Merge tag 'drm-next-2022-03-24' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Lots of work all over, Intel improving DG2 support, amdkfd CRIU
  support, msm new hw support, and faster fbdev support.

  dma-buf:
   - rename dma-buf-map to iosys-map

  core:
   - move buddy allocator to core
   - add pci/platform init macros
   - improve EDID parser deep color handling
   - EDID timing type 7 support
   - add GPD Win Max quirk
   - add yes/no helpers to string_helpers
   - flatten syncobj chains
   - add nomodeset support to lots of drivers
   - improve fb-helper clipping support
   - add default property value interface

  fbdev:
   - improve fbdev ops speed

  ttm:
   - add a backpointer from ttm bo->ttm resource

  dp:
   - move displayport headers
   - add a dp helper module

  bridge:
   - anx7625 atomic support, HDCP support

  panel:
   - split out panel-lvds and lvds bindings
   - find panels in OF subnodes

  privacy:
   - add chromeos privacy screen support

  fb:
   - hot unplug fw fb on forced removal

  simpledrm:
   - request region instead of marking ioresource busy
   - add panel oreintation property

  udmabuf:
   - fix oops with 0 pages

  amdgpu:
   - power management code cleanup
   - Enable freesync video mode by default
   - RAS code cleanup
   - Improve VRAM access for debug using SDMA
   - SR-IOV rework special register access and fixes
   - profiling power state request ioctl
   - expose IP discovery via sysfs
   - Cyan skillfish updates
   - GC 10.3.7, SDMA 5.2.7, DCN 3.1.6 updates
   - expose benchmark tests via debugfs
   - add module param to disable XGMI for testing
   - GPU reset debugfs register dumping support

  amdkfd:
   - CRIU support
   - SDMA queue fixes

  radeon:
   - UVD suspend fix
   - iMac backlight fix

  i915:
   - minimal parallel submission for execlists
   - DG2-G12 subplatform added
   - DG2 programming workarounds
   - DG2 accelerated migration support
   - flat CCS and CCS engine support for XeHP
   - initial small BAR support
   - drop fake LMEM support
   - ADL-N PCH support
   - bigjoiner updates
   - introduce VMA resources and async unbinding
   - register definitions cleanups
   - multi-FBC refactoring
   - DG1 OPROM over SPI support
   - ADL-N platform enabling
   - opregion mailbox #5 support
   - DP MST ESI improvements
   - drm device based logging
   - async flip optimisation for DG2
   - CPU arch abstraction fixes
   - improve GuC ADS init to work on aarch64
   - tweak TTM LRU priority hint
   - GuC 69.0.3 support
   - remove short term execbuf pins

  nouveau:
   - higher DP/eDP bitrates
   - backlight fixes

  msm:
   - dpu + dp support for sc8180x
   - dp support for sm8350
   - dpu + dsi support for qcm2290
   - 10nm dsi phy tuning support
   - bridge support for dp encoder
   - gpu support for additional 7c3 SKUs

  ingenic:
   - HDMI support for JZ4780
   - aux channel EDID support

  ast:
   - AST2600 support
   - add wide screen support
   - create DP/DVI connectors

  omapdrm:
   - fix implicit dma_buf fencing

  vc4:
   - add CSC + full range support
   - better display firmware handoff

  panfrost:
   - add initial dual-core GPU support

  stm:
   - new revision support
   - fb handover support

  mediatek:
   - transfer display binding document to yaml format.
   - add mt8195 display device binding.
   - allow commands to be sent during video mode.
   - add wait_for_event for crtc disable by cmdq.

  tegra:
   - YUV format support

  rcar-du:
   - LVDS support for M3-W+ (R8A77961)

  exynos:
   - BGR pixel format for FIMD device"

