kernel.git/drivers/gpu/drm/i915/i915_gem_execbuffer.c, branch linux-5.2.y

Merge tag 'drm-next-2019-05-09' of git://anongit.freedesktop.org/drm/drm

2019-05-09T04:35:19Z

Pull drm updates from Dave Airlie: "This has two exciting community drivers for ARM Mali accelerators. Since ARM has never been open source friendly on the GPU side of the house, the community has had to create open source drivers for the Mali GPUs. Lima covers the older t4xx and panfrost the newer 6xx/7xx series. Well done to all involved and hopefully this will help ARM head in the right direction. There is also now the ability if you don't have any of the legacy drivers enabled (pre-KMS) to remove all the pre-KMS support code from the core drm, this saves 10% or so in codesize on my machine. i915 also enable Icelake/Elkhart Lake Gen11 GPUs by default, vboxvideo moves out of staging. There are also some rcar-du patches which crossover with media tree but all should be acked by Mauro. Summary: uapi changes: - Colorspace connector property - fourcc - new YUV formts - timeline sync objects initially merged - expose FB_DAMAGE_CLIPS to atomic userspace new drivers: - vboxvideo: moved out of staging - aspeed: ASPEED SoC BMC chip display support - lima: ARM Mali4xx GPU acceleration driver support - panfrost: ARM Mali6xx/7xx Midgard/Bitfrost acceleration driver support core: - component helper docs - unplugging fixes - devm device init - MIPI/DSI rate control - shmem backed gem objects - connector, display_info, edid_quirks cleanups - dma_buf fence chain support - 64-bit dma-fence seqno comparison fixes - move initial fb config code to core - gem fence array helpers for Lima - ability to remove legacy support code if no drivers requires it (removes 10% of drm.ko size) - lease fixes ttm: - unified DRM_FILE_PAGE_OFFSET handling - Account for kernel allocations in kernel zone only panel: - OSD070T1718-19TS panel support - panel-tpo-td028ttec1 backlight support - Ronbo RB070D30 MIPI/DSI - Feiyang FY07024DI26A30-D MIPI-DSI panel - Rocktech jh057n00900 MIPI-DSI panel i915: - Comet Lake (Gen9) PCI IDs - Updated Icelake PCI IDs - Elkhartlake (Gen11) support - DP MST property addtions - plane and watermark fixes - Icelake port sync and VEBOX disable fixes - struct_mutex usage reduction - Icelake gamma fix - GuC reset fixes - make mmap more asynchronous - sound display power well race fixes - DDI/MIPI-DSI clocks for Icelake - Icelake RPS frequency changing support - Icelake workarounds amdgpu: - Use HMM for userptr - vega20 experimental smu11 support - RAS support for vega20 - BACO support for vega12 + fixes for vega20 - reworked IH interrupt handling - amdkfd RAS support - Freesync improvements - initial timeline sync object support - DC Z ordering fixes - NV12 planes support - colorspace properties for planes= - eDP opts if eDP already initialized nouveau: - misc fixes etnaviv: - misc fixes msm: - GPU zap shader support expansion - robustness ABI addition exynos: - Logging cleanups tegra: - Shared reset fix - CPU cache maintenance fix cirrus: - driver rewritten using simple helpers meson: - G12A support vmwgfx: - Resource dirtying management improvements - Userspace logging improvements virtio: - PRIME fixes rockchip: - rk3066 hdmi support sun4i: - DSI burst mode support vc4: - load tracker to detect underflow v3d: - v3d v4.2 support malidp: - initial Mali D71 support in komeda driver tfp410: - omap related improvement omapdrm: - drm bridge/panel support - drop some omap specific panels rcar-du: - Display writeback support" * tag 'drm-next-2019-05-09' of git://anongit.freedesktop.org/drm/drm: (1507 commits) drm/msm/a6xx: No zap shader is not an error drm/cma-helper: Fix drm_gem_cma_free_object() drm: Fix timestamp docs for variable refresh properties. drm/komeda: Mark the local functions as static drm/komeda: Fixed warning: Function parameter or member not described drm/komeda: Expose bus_width to Komeda-CORE drm/komeda: Add sysfs attribute: core_id and config_id drm: add non-desktop quirk for Valve HMDs drm/panfrost: Show stored feature registers drm/panfrost: Don't scream about deferred probe drm/panfrost: Disable PM on probe failure drm/panfrost: Set DMA masks earlier drm/panfrost: Add sanity checks to submit IOCTL drm/etnaviv: initialize idle mask before querying the HW db drm: introduce a capability flag for syncobj timeline support drm: report consistent errors when checking syncobj capibility drm/nouveau/nouveau: forward error generated while resuming objects tree drm/nouveau/fb/ramgk104: fix spelling mistake "sucessfully" -> "successfully" drm/nouveau/i2c: Disable i2c bus access after ->fini() drm/nouveau: Remove duplicate ACPI_VIDEO_NOTIFY_PROBE definition ...

i915, uaccess: Fix redundant CLAC

2019-04-03T07:36:28Z

New tooling noticed this: drivers/gpu/drm/i915/i915_gem_execbuffer.o: warning: objtool: .altinstr_replacement+0x3c: redundant UACCESS disable drivers/gpu/drm/i915/i915_gem_execbuffer.o: warning: objtool: .altinstr_replacement+0x66: redundant UACCESS disable You don't need user_access_end() if user_access_begin() fails. Signed-off-by: Peter Zijlstra (Intel) Cc: Borislav Petkov Cc: Chris Wilson Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar

drm/i915: Flush pages on acquisition

2019-03-21T17:28:12Z

When we return pages to the system, we ensure that they are marked as being in the CPU domain since any external access is uncontrolled and we must assume the worst. This means that we need to always flush the pages on acquisition if we need to use them on the GPU, and from the beginning have used set-domain. Set-domain is overkill for the purpose as it is a general synchronisation barrier, but our intent is to only flush the pages being swapped in. If we move that flush into the pages acquisition phase, we know then that when we have obj->mm.pages, they are coherent with the GPU and need only maintain that status without resorting to heavy handed use of set-domain. The principle knock-on effect for userspace is through mmap-gtt pagefaulting. Our uAPI has always implied that the GTT mmap was async (especially as when any pagefault occurs is unpredicatable to userspace) and so userspace had to apply explicit domain control itself (set-domain). However, swapping is transparent to the kernel, and so on first fault we need to acquire the pages and make them coherent for access through the GTT. Our use of set-domain here leaks into the uABI that the first pagefault was synchronous. This is unintentional and baring a few igt should be unoticed, nevertheless we bump the uABI version for mmap-gtt to reflect the change in behaviour. Another implication of the change is that gem_create() is presumed to create an object that is coherent with the CPU and is in the CPU write domain, so a set-domain(CPU) following a gem_create() would be a minor operation that merely checked whether we could allocate all pages for the object. On applying this change, a set-domain(CPU) causes a clflush as we acquire the pages. This will have a small impact on mesa as we move the clflush here on !llc from execbuf time to create, but that should have minimal performance impact as the same clflush exists but is now done early and because of the clflush issue, userspace recycles bo and so should resist allocating fresh objects. Internally, the presumption that objects are created in the CPU write-domain and remain so through writes to obj->mm.mapping is more prevalent than I expected; but easy enough to catch and apply a manual flush. For the future, we should push the page flush from the central set_pages() into the callers so that we can more finely control when it is applied, but for now doing it one location is easier to validate, at the cost of sometimes flushing when there is no need. Signed-off-by: Chris Wilson Cc: Matthew Auld Cc: Daniele Ceraolo Spurio Cc: Antonio Argenziano Cc: Joonas Lahtinen Reviewed-by: Matthew Auld Link: https://patchwork.freedesktop.org/patch/msgid/20190321161908.8007-1-chris@chris-wilson.co.uk

drm/i915: Move over to intel_context_lookup()

