -#define SVGA_IRQFLAG_FIFO_PROGRESS (1 << 1) /* Made forward progress in the FIFO */ -#define SVGA_IRQFLAG_FENCE_GOAL (1 << 2) /* SVGA_FIFO_FENCE_GOAL reached */ -#define SVGA_IRQFLAG_COMMAND_BUFFER (1 << 3) /* Command buffer completed */ -#define SVGA_IRQFLAG_ERROR (1 << 4) /* Error while processing commands */ -#define SVGA_IRQFLAG_MAX (1 << 5) +#define SVGA_IRQFLAG_ANY_FENCE (1 << 0) +#define SVGA_IRQFLAG_FIFO_PROGRESS (1 << 1) +#define SVGA_IRQFLAG_FENCE_GOAL (1 << 2) +#define SVGA_IRQFLAG_COMMAND_BUFFER (1 << 3) +#define SVGA_IRQFLAG_ERROR (1 << 4) +#define SVGA_IRQFLAG_REG_FENCE_GOAL (1 << 5) +#define SVGA_IRQFLAG_MAX (1 << 6) -/* - * The byte-size is the size of the actual cursor data, - * possibly after expanding it to the current bit depth. - * - * 40K is sufficient memory for two 32-bit planes for a 64 x 64 cursor. - * - * The dimension limit is a bound on the maximum width or height. - */ -#define SVGA_MAX_CURSOR_CMD_BYTES (40 * 1024) +#define SVGA_MAX_CURSOR_CMD_BYTES (40 * 1024) #define SVGA_MAX_CURSOR_CMD_DIMENSION 1024 -/* - * Registers - */ - enum { - SVGA_REG_ID = 0, - SVGA_REG_ENABLE = 1, - SVGA_REG_WIDTH = 2, - SVGA_REG_HEIGHT = 3, - SVGA_REG_MAX_WIDTH = 4, - SVGA_REG_MAX_HEIGHT = 5, - SVGA_REG_DEPTH = 6, - SVGA_REG_BITS_PER_PIXEL = 7, /* Current bpp in the guest */ - SVGA_REG_PSEUDOCOLOR = 8, - SVGA_REG_RED_MASK = 9, - SVGA_REG_GREEN_MASK = 10, - SVGA_REG_BLUE_MASK = 11, - SVGA_REG_BYTES_PER_LINE = 12, - SVGA_REG_FB_START = 13, /* (Deprecated) */ - SVGA_REG_FB_OFFSET = 14, - SVGA_REG_VRAM_SIZE = 15, - SVGA_REG_FB_SIZE = 16, - - /* ID 0 implementation only had the above registers, then the palette */ - SVGA_REG_ID_0_TOP = 17, - - SVGA_REG_CAPABILITIES = 17, - SVGA_REG_MEM_START = 18, /* (Deprecated) */ - SVGA_REG_MEM_SIZE = 19, - SVGA_REG_CONFIG_DONE = 20, /* Set when memory area configured */ - SVGA_REG_SYNC = 21, /* See "FIFO Synchronization Registers" */ - SVGA_REG_BUSY = 22, /* See "FIFO Synchronization Registers" */ - SVGA_REG_GUEST_ID = 23, /* (Deprecated) */ - SVGA_REG_DEAD = 24, /* Drivers should never write this. */ - SVGA_REG_CURSOR_X = 25, /* (Deprecated) */ - SVGA_REG_CURSOR_Y = 26, /* (Deprecated) */ - SVGA_REG_CURSOR_ON = 27, /* (Deprecated) */ - SVGA_REG_HOST_BITS_PER_PIXEL = 28, /* (Deprecated) */ - SVGA_REG_SCRATCH_SIZE = 29, /* Number of scratch registers */ - SVGA_REG_MEM_REGS = 30, /* Number of FIFO registers */ - SVGA_REG_NUM_DISPLAYS = 31, /* (Deprecated) */ - SVGA_REG_PITCHLOCK = 32, /* Fixed pitch for all modes */ - SVGA_REG_IRQMASK = 33, /* Interrupt mask */ - - /* Legacy multi-monitor support */ - SVGA_REG_NUM_GUEST_DISPLAYS = 34,/* Number of guest displays in X/Y direction */ - SVGA_REG_DISPLAY_ID = 35, /* Display ID for the following display attributes */ - SVGA_REG_DISPLAY_IS_PRIMARY = 36,/* Whether this is a primary display */ - SVGA_REG_DISPLAY_POSITION_X = 37,/* The display position x */ - SVGA_REG_DISPLAY_POSITION_Y = 38,/* The display position y */ - SVGA_REG_DISPLAY_WIDTH = 39, /* The display's width */ - SVGA_REG_DISPLAY_HEIGHT = 40, /* The display's height */ - - /* See "Guest memory regions" below. */ - SVGA_REG_GMR_ID = 41, - SVGA_REG_GMR_DESCRIPTOR = 42, - SVGA_REG_GMR_MAX_IDS = 43, - SVGA_REG_GMR_MAX_DESCRIPTOR_LENGTH = 44, - - SVGA_REG_TRACES = 45, /* Enable trace-based updates even when FIFO is on */ - SVGA_REG_GMRS_MAX_PAGES = 46, /* Maximum number of 4KB pages for all GMRs */ - SVGA_REG_MEMORY_SIZE = 47, /* Total dedicated device memory excluding FIFO */ - SVGA_REG_COMMAND_LOW = 48, /* Lower 32 bits and submits commands */ - SVGA_REG_COMMAND_HIGH = 49, /* Upper 32 bits of command buffer PA */ - - /* - * Max primary memory. - * See SVGA_CAP_NO_BB_RESTRICTION. - */ - SVGA_REG_MAX_PRIMARY_MEM = 50, - SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM = 50, - - /* - * Legacy version of SVGA_REG_GBOBJECT_MEM_SIZE_KB for drivers that - * don't know how to convert to a 64-bit byte value without overflowing. - * (See SVGA_REG_GBOBJECT_MEM_SIZE_KB). - */ - SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB = 51, - - SVGA_REG_DEV_CAP = 52, /* Write dev cap index, read value */ - SVGA_REG_CMD_PREPEND_LOW = 53, - SVGA_REG_CMD_PREPEND_HIGH = 54, - SVGA_REG_SCREENTARGET_MAX_WIDTH = 55, - SVGA_REG_SCREENTARGET_MAX_HEIGHT = 56, - SVGA_REG_MOB_MAX_SIZE = 57, - SVGA_REG_BLANK_SCREEN_TARGETS = 58, - SVGA_REG_CAP2 = 59, - SVGA_REG_DEVEL_CAP = 60, - - /* - * Allow the guest to hint to the device which driver is running. - * - * This should not generally change device behavior, but might be - * convenient to work-around specific bugs in guest drivers. - * - * Drivers should first write their id value into SVGA_REG_GUEST_DRIVER_ID, - * and then fill out all of the version registers that they have defined. - * - * After the driver has written all of the registers, they should - * then write the value SVGA_REG_GUEST_DRIVER_ID_SUBMIT to the - * SVGA_REG_GUEST_DRIVER_ID register, to signal that they have finished. - * - * The SVGA_REG_GUEST_DRIVER_ID values are defined below by the - * SVGARegGuestDriverId enum. - * - * The SVGA_REG_GUEST_DRIVER_VERSION fields are driver-specific, - * but ideally should encode a monotonically increasing number that allows - * the device to perform inequality checks against ranges of driver versions. - */ - SVGA_REG_GUEST_DRIVER_ID = 61, - SVGA_REG_GUEST_DRIVER_VERSION1 = 62, - SVGA_REG_GUEST_DRIVER_VERSION2 = 63, - SVGA_REG_GUEST_DRIVER_VERSION3 = 64, - SVGA_REG_CURSOR_MOBID = 65, - SVGA_REG_CURSOR_MAX_BYTE_SIZE = 66, - SVGA_REG_CURSOR_MAX_DIMENSION = 67, - - SVGA_REG_FIFO_CAPS = 68, - SVGA_REG_FENCE = 69, - - SVGA_REG_RESERVED1 = 70, - SVGA_REG_RESERVED2 = 71, - SVGA_REG_RESERVED3 = 72, - SVGA_REG_RESERVED4 = 73, - SVGA_REG_RESERVED5 = 74, - SVGA_REG_SCREENDMA = 75, - - /* - * The maximum amount of guest-backed objects that the device can have - * resident at a time. Guest-drivers should keep their working set size - * below this limit for best performance. - * - * Note that this value is in kilobytes, and not bytes, because the actual - * number of bytes might be larger than can fit in a 32-bit register. - * - * PLEASE USE A 64-BIT VALUE WHEN CONVERTING THIS INTO BYTES. - * (See SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB). - */ - SVGA_REG_GBOBJECT_MEM_SIZE_KB = 76, - - /* - + * These registers are for the addresses of the memory BARs for SVGA3 - */ - SVGA_REG_REGS_START_HIGH32 = 77, - SVGA_REG_REGS_START_LOW32 = 78, - SVGA_REG_FB_START_HIGH32 = 79, - SVGA_REG_FB_START_LOW32 = 80, - - /* - * A hint register that recommends which quality level the guest should - * currently use to define multisample surfaces. - * - * If the register is SVGA_REG_MSHINT_DISABLED, - * the guest is only allowed to use SVGA3D_MS_QUALITY_FULL. - * - * Otherwise, this is a live value that can change while the VM is - * powered on with the hint suggestion for which quality level the guest - * should be using. Guests are free to ignore the hint and use either - * RESOLVE or FULL quality. - */ - SVGA_REG_MSHINT = 81, - - SVGA_REG_IRQ_STATUS = 82, - SVGA_REG_DIRTY_TRACKING = 83, - - SVGA_REG_TOP = 84, /* Must be 1 more than the last register */ - - SVGA_PALETTE_BASE = 1024, /* Base of SVGA color map */ - /* Next 768 (== 256*3) registers exist for colormap */ - SVGA_SCRATCH_BASE = SVGA_PALETTE_BASE + SVGA_NUM_PALETTE_REGS - /* Base of scratch registers */ - /* Next reg[SVGA_REG_SCRATCH_SIZE] registers exist for scratch usage: - First 4 are reserved for VESA BIOS Extension; any remaining are for - the use of the current SVGA driver. */ -}; + SVGA_REG_ID = 0, + SVGA_REG_ENABLE = 1, + SVGA_REG_WIDTH = 2, + SVGA_REG_HEIGHT = 3, + SVGA_REG_MAX_WIDTH = 4, + SVGA_REG_MAX_HEIGHT = 5, + SVGA_REG_DEPTH = 6, + SVGA_REG_BITS_PER_PIXEL = 7, + SVGA_REG_PSEUDOCOLOR = 8, + SVGA_REG_RED_MASK = 9, + SVGA_REG_GREEN_MASK = 10, + SVGA_REG_BLUE_MASK = 11, + SVGA_REG_BYTES_PER_LINE = 12, + SVGA_REG_FB_START = 13, + SVGA_REG_FB_OFFSET = 14, + SVGA_REG_VRAM_SIZE = 15, + SVGA_REG_FB_SIZE = 16, + + SVGA_REG_ID_0_TOP = 17, + + SVGA_REG_CAPABILITIES = 17, + SVGA_REG_MEM_START = 18, + SVGA_REG_MEM_SIZE = 19, + SVGA_REG_CONFIG_DONE = 20, + SVGA_REG_SYNC = 21, + SVGA_REG_BUSY = 22, + SVGA_REG_GUEST_ID = 23, + SVGA_REG_DEAD = 24, + SVGA_REG_CURSOR_X = 25, + SVGA_REG_CURSOR_Y = 26, + SVGA_REG_CURSOR_ON = 27, + SVGA_REG_HOST_BITS_PER_PIXEL = 28, + SVGA_REG_SCRATCH_SIZE = 29, + SVGA_REG_MEM_REGS = 30, + SVGA_REG_NUM_DISPLAYS = 31, + SVGA_REG_PITCHLOCK = 32, + SVGA_REG_IRQMASK = 33, + + SVGA_REG_NUM_GUEST_DISPLAYS = 34, + SVGA_REG_DISPLAY_ID = 35, + SVGA_REG_DISPLAY_IS_PRIMARY = 36, + SVGA_REG_DISPLAY_POSITION_X = 37, + SVGA_REG_DISPLAY_POSITION_Y = 38, + SVGA_REG_DISPLAY_WIDTH = 39, + SVGA_REG_DISPLAY_HEIGHT = 40, + + SVGA_REG_GMR_ID = 41, + SVGA_REG_GMR_DESCRIPTOR = 42, + SVGA_REG_GMR_MAX_IDS = 43, + SVGA_REG_GMR_MAX_DESCRIPTOR_LENGTH = 44, + + SVGA_REG_TRACES = 45, + SVGA_REG_GMRS_MAX_PAGES = 46, + SVGA_REG_MEMORY_SIZE = 47, + SVGA_REG_COMMAND_LOW = 48, + SVGA_REG_COMMAND_HIGH = 49, + + SVGA_REG_MAX_PRIMARY_MEM = 50, + + SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB = 51, + + SVGA_REG_DEV_CAP = 52, + SVGA_REG_CMD_PREPEND_LOW = 53, + SVGA_REG_CMD_PREPEND_HIGH = 54, + SVGA_REG_SCREENTARGET_MAX_WIDTH = 55, + SVGA_REG_SCREENTARGET_MAX_HEIGHT = 56, + SVGA_REG_MOB_MAX_SIZE = 57, + SVGA_REG_BLANK_SCREEN_TARGETS = 58, + SVGA_REG_CAP2 = 59, + SVGA_REG_DEVEL_CAP = 60, + + SVGA_REG_GUEST_DRIVER_ID = 61, + SVGA_REG_GUEST_DRIVER_VERSION1 = 62, + SVGA_REG_GUEST_DRIVER_VERSION2 = 63, + SVGA_REG_GUEST_DRIVER_VERSION3 = 64, + + SVGA_REG_CURSOR_MOBID = 65, + SVGA_REG_CURSOR_MAX_BYTE_SIZE = 66, + SVGA_REG_CURSOR_MAX_DIMENSION = 67, + + SVGA_REG_FIFO_CAPS = 68, + SVGA_REG_FENCE = 69, + + SVGA_REG_CURSOR4_ON = 70, + SVGA_REG_CURSOR4_X = 71, + SVGA_REG_CURSOR4_Y = 72, + SVGA_REG_CURSOR4_SCREEN_ID = 73, + SVGA_REG_CURSOR4_SUBMIT = 74, + + SVGA_REG_SCREENDMA = 75, + + SVGA_REG_GBOBJECT_MEM_SIZE_KB = 76, + + SVGA_REG_REGS_START_HIGH32 = 77, + SVGA_REG_REGS_START_LOW32 = 78, + SVGA_REG_FB_START_HIGH32 = 79, + SVGA_REG_FB_START_LOW32 = 80, + + SVGA_REG_MSHINT = 81, + + SVGA_REG_IRQ_STATUS = 82, + + SVGA_REG_DIRTY_TRACKING = 83, + SVGA_REG_FENCE_GOAL = 84, + + SVGA_REG_TOP = 85, + + SVGA_PALETTE_BASE = 1024, + + SVGA_SCRATCH_BASE = SVGA_PALETTE_BASE + SVGA_NUM_PALETTE_REGS +}; -/* - * Values for SVGA_REG_GUEST_DRIVER_ID. - */ typedef enum SVGARegGuestDriverId { - SVGA_REG_GUEST_DRIVER_ID_UNKNOWN = 0, - SVGA_REG_GUEST_DRIVER_ID_WDDM = 1, - SVGA_REG_GUEST_DRIVER_ID_LINUX = 2, - SVGA_REG_GUEST_DRIVER_ID_MAX, + SVGA_REG_GUEST_DRIVER_ID_UNKNOWN = 0, + SVGA_REG_GUEST_DRIVER_ID_WDDM = 1, + SVGA_REG_GUEST_DRIVER_ID_LINUX = 2, + SVGA_REG_GUEST_DRIVER_ID_MAX, - SVGA_REG_GUEST_DRIVER_ID_SUBMIT = MAX_UINT32, + SVGA_REG_GUEST_DRIVER_ID_SUBMIT = MAX_UINT32, } SVGARegGuestDriverId; typedef enum SVGARegMSHint { - SVGA_REG_MSHINT_DISABLED = 0, - SVGA_REG_MSHINT_FULL = 1, - SVGA_REG_MSHINT_RESOLVED = 2, + SVGA_REG_MSHINT_DISABLED = 0, + SVGA_REG_MSHINT_FULL = 1, + SVGA_REG_MSHINT_RESOLVED = 2, } SVGARegMSHint; typedef enum SVGARegDirtyTracking { - SVGA_REG_DIRTY_TRACKING_PER_IMAGE = 0, - SVGA_REG_DIRTY_TRACKING_PER_SURFACE = 1, + SVGA_REG_DIRTY_TRACKING_PER_IMAGE = 0, + SVGA_REG_DIRTY_TRACKING_PER_SURFACE = 1, } SVGARegDirtyTracking; - -/* - * Guest memory regions (GMRs): - * - * This is a new memory mapping feature available in SVGA devices - * which have the SVGA_CAP_GMR bit set. Previously, there were two - * fixed memory regions available with which to share data between the - * device and the driver: the FIFO ('MEM') and the framebuffer. GMRs - * are our name for an extensible way of providing arbitrary DMA - * buffers for use between the driver and the SVGA device. They are a - * new alternative to framebuffer memory, usable for both 2D and 3D - * graphics operations. - * - * Since GMR mapping must be done synchronously with guest CPU - * execution, we use a new pair of SVGA registers: - * - * SVGA_REG_GMR_ID -- - * - * Read/write. - * This register holds the 32-bit ID (a small positive integer) - * of a GMR to create, delete, or redefine. Writing this register - * has no side-effects. - * - * SVGA_REG_GMR_DESCRIPTOR -- - * - * Write-only. - * Writing this register will create, delete, or redefine the GMR - * specified by the above ID register. If this register is zero, - * the GMR is deleted. Any pointers into this GMR (including those - * currently being processed by FIFO commands) will be - * synchronously invalidated. - * - * If this register is nonzero, it must be the physical page - * number (PPN) of a data structure which describes the physical - * layout of the memory region this GMR should describe. The - * descriptor structure will be read synchronously by the SVGA - * device when this register is written. The descriptor need not - * remain allocated for the lifetime of the GMR. - * - * The guest driver should write SVGA_REG_GMR_ID first, then - * SVGA_REG_GMR_DESCRIPTOR. - * - * SVGA_REG_GMR_MAX_IDS -- - * - * Read-only. - * The SVGA device may choose to support a maximum number of - * user-defined GMR IDs. This register holds the number of supported - * IDs. (The maximum supported ID plus 1) - * - * SVGA_REG_GMR_MAX_DESCRIPTOR_LENGTH -- - * - * Read-only. - * The SVGA device may choose to put a limit on the total number - * of SVGAGuestMemDescriptor structures it will read when defining - * a single GMR. - * - * The descriptor structure is an array of SVGAGuestMemDescriptor - * structures. Each structure may do one of three things: - * - * - Terminate the GMR descriptor list. - * (ppn==0, numPages==0) - * - * - Add a PPN or range of PPNs to the GMR's virtual address space. - * (ppn != 0, numPages != 0) - * - * - Provide the PPN of the next SVGAGuestMemDescriptor, in order to - * support multi-page GMR descriptor tables without forcing the - * driver to allocate physically contiguous memory. - * (ppn != 0, numPages == 0) - * - * Note that each physical page of SVGAGuestMemDescriptor structures - * can describe at least 2MB of guest memory. If the driver needs to - * use more than one page of descriptor structures, it must use one of - * its SVGAGuestMemDescriptors to point to an additional page. The - * device will never automatically cross a page boundary. - * - * Once the driver has described a GMR, it is immediately available - * for use via any FIFO command that uses an SVGAGuestPtr structure. - * These pointers include a GMR identifier plus an offset into that - * GMR. - * - * The driver must check the SVGA_CAP_GMR bit before using the GMR - * registers. - */ - -/* - * Special GMR IDs, allowing SVGAGuestPtrs to point to framebuffer - * memory as well. In the future, these IDs could even be used to - * allow legacy memory regions to be redefined by the guest as GMRs. - * - * Using the guest framebuffer (GFB) at BAR1 for general purpose DMA - * is being phased out. Please try to use user-defined GMRs whenever - * possible. - */ -#define SVGA_GMR_NULL ((uint32) -1) -#define SVGA_GMR_FRAMEBUFFER ((uint32) -2) /* Guest Framebuffer (GFB) */ - -typedef -#include "vmware_pack_begin.h" -struct SVGAGuestMemDescriptor { - uint32 ppn; - uint32 numPages; -} -#include "vmware_pack_end.h" -SVGAGuestMemDescriptor; - -typedef -#include "vmware_pack_begin.h" -struct SVGAGuestPtr { - uint32 gmrId; - uint32 offset; -} -#include "vmware_pack_end.h" -SVGAGuestPtr; - -/* - * Register based command buffers -- - * - * Provide an SVGA device interface that allows the guest to submit - * command buffers to the SVGA device through an SVGA device register. - * The metadata for each command buffer is contained in the - * SVGACBHeader structure along with the return status codes. - * - * The SVGA device supports command buffers if - * SVGA_CAP_COMMAND_BUFFERS is set in the device caps register. The - * fifo must be enabled for command buffers to be submitted. - * - * Command buffers are submitted when the guest writing the 64 byte - * aligned physical address into the SVGA_REG_COMMAND_LOW and - * SVGA_REG_COMMAND_HIGH. SVGA_REG_COMMAND_HIGH contains the upper 32 - * bits of the physical address. SVGA_REG_COMMAND_LOW contains the - * lower 32 bits of the physical address, since the command buffer - * headers are required to be 64 byte aligned the lower 6 bits are - * used for the SVGACBContext value. Writing to SVGA_REG_COMMAND_LOW - * submits the command buffer to the device and queues it for - * execution. The SVGA device supports at least - * SVGA_CB_MAX_QUEUED_PER_CONTEXT command buffers that can be queued - * per context and if that limit is reached the device will write the - * status SVGA_CB_STATUS_QUEUE_FULL to the status value of the command - * buffer header synchronously and not raise any IRQs. - * - * It is invalid to submit a command buffer without a valid physical - * address and results are undefined. - * - * The device guarantees that command buffers of size SVGA_CB_MAX_SIZE - * will be supported. If a larger command buffer is submitted results - * are unspecified and the device will either complete the command - * buffer or return an error. - * - * The device guarantees that any individual command in a command - * buffer can be up to SVGA_CB_MAX_COMMAND_SIZE in size which is - * enough to fit a 64x64 color-cursor definition. If the command is - * too large the device is allowed to process the command or return an - * error. - * - * The device context is a special SVGACBContext that allows for - * synchronous register like accesses with the flexibility of - * commands. There is a different command set defined by - * SVGADeviceContextCmdId. The commands in each command buffer is not - * allowed to straddle physical pages. - * - * The offset field which is available starting with the - * SVGA_CAP_CMD_BUFFERS_2 cap bit can be set by the guest to bias the - * start of command processing into the buffer. If an error is - * encountered the errorOffset will still be relative to the specific - * PA, not biased by the offset. When the command buffer is finished - * the guest should not read the offset field as there is no guarantee - * what it will set to. - * - * When the SVGA_CAP_HP_CMD_QUEUE cap bit is set a new command queue - * SVGA_CB_CONTEXT_1 is available. Commands submitted to this queue - * will be executed as quickly as possible by the SVGA device - * potentially before already queued commands on SVGA_CB_CONTEXT_0. - * The SVGA device guarantees that any command buffers submitted to - * SVGA_CB_CONTEXT_0 will be executed after any _already_ submitted - * command buffers to SVGA_CB_CONTEXT_1. - */ - -#define SVGA_CB_MAX_SIZE (512 * 1024) /* 512 KB */ +#define SVGA_GMR_NULL ((uint32)-1) +#define SVGA_GMR_FRAMEBUFFER ((uint32)-2) + +#pragma pack(push, 1) +typedef struct SVGAGuestMemDescriptor { + uint32 ppn; + uint32 numPages; +} SVGAGuestMemDescriptor; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct SVGAGuestPtr { + uint32 gmrId; + uint32 offset; +} SVGAGuestPtr; +#pragma pack(pop) + +#define SVGA_CB_MAX_SIZE_DEFAULT (KBYTES_2_BYTES(512)) +#define SVGA_CB_MAX_SIZE_4MB (MBYTES_2_BYTES(4)) +#define SVGA_CB_MAX_SIZE SVGA_CB_MAX_SIZE_4MB #define SVGA_CB_MAX_QUEUED_PER_CONTEXT 32 -#define SVGA_CB_MAX_COMMAND_SIZE (32 * 1024) /* 32 KB */ +#define SVGA_CB_MAX_COMMAND_SIZE (32 * 1024) #define SVGA_CB_CONTEXT_MASK 0x3f typedef enum { - SVGA_CB_CONTEXT_DEVICE = 0x3f, - SVGA_CB_CONTEXT_0 = 0x0, - SVGA_CB_CONTEXT_1 = 0x1, /* Supported with SVGA_CAP_HP_CMD_QUEUE */ - SVGA_CB_CONTEXT_MAX = 0x2, + SVGA_CB_CONTEXT_DEVICE = 0x3f, + SVGA_CB_CONTEXT_0 = 0x0, + SVGA_CB_CONTEXT_1 = 0x1, + SVGA_CB_CONTEXT_MAX = 0x2, } SVGACBContext; - typedef enum { - /* - * The guest is supposed to write SVGA_CB_STATUS_NONE to the status - * field before submitting the command buffer header, the host will - * change the value when it is done with the command buffer. - */ - SVGA_CB_STATUS_NONE = 0, - - /* - * Written by the host when a command buffer completes successfully. - * The device raises an IRQ with SVGA_IRQFLAG_COMMAND_BUFFER unless - * the SVGA_CB_FLAG_NO_IRQ flag is set. - */ - SVGA_CB_STATUS_COMPLETED = 1, - - /* - * Written by the host synchronously with the command buffer - * submission to indicate the command buffer was not submitted. No - * IRQ is raised. - */ - SVGA_CB_STATUS_QUEUE_FULL = 2, - - /* - * Written by the host when an error was detected parsing a command - * in the command buffer, errorOffset is written to contain the - * offset to the first byte of the failing command. The device - * raises the IRQ with both SVGA_IRQFLAG_ERROR and - * SVGA_IRQFLAG_COMMAND_BUFFER. Some of the commands may have been - * processed. - */ - SVGA_CB_STATUS_COMMAND_ERROR = 3, - - /* - * Written by the host if there is an error parsing the command - * buffer header. The device raises the IRQ with both - * SVGA_IRQFLAG_ERROR and SVGA_IRQFLAG_COMMAND_BUFFER. The device - * did not processes any of the command buffer. - */ - SVGA_CB_STATUS_CB_HEADER_ERROR = 4, - - /* - * Written by the host if the guest requested the host to preempt - * the command buffer. The device will not raise any IRQs and the - * command buffer was not processed. - */ - SVGA_CB_STATUS_PREEMPTED = 5, - - /* - * Written by the host synchronously with the command buffer - * submission to indicate the the command buffer was not submitted - * due to an error. No IRQ is raised. - */ - SVGA_CB_STATUS_SUBMISSION_ERROR = 6, - - /* - * Written by the host when the host finished a - * SVGA_DC_CMD_ASYNC_STOP_QUEUE request for this command buffer - * queue. The offset of the first byte not processed is stored in - * the errorOffset field of the command buffer header. All guest - * visible side effects of commands till that point are guaranteed - * to be finished before this is written. The - * SVGA_IRQFLAG_COMMAND_BUFFER IRQ is raised as long as the - * SVGA_CB_FLAG_NO_IRQ is not set. - */ - SVGA_CB_STATUS_PARTIAL_COMPLETE = 7, + + SVGA_CB_STATUS_NONE = 0, + + SVGA_CB_STATUS_COMPLETED = 1, + + SVGA_CB_STATUS_QUEUE_FULL = 2, + + SVGA_CB_STATUS_COMMAND_ERROR = 3, + + SVGA_CB_STATUS_CB_HEADER_ERROR = 4, + + SVGA_CB_STATUS_PREEMPTED = 5, + + SVGA_CB_STATUS_SUBMISSION_ERROR = 6, + + SVGA_CB_STATUS_PARTIAL_COMPLETE = 7, } SVGACBStatus; typedef enum { - SVGA_CB_FLAG_NONE = 0, - SVGA_CB_FLAG_NO_IRQ = 1 << 0, - SVGA_CB_FLAG_DX_CONTEXT = 1 << 1, - SVGA_CB_FLAG_MOB = 1 << 2, + SVGA_CB_FLAG_NONE = 0, + SVGA_CB_FLAG_NO_IRQ = 1 << 0, + SVGA_CB_FLAG_DX_CONTEXT = 1 << 1, + SVGA_CB_FLAG_MOB = 1 << 2, } SVGACBFlags; -typedef -#include "vmware_pack_begin.h" -struct { - volatile SVGACBStatus status; /* Modified by device. */ - volatile uint32 errorOffset; /* Modified by device. */ - uint64 id; - SVGACBFlags flags; - uint32 length; - union { - PA pa; - struct { - SVGAMobId mobid; - uint32 mobOffset; - } mob; - } ptr; - uint32 offset; /* Valid if CMD_BUFFERS_2 cap set, must be zero otherwise, - * modified by device. - */ - uint32 dxContext; /* Valid if DX_CONTEXT flag set, must be zero otherwise */ - uint32 mustBeZero[6]; -} -#include "vmware_pack_end.h" -SVGACBHeader; +#pragma pack(push, 1) +typedef struct { + volatile SVGACBStatus status; + volatile uint32 errorOffset; + uint64 id; + SVGACBFlags flags; + uint32 length; + union { + PA pa; + struct { + SVGAMobId mobid; + uint32 mobOffset; + } mob; + } ptr; + uint32 offset; + uint32 dxContext; + uint32 mustBeZero[6]; +} SVGACBHeader; +#pragma pack(pop) typedef enum { - SVGA_DC_CMD_NOP = 0, - SVGA_DC_CMD_START_STOP_CONTEXT = 1, - SVGA_DC_CMD_PREEMPT = 2, - SVGA_DC_CMD_START_QUEUE = 3, /* Requires SVGA_CAP_HP_CMD_QUEUE */ - SVGA_DC_CMD_ASYNC_STOP_QUEUE = 4, /* Requires SVGA_CAP_HP_CMD_QUEUE */ - SVGA_DC_CMD_EMPTY_CONTEXT_QUEUE = 5, /* Requires SVGA_CAP_HP_CMD_QUEUE */ - SVGA_DC_CMD_MAX = 6, + SVGA_DC_CMD_NOP = 0, + SVGA_DC_CMD_START_STOP_CONTEXT = 1, + SVGA_DC_CMD_PREEMPT = 2, + SVGA_DC_CMD_START_QUEUE = 3, + SVGA_DC_CMD_ASYNC_STOP_QUEUE = 4, + SVGA_DC_CMD_EMPTY_CONTEXT_QUEUE = 5, + SVGA_DC_CMD_MAX = 6 } SVGADeviceContextCmdId; -/* - * Starts or stops both SVGA_CB_CONTEXT_0 and SVGA_CB_CONTEXT_1. - */ - typedef struct SVGADCCmdStartStop { - uint32 enable; - SVGACBContext context; /* Must be zero */ + uint32 enable; + SVGACBContext context; } SVGADCCmdStartStop; -/* - * SVGADCCmdPreempt -- - * - * This command allows the guest to request that all command buffers - * on SVGA_CB_CONTEXT_0 be preempted that can be. After execution - * of this command all command buffers that were preempted will - * already have SVGA_CB_STATUS_PREEMPTED written into the status - * field. The device might still be processing a command buffer, - * assuming execution of it started before the preemption request was - * received. Specifying the ignoreIDZero flag to TRUE will cause the - * device to not preempt command buffers with the id field in the - * command buffer header set to zero. - */ - typedef struct SVGADCCmdPreempt { - SVGACBContext context; /* Must be zero */ - uint32 ignoreIDZero; + SVGACBContext context; + uint32 ignoreIDZero; } SVGADCCmdPreempt; -/* - * Starts the requested command buffer processing queue. Valid only - * if the SVGA_CAP_HP_CMD_QUEUE cap is set. - * - * For a command queue to be considered runnable it must be enabled - * and any corresponding higher priority queues must also be enabled. - * For example in order for command buffers to be processed on - * SVGA_CB_CONTEXT_0 both SVGA_CB_CONTEXT_0 and SVGA_CB_CONTEXT_1 must - * be enabled. But for commands to be runnable on SVGA_CB_CONTEXT_1 - * only that queue must be enabled. - */ - typedef struct SVGADCCmdStartQueue { - SVGACBContext context; + SVGACBContext context; } SVGADCCmdStartQueue; -/* - * Requests the SVGA device to stop processing the requested command - * buffer queue as soon as possible. The guest knows the stop has - * completed when one of the following happens. - * - * 1) A command buffer status of SVGA_CB_STATUS_PARTIAL_COMPLETE is returned - * 2) A command buffer error is encountered with would stop the queue - * regardless of the async stop request. - * 3) All command buffers that have been submitted complete successfully. - * 4) The stop completes synchronously if no command buffers are - * active on the queue when it is issued. - * - * If the command queue is not in a runnable state there is no - * guarentee this async stop will finish. For instance if the high - * priority queue is not enabled and a stop is requested on the low - * priority queue, the high priority queue must be reenabled to - * guarantee that the async stop will finish. - * - * This command along with SVGA_DC_CMD_EMPTY_CONTEXT_QUEUE can be used - * to implement mid command buffer preemption. - * - * Valid only if the SVGA_CAP_HP_CMD_QUEUE cap is set. - */ - typedef struct SVGADCCmdAsyncStopQueue { - SVGACBContext context; + SVGACBContext context; } SVGADCCmdAsyncStopQueue; -/* - * Requests the SVGA device to throw away any full command buffers on - * the requested command queue that have not been started. For a - * driver to know which command buffers were thrown away a driver - * should only issue this command when the queue is stopped, for - * whatever reason. - */ - typedef struct SVGADCCmdEmptyQueue { - SVGACBContext context; + SVGACBContext context; } SVGADCCmdEmptyQueue; - -/* - * SVGAGMRImageFormat -- - * - * This is a packed representation of the source 2D image format - * for a GMR-to-screen blit. Currently it is defined as an encoding - * of the screen's color depth and bits-per-pixel, however, 16 bits - * are reserved for future use to identify other encodings (such as - * RGBA or higher-precision images). - * - * Currently supported formats: - * - * bpp depth Format Name - * --- ----- ----------- - * 32 24 32-bit BGRX - * 24 24 24-bit BGR - * 16 16 RGB 5-6-5 - * 16 15 RGB 5-5-5 - * - */ - typedef struct SVGAGMRImageFormat { - union { - struct { - uint32 bitsPerPixel : 8; - uint32 colorDepth : 8; - uint32 reserved : 16; /* Must be zero */ - }; - - uint32 value; - }; + union { + struct { + uint32 bitsPerPixel : 8; + uint32 colorDepth : 8; + uint32 reserved : 16; + }; + + uint32 value; + }; } SVGAGMRImageFormat; -typedef -#include "vmware_pack_begin.h" -struct SVGAGuestImage { - SVGAGuestPtr ptr; - - /* - * A note on interpretation of pitch: This value of pitch is the - * number of bytes between vertically adjacent image - * blocks. Normally this is the number of bytes between the first - * pixel of two adjacent scanlines. With compressed textures, - * however, this may represent the number of bytes between - * compression blocks rather than between rows of pixels. - * - * XXX: Compressed textures currently must be tightly packed in guest memory. - * - * If the image is 1-dimensional, pitch is ignored. - * - * If 'pitch' is zero, the SVGA3D device calculates a pitch value - * assuming each row of blocks is tightly packed. - */ - uint32 pitch; -} -#include "vmware_pack_end.h" -SVGAGuestImage; +#pragma pack(push, 1) +typedef struct SVGAGuestImage { + SVGAGuestPtr ptr; -/* - * SVGAColorBGRX -- - * - * A 24-bit color format (BGRX), which does not depend on the - * format of the legacy guest framebuffer (GFB) or the current - * GMRFB state. - */ + uint32 pitch; +} SVGAGuestImage; +#pragma pack(pop) typedef struct SVGAColorBGRX { - union { - struct { - uint32 b : 8; - uint32 g : 8; - uint32 r : 8; - uint32 x : 8; /* Unused */ - }; - - uint32 value; - }; + union { + struct { + uint32 b : 8; + uint32 g : 8; + uint32 r : 8; + uint32 x : 8; + }; + + uint32 value; + }; } SVGAColorBGRX; - -/* - * SVGASignedRect -- - * SVGASignedPoint -- - * - * Signed rectangle and point primitives. These are used by the new - * 2D primitives for drawing to Screen Objects, which can occupy a - * signed virtual coordinate space. - * - * SVGASignedRect specifies a half-open interval: the (left, top) - * pixel is part of the rectangle, but the (right, bottom) pixel is - * not. - */ - -typedef -#include "vmware_pack_begin.h" -struct { - int32 left; - int32 top; - int32 right; - int32 bottom; -} -#include "vmware_pack_end.h" -SVGASignedRect; - -typedef -#include "vmware_pack_begin.h" -struct { - int32 x; - int32 y; -} -#include "vmware_pack_end.h" -SVGASignedPoint; - - -/* - * SVGA Device Capabilities - * - * Note the holes in the bitfield. Missing bits have been deprecated, - * and must not be reused. Those capabilities will never be reported - * by new versions of the SVGA device. - * - * SVGA_CAP_IRQMASK -- - * Provides device interrupts. Adds device register SVGA_REG_IRQMASK - * to set interrupt mask and direct I/O port SVGA_IRQSTATUS_PORT to - * set/clear pending interrupts. - * - * SVGA_CAP_GMR -- - * Provides synchronous mapping of guest memory regions (GMR). - * Adds device registers SVGA_REG_GMR_ID, SVGA_REG_GMR_DESCRIPTOR, - * SVGA_REG_GMR_MAX_IDS, and SVGA_REG_GMR_MAX_DESCRIPTOR_LENGTH. - * - * SVGA_CAP_TRACES -- - * Allows framebuffer trace-based updates even when FIFO is enabled. - * Adds device register SVGA_REG_TRACES. - * - * SVGA_CAP_GMR2 -- - * Provides asynchronous commands to define and remap guest memory - * regions. Adds device registers SVGA_REG_GMRS_MAX_PAGES and - * SVGA_REG_MEMORY_SIZE. - * - * SVGA_CAP_SCREEN_OBJECT_2 -- - * Allow screen object support, and require backing stores from the - * guest for each screen object. - * - * SVGA_CAP_COMMAND_BUFFERS -- - * Enable register based command buffer submission. - * - * SVGA_CAP_DEAD1 -- - * This cap was incorrectly used by old drivers and should not be - * reused. - * - * SVGA_CAP_CMD_BUFFERS_2 -- - * Enable support for the prepend command buffer submision - * registers. SVGA_REG_CMD_PREPEND_LOW and - * SVGA_REG_CMD_PREPEND_HIGH. - * - * SVGA_CAP_GBOBJECTS -- - * Enable guest-backed objects and surfaces. - * - * SVGA_CAP_DX -- - * Enable support for DX commands, and command buffers in a mob. - * - * SVGA_CAP_HP_CMD_QUEUE -- - * Enable support for the high priority command queue, and the - * ScreenCopy command. - * - * SVGA_CAP_NO_BB_RESTRICTION -- - * Allow ScreenTargets to be defined without regard to the 32-bpp - * bounding-box memory restrictions. ie: - * - * The summed memory usage of all screens (assuming they were defined as - * 32-bpp) must always be less than the value of the - * SVGA_REG_MAX_PRIMARY_MEM register. - * - * If this cap is not present, the 32-bpp bounding box around all screens - * must additionally be under the value of the SVGA_REG_MAX_PRIMARY_MEM - * register. - * - * If the cap is present, the bounding box restriction is lifted (and only - * the screen-sum limit applies). - * - * (Note that this is a slight lie... there is still a sanity limit on any - * dimension of the topology to be less than SVGA_SCREEN_ROOT_LIMIT, even - * when SVGA_CAP_NO_BB_RESTRICTION is present, but that should be - * large enough to express any possible topology without holes between - * monitors.) - * - * SVGA_CAP_CAP2_REGISTER -- - * If this cap is present, the SVGA_REG_CAP2 register is supported. - */ - -#define SVGA_CAP_NONE 0x00000000 -#define SVGA_CAP_RECT_COPY 0x00000002 -#define SVGA_CAP_CURSOR 0x00000020 -#define SVGA_CAP_CURSOR_BYPASS 0x00000040 -#define SVGA_CAP_CURSOR_BYPASS_2 0x00000080 -#define SVGA_CAP_8BIT_EMULATION 0x00000100 -#define SVGA_CAP_ALPHA_CURSOR 0x00000200 -#define SVGA_CAP_3D 0x00004000 -#define SVGA_CAP_EXTENDED_FIFO 0x00008000 -#define SVGA_CAP_MULTIMON 0x00010000 -#define SVGA_CAP_PITCHLOCK 0x00020000 -#define SVGA_CAP_IRQMASK 0x00040000 -#define SVGA_CAP_DISPLAY_TOPOLOGY 0x00080000 -#define SVGA_CAP_GMR 0x00100000 -#define SVGA_CAP_TRACES 0x00200000 -#define SVGA_CAP_GMR2 0x00400000 -#define SVGA_CAP_SCREEN_OBJECT_2 0x00800000 -#define SVGA_CAP_COMMAND_BUFFERS 0x01000000 -#define SVGA_CAP_DEAD1 0x02000000 -#define SVGA_CAP_CMD_BUFFERS_2 0x04000000 -#define SVGA_CAP_GBOBJECTS 0x08000000 -#define SVGA_CAP_DX 0x10000000 -#define SVGA_CAP_HP_CMD_QUEUE 0x20000000 -#define SVGA_CAP_NO_BB_RESTRICTION 0x40000000 -#define SVGA_CAP_CAP2_REGISTER 0x80000000 - -/* - * The SVGA_REG_CAP2 register is an additional set of SVGA capability bits. - * - * SVGA_CAP2_GROW_OTABLE -- - * Allow the GrowOTable/DXGrowCOTable commands. - * - * SVGA_CAP2_INTRA_SURFACE_COPY -- - * Allow the IntraSurfaceCopy command. - * - * SVGA_CAP2_DX2 -- - * Allow the DefineGBSurface_v3, WholeSurfaceCopy, WriteZeroSurface, and - * HintZeroSurface commands, and the SVGA_REG_GUEST_DRIVER_ID register. - * - * SVGA_CAP2_GB_MEMSIZE_2 -- - * Allow the SVGA_REG_GBOBJECT_MEM_SIZE_KB register. - * - * SVGA_CAP2_SCREENDMA_REG -- - * Allow the SVGA_REG_SCREENDMA register. - * - * SVGA_CAP2_OTABLE_PTDEPTH_2 -- - * Allow 2 level page tables for OTable commands. - * - * SVGA_CAP2_NON_MS_TO_MS_STRETCHBLT -- - * Allow a stretch blt from a non-multisampled surface to a multisampled - * surface. - * - * SVGA_CAP2_CURSOR_MOB -- - * Allow the SVGA_REG_CURSOR_MOBID register. - * - * SVGA_CAP2_MSHINT -- - * Allow the SVGA_REG_MSHINT register. - * - * SVGA_CAP2_DX3 -- - * Allows the DefineGBSurface_v4 command. - * Allows the DXDefineDepthStencilView_v2, DXDefineStreamOutputWithMob, - * and DXBindStreamOutput commands if 3D is also available. - * Allows the DXPredStagingCopy and DXStagingCopy commands if SM41 - * is also available. - * - * SVGA_CAP2_RESERVED -- - * Reserve the last bit for extending the SVGA capabilities to some - * future mechanisms. - */ -#define SVGA_CAP2_NONE 0x00000000 -#define SVGA_CAP2_GROW_OTABLE 0x00000001 -#define SVGA_CAP2_INTRA_SURFACE_COPY 0x00000002 -#define SVGA_CAP2_DX2 0x00000004 -#define SVGA_CAP2_GB_MEMSIZE_2 0x00000008 -#define SVGA_CAP2_SCREENDMA_REG 0x00000010 -#define SVGA_CAP2_OTABLE_PTDEPTH_2 0x00000020 +#pragma pack(push, 1) +typedef struct { + int32 left; + int32 top; + int32 right; + int32 bottom; +} SVGASignedRect; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + int32 x; + int32 y; +} SVGASignedPoint; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 x; + uint32 y; +} SVGAUnsignedPoint; +#pragma pack(pop) + +#define SVGA_CAP_NONE 0x00000000 +#define SVGA_CAP_RECT_COPY 0x00000002 +#define SVGA_CAP_CURSOR 0x00000020 +#define SVGA_CAP_CURSOR_BYPASS 0x00000040 +#define SVGA_CAP_CURSOR_BYPASS_2 0x00000080 +#define SVGA_CAP_8BIT_EMULATION 0x00000100 +#define SVGA_CAP_ALPHA_CURSOR 0x00000200 +#define SVGA_CAP_3D 0x00004000 +#define SVGA_CAP_EXTENDED_FIFO 0x00008000 +#define SVGA_CAP_MULTIMON 0x00010000 +#define SVGA_CAP_PITCHLOCK 0x00020000 +#define SVGA_CAP_IRQMASK 0x00040000 +#define SVGA_CAP_DISPLAY_TOPOLOGY 0x00080000 +#define SVGA_CAP_GMR 0x00100000 +#define SVGA_CAP_TRACES 0x00200000 +#define SVGA_CAP_GMR2 0x00400000 +#define SVGA_CAP_SCREEN_OBJECT_2 0x00800000 +#define SVGA_CAP_COMMAND_BUFFERS 0x01000000 +#define SVGA_CAP_DEAD1 0x02000000 +#define SVGA_CAP_CMD_BUFFERS_2 0x04000000 +#define SVGA_CAP_GBOBJECTS 0x08000000 +#define SVGA_CAP_DX 0x10000000 +#define SVGA_CAP_HP_CMD_QUEUE 0x20000000 +#define SVGA_CAP_NO_BB_RESTRICTION 0x40000000 +#define SVGA_CAP_CAP2_REGISTER 0x80000000 + +#define SVGA_CAP2_NONE 0x00000000 +#define SVGA_CAP2_GROW_OTABLE 0x00000001 +#define SVGA_CAP2_INTRA_SURFACE_COPY 0x00000002 +#define SVGA_CAP2_DX2 0x00000004 +#define SVGA_CAP2_GB_MEMSIZE_2 0x00000008 +#define SVGA_CAP2_SCREENDMA_REG 0x00000010 +#define SVGA_CAP2_OTABLE_PTDEPTH_2 0x00000020 #define SVGA_CAP2_NON_MS_TO_MS_STRETCHBLT 0x00000040 -#define SVGA_CAP2_CURSOR_MOB 0x00000080 -#define SVGA_CAP2_MSHINT 0x00000100 -#define SVGA_CAP2_DX3 0x00000400 -#define SVGA_CAP2_RESERVED 0x80000000 - - -/* - * The Guest can optionally read some SVGA device capabilities through - * the backdoor with command BDOOR_CMD_GET_SVGA_CAPABILITIES before - * the SVGA device is initialized. The type of capability the guest - * is requesting from the SVGABackdoorCapType enum should be placed in - * the upper 16 bits of the backdoor command id (ECX). On success the - * the value of EBX will be set to BDOOR_MAGIC and EAX will be set to - * the requested capability. If the command is not supported then EBX - * will be left unchanged and EAX will be set to -1. Because it is - * possible that -1 is the value of the requested cap the correct way - * to check if the command was successful is to check if EBX was changed - * to BDOOR_MAGIC making sure to initialize the register to something - * else first. - */ +#define SVGA_CAP2_CURSOR_MOB 0x00000080 +#define SVGA_CAP2_MSHINT 0x00000100 +#define SVGA_CAP2_CB_MAX_SIZE_4MB 0x00000200 +#define SVGA_CAP2_DX3 0x00000400 +#define SVGA_CAP2_FRAME_TYPE 0x00000800 +#define SVGA_CAP2_COTABLE_COPY 0x00001000 +#define SVGA_CAP2_TRACE_FULL_FB 0x00002000 +#define SVGA_CAP2_EXTRA_REGS 0x00004000 +#define SVGA_CAP2_LO_STAGING 0x00008000 +#define SVGA_CAP2_RESERVED 0x80000000 typedef enum { - SVGABackdoorCapDeviceCaps = 0, - SVGABackdoorCapFifoCaps = 1, - SVGABackdoorCap3dHWVersion = 2, - SVGABackdoorCapDeviceCaps2 = 3, - SVGABackdoorCapDevelCaps = 4, - SVGABackdoorDevelRenderer = 5, - SVGABackdoorCapMax = 6, + SVGABackdoorCapDeviceCaps = 0, + SVGABackdoorCapFifoCaps = 1, + SVGABackdoorCap3dHWVersion = 2, + SVGABackdoorCapDeviceCaps2 = 3, + SVGABackdoorCapDevelCaps = 4, + SVGABackdoorDevelRenderer = 5, + SVGABackdoorDevelUsingISB = 6, + SVGABackdoorCapMax = 7, } SVGABackdoorCapType; - -/* - * FIFO register indices. - * - * The FIFO is a chunk of device memory mapped into guest physmem. It - * is always treated as 32-bit words. - * - * The guest driver gets to decide how to partition it between - * - FIFO registers (there are always at least 4, specifying where the - * following data area is and how much data it contains; there may be - * more registers following these, depending on the FIFO protocol - * version in use) - * - FIFO data, written by the guest and slurped out by the VMX. - * These indices are 32-bit word offsets into the FIFO. - */ - enum { - /* - * Block 1 (basic registers): The originally defined FIFO registers. - * These exist and are valid for all versions of the FIFO protocol. - */ - - SVGA_FIFO_MIN = 0, - SVGA_FIFO_MAX, /* The distance from MIN to MAX must be at least 10K */ - SVGA_FIFO_NEXT_CMD, - SVGA_FIFO_STOP, - - /* - * Block 2 (extended registers): Mandatory registers for the extended - * FIFO. These exist if the SVGA caps register includes - * SVGA_CAP_EXTENDED_FIFO; some of them are valid only if their - * associated capability bit is enabled. - * - * Note that when originally defined, SVGA_CAP_EXTENDED_FIFO implied - * support only for (FIFO registers) CAPABILITIES, FLAGS, and FENCE. - * This means that the guest has to test individually (in most cases - * using FIFO caps) for the presence of registers after this; the VMX - * can define "extended FIFO" to mean whatever it wants, and currently - * won't enable it unless there's room for that set and much more. - */ - - SVGA_FIFO_CAPABILITIES = 4, - SVGA_FIFO_FLAGS, - /* Valid with SVGA_FIFO_CAP_FENCE: */ - SVGA_FIFO_FENCE, - - /* - * Block 3a (optional extended registers): Additional registers for the - * extended FIFO, whose presence isn't actually implied by - * SVGA_CAP_EXTENDED_FIFO; these exist if SVGA_FIFO_MIN is high enough to - * leave room for them. - * - * These in block 3a, the VMX currently considers mandatory for the - * extended FIFO. - */ - - /* Valid if exists (i.e. if extended FIFO enabled): */ - SVGA_FIFO_3D_HWVERSION, /* See SVGA3dHardwareVersion in svga3d_reg.h */ - /* Valid with SVGA_FIFO_CAP_PITCHLOCK: */ - SVGA_FIFO_PITCHLOCK, - - /* Valid with SVGA_FIFO_CAP_CURSOR_BYPASS_3: */ - SVGA_FIFO_CURSOR_ON, /* Cursor bypass 3 show/hide register */ - SVGA_FIFO_CURSOR_X, /* Cursor bypass 3 x register */ - SVGA_FIFO_CURSOR_Y, /* Cursor bypass 3 y register */ - SVGA_FIFO_CURSOR_COUNT, /* Incremented when any of the other 3 change */ - SVGA_FIFO_CURSOR_LAST_UPDATED,/* Last time the host updated the cursor */ - - /* Valid with SVGA_FIFO_CAP_RESERVE: */ - SVGA_FIFO_RESERVED, /* Bytes past NEXT_CMD with real contents */ - - /* - * Valid with SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2: - * - * By default this is SVGA_ID_INVALID, to indicate that the cursor - * coordinates are specified relative to the virtual root. If this - * is set to a specific screen ID, cursor position is reinterpreted - * as a signed offset relative to that screen's origin. - */ - SVGA_FIFO_CURSOR_SCREEN_ID, - - /* - * Valid with SVGA_FIFO_CAP_DEAD - * - * An arbitrary value written by the host, drivers should not use it. - */ - SVGA_FIFO_DEAD, - - /* - * Valid with SVGA_FIFO_CAP_3D_HWVERSION_REVISED: - * - * Contains 3D HWVERSION (see SVGA3dHardwareVersion in svga3d_reg.h) - * on platforms that can enforce graphics resource limits. - */ - SVGA_FIFO_3D_HWVERSION_REVISED, - - /* - * XXX: The gap here, up until SVGA_FIFO_3D_CAPS, can be used for new - * registers, but this must be done carefully and with judicious use of - * capability bits, since comparisons based on SVGA_FIFO_MIN aren't - * enough to tell you whether the register exists: we've shipped drivers - * and products that used SVGA_FIFO_3D_CAPS but didn't know about some of - * the earlier ones. The actual order of introduction was: - * - PITCHLOCK - * - 3D_CAPS - * - CURSOR_* (cursor bypass 3) - * - RESERVED - * So, code that wants to know whether it can use any of the - * aforementioned registers, or anything else added after PITCHLOCK and - * before 3D_CAPS, needs to reason about something other than - * SVGA_FIFO_MIN. - */ - - /* - * 3D caps block space; valid with 3D hardware version >= - * SVGA3D_HWVERSION_WS6_B1. - */ - SVGA_FIFO_3D_CAPS = 32, - SVGA_FIFO_3D_CAPS_LAST = 32 + 255, - - /* - * End of VMX's current definition of "extended-FIFO registers". - * Registers before here are always enabled/disabled as a block; either - * the extended FIFO is enabled and includes all preceding registers, or - * it's disabled entirely. - * - * Block 3b (truly optional extended registers): Additional registers for - * the extended FIFO, which the VMX already knows how to enable and - * disable with correct granularity. - * - * Registers after here exist if and only if the guest SVGA driver - * sets SVGA_FIFO_MIN high enough to leave room for them. - */ - - /* Valid if register exists: */ - SVGA_FIFO_GUEST_3D_HWVERSION, /* Guest driver's 3D version */ - SVGA_FIFO_FENCE_GOAL, /* Matching target for SVGA_IRQFLAG_FENCE_GOAL */ - SVGA_FIFO_BUSY, /* See "FIFO Synchronization Registers" */ - - /* - * Always keep this last. This defines the maximum number of - * registers we know about. At power-on, this value is placed in - * the SVGA_REG_MEM_REGS register, and we expect the guest driver - * to allocate this much space in FIFO memory for registers. - */ - SVGA_FIFO_NUM_REGS -}; + SVGA_FIFO_MIN = 0, + SVGA_FIFO_MAX, + SVGA_FIFO_NEXT_CMD, + SVGA_FIFO_STOP, -/* - * Definition of registers included in extended FIFO support. - * - * The guest SVGA driver gets to allocate the FIFO between registers - * and data. It must always allocate at least 4 registers, but old - * drivers stopped there. - * - * The VMX will enable extended FIFO support if and only if the guest - * left enough room for all registers defined as part of the mandatory - * set for the extended FIFO. - * - * Note that the guest drivers typically allocate the FIFO only at - * initialization time, not at mode switches, so it's likely that the - * number of FIFO registers won't change without a reboot. - * - * All registers less than this value are guaranteed to be present if - * svgaUser->fifo.extended is set. Any later registers must be tested - * individually for compatibility at each use (in the VMX). - * - * This value is used only by the VMX, so it can change without - * affecting driver compatibility; keep it that way? - */ -#define SVGA_FIFO_EXTENDED_MANDATORY_REGS (SVGA_FIFO_3D_CAPS_LAST + 1) + SVGA_FIFO_CAPABILITIES = 4, + SVGA_FIFO_FLAGS, + SVGA_FIFO_FENCE, -/* - * FIFO Synchronization Registers - * - * SVGA_REG_SYNC -- - * - * The SYNC register can be used by the guest driver to signal to the - * device that the guest driver is waiting for previously submitted - * commands to complete. - * - * When the guest driver writes to the SYNC register, the device sets - * the BUSY register to TRUE, and starts processing the submitted commands - * (if it was not already doing so). When all previously submitted - * commands are finished and the device is idle again, it sets the BUSY - * register back to FALSE. (If the guest driver submits new commands - * after writing the SYNC register, the new commands are not guaranteed - * to have been procesesd.) - * - * When guest drivers are submitting commands using the FIFO, the device - * periodically polls to check for new FIFO commands when idle, which may - * introduce a delay in command processing. If the guest-driver wants - * the commands to be processed quickly (which it typically does), it - * should write SYNC after each batch of commands is committed to the - * FIFO to immediately wake up the device. For even better performance, - * the guest can use the SVGA_FIFO_BUSY register to avoid these extra - * SYNC writes if the device is already active, using the technique known - * as "Ringing the Doorbell" (described below). (Note that command - * buffer submission implicitly wakes up the device, and so doesn't - * suffer from this problem.) - * - * The SYNC register can also be used in combination with BUSY to - * synchronously ensure that all SVGA commands are processed (with both - * the FIFO and command-buffers). To do this, the guest driver should - * write to SYNC, and then loop reading BUSY until BUSY returns FALSE. - * This technique is known as a "Legacy Sync". - * - * SVGA_REG_BUSY -- - * - * This register is set to TRUE when SVGA_REG_SYNC is written, - * and is set back to FALSE when the device has finished processing - * all commands and is idle again. - * - * Every read from the BUSY reigster will block for an undefined - * amount of time (normally until the device finishes some interesting - * work unit), or the device is idle. - * - * Guest drivers can also do a partial Legacy Sync to check for some - * particular condition, for instance by stopping early when a fence - * passes before BUSY has been set back to FALSE. This is particularly - * useful if the guest-driver knows that it is blocked waiting on the - * device, because it will yield CPU time back to the host. - * - * SVGA_FIFO_BUSY -- - * - * The SVGA_FIFO_BUSY register is a fast way for the guest driver to check - * whether the device is actively processing FIFO commands before writing - * the more expensive SYNC register. - * - * If this register reads as TRUE, the device is actively processing - * FIFO commands. - * - * If this register reads as FALSE, the device may not be actively - * processing commands, and the guest driver should try - * "Ringing the Doorbell". - * - * To Ring the Doorbell, the guest should: - * - * 1. Have already written their batch of commands into the FIFO. - * 2. Check if the SVGA_FIFO_BUSY register is available by reading - * SVGA_FIFO_MIN. - * 3. Read SVGA_FIFO_BUSY. If it reads as TRUE, the device is actively - * processing FIFO commands, and no further action is necessary. - * 4. If SVGA_FIFO_BUSY was FALSE, write TRUE to SVGA_REG_SYNC. - * - * For maximum performance, this procedure should be followed after - * every meaningful batch of commands has been written into the FIFO. - * (Normally when the underlying application signals it's finished a - * meaningful work unit by calling Flush.) - */ + SVGA_FIFO_3D_HWVERSION, + SVGA_FIFO_PITCHLOCK, -/* - * FIFO Capabilities - * - * Fence -- Fence register and command are supported - * Accel Front -- Front buffer only commands are supported - * Pitch Lock -- Pitch lock register is supported - * Video -- SVGA Video overlay units are supported - * Escape -- Escape command is supported - * - * SVGA_FIFO_CAP_SCREEN_OBJECT -- - * - * Provides dynamic multi-screen rendering, for improved Unity and - * multi-monitor modes. With Screen Object, the guest can - * dynamically create and destroy 'screens', which can represent - * Unity windows or virtual monitors. Screen Object also provides - * strong guarantees that DMA operations happen only when - * guest-initiated. Screen Object deprecates the BAR1 guest - * framebuffer (GFB) and all commands that work only with the GFB. - * - * New registers: - * FIFO_CURSOR_SCREEN_ID, VIDEO_DATA_GMRID, VIDEO_DST_SCREEN_ID - * - * New 2D commands: - * DEFINE_SCREEN, DESTROY_SCREEN, DEFINE_GMRFB, BLIT_GMRFB_TO_SCREEN, - * BLIT_SCREEN_TO_GMRFB, ANNOTATION_FILL, ANNOTATION_COPY - * - * New 3D commands: - * BLIT_SURFACE_TO_SCREEN - * - * New guarantees: - * - * - The host will not read or write guest memory, including the GFB, - * except when explicitly initiated by a DMA command. - * - * - All DMA, including legacy DMA like UPDATE and PRESENT_READBACK, - * is guaranteed to complete before any subsequent FENCEs. - * - * - All legacy commands which affect a Screen (UPDATE, PRESENT, - * PRESENT_READBACK) as well as new Screen blit commands will - * all behave consistently as blits, and memory will be read - * or written in FIFO order. - * - * For example, if you PRESENT from one SVGA3D surface to multiple - * places on the screen, the data copied will always be from the - * SVGA3D surface at the time the PRESENT was issued in the FIFO. - * This was not necessarily true on devices without Screen Object. - * - * This means that on devices that support Screen Object, the - * PRESENT_READBACK command should not be necessary unless you - * actually want to read back the results of 3D rendering into - * system memory. (And for that, the BLIT_SCREEN_TO_GMRFB - * command provides a strict superset of functionality.) - * - * - When a screen is resized, either using Screen Object commands or - * legacy multimon registers, its contents are preserved. - * - * SVGA_FIFO_CAP_GMR2 -- - * - * Provides new commands to define and remap guest memory regions (GMR). - * - * New 2D commands: - * DEFINE_GMR2, REMAP_GMR2. - * - * SVGA_FIFO_CAP_3D_HWVERSION_REVISED -- - * - * Indicates new register SVGA_FIFO_3D_HWVERSION_REVISED exists. - * This register may replace SVGA_FIFO_3D_HWVERSION on platforms - * that enforce graphics resource limits. This allows the platform - * to clear SVGA_FIFO_3D_HWVERSION and disable 3D in legacy guest - * drivers that do not limit their resources. - * - * Note this is an alias to SVGA_FIFO_CAP_GMR2 because these indicators - * are codependent (and thus we use a single capability bit). - * - * SVGA_FIFO_CAP_SCREEN_OBJECT_2 -- - * - * Modifies the DEFINE_SCREEN command to include a guest provided - * backing store in GMR memory and the bytesPerLine for the backing - * store. This capability requires the use of a backing store when - * creating screen objects. However if SVGA_FIFO_CAP_SCREEN_OBJECT - * is present then backing stores are optional. - * - * SVGA_FIFO_CAP_DEAD -- - * - * Drivers should not use this cap bit. This cap bit can not be - * reused since some hosts already expose it. - */ + SVGA_FIFO_CURSOR_ON, + SVGA_FIFO_CURSOR_X, + SVGA_FIFO_CURSOR_Y, + SVGA_FIFO_CURSOR_COUNT, + SVGA_FIFO_CURSOR_LAST_UPDATED, -#define SVGA_FIFO_CAP_NONE 0 -#define SVGA_FIFO_CAP_FENCE (1<<0) -#define SVGA_FIFO_CAP_ACCELFRONT (1<<1) -#define SVGA_FIFO_CAP_PITCHLOCK (1<<2) -#define SVGA_FIFO_CAP_VIDEO (1<<3) -#define SVGA_FIFO_CAP_CURSOR_BYPASS_3 (1<<4) -#define SVGA_FIFO_CAP_ESCAPE (1<<5) -#define SVGA_FIFO_CAP_RESERVE (1<<6) -#define SVGA_FIFO_CAP_SCREEN_OBJECT (1<<7) -#define SVGA_FIFO_CAP_GMR2 (1<<8) -#define SVGA_FIFO_CAP_3D_HWVERSION_REVISED SVGA_FIFO_CAP_GMR2 -#define SVGA_FIFO_CAP_SCREEN_OBJECT_2 (1<<9) -#define SVGA_FIFO_CAP_DEAD (1<<10) + SVGA_FIFO_RESERVED, + SVGA_FIFO_CURSOR_SCREEN_ID, -/* - * FIFO Flags - * - * Accel Front -- Driver should use front buffer only commands - */ + SVGA_FIFO_DEAD, -#define SVGA_FIFO_FLAG_NONE 0 -#define SVGA_FIFO_FLAG_ACCELFRONT (1<<0) -#define SVGA_FIFO_FLAG_RESERVED (1<<31) /* Internal use only */ + SVGA_FIFO_3D_HWVERSION_REVISED, -/* - * FIFO reservation sentinel value - */ + SVGA_FIFO_3D_CAPS = 32, + SVGA_FIFO_3D_CAPS_LAST = 32 + 255, -#define SVGA_FIFO_RESERVED_UNKNOWN 0xffffffff + SVGA_FIFO_GUEST_3D_HWVERSION, + SVGA_FIFO_FENCE_GOAL, + SVGA_FIFO_BUSY, + SVGA_FIFO_NUM_REGS +}; -/* - * ScreenDMA Register Values - */ +#define SVGA_FIFO_3D_CAPS_SIZE (SVGA_FIFO_3D_CAPS_LAST - SVGA_FIFO_3D_CAPS + 1) -#define SVGA_SCREENDMA_REG_UNDEFINED 0 -#define SVGA_SCREENDMA_REG_NOT_PRESENT 1 -#define SVGA_SCREENDMA_REG_PRESENT 2 -#define SVGA_SCREENDMA_REG_MAX 3 +#define SVGA3D_FIFO_CAPS_RECORD_DEVCAPS 0x100 +typedef uint32 SVGA3dFifoCapsRecordType; -/* - * Video overlay support - */ +typedef uint32 SVGA3dFifoCapPair[2]; -#define SVGA_NUM_OVERLAY_UNITS 32 +#pragma pack(push, 1) +typedef struct SVGA3dFifoCapsRecordHeader { + uint32 length; + SVGA3dFifoCapsRecordType type; +} SVGA3dFifoCapsRecordHeader; +#pragma pack(pop) -/* - * Video capabilities that the guest is currently using - */ +#define SVGA_FIFO_EXTENDED_MANDATORY_REGS (SVGA_FIFO_3D_CAPS_LAST + 1) -#define SVGA_VIDEO_FLAG_COLORKEY 0x0001 +#define SVGA_FIFO_CAP_NONE 0 +#define SVGA_FIFO_CAP_FENCE (1 << 0) +#define SVGA_FIFO_CAP_ACCELFRONT (1 << 1) +#define SVGA_FIFO_CAP_PITCHLOCK (1 << 2) +#define SVGA_FIFO_CAP_VIDEO (1 << 3) +#define SVGA_FIFO_CAP_CURSOR_BYPASS_3 (1 << 4) +#define SVGA_FIFO_CAP_ESCAPE (1 << 5) +#define SVGA_FIFO_CAP_RESERVE (1 << 6) +#define SVGA_FIFO_CAP_SCREEN_OBJECT (1 << 7) +#define SVGA_FIFO_CAP_GMR2 (1 << 8) +#define SVGA_FIFO_CAP_3D_HWVERSION_REVISED SVGA_FIFO_CAP_GMR2 +#define SVGA_FIFO_CAP_SCREEN_OBJECT_2 (1 << 9) +#define SVGA_FIFO_CAP_DEAD (1 << 10) +#define SVGA_FIFO_FLAG_NONE 0 +#define SVGA_FIFO_FLAG_ACCELFRONT (1 << 0) +#define SVGA_FIFO_FLAG_RESERVED (1 << 31) -/* - * Offsets for the video overlay registers - */ +#define SVGA_FIFO_RESERVED_UNKNOWN 0xffffffff -enum { - SVGA_VIDEO_ENABLED = 0, - SVGA_VIDEO_FLAGS, - SVGA_VIDEO_DATA_OFFSET, - SVGA_VIDEO_FORMAT, - SVGA_VIDEO_COLORKEY, - SVGA_VIDEO_SIZE, /* Deprecated */ - SVGA_VIDEO_WIDTH, - SVGA_VIDEO_HEIGHT, - SVGA_VIDEO_SRC_X, - SVGA_VIDEO_SRC_Y, - SVGA_VIDEO_SRC_WIDTH, - SVGA_VIDEO_SRC_HEIGHT, - SVGA_VIDEO_DST_X, /* Signed int32 */ - SVGA_VIDEO_DST_Y, /* Signed int32 */ - SVGA_VIDEO_DST_WIDTH, - SVGA_VIDEO_DST_HEIGHT, - SVGA_VIDEO_PITCH_1, - SVGA_VIDEO_PITCH_2, - SVGA_VIDEO_PITCH_3, - SVGA_VIDEO_DATA_GMRID, /* Optional, defaults