accel/amdxdna: Fix incorrect command state for timed out job

When a command times out, mark it as ERT_CMD_STATE_TIMEOUT. Any other
commands that are canceled due to this timeout should be marked as
ERT_CMD_STATE_ABORT.

Fixes: aac243092b ("accel/amdxdna: Add command execution")
Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20251029193423.2430463-1-lizhi.hou@amd.com
This commit is contained in:
Lizhi Hou 2025-10-29 12:34:23 -07:00
parent 231668043d
commit 6fb7f29888
2 changed files with 14 additions and 2 deletions

View File

@ -204,10 +204,13 @@ aie2_sched_resp_handler(void *handle, void __iomem *data, size_t size)
cmd_abo = job->cmd_bo;
if (unlikely(!data))
if (unlikely(job->job_timeout)) {
amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_TIMEOUT);
ret = -EINVAL;
goto out;
}
if (unlikely(size != sizeof(u32))) {
if (unlikely(!data) || unlikely(size != sizeof(u32))) {
amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT);
ret = -EINVAL;
goto out;
@ -258,6 +261,13 @@ aie2_sched_cmdlist_resp_handler(void *handle, void __iomem *data, size_t size)
int ret = 0;
cmd_abo = job->cmd_bo;
if (unlikely(job->job_timeout)) {
amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_TIMEOUT);
ret = -EINVAL;
goto out;
}
if (unlikely(!data) || unlikely(size != sizeof(u32) * 3)) {
amdxdna_cmd_set_state(cmd_abo, ERT_CMD_STATE_ABORT);
ret = -EINVAL;
@ -370,6 +380,7 @@ aie2_sched_job_timedout(struct drm_sched_job *sched_job)
xdna = hwctx->client->xdna;
trace_xdna_job(sched_job, hwctx->name, "job timedout", job->seq);
job->job_timeout = true;
mutex_lock(&xdna->dev_lock);
aie2_hwctx_stop(xdna, hwctx, sched_job);

View File

@ -116,6 +116,7 @@ struct amdxdna_sched_job {
/* user can wait on this fence */
struct dma_fence *out_fence;
bool job_done;
bool job_timeout;
u64 seq;
struct amdxdna_drv_cmd *drv_cmd;
struct amdxdna_gem_obj *cmd_bo;