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

BugLink: https://bugs.launchpad.net/bugs/1933691
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: ae363a212b14 ("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>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Kelsey Skunberg <kelsey.skunberg@canonical.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 0350205c48974e0dfafd81c2f14b365ebbff7e91..6819fe5612d9e7a1a1f2b9a148b0990f5533ba68 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -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;
 }