Commit 2871e101 authored by Luben Tuikov's avatar Luben Tuikov Committed by Alex Deucher

drm/amdgpu: Don't query CE and UE errors

On QUERY2 IOCTL don't query counts of correctable
and uncorrectable errors, since when RAS is
enabled and supported on Vega20 server boards,
this takes insurmountably long time, in O(n^3),
which slows the system down to the point of it
being unusable when we have GUI up.

Fixes: ae363a21 ("drm/amdgpu: Add a new flag to AMDGPU_CTX_OP_QUERY_STATE2")
Cc: Alexander Deucher <Alexander.Deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: default avatarLuben Tuikov <luben.tuikov@amd.com>
Reviewed-by: default avatarAlexander Deucher <Alexander.Deucher@amd.com>
Reviewed-by: default avatarChristian König <christian.koenig@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent 5a645ff5
......@@ -337,7 +337,6 @@ static int amdgpu_ctx_query2(struct amdgpu_device *adev,
{
struct amdgpu_ctx *ctx;
struct amdgpu_ctx_mgr *mgr;
unsigned long ras_counter;
if (!fpriv)
return -EINVAL;
......@@ -362,21 +361,6 @@ 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;
}
/*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;
}
mutex_unlock(&mgr->lock);
return 0;
}
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment