Merge tag 'vfs-6.18-rc1.workqueue' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs workqueue updates from Christian Brauner:
 "This contains various workqueue changes affecting the filesystem
  layer.

  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 replaces the use of system_wq and system_unbound_wq. system_wq is
  a per-CPU workqueue which isn't very obvious from the name and
  system_unbound_wq is to be used when locality is not required.

  So this renames system_wq to system_percpu_wq, and system_unbound_wq
  to system_dfl_wq.

  This also adds a new WQ_PERCPU flag to allow the fs subsystem users to
  explicitly request the use of per-CPU behavior. Both WQ_UNBOUND and
  WQ_PERCPU flags coexist for one release cycle to allow callers to
  transition their calls. WQ_UNBOUND will be removed in a next release
  cycle"

* tag 'vfs-6.18-rc1.workqueue' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  fs: WQ_PERCPU added to alloc_workqueue users
  fs: replace use of system_wq with system_percpu_wq
  fs: replace use of system_unbound_wq with system_dfl_wq

40 files changed, 79 insertions, 65 deletions

diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index 69e1dd55b160..894d2bad6b6c 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -42,7 +42,7 @@ static void afs_volume_init_callback(struct afs_volume *volume)
 	list_for_each_entry(vnode, &volume->open_mmaps, cb_mmap_link) {
 		if (vnode->cb_v_check != atomic_read(&volume->cb_v_break)) {
 			afs_clear_cb_promise(vnode, afs_cb_promise_clear_vol_init_cb);
-			queue_work(system_unbound_wq, &vnode->cb_work);
+			queue_work(system_dfl_wq, &vnode->cb_work);
 		}
 	}
 
@@ -90,7 +90,7 @@ void __afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reas
 		if (reason != afs_cb_break_for_deleted &&
 		    vnode->status.type == AFS_FTYPE_FILE &&
 		    atomic_read(&vnode->cb_nr_mmap))
-			queue_work(system_unbound_wq, &vnode->cb_work);
+			queue_work(system_dfl_wq, &vnode->cb_work);
 
 		trace_afs_cb_break(&vnode->fid, vnode->cb_break, reason, true);
 	} else {
diff --git a/fs/afs/main.c b/fs/afs/main.c
index 02475d415d88..e6bb8237db98 100644
--- 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/afs/write.c b/fs/afs/write.c
index 2e7526ea883a..93ad86ff3345 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -172,7 +172,7 @@ static void afs_issue_write_worker(struct work_struct *work)
 void afs_issue_write(struct netfs_io_subrequest *subreq)
 {
 	subreq->work.func = afs_issue_write_worker;
-	if (!queue_work(system_unbound_wq, &subreq->work))
+	if (!queue_work(system_dfl_wq, &subreq->work))
 		WARN_ON_ONCE(1);
 }
 
diff --git a/fs/aio.c b/fs/aio.c
index 7fc7b6221312..6002617f078c 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -636,7 +636,7 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
 
 	/* Synchronize against RCU protected table->table[] dereferences */
 	INIT_RCU_WORK(&ctx->free_rwork, free_ioctx);
-	queue_rcu_work(system_wq, &ctx->free_rwork);
+	queue_rcu_work(system_percpu_wq, &ctx->free_rwork);
 }
 
 /*
diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c
index 4b095235a0d2..0afb44ce1a85 100644
--- a/fs/bcachefs/btree_write_buffer.c
+++ b/fs/bcachefs/btree_write_buffer.c
@@ -827,7 +827,7 @@ int bch2_journal_keys_to_write_buffer_end(struct bch_fs *c, struct journal_keys_
 
 	if (bch2_btree_write_buffer_should_flush(c) &&
 	    __enumerated_ref_tryget(&c->writes, BCH_WRITE_REF_btree_write_buffer) &&
-	    !queue_work(system_unbound_wq, &c->btree_write_buffer.flush_work))
+	    !queue_work(system_dfl_wq, &c->btree_write_buffer.flush_work))
 		enumerated_ref_put(&c->writes, BCH_WRITE_REF_btree_write_buffer);
 
