From f1370241fe8045702bc9d0812b996791f0500f1b Mon Sep 17 00:00:00 2001 From: Lizhi Hou Date: Thu, 29 Jan 2026 16:32:55 -0800 Subject: [PATCH] accel/amdxdna: Stop job scheduling across aie2_release_resource() Running jobs on a hardware context while it is in the process of releasing resources can lead to use-after-free and crashes. Fix this by stopping job scheduling before calling aie2_release_resource() and restarting it after the release completes. Additionally, aie2_sched_job_run() now checks whether the hardware context is still active. Fixes: 4fd6ca90fc7f ("accel/amdxdna: Refactor hardware context destroy routine") Reviewed-by: Mario Limonciello (AMD) Signed-off-by: Lizhi Hou Link: https://patch.msgid.link/20260130003255.2083255-1-lizhi.hou@amd.com --- drivers/accel/amdxdna/aie2_ctx.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c index 5511ab2ef242c..c4a58c00e442a 100644 --- a/drivers/accel/amdxdna/aie2_ctx.c +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -315,6 +315,9 @@ aie2_sched_job_run(struct drm_sched_job *sched_job) struct dma_fence *fence; int ret; + if (hwctx->status != HWCTX_STAT_READY) + return NULL; + if (!mmget_not_zero(job->mm)) return ERR_PTR(-ESRCH); @@ -705,7 +708,10 @@ void aie2_hwctx_fini(struct amdxdna_hwctx *hwctx) aie2_hwctx_wait_for_idle(hwctx); /* Request fw to destroy hwctx and cancel the rest pending requests */ + drm_sched_stop(&hwctx->priv->sched, NULL); aie2_release_resource(hwctx); + hwctx->status = HWCTX_STAT_STOP; + drm_sched_start(&hwctx->priv->sched, 0); mutex_unlock(&xdna->dev_lock); drm_sched_entity_destroy(&hwctx->priv->entity); -- 2.47.3