diff options
| author | Lizhi Hou <lizhi.hou@amd.com> | 2026-01-29 16:32:55 -0800 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2026-02-26 14:59:14 -0800 |
| commit | b79d31dce49b50c79620389b3639280802a86960 (patch) | |
| tree | 36b0a4cc57fcf9f8c9ea9936c4b6ae0a4b2d5c5f /drivers/accel | |
| parent | f6b4c1d98a7b8040d4d02e89425b3942016a2c2c (diff) | |
accel/amdxdna: Stop job scheduling across aie2_release_resource()
[ Upstream commit f1370241fe8045702bc9d0812b996791f0500f1b ]
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) <superm1@kernel.org>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patch.msgid.link/20260130003255.2083255-1-lizhi.hou@amd.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
Diffstat (limited to 'drivers/accel')
| -rw-r--r-- | drivers/accel/amdxdna/aie2_ctx.c | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c index 75246c481fa5..c3cb24d96cee 100644 --- a/drivers/accel/amdxdna/aie2_ctx.c +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -317,6 +317,9 @@ 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); @@ -684,7 +687,10 @@ 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); |