Merge tag 'amd-drm-next-5.14-2021-06-02' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.14-2021-06-02:

amdgpu:
- GC/MM register access macro clean up for SR-IOV
- Beige Goby updates
- W=1 Fixes
- Aldebaran fixes
- Misc display fixes
- ACPI ATCS/ATIF handling rework
- SR-IOV fixes
- RAS fixes
- 16bpc fixed point format support
- Initial smartshift support
- RV/PCO power tuning fixes for suspend/resume
- More buffer object subclassing work
- Add new INFO query for additional vbios information
- Add new placement for preemptable SG buffers

amdkfd:
- Misc fixes

radeon:
- W=1 Fixes
- Misc cleanups

UAPI:
- Add new INFO query for additional vbios information
  Useful for debugging vbios related issues.  Proposed umr patch:
  https://patchwork.freedesktop.org/patch/433297/
- 16bpc fixed point format support
  IGT test:
  https://lists.freedesktop.org/archives/igt-dev/2021-May/031507.html
  Proposed Vulkan patch:
  https://github.com/kleinerm/pal/commit/a25d4802074b13a8d5f7edc96ae45469ecbac3c4
- Add a new GEM flag which is only used internally in the kernel driver.  Userspace
  is not allowed to set it.

drm:
- 16bpc fixed point format fourcc

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210602214009.4553-1-alexander.deucher@amd.com

1 files changed, 26 insertions, 15 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index fc83445fbc40..e7a010b7ca1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -331,13 +331,15 @@ static int amdgpu_ctx_query(struct amdgpu_device *adev,
 	return 0;
 }
 
+#define AMDGPU_RAS_COUNTE_DELAY_MS 3000
+
 static int amdgpu_ctx_query2(struct amdgpu_device *adev,
-	struct amdgpu_fpriv *fpriv, uint32_t id,
-	union drm_amdgpu_ctx_out *out)
+			     struct amdgpu_fpriv *fpriv, uint32_t id,
+			     union drm_amdgpu_ctx_out *out)
 {
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct amdgpu_ctx *ctx;
 	struct amdgpu_ctx_mgr *mgr;
-	unsigned long ras_counter;
 
 	if (!fpriv)
 		return -EINVAL;
@@ -362,19 +364,28 @@ static int amdgpu_ctx_query2(struct amdgpu_device *adev,
 	if (atomic_read(&ctx->guilty))
 		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_GUILTY;
 
-	/*query ue count*/
-	ras_counter = amdgpu_ras_query_error_count(adev, false);
-	/*ras counter is monotonic increasing*/
-	if (ras_counter != ctx->ras_counter_ue) {
-		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_RAS_UE;
-		ctx->ras_counter_ue = ras_counter;
-	}
+	if (adev->ras_enabled && con) {
+		/* Return the cached values in O(1),
+		 * and schedule delayed work to cache
+		 * new vaues.
+		 */
+		int ce_count, ue_count;
+
+		ce_count = atomic_read(&con->ras_ce_count);
+		ue_count = atomic_read(&con->ras_ue_count);
+
+		if (ce_count != ctx->ras_counter_ce) {
+			ctx->ras_counter_ce = ce_count;
+			out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_RAS_CE;
+		}
+
+		if (ue_count != ctx->ras_counter_ue) {
+			ctx->ras_counter_ue = ue_count;
+			out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_RAS_UE;
+		}
 
-	/*query ce count*/
-	ras_counter = amdgpu_ras_query_error_count(adev, true);
-	if (ras_counter != ctx->ras_counter_ce) {
-		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_RAS_CE;
-		ctx->ras_counter_ce = ras_counter;
+		schedule_delayed_work(&con->ras_counte_delay_work,
+				      msecs_to_jiffies(AMDGPU_RAS_COUNTE_DELAY_MS));
 	}
 
 	mutex_unlock(&mgr->lock);