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, 25 insertions, 11 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 6c7d672412b2..2bd1a54ee866 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -600,7 +600,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 
 	if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 	    bo->tbo.resource->mem_type == TTM_PL_VRAM &&
-	    bo->tbo.resource->start < adev->gmc.visible_vram_size >> PAGE_SHIFT)
+	    amdgpu_bo_in_cpu_visible_vram(bo))
 		amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved,
 					     ctx.bytes_moved);
 	else
@@ -1265,24 +1265,41 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 	trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
 }
 
-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)
 {
 	unsigned int domain;
+	uint64_t size = amdgpu_bo_size(bo);
 
 	domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type);
 	switch (domain) {
 	case AMDGPU_GEM_DOMAIN_VRAM:
-		*vram_mem += amdgpu_bo_size(bo);
+		stats->vram += size;
+		if (amdgpu_bo_in_cpu_visible_vram(bo))
+			stats->visible_vram += size;
 		break;
 	case AMDGPU_GEM_DOMAIN_GTT:
-		*gtt_mem += amdgpu_bo_size(bo);
+		stats->gtt += size;
 		break;
 	case AMDGPU_GEM_DOMAIN_CPU:
 	default:
-		*cpu_mem += amdgpu_bo_size(bo);
+		stats->cpu += size;
 		break;
 	}
+
+	if (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) {
+		stats->requested_vram += size;
+		if (bo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)
+			stats->requested_visible_vram += size;
+
+		if (domain != AMDGPU_GEM_DOMAIN_VRAM) {
+			stats->evicted_vram += size;
+			if (bo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)
+				stats->evicted_visible_vram += size;
+		}
+	} else if (bo->preferred_domains & AMDGPU_GEM_DOMAIN_GTT) {
+		stats->requested_gtt += size;
+	}
 }
 
 /**
@@ -1346,7 +1363,6 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
 	struct ttm_operation_ctx ctx = { false, false };
 	struct amdgpu_bo *abo = ttm_to_amdgpu_bo(bo);
-	unsigned long offset;
 	int r;
 
 	/* Remember that this BO was accessed by the CPU */
@@ -1355,8 +1371,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	if (bo->resource->mem_type != TTM_PL_VRAM)
 		return 0;
 
-	offset = bo->resource->start << PAGE_SHIFT;
-	if ((offset + bo->base.size) <= adev->gmc.visible_vram_size)
+	if (amdgpu_bo_in_cpu_visible_vram(abo))
 		return 0;
 
 	/* Can't move a pinned BO to visible VRAM */
@@ -1378,10 +1393,9 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	else if (unlikely(r))
 		return VM_FAULT_SIGBUS;
 
-	offset = bo->resource->start << PAGE_SHIFT;
 	/* this should never happen */
 	if (bo->resource->mem_type == TTM_PL_VRAM &&
-	    (offset + bo->base.size) > adev->gmc.visible_vram_size)
+	    !amdgpu_bo_in_cpu_visible_vram(abo))
 		return VM_FAULT_SIGBUS;
 
 	ttm_bo_move_to_lru_tail_unlocked(bo);