to SVGA_GMR_FRAMEBUFFER */ - SVGA_VIDEO_DST_SCREEN_ID, /* Optional, defaults to virtual coords */ - /* (SVGA_ID_INVALID) */ - SVGA_VIDEO_NUM_REGS -}; +#define SVGA_SCREENDMA_REG_UNDEFINED 0 +#define SVGA_SCREENDMA_REG_NOT_PRESENT 1 +#define SVGA_SCREENDMA_REG_PRESENT 2 +#define SVGA_SCREENDMA_REG_MAX 3 +#define SVGA_NUM_OVERLAY_UNITS 32 -/* - * SVGA Overlay Units - * - * width and height relate to the entire source video frame. - * srcX, srcY, srcWidth and srcHeight represent subset of the source - * video frame to be displayed. - */ +#define SVGA_VIDEO_FLAG_COLORKEY 0x0001 -typedef -#include "vmware_pack_begin.h" -struct SVGAOverlayUnit { - uint32 enabled; - uint32 flags; - uint32 dataOffset; - uint32 format; - uint32 colorKey; - uint32 size; - uint32 width; - uint32 height; - uint32 srcX; - uint32 srcY; - uint32 srcWidth; - uint32 srcHeight; - int32 dstX; - int32 dstY; - uint32 dstWidth; - uint32 dstHeight; - uint32 pitches[3]; - uint32 dataGMRId; - uint32 dstScreenId; -} -#include "vmware_pack_end.h" -SVGAOverlayUnit; +enum { + SVGA_VIDEO_ENABLED = 0, + SVGA_VIDEO_FLAGS, + SVGA_VIDEO_DATA_OFFSET, + SVGA_VIDEO_FORMAT, + SVGA_VIDEO_COLORKEY, + SVGA_VIDEO_SIZE, + SVGA_VIDEO_WIDTH, + SVGA_VIDEO_HEIGHT, + SVGA_VIDEO_SRC_X, + SVGA_VIDEO_SRC_Y, + SVGA_VIDEO_SRC_WIDTH, + SVGA_VIDEO_SRC_HEIGHT, + SVGA_VIDEO_DST_X, + SVGA_VIDEO_DST_Y, + SVGA_VIDEO_DST_WIDTH, + SVGA_VIDEO_DST_HEIGHT, + SVGA_VIDEO_PITCH_1, + SVGA_VIDEO_PITCH_2, + SVGA_VIDEO_PITCH_3, + SVGA_VIDEO_DATA_GMRID, + SVGA_VIDEO_DST_SCREEN_ID, + SVGA_VIDEO_NUM_REGS +}; +#pragma pack(push, 1) +typedef struct SVGAOverlayUnit { + uint32 enabled; + uint32 flags; + uint32 dataOffset; + uint32 format; + uint32 colorKey; + uint32 size; + uint32 width; + uint32 height; + uint32 srcX; + uint32 srcY; + uint32 srcWidth; + uint32 srcHeight; + int32 dstX; + int32 dstY; + uint32 dstWidth; + uint32 dstHeight; + uint32 pitches[3]; + uint32 dataGMRId; + uint32 dstScreenId; +} SVGAOverlayUnit; +#pragma pack(pop) -/* - * Guest display topology - * - * XXX: This structure is not part of the SVGA device's interface, and - * doesn't really belong here. - */ #define SVGA_INVALID_DISPLAY_ID ((uint32)-1) typedef struct SVGADisplayTopology { - uint16 displayId; - uint16 isPrimary; - uint32 width; - uint32 height; - uint32 positionX; - uint32 positionY; + uint16 displayId; + uint16 isPrimary; + uint32 width; + uint32 height; + uint32 positionX; + uint32 positionY; } SVGADisplayTopology; - -/* - * SVGAScreenObject -- - * - * This is a new way to represent a guest's multi-monitor screen or - * Unity window. Screen objects are only supported if the - * SVGA_FIFO_CAP_SCREEN_OBJECT capability bit is set. - * - * If Screen Objects are supported, they can be used to fully - * replace the functionality provided by the framebuffer registers - * (SVGA_REG_WIDTH, HEIGHT, etc.) and by SVGA_CAP_DISPLAY_TOPOLOGY. - * - * The screen object is a struct with guaranteed binary - * compatibility. New flags can be added, and the struct may grow, - * but existing fields must retain their meaning. - * - * Added with SVGA_FIFO_CAP_SCREEN_OBJECT_2 are required fields of - * a SVGAGuestPtr that is used to back the screen contents. This - * memory must come from the GFB. The guest is not allowed to - * access the memory and doing so will have undefined results. The - * backing store is required to be page aligned and the size is - * padded to the next page boundry. The number of pages is: - * (bytesPerLine * size.width * 4 + PAGE_SIZE - 1) / PAGE_SIZE - * - * The pitch in the backingStore is required to be at least large - * enough to hold a 32bbp scanline. It is recommended that the - * driver pad bytesPerLine for a potential performance win. - * - * The cloneCount field is treated as a hint from the guest that - * the user wants this display to be cloned, countCount times. A - * value of zero means no cloning should happen. - */ - -#define SVGA_SCREEN_MUST_BE_SET (1 << 0) -#define SVGA_SCREEN_HAS_ROOT SVGA_SCREEN_MUST_BE_SET /* Deprecated */ -#define SVGA_SCREEN_IS_PRIMARY (1 << 1) +#define SVGA_SCREEN_MUST_BE_SET (1 << 0) +#define SVGA_SCREEN_HAS_ROOT SVGA_SCREEN_MUST_BE_SET +#define SVGA_SCREEN_IS_PRIMARY (1 << 1) #define SVGA_SCREEN_FULLSCREEN_HINT (1 << 2) -/* - * Added with SVGA_FIFO_CAP_SCREEN_OBJECT_2. When the screen is - * deactivated the base layer is defined to lose all contents and - * become black. When a screen is deactivated the backing store is - * optional. When set backingPtr and bytesPerLine will be ignored. - */ -#define SVGA_SCREEN_DEACTIVATE (1 << 3) +#define SVGA_SCREEN_DEACTIVATE (1 << 3) -/* - * Added with SVGA_FIFO_CAP_SCREEN_OBJECT_2. When this flag is set - * the screen contents will be outputted as all black to the user - * though the base layer contents is preserved. The screen base layer - * can still be read and written to like normal though the no visible - * effect will be seen by the user. When the flag is changed the - * screen will be blanked or redrawn to the current contents as needed - * without any extra commands from the driver. This flag only has an - * effect when the screen is not deactivated. - */ #define SVGA_SCREEN_BLANKING (1 << 4) -typedef -#include "vmware_pack_begin.h" -struct { - uint32 structSize; /* sizeof(SVGAScreenObject) */ - uint32 id; - uint32 flags; - struct { - uint32 width; - uint32 height; - } size; - struct { - int32 x; - int32 y; - } root; - - /* - * Added and required by SVGA_FIFO_CAP_SCREEN_OBJECT_2, optional - * with SVGA_FIFO_CAP_SCREEN_OBJECT. - */ - SVGAGuestImage backingStore; - - /* - * The cloneCount field is treated as a hint from the guest that - * the user wants this display to be cloned, cloneCount times. - * - * A value of zero means no cloning should happen. - */ - uint32 cloneCount; -} -#include "vmware_pack_end.h" -SVGAScreenObject; - - -/* - * Commands in the command FIFO: - * - * Command IDs defined below are used for the traditional 2D FIFO - * communication (not all commands are available for all versions of the - * SVGA FIFO protocol). - * - * Note the holes in the command ID numbers: These commands have been - * deprecated, and the old IDs must not be reused. - * - * Command IDs from 1000 to 2999 are reserved for use by the SVGA3D - * protocol. - * - * Each command's parameters are described by the comments and - * structs below. - */ +#pragma pack(push, 1) +typedef struct { + uint32 structSize; + uint32 id; + uint32 flags; + struct { + uint32 width; + uint32 height; + } size; + struct { + int32 x; + int32 y; + } root; + + SVGAGuestImage backingStore; + + uint32 cloneCount; +} SVGAScreenObject; +#pragma pack(pop) typedef enum { - SVGA_CMD_INVALID_CMD = 0, - SVGA_CMD_UPDATE = 1, - SVGA_CMD_RECT_COPY = 3, - SVGA_CMD_RECT_ROP_COPY = 14, - SVGA_CMD_DEFINE_CURSOR = 19, - SVGA_CMD_DEFINE_ALPHA_CURSOR = 22, - SVGA_CMD_UPDATE_VERBOSE = 25, - SVGA_CMD_FRONT_ROP_FILL = 29, - SVGA_CMD_FENCE = 30, - SVGA_CMD_ESCAPE = 33, - SVGA_CMD_DEFINE_SCREEN = 34, - SVGA_CMD_DESTROY_SCREEN = 35, - SVGA_CMD_DEFINE_GMRFB = 36, - SVGA_CMD_BLIT_GMRFB_TO_SCREEN = 37, - SVGA_CMD_BLIT_SCREEN_TO_GMRFB = 38, - SVGA_CMD_ANNOTATION_FILL = 39, - SVGA_CMD_ANNOTATION_COPY = 40, - SVGA_CMD_DEFINE_GMR2 = 41, - SVGA_CMD_REMAP_GMR2 = 42, - SVGA_CMD_DEAD = 43, - SVGA_CMD_DEAD_2 = 44, - SVGA_CMD_NOP = 45, - SVGA_CMD_NOP_ERROR = 46, - SVGA_CMD_MAX + SVGA_CMD_INVALID_CMD = 0, + SVGA_CMD_UPDATE = 1, + SVGA_CMD_RECT_COPY = 3, + SVGA_CMD_RECT_ROP_COPY = 14, + SVGA_CMD_DEFINE_CURSOR = 19, + SVGA_CMD_DEFINE_ALPHA_CURSOR = 22, + SVGA_CMD_UPDATE_VERBOSE = 25, + SVGA_CMD_FRONT_ROP_FILL = 29, + SVGA_CMD_FENCE = 30, + SVGA_CMD_ESCAPE = 33, + SVGA_CMD_DEFINE_SCREEN = 34, + SVGA_CMD_DESTROY_SCREEN = 35, + SVGA_CMD_DEFINE_GMRFB = 36, + SVGA_CMD_BLIT_GMRFB_TO_SCREEN = 37, + SVGA_CMD_BLIT_SCREEN_TO_GMRFB = 38, + SVGA_CMD_ANNOTATION_FILL = 39, + SVGA_CMD_ANNOTATION_COPY = 40, + SVGA_CMD_DEFINE_GMR2 = 41, + SVGA_CMD_REMAP_GMR2 = 42, + SVGA_CMD_DEAD = 43, + SVGA_CMD_DEAD_2 = 44, + SVGA_CMD_NOP = 45, + SVGA_CMD_NOP_ERROR = 46, + SVGA_CMD_MAX } SVGAFifoCmdId; -#define SVGA_CMD_MAX_DATASIZE (256 * 1024) -#define SVGA_CMD_MAX_ARGS 64 - - -/* - * SVGA_CMD_UPDATE -- - * - * This is a DMA transfer which copies from the Guest Framebuffer - * (GFB) at BAR1 + SVGA_REG_FB_OFFSET to any screens which - * intersect with the provided virtual rectangle. - * - * This command does not support using arbitrary guest memory as a - * data source- it only works with the pre-defined GFB memory. - * This command also does not support signed virtual coordinates. - * If you have defined screens (using SVGA_CMD_DEFINE_SCREEN) with - * negative root x/y coordinates, the negative portion of those - * screens will not be reachable by this command. - * - * This command is not necessary when using framebuffer - * traces. Traces are automatically enabled if the SVGA FIFO is - * disabled, and you may explicitly enable/disable traces using - * SVGA_REG_TRACES. With traces enabled, any write to the GFB will - * automatically act as if a subsequent SVGA_CMD_UPDATE was issued. - * - * Traces and SVGA_CMD_UPDATE are the only supported ways to render - * pseudocolor screen updates. The newer Screen Object commands - * only support true color formats. - * - * Availability: - * Always available. - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 x; - uint32 y; - uint32 width; - uint32 height; -} -#include "vmware_pack_end.h" -SVGAFifoCmdUpdate; - - -/* - * SVGA_CMD_RECT_COPY -- - * - * Perform a rectangular DMA transfer from one area of the GFB to - * another, and copy the result to any screens which intersect it. - * - * Availability: - * SVGA_CAP_RECT_COPY - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 srcX; - uint32 srcY; - uint32 destX; - uint32 destY; - uint32 width; - uint32 height; -} -#include "vmware_pack_end.h" -SVGAFifoCmdRectCopy; - - -/* - * SVGA_CMD_RECT_ROP_COPY -- - * - * Perform a rectangular DMA transfer from one area of the GFB to - * another, and copy the result to any screens which intersect it. - * The value of ROP may only be SVGA_ROP_COPY, and this command is - * only supported for backwards compatibility reasons. - * - * Availability: - * SVGA_CAP_RECT_COPY - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 srcX; - uint32 srcY; - uint32 destX; - uint32 destY; - uint32 width; - uint32 height; - uint32 rop; -} -#include "vmware_pack_end.h" -SVGAFifoCmdRectRopCopy; - - -/* - * SVGA_CMD_DEFINE_CURSOR -- - * - * Provide a new cursor image, as an AND/XOR mask. - * - * The recommended way to position the cursor overlay is by using - * the SVGA_FIFO_CURSOR_* registers, supported by the - * SVGA_FIFO_CAP_CURSOR_BYPASS_3 capability. - * - * Availability: - * SVGA_CAP_CURSOR - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 id; /* Reserved, must be zero. */ - uint32 hotspotX; - uint32 hotspotY; - uint32 width; - uint32 height; - uint32 andMaskDepth; /* Value must be 1 or equal to BITS_PER_PIXEL */ - uint32 xorMaskDepth; /* Value must be 1 or equal to BITS_PER_PIXEL */ - /* - * Followed by scanline data for AND mask, then XOR mask. - * Each scanline is padded to a 32-bit boundary. - */ -} -#include "vmware_pack_end.h" -SVGAFifoCmdDefineCursor; - - -/* - * SVGA_CMD_DEFINE_ALPHA_CURSOR -- - * - * Provide a new cursor image, in 32-bit BGRA format. - * - * The recommended way to position the cursor overlay is by using - * the SVGA_FIFO_CURSOR_* registers, supported by the - * SVGA_FIFO_CAP_CURSOR_BYPASS_3 capability. - * - * Availability: - * SVGA_CAP_ALPHA_CURSOR - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 id; /* Reserved, must be zero. */ - uint32 hotspotX; - uint32 hotspotY; - uint32 width; - uint32 height; - /* Followed by scanline data */ -} -#include "vmware_pack_end.h" -SVGAFifoCmdDefineAlphaCursor; - - -/* - * Provide a new large cursor image, as an AND/XOR mask. - * - * Should only be used for CursorMob functionality - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 hotspotX; - uint32 hotspotY; - uint32 width; - uint32 height; - uint32 andMaskDepth; - uint32 xorMaskDepth; - /* - * Followed by scanline data for AND mask, then XOR mask. - * Each scanline is padded to a 32-bit boundary. - */ -} -#include "vmware_pack_end.h" -SVGAGBColorCursorHeader; - - -/* - * Provide a new large cursor image, in 32-bit BGRA format. - * - * Should only be used for CursorMob functionality - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 hotspotX; - uint32 hotspotY; - uint32 width; - uint32 height; - /* Followed by scanline data */ -} -#include "vmware_pack_end.h" -SVGAGBAlphaCursorHeader; - - /* - * Define the SVGA guest backed cursor types - */ +#define SVGA_CMD_MAX_DATASIZE (256 * 1024) +#define SVGA_CMD_MAX_ARGS 64 + +#pragma pack(push, 1) +typedef struct { + uint32 x; + uint32 y; + uint32 width; + uint32 height; +} SVGAFifoCmdUpdate; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 srcX; + uint32 srcY; + uint32 destX; + uint32 destY; + uint32 width; + uint32 height; +} SVGAFifoCmdRectCopy; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 srcX; + uint32 srcY; + uint32 destX; + uint32 destY; + uint32 width; + uint32 height; + uint32 rop; +} SVGAFifoCmdRectRopCopy; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 id; + uint32 hotspotX; + uint32 hotspotY; + uint32 width; + uint32 height; + uint32 andMaskDepth; + uint32 xorMaskDepth; + +} SVGAFifoCmdDefineCursor; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 id; + uint32 hotspotX; + uint32 hotspotY; + uint32 width; + uint32 height; + +} SVGAFifoCmdDefineAlphaCursor; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 hotspotX; + uint32 hotspotY; + uint32 width; + uint32 height; + uint32 andMaskDepth; + uint32 xorMaskDepth; + +} SVGAGBColorCursorHeader; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 hotspotX; + uint32 hotspotY; + uint32 width; + uint32 height; + +} SVGAGBAlphaCursorHeader; +#pragma pack(pop) typedef enum { - SVGA_COLOR_CURSOR = 0, - SVGA_ALPHA_CURSOR = 1, + SVGA_COLOR_CURSOR = 0, + SVGA_ALPHA_CURSOR = 1, } SVGAGBCursorType; -/* - * Provide a new large cursor image. - * - * Should only be used for CursorMob functionality - */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGAGBCursorType type; - union { - SVGAGBColorCursorHeader colorHeader; - SVGAGBAlphaCursorHeader alphaHeader; - } header; - uint32 sizeInBytes; - /* - * Followed by the cursor data - */ -} -#include "vmware_pack_end.h" -SVGAGBCursorHeader; - - -/* - * SVGA_CMD_UPDATE_VERBOSE -- - * - * Just like SVGA_CMD_UPDATE, but also provide a per-rectangle - * 'reason' value, an opaque cookie which is used by internal - * debugging tools. Third party drivers should not use this - * command. - * - * Availability: - * SVGA_CAP_EXTENDED_FIFO - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 x; - uint32 y; - uint32 width; - uint32 height; - uint32 reason; -} -#include "vmware_pack_end.h" -SVGAFifoCmdUpdateVerbose; - - -/* - * SVGA_CMD_FRONT_ROP_FILL -- - * - * This is a hint which tells the SVGA device that the driver has - * just filled a rectangular region of the GFB with a solid - * color. Instead of reading these pixels from the GFB, the device - * can assume that they all equal 'color'. This is primarily used - * for remote desktop protocols. - * - * Availability: - * SVGA_FIFO_CAP_ACCELFRONT - */ - -#define SVGA_ROP_COPY 0x03 - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 color; /* In the same format as the GFB */ - uint32 x; - uint32 y; - uint32 width; - uint32 height; - uint32 rop; /* Must be SVGA_ROP_COPY */ -} -#include "vmware_pack_end.h" -SVGAFifoCmdFrontRopFill; - - -/* - * SVGA_CMD_FENCE -- - * - * Insert a synchronization fence. When the SVGA device reaches - * this command, it will copy the 'fence' value into the - * SVGA_FIFO_FENCE register. It will also compare the fence against - * SVGA_FIFO_FENCE_GOAL. If the fence matches the goal and the - * SVGA_IRQFLAG_FENCE_GOAL interrupt is enabled, the device will - * raise this interrupt. - * - * Availability: - * SVGA_FIFO_FENCE for this command, - * SVGA_CAP_IRQMASK for SVGA_FIFO_FENCE_GOAL. - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 fence; -} -#include "vmware_pack_end.h" -SVGAFifoCmdFence; - - -/* - * SVGA_CMD_ESCAPE -- - * - * Send an extended or vendor-specific variable length command. - * This is used for video overlay, third party plugins, and - * internal debugging tools. See svga_escape.h - * - * Availability: - * SVGA_FIFO_CAP_ESCAPE - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 nsid; - uint32 size; - /* followed by 'size' bytes of data */ -} -#include "vmware_pack_end.h" -SVGAFifoCmdEscape; - - -/* - * SVGA_CMD_DEFINE_SCREEN -- - * - * Define or redefine an SVGAScreenObject. See the description of - * SVGAScreenObject above. The video driver is responsible for - * generating new screen IDs. They should be small positive - * integers. The virtual device will have an implementation - * specific upper limit on the number of screen IDs - * supported. Drivers are responsible for recycling IDs. The first - * valid ID is zero. - * - * - Interaction with other registers: - * - * For backwards compatibility, when the GFB mode registers (WIDTH, - * HEIGHT, PITCHLOCK, BITS_PER_PIXEL) are modified, the SVGA device - * deletes all screens other than screen #0, and redefines screen - * #0 according to the specified mode. Drivers that use - * SVGA_CMD_DEFINE_SCREEN should destroy or redefine screen #0. - * - * If you use screen objects, do not use the legacy multi-mon - * registers (SVGA_REG_NUM_GUEST_DISPLAYS, SVGA_REG_DISPLAY_*). - * - * Availability: - * SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2 - */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGAScreenObject screen; /* Variable-length according to version */ -} -#include "vmware_pack_end.h" -SVGAFifoCmdDefineScreen; - - -/* - * SVGA_CMD_DESTROY_SCREEN -- - * - * Destroy an SVGAScreenObject. Its ID is immediately available for - * re-use. - * - * Availability: - * SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2 - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 screenId; -} -#include "vmware_pack_end.h" -SVGAFifoCmdDestroyScreen; - - -/* - * SVGA_CMD_DEFINE_GMRFB -- - * - * This command sets a piece of SVGA device state called the - * Guest Memory Region Framebuffer, or GMRFB. The GMRFB is a - * piece of light-weight state which identifies the location and - * format of an image in guest memory or in BAR1. The GMRFB has - * an arbitrary size, and it doesn't need to match the geometry - * of the GFB or any screen object. - * - * The GMRFB can be redefined as often as you like. You could - * always use the same GMRFB, you could redefine it before - * rendering from a different guest screen, or you could even - * redefine it before every blit. - * - * There are multiple ways to use this command. The simplest way is - * to use it to move the framebuffer either to elsewhere in the GFB - * (BAR1) memory region, or to a user-defined GMR. This lets a - * driver use a framebuffer allocated entirely out of normal system - * memory, which we encourage. - * - * Another way to use this command is to set up a ring buffer of - * updates in GFB memory. If a driver wants to ensure that no - * frames are skipped by the SVGA device, it is important that the - * driver not modify the source data for a blit until the device is - * done processing the command. One efficient way to accomplish - * this is to use a ring of small DMA buffers. Each buffer is used - * for one blit, then we move on to the next buffer in the - * ring. The FENCE mechanism is used to protect each buffer from - * re-use until the device is finished with that buffer's - * corresponding blit. - * - * This command does not affect the meaning of SVGA_CMD_UPDATE. - * UPDATEs always occur from the legacy GFB memory area. This - * command has no support for pseudocolor GMRFBs. Currently only - * true-color 15, 16, and 24-bit depths are supported. Future - * devices may expose capabilities for additional framebuffer - * formats. - * - * The default GMRFB value is undefined. Drivers must always send - * this command at least once before performing any blit from the - * GMRFB. - * - * Availability: - * SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2 - */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGAGuestPtr ptr; - uint32 bytesPerLine; - SVGAGMRImageFormat format; -} -#include "vmware_pack_end.h" -SVGAFifoCmdDefineGMRFB; - - -/* - * SVGA_CMD_BLIT_GMRFB_TO_SCREEN -- - * - * This is a guest-to-host blit. It performs a DMA operation to - * copy a rectangular region of pixels from the current GMRFB to - * a ScreenObject. - * - * The destination coordinate may be specified relative to a - * screen's origin. The provided screen ID must be valid. - * - * The SVGA device is guaranteed to finish reading from the GMRFB - * by the time any subsequent FENCE commands are reached. - * - * This command consumes an annotation. See the - * SVGA_CMD_ANNOTATION_* commands for details. - * - * Availability: - * SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2 - */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGASignedPoint srcOrigin; - SVGASignedRect destRect; - uint32 destScreenId; -} -#include "vmware_pack_end.h" -SVGAFifoCmdBlitGMRFBToScreen; - - -/* - * SVGA_CMD_BLIT_SCREEN_TO_GMRFB -- - * - * This is a host-to-guest blit. It performs a DMA operation to - * copy a rectangular region of pixels from a single ScreenObject - * back to the current GMRFB. - * - * The source coordinate is specified relative to a screen's - * origin. The provided screen ID must be valid. If any parameters - * are invalid, the resulting pixel values are undefined. - * - * The SVGA device is guaranteed to finish writing to the GMRFB by - * the time any subsequent FENCE commands are reached. - * - * Availability: - * SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2 - */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGASignedPoint destOrigin; - SVGASignedRect srcRect; - uint32 srcScreenId; -} -#include "vmware_pack_end.h" -SVGAFifoCmdBlitScreenToGMRFB; - - -/* - * SVGA_CMD_ANNOTATION_FILL -- - * - * The annotation commands have been deprecated, should not be used - * by new drivers. They used to provide performance hints to the SVGA - * device about the content of screen updates, but newer SVGA devices - * ignore these. - * - * Availability: - * SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2 - */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGAColorBGRX color; -} -#include "vmware_pack_end.h" -SVGAFifoCmdAnnotationFill; - - -/* - * SVGA_CMD_ANNOTATION_COPY -- - * - * The annotation commands have been deprecated, should not be used - * by new drivers. They used to provide performance hints to the SVGA - * device about the content of screen updates, but newer SVGA devices - * ignore these. - * - * Availability: - * SVGA_FIFO_CAP_SCREEN_OBJECT or SVGA_FIFO_CAP_SCREEN_OBJECT_2 - */ - -typedef -#include "vmware_pack_begin.h" -struct { - SVGASignedPoint srcOrigin; - uint32 srcScreenId; -} -#include "vmware_pack_end.h" -SVGAFifoCmdAnnotationCopy; - - -/* - * SVGA_CMD_DEFINE_GMR2 -- - * - * Define guest memory region v2. See the description of GMRs above. - * - * Availability: - * SVGA_CAP_GMR2 - */ - -typedef -#include "vmware_pack_begin.h" -struct { - uint32 gmrId; - uint32 numPages; -} -#include "vmware_pack_end.h" -SVGAFifoCmdDefineGMR2; - - -/* - * SVGA_CMD_REMAP_GMR2 -- - * - * Remap guest memory region v2. See the description of GMRs above. - * - * This command allows guest to modify a portion of an existing GMR by - * invalidating it or reassigning it to different guest physical pages. - * The pages are identified by physical page number (PPN). The pages - * are assumed to be pinned and valid for DMA operations. - * - * Description of command flags: - * - * SVGA_REMAP_GMR2_VIA_GMR: If enabled, references a PPN list in a GMR. - * The PPN list must not overlap with the remap region (this can be - * handled trivially by referencing a separate GMR). If flag is - * disabled, PPN list is appended to SVGARemapGMR command. - * - * SVGA_REMAP_GMR2_PPN64: If set, PPN list is in PPN64 format, otherwise - * it is in PPN32 format. - * - * SVGA_REMAP_GMR2_SINGLE_PPN: If set, PPN list contains a single entry. - * A single PPN can be used to invalidate a portion of a GMR or - * map it to to a single guest scratch page. - * - * Availability: - * SVGA_CAP_GMR2 - */ +#pragma pack(push, 1) +typedef struct { + SVGAGBCursorType type; + union { + SVGAGBColorCursorHeader colorHeader; + SVGAGBAlphaCursorHeader alphaHeader; + } header; + uint32 sizeInBytes; + +} SVGAGBCursorHeader; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 x; + uint32 y; + uint32 width; + uint32 height; + uint32 reason; +} SVGAFifoCmdUpdateVerbose; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 color; + uint32 x; + uint32 y; + uint32 width; + uint32 height; + uint32 rop; +} SVGAFifoCmdFrontRopFill; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 fence; +} SVGAFifoCmdFence; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 nsid; + uint32 size; + +} SVGAFifoCmdEscape; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGAScreenObject screen; +} SVGAFifoCmdDefineScreen; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 screenId; +} SVGAFifoCmdDestroyScreen; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGAGuestPtr ptr; + uint32 bytesPerLine; + SVGAGMRImageFormat format; +} SVGAFifoCmdDefineGMRFB; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGASignedPoint srcOrigin; + SVGASignedRect destRect; + uint32 destScreenId; +} SVGAFifoCmdBlitGMRFBToScreen; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGASignedPoint destOrigin; + SVGASignedRect srcRect; + uint32 srcScreenId; +} SVGAFifoCmdBlitScreenToGMRFB; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGAColorBGRX color; +} SVGAFifoCmdAnnotationFill; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + SVGASignedPoint srcOrigin; + uint32 srcScreenId; +} SVGAFifoCmdAnnotationCopy; +#pragma pack(pop) + +#pragma pack(push, 1) +typedef struct { + uint32 gmrId; + uint32 numPages; +} SVGAFifoCmdDefineGMR2; +#pragma pack(pop) typedef enum { - SVGA_REMAP_GMR2_PPN32 = 0, - SVGA_REMAP_GMR2_VIA_GMR = (1 << 0), - SVGA_REMAP_GMR2_PPN64 = (1 << 1), - SVGA_REMAP_GMR2_SINGLE_PPN = (1 << 2), + SVGA_REMAP_GMR2_PPN32 = 0, + SVGA_REMAP_GMR2_VIA_GMR = (1 << 0), + SVGA_REMAP_GMR2_PPN64 = (1 << 1), + SVGA_REMAP_GMR2_SINGLE_PPN = (1 << 2), } SVGARemapGMR2Flags; -typedef -#include "vmware_pack_begin.h" -struct { - uint32 gmrId; - SVGARemapGMR2Flags flags; - uint32 offsetPages; /* offset in pages to begin remap */ - uint32 numPages; /* number of pages to remap */ - /* - * Followed by additional data depending on SVGARemapGMR2Flags. - * - * If flag SVGA_REMAP_GMR2_VIA_GMR is set, single SVGAGuestPtr follows. - * Otherwise an array of page descriptors in PPN32 or PPN64 format - * (according to flag SVGA_REMAP_GMR2_PPN64) follows. If flag - * SVGA_REMAP_GMR2_SINGLE_PPN is set, array contains a single entry. - */ -} -#include "vmware_pack_end.h" -SVGAFifoCmdRemapGMR2; - - -/* - * Size of SVGA device memory such as frame buffer and FIFO. - */ -#define SVGA_VRAM_MIN_SIZE (4 * 640 * 480) /* bytes */ -#define SVGA_VRAM_MIN_SIZE_3D (16 * 1024 * 1024) -#define SVGA_VRAM_MAX_SIZE (128 * 1024 * 1024) -#define SVGA_MEMORY_SIZE_MAX (1024 * 1024 * 1024) -#define SVGA_FIFO_SIZE_MAX (2 * 1024 * 1024) -#define SVGA_GRAPHICS_MEMORY_KB_MIN (32 * 1024) +#pragma pack(push, 1) +typedef struct { + uint32 gmrId; + SVGARemapGMR2Flags flags; + uint32 offsetPages; + uint32 numPages; + +} SVGAFifoCmdRemapGMR2; +#pragma pack(pop) + +#define SVGA_VRAM_MIN_SIZE (4 * 640 * 480) +#define SVGA_VRAM_MIN_SIZE_3D (16 * 1024 * 1024) +#define SVGA_VRAM_MAX_SIZE (128 * 1024 * 1024) +#define SVGA_MEMORY_SIZE_MAX (1024 * 1024 * 1024) +#define SVGA_FIFO_SIZE_MAX (2 * 1024 * 1024) +#define SVGA_GRAPHICS_MEMORY_KB_MIN (32 * 1024) #define SVGA_GRAPHICS_MEMORY_KB_MAX_2GB (2 * 1024 * 1024) #define SVGA_GRAPHICS_MEMORY_KB_MAX_3GB (3 * 1024 * 1024) #define