fs: WQ_PERCPU added to alloc_workqueue users

DispatchCode · brauner · commit 69635d7f4b34 · 2025-09-19T16:15:07.000+02:00
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>
diff --git a/fs/afs/main.c b/fs/afs/main.c
@@ -169,13 +169,13 @@ static int __init afs_init(void)
 
 	printk(KERN_INFO "kAFS: Red Hat AFS client v0.1 registering.\n");
 
-	afs_wq = alloc_workqueue("afs", 0, 0);
+	afs_wq = alloc_workqueue("afs", WQ_PERCPU, 0);
 	if (!afs_wq)
 		goto error_afs_wq;
 	afs_async_calls = alloc_workqueue("kafsd", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
 	if (!afs_async_calls)
 		goto error_async;
-	afs_lock_manager = alloc_workqueue("kafs_lockd", WQ_MEM_RECLAIM, 0);
+	afs_lock_manager = alloc_workqueue("kafs_lockd", WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!afs_lock_manager)
 		goto error_lockmgr;
 
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
@@ -801,13 +801,13 @@ int bch2_fs_init_rw(struct bch_fs *c)
 	if (!(c->btree_update_wq = alloc_workqueue("bcachefs",
 				WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM|WQ_UNBOUND, 512)) ||
 	    !(c->btree_write_complete_wq = alloc_workqueue("bcachefs_btree_write_complete",
-				WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM, 1)) ||
+				WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM|WQ_PERCPU, 1)) ||
 	    !(c->copygc_wq = alloc_workqueue("bcachefs_copygc",
-				WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 1)) ||
+				WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE|WQ_PERCPU, 1)) ||
 	    !(c->btree_write_submit_wq = alloc_workqueue("bcachefs_btree_write_sumit",
-				WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM, 1)) ||
+				WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM|WQ_PERCPU, 1)) ||
 	    !(c->write_ref_wq = alloc_workqueue("bcachefs_write_ref",
-				WQ_FREEZABLE, 0)))
+				WQ_FREEZABLE|WQ_PERCPU, 0)))
 		return bch_err_throw(c, ENOMEM_fs_other_alloc);
 
 	int ret = bch2_fs_btree_interior_update_init(c) ?:
@@ -975,7 +975,7 @@ static struct bch_fs *bch2_fs_alloc(struct bch_sb *sb, struct bch_opts *opts,
 		sizeof(struct sort_iter_set);
 
 	if (!(c->btree_read_complete_wq = alloc_workqueue("bcachefs_btree_read_complete",
-				WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM, 512)) ||
+				WQ_HIGHPRI|WQ_FREEZABLE|WQ_MEM_RECLAIM|WQ_PERCPU, 512)) ||
 	    enumerated_ref_init(&c->writes, BCH_WRITE_REF_NR,
 				bch2_writes_disabled) ||
 	    mempool_init_kmalloc_pool(&c->fill_iter, 1, iter_size) ||
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
@@ -1958,7 +1958,7 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info)
 {
 	u32 max_active = fs_info->thread_pool_size;
 	unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND;
-	unsigned int ordered_flags = WQ_MEM_RECLAIM | WQ_FREEZABLE;
+	unsigned int ordered_flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_PERCPU;
 
 	fs_info->workers =
 		btrfs_alloc_workqueue(fs_info, "worker", flags, max_active, 16);
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
@@ -862,7 +862,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	fsc->inode_wq = alloc_workqueue("ceph-inode", WQ_UNBOUND, 0);
 	if (!fsc->inode_wq)
 		goto fail_client;
-	fsc->cap_wq = alloc_workqueue("ceph-cap", 0, 1);
+	fsc->cap_wq = alloc_workqueue("ceph-cap", WQ_PERCPU, 1);
 	if (!fsc->cap_wq)
 		goto fail_inode_wq;
 
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
@@ -1703,7 +1703,7 @@ static int work_start(void)
 		return -ENOMEM;
 	}
 
-	process_workqueue = alloc_workqueue("dlm_process", WQ_HIGHPRI | WQ_BH, 0);
+	process_workqueue = alloc_workqueue("dlm_process", WQ_HIGHPRI | WQ_BH | WQ_PERCPU, 0);
 	if (!process_workqueue) {
 		log_print("can't start dlm_process");
 		destroy_workqueue(io_workqueue);
diff --git a/fs/dlm/main.c b/fs/dlm/main.c
@@ -52,7 +52,7 @@ static int __init init_dlm(void)
 	if (error)
 		goto out_user;
 
