public-mirrors/linux
1
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-08-05 16:54:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

drm/amdgpu: refine RAS poison consumption handler

Browse source 
Qeury ras status before ras poison consumption handling, add more
comment and log.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-and-tested-by: Mohammad Zafar Ziya <Mohammadzafar.ziya@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Tao Zhou 2022-05-09 17:52:15 +08:00 • committed by Alex Deucher
parent 3678060682
commit b63ac5d303
1 changed files with 25 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

41
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
View file

@ -1538,33 +1538,42 @@ void amdgpu_ras_interrupt_fatal_error_handler(struct amdgpu_device *adev)
static void amdgpu_ras_interrupt_poison_consumption_handler(struct ras_manager *obj,
struct amdgpu_iv_entry *entry)
{
bool poison_stat = true, need_reset = true;
bool poison_stat = false;
struct amdgpu_device *adev = obj->adev;
struct ras_err_data err_data = {0, 0, 0, NULL};
struct amdgpu_ras_block_object *block_obj =
amdgpu_ras_get_ras_block(adev, obj->head.block, 0);
if (!adev->gmc.xgmi.connected_to_cpu)
amdgpu_umc_poison_handler(adev, &err_data, false);
if (!block_obj || !block_obj->hw_ops)
return;
/* both query_poison_status and handle_poison_consumption are optional */
if (block_obj && block_obj->hw_ops) {
if (block_obj->hw_ops->query_poison_status) {
poison_stat = block_obj->hw_ops->query_poison_status(adev);
if (!poison_stat)
dev_info(adev->dev, "No RAS poison status in %s poison IH.\n",
block_obj->ras_comm.name);
}
/* both query_poison_status and handle_poison_consumption are optional,
* but at least one of them should be implemented if we need poison
* consumption handler
*/
if (block_obj->hw_ops->query_poison_status) {
poison_stat = block_obj->hw_ops->query_poison_status(adev);
if (!poison_stat) {
/* Not poison consumption interrupt, no need to handle it */
dev_info(adev->dev, "No RAS poison status in %s poison IH.\n",
block_obj->ras_comm.name);
if (poison_stat && block_obj->hw_ops->handle_poison_consumption) {
poison_stat = block_obj->hw_ops->handle_poison_consumption(adev);
need_reset = poison_stat;
return;
}
}
/* gpu reset is fallback for all failed cases */
if (need_reset)
if (!adev->gmc.xgmi.connected_to_cpu)
amdgpu_umc_poison_handler(adev, &err_data, false);
if (block_obj->hw_ops->handle_poison_consumption)
poison_stat = block_obj->hw_ops->handle_poison_consumption(adev);
/* gpu reset is fallback for failed and default cases */
if (poison_stat) {
dev_info(adev->dev, "GPU reset for %s RAS poison consumption is issued!\n",
block_obj->ras_comm.name);
amdgpu_ras_reset_gpu(adev);
}
}
static void amdgpu_ras_interrupt_poison_creation_handler(struct ras_manager *obj,