SVGA_GRAPHICS_MEMORY_KB_MAX_4GB (4 * 1024 * 1024) #define SVGA_GRAPHICS_MEMORY_KB_MAX_8GB (8 * 1024 * 1024) #define SVGA_GRAPHICS_MEMORY_KB_DEFAULT (256 * 1024) -#define SVGA_VRAM_SIZE_W2K (64 * 1024 * 1024) /* 64 MB */ +#define SVGA_VRAM_SIZE_W2K (64 * 1024 * 1024) #if defined(VMX86_SERVER) -#define SVGA_VRAM_SIZE (4 * 1024 * 1024) -#define SVGA_VRAM_SIZE_3D (64 * 1024 * 1024) -#define SVGA_FIFO_SIZE (256 * 1024) -#define SVGA_FIFO_SIZE_3D (516 * 1024) -#define SVGA_MEMORY_SIZE_DEFAULT (160 * 1024 * 1024) -#define SVGA_AUTODETECT_DEFAULT FALSE +#define SVGA_VRAM_SIZE (4 * 1024 * 1024) +#define SVGA_VRAM_SIZE_3D (64 * 1024 * 1024) +#define SVGA_FIFO_SIZE (256 * 1024) +#define SVGA_FIFO_SIZE_3D (516 * 1024) +#define SVGA_MEMORY_SIZE_DEFAULT (160 * 1024 * 1024) +#define SVGA_AUTODETECT_DEFAULT FALSE #else -#define SVGA_VRAM_SIZE (16 * 1024 * 1024) -#define SVGA_VRAM_SIZE_3D SVGA_VRAM_MAX_SIZE -#define SVGA_FIFO_SIZE (2 * 1024 * 1024) -#define SVGA_FIFO_SIZE_3D SVGA_FIFO_SIZE -#define SVGA_MEMORY_SIZE_DEFAULT (768 * 1024 * 1024) -#define SVGA_AUTODETECT_DEFAULT TRUE +#define SVGA_VRAM_SIZE (16 * 1024 * 1024) +#define SVGA_VRAM_SIZE_3D SVGA_VRAM_MAX_SIZE +#define SVGA_FIFO_SIZE (2 * 1024 * 1024) +#define SVGA_FIFO_SIZE_3D SVGA_FIFO_SIZE +#define SVGA_MEMORY_SIZE_DEFAULT (768 * 1024 * 1024) +#define SVGA_AUTODETECT_DEFAULT TRUE #endif -#define SVGA_FIFO_SIZE_GBOBJECTS (256 * 1024) -#define SVGA_VRAM_SIZE_GBOBJECTS (4 * 1024 * 1024) - -#define SVGA_PCI_REGS_PAGES (1) +#define SVGA_FIFO_SIZE_GBOBJECTS (256 * 1024) +#define SVGA_VRAM_SIZE_GBOBJECTS (4 * 1024 * 1024) #endif diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_types.h b/drivers/gpu/drm/vmwgfx/device_include/svga_types.h deleted file mode 100644 index beddccee40f6..000000000000 --- a/drivers/gpu/drm/vmwgfx/device_include/svga_types.h +++ /dev/null @@ -1,51 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR MIT */ -/********************************************************** - * Copyright 2015 VMware, Inc. - * - * Permission is hereby granted, free of charge, to any person - * obtaining a copy of this software and associated documentation - * files (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, - * modify, merge, publish, distribute, sublicense, and/or sell copies - * of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be - * included in all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - * - **********************************************************/ -#ifndef _VM_BASIC_TYPES_H_ -#define _VM_BASIC_TYPES_H_ -#include <linux/kernel.h> - -typedef u32 uint32; -typedef s32 int32; -typedef u64 uint64; -typedef u16 uint16; -typedef s16 int16; -typedef u8 uint8; -typedef s8 int8; - -typedef uint64 PA; -typedef uint32 PPN; -typedef uint32 PPN32; -typedef uint64 PPN64; - -typedef bool Bool; - -#define MAX_UINT64 U64_MAX -#define MAX_UINT32 U32_MAX -#define MAX_UINT16 U16_MAX - -#define CONST64U(x) x##ULL - -#endif diff --git a/drivers/gpu/drm/vmwgfx/device_include/vm_basic_types.h b/drivers/gpu/drm/vmwgfx/device_include/vm_basic_types.h index 3a195e8106b3..35bd2852189f 100644 --- a/drivers/gpu/drm/vmwgfx/device_include/vm_basic_types.h +++ b/drivers/gpu/drm/vmwgfx/device_include/vm_basic_types.h @@ -1,7 +1,34 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _VM_BASIC_TYPES_H_ -#define _VM_BASIC_TYPES_H_ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/********************************************************** + * Copyright 2015-2021 VMware, Inc. + * + * Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, + * modify, merge, publish, distribute, sublicense, and/or sell copies + * of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + **********************************************************/ +#ifndef VM_BASIC_TYPES_H +#define VM_BASIC_TYPES_H + #include <linux/kernel.h> +#include <linux/mm.h> +#include <asm/page.h> typedef u32 uint32; typedef s32 int32; @@ -13,10 +40,108 @@ typedef s8 int8; typedef uint64 PA; typedef uint32 PPN; +typedef uint32 PPN32; typedef uint64 PPN64; typedef bool Bool; +#define MAX_UINT64 U64_MAX #define MAX_UINT32 U32_MAX +#define MAX_UINT16 U16_MAX + +#define CONST64U(x) x##ULL + +#ifndef MBYTES_SHIFT +#define MBYTES_SHIFT 20 +#endif +#ifndef MBYTES_2_BYTES +#define MBYTES_2_BYTES(_nbytes) ((uint64)(_nbytes) << MBYTES_SHIFT) +#endif + +/* + * MKS Guest Stats types + */ + +typedef struct MKSGuestStatCounter { + atomic64_t count; +} MKSGuestStatCounter; + +typedef struct MKSGuestStatCounterTime { + MKSGuestStatCounter counter; + atomic64_t selfCycles; + atomic64_t totalCycles; +} MKSGuestStatCounterTime; + +/* + * Flags for MKSGuestStatInfoEntry::flags below + */ + +#define MKS_GUEST_STAT_FLAG_NONE 0 +#define MKS_GUEST_STAT_FLAG_TIME (1U << 0) + +typedef __attribute__((aligned(32))) struct MKSGuestStatInfoEntry { + union { + const char *s; + uint64 u; + } name; + union { + const char *s; + uint64 u; + } description; + uint64 flags; + union { + MKSGuestStatCounter *counter; + MKSGuestStatCounterTime *counterTime; + uint64 u; + } stat; +} MKSGuestStatInfoEntry; + +#define INVALID_PPN64 ((PPN64)0x000fffffffffffffULL) +#define vmw_num_pages(size) (PAGE_ALIGN(size) >> PAGE_SHIFT) + +#define MKS_GUEST_STAT_INSTANCE_DESC_LENGTH 1024 +#define MKS_GUEST_STAT_INSTANCE_MAX_STATS 4096 +#define MKS_GUEST_STAT_INSTANCE_MAX_STAT_PPNS \ + (vmw_num_pages(MKS_GUEST_STAT_INSTANCE_MAX_STATS * \ + sizeof(MKSGuestStatCounterTime))) +#define MKS_GUEST_STAT_INSTANCE_MAX_INFO_PPNS \ + (vmw_num_pages(MKS_GUEST_STAT_INSTANCE_MAX_STATS * \ + sizeof(MKSGuestStatInfoEntry))) +#define MKS_GUEST_STAT_AVERAGE_NAME_LENGTH 40 +#define MKS_GUEST_STAT_INSTANCE_MAX_STRS_PPNS \ + (vmw_num_pages(MKS_GUEST_STAT_INSTANCE_MAX_STATS * \ + MKS_GUEST_STAT_AVERAGE_NAME_LENGTH)) + +/* + * The MKSGuestStatInstanceDescriptor is used as main interface to + * communicate guest stats back to the host code. The guest must + * allocate an instance of this structure at the start of a page and + * provide the physical address to the host. From there the host code + * can walk this structure to find other (pinned) pages containing the + * stats data. + * + * Since the MKSGuestStatInfoEntry structures contain userlevel + * pointers, the InstanceDescriptor also contains pointers to the + * begining of these sections allowing the host side code to correctly + * interpret the pointers. + * + * Because the host side code never acknowledges anything back to the + * guest there is no strict requirement to maintain compatability + * across releases. If the interface changes the host might not be + * able to log stats, but the guest will continue to run normally. + */ + +typedef struct MKSGuestStatInstanceDescriptor { + uint64 reservedMBZ; /* must be zero for now. */ + uint64 statStartVA; /* VA of the start of the stats section. */ + uint64 strsStartVA; /* VA of the start of the strings section. */ + uint64 statLength; /* length of the stats section in bytes. */ + uint64 infoLength; /* length of the info entry section in bytes. */ + uint64 strsLength; /* length of the strings section in bytes. */ + PPN64 statPPNs[MKS_GUEST_STAT_INSTANCE_MAX_STAT_PPNS]; /* stat counters */ + PPN64 infoPPNs[MKS_GUEST_STAT_INSTANCE_MAX_INFO_PPNS]; /* stat info */ + PPN64 strsPPNs[MKS_GUEST_STAT_INSTANCE_MAX_STRS_PPNS]; /* strings */ + char description[MKS_GUEST_STAT_INSTANCE_DESC_LENGTH]; +} MKSGuestStatInstanceDescriptor; #endif diff --git a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_begin.h b/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_begin.h deleted file mode 100644 index 75308bd0d970..000000000000 --- a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_begin.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <linux/compiler.h> diff --git a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_end.h b/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_end.h deleted file mode 100644 index e93d6f28b68c..000000000000 --- a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_end.h +++ /dev/null @@ -1,2 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -__packed diff --git a/drivers/gpu/drm/vmwgfx/ttm_memory.c b/drivers/gpu/drm/vmwgfx/ttm_memory.c index aeb0a22a2c34..edd17c30d5a5 100644 --- a/drivers/gpu/drm/vmwgfx/ttm_memory.c +++ b/drivers/gpu/drm/vmwgfx/ttm_memory.c @@ -435,8 +435,10 @@ int ttm_mem_global_init(struct ttm_mem_global *glob, struct device *dev) si_meminfo(&si); + spin_lock(&glob->lock); /* set it as 0 by default to keep original behavior of OOM */ glob->lower_mem_limit = 0; + spin_unlock(&glob->lock); ret = ttm_mem_init_kernel_zone(glob, &si); if (unlikely(ret != 0)) diff --git a/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h b/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h new file mode 100644 index 000000000000..b0d87c5f58d8 --- /dev/null +++ b/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h @@ -0,0 +1,539 @@ +/********************************************************** + * Copyright 2021 VMware, Inc. + * SPDX-License-Identifier: GPL-2.0 OR MIT + * + * Permission is hereby granted, free of charge, to any person + * obtaining a copy of this software and associated documentation + * files (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, + * modify, merge, publish, distribute, sublicense, and/or sell copies + * of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be + * included in all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + **********************************************************/ + +#ifndef VMW_SURFACE_CACHE_H +#define VMW_SURFACE_CACHE_H + +#include "device_include/svga3d_surfacedefs.h" + +#include <drm/vmwgfx_drm.h> + +static inline u32 clamped_umul32(u32 a, u32 b) +{ + uint64_t tmp = (uint64_t) a*b; + return (tmp > (uint64_t) ((u32) -1)) ? (u32) -1 : tmp; +} + +/** + * vmw_surface_get_desc - Look up the appropriate SVGA3dSurfaceDesc for the + * given format. + */ +static inline const SVGA3dSurfaceDesc * +vmw_surface_get_desc(SVGA3dSurfaceFormat format) +{ + if (format < ARRAY_SIZE(g_SVGA3dSurfaceDescs)) + return &g_SVGA3dSurfaceDescs[format]; + + return &g_SVGA3dSurfaceDescs[SVGA3D_FORMAT_INVALID]; +} + +/** + * vmw_surface_get_mip_size - Given a base level size and the mip level, + * compute the size of the mip level. + */ +static inline struct drm_vmw_size +vmw_surface_get_mip_size(struct drm_vmw_size base_level, u32 mip_level) +{ + struct drm_vmw_size size = { + .width = max_t(u32, base_level.width >> mip_level, 1), + .height = max_t(u32, base_level.height >> mip_level, 1), + .depth = max_t(u32, base_level.depth >> mip_level, 1) + }; + + return size; +} + +static inline void +vmw_surface_get_size_in_blocks(const SVGA3dSurfaceDesc *desc, + const struct drm_vmw_size *pixel_size, + SVGA3dSize *block_size) +{ + block_size->width = __KERNEL_DIV_ROUND_UP(pixel_size->width, + desc->blockSize.width); + block_size->height = __KERNEL_DIV_ROUND_UP(pixel_size->height, + desc->blockSize.height); + block_size->depth = __KERNEL_DIV_ROUND_UP(pixel_size->depth, + desc->blockSize.depth); +} + +static inline bool +vmw_surface_is_planar_surface(const SVGA3dSurfaceDesc *desc) +{ + return (desc->blockDesc & SVGA3DBLOCKDESC_PLANAR_YUV) != 0; +} + +static inline u32 +vmw_surface_calculate_pitch(const SVGA3dSurfaceDesc *desc, + const struct drm_vmw_size *size) +{ + u32 pitch; + SVGA3dSize blocks; + + vmw_surface_get_size_in_blocks(desc, size, &blocks); + + pitch = blocks.width * desc->pitchBytesPerBlock; + + return pitch; +} + +/** + * vmw_surface_get_image_buffer_size - Calculates image buffer size. + * + * Return the number of bytes of buffer space required to store one image of a + * surface, optionally using the specified pitch. + * + * If pitch is zero, it is assumed that rows are tightly packed. + * + * This function is overflow-safe. If the result would have overflowed, instead + * we return MAX_UINT32. + */ +static inline u32 +vmw_surface_get_image_buffer_size(const SVGA3dSurfaceDesc *desc, + const struct drm_vmw_size *size, + u32 pitch) +{ + SVGA3dSize image_blocks; + u32 slice_size, total_size; + + vmw_surface_get_size_in_blocks(desc, size, &image_blocks); + + if (vmw_surface_is_planar_surface(desc)) { + total_size = clamped_umul32(image_blocks.width, + image_blocks.height); + total_size = clamped_umul32(total_size, image_blocks.depth); + total_size = clamped_umul32(total_size, desc->bytesPerBlock); + return total_size; + } + + if (pitch == 0) + pitch = vmw_surface_calculate_pitch(desc, size); + + slice_size = clamped_umul32(image_blocks.height, pitch); + total_size = clamped_umul32(slice_size, image_blocks.depth); + + return total_size; +} + +/** + * vmw_surface_get_serialized_size - Get the serialized size for the image. + */ +static inline u32 +vmw_surface_get_serialized_size(SVGA3dSurfaceFormat format, + struct drm_vmw_size base_level_size, + u32 num_mip_levels, + u32 num_layers) +{ + const SVGA3dSurfaceDesc *desc = vmw_surface_get_desc(format); + u32 total_size = 0; + u32 mip; + + for (mip = 0; mip < num_mip_levels; mip++) { + struct drm_vmw_size size = + vmw_surface_get_mip_size(base_level_size, mip); + total_size += vmw_surface_get_image_buffer_size(desc, + &size, 0); + } + + return total_size * num_layers; +} + +/** + * vmw_surface_get_serialized_size_extended - Returns the number of bytes + * required for a surface with given parameters. Support for sample count. + */ +static inline u32 +vmw_surface_get_serialized_size_extended(SVGA3dSurfaceFormat format, + struct drm_vmw_size base_level_size, + u32 num_mip_levels, + u32 num_layers, + u32 num_samples) +{ + uint64_t total_size = + vmw_surface_get_serialized_size(format, + base_level_size, + num_mip_levels, + num_layers); + total_size *= max_t(u32, 1, num_samples); + + return min_t(uint64_t, total_size, (uint64_t)U32_MAX); +} + +/** + * vmw_surface_get_pixel_offset - Compute the offset (in bytes) to a pixel + * in an image (or volume). + * + * @width: The image width in pixels. + * @height: The image height in pixels + */ +static inline u32 +vmw_surface_get_pixel_offset(SVGA3dSurfaceFormat format, + u32 width, u32 height, + u32 x, u32 y, u32 z) +{ + const SVGA3dSurfaceDesc *desc = vmw_surface_get_desc(format); + const u32 bw = desc->blockSize.width, bh = desc->blockSize.height; + const u32 bd = desc->blockSize.depth; + const u32 rowstride = __KERNEL_DIV_ROUND_UP(width, bw) * + desc->bytesPerBlock; + const u32 imgstride = __KERNEL_DIV_ROUND_UP(height, bh) * rowstride; + const u32 offset = (z / bd * imgstride + + y / bh * rowstride + + x / bw * desc->bytesPerBlock); + return offset; +} + +static inline u32 +vmw_surface_get_image_offset(SVGA3dSurfaceFormat format, + struct drm_vmw_size baseLevelSize, + u32 numMipLevels, + u32 face, + u32 mip) + +{ + u32 offset; + u32 mipChainBytes; + u32 mipChainBytesToLevel; + u32 i; + const SVGA3dSurfaceDesc *desc; + struct drm_vmw_size mipSize; + u32 bytes; + + desc = vmw_surface_get_desc(format); + + mipChainBytes = 0; + mipChainBytesToLevel = 0; + for (i = 0; i < numMipLevels; i++) { + mipSize = vmw_surface_get_mip_size(baseLevelSize, i); + bytes = vmw_surface_get_image_buffer_size(desc, &mipSize, 0); + mipChainBytes += bytes; + if (i < mip) + mipChainBytesToLevel += bytes; + } + + offset = mipChainBytes * face + mipChainBytesToLevel; + + return offset; +} + + +/** + * vmw_surface_is_gb_screen_target_format - Is the specified format usable as + * a ScreenTarget? + * (with just the GBObjects cap-bit + * set) + * @format: format to queried + * + * RETURNS: + * true if queried format is valid for screen targets + */ +static inline bool +vmw_surface_is_gb_screen_target_format(SVGA3dSurfaceFormat format) +{ + return (format == SVGA3D_X8R8G8B8 || + format == SVGA3D_A8R8G8B8 || + format == SVGA3D_R5G6B5 || + format == SVGA3D_X1R5G5B5 || + format == SVGA3D_A1R5G5B5 || + format == SVGA3D_P8); +} + + +/** + * vmw_surface_is_dx_screen_target_format - Is the specified format usable as + * a ScreenTarget? + * (with DX10 enabled) + * + * @format: format to queried + * + * Results: + * true if queried format is valid for screen targets + */ +static inline bool +vmw_surface_is_dx_screen_target_format(SVGA3dSurfaceFormat format) +{ + return (format == SVGA3D_R8G8B8A8_UNORM || + format == SVGA3D_B8G8R8A8_UNORM || + format == SVGA3D_B8G8R8X8_UNORM); +} + + +/** + * vmw_surface_is_screen_target_format - Is the specified format usable as a + * ScreenTarget? + * (for some combination of caps) + * + * @format: format to queried + * + * Results: + * true if queried format is valid for screen targets + */ +static inline bool +vmw_surface_is_screen_target_format(SVGA3dSurfaceFormat format) +{ + if (vmw_surface_is_gb_screen_target_format(format)) { + return true; + } + return vmw_surface_is_dx_screen_target_format(format); +} + +/** + * struct vmw_surface_mip - Mimpmap level information + * @bytes: Bytes required in the backing store of this mipmap level. + * @img_stride: Byte stride per image. + * @row_stride: Byte stride per block row. + * @size: The size of the mipmap. + */ +struct vmw_surface_mip { + size_t bytes; + size_t img_stride; + size_t row_stride; + struct drm_vmw_size size; + +}; + +/** + * struct vmw_surface_cache - Cached surface information + * @desc: Pointer to the surface descriptor + * @mip: Array of mipmap level information. Valid size is @num_mip_levels. + * @mip_chain_bytes: Bytes required in the backing store for the whole chain + * of mip levels. + * @sheet_bytes: Bytes required in the backing store for a sheet + * representing a single sample. + * @num_mip_levels: Valid size of the @mip array. Number of mipmap levels in + * a chain. + * @num_layers: Number of slices in an array texture or number of faces in + * a cubemap texture. + */ +struct vmw_surface_cache { + const SVGA3dSurfaceDesc *desc; + struct vmw_surface_mip mip[DRM_VMW_MAX_MIP_LEVELS]; + size_t mip_chain_bytes; + size_t sheet_bytes; + u32 num_mip_levels; + u32 num_layers; +}; + +/** + * struct vmw_surface_loc - Surface location + * @sheet: The multisample sheet. + * @sub_resource: Surface subresource. Defined as layer * num_mip_levels + + * mip_level. + * @x: X coordinate. + * @y: Y coordinate. + * @z: Z coordinate. + */ +struct vmw_surface_loc { + u32 sheet; + u32 sub_resource; + u32 x, y, z; +}; + +/** + * vmw_surface_subres - Compute the subresource from layer and mipmap. + * @cache: Surface layout data. + * @mip_level: The mipmap level. + * @layer: The surface layer (face or array slice). + * + * Return: The subresource. + */ +static inline u32 vmw_surface_subres(const struct vmw_surface_cache *cache, + u32 mip_level, u32 layer) +{ + return cache->num_mip_levels * layer + mip_level; +} + +/** + * vmw_surface_setup_cache - Build a surface cache entry + * @size: The surface base level dimensions. + * @format: The surface format. + * @num_mip_levels: Number of mipmap levels. + * @num_layers: Number of layers. + * @cache: Pointer to a struct vmw_surface_cach object to be filled in. + * + * Return: Zero on success, -EINVAL on invalid surface layout. + */ +static inline int vmw_surface_setup_cache(const struct drm_vmw_size *size, + SVGA3dSurfaceFormat format, + u32 num_mip_levels, + u32 num_layers, + u32 num_samples, + struct vmw_surface_cache *cache) +{ + const SVGA3dSurfaceDesc *desc; + u32 i; + + memset(cache, 0, sizeof(*cache)); + cache->desc = desc = vmw_surface_get_desc(format); + cache->num_mip_levels = num_mip_levels; + cache->num_layers = num_layers; + for (i = 0; i < cache->num_mip_levels; i++) { + struct vmw_surface_mip *mip = &cache->mip[i]; + + mip->size = vmw_surface_get_mip_size(*size, i); + mip->bytes = vmw_surface_get_image_buffer_size + (desc, &mip->size, 0); + mip->row_stride = + __KERNEL_DIV_ROUND_UP(mip->size.width, + desc->blockSize.width) * + desc->bytesPerBlock * num_samples; + if (!mip->row_stride) + goto invalid_dim; + + mip->img_stride = + __KERNEL_DIV_ROUND_UP(mip->size.height, + desc->blockSize.height) * + mip->row_stride; + if (!mip->img_stride) + goto invalid_dim; + + cache->mip_chain_bytes += mip->bytes; + } + cache->sheet_bytes = cache->mip_chain_bytes * num_layers; + if (!cache->sheet_bytes) + goto invalid_dim; + + return 0; + +invalid_dim: + VMW_DEBUG_USER("Invalid surface layout for dirty tracking.\n"); + return -EINVAL; +} + +/** + * vmw_surface_get_loc - Get a surface location from an offset into the + * backing store + * @cache: Surface layout data. + * @loc: Pointer to a struct vmw_surface_loc to be filled in. + * @offset: Offset into the surface backing store. + */ +static inline void +vmw_surface_get_loc(const struct vmw_surface_cache *cache, + struct vmw_surface_loc *loc, + size_t offset) +{ + const struct vmw_surface_mip *mip = &cache->mip[0]; + const SVGA3dSurfaceDesc *desc = cache->desc; + u32 layer; + int i; + + loc->sheet = offset / cache->sheet_bytes; + offset -= loc->sheet * cache->sheet_bytes; + + layer = offset / cache->mip_chain_bytes; + offset -= layer * cache->mip_chain_bytes; + for (i = 0; i < cache->num_mip_levels; ++i, ++mip) { + if (mip->bytes > offset) + break; + offset -= mip->bytes; + } + + loc->sub_resource = vmw_surface_subres(cache, i, layer); + loc->z = offset / mip->img_stride; + offset -= loc->z * mip->img_stride; + loc->z *= desc->blockSize.depth; + loc->y = offset / mip->row_stride; + offset -= loc->y * mip->row_stride; + loc->y *= desc->blockSize.height; + loc->x = offset / desc->bytesPerBlock; + loc->x *= desc->blockSize.width; +} + +/** + * vmw_surface_inc_loc - Clamp increment a surface location with one block + * size + * in each dimension. + * @loc: Pointer to a struct vmw_surface_loc to be incremented. + * + * When computing the size of a range as size = end - start, the range does not + * include the end element. However a location representing the last byte + * of a touched region in the backing store *is* included in the range. + * This function modifies such a location to match the end definition + * given as start + size which is the one used in a SVGA3dBox. + */ +static inline void +vmw_surface_inc_loc(const struct vmw_surface_cache *cache, + struct vmw_surface_loc *loc) +{ + const SVGA3dSurfaceDesc *desc = cache->desc; + u32 mip = loc->sub_resource % cache->num_mip_levels; + const struct drm_vmw_size *size = &cache->mip[mip].size; + + loc->sub_resource++; + loc->x += desc->blockSize.width; + if (loc->x > size->width) + loc->x = size->width; + loc->y += desc->blockSize.height; + if (loc->y > size->height) + loc->y = size->height; + loc->z += desc->blockSize.depth; + if (loc->z > size->depth) + loc->z = size->depth; +} + +/** + * vmw_surface_min_loc - The start location in a subresource + * @cache: Surface layout data. + * @sub_resource: The subresource. + * @loc: Pointer to a struct vmw_surface_loc to be filled in. + */ +static inline void +vmw_surface_min_loc(const struct vmw_surface_cache *cache, + u32 sub_resource, + struct vmw_surface_loc *loc) +{ + loc->sheet = 0; + loc->sub_resource = sub_resource; + loc->x = loc->y = loc->z = 0; +} + +/** + * vmw_surface_min_loc - The end location in a subresource + * @cache: Surface layout data. + * @sub_resource: The subresource. + * @loc: Pointer to a struct vmw_surface_loc to be filled in. + * + * Following the end definition given in vmw_surface_inc_loc(), + * Compute the end location of a surface subresource. + */ +static inline void +vmw_surface_max_loc(const struct vmw_surface_cache *cache, + u32 sub_resource, + struct vmw_surface_loc *loc) +{ + const struct drm_vmw_size *size; + u32 mip; + + loc->sheet = 0; + loc->sub_resource = sub_resource + 1; + mip = sub_resource % cache->num_mip_levels; + size = &cache->mip[mip].size; + loc->x = size->width; + loc->y = size->height; + loc->z = size->depth; +} + + +#endif /* VMW_SURFACE_CACHE_H */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c index 05b324825900..6f27d69bad0e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c @@ -715,7 +715,7 @@ static int vmw_binding_scrub_cb(struct vmw_ctx_bindinfo *bi, bool rebind) * without checking which bindings actually need to be emitted * * @cbs: Pointer to the context's struct vmw_ctx_binding_state - * @bi: Pointer to where the binding info array is stored in @cbs + * @biv: Pointer to where the binding info array is stored in @cbs * @max_num: Maximum number of entries in the @bi array. * * Scans the @bi array for bindings and builds a buffer of view id data. @@ -725,11 +725,9 @@ static int vmw_binding_scrub_cb(struct vmw_ctx_bindinfo *bi, bool rebind) * contains the command data. */ static void vmw_collect_view_ids(struct vmw_ctx_binding_state *cbs, - const struct vmw_ctx_bindinfo *bi, + const struct vmw_ctx_bindinfo_view *biv, u32 max_num) { - const struct vmw_ctx_bindinfo_view *biv = - container_of(bi, struct vmw_ctx_bindinfo_view, bi); unsigned long i; cbs->bind_cmd_count = 0; @@ -838,7 +836,7 @@ static int vmw_emit_set_sr(struct vmw_ctx_binding_state *cbs, */ static int vmw_emit_set_rt(struct vmw_ctx_binding_state *cbs) { - const struct vmw_ctx_bindinfo *loc = &cbs->render_targets[0].bi; + const struct vmw_ctx_bindinfo_view *loc = &cbs->render_targets[0]; struct { SVGA3dCmdHeader header; SVGA3dCmdDXSetRenderTargets body; @@ -846,7 +844,7 @@ static int vmw_emit_set_rt(struct vmw_ctx_binding_state *cbs) size_t cmd_size, view_id_size; const struct vmw_resource *ctx = vmw_cbs_context(cbs); - vmw_collect_view_ids(cbs, loc, SVGA3D_MAX_SIMULTANEOUS_RENDER_TARGETS); + vmw_collect_view_ids(cbs, loc, SVGA3D_DX_MAX_RENDER_TARGETS); view_id_size = cbs->bind_cmd_count*sizeof(uint32); cmd_size = sizeof(*cmd) + view_id_size; cmd = VMW_CMD_CTX_RESERVE(ctx->dev_priv, cmd_size, ctx->id); @@ -874,7 +872,7 @@ static int vmw_emit_set_rt(struct vmw_ctx_binding_state *cbs) * without checking which bindings actually need to be emitted * * @cbs: Pointer to the context's struct vmw_ctx_binding_state - * @bi: Pointer to where the binding info array is stored in @cbs + * @biso: Pointer to where the binding info array is stored in @cbs * @max_num: Maximum number of entries in the @bi array. * * Scans the @bi array for bindings and builds a buffer of SVGA3dSoTarget data. @@ -884,11 +882,9 @@ static int vmw_emit_set_rt(struct vmw_ctx_binding_state *cbs) * contains the command data. */ static void vmw_collect_so_targets(struct vmw_ctx_binding_state *cbs, - const struct vmw_ctx_bindinfo *bi, + const struct vmw_ctx_bindinfo_so_target *biso, u32 max_num) { - const struct vmw_ctx_bindinfo_so_target *biso = - container_of(bi, struct vmw_ctx_bindinfo_so_target, bi); unsigned long i; SVGA3dSoTarget *so_buffer = (SVGA3dSoTarget *) cbs->bind_cmd_buffer; @@ -919,7 +915,7 @@ static void vmw_collect_so_targets(struct vmw_ctx_binding_state *cbs, */ static int vmw_emit_set_so_target(struct vmw_ctx_binding_state *cbs) { - const struct vmw_ctx_bindinfo *loc = &cbs->so_targets[0].bi; + const struct vmw_ctx_bindinfo_so_target *loc = &cbs->so_targets[0]; struct { SVGA3dCmdHeader header; SVGA3dCmdDXSetSOTargets body; @@ -1066,7 +1062,7 @@ static int vmw_emit_set_vb(struct vmw_ctx_binding_state *cbs) static int vmw_emit_set_uav(struct vmw_ctx_binding_state *cbs) { - const struct vmw_ctx_bindinfo *loc = &cbs->ua_views[0].views[0].bi; + const struct vmw_ctx_bindinfo_view *loc = &cbs->ua_views[0].views[0]; struct { SVGA3dCmdHeader header; SVGA3dCmdDXSetUAViews body; @@ -1096,7 +1092,7 @@ static int vmw_emit_set_uav(struct vmw_ctx_binding_state *cbs) static int vmw_emit_set_cs_uav(struct vmw_ctx_binding_state *cbs) { - const struct vmw_ctx_bindinfo *loc = &cbs->ua_views[1].views[0].bi; + const struct vmw_ctx_bindinfo_view *loc = &cbs->ua_views[1].views[0]; struct { SVGA3dCmdHeader header; SVGA3dCmdDXSetCSUAViews body; @@ -1444,7 +1440,7 @@ u32 vmw_binding_dirtying(enum vmw_ctx_binding_type binding_type) static void vmw_binding_build_asserts(void) { BUILD_BUG_ON(SVGA3D_NUM_SHADERTYPE_DX10 != 3); - BUILD_BUG_ON(SVGA3D_MAX_SIMULTANEOUS_RENDER_TARGETS > SVGA3D_RT_MAX); + BUILD_BUG_ON(SVGA3D_DX_MAX_RENDER_TARGETS > SVGA3D_RT_MAX); BUILD_BUG_ON(sizeof(uint32) != sizeof(u32)); /* diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c index 956b85e35cef..30a837b5baa6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c @@ -30,6 +30,7 @@ #include <drm/ttm/ttm_placement.h> #include "vmwgfx_drv.h" +#include "vmwgfx_devcaps.h" bool vmw_supports_3d(struct vmw_private *dev_priv) { @@ -45,10 +46,7 @@ bool vmw_supports_3d(struct vmw_private *dev_priv) if (!dev_priv->has_mob) return false; - spin_lock(&dev_priv->cap_lock); - vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_3D); - result = vmw_read(dev_priv, SVGA_REG_DEV_CAP); - spin_unlock(&dev_priv->cap_lock); + result = vmw_devcap_get(dev_priv, SVGA3D_DEVCAP_3D); return (result != 0); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c index 6bb4961e64a5..9656d4a2abff 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c @@ -516,7 +516,7 @@ static void vmw_cmdbuf_work_func(struct work_struct *work) struct vmw_cmdbuf_man *man = container_of(work, struct vmw_cmdbuf_man, work); struct vmw_cmdbuf_header *entry, *next; - uint32_t dummy; + uint32_t dummy = 0; bool send_fence = false; struct list_head restart_head[SVGA_CB_CONTEXT_MAX]; int i; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c index b262d61d839d..9487faff5229 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c @@ -159,6 +159,7 @@ void vmw_cmdbuf_res_commit(struct list_head *list) void vmw_cmdbuf_res_revert(struct list_head *list) { struct vmw_cmdbuf_res *entry, *next; + int ret; list_for_each_entry_safe(entry, next, list, head) { switch (entry->state) { @@ -166,7 +167,8 @@ void vmw_cmdbuf_res_revert(struct list_head *list) vmw_cmdbuf_res_free(entry->man, entry); break; case VMW_CMDBUF_RES_DEL: - drm_ht_insert_item(&entry->man->resources, &entry->hash); + ret = drm_ht_insert_item(&entry->man->resources, &entry->hash); + BUG_ON(ret); list_del(&entry->head); list_add_tail(&entry->head, &entry->man->list); entry->state = VMW_CMDBUF_RES_COMMITTED; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c index dffe3804ad3e..4446758b6880 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c @@ -185,7 +185,7 @@ static int vmw_gb_context_init(struct vmw_private *dev_priv, container_of(res, struct vmw_user_context, res); res->backup_size = (dx ? sizeof(SVGADXContextMobFormat) : - SVGA3D_CONTEXT_DATA_SIZE); + sizeof(SVGAGBContextData)); ret = vmw_resource_init(dev_priv, res, true, res_free, dx ? &vmw_dx_context_func : @@ -259,7 +259,7 @@ static int vmw_context_init(struct vmw_private *dev_priv, goto out_early; } - if (unlikely(res->id >= SVGA3D_MAX_CONTEXT_IDS)) { + if (unlikely(res->id >= SVGA3D_HB_MAX_CONTEXT_IDS)) { DRM_ERROR("Out of hw context ids.