-	dlm_wq = alloc_workqueue("dlm_wq", 0, 0);
+	dlm_wq = alloc_workqueue("dlm_wq", WQ_PERCPU, 0);
 	if (!dlm_wq) {
 		error = -ENOMEM;
 		goto out_plock;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
@@ -1180,7 +1180,7 @@ void cgroup_writeback_umount(struct super_block *sb)
 
 static int __init cgroup_writeback_init(void)
 {
-	isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0);
+	isw_wq = alloc_workqueue("inode_switch_wbs", WQ_PERCPU, 0);
 	if (!isw_wq)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
@@ -151,7 +151,8 @@ static int __init init_gfs2_fs(void)
 
 	error = -ENOMEM;
 	gfs2_recovery_wq = alloc_workqueue("gfs2_recovery",
-					  WQ_MEM_RECLAIM | WQ_FREEZABLE, 0);
+					  WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_PERCPU,
+					  0);
 	if (!gfs2_recovery_wq)
 		goto fail_wq1;
 
@@ -160,7 +161,7 @@ static int __init init_gfs2_fs(void)
 	if (!gfs2_control_wq)
 		goto fail_wq2;
 
-	gfs2_freeze_wq = alloc_workqueue("gfs2_freeze", 0, 0);
+	gfs2_freeze_wq = alloc_workqueue("gfs2_freeze", WQ_PERCPU, 0);
 
 	if (!gfs2_freeze_wq)
 		goto fail_wq3;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
@@ -1193,13 +1193,15 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	error = -ENOMEM;
 	sdp->sd_glock_wq = alloc_workqueue("gfs2-glock/%s",
-			WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_FREEZABLE, 0,
+			WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_FREEZABLE | WQ_PERCPU,
+			0,
 			sdp->sd_fsname);
 	if (!sdp->sd_glock_wq)
 		goto fail_iput;
 
 	sdp->sd_delete_wq = alloc_workqueue("gfs2-delete/%s",
-			WQ_MEM_RECLAIM | WQ_FREEZABLE, 0, sdp->sd_fsname);
+			WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_PERCPU, 0,
+			sdp->sd_fsname);
 	if (!sdp->sd_delete_wq)
 		goto fail_glock_wq;
 
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
@@ -1876,7 +1876,8 @@ static int dlm_join_domain(struct dlm_ctxt *dlm)
 	dlm_debug_init(dlm);
 
 	snprintf(wq_name, O2NM_MAX_NAME_LEN, "dlm_wq-%s", dlm->name);
-	dlm->dlm_worker = alloc_workqueue(wq_name, WQ_MEM_RECLAIM, 0);
+	dlm->dlm_worker = alloc_workqueue(wq_name, WQ_MEM_RECLAIM | WQ_PERCPU,
+					  0);
 	if (!dlm->dlm_worker) {
 		status = -ENOMEM;
 		mlog_errno(status);
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
@@ -595,7 +595,8 @@ static int __init init_dlmfs_fs(void)
 	}
 	cleanup_inode = 1;
 
-	user_dlm_worker = alloc_workqueue("user_dlm", WQ_MEM_RECLAIM, 0);
+	user_dlm_worker = alloc_workqueue("user_dlm",
+					  WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!user_dlm_worker) {
 		status = -ENOMEM;
 		goto bail;
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
@@ -1881,7 +1881,9 @@ init_cifs(void)
 		cifs_dbg(VFS, "dir_cache_timeout set to max of 65000 seconds\n");
 	}
 
-	cifsiod_wq = alloc_workqueue("cifsiod", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
+	cifsiod_wq = alloc_workqueue("cifsiod",
+				     WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU,
+				     0);
 	if (!cifsiod_wq) {
 		rc = -ENOMEM;
 		goto out_clean_proc;
@@ -1909,28 +1911,32 @@ init_cifs(void)
 	}
 
 	cifsoplockd_wq = alloc_workqueue("cifsoplockd",
-					 WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
+					 WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU,
+					 0);
 	if (!cifsoplockd_wq) {
 		rc = -ENOMEM;
 		goto out_destroy_fileinfo_put_wq;
 	}
 
 	deferredclose_wq = alloc_workqueue("deferredclose",
-					   WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
+					   WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU,
+					   0);
 	if (!deferredclose_wq) {
 		rc = -ENOMEM;
 		goto out_destroy_cifsoplockd_wq;
 	}
 
 	serverclose_wq = alloc_workqueue("serverclose",
-					   WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
+					   WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU,
+					   0);
 	if (!serverclose_wq) {
 		rc = -ENOMEM;
 		goto out_destroy_deferredclose_wq;
 	}
 
