Commit 5a836bf6b09f ("mm: slub: move flush_cpu_slab() invocations
__free_slab() invocations out of IRQ context") moved all flush_cpu_slab()
invocations to the global workqueue to avoid a problem related
with deactivate_slab()/__free_slab() being called from an IRQ context
on PREEMPT_RT kernels.
When the flush_all_cpu_locked() function is called from a task context
it may happen that a workqueue with WQ_MEM_RECLAIM bit set ends up
flushing the global workqueue, this will cause a dependency issue.
workqueue: WQ_MEM_RECLAIM nvme-delete-wq:nvme_delete_ctrl_work [nvme_core]
is flushing !WQ_MEM_RECLAIM events:flush_cpu_slab
WARNING: CPU: 37 PID: 410 at kernel/workqueue.c:2637
check_flush_dependency+0x10a/0x120
Workqueue: nvme-delete-wq nvme_delete_ctrl_work [nvme_core]
RIP: 0010:check_flush_dependency+0x10a/0x120[ 453.262125] Call Trace:
__flush_work.isra.0+0xbf/0x220
? __queue_work+0x1dc/0x420
flush_all_cpus_locked+0xfb/0x120
__kmem_cache_shutdown+0x2b/0x320
kmem_cache_destroy+0x49/0x100
bioset_exit+0x143/0x190
blk_release_queue+0xb9/0x100
kobject_cleanup+0x37/0x130
nvme_fc_ctrl_free+0xc6/0x150 [nvme_fc]
nvme_free_ctrl+0x1ac/0x2b0 [nvme_core]
Fix this bug by creating a workqueue for the flush operation with
the WQ_MEM_RECLAIM bit set.
v2: Create a workqueue with WQ_MEM_RECLAIM
instead of trying to revert the changes.
Signed-off-by: Maurizio Lombardi <mlombard@xxxxxxxxxx>
---
mm/slub.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/mm/slub.c b/mm/slub.c
index 862dbd9af4f5..cdb8011884d0 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -310,6 +310,11 @@ static inline void stat(const struct kmem_cache *s, enum stat_item si)
*/
static nodemask_t slab_nodes;
+/*
+ * Workqueue used for flush_cpu_slab().
+ */
+static struct workqueue_struct *flushwq;
+
/********************************************************************
* Core slab cache functions
*******************************************************************/
@@ -2730,7 +2735,7 @@ static void flush_all_cpus_locked(struct kmem_cache *s)
INIT_WORK(&sfw->work, flush_cpu_slab);
sfw->skip = false;
sfw->s = s;
- schedule_work_on(cpu, &sfw->work);
+ queue_work_on(cpu, flushwq, &sfw->work);
}
for_each_online_cpu(cpu) {
@@ -4858,6 +4863,8 @@ void __init kmem_cache_init(void)
void __init kmem_cache_init_late(void)
{
+ flushwq = create_workqueue("slub_flushwq");
+ BUG_ON(!flushwq);
}
struct kmem_cache *
--
2.31.1
