drm/amdgpu: Use delayed work to collect RAS error counters

On Context Query2 IOCTL return the correctable and
uncorrectable errors in O(1) fashion, from cached
values, and schedule a delayed work function to
calculate and cache them for the next such IOCTL.

v2: Cancel pending delayed work at ras_fini().
v3: Remove conditionals when dealing with delayed
    work manipulation as they're inherently racy.

Cc: Alexander Deucher <Alexander.Deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: John Clements <john.clements@amd.com>
Cc: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Luben Tuikov <luben.tuikov@amd.com>
Reviewed-by: Alexander Deucher <Alexander.Deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 29 insertions, 2 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index bb0cfe871aba..e7a010b7ca1f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -331,10 +331,13 @@ 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;
 
@@ -361,6 +364,30 @@ static int amdgpu_ctx_query2(struct amdgpu_device *adev,
 	if (atomic_read(&ctx->guilty))
 		out->state.flags |= AMDGPU_CTX_QUERY2_FLAGS_GUILTY;
 
+	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;
+		}
+
+		schedule_delayed_work(&con->ras_counte_delay_work,
+				      msecs_to_jiffies(AMDGPU_RAS_COUNTE_DELAY_MS));
+	}
+
 	mutex_unlock(&mgr->lock);
 	return 0;
 }