\n"); vmw_resource_unreference(&res); return -ENOMEM; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.c b/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.c new file mode 100644 index 000000000000..829df395c2ed --- /dev/null +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.c @@ -0,0 +1,142 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/************************************************************************** + * + * Copyright 2021 VMware, Inc., Palo Alto, CA., USA + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + **************************************************************************/ + +#include "vmwgfx_devcaps.h" + +#include "vmwgfx_drv.h" + + +struct svga_3d_compat_cap { + SVGA3dFifoCapsRecordHeader header; + SVGA3dFifoCapPair pairs[SVGA3D_DEVCAP_MAX]; +}; + + +static u32 vmw_mask_legacy_multisample(unsigned int cap, u32 fmt_value) +{ + /* + * A version of user-space exists which use MULTISAMPLE_MASKABLESAMPLES + * to check the sample count supported by virtual device. Since there + * never was support for multisample count for backing MOB return 0. + * + * MULTISAMPLE_MASKABLESAMPLES devcap is marked as deprecated by virtual + * device. + */ + if (cap == SVGA3D_DEVCAP_DEAD5) + return 0; + + return fmt_value; +} + +static int vmw_fill_compat_cap(struct vmw_private *dev_priv, void *bounce, + size_t size) +{ + struct svga_3d_compat_cap *compat_cap = + (struct svga_3d_compat_cap *) bounce; + unsigned int i; + size_t pair_offset = offsetof(struct svga_3d_compat_cap, pairs); + unsigned int max_size; + + if (size < pair_offset) + return -EINVAL; + + max_size = (size - pair_offset) / sizeof(SVGA3dFifoCapPair); + + if (max_size > SVGA3D_DEVCAP_MAX) + max_size = SVGA3D_DEVCAP_MAX; + + compat_cap->header.length = + (pair_offset + max_size * sizeof(SVGA3dFifoCapPair)) / sizeof(u32); + compat_cap->header.type = SVGA3D_FIFO_CAPS_RECORD_DEVCAPS; + + for (i = 0; i < max_size; ++i) { + compat_cap->pairs[i][0] = i; + compat_cap->pairs[i][1] = vmw_mask_legacy_multisample + (i, dev_priv->devcaps[i]); + } + + return 0; +} + +int vmw_devcaps_create(struct vmw_private *vmw) +{ + bool gb_objects = !!(vmw->capabilities & SVGA_CAP_GBOBJECTS); + uint32_t i; + + if (gb_objects) { + vmw->devcaps = vzalloc(sizeof(uint32_t) * SVGA3D_DEVCAP_MAX); + if (!vmw->devcaps) + return -ENOMEM; + for (i = 0; i < SVGA3D_DEVCAP_MAX; ++i) { + vmw_write(vmw, SVGA_REG_DEV_CAP, i); + vmw->devcaps[i] = vmw_read(vmw, SVGA_REG_DEV_CAP); + } + } + return 0; +} + +void vmw_devcaps_destroy(struct vmw_private *vmw) +{ + vfree(vmw->devcaps); + vmw->devcaps = NULL; +} + + +uint32 vmw_devcaps_size(const struct vmw_private *vmw, + bool gb_aware) +{ + bool gb_objects = !!(vmw->capabilities & SVGA_CAP_GBOBJECTS); + if (gb_objects && gb_aware) + return SVGA3D_DEVCAP_MAX * sizeof(uint32_t); + else if (gb_objects) + return sizeof(struct svga_3d_compat_cap) + + sizeof(uint32_t); + else if (vmw->fifo_mem != NULL) + return (SVGA_FIFO_3D_CAPS_LAST - SVGA_FIFO_3D_CAPS + 1) * + sizeof(uint32_t); + else + return 0; +} + +int vmw_devcaps_copy(struct vmw_private *vmw, bool gb_aware, + void *dst, uint32_t dst_size) +{ + int ret; + bool gb_objects = !!(vmw->capabilities & SVGA_CAP_GBOBJECTS); + if (gb_objects && gb_aware) { + memcpy(dst, vmw->devcaps, dst_size); + } else if (gb_objects) { + ret = vmw_fill_compat_cap(vmw, dst, dst_size); + if (unlikely(ret != 0)) + return ret; + } else if (vmw->fifo_mem) { + u32 *fifo_mem = vmw->fifo_mem; + memcpy(dst, &fifo_mem[SVGA_FIFO_3D_CAPS], dst_size); + } else + return -EINVAL; + return 0; +} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.h b/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.h new file mode 100644 index 000000000000..f70e923ac3e6 --- /dev/null +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_devcaps.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/************************************************************************** + * + * Copyright 2021 VMware, Inc., Palo Alto, CA., USA + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + **************************************************************************/ + +#ifndef _VMWGFX_DEVCAPS_H_ +#define _VMWGFX_DEVCAPS_H_ + +#include "vmwgfx_drv.h" + +#include "device_include/svga_reg.h" + +int vmw_devcaps_create(struct vmw_private *vmw); +void vmw_devcaps_destroy(struct vmw_private *vmw); +uint32_t vmw_devcaps_size(const struct vmw_private *vmw, bool gb_aware); +int vmw_devcaps_copy(struct vmw_private *vmw, bool gb_aware, + void *dst, uint32_t dst_size); + +static inline uint32_t vmw_devcap_get(struct vmw_private *vmw, + uint32_t devcap) +{ + bool gb_objects = !!(vmw->capabilities & SVGA_CAP_GBOBJECTS); + if (gb_objects) + return vmw->devcaps[devcap]; + return 0; +} + +#endif diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 45aeeca9b8f6..40864ce19ae1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -42,7 +42,9 @@ #include "ttm_object.h" #include "vmwgfx_binding.h" +#include "vmwgfx_devcaps.h" #include "vmwgfx_drv.h" +#include "vmwgfx_mksstat.h" #define VMWGFX_DRIVER_DESC "Linux drm driver for VMware graphics devices" @@ -148,6 +150,14 @@ #define DRM_IOCTL_VMW_MSG \ DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_MSG, \ struct drm_vmw_msg_arg) +#define DRM_IOCTL_VMW_MKSSTAT_RESET \ + DRM_IO(DRM_COMMAND_BASE + DRM_VMW_MKSSTAT_RESET) +#define DRM_IOCTL_VMW_MKSSTAT_ADD \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_MKSSTAT_ADD, \ + struct drm_vmw_mksstat_add_arg) +#define DRM_IOCTL_VMW_MKSSTAT_REMOVE \ + DRM_IOW(DRM_COMMAND_BASE + DRM_VMW_MKSSTAT_REMOVE, \ + struct drm_vmw_mksstat_remove_arg) /* * The core DRM version of this macro doesn't account for @@ -244,6 +254,15 @@ static const struct drm_ioctl_desc vmw_ioctls[] = { VMW_IOCTL_DEF(VMW_MSG, vmw_msg_ioctl, DRM_RENDER_ALLOW), + VMW_IOCTL_DEF(VMW_MKSSTAT_RESET, + vmw_mksstat_reset_ioctl, + DRM_RENDER_ALLOW), + VMW_IOCTL_DEF(VMW_MKSSTAT_ADD, + vmw_mksstat_add_ioctl, + DRM_RENDER_ALLOW), + VMW_IOCTL_DEF(VMW_MKSSTAT_REMOVE, + vmw_mksstat_remove_ioctl, + DRM_RENDER_ALLOW), }; static const struct pci_device_id vmw_pci_id_list[] = { @@ -254,7 +273,6 @@ static const struct pci_device_id vmw_pci_id_list[] = { MODULE_DEVICE_TABLE(pci, vmw_pci_id_list); static int enable_fbdev = IS_ENABLED(CONFIG_DRM_VMWGFX_FBCON); -static int vmw_force_iommu; static int vmw_restrict_iommu; static int vmw_force_coherent; static int vmw_restrict_dma_mask; @@ -266,8 +284,6 @@ static int vmwgfx_pm_notifier(struct notifier_block *nb, unsigned long val, MODULE_PARM_DESC(enable_fbdev, "Enable vmwgfx fbdev"); module_param_named(enable_fbdev, enable_fbdev, int, 0600); -MODULE_PARM_DESC(force_dma_api, "Force using the DMA API for TTM pages"); -module_param_named(force_dma_api, vmw_force_iommu, int, 0600); MODULE_PARM_DESC(restrict_iommu, "Try to limit IOMMU usage for TTM pages"); module_param_named(restrict_iommu, vmw_restrict_iommu, int, 0600); MODULE_PARM_DESC(force_coherent, "Force coherent TTM pages"); @@ -627,7 +643,6 @@ static void vmw_get_initial_size(struct vmw_private *dev_priv) static int vmw_dma_select_mode(struct vmw_private *dev_priv) { static const char *names[vmw_dma_map_max] = { - [vmw_dma_phys] = "Using physical TTM page addresses.", [vmw_dma_alloc_coherent] = "Using coherent TTM pages.", [vmw_dma_map_populate] = "Caching DMA mappings.", [vmw_dma_map_bind] = "Giving up DMA mappings early."}; @@ -661,8 +676,7 @@ static int vmw_dma_masks(struct vmw_private *dev_priv) int ret = 0; ret = dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)); - if (dev_priv->map_mode != vmw_dma_phys && - (sizeof(unsigned long) == 4 || vmw_restrict_dma_mask)) { + if (sizeof(unsigned long) == 4 || vmw_restrict_dma_mask) { DRM_INFO("Restricting DMA addresses to 44 bits.\n"); return dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(44)); } @@ -693,7 +707,7 @@ static void vmw_vram_manager_fini(struct vmw_private *dev_priv) } static int vmw_setup_pci_resources(struct vmw_private *dev, - unsigned long pci_id) + u32 pci_id) { resource_size_t rmmio_start; resource_size_t rmmio_size; @@ -770,7 +784,7 @@ static int vmw_detect_version(struct vmw_private *dev) svga_id = vmw_read(dev, SVGA_REG_ID); if (svga_id != SVGA_ID_2 && svga_id != SVGA_ID_3) { DRM_ERROR("Unsupported SVGA ID 0x%x on chipset 0x%x\n", - svga_id, dev->vmw_chipset); + svga_id, dev->pci_id); return -ENOSYS; } BUG_ON(vmw_is_svga_v3(dev) && (svga_id != SVGA_ID_3)); @@ -785,7 +799,6 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) bool refuse_dma = false; struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); - dev_priv->vmw_chipset = pci_id; dev_priv->drm.dev_private = dev_priv; mutex_init(&dev_priv->cmdbuf_mutex); @@ -793,7 +806,6 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) spin_lock_init(&dev_priv->resource_lock); spin_lock_init(&dev_priv->hw_lock); spin_lock_init(&dev_priv->waiter_lock); - spin_lock_init(&dev_priv->cap_lock); spin_lock_init(&dev_priv->cursor_lock); ret = vmw_setup_pci_resources(dev_priv, pci_id); @@ -879,9 +891,8 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) mem_size *= 3; dev_priv->max_mob_pages = mem_size * 1024 / PAGE_SIZE; - dev_priv->prim_bb_mem = - vmw_read(dev_priv, - SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM); + dev_priv->max_primary_mem = + vmw_read(dev_priv, SVGA_REG_MAX_PRIMARY_MEM); dev_priv->max_mob_size = vmw_read(dev_priv, SVGA_REG_MOB_MAX_SIZE); dev_priv->stdu_max_width = @@ -900,7 +911,7 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) } else { dev_priv->texture_max_width = 8192; dev_priv->texture_max_height = 8192; - dev_priv->prim_bb_mem = dev_priv->vram_size; + dev_priv->max_primary_mem = dev_priv->vram_size; } vmw_print_capabilities(dev_priv->capabilities); @@ -924,7 +935,7 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) (unsigned)dev_priv->memory_size / 1024); } DRM_INFO("Maximum display memory size is %llu kiB\n", - (uint64_t)dev_priv->prim_bb_mem / 1024); + (uint64_t)dev_priv->max_primary_mem / 1024); /* Need mmio memory to check for fifo pitchlock cap. */ if (!(dev_priv->capabilities & SVGA_CAP_DISPLAY_TOPOLOGY) && @@ -983,6 +994,12 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) goto out_no_vram; } + ret = vmw_devcaps_create(dev_priv); + if (unlikely(ret != 0)) { + DRM_ERROR("Failed initializing device caps.\n"); + goto out_no_vram; + } + /* * "Guest Memory Regions" is an aperture like feature with * one slot per bo. There is an upper limit of the number of @@ -1009,11 +1026,8 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) } if (dev_priv->has_mob && (dev_priv->capabilities & SVGA_CAP_DX)) { - spin_lock(&dev_priv->cap_lock); - vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_DXCONTEXT); - if (vmw_read(dev_priv, SVGA_REG_DEV_CAP)) + if (vmw_devcap_get(dev_priv, SVGA3D_DEVCAP_DXCONTEXT)) dev_priv->sm_type = VMW_SM_4; - spin_unlock(&dev_priv->cap_lock); } vmw_validation_mem_init_ttm(dev_priv, VMWGFX_VALIDATION_MEM_GRAN); @@ -1021,15 +1035,11 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) /* SVGA_CAP2_DX2 (DefineGBSurface_v3) is needed for SM4_1 support */ if (has_sm4_context(dev_priv) && (dev_priv->capabilities2 & SVGA_CAP2_DX2)) { - vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_SM41); - - if (vmw_read(dev_priv, SVGA_REG_DEV_CAP)) + if (vmw_devcap_get(dev_priv, SVGA3D_DEVCAP_SM41)) dev_priv->sm_type = VMW_SM_4_1; - if (has_sm4_1_context(dev_priv) && - (dev_priv->capabilities2 & SVGA_CAP2_DX3)) { - vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_SM5); - if (vmw_read(dev_priv, SVGA_REG_DEV_CAP)) + (dev_priv->capabilities2 & SVGA_CAP2_DX3)) { + if (vmw_devcap_get(dev_priv, SVGA3D_DEVCAP_SM5)) dev_priv->sm_type = VMW_SM_5; } } @@ -1074,6 +1084,7 @@ out_no_kms: vmw_gmrid_man_fini(dev_priv, VMW_PL_MOB); if (dev_priv->has_gmr) vmw_gmrid_man_fini(dev_priv, VMW_PL_GMR); + vmw_devcaps_destroy(dev_priv); vmw_vram_manager_fini(dev_priv); out_no_vram: ttm_device_fini(&dev_priv->bdev); @@ -1122,6 +1133,7 @@ static void vmw_driver_unload(struct drm_device *dev) vmw_release_device_early(dev_priv); if (dev_priv->has_mob) vmw_gmrid_man_fini(dev_priv, VMW_PL_MOB); + vmw_devcaps_destroy(dev_priv); vmw_vram_manager_fini(dev_priv); ttm_device_fini(&dev_priv->bdev); drm_vma_offset_manager_destroy(&dev_priv->vma_manager); @@ -1137,6 +1149,8 @@ static void vmw_driver_unload(struct drm_device *dev) for (i = vmw_res_context; i < vmw_res_max; ++i) idr_destroy(&dev_priv->res_idr[i]); + vmw_mksstat_remove_all(dev_priv); + pci_release_regions(pdev); } @@ -1560,7 +1574,7 @@ static int vmw_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct vmw_private *vmw; int ret; - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, "svgadrmfb"); + ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &driver); if (ret) return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index d1cef3b69e9d..356f82c26f59 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 OR MIT */ /************************************************************************** * - * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA + * Copyright 2009-2021 VMware, Inc., Palo Alto, CA., USA * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the @@ -91,6 +91,9 @@ #define VMW_RES_FENCE ttm_driver_type3 #define VMW_RES_SHADER ttm_driver_type4 +#define MKSSTAT_CAPACITY_LOG2 5U +#define MKSSTAT_CAPACITY (1U << MKSSTAT_CAPACITY_LOG2) + struct vmw_fpriv { struct ttm_object_file *tfile; bool gb_aware; /* user-space is guest-backed aware */ @@ -311,7 +314,6 @@ struct vmw_res_cache_entry { * enum vmw_dma_map_mode - indicate how to perform TTM page dma mappings. */ enum vmw_dma_map_mode { - vmw_dma_phys, /* Use physical page addresses */ vmw_dma_alloc_coherent, /* Use TTM coherent pages */ vmw_dma_map_populate, /* Unmap from DMA just after unpopulate */ vmw_dma_map_bind, /* Unmap from DMA just before unbind */ @@ -356,7 +358,6 @@ struct vmw_piter { unsigned long num_pages; bool (*next)(struct vmw_piter *); dma_addr_t (*dma_address)(struct vmw_piter *); - struct page *(*page)(struct vmw_piter *); }; /* @@ -486,13 +487,12 @@ struct vmw_private { struct ttm_device bdev; struct drm_vma_offset_manager vma_manager; - unsigned long pci_id; - u32 vmw_chipset; + u32 pci_id; resource_size_t io_start; resource_size_t vram_start; resource_size_t vram_size; - resource_size_t prim_bb_mem; - void __iomem *rmmio; + resource_size_t max_primary_mem; + u32 __iomem *rmmio; u32 *fifo_mem; resource_size_t fifo_mem_size; uint32_t fb_max_width; @@ -513,7 +513,6 @@ struct vmw_private { bool has_gmr; bool has_mob; spinlock_t hw_lock; - spinlock_t cap_lock; bool assume_16bpp; enum vmw_sm_type sm_type; @@ -629,6 +628,20 @@ struct vmw_private { /* Validation memory reservation */ struct vmw_validation_mem vvm; + + uint32 *devcaps; + + /* + * mksGuestStat instance-descriptor and pid arrays + */ + struct page *mksstat_user_pages[MKSSTAT_CAPACITY]; + atomic_t mksstat_user_pids[MKSSTAT_CAPACITY]; + +#if IS_ENABLED(CONFIG_DRM_VMWGFX_MKSSTATS) + struct page *mksstat_kern_pages[MKSSTAT_CAPACITY]; + u8 mksstat_kern_top_timer[MKSSTAT_CAPACITY]; + atomic_t mksstat_kern_pids[MKSSTAT_CAPACITY]; +#endif }; static inline struct vmw_surface *vmw_res_to_srf(struct vmw_resource *res) @@ -1073,7 +1086,7 @@ static inline dma_addr_t vmw_piter_dma_addr(struct vmw_piter *viter) */ static inline struct page *vmw_piter_page(struct vmw_piter *viter) { - return viter->page(viter); + return viter->pages[viter->i]; } /** @@ -1502,6 +1515,17 @@ __printf(1, 2) int vmw_host_printf(const char *fmt, ...); int vmw_msg_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); +/* Host mksGuestStats -vmwgfx_msg.c: */ +int vmw_mksstat_get_kern_slot(pid_t pid, struct vmw_private *dev_priv); + +int vmw_mksstat_reset_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv); +int vmw_mksstat_add_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv); +int vmw_mksstat_remove_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv); +int vmw_mksstat_remove_all(struct vmw_private *dev_priv); + /* VMW logging */ /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index a2b8464b3f56..5f2ffa9de5c8 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -32,6 +32,7 @@ #include <drm/ttm/ttm_placement.h> #include "vmwgfx_so.h" #include "vmwgfx_binding.h" +#include "vmwgfx_mksstat.h" #define VMW_RES_HT_ORDER 12 @@ -2364,7 +2365,7 @@ static int vmw_cmd_dx_set_rendertargets(struct vmw_private *dev_priv, sizeof(SVGA3dRenderTargetViewId); int ret; - if (num_rt_view > SVGA3D_MAX_SIMULTANEOUS_RENDER_TARGETS) { + if (num_rt_view > SVGA3D_DX_MAX_RENDER_TARGETS) { VMW_DEBUG_USER("Invalid DX Rendertarget binding.\n"); return -EINVAL; } @@ -2546,6 +2547,8 @@ static int vmw_cmd_dx_so_define(struct vmw_private *dev_priv, so_type = vmw_so_cmd_to_type(header->id); res = vmw_context_cotable(ctx_node->ctx, vmw_so_cotables[so_type]); + if (IS_ERR(res)) + return PTR_ERR(res); cmd = container_of(header, typeof(*cmd), header); ret = vmw_cotable_notify(res, cmd->defined_id); @@ -4406,6 +4409,9 @@ int vmw_execbuf_ioctl(struct drm_device *dev, void *data, int ret; struct dma_fence *in_fence = NULL; + MKS_STAT_TIME_DECL(MKSSTAT_KERN_EXECBUF); + MKS_STAT_TIME_PUSH(MKSSTAT_KERN_EXECBUF); + /* * Extend the ioctl argument while maintaining backwards compatibility: * We take different code paths depending on the value of arg->version. @@ -4415,7 +4421,8 @@ int vmw_execbuf_ioctl(struct drm_device *dev, void *data, if (unlikely(arg->version > DRM_VMW_EXECBUF_VERSION || arg->version == 0)) { VMW_DEBUG_USER("Incorrect execbuf version.\n"); - return -EINVAL; + ret = -EINVAL; + goto mksstats_out; } switch (arg->version) { @@ -4435,7 +4442,8 @@ int vmw_execbuf_ioctl(struct drm_device *dev, void *data, if (!in_fence) { VMW_DEBUG_USER("Cannot get imported fence\n"); - return -EINVAL; + ret = -EINVAL; + goto mksstats_out; } ret = vmw_wait_dma_fence(dev_priv->fman, in_fence); @@ -4458,5 +4466,8 @@ int vmw_execbuf_ioctl(struct drm_device *dev, void *data, out: if (in_fence) dma_fence_put(in_fence); + +mksstats_out: + MKS_STAT_TIME_POP(MKSSTAT_KERN_EXECBUF); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c index 4fdacf9924e6..28af34ab6ed6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c @@ -26,14 +26,9 @@ **************************************************************************/ #include "vmwgfx_drv.h" +#include "vmwgfx_devcaps.h" #include <drm/vmwgfx_drm.h> #include "vmwgfx_kms.h" -#include "device_include/svga3d_caps.h" - -struct svga_3d_compat_cap { - SVGA3dCapsRecordHeader header; - SVGA3dCapPair pairs[SVGA3D_DEVCAP_MAX]; -}; int vmw_getparam_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) @@ -63,7 +58,7 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data, param->value = vmw_fifo_caps(dev_priv); break; case DRM_VMW_PARAM_MAX_FB_SIZE: - param->value = dev_priv->prim_bb_mem; + param->value = dev_priv->max_primary_mem; break; case DRM_VMW_PARAM_FIFO_HW_VERSION: { @@ -88,16 +83,7 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data, param->value = dev_priv->memory_size; break; case DRM_VMW_PARAM_3D_CAPS_SIZE: - if ((dev_priv->capabilities & SVGA_CAP_GBOBJECTS) && - vmw_fp->gb_aware) - param->value = SVGA3D_DEVCAP_MAX * sizeof(uint32_t); - else if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) - param->value = sizeof(struct svga_3d_compat_cap) + - sizeof(uint32_t); - else - param->value = (SVGA_FIFO_3D_CAPS_LAST - - SVGA_FIFO_3D_CAPS + 1) * - sizeof(uint32_t); + param->value = vmw_devcaps_size(dev_priv, vmw_fp->gb_aware); break; case DRM_VMW_PARAM_MAX_MOB_MEMORY: vmw_fp->gb_aware = true; @@ -126,55 +112,6 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data, return 0; } -static u32 vmw_mask_legacy_multisample(unsigned int cap, u32 fmt_value) -{ - /* - * A version of user-space exists which use MULTISAMPLE_MASKABLESAMPLES - * to check the sample count supported by virtual device. Since there - * never was support for multisample count for backing MOB return 0. - * - * MULTISAMPLE_MASKABLESAMPLES devcap is marked as deprecated by virtual - * device. - */ - if (cap == SVGA3D_DEVCAP_DEAD5) - return 0; - - return fmt_value; -} - -static int vmw_fill_compat_cap(struct vmw_private *dev_priv, void *bounce, - size_t size) -{ - struct svga_3d_compat_cap *compat_cap = - (struct svga_3d_compat_cap *) bounce; - unsigned int i; - size_t pair_offset = offsetof(struct svga_3d_compat_cap, pairs); - unsigned int max_size; - - if (size < pair_offset) - return -EINVAL; - - max_size = (size - pair_offset) / sizeof(SVGA3dCapPair); - - if (max_size > SVGA3D_DEVCAP_MAX) - max_size = SVGA3D_DEVCAP_MAX; - - compat_cap->header.length = - (pair_offset + max_size * sizeof(SVGA3dCapPair)) / sizeof(u32); - compat_cap->header.type = SVGA3DCAPS_RECORD_DEVCAPS; - - spin_lock(&dev_priv->cap_lock); - for (i = 0; i < max_size; ++i) { - vmw_write(dev_priv, SVGA_REG_DEV_CAP, i); - compat_cap->pairs[i][0] = i; - compat_cap->pairs[i][1] = vmw_mask_legacy_multisample - (i, vmw_read(dev_priv, SVGA_REG_DEV_CAP)); - } - spin_unlock(&dev_priv->cap_lock); - - return 0; -} - int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) @@ -183,11 +120,9 @@ int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data, (struct drm_vmw_get_3d_cap_arg *) data; struct vmw_private *dev_priv = vmw_priv(dev); uint32_t size; - u32 *fifo_mem; void __user *buffer = (void __user *)((unsigned long)(arg->buffer)); - void *bounce; + void *bounce = NULL; int ret; - bool gb_objects = !!(dev_priv->capabilities & SVGA_CAP_GBOBJECTS); struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv); if (unlikely(arg->pad64 != 0 || arg->max_size == 0)) { @@ -195,13 +130,11 @@ int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data, return -EINVAL; } - if (gb_objects && vmw_fp->gb_aware) - size = SVGA3D_DEVCAP_MAX * sizeof(uint32_t); - else if (gb_objects) - size = sizeof(struct svga_3d_compat_cap) + sizeof(uint32_t); - else - size = (SVGA_FIFO_3D_CAPS_LAST - SVGA_FIFO_3D_CAPS + 1) * - sizeof(uint32_t); + size = vmw_devcaps_size(dev_priv, vmw_fp->gb_aware); + if (unlikely(size == 0)) { + DRM_ERROR("Failed to figure out the devcaps size (no 3D).\n"); + return -ENOMEM; + } if (arg->max_size < size) size = arg->max_size; @@ -212,29 +145,9 @@ int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data, return -ENOMEM; } - if (gb_objects && vmw_fp->gb_aware) { - int i, num; - uint32_t *bounce32 = (uint32_t *) bounce; - - num = size / sizeof(uint32_t); - if (num > SVGA3D_DEVCAP_MAX) - num = SVGA3D_DEVCAP_MAX; - - spin_lock(&dev_priv->cap_lock); - for (i = 0; i < num; ++i) { - vmw_write(dev_priv, SVGA_REG_DEV_CAP, i); - *bounce32++ = vmw_mask_legacy_multisample - (i, vmw_read(dev_priv, SVGA_REG_DEV_CAP)); - } - spin_unlock(&dev_priv->cap_lock); - } else if (gb_objects) { - ret = vmw_fill_compat_cap(dev_priv, bounce, size); - if (unlikely(ret != 0)) - goto out_err; - } else { - fifo_mem = dev_priv->fifo_mem; - memcpy(bounce, &fifo_mem[SVGA_FIFO_3D_CAPS], size); - } + ret = vmw_devcaps_copy(dev_priv, vmw_fp->gb_aware, bounce, size); + if (unlikely (ret != 0)) + goto out_err; ret = copy_to_user(buffer, bounce, size); if (ret) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c index b9a9b7ddadbd..c5191de365ca 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c @@ -25,6 +25,7 @@ * **************************************************************************/ +#include <linux/pci.h> #include <linux/sched/signal.h> #include "vmwgfx_drv.h" @@ -287,21 +288,18 @@ static void vmw_irq_preinstall(struct drm_device *dev) void vmw_irq_uninstall(struct drm_device *dev) { struct vmw_private *dev_priv = vmw_priv(dev); + struct pci_dev *pdev = to_pci_dev(dev->dev); uint32_t status; if (!(dev_priv->capabilities & SVGA_CAP_IRQMASK)) return; - if (!dev->irq_enabled) - return; - vmw_write(dev_priv, SVGA_REG_IRQMASK, 0); status = vmw_irq_status_read(dev_priv); vmw_irq_status_write(dev_priv, status); - dev->irq_enabled = false; - free_irq(dev->irq, dev); + free_irq(pdev->irq, dev); } /** @@ -313,20 +311,8 @@ void vmw_irq_uninstall(struct drm_device *dev) */ int vmw_irq_install(struct drm_device *dev, int irq) { - int ret; - - if (dev->irq_enabled) - return -EBUSY; - vmw_irq_preinstall(dev); - ret = request_threaded_irq(irq, vmw_irq_handler, vmw_thread_fn, - IRQF_SHARED, VMWGFX_DRIVER_NAME, dev); - if (ret < 0) - return ret; - - dev->irq_enabled = true; - dev->irq = irq; - - return ret; + return request_threaded_irq(irq, vmw_irq_handler, vmw_thread_fn, + IRQF_SHARED, VMWGFX_DRIVER_NAME, dev); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 220f9fd0d420..2ddf4932d62c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1487,7 +1487,7 @@ static int vmw_kms_check_display_memory(struct drm_device *dev, * SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM is not present vram size is * limit on primary bounding box */ - if (pixel_mem > dev_priv->prim_bb_mem) { + if (pixel_mem > dev_priv->max_primary_mem) { VMW_DEBUG_KMS("Combined output size too large.\n"); return -EINVAL; } @@ -1497,7 +1497,7 @@ static int vmw_kms_check_display_memory(struct drm_device *dev, !(dev_priv->capabilities & SVGA_CAP_NO_BB_RESTRICTION)) { bb_mem = (u64) bounding_box.x2 * bounding_box.y2 * 4; - if (bb_mem > dev_priv->prim_bb_mem) { + if (bb_mem > dev_priv->max_primary_mem) { VMW_DEBUG_KMS("Topology is beyond supported limits.