* tag 'drm-next-2022-03-24' of git://anongit.freedesktop.org/drm/drm: (1529 commits)
  drm/i915/display: Do not re-enable PSR after it was marked as not reliable
  drm/i915/display: Fix HPD short pulse handling for eDP
  drm/amdgpu: Use drm_mode_copy()
  drm/radeon: Use drm_mode_copy()
  drm/amdgpu: Use ternary operator in `vcn_v1_0_start()`
  drm/amdgpu: Remove pointless on stack mode copies
  drm/amd/pm: fix indenting in __smu_cmn_reg_print_error()
  drm/amdgpu/dc: fix typos in comments
  drm/amdgpu: fix typos in comments
  drm/amd/pm: fix typos in comments
  drm/amdgpu: Add stolen reserved memory for MI25 SRIOV.
  drm/amdgpu: Merge get_reserved_allocation to get_vbios_allocations.
  drm/amdkfd: evict svm bo worker handle error
  drm/amdgpu/vcn: fix vcn ring test failure in igt reload test
  drm/amdgpu: only allow secure submission on rings which support that
  drm/amdgpu: fixed the warnings reported by kernel test robot
  drm/amd/display: 3.2.177
  drm/amd/display: [FW Promotion] Release 0.0.108.0
  drm/amd/display: Add save/restore PANEL_PWRSEQ_REF_DIV2
  drm/amd/display: Wait for hubp read line for Pollock
  ...

1 files changed, 130 insertions, 114 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
index 313517f7cf107..edc6377ec5ff2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
@@ -29,14 +29,13 @@
 #define AMDGPU_BENCHMARK_COMMON_MODES_N 17
 
 static int amdgpu_benchmark_do_move(struct amdgpu_device *adev, unsigned size,
-				    uint64_t saddr, uint64_t daddr, int n)
+				    uint64_t saddr, uint64_t daddr, int n, s64 *time_ms)
 {
-	unsigned long start_jiffies;
-	unsigned long end_jiffies;
+	ktime_t stime, etime;
 	struct dma_fence *fence;
 	int i, r;
 
-	start_jiffies = jiffies;
+	stime = ktime_get();
 	for (i = 0; i < n; i++) {
 		struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
 		r = amdgpu_copy_buffer(ring, saddr, daddr, size, NULL, &fence,
@@ -48,120 +47,81 @@ static int amdgpu_benchmark_do_move(struct amdgpu_device *adev, unsigned size,
 		if (r)
 			goto exit_do_move;
 	}
-	end_jiffies = jiffies;
-	r = jiffies_to_msecs(end_jiffies - start_jiffies);
 
 exit_do_move:
+	etime = ktime_get();
+	*time_ms = ktime_ms_delta(etime, stime);
+
 	return r;
 }
 
 
-static void amdgpu_benchmark_log_results(int n, unsigned size,
-					 unsigned int time,
+static void amdgpu_benchmark_log_results(struct amdgpu_device *adev,
+					 int n, unsigned size,
+					 s64 time_ms,
 					 unsigned sdomain, unsigned ddomain,
 					 char *kind)
 {
-	unsigned int throughput = (n * (size >> 10)) / time;
-	DRM_INFO("amdgpu: %s %u bo moves of %u kB from"
-		 " %d to %d in %u ms, throughput: %u Mb/s or %u MB/s\n",
-		 kind, n, size >> 10, sdomain, ddomain, time,
+	s64 throughput = (n * (size >> 10));
+
+	throughput = div64_s64(throughput, time_ms);
+
+	dev_info(adev->dev, "amdgpu: %s %u bo moves of %u kB from"
+		 " %d to %d in %lld ms, throughput: %lld Mb/s or %lld MB/s\n",
+		 kind, n, size >> 10, sdomain, ddomain, time_ms,
 		 throughput * 8, throughput);
 }
 
