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, 19 insertions, 14 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 06d07502a1f68..970b065e9a6b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -32,6 +32,7 @@
 
 #include <drm/amdgpu_drm.h>
 #include <drm/drm_syncobj.h>
+#include "amdgpu_cs.h"
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
 #include "amdgpu_gmc.h"
@@ -127,8 +128,6 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs
 		goto free_chunk;
 	}
 
-	mutex_lock(&p->ctx->lock);
-
 	/* skip guilty context job */
 	if (atomic_read(&p->ctx->guilty) == 1) {
 		ret = -ECANCELED;
@@ -314,7 +313,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev,
 	}
 
 	total_vram = adev->gmc.real_vram_size - atomic64_read(&adev->vram_pin_size);
-	used_vram = amdgpu_vram_mgr_usage(&adev->mman.vram_mgr);
+	used_vram = ttm_resource_manager_usage(&adev->mman.vram_mgr.manager);
 	free_vram = used_vram >= total_vram ? 0 : total_vram - used_vram;
 
 	spin_lock(&adev->mm_stats.lock);
@@ -341,7 +340,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev,
 	if (free_vram >= 128 * 1024 * 1024 || free_vram >= total_vram / 8) {
 		s64 min_us;
 
-		/* Be more aggresive on dGPUs. Try to fill a portion of free
+		/* Be more aggressive on dGPUs. Try to fill a portion of free
 		 * VRAM now.
 		 */
 		if (!(adev->flags & AMD_IS_APU))
@@ -585,6 +584,16 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		}
 	}
 
+	/* Move fence waiting after getting reservation lock of
+	 * PD root. Then there is no need on a ctx mutex lock.
+	 */
+	r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entity);
+	if (unlikely(r != 0)) {
+		if (r != -ERESTARTSYS)
+			DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n");
+		goto error_validate;
+	}
+
 	amdgpu_cs_get_threshold_for_moves(p->adev, &p->bytes_moved_threshold,
 					  &p->bytes_moved_vis_threshold);
 	p->bytes_moved = 0;
@@ -700,7 +709,6 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error,
 	dma_fence_put(parser->fence);
 
 	if (parser->ctx) {
-		mutex_unlock(&parser->ctx->lock);
 		amdgpu_ctx_put(parser->ctx);
 	}
 	if (parser->bo_list)
@@ -775,12 +783,12 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 				memcpy(ib->ptr, kptr, chunk_ib->ib_bytes);
 				amdgpu_bo_kunmap(aobj);
 
-				r = amdgpu_ring_parse_cs(ring, p, j);
+				r = amdgpu_ring_parse_cs(ring, p, p->job, ib);
 				if (r)
 					return r;
 			} else {
 				ib->ptr = (uint32_t *)kptr;
-				r = amdgpu_ring_patch_cs_in_place(ring, p, j);
+				r = amdgpu_ring_patch_cs_in_place(ring, p, p->job, ib);
 				amdgpu_bo_kunmap(aobj);
 				if (r)
 					return r;
@@ -944,7 +952,7 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 	if (parser->job->uf_addr && ring->funcs->no_user_fence)
 		return -EINVAL;
 
-	return amdgpu_ctx_wait_prev_fence(parser->ctx, parser->entity);
+	return 0;
 }
 
 static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p,
@@ -1272,16 +1280,13 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 			continue;
 
 		/*
-		 * Work around dma_resv shortcommings by wrapping up the
+		 * Work around dma_resv shortcomings 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.
+		 * fence.
 		 */
 		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;
 	}
@@ -1363,7 +1368,6 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		goto out;
 
 	r = amdgpu_cs_submit(&parser, cs);
-
 out:
 	amdgpu_cs_parser_fini(&parser, r, reserved_buffers);
 
@@ -1509,6 +1513,7 @@ int amdgpu_cs_fence_to_handle_ioctl(struct drm_device *dev, void *data,
 		return 0;
 
 	default:
+		dma_fence_put(fence);
 		return -EINVAL;
 	}
 }