\n"); return -EINVAL; } @@ -1897,7 +1897,7 @@ bool vmw_kms_validate_mode_vram(struct vmw_private *dev_priv, { return ((u64) pitch * (u64) height) < (u64) ((dev_priv->active_display_unit == vmw_du_screen_target) ? - dev_priv->prim_bb_mem : dev_priv->vram_size); + dev_priv->max_primary_mem : dev_priv->vram_size); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mksstat.h b/drivers/gpu/drm/vmwgfx/vmwgfx_mksstat.h new file mode 100644 index 000000000000..0509f55f07b4 --- /dev/null +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mksstat.h @@ -0,0 +1,144 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/************************************************************************** + * + * Copyright 2021 VMware, Inc., Palo Alto, CA., USA + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sub license, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial portions + * of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, + * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR + * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE + * USE OR OTHER DEALINGS IN THE SOFTWARE. + * + **************************************************************************/ + +#ifndef _VMWGFX_MKSSTAT_H_ +#define _VMWGFX_MKSSTAT_H_ + +#include <asm/page.h> + +/* Reservation marker for mksstat pid's */ +#define MKSSTAT_PID_RESERVED -1 + +#if IS_ENABLED(CONFIG_DRM_VMWGFX_MKSSTATS) +/* + * Kernel-internal mksGuestStat counters. The order of this enum dictates the + * order of instantiation of these counters in the mksGuestStat pages. + */ + +typedef enum { + MKSSTAT_KERN_EXECBUF, /* vmw_execbuf_ioctl */ + + MKSSTAT_KERN_COUNT /* Reserved entry; always last */ +} mksstat_kern_stats_t; + +/** + * vmw_mksstat_get_kern_pstat: Computes the address of the MKSGuestStatCounterTime + * array from the address of the base page. + * + * @page_addr: Pointer to the base page. + * Return: Pointer to the MKSGuestStatCounterTime array. + */ + +static inline void *vmw_mksstat_get_kern_pstat(void *page_addr) +{ + return page_addr + PAGE_SIZE * 1; +} + +/** + * vmw_mksstat_get_kern_pinfo: Computes the address of the MKSGuestStatInfoEntry + * array from the address of the base page. + * + * @page_addr: Pointer to the base page. + * Return: Pointer to the MKSGuestStatInfoEntry array. + */ + +static inline void *vmw_mksstat_get_kern_pinfo(void *page_addr) +{ + return page_addr + PAGE_SIZE * 2; +} + +/** + * vmw_mksstat_get_kern_pstrs: Computes the address of the mksGuestStat strings + * sequence from the address of the base page. + * + * @page_addr: Pointer to the base page. + * Return: Pointer to the mksGuestStat strings sequence. + */ + +static inline void *vmw_mksstat_get_kern_pstrs(void *page_addr) +{ + return page_addr + PAGE_SIZE * 3; +} + +/* + * MKS_STAT_TIME_DECL/PUSH/POP macros to be used in timer-counted routines. + */ + +struct mksstat_timer_t { +/* mutable */ mksstat_kern_stats_t old_top; + const u64 t0; + const int slot; +}; + +#define MKS_STAT_TIME_DECL(kern_cntr) \ + struct mksstat_timer_t _##kern_cntr = { \ + .t0 = rdtsc(), \ + .slot = vmw_mksstat_get_kern_slot(current->pid, dev_priv) \ + } + +#define MKS_STAT_TIME_PUSH(kern_cntr) \ + do { \ + if (_##kern_cntr.slot >= 0) { \ + _##kern_cntr.old_top = dev_priv->mksstat_kern_top_timer[_##kern_cntr.slot]; \ + dev_priv->mksstat_kern_top_timer[_##kern_cntr.slot] = kern_cntr; \ + } \ + } while (0) + +#define MKS_STAT_TIME_POP(kern_cntr) \ + do { \ + if (_##kern_cntr.slot >= 0) { \ + const pid_t pid = atomic_cmpxchg(&dev_priv->mksstat_kern_pids[_##kern_cntr.slot], current->pid, MKSSTAT_PID_RESERVED); \ + dev_priv->mksstat_kern_top_timer[_##kern_cntr.slot] = _##kern_cntr.old_top; \ + \ + if (pid == current->pid) { \ + const u64 dt = rdtsc() - _##kern_cntr.t0; \ + MKSGuestStatCounterTime *pstat; \ + \ + BUG_ON(!dev_priv->mksstat_kern_pages[_##kern_cntr.slot]); \ + \ + pstat = vmw_mksstat_get_kern_pstat(page_address(dev_priv->mksstat_kern_pages[_##kern_cntr.slot])); \ + \ + atomic64_inc(&pstat[kern_cntr].counter.count); \ + atomic64_add(dt, &pstat[kern_cntr].selfCycles); \ + atomic64_add(dt, &pstat[kern_cntr].totalCycles); \ + \ + if (_##kern_cntr.old_top != MKSSTAT_KERN_COUNT) \ + atomic64_sub(dt, &pstat[_##kern_cntr.old_top].selfCycles); \ + \ + atomic_set(&dev_priv->mksstat_kern_pids[_##kern_cntr.slot], current->pid); \ + } \ + } \ + } while (0) + +#else +#define MKS_STAT_TIME_DECL(kern_cntr) +#define MKS_STAT_TIME_PUSH(kern_cntr) +#define MKS_STAT_TIME_POP(kern_cntr) + +#endif /* IS_ENABLED(CONFIG_DRM_VMWGFX_MKSSTATS */ + +#endif diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c index f2d625415458..c8e578f63c9c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c @@ -37,14 +37,14 @@ #ifdef CONFIG_64BIT #define VMW_PPN_SIZE 8 -#define VMW_MOBFMT_PTDEPTH_0 SVGA3D_MOBFMT_PTDEPTH64_0 -#define VMW_MOBFMT_PTDEPTH_1 SVGA3D_MOBFMT_PTDEPTH64_1 -#define VMW_MOBFMT_PTDEPTH_2 SVGA3D_MOBFMT_PTDEPTH64_2 +#define VMW_MOBFMT_PTDEPTH_0 SVGA3D_MOBFMT_PT64_0 +#define VMW_MOBFMT_PTDEPTH_1 SVGA3D_MOBFMT_PT64_1 +#define VMW_MOBFMT_PTDEPTH_2 SVGA3D_MOBFMT_PT64_2 #else #define VMW_PPN_SIZE 4 -#define VMW_MOBFMT_PTDEPTH_0 SVGA3D_MOBFMT_PTDEPTH_0 -#define VMW_MOBFMT_PTDEPTH_1 SVGA3D_MOBFMT_PTDEPTH_1 -#define VMW_MOBFMT_PTDEPTH_2 SVGA3D_MOBFMT_PTDEPTH_2 +#define VMW_MOBFMT_PTDEPTH_0 SVGA3D_MOBFMT_PT_0 +#define VMW_MOBFMT_PTDEPTH_1 SVGA3D_MOBFMT_PT_1 +#define VMW_MOBFMT_PTDEPTH_2 SVGA3D_MOBFMT_PT_2 #endif /* @@ -70,20 +70,20 @@ struct vmw_mob { * @page_table: Pointer to a struct vmw_mob holding the page table. */ static const struct vmw_otable pre_dx_tables[] = { - {VMWGFX_NUM_MOB * SVGA3D_OTABLE_MOB_ENTRY_SIZE, NULL, true}, - {VMWGFX_NUM_GB_SURFACE * SVGA3D_OTABLE_SURFACE_ENTRY_SIZE, NULL, true}, - {VMWGFX_NUM_GB_CONTEXT * SVGA3D_OTABLE_CONTEXT_ENTRY_SIZE, NULL, true}, - {VMWGFX_NUM_GB_SHADER * SVGA3D_OTABLE_SHADER_ENTRY_SIZE, NULL, true}, - {VMWGFX_NUM_GB_SCREEN_TARGET * SVGA3D_OTABLE_SCREEN_TARGET_ENTRY_SIZE, + {VMWGFX_NUM_MOB * sizeof(SVGAOTableMobEntry), NULL, true}, + {VMWGFX_NUM_GB_SURFACE * sizeof(SVGAOTableSurfaceEntry), NULL, true}, + {VMWGFX_NUM_GB_CONTEXT * sizeof(SVGAOTableContextEntry), NULL, true}, + {VMWGFX_NUM_GB_SHADER * sizeof(SVGAOTableShaderEntry), NULL, true}, + {VMWGFX_NUM_GB_SCREEN_TARGET * sizeof(SVGAOTableScreenTargetEntry), NULL, VMWGFX_ENABLE_SCREEN_TARGET_OTABLE} }; static const struct vmw_otable dx_tables[] = { - {VMWGFX_NUM_MOB * SVGA3D_OTABLE_MOB_ENTRY_SIZE, NULL, true}, - {VMWGFX_NUM_GB_SURFACE * SVGA3D_OTABLE_SURFACE_ENTRY_SIZE, NULL, true}, - {VMWGFX_NUM_GB_CONTEXT * SVGA3D_OTABLE_CONTEXT_ENTRY_SIZE, NULL, true}, - {VMWGFX_NUM_GB_SHADER * SVGA3D_OTABLE_SHADER_ENTRY_SIZE, NULL, true}, - {VMWGFX_NUM_GB_SCREEN_TARGET * SVGA3D_OTABLE_SCREEN_TARGET_ENTRY_SIZE, + {VMWGFX_NUM_MOB * sizeof(SVGAOTableMobEntry), NULL, true}, + {VMWGFX_NUM_GB_SURFACE * sizeof(SVGAOTableSurfaceEntry), NULL, true}, + {VMWGFX_NUM_GB_CONTEXT * sizeof(SVGAOTableContextEntry), NULL, true}, + {VMWGFX_NUM_GB_SHADER * sizeof(SVGAOTableShaderEntry), NULL, true}, + {VMWGFX_NUM_GB_SCREEN_TARGET * sizeof(SVGAOTableScreenTargetEntry), NULL, VMWGFX_ENABLE_SCREEN_TARGET_OTABLE}, {VMWGFX_NUM_DXCONTEXT * sizeof(SVGAOTableDXContextEntry), NULL, true}, }; @@ -155,7 +155,7 @@ static int vmw_setup_otable_base(struct vmw_private *dev_priv, goto out_no_populate; vmw_mob_pt_setup(mob, iter, otable->size >> PAGE_SHIFT); - mob->pt_level += VMW_MOBFMT_PTDEPTH_1 - SVGA3D_MOBFMT_PTDEPTH_1; + mob->pt_level += VMW_MOBFMT_PTDEPTH_1 - SVGA3D_MOBFMT_PT_1; } cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd)); @@ -506,11 +506,13 @@ static void vmw_mob_pt_setup(struct vmw_mob *mob, { unsigned long num_pt_pages = 0; struct ttm_buffer_object *bo = mob->pt_bo; - struct vmw_piter save_pt_iter; + struct vmw_piter save_pt_iter = {0}; struct vmw_piter pt_iter; const struct vmw_sg_table *vsgt; int ret; + BUG_ON(num_data_pages == 0); + ret = ttm_bo_reserve(bo, false, true, NULL); BUG_ON(ret != 0); @@ -633,7 +635,7 @@ int vmw_mob_bind(struct vmw_private *dev_priv, vmw_mob_pt_setup(mob, data_iter, num_data_pages); pt_set_up = true; - mob->pt_level += VMW_MOBFMT_PTDEPTH_1 - SVGA3D_MOBFMT_PTDEPTH_1; + mob->pt_level += VMW_MOBFMT_PTDEPTH_1 - SVGA3D_MOBFMT_PT_1; } vmw_fifo_resource_inc(dev_priv); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c index 3d08f5700bdb..ed9c7b3a1e08 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c @@ -31,10 +31,12 @@ #include <linux/mem_encrypt.h> #include <asm/hypervisor.h> +#include <drm/drm_ioctl.h> #include "vmwgfx_drv.h" #include "vmwgfx_msg_x86.h" #include "vmwgfx_msg_arm64.h" +#include "vmwgfx_mksstat.h" #define MESSAGE_STATUS_SUCCESS 0x0001 #define MESSAGE_STATUS_DORECV 0x0002 @@ -56,6 +58,11 @@ #define VMW_PORT_CMD_RECVSIZE (MSG_TYPE_RECVSIZE << 16 | VMW_PORT_CMD_MSG) #define VMW_PORT_CMD_RECVSTATUS (MSG_TYPE_RECVSTATUS << 16 | VMW_PORT_CMD_MSG) +#define VMW_PORT_CMD_MKS_GUEST_STATS 85 +#define VMW_PORT_CMD_MKSGS_RESET (0 << 16 | VMW_PORT_CMD_MKS_GUEST_STATS) +#define VMW_PORT_CMD_MKSGS_ADD_PPN (1 << 16 | VMW_PORT_CMD_MKS_GUEST_STATS) +#define VMW_PORT_CMD_MKSGS_REMOVE_PPN (2 << 16 | VMW_PORT_CMD_MKS_GUEST_STATS) + #define HIGH_WORD(X) ((X & 0xFFFF0000) >> 16) #define MAX_USER_MSG_LENGTH PAGE_SIZE @@ -155,6 +162,7 @@ static unsigned long vmw_port_hb_out(struct rpc_channel *channel, /* HB port can't access encrypted memory. */ if (hb && !mem_encrypt_active()) { unsigned long bp = channel->cookie_high; + u32 channel_id = (channel->channel_id << 16); si = (uintptr_t) msg; di = channel->cookie_low; @@ -162,7 +170,7 @@ static unsigned long vmw_port_hb_out(struct rpc_channel *channel, VMW_PORT_HB_OUT( (MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG, msg_len, si, di, - VMWARE_HYPERVISOR_HB | (channel->channel_id << 16) | + VMWARE_HYPERVISOR_HB | channel_id | VMWARE_HYPERVISOR_OUT, VMW_HYPERVISOR_MAGIC, bp, eax, ebx, ecx, edx, si, di); @@ -210,6 +218,7 @@ static unsigned long vmw_port_hb_in(struct rpc_channel *channel, char *reply, /* HB port can't access encrypted memory */ if (hb && !mem_encrypt_active()) { unsigned long bp = channel->cookie_low; + u32 channel_id = (channel->channel_id << 16); si = channel->cookie_high; di = (uintptr_t) reply; @@ -217,7 +226,7 @@ static unsigned long vmw_port_hb_in(struct rpc_channel *channel, char *reply, VMW_PORT_HB_IN( (MESSAGE_STATUS_SUCCESS << 16) | VMW_PORT_CMD_HB_MSG, reply_len, si, di, - VMWARE_HYPERVISOR_HB | (channel->channel_id << 16), + VMWARE_HYPERVISOR_HB | channel_id, VMW_HYPERVISOR_MAGIC, bp, eax, ebx, ecx, edx, si, di); @@ -612,3 +621,569 @@ out_open: return -EINVAL; } + +/** + * reset_ppn_array: Resets a PPN64 array to INVALID_PPN64 content + * + * @arr: Array to reset. + * @size: Array length. + */ +static inline void reset_ppn_array(PPN64 *arr, size_t size) +{ + size_t i; + + BUG_ON(!arr || size == 0); + + for (i = 0; i < size; ++i) + arr[i] = INVALID_PPN64; +} + +/** + * hypervisor_ppn_reset_all: Removes all mksGuestStat instance descriptors from + * the hypervisor. All related pages should be subsequently unpinned or freed. + * + */ +static inline void hypervisor_ppn_reset_all(void) +{ + unsigned long eax, ebx, ecx, edx, si = 0, di = 0; + + VMW_PORT(VMW_PORT_CMD_MKSGS_RESET, + 0, si, di, + 0, + VMW_HYPERVISOR_MAGIC, + eax, ebx, ecx, edx, si, di); +} + +/** + * hypervisor_ppn_add: Adds a single mksGuestStat instance descriptor to the + * hypervisor. Any related userspace pages should be pinned in advance. + * + * @pfn: Physical page number of the instance descriptor + */ +static inline void hypervisor_ppn_add(PPN64 pfn) +{ + unsigned long eax, ebx, ecx, edx, si = 0, di = 0; + + VMW_PORT(VMW_PORT_CMD_MKSGS_ADD_PPN, + (unsigned long)pfn, si, di, + 0, + VMW_HYPERVISOR_MAGIC, + eax, ebx, ecx, edx, si, di); +} + +/** + * hypervisor_ppn_remove: Removes a single mksGuestStat instance descriptor from + * the hypervisor. All related pages should be subsequently unpinned or freed. + * + * @pfn: Physical page number of the instance descriptor + */ +static inline void hypervisor_ppn_remove(PPN64 pfn) +{ + unsigned long eax, ebx, ecx, edx, si = 0, di = 0; + + VMW_PORT(VMW_PORT_CMD_MKSGS_REMOVE_PPN, + (unsigned long)pfn, si, di, + 0, + VMW_HYPERVISOR_MAGIC, + eax, ebx, ecx, edx, si, di); +} + +#if IS_ENABLED(CONFIG_DRM_VMWGFX_MKSSTATS) + +/* Order of the total number of pages used for kernel-internal mksGuestStat; at least 2 */ +#define MKSSTAT_KERNEL_PAGES_ORDER 2 +/* Header to the text description of mksGuestStat instance descriptor */ +#define MKSSTAT_KERNEL_DESCRIPTION "vmwgfx" + +/* Kernel mksGuestStats counter names and desciptions; same order as enum mksstat_kern_stats_t */ +static const char* const mksstat_kern_name_desc[MKSSTAT_KERN_COUNT][2] = +{ + { "vmw_execbuf_ioctl", "vmw_execbuf_ioctl" }, +}; + +/** + * mksstat_init_record: Initializes an MKSGuestStatCounter-based record + * for the respective mksGuestStat index. + * + * @stat_idx: Index of the MKSGuestStatCounter-based mksGuestStat record. + * @pstat: Pointer to array of MKSGuestStatCounterTime. + * @pinfo: Pointer to array of MKSGuestStatInfoEntry. + * @pstrs: Pointer to current end of the name/description sequence. + * Return: Pointer to the new end of the names/description sequence. + */ + +static inline char *mksstat_init_record(mksstat_kern_stats_t stat_idx, + MKSGuestStatCounterTime *pstat, MKSGuestStatInfoEntry *pinfo, char *pstrs) +{ + char *const pstrd = pstrs + strlen(mksstat_kern_name_desc[stat_idx][0]) + 1; + strcpy(pstrs, mksstat_kern_name_desc[stat_idx][0]); + strcpy(pstrd, mksstat_kern_name_desc[stat_idx][1]); + + pinfo[stat_idx].name.s = pstrs; + pinfo[stat_idx].description.s = pstrd; + pinfo[stat_idx].flags = MKS_GUEST_STAT_FLAG_NONE; + pinfo[stat_idx].stat.counter = (MKSGuestStatCounter *)&pstat[stat_idx]; + + return pstrd + strlen(mksstat_kern_name_desc[stat_idx][1]) + 1; +} + +/** + * mksstat_init_record_time: Initializes an MKSGuestStatCounterTime-based record + * for the respective mksGuestStat index. + * + * @stat_idx: Index of the MKSGuestStatCounterTime-based mksGuestStat record. + * @pstat: Pointer to array of MKSGuestStatCounterTime. + * @pinfo: Pointer to array of MKSGuestStatInfoEntry. + * @pstrs: Pointer to current end of the name/description sequence. + * Return: Pointer to the new end of the names/description sequence. + */ + +static inline char *mksstat_init_record_time(mksstat_kern_stats_t stat_idx, + MKSGuestStatCounterTime *pstat, MKSGuestStatInfoEntry *pinfo, char *pstrs) +{ + char *const pstrd = pstrs + strlen(mksstat_kern_name_desc[stat_idx][0]) + 1; + strcpy(pstrs, mksstat_kern_name_desc[stat_idx][0]); + strcpy(pstrd, mksstat_kern_name_desc[stat_idx][1]); + + pinfo[stat_idx].name.s = pstrs; + pinfo[stat_idx].description.s = pstrd; + pinfo[stat_idx].flags = MKS_GUEST_STAT_FLAG_TIME; + pinfo[stat_idx].stat.counterTime = &pstat[stat_idx]; + + return pstrd + strlen(mksstat_kern_name_desc[stat_idx][1]) + 1; +} + +/** + * mksstat_init_kern_id: Creates a single mksGuestStat instance descriptor and + * kernel-internal counters. Adds PFN mapping to the hypervisor. + * + * Create a single mksGuestStat instance descriptor and corresponding structures + * for all kernel-internal counters. The corresponding PFNs are mapped with the + * hypervisor. + * + * @ppage: Output pointer to page containing the instance descriptor. + * Return: Zero on success, negative error code on error. + */ + +static int mksstat_init_kern_id(struct page **ppage) +{ + MKSGuestStatInstanceDescriptor *pdesc; + MKSGuestStatCounterTime *pstat; + MKSGuestStatInfoEntry *pinfo; + char *pstrs, *pstrs_acc; + + /* Allocate pages for the kernel-internal instance descriptor */ + struct page *page = alloc_pages(GFP_KERNEL | __GFP_ZERO, MKSSTAT_KERNEL_PAGES_ORDER); + + if (!page) + return -ENOMEM; + + pdesc = page_address(page); + pstat = vmw_mksstat_get_kern_pstat(pdesc); + pinfo = vmw_mksstat_get_kern_pinfo(pdesc); + pstrs = vmw_mksstat_get_kern_pstrs(pdesc); + + /* Set up all kernel-internal counters and corresponding structures */ + pstrs_acc = pstrs; + pstrs_acc = mksstat_init_record_time(MKSSTAT_KERN_EXECBUF, pstat, pinfo, pstrs_acc); + + /* Add new counters above, in their order of appearance in mksstat_kern_stats_t */ + + BUG_ON(pstrs_acc - pstrs > PAGE_SIZE); + + /* Set up the kernel-internal instance descriptor */ + pdesc->reservedMBZ = 0; + pdesc->statStartVA = (uintptr_t)pstat; + pdesc->strsStartVA = (uintptr_t)pstrs; + pdesc->statLength = sizeof(*pstat) * MKSSTAT_KERN_COUNT; + pdesc->infoLength = sizeof(*pinfo) * MKSSTAT_KERN_COUNT; + pdesc->strsLength = pstrs_acc - pstrs; + snprintf(pdesc->description, ARRAY_SIZE(pdesc->description) - 1, "%s pid=%d", + MKSSTAT_KERNEL_DESCRIPTION, current->pid); + + pdesc->statPPNs[0] = page_to_pfn(virt_to_page(pstat)); + reset_ppn_array(pdesc->statPPNs + 1, ARRAY_SIZE(pdesc->statPPNs) - 1); + + pdesc->infoPPNs[0] = page_to_pfn(virt_to_page(pinfo)); + reset_ppn_array(pdesc->infoPPNs + 1, ARRAY_SIZE(pdesc->infoPPNs) - 1); + + pdesc->strsPPNs[0] = page_to_pfn(virt_to_page(pstrs)); + reset_ppn_array(pdesc->strsPPNs + 1, ARRAY_SIZE(pdesc->strsPPNs) - 1); + + *ppage = page; + + hypervisor_ppn_add((PPN64)page_to_pfn(page)); + + return 0; +} + +/** + * vmw_mksstat_get_kern_slot: Acquires a slot for a single kernel-internal + * mksGuestStat instance descriptor. + * + * Find a slot for a single kernel-internal mksGuestStat instance descriptor. + * In case no such was already present, allocate a new one and set up a kernel- + * internal mksGuestStat instance descriptor for the former. + * + * @pid: Process for which a slot is sought. + * @dev_priv: Identifies the drm private device. + * Return: Non-negative slot on success, negative error code on error. + */ + +int vmw_mksstat_get_kern_slot(pid_t pid, struct vmw_private *dev_priv) +{ + const size_t base = (u32)hash_32(pid, MKSSTAT_CAPACITY_LOG2); + size_t i; + + for (i = 0; i < ARRAY_SIZE(dev_priv->mksstat_kern_pids); ++i) { + const size_t slot = (i + base) % ARRAY_SIZE(dev_priv->mksstat_kern_pids); + + /* Check if an instance descriptor for this pid is already present */ + if (pid == (pid_t)atomic_read(&dev_priv->mksstat_kern_pids[slot])) + return (int)slot; + + /* Set up a new instance descriptor for this pid */ + if (!atomic_cmpxchg(&dev_priv->mksstat_kern_pids[slot], 0, MKSSTAT_PID_RESERVED)) { + const int ret = mksstat_init_kern_id(&dev_priv->mksstat_kern_pages[slot]); + + if (!ret) { + /* Reset top-timer tracking for this slot */ + dev_priv->mksstat_kern_top_timer[slot] = MKSSTAT_KERN_COUNT; + + atomic_set(&dev_priv->mksstat_kern_pids[slot], pid); + return (int)slot; + } + + atomic_set(&dev_priv->mksstat_kern_pids[slot], 0); + return ret; + } + } + + return -ENOSPC; +} + +#endif + +/** + * vmw_mksstat_cleanup_descriptor: Frees a single userspace-originating + * mksGuestStat instance-descriptor page and unpins all related user pages. + * + * Unpin all user pages realated to this instance descriptor and free + * the instance-descriptor page itself. + * + * @page: Page of the instance descriptor. + */ + +static void vmw_mksstat_cleanup_descriptor(struct page *page) +{ + MKSGuestStatInstanceDescriptor *pdesc = page_address(page); + size_t i; + + for (i = 0; i < ARRAY_SIZE(pdesc->statPPNs) && pdesc->statPPNs[i] != INVALID_PPN64; ++i) + unpin_user_page(pfn_to_page(pdesc->statPPNs[i])); + + for (i = 0; i < ARRAY_SIZE(pdesc->infoPPNs) && pdesc->infoPPNs[i] != INVALID_PPN64; ++i) + unpin_user_page(pfn_to_page(pdesc->infoPPNs[i])); + + for (i = 0; i < ARRAY_SIZE(pdesc->strsPPNs) && pdesc->strsPPNs[i] != INVALID_PPN64; ++i) + unpin_user_page(pfn_to_page(pdesc->strsPPNs[i])); + + __free_page(page); +} + +/** + * vmw_mksstat_remove_all: Resets all mksGuestStat instance descriptors + * from the hypervisor. + * + * Discard all hypervisor PFN mappings, containing active mksGuestState instance + * descriptors, unpin the related userspace pages and free the related kernel pages. + * + * @dev_priv: Identifies the drm private device. + * Return: Zero on success, negative error code on error. + */ + +int vmw_mksstat_remove_all(struct vmw_private *dev_priv) +{ + int ret = 0; + size_t i; + + /* Discard all PFN mappings with the hypervisor */ + hypervisor_ppn_reset_all(); + + /* Discard all userspace-originating instance descriptors and unpin all related pages */ + for (i = 0; i < ARRAY_SIZE(dev_priv->mksstat_user_pids); ++i) { + const pid_t pid0 = (pid_t)atomic_read(&dev_priv->mksstat_user_pids[i]); + + if (!pid0) + continue; + + if (pid0 != MKSSTAT_PID_RESERVED) { + const pid_t pid1 = atomic_cmpxchg(&dev_priv->mksstat_user_pids[i], pid0, MKSSTAT_PID_RESERVED); + + if (!pid1) + continue; + + if (pid1 == pid0) { + struct page *const page = dev_priv->mksstat_user_pages[i]; + + BUG_ON(!page); + + dev_priv->mksstat_user_pages[i] = NULL; + atomic_set(&dev_priv->mksstat_user_pids[i], 0); + + vmw_mksstat_cleanup_descriptor(page); + continue; + } + } + + ret = -EAGAIN; + } + +#if IS_ENABLED(CONFIG_DRM_VMWGFX_MKSSTATS) + /* Discard all kernel-internal instance descriptors and free all related pages */ + for (i = 0; i < ARRAY_SIZE(dev_priv->mksstat_kern_pids); ++i) { + const pid_t pid0 = (pid_t)atomic_read(&dev_priv->mksstat_kern_pids[i]); + + if (!pid0) + continue; + + if (pid0 != MKSSTAT_PID_RESERVED) { + const pid_t pid1 = atomic_cmpxchg(&dev_priv->mksstat_kern_pids[i], pid0, MKSSTAT_PID_RESERVED); + + if (!pid1) + continue; + + if (pid1 == pid0) { + struct page *const page = dev_priv->mksstat_kern_pages[i]; + + BUG_ON(!page); + + dev_priv->mksstat_kern_pages[i] = NULL; + atomic_set(&dev_priv->mksstat_kern_pids[i], 0); + + __free_pages(page, MKSSTAT_KERNEL_PAGES_ORDER); + continue; + } + } + + ret = -EAGAIN; + } + +#endif + return ret; +} + +/** + * vmw_mksstat_reset_ioctl: Resets all mksGuestStat instance descriptors + * from the hypervisor. + * + * Discard all hypervisor PFN mappings, containing active mksGuestStat instance + * descriptors, unpin the related userspace pages and free the related kernel pages. + * + * @dev: Identifies the drm device. + * @data: Pointer to the ioctl argument. + * @file_priv: Identifies the caller; unused. + * Return: Zero on success, negative error code on error. + */ + +int vmw_mksstat_reset_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct vmw_private *const dev_priv = vmw_priv(dev); + return vmw_mksstat_remove_all(dev_priv); +} + +/** + * vmw_mksstat_add_ioctl: Creates a single userspace-originating mksGuestStat + * instance descriptor and registers that with the hypervisor. + * + * Create a hypervisor PFN mapping, containing a single mksGuestStat instance + * descriptor and pin the corresponding userspace pages. + * + * @dev: Identifies the drm device. + * @data: Pointer to the ioctl argument. + * @file_priv: Identifies the caller; unused. + * Return: Zero on success, negative error code on error. + */ + +int vmw_mksstat_add_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct drm_vmw_mksstat_add_arg *arg = + (struct drm_vmw_mksstat_add_arg *) data; + + struct vmw_private *const dev_priv = vmw_priv(dev); + + struct page *page; + MKSGuestStatInstanceDescriptor *pdesc; + const size_t num_pages_stat = vmw_num_pages(arg->stat_len); + const size_t num_pages_info = vmw_num_pages(arg->info_len); + const size_t num_pages_strs = vmw_num_pages(arg->strs_len); + long desc_len; + long nr_pinned_stat; + long nr_pinned_info; + long nr_pinned_strs; + struct page *pages_stat[ARRAY_SIZE(pdesc->statPPNs)]; + struct page *pages_info[ARRAY_SIZE(pdesc->infoPPNs)]; + struct page *pages_strs[ARRAY_SIZE(pdesc->strsPPNs)]; + size_t i, slot; + + arg->id = -1; + + if (!arg->stat || !arg->info || !arg->strs) + return -EINVAL; + + if (!arg->stat_len || !arg->info_len || !arg->strs_len) + return -EINVAL; + + if (!arg->description) + return -EINVAL; + + if (num_pages_stat > ARRAY_SIZE(pdesc->statPPNs) || + num_pages_info > ARRAY_SIZE(pdesc->infoPPNs) || + num_pages_strs > ARRAY_SIZE(pdesc->strsPPNs)) + return -EINVAL; + + /* Find an available slot in the mksGuestStats user array and reserve it */ + for (slot = 0; slot < ARRAY_SIZE(dev_priv->mksstat_user_pids); ++slot) + if (!atomic_cmpxchg(&dev_priv->mksstat_user_pids[slot], 0, MKSSTAT_PID_RESERVED)) + break; + + if (slot == ARRAY_SIZE(dev_priv->mksstat_user_pids)) + return -ENOSPC; + + BUG_ON(dev_priv->mksstat_user_pages[slot]); + + /* Allocate a page for the instance descriptor */ + page = alloc_page(GFP_KERNEL | __GFP_ZERO); + + if (!page) { + atomic_set(&dev_priv->mksstat_user_pids[slot], 0); + return -ENOMEM; + } + + /* Set up the instance descriptor */ + pdesc = page_address(page); + + pdesc->reservedMBZ = 0; + pdesc->statStartVA = arg->stat; + pdesc->strsStartVA = arg->strs; + pdesc->statLength = arg->stat_len; + pdesc->infoLength = arg->info_len; + pdesc->strsLength = arg->strs_len; + desc_len = strncpy_from_user(pdesc->description, u64_to_user_ptr(arg->description), + ARRAY_SIZE(pdesc->description) - 1); + + if (desc_len < 0) { + atomic_set(&dev_priv->mksstat_user_pids[slot], 0); + return -EFAULT; + } + + reset_ppn_array(pdesc->statPPNs, ARRAY_SIZE(pdesc->statPPNs)); + reset_ppn_array(pdesc->infoPPNs, ARRAY_SIZE(pdesc->infoPPNs)); + reset_ppn_array(pdesc->strsPPNs, ARRAY_SIZE(pdesc->strsPPNs)); + + /* Pin mksGuestStat user pages and store those in the instance descriptor */ + nr_pinned_stat = pin_user_pages(arg->stat, num_pages_stat, FOLL_LONGTERM, pages_stat, NULL); + if (num_pages_stat != nr_pinned_stat) + goto err_pin_stat; + + for (i = 0; i < num_pages_stat; ++i) + pdesc->statPPNs[i] = page_to_pfn(pages_stat[i]); + + nr_pinned_info = pin_user_pages(arg->info, num_pages_info, FOLL_LONGTERM, pages_info, NULL); + if (num_pages_info != nr_pinned_info) + goto err_pin_info; + + for (i = 0; i < num_pages_info; ++i) + pdesc->infoPPNs[i] = page_to_pfn(pages_info[i]); + + nr_pinned_strs = pin_user_pages(arg->strs, num_pages_strs, FOLL_LONGTERM, pages_strs, NULL); + if (num_pages_strs != nr_pinned_strs) + goto err_pin_strs; + + for (i = 0; i < num_pages_strs; ++i) + pdesc->strsPPNs[i] = page_to_pfn(pages_strs[i]); + + /* Send the descriptor to the host via a hypervisor call. The mksGuestStat + pages will remain in use until the user requests a matching remove stats + or a stats reset occurs. */ + hypervisor_ppn_add((PPN64)page_to_pfn(page)); + + dev_priv->mksstat_user_pages[slot] = page; + atomic_set(&dev_priv->mksstat_user_pids[slot], task_pgrp_vnr(current)); + + arg->id = slot; + + DRM_DEV_INFO(dev->dev, "pid=%d arg.description='%.*s' id=%zu\n", current->pid, (int)desc_len, pdesc->description, slot); + + return 0; + +err_pin_strs: + if (nr_pinned_strs > 0) + unpin_user_pages(pages_strs, nr_pinned_strs); + +err_pin_info: + if (nr_pinned_info > 0) + unpin_user_pages(pages_info, nr_pinned_info); + +err_pin_stat: + if (nr_pinned_stat > 0) + unpin_user_pages(pages_stat, nr_pinned_stat); + + atomic_set(&dev_priv->mksstat_user_pids[slot], 0); + __free_page(page); + return -ENOMEM; +} + +/** + * vmw_mksstat_remove_ioctl: Removes a single userspace-originating mksGuestStat + * instance descriptor from the hypervisor. + * + * Discard a hypervisor PFN mapping, containing a single mksGuestStat instance + * descriptor and unpin the corresponding userspace pages. + * + * @dev: Identifies the drm device. + * @data: Pointer to the ioctl argument. + * @file_priv: Identifies the caller; unused. + * Return: Zero on success, negative error code on error. + */ + +int vmw_mksstat_remove_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct drm_vmw_mksstat_remove_arg *arg = + (struct drm_vmw_mksstat_remove_arg *) data; + + struct vmw_private *const dev_priv = vmw_priv(dev); + + const size_t slot = arg->id; + pid_t pgid, pid; + + if (slot >= ARRAY_SIZE(dev_priv->mksstat_user_pids)) + return -EINVAL; + + DRM_DEV_INFO(dev->dev, "pid=%d arg.id=%zu\n", current->pid, slot); + + pgid = task_pgrp_vnr(current); + pid = atomic_cmpxchg(&dev_priv->mksstat_user_pids[slot], pgid, MKSSTAT_PID_RESERVED); + + if (!pid) + return 0; + + if (pid == pgid) { + struct page *const page = dev_priv->mksstat_user_pages[slot]; + + BUG_ON(!page); + + dev_priv->mksstat_user_pages[slot] = NULL; + atomic_set(&dev_priv->mksstat_user_pids[slot], 0); + + hypervisor_ppn_remove((PPN64)page_to_pfn(page)); + + vmw_mksstat_cleanup_descriptor(page); + return 0; + } + + return -EAGAIN; +} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 7b45393ad98e..3b6f6044c325 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -114,6 +114,7 @@ static void vmw_resource_release(struct kref *kref) container_of(kref, struct vmw_resource, kref); struct vmw_private *dev_priv = res->dev_priv; int id; + int ret; struct idr *idr = &dev_priv->res_idr[res->func->res_type]; spin_lock(&dev_priv->resource_lock); @@ -122,7 +123,8 @@ static void vmw_resource_release(struct kref *kref) if (res->backup) { struct ttm_buffer_object *bo = &res->backup->base; - ttm_bo_reserve(bo, false, false, NULL); + ret = ttm_bo_reserve(bo, false, false, NULL); + BUG_ON(ret); if (vmw_resource_mob_attached(res) && res->func->unbind != NULL) { struct ttm_validate_buffer val_buf; @@ -1001,7 +1003,9 @@ int vmw_resource_pin(struct vmw_resource *res, bool interruptible) if (res->backup) { vbo = res->backup; - ttm_bo_reserve(&vbo->base, interruptible, false, NULL); + ret = ttm_bo_reserve(&vbo->base, interruptible, false, NULL); + if (ret) + goto out_no_validate; if (!vbo->base.pin_count) { ret = ttm_bo_validate (&vbo->base, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_so.c b/drivers/gpu/drm/vmwgfx/vmwgfx_so.c index c3a8d6e8380e..9efb4463ce99 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_so.