-static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
-				  unsigned sdomain, unsigned ddomain)
+static int amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
+				 unsigned sdomain, unsigned ddomain)
 {
 	struct amdgpu_bo *dobj = NULL;
 	struct amdgpu_bo *sobj = NULL;
-	struct amdgpu_bo_param bp;
 	uint64_t saddr, daddr;
+	s64 time_ms;
 	int r, n;
-	int time;
-
-	memset(&bp, 0, sizeof(bp));
-	bp.size = size;
-	bp.byte_align = PAGE_SIZE;
-	bp.domain = sdomain;
-	bp.flags = 0;
-	bp.type = ttm_bo_type_kernel;
-	bp.resv = NULL;
-	bp.bo_ptr_size = sizeof(struct amdgpu_bo);
 
 	n = AMDGPU_BENCHMARK_ITERATIONS;
-	r = amdgpu_bo_create(adev, &bp, &sobj);
-	if (r) {
-		goto out_cleanup;
-	}
-	r = amdgpu_bo_reserve(sobj, false);
-	if (unlikely(r != 0))
-		goto out_cleanup;
-	r = amdgpu_bo_pin(sobj, sdomain);
-	if (r) {
-		amdgpu_bo_unreserve(sobj);
-		goto out_cleanup;
-	}
-	r = amdgpu_ttm_alloc_gart(&sobj->tbo);
-	amdgpu_bo_unreserve(sobj);
-	if (r) {
-		goto out_cleanup;
-	}
-	saddr = amdgpu_bo_gpu_offset(sobj);
-	bp.domain = ddomain;
-	r = amdgpu_bo_create(adev, &bp, &dobj);
-	if (r) {
-		goto out_cleanup;
-	}
-	r = amdgpu_bo_reserve(dobj, false);
-	if (unlikely(r != 0))
-		goto out_cleanup;
-	r = amdgpu_bo_pin(dobj, ddomain);
-	if (r) {
-		amdgpu_bo_unreserve(sobj);
+
+	r = amdgpu_bo_create_kernel(adev, size,
+				    PAGE_SIZE, sdomain,
+				    &sobj,
+				    &saddr,
+				    NULL);
+	if (r)
 		goto out_cleanup;
-	}
-	r = amdgpu_ttm_alloc_gart(&dobj->tbo);
-	amdgpu_bo_unreserve(dobj);
-	if (r) {
+	r = amdgpu_bo_create_kernel(adev, size,
+				    PAGE_SIZE, ddomain,
+				    &dobj,
+				    &daddr,
+				    NULL);
+	if (r)
 		goto out_cleanup;
-	}
-	daddr = amdgpu_bo_gpu_offset(dobj);
 
 	if (adev->mman.buffer_funcs) {
-		time = amdgpu_benchmark_do_move(adev, size, saddr, daddr, n);
-		if (time < 0)
+		r = amdgpu_benchmark_do_move(adev, size, saddr, daddr, n, &time_ms);
+		if (r)
 			goto out_cleanup;
-		if (time > 0)
-			amdgpu_benchmark_log_results(n, size, time,
+		else
+			amdgpu_benchmark_log_results(adev, n, size, time_ms,
 						     sdomain, ddomain, "dma");
 	}
 
 out_cleanup:
 	/* Check error value now. The value can be overwritten when clean up.*/
-	if (r) {
-		DRM_ERROR("Error while benchmarking BO move.\n");
-	}
+	if (r < 0)
+		dev_info(adev->dev, "Error while benchmarking BO move.\n");
 
-	if (sobj) {
-		r = amdgpu_bo_reserve(sobj, true);
-		if (likely(r == 0)) {
-			amdgpu_bo_unpin(sobj);
-			amdgpu_bo_unreserve(sobj);
-		}
-		amdgpu_bo_unref(&sobj);
-	}
-	if (dobj) {
-		r = amdgpu_bo_reserve(dobj, true);
-		if (likely(r == 0)) {
-			amdgpu_bo_unpin(dobj);
-			amdgpu_bo_unreserve(dobj);
-		}
-		amdgpu_bo_unref(&dobj);
-	}
+	if (sobj)
+		amdgpu_bo_free_kernel(&sobj, &saddr, NULL);
+	if (dobj)
+		amdgpu_bo_free_kernel(&dobj, &daddr, NULL);
+	return r;
 }
 
