Merge tag 'drm-next-2023-04-24' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "There is a new Qualcomm accel driver for their QAIC, dma-fence got a
  deadline feature added, lots of refactoring around fbdev emulation,
  and the usual pre-release hw enablements from AMD and Intel and fixes
  everywhere.

  New drivers:
   - add QAIC acceleration driver

  dma-buf:
   - constify kobj_type structs
   - Reject prime DMA-Buf attachment if get_sg_table is missing.

  fbdev:
   - cmdline parser fixes
   - implement fbdev emulation for GEM DMA drivers
   - always use shadow buffer in fbdev emulation helpers

  dma-fence:
   - add deadline hint to fences
   - signal private stub fence

  core:
   - improve DisplayID 2.0 and EDID parsing
   - add gem eviction function + callback
   - prep to convert shmem helper to GEM resv lock
   - move suballocator from radeon/amdgpu to core for Xe
   - HPD polling fixes
   - Documentation improvements
   - Add atomic enable_plane callback
   - use tgid instead of pid for client tracking
   - DP: Add SDP Error Detection Configuration Register
   - Add prime import/export to vram-helper
   - use pci aperture helpers in more drivers

  panel:
   - Radxa 8/10HD support
   - Samsung AMD495QA01 support
   - Elida KD50T048A
   - Sony TD4353
   - Novatek NT36523
   - STARRY 2081101QFH032011-53G
   - B133UAN01.0
   - AUO NE135FBM-N41

  i915:
   - More MTL enabling
   - fix s/r problems with MEI/PXP
   - Implement fb_dirty for PSR,FBC,DRRS fixes
   - Fix eDP+DSI dual panel systems
   - Fix issue #6333: "list_add corruption" and full system lockup from
     performance monitoring
   - Don't use stolen memory or BAR for ring buffers on LLC platforms
   - Make sure DSM size has correct 1MiB granularity on Gen12+
   - Whitelist COMMON_SLICE_CHICKEN3 for UMD access on Gen12+
   - Add engine TLB invalidation for Meteorlake
   - Fix GSC races on driver load/unload on Meteorlake+
   - Make kobj_type structures constant
   - Move fd_install after last use of fence
   - wm/vblank refactoring
   - display code refactoring
   - Create GSC submission targeting HDCP and PXP usages on MTL+
   - Enable HDCP2.x via GSC CS
   - Fix context runtime accounting on sysfs fdinfo for heavy workloads
   - Use i915 instead of dev_priv insied the file_priv structure
   - Replace fake flex-array with flexible-array member

  amdgpu:
   - Make kobj structures const
   - Generalize dmabuf import to work with KFD
   - Add capped/uncapped workload handling for supported APUs
   - Expose additional memory stats via fdinfo
   - Register vga_switcheroo for apple-gmux
   - Initial NBIO7.9, GC 9.4.3, GFXHUB 1.2, MMHUB 1.8 support
   - Initial DC FAM infrastructure
   - Link DC backlight to connector device rather than PCI device
   - Add sysfs nodes for secondary VCN clocks

  amdkfd:
   - Make kobj structures const
   - Support for exporting buffers via dmabuf
   - Multi-VMA page migration fixes
   - initial GC 9.4.3 support

  radeon:
   - iMac fix
   - convert to client based fbdev emulation

  habanalabs:
   - Add opcodes to the CS ioctl to allow user to stall/resume specific
     engines inside Gaudi2.
   - INFO ioctl the amount of device memory that the driver and f/w
     reserve for themselves.
   - INFO ioctl a bit-mask of the available rotator engines
   - INFO ioctl the register's address of the f/w that should be used to
     trigger interrupts
   - INFO ioctl two new opcodes to fetch information on h/w and f/w
     events
   - Enable graceful reset mechanism for compute-reset.
   - Align to the latest firmware specs.
   - Enforce the release order of the compute device and dma-buf.

  msm:
   - UBWC decoder programming rework
   - SM8550, SM8450 bindings update
   - uapi C++ fix
   - a3xx and a4xx devfreq support
   - GPU and GEM updates to avoid allocations which could trigger
     reclaim (shrinker) in fence signaling path
   - dma-fence deadline hint support and wait-boost
   - a640/650 speed bin support

  cirrus:
   - convert to regular atomic helpers
   - add damage clipping

  mediatek:
   - 10-bit overlay support
   - mt8195 support
   - Only trigger DRM HPD events if bridge is attached
   - Change the aux retries times when receiving AUX_DEFER

  rockchip:
   - add 4K support

  vc4:
   - use drm_gem_objects

  virtio:
   - allow KMS support to be disabled
   - add damage clipping

  vmwgfx:
   - buffer object lifetime fixes

  exynos:
   - move MIPI DSI driver to drm bridge for iMX sharing
   - use kernel fbdev emulation

  panfrost:
   - add support for mali MT81xx devices
   - add speed binning support

  lima:
   - add usage stats

  tegra:
   - fbdev client conversion

  vkms:
   - Add primary plane positioning support"