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_so.c @@ -539,7 +539,8 @@ const SVGACOTableType vmw_so_cotables[] = { [vmw_so_ds] = SVGA_COTABLE_DEPTHSTENCIL, [vmw_so_rs] = SVGA_COTABLE_RASTERIZERSTATE, [vmw_so_ss] = SVGA_COTABLE_SAMPLER, - [vmw_so_so] = SVGA_COTABLE_STREAMOUTPUT + [vmw_so_so] = SVGA_COTABLE_STREAMOUTPUT, + [vmw_so_max]= SVGA_COTABLE_MAX }; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index 9e236f9f8a8a..365ed93dd3e8 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -33,7 +33,7 @@ #include <drm/drm_vblank.h> #include "vmwgfx_kms.h" -#include "device_include/svga3d_surfacedefs.h" +#include "vmw_surface_cache.h" #define vmw_crtc_to_stdu(x) \ container_of(x, struct vmw_screen_target_display_unit, base.crtc) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 0835468bb2ee..0eba47762bed 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -31,6 +31,7 @@ #include "vmwgfx_resource_priv.h" #include "vmwgfx_so.h" #include "vmwgfx_binding.h" +#include "vmw_surface_cache.h" #include "device_include/svga3d_surfacedefs.h" #define SVGA3D_FLAGS_64(upper32, lower32) (((uint64_t)upper32 << 32) | lower32) @@ -78,7 +79,7 @@ struct vmw_surface_offset { * @boxes: Array of SVGA3dBoxes indicating dirty regions. One per subresource. */ struct vmw_surface_dirty { - struct svga3dsurface_cache cache; + struct vmw_surface_cache cache; size_t size; u32 num_subres; SVGA3dBox boxes[]; @@ -307,8 +308,8 @@ static void vmw_surface_dma_encode(struct vmw_surface *srf, { uint32_t i; struct vmw_surface_dma *cmd = (struct vmw_surface_dma *)cmd_space; - const struct svga3d_surface_desc *desc = - svga3dsurface_get_desc(srf->metadata.format); + const struct SVGA3dSurfaceDesc *desc = + vmw_surface_get_desc(srf->metadata.format); for (i = 0; i < srf->metadata.num_sizes; ++i) { SVGA3dCmdHeader *header = &cmd->header; @@ -323,8 +324,7 @@ static void vmw_surface_dma_encode(struct vmw_surface *srf, body->guest.ptr = *ptr; body->guest.ptr.offset += cur_offset->bo_offset; - body->guest.pitch = svga3dsurface_calculate_pitch(desc, - cur_size); + body->guest.pitch = vmw_surface_calculate_pitch(desc, cur_size); body->host.sid = srf->res.id; body->host.face = cur_offset->face; body->host.mipmap = cur_offset->mip; @@ -342,7 +342,7 @@ static void vmw_surface_dma_encode(struct vmw_surface *srf, suffix->suffixSize = sizeof(*suffix); suffix->maximumOffset = - svga3dsurface_get_image_buffer_size(desc, cur_size, + vmw_surface_get_image_buffer_size(desc, cur_size, body->guest.pitch); suffix->flags.discard = 0; suffix->flags.unsynchronized = 0; @@ -432,7 +432,7 @@ static int vmw_legacy_srf_create(struct vmw_resource *res) goto out_no_id; } - if (unlikely(res->id >= SVGA3D_MAX_SURFACE_IDS)) { + if (unlikely(res->id >= SVGA3D_HB_MAX_SURFACE_IDS)) { ret = -EBUSY; goto out_no_fifo; } @@ -751,7 +751,7 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data, struct vmw_surface_offset *cur_offset; uint32_t num_sizes; uint32_t size; - const struct svga3d_surface_desc *desc; + const SVGA3dSurfaceDesc *desc; if (unlikely(vmw_user_surface_size == 0)) vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) + @@ -772,8 +772,8 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data, ttm_round_pot(num_sizes * sizeof(struct drm_vmw_size)) + ttm_round_pot(num_sizes * sizeof(struct vmw_surface_offset)); - desc = svga3dsurface_get_desc(req->format); - if (unlikely(desc->block_desc == SVGA3DBLOCKDESC_NONE)) { + desc = vmw_surface_get_desc(req->format); + if (unlikely(desc->blockDesc == SVGA3DBLOCKDESC_NONE)) { VMW_DEBUG_USER("Invalid format %d for surface creation.\n", req->format); return -EINVAL; @@ -833,13 +833,13 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data, for (i = 0; i < DRM_VMW_MAX_SURFACE_FACES; ++i) { for (j = 0; j < metadata->mip_levels[i]; ++j) { - uint32_t stride = svga3dsurface_calculate_pitch - (desc, cur_size); + uint32_t stride = vmw_surface_calculate_pitch( + desc, cur_size); cur_offset->face = i; cur_offset->mip = j; cur_offset->bo_offset = cur_bo_offset; - cur_bo_offset += svga3dsurface_get_image_buffer_size + cur_bo_offset += vmw_surface_get_image_buffer_size (desc, cur_size, stride); ++cur_offset; ++cur_size; @@ -1711,10 +1711,10 @@ out_bad_resource: * than partial z slices are dirtied. */ static void vmw_subres_dirty_add(struct vmw_surface_dirty *dirty, - const struct svga3dsurface_loc *loc_start, - const struct svga3dsurface_loc *loc_end) + const struct vmw_surface_loc *loc_start, + const struct vmw_surface_loc *loc_end) { - const struct svga3dsurface_cache *cache = &dirty->cache; + const struct vmw_surface_cache *cache = &dirty->cache; SVGA3dBox *box = &dirty->boxes[loc_start->sub_resource]; u32 mip = loc_start->sub_resource % cache->num_mip_levels; const struct drm_vmw_size *size = &cache->mip[mip].size; @@ -1760,7 +1760,7 @@ static void vmw_subres_dirty_add(struct vmw_surface_dirty *dirty, */ static void vmw_subres_dirty_full(struct vmw_surface_dirty *dirty, u32 subres) { - const struct svga3dsurface_cache *cache = &dirty->cache; + const struct vmw_surface_cache *cache = &dirty->cache; u32 mip = subres % cache->num_mip_levels; const struct drm_vmw_size *size = &cache->mip[mip].size; SVGA3dBox *box = &dirty->boxes[subres]; @@ -1783,15 +1783,15 @@ static void vmw_surface_tex_dirty_range_add(struct vmw_resource *res, struct vmw_surface_dirty *dirty = (struct vmw_surface_dirty *) res->dirty; size_t backup_end = res->backup_offset + res->backup_size; - struct svga3dsurface_loc loc1, loc2; - const struct svga3dsurface_cache *cache; + struct vmw_surface_loc loc1, loc2; + const struct vmw_surface_cache *cache; start = max_t(size_t, start, res->backup_offset) - res->backup_offset; end = min(end, backup_end) - res->backup_offset; cache = &dirty->cache; - svga3dsurface_get_loc(cache, &loc1, start); - svga3dsurface_get_loc(cache, &loc2, end - 1); - svga3dsurface_inc_loc(cache, &loc2); + vmw_surface_get_loc(cache, &loc1, start); + vmw_surface_get_loc(cache, &loc2, end - 1); + vmw_surface_inc_loc(cache, &loc2); if (loc1.sheet != loc2.sheet) { u32 sub_res; @@ -1811,12 +1811,12 @@ static void vmw_surface_tex_dirty_range_add(struct vmw_resource *res, vmw_subres_dirty_add(dirty, &loc1, &loc2); } else { /* Dirty range covers multiple sub-resources */ - struct svga3dsurface_loc loc_min, loc_max; + struct vmw_surface_loc loc_min, loc_max; u32 sub_res; - svga3dsurface_max_loc(cache, loc1.sub_resource, &loc_max); + vmw_surface_max_loc(cache, loc1.sub_resource, &loc_max); vmw_subres_dirty_add(dirty, &loc1, &loc_max); - svga3dsurface_min_loc(cache, loc2.sub_resource - 1, &loc_min); + vmw_surface_min_loc(cache, loc2.sub_resource - 1, &loc_min); vmw_subres_dirty_add(dirty, &loc_min, &loc2); for (sub_res = loc1.sub_resource + 1; sub_res < loc2.sub_resource - 1; ++sub_res) @@ -1833,7 +1833,7 @@ static void vmw_surface_buf_dirty_range_add(struct vmw_resource *res, { struct vmw_surface_dirty *dirty = (struct vmw_surface_dirty *) res->dirty; - const struct svga3dsurface_cache *cache = &dirty->cache; + const struct vmw_surface_cache *cache = &dirty->cache; size_t backup_end = res->backup_offset + cache->mip_chain_bytes; SVGA3dBox *box = &dirty->boxes[0]; u32 box_c2; @@ -1872,12 +1872,11 @@ static void vmw_surface_dirty_range_add(struct vmw_resource *res, size_t start, static int vmw_surface_dirty_sync(struct vmw_resource *res) { struct vmw_private *dev_priv = res->dev_priv; - bool has_dx = 0; u32 i, num_dirty; struct vmw_surface_dirty *dirty = (struct vmw_surface_dirty *) res->dirty; size_t alloc_size; - const struct svga3dsurface_cache *cache = &dirty->cache; + const struct vmw_surface_cache *cache = &dirty->cache; struct { SVGA3dCmdHeader header; SVGA3dCmdDXUpdateSubResource body; @@ -1899,7 +1898,7 @@ static int vmw_surface_dirty_sync(struct vmw_resource *res) if (!num_dirty) goto out; - alloc_size = num_dirty * ((has_dx) ? sizeof(*cmd1) : sizeof(*cmd2)); + alloc_size = num_dirty * ((has_sm4_context(dev_priv)) ? sizeof(*cmd1) : sizeof(*cmd2)); cmd = VMW_CMD_RESERVE(dev_priv, alloc_size); if (!cmd) return -ENOMEM; @@ -1917,7 +1916,7 @@ static int vmw_surface_dirty_sync(struct vmw_resource *res) * DX_UPDATE_SUBRESOURCE is aware of array surfaces. * UPDATE_GB_IMAGE is not. */ - if (has_dx) { + if (has_sm4_context(dev_priv)) { cmd1->header.id = SVGA_3D_CMD_DX_UPDATE_SUBRESOURCE; cmd1->header.size = sizeof(cmd1->body); cmd1->body.sid = res->id; @@ -1990,7 +1989,7 @@ static int vmw_surface_dirty_alloc(struct vmw_resource *res) } num_samples = max_t(u32, 1, metadata->multisample_count); - ret = svga3dsurface_setup_cache(&metadata->base_size, metadata->format, + ret = vmw_surface_setup_cache(&metadata->base_size, metadata->format, num_mip, num_layers, num_samples, &dirty->cache); if (ret) @@ -2081,7 +2080,7 @@ int vmw_gb_surface_define(struct vmw_private *dev_priv, *srf_out = NULL; if (req->scanout) { - if (!svga3dsurface_is_screen_target_format(req->format)) { + if (!vmw_surface_is_screen_target_format(req->format)) { VMW_DEBUG_USER("Invalid Screen Target surface format."); return -EINVAL; } @@ -2096,10 +2095,10 @@ int vmw_gb_surface_define(struct vmw_private *dev_priv, return -EINVAL; } } else { - const struct svga3d_surface_desc *desc = - svga3dsurface_get_desc(req->format); + const SVGA3dSurfaceDesc *desc = + vmw_surface_get_desc(req->format); - if (desc->block_desc == SVGA3DBLOCKDESC_NONE) { + if (desc->blockDesc == SVGA3DBLOCKDESC_NONE) { VMW_DEBUG_USER("Invalid surface format.\n"); return -EINVAL; } @@ -2148,11 +2147,12 @@ int vmw_gb_surface_define(struct vmw_private *dev_priv, sample_count = metadata->multisample_count; srf->res.backup_size = - svga3dsurface_get_serialized_size_extended(metadata->format, - metadata->base_size, - metadata->mip_levels[0], - num_layers, - sample_count); + vmw_surface_get_serialized_size_extended( + metadata->format, + metadata->base_size, + metadata->mip_levels[0], + num_layers, + sample_count); if (metadata->flags & SVGA3D_SURFACE_BIND_STREAM_OUTPUT) srf->res.backup_size += sizeof(SVGA3dDXSOState); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index 0488042fb287..b0973c27e774 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -222,36 +222,6 @@ static bool __vmw_piter_sg_next(struct vmw_piter *viter) } -/** - * __vmw_piter_non_sg_page: Helper functions to return a pointer - * to the current page. - * - * @viter: Pointer to the iterator - * - * These functions return a pointer to the page currently - * pointed to by @viter. Functions are selected depending on the - * current mapping mode. - */ -static struct page *__vmw_piter_non_sg_page(struct vmw_piter *viter) -{ - return viter->pages[viter->i]; -} - -/** - * __vmw_piter_phys_addr: Helper functions to return the DMA - * address of the current page. - * - * @viter: Pointer to the iterator - * - * These functions return the DMA address of the page currently - * pointed to by @viter. Functions are selected depending on the - * current mapping mode. - */ -static dma_addr_t __vmw_piter_phys_addr(struct vmw_piter *viter) -{ - return page_to_phys(viter->pages[viter->i]); -} - static dma_addr_t __vmw_piter_dma_addr(struct vmw_piter *viter) { return viter->addrs[viter->i]; @@ -279,13 +249,8 @@ void vmw_piter_start(struct vmw_piter *viter, const struct vmw_sg_table *vsgt, { viter->i = p_offset - 1; viter->num_pages = vsgt->num_pages; - viter->page = &__vmw_piter_non_sg_page; viter->pages = vsgt->pages; switch (vsgt->mode) { - case vmw_dma_phys: - viter->next = &__vmw_piter_non_sg_next; - viter->dma_address = &__vmw_piter_phys_addr; - break; case vmw_dma_alloc_coherent: viter->next = &__vmw_piter_non_sg_next; viter->dma_address = &__vmw_piter_dma_addr; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c index 8338b1d20f2a..b09094b50c5d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c @@ -586,13 +586,13 @@ int vmw_validation_bo_validate(struct vmw_validation_context *ctx, bool intr) container_of(entry->base.bo, typeof(*vbo), base); if (entry->cpu_blit) { - struct ttm_operation_ctx ctx = { + struct ttm_operation_ctx ttm_ctx = { .interruptible = intr, .no_wait_gpu = false }; ret = ttm_bo_validate(entry->base.bo, - &vmw_nonfixed_placement, &ctx); + &vmw_nonfixed_placement, &ttm_ctx); } else { ret = vmw_validation_bo_validate_single (entry->base.bo, intr, entry->as_mob); diff --git a/drivers/gpu/drm/xen/xen_drm_front_kms.c b/drivers/gpu/drm/xen/xen_drm_front_kms.c index 371202ebe900..cfda74490765 100644 --- a/drivers/gpu/drm/xen/xen_drm_front_kms.c +++ b/drivers/gpu/drm/xen/xen_drm_front_kms.c @@ -302,7 +302,6 @@ static const struct drm_simple_display_pipe_funcs display_funcs = { .mode_valid = display_mode_valid, .enable = display_enable, .disable = display_disable, - .prepare_fb = drm_gem_simple_display_pipe_prepare_fb, .check = display_check, .update = display_update, }; diff --git a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c index 0c1c50271a88..ac37053412a1 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c +++ b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c @@ -111,8 +111,6 @@ static int zynqmp_dpsub_drm_init(struct zynqmp_dpsub *dpsub) if (ret) return ret; - drm->irq_enabled = 1; - drm_kms_helper_poll_init(drm); /* diff --git a/drivers/gpu/drm/zte/zx_drm_drv.c b/drivers/gpu/drm/zte/zx_drm_drv.c index 5506336594e2..064056503ebb 100644 --- a/drivers/gpu/drm/zte/zx_drm_drv.c +++ b/drivers/gpu/drm/zte/zx_drm_drv.c @@ -75,12 +75,6 @@ static int zx_drm_bind(struct device *dev) goto out_unbind; } - /* - * We will manage irq handler on our own. In this case, irq_enabled - * need to be true for using vblank core support. - */ - drm->irq_enabled = true; - drm_mode_config_reset(drm); drm_kms_helper_poll_init(drm); diff --git a/drivers/video/fbdev/omap2/omapfb/dss/apply.c b/drivers/video/fbdev/omap2/omapfb/dss/apply.c index c71021091828..acca991c7540 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/apply.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/apply.c @@ -108,7 +108,7 @@ static struct { } dss_data; /* protects dss_data */ -static spinlock_t data_lock; +static DEFINE_SPINLOCK(data_lock); /* lock for blocking functions */ static DEFINE_MUTEX(apply_lock); static DECLARE_COMPLETION(extra_updated_completion); @@ -131,8 +131,6 @@ static void apply_init_priv(void) struct mgr_priv_data *mp; int i; - spin_lock_init(&data_lock); - for (i = 0; i < num_ovls; ++i) { struct ovl_priv_data *op; diff --git a/include/drm/drm_aperture.h b/include/drm/drm_aperture.h index 6c148078780c..7096703c3949 100644 --- a/include/drm/drm_aperture.h +++ b/include/drm/drm_aperture.h @@ -6,20 +6,22 @@ #include <linux/types.h> struct drm_device; +struct drm_driver; struct pci_dev; int devm_aperture_acquire_from_firmware(struct drm_device *dev, resource_size_t base, resource_size_t size); int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_size_t size, - bool primary, const char *name); + bool primary, const struct drm_driver *req_driver); -int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const char *name); +int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, + const struct drm_driver *req_driver); /** * drm_aperture_remove_framebuffers - remove all existing framebuffers * @primary: also kick vga16fb if present - * @name: requesting driver name + * @req_driver: requesting DRM driver * * This function removes all graphics device drivers. Use this function on systems * that can have their framebuffer located anywhere in memory. @@ -27,9 +29,11 @@ int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const * Returns: * 0 on success, or a negative errno code otherwise */ -static inline int drm_aperture_remove_framebuffers(bool primary, const char *name) +static inline int +drm_aperture_remove_framebuffers(bool primary, const struct drm_driver *req_driver) { - return drm_aperture_remove_conflicting_framebuffers(0, (resource_size_t)-1, primary, name); + return drm_aperture_remove_conflicting_framebuffers(0, (resource_size_t)-1, primary, + req_driver); } #endif diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h index 2195daa289d2..46bdfa48c413 100644 --- a/include/drm/drm_bridge.h +++ b/include/drm/drm_bridge.h @@ -171,6 +171,11 @@ struct drm_bridge_funcs { * signals) feeding it is still running when this callback is called. * * The @disable callback is optional. + * + * NOTE: + * + * This is deprecated, do not use! + * New drivers shall use &drm_bridge_funcs.atomic_disable. */ void (*disable)(struct drm_bridge *bridge); @@ -190,6 +195,11 @@ struct drm_bridge_funcs { * called. * * The @post_disable callback is optional. + * + * NOTE: + * + * This is deprecated, do not use! + * New drivers shall use &drm_bridge_funcs.atomic_post_disable. */ void (*post_disable)(struct drm_bridge *bridge); @@ -215,9 +225,9 @@ struct drm_bridge_funcs { * * NOTE: * - * If a need arises to store and access modes adjusted for other - * locations than the connection between the CRTC and the first bridge, - * the DRM framework will have to be extended with DRM bridge states. + * This is deprecated, do not use! + * New drivers shall set their mode in the + * &drm_bridge_funcs.atomic_enable operation. */ void (*mode_set)(struct drm_bridge *bridge, const struct drm_display_mode *mode, @@ -239,6 +249,11 @@ struct drm_bridge_funcs { * there is one) when this callback is called. * * The @pre_enable callback is optional. + * + * NOTE: + * + * This is deprecated, do not use! + * New drivers shall use &drm_bridge_funcs.atomic_pre_enable. */ void (*pre_enable)(struct drm_bridge *bridge); @@ -259,6 +274,11 @@ struct drm_bridge_funcs { * chain if there is one. * * The @enable callback is optional. + * + * NOTE: + * + * This is deprecated, do not use! + * New drivers shall use &drm_bridge_funcs.atomic_enable. */ void (*enable)(struct drm_bridge *bridge); diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 714d1a01c065..0a1d9a0fcbb2 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -848,6 +848,11 @@ struct drm_connector_funcs { * locks to avoid races with concurrent modeset changes need to use * &drm_connector_helper_funcs.detect_ctx instead. * + * Also note that this callback can be called no matter the + * state the connector is in. Drivers that need the underlying + * device to be powered to perform the detection will first need + * to make sure it's been properly enabled. + * * RETURNS: * * drm_connector_status indicating the connector's status. diff --git a/include/drm/drm_dp_aux_bus.h b/include/drm/drm_dp_aux_bus.h new file mode 100644 index 000000000000..4f19b20b1dd6 --- /dev/null +++ b/include/drm/drm_dp_aux_bus.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2021 Google Inc. + * + * The DP AUX bus is used for devices that are connected over a DisplayPort + * AUX bus. The devices on the far side of the bus are referred to as + * endpoints in this code. + */ + +#ifndef _DP_AUX_BUS_H_ +#define _DP_AUX_BUS_H_ + +#include <linux/device.h> +#include <linux/mod_devicetable.h> + +/** + * struct dp_aux_ep_device - Main dev structure for DP AUX endpoints + * + * This is used to instantiate devices that are connected via a DP AUX + * bus. Usually the device is a panel, but conceivable other devices could + * be hooked up there. + */ +struct dp_aux_ep_device { + /** @dev: The normal dev pointer */ + struct device dev; + /** @aux: Pointer to the aux bus */ + struct drm_dp_aux *aux; +}; + +struct dp_aux_ep_driver { + int (*probe)(struct dp_aux_ep_device *aux_ep); + void (*remove)(struct dp_aux_ep_device *aux_ep); + void (*shutdown)(struct dp_aux_ep_device *aux_ep); + struct device_driver driver; +}; + +static inline struct dp_aux_ep_device *to_dp_aux_ep_dev(struct device *dev) +{ + return container_of(dev, struct dp_aux_ep_device, dev); +} + +static inline struct dp_aux_ep_driver *to_dp_aux_ep_drv(struct device_driver *drv) +{ + return container_of(drv, struct dp_aux_ep_driver, driver); +} + +int of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux); +void of_dp_aux_depopulate_ep_devices(struct drm_dp_aux *aux); +int devm_of_dp_aux_populate_ep_devices(struct drm_dp_aux *aux); + +#define dp_aux_dp_driver_register(aux_ep_drv) \ + __dp_aux_dp_driver_register(aux_ep_drv, THIS_MODULE) +int __dp_aux_dp_driver_register(struct dp_aux_ep_driver *aux_ep_drv, + struct module *owner); +void dp_aux_dp_driver_unregister(struct dp_aux_ep_driver *aux_ep_drv); + +#endif /* _DP_AUX_BUS_H_ */ diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h index 3f2715eb965f..1d5b3dbb6e56 100644 --- a/include/drm/drm_dp_helper.h +++ b/include/drm/drm_dp_helper.h @@ -30,6 +30,7 @@ struct drm_device; struct drm_dp_aux; +struct drm_panel; /* * Unless otherwise noted, all values are from the DP 1.1a spec. Note that @@ -1818,6 +1819,24 @@ drm_dp_sink_can_do_video_without_timing_msa(const u8 dpcd[DP_RECEIVER_CAP_SIZE]) DP_MSA_TIMING_PAR_IGNORED; } +/** + * drm_edp_backlight_supported() - Check an eDP DPCD for VESA backlight support + * @edp_dpcd: The DPCD to check + * + * Note that currently this function will return %false for panels which support various DPCD + * backlight features but which require the brightness be set through PWM, and don't support setting + * the brightness level via the DPCD. This is a TODO. + * + * Returns: %True if @edp_dpcd indicates that VESA backlight controls are supported, %false + * otherwise + */ +static inline bool +drm_edp_backlight_supported(const u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE]) +{ + return (edp_dpcd[1] & DP_EDP_TCON_BACKLIGHT_ADJUSTMENT_CAP) && + (edp_dpcd[2] & DP_EDP_BACKLIGHT_BRIGHTNESS_AUX_SET_CAP); +} + /* * DisplayPort AUX channel */ @@ -1858,35 +1877,6 @@ struct drm_dp_aux_cec { /** * struct drm_dp_aux - DisplayPort AUX channel - * @name: user-visible name of this AUX channel and the I2C-over-AUX adapter - * @ddc: I2C adapter that can be used for I2C-over-AUX communication - * @dev: pointer to struct device that is the parent for this AUX channel - * @drm_dev: pointer to the &drm_device that owns this AUX channel. Beware, this - * may be %NULL before drm_dp_aux_register() has been called. - * @crtc: backpointer to the crtc that is currently using this AUX channel - * @hw_mutex: internal mutex used for locking transfers - * @crc_work: worker that captures CRCs for each frame - * @crc_count: counter of captured frame CRCs - * @transfer: transfers a message representing a single AUX transaction - * - * The @dev field should be set to a pointer to the device that implements the - * AUX channel. As well, the @drm_dev field should be set to the &drm_device - * that will be using this AUX channel as early as possible. For many graphics - * drivers this should happen before drm_dp_aux_init(), however it's perfectly - * fine to set this field later so long as it's assigned before calling - * drm_dp_aux_register(). - * - * The @name field may be used to specify the name of the I2C adapter. If set to - * %NULL, dev_name() of @dev will be used. - * - * Drivers provide a hardware-specific implementation of how transactions are - * executed via the @transfer() function. A pointer to a &drm_dp_aux_msg - * structure describing the transaction is passed into this function. Upon - * success, the implementation should return the number of payload bytes that - * were transferred, or a negative error-code on failure. Helpers propagate - * errors from the @transfer() function, with the exception of the %-EBUSY - * error, which causes a transaction to be retried. On a short, helpers will - * return %-EPROTO to make it simpler to check for failure. * * An AUX channel can also be used to transport I2C messages to a sink. A * typical application of that is to access an EDID that's present in the sink @@ -1897,22 +1887,96 @@ struct drm_dp_aux_cec { * transfers by default; if a partial response is received, the adapter will * drop down to the size given by the partial response for this transaction * only. - * - * Note that the aux helper code assumes that the @transfer() function only - * modifies the reply field of the &drm_dp_aux_msg structure. The retry logic - * and i2c helpers assume this is the case. */ struct drm_dp_aux { + /** + * @name: user-visible name of this AUX channel and the + * I2C-over-AUX adapter. + * + * It's also used to specify the name of the I2C adapter. If set + * to %NULL, dev_name() of @dev will be used. + */ const char *name; + + /** + * @ddc: I2C adapter that can be used for I2C-over-AUX + * communication + */ struct i2c_adapter ddc; + + /** + * @dev: pointer to struct device that is the parent for this + * AUX channel. + */ struct device *dev; + + /** + * @drm_dev: pointer to the &drm_device that owns this AUX channel. + * Beware, this may be %NULL before drm_dp_aux_register() has been + * called. + * + * It should be set to the &drm_device that will be using this AUX + * channel as early as possible. For many graphics drivers this should + * happen before drm_dp_aux_init(), however it's perfectly fine to set + * this field later so long as it's assigned before calling + * drm_dp_aux_register(). + */ struct drm_device *drm_dev; + + /** + * @crtc: backpointer to the crtc that is currently using this + * AUX channel + */ struct drm_crtc *crtc; + + /** + * @hw_mutex: internal mutex used for locking transfers. + * + * Note that if the underlying hardware is shared among multiple + * channels, the driver needs to do additional locking to + * prevent concurrent access. + */ struct mutex hw_mutex; + + /** + * @crc_work: worker that captures CRCs for each frame + */ struct work_struct crc_work; + + /** + * @crc_count: counter of captured frame CRCs + */ u8 crc_count; + + /** + * @transfer: transfers a message representing a single AUX + * transaction. + * + * This is a hardware-specific implementation of how + * transactions are executed that the drivers must provide. + * + * A pointer to a &drm_dp_aux_msg structure describing the + * transaction is passed into this function. Upon success, the + * implementation should return the number of payload bytes that + * were transferred, or a negative error-code on failure. + * + * Helpers will propagate these errors, with the exception of + * the %-EBUSY error, which causes a transaction to be retried. + * On a short, helpers will return %-EPROTO to make it simpler + * to check for failure. + * + * The @transfer() function must only modify the reply field of + * the &drm_dp_aux_msg structure. The retry logic and i2c + * helpers assume this is the case. + * + * Also note that this callback can be called no matter the + * state @dev is in. Drivers that need that device to be powered + * to perform this operation will first need to make sure it's + * been properly enabled. + */ ssize_t (*transfer)(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg); + /** * @i2c_nack_count: Counts I2C NACKs, used for DP validation. */ @@ -2124,6 +2188,51 @@ drm_dp_has_quirk(const struct drm_dp_desc *desc, enum drm_dp_quirk quirk) return desc->quirks & BIT(quirk); } +/** + * struct drm_edp_backlight_info - Probed eDP backlight info struct + * @pwmgen_bit_count: The pwmgen bit count + * @pwm_freq_pre_divider: The PWM frequency pre-divider value being