 	cfid_put_wq = alloc_workqueue("cfid_put_wq",
-				      WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
+				      WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU,
+				      0);
 	if (!cfid_put_wq) {
 		rc = -ENOMEM;
 		goto out_destroy_serverclose_wq;
diff --git a/fs/smb/server/ksmbd_work.c b/fs/smb/server/ksmbd_work.c
@@ -78,7 +78,7 @@ int ksmbd_work_pool_init(void)
 
 int ksmbd_workqueue_init(void)
 {
-	ksmbd_wq = alloc_workqueue("ksmbd-io", 0, 0);
+	ksmbd_wq = alloc_workqueue("ksmbd-io", WQ_PERCPU, 0);
 	if (!ksmbd_wq)
 		return -ENOMEM;
 	return 0;
diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c
@@ -2177,7 +2177,8 @@ int ksmbd_rdma_init(void)
 	 * for lack of credits
 	 */
 	smb_direct_wq = alloc_workqueue("ksmbd-smb_direct-wq",
-					WQ_HIGHPRI | WQ_MEM_RECLAIM, 0);
+					WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_PERCPU,
+					0);
 	if (!smb_direct_wq)
 		return -ENOMEM;
 
diff --git a/fs/super.c b/fs/super.c
@@ -2314,7 +2314,8 @@ int sb_init_dio_done_wq(struct super_block *sb)
 {
 	struct workqueue_struct *old;
 	struct workqueue_struct *wq = alloc_workqueue("dio/%s",
-						      WQ_MEM_RECLAIM, 0,
+						      WQ_MEM_RECLAIM | WQ_PERCPU,
+						      0,
 						      sb->s_id);
 	if (!wq)
 		return -ENOMEM;
diff --git a/fs/verity/verify.c b/fs/verity/verify.c
@@ -355,7 +355,7 @@ void __init fsverity_init_workqueue(void)
 	 * latency on ARM64.
 	 */
 	fsverity_read_workqueue = alloc_workqueue("fsverity_read_queue",
-						  WQ_HIGHPRI,
+						  WQ_HIGHPRI | WQ_PERCPU,
 						  num_online_cpus());
 	if (!fsverity_read_workqueue)
 		panic("failed to allocate fsverity_read_queue");
diff --git 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
@@ -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
@@ -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;
 

Original file line number	Diff line number	Diff line change
`@@ -1958,7 +1958,7 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info)`
`1958`	`1958`	`{`
`1959`	`1959`	`u32 max_active = fs_info->thread_pool_size;`
`1960`	`1960`	`unsigned int flags = WQ_MEM_RECLAIM \| WQ_FREEZABLE \| WQ_UNBOUND;`
`1961`		`- unsigned int ordered_flags = WQ_MEM_RECLAIM \| WQ_FREEZABLE;`
	`1961`	`+ unsigned int ordered_flags = WQ_MEM_RECLAIM \| WQ_FREEZABLE \| WQ_PERCPU;`
`1962`	`1962`
`1963`	`1963`	`fs_info->workers =`
`1964`	`1964`	`btrfs_alloc_workqueue(fs_info, "worker", flags, max_active, 16);`
Original file line number	Diff line number	Diff line change
`@@ -1703,7 +1703,7 @@ static int work_start(void)`
`1703`	`1703`	`return -ENOMEM;`
`1704`	`1704`	`}`
`1705`	`1705`
`1706`		`- process_workqueue = alloc_workqueue("dlm_process", WQ_HIGHPRI \| WQ_BH, 0);`
	`1706`	`+ process_workqueue = alloc_workqueue("dlm_process", WQ_HIGHPRI \| WQ_BH \| WQ_PERCPU, 0);`
`1707`	`1707`	`if (!process_workqueue) {`
`1708`	`1708`	`log_print("can't start dlm_process");`
`1709`	`1709`	`destroy_workqueue(io_workqueue);`
Original file line number	Diff line number	Diff line change
`@@ -1180,7 +1180,7 @@ void cgroup_writeback_umount(struct super_block *sb)`
`1180`	`1180`
`1181`	`1181`	`static int __init cgroup_writeback_init(void)`
`1182`	`1182`	`{`
`1183`		`- isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0);`
	`1183`	`+ isw_wq = alloc_workqueue("inode_switch_wbs", WQ_PERCPU, 0);`
`1184`	`1184`	`if (!isw_wq)`
`1185`	`1185`	`return -ENOMEM;`
`1186`	`1186`	`return 0;`