-void amdgpu_benchmark(struct amdgpu_device *adev, int test_number)
+int amdgpu_benchmark(struct amdgpu_device *adev, int test_number)
 {
-	int i;
+	int i, r;
 	static const int common_modes[AMDGPU_BENCHMARK_COMMON_MODES_N] = {
 		640 * 480 * 4,
 		720 * 480 * 4,
@@ -182,63 +142,119 @@ void amdgpu_benchmark(struct amdgpu_device *adev, int test_number)
 		1920 * 1200 * 4
 	};
 
+	mutex_lock(&adev->benchmark_mutex);
 	switch (test_number) {
 	case 1:
+		dev_info(adev->dev,
+			 "benchmark test: %d (simple test, VRAM to GTT and GTT to VRAM)\n",
+			 test_number);
 		/* simple test, VRAM to GTT and GTT to VRAM */
-		amdgpu_benchmark_move(adev, 1024*1024, AMDGPU_GEM_DOMAIN_GTT,
-				      AMDGPU_GEM_DOMAIN_VRAM);
-		amdgpu_benchmark_move(adev, 1024*1024, AMDGPU_GEM_DOMAIN_VRAM,
-				      AMDGPU_GEM_DOMAIN_GTT);
+		r = amdgpu_benchmark_move(adev, 1024*1024, AMDGPU_GEM_DOMAIN_GTT,
+					  AMDGPU_GEM_DOMAIN_VRAM);
+		if (r)
+			goto done;
+		r = amdgpu_benchmark_move(adev, 1024*1024, AMDGPU_GEM_DOMAIN_VRAM,
+					  AMDGPU_GEM_DOMAIN_GTT);
+		if (r)
+			goto done;
 		break;
 	case 2:
+		dev_info(adev->dev,
+			 "benchmark test: %d (simple test, VRAM to VRAM)\n",
+			 test_number);
 		/* simple test, VRAM to VRAM */
-		amdgpu_benchmark_move(adev, 1024*1024, AMDGPU_GEM_DOMAIN_VRAM,
-				      AMDGPU_GEM_DOMAIN_VRAM);
+		r = amdgpu_benchmark_move(adev, 1024*1024, AMDGPU_GEM_DOMAIN_VRAM,
+					  AMDGPU_GEM_DOMAIN_VRAM);
+		if (r)
+			goto done;
 		break;
 	case 3:
+		dev_info(adev->dev,
+			 "benchmark test: %d (GTT to VRAM, buffer size sweep, powers of 2)\n",
+			 test_number);
 		/* GTT to VRAM, buffer size sweep, powers of 2 */
-		for (i = 1; i <= 16384; i <<= 1)
-			amdgpu_benchmark_move(adev, i * AMDGPU_GPU_PAGE_SIZE,
-					      AMDGPU_GEM_DOMAIN_GTT,
-					      AMDGPU_GEM_DOMAIN_VRAM);
+		for (i = 1; i <= 16384; i <<= 1) {
+			r = amdgpu_benchmark_move(adev, i * AMDGPU_GPU_PAGE_SIZE,
+						  AMDGPU_GEM_DOMAIN_GTT,
+						  AMDGPU_GEM_DOMAIN_VRAM);
+			if (r)
+				goto done;
+		}
 		break;
 	case 4:
+		dev_info(adev->dev,
+			 "benchmark test: %d (VRAM to GTT, buffer size sweep, powers of 2)\n",
+			 test_number);
 		/* VRAM to GTT, buffer size sweep, powers of 2 */
-		for (i = 1; i <= 16384; i <<= 1)
-			amdgpu_benchmark_move(adev, i * AMDGPU_GPU_PAGE_SIZE,
-					      AMDGPU_GEM_DOMAIN_VRAM,
-					      AMDGPU_GEM_DOMAIN_GTT);
+		for (i = 1; i <= 16384; i <<= 1) {
+			r = amdgpu_benchmark_move(adev, i * AMDGPU_GPU_PAGE_SIZE,
+						  AMDGPU_GEM_DOMAIN_VRAM,