used for this backlight, if any + * @max: The maximum backlight level that may be set + * @lsb_reg_used: Do we also write values to the DP_EDP_BACKLIGHT_BRIGHTNESS_LSB register? + * @aux_enable: Does the panel support the AUX enable cap? + * + * This structure contains various data about an eDP backlight, which can be populated by using + * drm_edp_backlight_init(). + */ +struct drm_edp_backlight_info { + u8 pwmgen_bit_count; + u8 pwm_freq_pre_divider; + u16 max; + + bool lsb_reg_used : 1; + bool aux_enable : 1; +}; + +int +drm_edp_backlight_init(struct drm_dp_aux *aux, struct drm_edp_backlight_info *bl, + u16 driver_pwm_freq_hz, const u8 edp_dpcd[EDP_DISPLAY_CTL_CAP_SIZE], + u16 *current_level, u8 *current_mode); +int drm_edp_backlight_set_level(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl, + u16 level); +int drm_edp_backlight_enable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl, + u16 level); +int drm_edp_backlight_disable(struct drm_dp_aux *aux, const struct drm_edp_backlight_info *bl); + +#if IS_ENABLED(CONFIG_DRM_KMS_HELPER) && (IS_BUILTIN(CONFIG_BACKLIGHT_CLASS_DEVICE) || \ + (IS_MODULE(CONFIG_DRM_KMS_HELPER) && IS_MODULE(CONFIG_BACKLIGHT_CLASS_DEVICE))) + +int drm_panel_dp_aux_backlight(struct drm_panel *panel, struct drm_dp_aux *aux); + +#else + +static inline int drm_panel_dp_aux_backlight(struct drm_panel *panel, + struct drm_dp_aux *aux) +{ + return 0; +} + +#endif + #ifdef CONFIG_DRM_DP_CEC void drm_dp_cec_irq(struct drm_dp_aux *aux); void drm_dp_cec_register_connector(struct drm_dp_aux *aux, diff --git a/include/drm/drm_gem_atomic_helper.h b/include/drm/drm_gem_atomic_helper.h index cfc5adee3d13..d82c23622156 100644 --- a/include/drm/drm_gem_atomic_helper.h +++ b/include/drm/drm_gem_atomic_helper.h @@ -53,6 +53,12 @@ to_drm_shadow_plane_state(struct drm_plane_state *state) return container_of(state, struct drm_shadow_plane_state, base); } +void __drm_gem_duplicate_shadow_plane_state(struct drm_plane *plane, + struct drm_shadow_plane_state *new_shadow_plane_state); +void __drm_gem_destroy_shadow_plane_state(struct drm_shadow_plane_state *shadow_plane_state); +void __drm_gem_reset_shadow_plane(struct drm_plane *plane, + struct drm_shadow_plane_state *shadow_plane_state); + void drm_gem_reset_shadow_plane(struct drm_plane *plane); struct drm_plane_state *drm_gem_duplicate_shadow_plane_state(struct drm_plane *plane); void drm_gem_destroy_shadow_plane_state(struct drm_plane *plane, diff --git a/include/drm/drm_gem_vram_helper.h b/include/drm/drm_gem_vram_helper.h index 27ed7e9243b9..d3cf06c9af65 100644 --- a/include/drm/drm_gem_vram_helper.h +++ b/include/drm/drm_gem_vram_helper.h @@ -124,6 +124,18 @@ void drm_gem_vram_plane_helper_cleanup_fb(struct drm_plane *plane, struct drm_plane_state *old_state); +/** + * DRM_GEM_VRAM_PLANE_HELPER_FUNCS - + * Initializes struct drm_plane_helper_funcs for VRAM handling + * + * Drivers may use GEM BOs as VRAM helpers for the framebuffer memory. This + * macro initializes struct drm_plane_helper_funcs to use the respective helper + * functions. + */ +#define DRM_GEM_VRAM_PLANE_HELPER_FUNCS \ + .prepare_fb = drm_gem_vram_plane_helper_prepare_fb, \ + .cleanup_fb = drm_gem_vram_plane_helper_cleanup_fb + /* * Helpers for struct drm_simple_display_pipe_funcs */ @@ -192,10 +204,6 @@ void drm_vram_mm_debugfs_init(struct drm_minor *minor); * Helpers for integration with struct drm_device */ -struct drm_vram_mm *drm_vram_helper_alloc_mm( - struct drm_device *dev, uint64_t vram_base, size_t vram_size); -void drm_vram_helper_release_mm(struct drm_device *dev); - int drmm_vram_helper_init(struct drm_device *dev, uint64_t vram_base, size_t vram_size); diff --git a/include/drm/drm_mipi_dbi.h b/include/drm/drm_mipi_dbi.h index f543d6e3e822..05e194958265 100644 --- a/include/drm/drm_mipi_dbi.h +++ b/include/drm/drm_mipi_dbi.h @@ -183,7 +183,12 @@ int mipi_dbi_buf_copy(void *dst, struct drm_framebuffer *fb, #define mipi_dbi_command(dbi, cmd, seq...) \ ({ \ const u8 d[] = { seq }; \ - mipi_dbi_command_stackbuf(dbi, cmd, d, ARRAY_SIZE(d)); \ + struct device *dev = &(dbi)->spi->dev; \ + int ret; \ + ret = mipi_dbi_command_stackbuf(dbi, cmd, d, ARRAY_SIZE(d)); \ + if (ret) \ + dev_err_ratelimited(dev, "error %d when sending command %#02x\n", ret, cmd); \ + ret; \ }) #ifdef CONFIG_DEBUG_FS diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h index 360e6377e84b..849d3029e303 100644 --- a/include/drm/drm_mipi_dsi.h +++ b/include/drm/drm_mipi_dsi.h @@ -80,6 +80,11 @@ int mipi_dsi_create_packet(struct mipi_dsi_packet *packet, * Note that typically DSI packet transmission is atomic, so the .transfer() * function will seldomly return anything other than the number of bytes * contained in the transmit buffer on success. + * + * Also note that those callbacks can be called no matter the state the + * host is in. Drivers that need the underlying device to be powered to + * perform these operations will first need to make sure it's been + * properly enabled. */ struct mipi_dsi_host_ops { int (*attach)(struct mipi_dsi_host *host, diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h index f3a4b47b3986..fdfa9f37ce05 100644 --- a/include/drm/drm_modeset_helper_vtables.h +++ b/include/drm/drm_modeset_helper_vtables.h @@ -1178,8 +1178,11 @@ struct drm_plane_helper_funcs { * equivalent functionality should be implemented through private * members in the plane structure. * - * Drivers which always have their buffers pinned should use - * drm_gem_plane_helper_prepare_fb() for this hook. + * For GEM drivers who neither have a @prepare_fb nor @cleanup_fb hook + * set drm_gem_plane_helper_prepare_fb() is called automatically to + * implement this. Other drivers which need additional plane processing + * can call drm_gem_plane_helper_prepare_fb() from their @prepare_fb + * hook. * * The helpers will call @cleanup_fb with matching arguments for every * successful call to this hook. diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h index 33605c3f0eba..4602f833eb51 100644 --- a/include/drm/drm_panel.h +++ b/include/drm/drm_panel.h @@ -64,8 +64,8 @@ enum drm_panel_orientation; * the panel. This is the job of the .unprepare() function. * * Backlight can be handled automatically if configured using - * drm_panel_of_backlight(). Then the driver does not need to implement the - * functionality to enable/disable backlight. + * drm_panel_of_backlight() or drm_panel_dp_aux_backlight(). Then the driver + * does not need to implement the functionality to enable/disable backlight. */ struct drm_panel_funcs { /** @@ -144,8 +144,8 @@ struct drm_panel { * Backlight device, used to turn on backlight after the call * to enable(), and to turn off backlight before the call to * disable(). - * backlight is set by drm_panel_of_backlight() and drivers - * shall not assign it. + * backlight is set by drm_panel_of_backlight() or + * drm_panel_dp_aux_backlight() and drivers shall not assign it. */ struct backlight_device *backlight; diff --git a/include/drm/drm_simple_kms_helper.h b/include/drm/drm_simple_kms_helper.h index ef9944e9c5fc..cf07132d4ee8 100644 --- a/include/drm/drm_simple_kms_helper.h +++ b/include/drm/drm_simple_kms_helper.h @@ -116,8 +116,11 @@ struct drm_simple_display_pipe_funcs { * the documentation for the &drm_plane_helper_funcs.prepare_fb hook for * more details. * - * Drivers which always have their buffers pinned should use - * drm_gem_simple_display_pipe_prepare_fb() for this hook. + * For GEM drivers who neither have a @prepare_fb nor @cleanup_fb hook + * set drm_gem_simple_display_pipe_prepare_fb() is called automatically + * to implement this. Other drivers which need additional plane + * processing can call drm_gem_simple_display_pipe_prepare_fb() from + * their @prepare_fb hook. */ int (*prepare_fb)(struct drm_simple_display_pipe *pipe, struct drm_plane_state *plane_state); diff --git a/include/drm/drm_vma_manager.h b/include/drm/drm_vma_manager.h index 76ac5e97a559..4f8c35206f7c 100644 --- a/include/drm/drm_vma_manager.h +++ b/include/drm/drm_vma_manager.h @@ -53,7 +53,7 @@ struct drm_vma_offset_node { rwlock_t vm_lock; struct drm_mm_node vm_node; struct rb_root vm_files; - bool readonly:1; + void *driver_private; }; struct drm_vma_offset_manager { diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index d18af49fd009..88ae7f331bb1 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -239,6 +239,38 @@ struct drm_sched_backend_ops { * @timedout_job: Called when a job has taken too long to execute, * to trigger GPU recovery. * + * This method is called in a workqueue context. + * + * Drivers typically issue a reset to recover from GPU hangs, and this + * procedure usually follows the following workflow: + * + * 1. Stop the scheduler using drm_sched_stop(). This will park the + * scheduler thread and cancel the timeout work, guaranteeing that + * nothing is queued while we reset the hardware queue + * 2. Try to gracefully stop non-faulty jobs (optional) + * 3. Issue a GPU reset (driver-specific) + * 4. Re-submit jobs using drm_sched_resubmit_jobs() + * 5. Restart the scheduler using drm_sched_start(). At that point, new + * jobs can be queued, and the scheduler thread is unblocked + * + * Note that some GPUs have distinct hardware queues but need to reset + * the GPU globally, which requires extra synchronization between the + * timeout handler of the different &drm_gpu_scheduler. One way to + * achieve this synchronization is to create an ordered workqueue + * (using alloc_ordered_workqueue()) at the driver level, and pass this + * queue to drm_sched_init(), to guarantee that timeout handlers are + * executed sequentially. The above workflow needs to be slightly + * adjusted in that case: + * + * 1. Stop all schedulers impacted by the reset using drm_sched_stop() + * 2. Try to gracefully stop non-faulty jobs on all queues impacted by + * the reset (optional) + * 3. Issue a GPU reset on all faulty queues (driver-specific) + * 4. Re-submit jobs on all schedulers impacted by the reset using + * drm_sched_resubmit_jobs() + * 5. Restart all schedulers that were stopped in step #1 using + * drm_sched_start() + * * Return DRM_GPU_SCHED_STAT_NOMINAL, when all is normal, * and the underlying driver has started or completed recovery. * @@ -269,6 +301,7 @@ struct drm_sched_backend_ops { * finished. * @hw_rq_count: the number of jobs currently in the hardware queue. * @job_id_count: used to assign unique id to the each job. + * @timeout_wq: workqueue used to queue @work_tdr * @work_tdr: schedules a delayed call to @drm_sched_job_timedout after the * timeout interval is over. * @thread: the kthread on which the scheduler which run. @@ -293,6 +326,7 @@ struct drm_gpu_scheduler { wait_queue_head_t job_scheduled; atomic_t hw_rq_count; atomic64_t job_id_count; + struct workqueue_struct *timeout_wq; struct delayed_work work_tdr; struct task_struct *thread; struct list_head pending_list; @@ -306,7 +340,8 @@ struct drm_gpu_scheduler { int drm_sched_init(struct drm_gpu_scheduler *sched, const struct drm_sched_backend_ops *ops, - uint32_t hw_submission, unsigned hang_limit, long timeout, + uint32_t hw_submission, unsigned hang_limit, + long timeout, struct workqueue_struct *timeout_wq, atomic_t *score, const char *name); void drm_sched_fini(struct drm_gpu_scheduler *sched); diff --git a/include/drm/ttm/ttm_placement.h b/include/drm/ttm/ttm_placement.h index aa6ba4d0cf78..8995c9e4ec1b 100644 --- a/include/drm/ttm/ttm_placement.h +++ b/include/drm/ttm/ttm_placement.h @@ -47,8 +47,11 @@ * top of the memory area, instead of the bottom. */ -#define TTM_PL_FLAG_CONTIGUOUS (1 << 19) -#define TTM_PL_FLAG_TOPDOWN (1 << 22) +#define TTM_PL_FLAG_CONTIGUOUS (1 << 0) +#define TTM_PL_FLAG_TOPDOWN (1 << 1) + +/* For multihop handling */ +#define TTM_PL_FLAG_TEMPORARY (1 << 2) /** * struct ttm_place diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index efdc56b9d95f..2b814fde0d11 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -96,6 +96,12 @@ struct dma_buf_ops { * This is called automatically for non-dynamic importers from * dma_buf_attach(). * + * Note that similar to non-dynamic exporters in their @map_dma_buf + * callback the driver must guarantee that the memory is available for + * use and cleared of any old data by the time this function returns. + * Drivers which pipeline their buffer moves internally must wait for + * all moves and clears to complete. + * * Returns: * * 0 on success, negative error code on failure. @@ -144,6 +150,15 @@ struct dma_buf_ops { * This is always called with the dmabuf->resv object locked when * the dynamic_mapping flag is true. * + * Note that for non-dynamic exporters the driver must guarantee that + * that the memory is available for use and cleared of any old data by + * the time this function returns. Drivers which pipeline their buffer + * moves internally must wait for all moves and clears to complete. + * Dynamic exporters do not need to follow this rule: For non-dynamic + * importers the buffer is already pinned through @pin, which has the + * same requirements. Dynamic importers otoh are required to obey the + * dma_resv fences. + * * Returns: * * A &sg_table scatter list of or the backing storage of the DMA buffer, @@ -274,27 +289,6 @@ struct dma_buf_ops { /** * struct dma_buf - shared buffer object - * @size: size of the buffer; invariant over the lifetime of the buffer. - * @file: file pointer used for sharing buffers across, and for refcounting. - * @attachments: list of dma_buf_attachment that denotes all devices attached, - * protected by dma_resv lock. - * @ops: dma_buf_ops associated with this buffer object. - * @lock: used internally to serialize list manipulation, attach/detach and - * vmap/unmap - * @vmapping_counter: used internally to refcnt the vmaps - * @vmap_ptr: the current vmap ptr if vmapping_counter > 0 - * @exp_name: name of the exporter; useful for debugging. - * @name: userspace-provided name; useful for accounting and debugging, - * protected by @resv. - * @name_lock: spinlock to protect name access - * @owner: pointer to exporter module; used for refcounting when exporter is a - * kernel module. - * @list_node: node for dma_buf accounting and debugging. - * @priv: exporter specific private data for this buffer object. - * @resv: reservation object linked to this dma-buf - * @poll: for userspace poll support - * @cb_excl: for userspace poll support - * @cb_shared: for userspace poll support * * This represents a shared buffer, created by calling dma_buf_export(). The * userspace representation is a normal file descriptor, which can be created by @@ -306,30 +300,161 @@ struct dma_buf_ops { * Device DMA access is handled by the separate &struct dma_buf_attachment. */ struct dma_buf { + /** + * @size: + * + * Size of the buffer; invariant over the lifetime of the buffer. + */ size_t size; + + /** + * @file: + * + * File pointer used for sharing buffers across, and for refcounting. + * See dma_buf_get() and dma_buf_put(). + */ struct file *file; + + /** + * @attachments: + * + * List of dma_buf_attachment that denotes all devices attached, + * protected by &dma_resv lock @resv. + */ struct list_head attachments; + + /** @ops: dma_buf_ops associated with this buffer object. */ const struct dma_buf_ops *ops; + + /** + * @lock: + * + * Used internally to serialize list manipulation, attach/detach and + * vmap/unmap. Note that in many cases this is superseeded by + * dma_resv_lock() on @resv. + */ struct mutex lock; + + /** + * @vmapping_counter: + * + * Used internally to refcnt the vmaps returned by dma_buf_vmap(). + * Protected by @lock. + */ unsigned vmapping_counter; + + /** + * @vmap_ptr: + * The current vmap ptr if @vmapping_counter > 0. Protected by @lock. + */ struct dma_buf_map vmap_ptr; + + /** + * @exp_name: + * + * Name of the exporter; useful for debugging. See the + * DMA_BUF_SET_NAME IOCTL. + */ const char *exp_name; + + /** + * @name: + * + * Userspace-provided name; useful for accounting and debugging, + * protected by dma_resv_lock() on @resv and @name_lock for read access. + */ const char *name; + + /** @name_lock: Spinlock to protect name acces for read access. */ spinlock_t name_lock; + + /** + * @owner: + * + * Pointer to exporter module; used for refcounting when exporter is a + * kernel module. + */ struct module *owner; + + /** @list_node: node for dma_buf accounting and debugging. */ struct list_head list_node; + + /** @priv: exporter specific private data for this buffer object. */ void *priv; + + /** + * @resv: + * + * Reservation object linked to this dma-buf. + * + * IMPLICIT SYNCHRONIZATION RULES: + * + * Drivers which support implicit synchronization of buffer access as + * e.g. exposed in `Implicit Fence Poll Support`_ must follow the + * below rules. + * + * - Drivers must add a shared fence through dma_resv_add_shared_fence() + * for anything the userspace API considers a read access. This highly + * depends upon the API and window system. + * + * - Similarly drivers must set the exclusive fence through + * dma_resv_add_excl_fence() for anything the userspace API considers + * write access. + * + * - Drivers may just always set the exclusive fence, since that only + * causes unecessarily synchronization, but no correctness issues. + * + * - Some drivers only expose a synchronous userspace API with no + * pipelining across drivers. These do not set any fences for their + * access. An example here is v4l. + * + * DYNAMIC IMPORTER RULES: + * + * Dynamic importers, see dma_buf_attachment_is_dynamic(), have + * additional constraints on how they set up fences: + * + * - Dynamic importers must obey the exclusive fence and wait for it to + * signal before allowing access to the buffer's underlying storage + * through the device. + * + * - Dynamic importers should set fences for any access that they can't + * disable immediately from their &dma_buf_attach_ops.move_notify + * callback. + */ struct dma_resv *resv; - /* poll support */ + /** @poll: for userspace poll support */ wait_queue_head_t poll; + /** @cb_excl: for userspace poll support */ + /** @cb_shared: for userspace poll support */ struct dma_buf_poll_cb_t { struct dma_fence_cb cb; wait_queue_head_t *poll; __poll_t active; } cb_excl, cb_shared; +#ifdef CONFIG_DMABUF_SYSFS_STATS + /** + * @sysfs_entry: + * + * For exposing information about this buffer in sysfs. See also + * `DMA-BUF statistics`_ for the uapi this enables. + */ + struct dma_buf_sysfs_entry { + struct kobject kobj; + struct dma_buf *dmabuf; + + /** + * @sysfs_entry.attachment_uid: + * + * This is protected by the dma_resv_lock() on @resv and is + * incremented on each attach. + */ + unsigned int attachment_uid; + struct kset *attach_stats_kset; + } *sysfs_entry; +#endif }; /** @@ -379,6 +504,7 @@ struct dma_buf_attach_ops { * @importer_ops: importer operations for this attachment, if provided * dma_buf_map/unmap_attachment() must be called with the dma_resv lock held. * @importer_priv: importer specific attachment data. + * @sysfs_entry: For exposing information about this attachment in sysfs. * * This structure holds the attachment information between the dma_buf buffer * and its user device(s). The list contains one attachment struct per device @@ -399,6 +525,13 @@ struct dma_buf_attachment { const struct dma_buf_attach_ops *importer_ops; void *importer_priv; void *priv; +#ifdef CONFIG_DMABUF_SYSFS_STATS + /* for sysfs stats */ + struct dma_buf_attach_sysfs_entry { + struct kobject kobj; + unsigned int map_counter; + } *sysfs_entry; +#endif }; /** diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 10462a029da2..54fe3443fd2c 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -12,25 +12,41 @@ #include <linux/dma-fence.h> #include <linux/irq_work.h> +#include <linux/slab.h> /** * struct dma_fence_chain - fence to represent an node of a fence chain * @base: fence base class - * @lock: spinlock for fence handling * @prev: previous fence of the chain * @prev_seqno: original previous seqno before garbage collection * @fence: encapsulated fence - * @cb: callback structure for signaling - * @work: irq work item for signaling + * @lock: spinlock for fence handling */ struct dma_fence_chain { struct dma_fence base; - spinlock_t lock; struct dma_fence __rcu *prev; u64 prev_seqno; struct dma_fence *fence; - struct dma_fence_cb cb; - struct irq_work work; + union { + /** + * @cb: callback for signaling + * + * This is used to add the callback for signaling the + * complection of the fence chain. Never used at the same time + * as the irq work. + */ + struct dma_fence_cb cb; + + /** + * @work: irq work item for signaling + * + * Irq work structure to allow us to add the callback without + * running into lock inversion. Never used at the same time as + * the callback. + */ + struct irq_work work; + }; + spinlock_t lock; }; extern const struct dma_fence_ops dma_fence_chain_ops; @@ -52,6 +68,30 @@ to_dma_fence_chain(struct dma_fence *fence) } /** + * dma_fence_chain_alloc + * + * Returns a new struct dma_fence_chain object or NULL on failure. + */ +static inline struct dma_fence_chain *dma_fence_chain_alloc(void) +{ + return kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL); +}; + +/** + * dma_fence_chain_free + * @chain: chain node to free + * + * Frees up an allocated but not used struct dma_fence_chain object. This + * doesn't need an RCU grace period since the fence was never initialized nor + * published. After dma_fence_chain_init() has been called the fence must be + * released by calling dma_fence_put(), and not through this function. + */ +static inline void dma_fence_chain_free(struct dma_fence_chain *chain) +{ + kfree(chain); +}; + +/** * dma_fence_chain_for_each - iterate over all fences in chain * @iter: current fence * @head: starting point diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index d043752a74cf..e1f49dd241f7 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -635,8 +635,8 @@ struct drm_gem_open { /** * DRM_CAP_VBLANK_HIGH_CRTC * - * If set to 1, the kernel supports specifying a CRTC index in the high bits of - * &drm_wait_vblank_request.type. + * If set to 1, the kernel supports specifying a :ref:`CRTC index<crtc_index>` + * in the high bits of &drm_wait_vblank_request.type. * * Starting kernel version 2.6.39, this capability is always set to 1. */ diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h index 9b6722d45f36..98bf130feda5 100644 --- a/include/uapi/drm/drm_mode.h +++ b/include/uapi/drm/drm_mode.h @@ -312,16 +312,48 @@ struct drm_mode_set_plane { __u32 src_w; }; +/** + * struct drm_mode_get_plane - Get plane metadata. + * + * Userspace can perform a GETPLANE ioctl to retrieve information about a + * plane. + * + * To retrieve the number of formats supported, set @count_format_types to zero + * and call the ioctl. @count_format_types will be updated with the value. + * + * To retrieve these formats, allocate an array with the memory needed to store + * @count_format_types formats. Point @format_type_ptr to this array and call + * the ioctl again (with @count_format_types still set to the value returned in + * the first ioctl call). + */ struct drm_mode_get_plane { + /** + * @plane_id: Object ID of the plane whose information should be + * retrieved. Set by caller. + */ __u32 plane_id; + /** @crtc_id: Object ID of the current CRTC. */ __u32 crtc_id; + /** @fb_id: Object ID of the current fb. */ __u32 fb_id; + /** + * @possible_crtcs: Bitmask of CRTC's compatible with the plane. CRTC's + * are created and they receive an index, which corresponds to their + * position in the bitmask. Bit N corresponds to + * :ref:`CRTC index<crtc_index>` N. + */ __u32 possible_crtcs; + /** @gamma_size: Never used. */ __u32 gamma_size; + /** @count_format_types: Number of formats. */ __u32 count_format_types; + /** + * @format_type_ptr: Pointer to ``__u32`` array of formats that are + * supported by the plane. These formats do not require modifiers. + */ __u64 format_type_ptr; }; diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h index 02e917507479..9078775feb51 100644 --- a/include/uapi/drm/vmwgfx_drm.h +++ b/include/uapi/drm/vmwgfx_drm.h @@ -72,6 +72,9 @@ extern "C" { #define DRM_VMW_GB_SURFACE_CREATE_EXT 27 #define DRM_VMW_GB_SURFACE_REF_EXT 28 #define DRM_VMW_MSG 29 +#define DRM_VMW_MKSSTAT_RESET 30 +#define DRM_VMW_MKSSTAT_ADD 31 +#define DRM_VMW_MKSSTAT_REMOVE 32 /*************************************************************************/ /** @@ -1236,6 +1239,44 @@ struct drm_vmw_msg_arg { __u32 receive_len; }; +/** + * struct drm_vmw_mksstat_add_arg + * + * @stat: Pointer to user-space stat-counters array, page-aligned. + * @info: Pointer to user-space counter-infos array, page-aligned. + * @strs: Pointer to user-space stat strings, page-aligned. + * @stat_len: Length in bytes of stat-counters array. + * @info_len: Length in bytes of counter-infos array. + * @strs_len: Length in bytes of the stat strings, terminators included. + * @description: Pointer to instance descriptor string; will be truncated + * to MKS_GUEST_STAT_INSTANCE_DESC_LENGTH chars. + * @id: Output identifier of the produced record; -1 if error. + * + * Argument to the DRM_VMW_MKSSTAT_ADD ioctl. + */ +struct drm_vmw_mksstat_add_arg { + __u64 stat; + __u64 info; + __u64 strs; + __u64 stat_len; + __u64 info_len; + __u64 strs_len; + __u64 description; + __u64 id; +}; + +/** + * struct drm_vmw_mksstat_remove_arg + * + * @id: Identifier of the record being disposed, originally obtained through + * DRM_VMW_MKSSTAT_ADD ioctl. + * + * Argument to the DRM_VMW_MKSSTAT_REMOVE ioctl. + */ +struct drm_vmw_mksstat_remove_arg { + __u64 id; +}; + #if defined(__cplusplus) } #endif diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index 7f30393b92c3..8e4a2ca0bcbf 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -22,8 +22,56 @@ #include <linux/types.h> -/* begin/end dma-buf functions used for userspace mmap. */ +/** + * struct dma_buf_sync - Synchronize with CPU access. + * + * When a DMA buffer is accessed from the CPU via mmap, it is not always + * possible to guarantee coherency between the CPU-visible map and underlying + * memory. To manage coherency, DMA_BUF_IOCTL_SYNC must be used to bracket + * any CPU access to give the kernel the chance to shuffle memory around if + * needed. + * + * Prior to accessing the map, the client must call DMA_BUF_IOCTL_SYNC + * with DMA_BUF_SYNC_START and the appropriate read/write flags. Once the + * access is complete, the client should call DMA_BUF_IOCTL_SYNC with + * DMA_BUF_SYNC_END and the same read/write flags. + * + * The synchronization provided via DMA_BUF_IOCTL_SYNC only provides cache + * coherency. It does not prevent other processes or devices from + * accessing the memory at the same time. If synchronization with a GPU or + * other device driver is required, it is the client's responsibility to + * wait for buffer to be ready for reading or writing before calling this + * ioctl with DMA_BUF_SYNC_START. Likewise, the client must ensure that + * follow-up work is not submitted to GPU or other device driver until + * after this ioctl has been called with DMA_BUF_SYNC_END? + * + * If the driver or API with which the client is interacting uses implicit + * synchronization, waiting for prior work to complete can be done via + * poll() on the DMA buffer file descriptor. If the driver or API requires + * explicit synchronization, the client may have to wait on a sync_file or + * other synchronization primitive outside the scope of the DMA buffer API. + */ struct dma_buf_sync { + /** + * @flags: Set of access flags + * + * DMA_BUF_SYNC_START: + * Indicates the start of a map access session. + * + * DMA_BUF_SYNC_END: + * Indicates the end of a map access session. + * + * DMA_BUF_SYNC_READ: + * Indicates that the mapped DMA buffer will be read by the + * client via the CPU map. + * + * DMA_BUF_SYNC_WRITE: + * Indicates that the mapped DMA buffer will be written by the + * client via the CPU map. + * + * DMA_BUF_SYNC_RW: + * An alias for DMA_BUF_SYNC_READ | DMA_BUF_SYNC_WRITE. + */ __u64 flags; }; |