If a DRM fence is set to -ENODATA, that means that this context was a cause of a soft reset, but is never marked as guilty. Flag it as guilty and log to user that this context won't accept more submissions. Signed-off-by: André Almeida <andrealmeid@xxxxxxxxxx> --- drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 0dc9c655c4fb..fe8e47d063da 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -459,6 +459,12 @@ int amdgpu_ctx_get_entity(struct amdgpu_ctx *ctx, u32 hw_ip, u32 instance, ctx_entity = &ctx->entities[hw_ip][ring]->entity; r = drm_sched_entity_error(ctx_entity); if (r) { + if (r == -ENODATA) { + DRM_ERROR("%s (%d) context caused a reset," + "marking it guilty and refusing new submissions.\n", + current->comm, current->pid); + atomic_set(&ctx->guilty, 1); + } DRM_DEBUG("error entity %p\n", ctx_entity); return r; } -- 2.41.0