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

commit dce3d8e1d070900e0feeb06787a319ff9379212c upstream.

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: ae363a212b ("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: 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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Luben Tuikov 2021-05-12 12:33:23 -04:00 committed by Greg Kroah-Hartman
parent 5d4c4b06ed
commit 24c06e5452
1 changed files with 0 additions and 16 deletions

View File

@ -351,7 +351,6 @@ 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;
@ -376,21 +375,6 @@ 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;
}