6.17-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lizhi Hou lizhi.hou@amd.com
[ Upstream commit 6fb7f298883246e21f60f971065adcb789ae6eba ]
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: aac243092b70 ("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 Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/accel/amdxdna/aie2_ctx.c | 15 +++++++++++++-- drivers/accel/amdxdna/amdxdna_ctx.h | 1 + 2 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c index 6f77d1794e483..3a9239da588c5 100644 --- a/drivers/accel/amdxdna/aie2_ctx.c +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -198,10 +198,13 @@ 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; @@ -254,6 +257,13 @@ 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; @@ -356,6 +366,7 @@ 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);
diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h index c652229547a3c..e454b19d6ba73 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.h +++ b/drivers/accel/amdxdna/amdxdna_ctx.h @@ -105,6 +105,7 @@ 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_gem_obj *cmd_bo; size_t bo_cnt;