iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

drm/amdgpu: fix ras UE error injection failure issue

Browse Source 
The ras command shared memory is allocated from
VRAM and the response status of the command
buffer will not be zero due to gpu being in
fatal error state after ras UE error injection.

Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 8284951a6e79c6806c675e5f68a4cd425dd56bc4)
This commit is contained in:
YiPeng Chai 2024-07-19 20:43:04 +08:00 committed by Alex Deucher
parent 5302d1a06a
commit afac8c6554
1 changed files with 1 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
View File

@ -1630,9 +1630,7 @@ static int psp_ras_send_cmd(struct psp_context *psp,
switch (cmd) {
case TA_RAS_COMMAND__TRIGGER_ERROR:
if (ret || psp->cmd_buf_mem->resp.status)
ret = -EINVAL;
else if (out)
if (!ret && out)
memcpy(out, &ras_cmd->ras_status, sizeof(ras_cmd->ras_status));
break;
case TA_RAS_COMMAND__QUERY_ADDRESS: