fs: WQ_PERCPU added to alloc_workqueue users

Currently if a user enqueue a work item using schedule_delayed_work() the
used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use
WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to
schedule_work() that is using system_wq and queue_work(), that makes use
again of WORK_CPU_UNBOUND.
This lack of consistentcy cannot be addressed without refactoring the API.

alloc_workqueue() treats all queues as per-CPU by default, while unbound
workqueues must opt-in via WQ_UNBOUND.

This default is suboptimal: most workloads benefit from unbound queues,
allowing the scheduler to place worker threads where they’re needed and
reducing noise when CPUs are isolated.

This patch adds a new WQ_PERCPU flag to all the fs subsystem users to
explicitly request the use of the per-CPU behavior. Both flags coexist
for one release cycle to allow callers to transition their calls.

Once migration is complete, WQ_UNBOUND can be removed and unbound will
become the implicit default.

With the introduction of the WQ_PERCPU flag (equivalent to !WQ_UNBOUND),
any alloc_workqueue() caller that doesn’t explicitly specify WQ_UNBOUND
must now use WQ_PERCPU.

All existing users have been updated accordingly.

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
Link: https://lore.kernel.org/20250916082906.77439-4-marco.crivellari@suse.com
Signed-off-by: Christian Brauner <brauner@kernel.org>

3 files changed, 11 insertions, 10 deletions

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index c8a57e21a1d3..0da19472d603 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1489,8 +1489,7 @@ xlog_alloc_log(
 	log->l_iclog->ic_prev = prev_iclog;	/* re-write 1st prev ptr */
 
 	log->l_ioend_workqueue = alloc_workqueue("xfs-log/%s",
-			XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM |
-				    WQ_HIGHPRI),
+			XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU),
 			0, mp->m_super->s_id);
 	if (!log->l_ioend_workqueue)
 		goto out_free_iclog;
diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c
index 866c71d9fbae..73b7e72944e4 100644
--- a/fs/xfs/xfs_mru_cache.c
+++ b/fs/xfs/xfs_mru_cache.c
@@ -293,7 +293,8 @@ int
 xfs_mru_cache_init(void)
 {
 	xfs_mru_reap_wq = alloc_workqueue("xfs_mru_cache",
-			XFS_WQFLAGS(WQ_MEM_RECLAIM | WQ_FREEZABLE), 1);
+			XFS_WQFLAGS(WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_PERCPU),
+			1);
 	if (!xfs_mru_reap_wq)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index bb0a82635a77..43e9aab71610 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -578,19 +578,19 @@ xfs_init_mount_workqueues(
 	struct xfs_mount	*mp)
 {
 	mp->m_buf_workqueue = alloc_workqueue("xfs-buf/%s",
-			XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM),
+			XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU),
 			1, mp->m_super->s_id);
 	if (!mp->m_buf_workqueue)
 		goto out;
 
 	mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s",
-			XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM),
+			XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU),
 			0, mp->m_super->s_id);
 	if (!mp->m_unwritten_workqueue)
 		goto out_destroy_buf;
 
 	mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s",
-			XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM),
+			XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU),
 			0, mp->m_super->s_id);
 	if (!mp->m_reclaim_workqueue)
 		goto out_destroy_unwritten;
@@ -602,13 +602,14 @@ xfs_init_mount_workqueues(
 		goto out_destroy_reclaim;
 
 	mp->m_inodegc_wq = alloc_workqueue("xfs-inodegc/%s",
-			XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM),
+			XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU),
 			1, mp->m_super->s_id);
 	if (!mp->m_inodegc_wq)
 		goto out_destroy_blockgc;
 
 	mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s",
-			XFS_WQFLAGS(WQ_FREEZABLE), 0, mp->m_super->s_id);
+			XFS_WQFLAGS(WQ_FREEZABLE | WQ_PERCPU), 0,
+			mp->m_super->s_id);
 	if (!mp->m_sync_workqueue)
 		goto out_destroy_inodegc;
 
@@ -2596,8 +2597,8 @@ xfs_init_workqueues(void)
 	 * AGs in all the filesystems mounted. Hence use the default large
 	 * max_active value for this workqueue.
 	 */
-	xfs_alloc_wq = alloc_workqueue("xfsalloc",
-			XFS_WQFLAGS(WQ_MEM_RECLAIM | WQ_FREEZABLE), 0);
+	xfs_alloc_wq = alloc_workqueue("xfsalloc", XFS_WQFLAGS(WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_PERCPU),
+			0);
 	if (!xfs_alloc_wq)
 		return -ENOMEM;