* tag 'drm-next-2023-04-24' of git://anongit.freedesktop.org/drm/drm: (1495 commits)
  drm/i915/dp_mst: Fix active port PLL selection for secondary MST streams
  drm/exynos: Implement fbdev emulation as in-kernel client
  drm/exynos: Initialize fbdev DRM client
  drm/exynos: Remove fb_helper from struct exynos_drm_private
  drm/exynos: Remove struct exynos_drm_fbdev
  drm/exynos: Remove exynos_gem from struct exynos_drm_fbdev
  drm/i915: Fix memory leaks in i915 selftests
  drm/i915: Make intel_get_crtc_new_encoder() less oopsy
  drm/i915/gt: Avoid out-of-bounds access when loading HuC
  drm/amdgpu: add some basic elements for multiple XCD case
  drm/amdgpu: move vmhub out of amdgpu_ring_funcs (v4)
  Revert "drm/amdgpu: enable ras for mp0 v13_0_10 on SRIOV"
  drm/amdgpu: add common ip block for GC 9.4.3
  drm/amd/display: Add logging when DP link training Clock recovery is Successful
  drm/amdgpu: add common early init support for GC 9.4.3
  drm/amdgpu: switch to v9_4_3 gfx_funcs callbacks for GC 9.4.3
  drm/amd/display: Add logging when setting DP sink power state fails
  drm/amdkfd: Add gfx_target_version for GC 9.4.3
  drm/amdkfd: Enable HW_UPDATE_RPTR on GC 9.4.3
  drm/amdgpu: reserve the old gc_11_0_*_mes.bin
  ...

1 files changed, 38 insertions, 10 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 93207badf83f..35b8106816a1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -126,6 +126,27 @@ struct amdgpu_bo_vm {
 	struct amdgpu_vm_bo_base        entries[];
 };
 
+struct amdgpu_mem_stats {
+	/* current VRAM usage, includes visible VRAM */
+	uint64_t vram;
+	/* current visible VRAM usage */
+	uint64_t visible_vram;
+	/* current GTT usage */
+	uint64_t gtt;
+	/* current system memory usage */
+	uint64_t cpu;
+	/* sum of evicted buffers, includes visible VRAM */
+	uint64_t evicted_vram;
+	/* sum of evicted buffers due to CPU access */
+	uint64_t evicted_visible_vram;
+	/* how much userspace asked for, includes vis.VRAM */
+	uint64_t requested_vram;
+	/* how much userspace asked for */
+	uint64_t requested_visible_vram;
+	/* how much userspace asked for */
+	uint64_t requested_gtt;
+};
+
 static inline struct amdgpu_bo *ttm_to_amdgpu_bo(struct ttm_buffer_object *tbo)
 {
 	return container_of(tbo, struct amdgpu_bo, tbo);
@@ -325,8 +346,8 @@ int amdgpu_bo_sync_wait_resv(struct amdgpu_device *adev, struct dma_resv *resv,
 int amdgpu_bo_sync_wait(struct amdgpu_bo *bo, void *owner, bool intr);
 u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo);
 u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo);
-void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem,
-				uint64_t *gtt_mem, uint64_t *cpu_mem);
+void amdgpu_bo_get_memory(struct amdgpu_bo *bo,
+			  struct amdgpu_mem_stats *stats);
 void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo);
 int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow,
 			     struct dma_fence **fence);
@@ -336,15 +357,22 @@ uint32_t amdgpu_bo_get_preferred_domain(struct amdgpu_device *adev,
 /*
  * sub allocation
  */
+static inline struct amdgpu_sa_manager *
+to_amdgpu_sa_manager(struct drm_suballoc_manager *manager)
+{
+	return container_of(manager, struct amdgpu_sa_manager, base);
+}
 
-static inline uint64_t amdgpu_sa_bo_gpu_addr(struct amdgpu_sa_bo *sa_bo)
+static inline uint64_t amdgpu_sa_bo_gpu_addr(struct drm_suballoc *sa_bo)
 {
-	return sa_bo->manager->gpu_addr + sa_bo->soffset;
+	return to_amdgpu_sa_manager(sa_bo->manager)->gpu_addr +
+		drm_suballoc_soffset(sa_bo);
 }
 
-static inline void * amdgpu_sa_bo_cpu_addr(struct amdgpu_sa_bo *sa_bo)
+static inline void *amdgpu_sa_bo_cpu_addr(struct drm_suballoc *sa_bo)
 {
-	return sa_bo->manager->cpu_ptr + sa_bo->soffset;
+	return to_amdgpu_sa_manager(sa_bo->manager)->cpu_ptr +
+		drm_suballoc_soffset(sa_bo);
 }
 
 int amdgpu_sa_bo_manager_init(struct amdgpu_device *adev,
@@ -355,11 +383,11 @@ void amdgpu_sa_bo_manager_fini(struct amdgpu_device *adev,
 int amdgpu_sa_bo_manager_start(struct amdgpu_device *adev,
 				      struct amdgpu_sa_manager *sa_manager);
 int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager,
-		     struct amdgpu_sa_bo **sa_bo,
-		     unsigned size, unsigned align);
+		     struct drm_suballoc **sa_bo,
+		     unsigned int size);
 void amdgpu_sa_bo_free(struct amdgpu_device *adev,
-			      struct amdgpu_sa_bo **sa_bo,
-			      struct dma_fence *fence);
+		       struct drm_suballoc **sa_bo,
+		       struct dma_fence *fence);
 #if defined(CONFIG_DEBUG_FS)
 void amdgpu_sa_bo_dump_debug_info(struct amdgpu_sa_manager *sa_manager,
 					 struct seq_file *m);