+						  AMDGPU_GEM_DOMAIN_GTT);
+			if (r)
+				goto done;
+		}
 		break;
 	case 5:
+		dev_info(adev->dev,
+			 "benchmark test: %d (VRAM to VRAM, buffer size sweep, powers of 2)\n",
+			 test_number);
 		/* VRAM to VRAM, buffer size sweep, powers of 2 */
-		for (i = 1; i <= 16384; i <<= 1)
-			amdgpu_benchmark_move(adev, i * AMDGPU_GPU_PAGE_SIZE,
-					      AMDGPU_GEM_DOMAIN_VRAM,
-					      AMDGPU_GEM_DOMAIN_VRAM);
+		for (i = 1; i <= 16384; i <<= 1) {
+			r = amdgpu_benchmark_move(adev, i * AMDGPU_GPU_PAGE_SIZE,
+						  AMDGPU_GEM_DOMAIN_VRAM,
+						  AMDGPU_GEM_DOMAIN_VRAM);
+			if (r)
+				goto done;
+		}
 		break;
 	case 6:
+		dev_info(adev->dev,
+			 "benchmark test: %d (GTT to VRAM, buffer size sweep, common modes)\n",
+			 test_number);
 		/* GTT to VRAM, buffer size sweep, common modes */
-		for (i = 0; i < AMDGPU_BENCHMARK_COMMON_MODES_N; i++)
-			amdgpu_benchmark_move(adev, common_modes[i],
-					      AMDGPU_GEM_DOMAIN_GTT,
-					      AMDGPU_GEM_DOMAIN_VRAM);
+		for (i = 0; i < AMDGPU_BENCHMARK_COMMON_MODES_N; i++) {
+			r = amdgpu_benchmark_move(adev, common_modes[i],
+						  AMDGPU_GEM_DOMAIN_GTT,
+						  AMDGPU_GEM_DOMAIN_VRAM);
+			if (r)
+				goto done;
+		}
 		break;
 	case 7:
+		dev_info(adev->dev,
+			 "benchmark test: %d (VRAM to GTT, buffer size sweep, common modes)\n",
+			 test_number);
 		/* VRAM to GTT, buffer size sweep, common modes */
-		for (i = 0; i < AMDGPU_BENCHMARK_COMMON_MODES_N; i++)
-			amdgpu_benchmark_move(adev, common_modes[i],
-					      AMDGPU_GEM_DOMAIN_VRAM,
-					      AMDGPU_GEM_DOMAIN_GTT);
+		for (i = 0; i < AMDGPU_BENCHMARK_COMMON_MODES_N; i++) {
+			r = amdgpu_benchmark_move(adev, common_modes[i],
+						  AMDGPU_GEM_DOMAIN_VRAM,
+						  AMDGPU_GEM_DOMAIN_GTT);
+			if (r)
+				goto done;
+		}
 		break;
 	case 8:
+		dev_info(adev->dev,
+			 "benchmark test: %d (VRAM to VRAM, buffer size sweep, common modes)\n",
+			 test_number);
 		/* VRAM to VRAM, buffer size sweep, common modes */
-		for (i = 0; i < AMDGPU_BENCHMARK_COMMON_MODES_N; i++)
-			amdgpu_benchmark_move(adev, common_modes[i],
+		for (i = 0; i < AMDGPU_BENCHMARK_COMMON_MODES_N; i++) {
+			r = amdgpu_benchmark_move(adev, common_modes[i],
 					      AMDGPU_GEM_DOMAIN_VRAM,
 					      AMDGPU_GEM_DOMAIN_VRAM);
+			if (r)
+				goto done;
+		}
 		break;
 
 	default:
-		DRM_ERROR("Unknown benchmark\n");
+		dev_info(adev->dev, "Unknown benchmark %d\n", test_number);
+		r = -EINVAL;
+		break;
 	}
+
+done:
+	mutex_unlock(&adev->benchmark_mutex);
+
+	return r;
 }