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: 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

diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c
index c6c473c7835222038aea2c60eb1ad98d24c8c35e..289a2aaf4cae8a61e390ddc2fb781b3409bd00e6 100644 (file)
--- a/drivers/accel/amdxdna/aie2_ctx.c
+++ b/drivers/accel/amdxdna/aie2_ctx.c
@@ -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);
 

diff --git a/drivers/accel/amdxdna/amdxdna_ctx.h b/drivers/accel/amdxdna/amdxdna_ctx.h
index cbe60efbe60ba292cb3a8889145d7cf924b226a6..919c654dfea63747621e6d4e809bc62f1ab4063c 100644 (file)
--- a/drivers/accel/amdxdna/amdxdna_ctx.h
+++ b/drivers/accel/amdxdna/amdxdna_ctx.h
@@ -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;