2019-03-08T13:59:52Z

In preparation for an ever growing number of engines and so ever increasing static array of HW contexts within the GEM context, move the array over to an rbtree, allocated upon first use. Unfortunately, this imposes an rbtree lookup at a few frequent callsites, but we should be able to mitigate those by moving over to using the HW context as our primary type and so only incur the lookup on the boundary with the user GEM context and engines. v2: Check for no HW context in guc_stage_desc_init Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20190308132522.21573-4-chris@chris-wilson.co.uk

drm/i915: Store the BIT(engine->id) as the engine's mask

2019-03-05T18:19:50Z

In the next patch, we are introducing a broad virtual engine to encompass multiple physical engines, losing the 1:1 nature of BIT(engine->id). To reflect the broader set of engines implied by the virtual instance, lets store the full bitmask. v2: Use intel_engine_mask_t (s/ring_mask/engine_mask/) v3: Tvrtko voted for moah churn so teach everyone to not mention ring and use $class$instance throughout. v4: Comment upon the disparity in bspec for using VCS1,VCS2 in gen8 and VCS[0-4] in later gen. We opt to keep the code consistent and use 0-index naming throughout. Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20190305180332.30900-1-chris@chris-wilson.co.uk

drm/i915: Re-arrange execbuf so context is known before engine

2019-03-01T22:25:11Z

Needed for a following patch. Signed-off-by: Tvrtko Ursulin Reviewed-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20190301140404.26690-23-chris@chris-wilson.co.uk Signed-off-by: Chris Wilson

drm/i915: Make object/vma allocation caches global

2019-02-28T11:08:02Z

As our allocations are not device specific, we can move our slab caches to a global scope. Signed-off-by: Chris Wilson Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20190228102035.5857-2-chris@chris-wilson.co.uk

drm/i915: remove redundant likely/unlikely annotation

2019-02-21T16:01:00Z

unlikely has already included in IS_ERR(), so just remove redundant likely/unlikely annotation. Signed-off-by: Chengguang Xu Reviewed-by: Chris Wilson Signed-off-by: Chris Wilson Link: https://patchwork.freedesktop.org/patch/msgid/20190221020819.21832-1-cgxu519@gmx.com

drm/i915: Hack and slash, throttle execbuffer hogs

2019-02-07T16:13:21Z

Apply backpressure to hogs that emit requests faster than the GPU can process them by waiting for their ring to be less than half-full before proceeding with taking the struct_mutex. This is a gross hack to apply throttling backpressure, the long term goal is to remove the struct_mutex contention so that each client naturally waits, preferably in an asynchronous, nonblocking fashion (pipelined operations for the win), for their own resources and never blocks another client within the driver at least. (Realtime priority goals would extend to ensuring that resource contention favours high priority clients as well.) This patch only limits excessive request production and does not attempt to throttle clients that block waiting for eviction (either global GTT or system memory) or any other global resources, see above for the long term goal. No microbenchmarks are harmed (to the best of my knowledge). Testcase: igt/gem_exec_schedule/pi-ringfull-* Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Cc: Joonas Lahtinen Cc: John Harrison Reviewed-by: Joonas Lahtinen Link: https://patchwork.freedesktop.org/patch/msgid/20190207071829.5574-1-chris@chris-wilson.co.uk

drm/i915: Identify active requests

2019-01-29T19:59:59Z

To allow requests to forgo a common execution timeline, one question we need to be able to answer is "is this request running?". To track whether a request has started on HW, we can emit a breadcrumb at the beginning of the request and check its timeline's HWSP to see if the breadcrumb has advanced past the start of this request. (This is in contrast to the global timeline where we need only ask if we are on the global timeline and if the timeline has advanced past the end of the previous request.) There is still confusion from a preempted request, which has already started but relinquished the HW to a high priority request. For the common case, this discrepancy should be negligible. However, for identification of hung requests, knowing which one was running at the time of the hang will be much more important. Signed-off-by: Chris Wilson Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20190129185452.20989-2-chris@chris-wilson.co.uk