xe_file_close triggers an asynchronous queue cleanup and then frees up
the xef object. Since queue cleanup flushes all pending jobs and the KMD
stores client usage stats into the xef object after jobs are flushed, we
see a use-after-free for the xef object. Resolve this by taking a
reference to xef from xe_exec_queue.
While at it, revert an earlier change that contained a partial work
around for this issue.
v2:
- Take a ref to xef even for the VM bind queue (Matt)
- Squash patches relevant to that fix and work around (Lucas)
v3: Fix typo (Lucas)
Fixes: ce62827bc294 ("drm/xe: Do not access xe file when updating exec queue run_ticks")
Fixes: 6109f24f87d7 ("drm/xe: Add helper to accumulate exec queue runtime")
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/issues/1908
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240718210548.3580382-5-umesh.nerlige.ramappa@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit
2149ded63079449b8dddf9da38392632f155e6b5)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
/* Accumulate all the exec queues from this client */
mutex_lock(&xef->exec_queue.lock);
- xa_for_each(&xef->exec_queue.xa, i, q) {
+ xa_for_each(&xef->exec_queue.xa, i, q)
xe_exec_queue_update_run_ticks(q);
- xef->run_ticks[q->class] += q->run_ticks - q->old_run_ticks;
- q->old_run_ticks = q->run_ticks;
- }
mutex_unlock(&xef->exec_queue.lock);
/* Get the total GPU cycles */
{
if (q->vm)
xe_vm_put(q->vm);
+
+ if (q->xef)
+ xe_file_put(q->xef);
+
kfree(q);
}
goto kill_exec_queue;
args->exec_queue_id = id;
+ q->xef = xe_file_get(xef);
return 0;
*/
void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
{
+ struct xe_file *xef;
struct xe_lrc *lrc;
u32 old_ts, new_ts;
if (!q->vm || !q->vm->xef)
return;
+ xef = q->vm->xef;
+
/*
* Only sample the first LRC. For parallel submission, all of them are
* scheduled together and we compensate that below by multiplying by
*/
lrc = q->lrc[0];
new_ts = xe_lrc_update_timestamp(lrc, &old_ts);
- q->run_ticks += (new_ts - old_ts) * q->width;
+ xef->run_ticks[q->class] += (new_ts - old_ts) * q->width;
}
void xe_exec_queue_kill(struct xe_exec_queue *q)
* a kernel object.
*/
struct xe_exec_queue {
+ /** @xef: Back pointer to xe file if this is user created exec queue */
+ struct xe_file *xef;
+
/** @gt: graphics tile this exec queue can submit to */
struct xe_gt *gt;
/**
* Protected by @vm's resv. Unused if @vm == NULL.
*/
u64 tlb_flush_seqno;
- /** @old_run_ticks: prior hw engine class run time in ticks for this exec queue */
- u64 old_run_ticks;
- /** @run_ticks: hw engine class run time in ticks for this exec queue */
- u64 run_ticks;
/** @lrc: logical ring context for this exec queue */
struct xe_lrc *lrc[];
};