Merge branch 'drm-next-4.11' of git://people.freedesktop.org/~agd5f/linux into drm-next

This is the main feature pull for radeon and amdgpu for 4.11.  Highlights:
- Power and clockgating improvements
- Preliminary SR-IOV support
- ttm buffer priority support
- ttm eviction fixes
- Removal of the ttm lru callbacks
- Remove SI DPM quirks due to MC firmware issues
- Handle VFCT with multiple vbioses
- Powerplay improvements
- Lots of driver cleanups

* 'drm-next-4.11' of git://people.freedesktop.org/~agd5f/linux: (120 commits)
  drm/amdgpu: fix amdgpu_bo_va_mapping flags
  drm/amdgpu: access stolen VRAM directly on CZ (v2)
  drm/amdgpu: access stolen VRAM directly on KV/KB (v2)
  drm/amdgpu: fix kernel panic when dpm disabled on Kv.
  drm/amdgpu: fix dpm bug on Kv.
  drm/amd/powerplay: fix regresstion issue can't set manual dpm mode.
  drm/amdgpu: handle vfct with multiple vbios images
  drm/radeon: handle vfct with multiple vbios images
  drm/amdgpu: move misc si headers into amdgpu
  drm/amdgpu: remove unused header si_reg.h
  drm/radeon: drop pitcairn dpm quirks
  drm/amdgpu: drop pitcairn dpm quirks
  drm: radeon: radeon_ttm: Handle return NULL error from ioremap_nocache
  drm/amd/amdgpu/amdgpu_ttm: Handle return NULL error from ioremap_nocache
  drm/amdgpu: add new virtual display ID
  drm/amd/amdgpu: remove the uncessary parameter for ib scheduler
  drm/amdgpu: Bring bo creation in line with radeon driver (v2)
  drm/amd/powerplay: fix misspelling in header guard
  drm/ttm: revert "add optional LRU removal callback v2"
  drm/ttm: revert "implement LRU add callbacks v2"
  ...

1 files changed, 41 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index bf79b73e1538e..d1aa291b26380 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -363,11 +363,31 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
 
 	bo->flags = flags;
 
+#ifdef CONFIG_X86_32
+	/* XXX: Write-combined CPU mappings of GTT seem broken on 32-bit
+	 * See https://bugs.freedesktop.org/show_bug.cgi?id=84627
+	 */
+	bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+#elif defined(CONFIG_X86) && !defined(CONFIG_X86_PAT)
+	/* Don't try to enable write-combining when it can't work, or things
+	 * may be slow
+	 * See https://bugs.freedesktop.org/show_bug.cgi?id=88758
+	 */
+
+#warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \
+	 thanks to write-combining
+
+	if (bo->flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC)
+		DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "
+			      "better performance thanks to write-combining\n");
+	bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+#else
 	/* For architectures that don't support WC memory,
 	 * mask out the WC flag from the BO
 	 */
 	if (!drm_arch_can_wc_memory())
 		bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+#endif
 
 	amdgpu_fill_placement_to_bo(bo, placement);
 	/* Kernel allocation are uninterruptible */
@@ -386,6 +406,11 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
 	if (unlikely(r != 0))
 		return r;
 
+	bo->tbo.priority = ilog2(bo->tbo.num_pages);
+	if (kernel)
+		bo->tbo.priority *= 2;
+	bo->tbo.priority = min(bo->tbo.priority, (unsigned)(TTM_MAX_BO_PRIORITY - 1));
+
 	if (flags & AMDGPU_GEM_CREATE_VRAM_CLEARED &&
 	    bo->tbo.mem.placement & TTM_PL_FLAG_VRAM) {
 		struct dma_fence *fence;
@@ -408,7 +433,8 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
 	return 0;
 
 fail_unreserve:
-	ww_mutex_unlock(&bo->tbo.resv->lock);
+	if (!resv)
+		ww_mutex_unlock(&bo->tbo.resv->lock);
 	amdgpu_bo_unref(&bo);
 	return r;
 }
@@ -472,7 +498,16 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 		return r;
 
 	if (amdgpu_need_backup(adev) && (flags & AMDGPU_GEM_CREATE_SHADOW)) {
+		if (!resv) {
+			r = ww_mutex_lock(&(*bo_ptr)->tbo.resv->lock, NULL);
+			WARN_ON(r != 0);
+		}
+
 		r = amdgpu_bo_create_shadow(adev, size, byte_align, (*bo_ptr));
+
+		if (!resv)
+			ww_mutex_unlock(&(*bo_ptr)->tbo.resv->lock);
+
 		if (r)
 			amdgpu_bo_unref(bo_ptr);
 	}
@@ -849,6 +884,7 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
 }
 
 void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
+			   bool evict,
 			   struct ttm_mem_reg *new_mem)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
@@ -861,6 +897,10 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 	abo = container_of(bo, struct amdgpu_bo, tbo);
 	amdgpu_vm_bo_invalidate(adev, abo);
 
+	/* remember the eviction */
+	if (evict)
+		atomic64_inc(&adev->num_evictions);
+
 	/* update statistics */
 	if (!new_mem)
 		return;