 	if (dst->wb == &wb->flushing)
diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c
index e0874ad9a6cf..460e2e6341f1 100644
--- a/fs/bcachefs/io_read.c
+++ b/fs/bcachefs/io_read.c
@@ -684,7 +684,7 @@ static void bch2_rbio_error(struct bch_read_bio *rbio,
 
 	if (bch2_err_matches(ret, BCH_ERR_data_read_retry)) {
 		bch2_rbio_punt(rbio, bch2_rbio_retry,
-			       RBIO_CONTEXT_UNBOUND, system_unbound_wq);
+			       RBIO_CONTEXT_UNBOUND, system_dfl_wq);
 	} else {
 		rbio = bch2_rbio_free(rbio);
 
@@ -921,10 +921,10 @@ csum_err:
 	bch2_rbio_error(rbio, -BCH_ERR_data_read_retry_csum_err, BLK_STS_IOERR);
 	goto out;
 decompression_err:
-	bch2_rbio_punt(rbio, bch2_read_decompress_err, RBIO_CONTEXT_UNBOUND, system_unbound_wq);
+	bch2_rbio_punt(rbio, bch2_read_decompress_err, RBIO_CONTEXT_UNBOUND, system_dfl_wq);
 	goto out;
 decrypt_err:
-	bch2_rbio_punt(rbio, bch2_read_decrypt_err, RBIO_CONTEXT_UNBOUND, system_unbound_wq);
+	bch2_rbio_punt(rbio, bch2_read_decrypt_err, RBIO_CONTEXT_UNBOUND, system_dfl_wq);
 	goto out;
 }
 
@@ -963,7 +963,7 @@ static void bch2_read_endio(struct bio *bio)
 	    rbio->promote ||
 	    crc_is_compressed(rbio->pick.crc) ||
 	    bch2_csum_type_is_encryption(rbio->pick.crc.csum_type))
-		context = RBIO_CONTEXT_UNBOUND,	wq = system_unbound_wq;
+		context = RBIO_CONTEXT_UNBOUND,	wq = system_dfl_wq;
 	else if (rbio->pick.crc.csum_type)
 		context = RBIO_CONTEXT_HIGHPRI,	wq = system_highpri_wq;
 
diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c
index 9e028dbcc3d0..29bea8e0e495 100644
--- a/fs/bcachefs/journal_io.c
+++ b/fs/bcachefs/journal_io.c
@@ -1362,7 +1362,7 @@ int bch2_journal_read(struct bch_fs *c,
 					  BCH_DEV_READ_REF_journal_read))
 			closure_call(&ca->journal.read,
 				     bch2_journal_read_device,
-				     system_unbound_wq,
+				     system_dfl_wq,
 				     &jlist.cl);
 		else
 			degraded = true;
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index c46b1053a02c..f2417d298b84 100644
--- 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/block-group.c b/fs/btrfs/block-group.c
index 499a9edf0ca3..fcd274d83fd7 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -2038,7 +2038,7 @@ void btrfs_reclaim_bgs(struct btrfs_fs_info *fs_info)
 	btrfs_reclaim_sweep(fs_info);
 	spin_lock(&fs_info->unused_bgs_lock);
 	if (!list_empty(&fs_info->reclaim_bgs))
-		queue_work(system_unbound_wq, &fs_info->reclaim_bgs_work);
+		queue_work(system_dfl_wq, &fs_info->reclaim_bgs_work);
 	spin_unlock(&fs_info->unused_bgs_lock);
 }
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 70fc4e7cc5a0..aa4393eba997 100644
--- 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/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 57f52585a6dd..9a5a497edc97 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -1372,7 +1372,7 @@ void btrfs_free_extent_maps(struct btrfs_fs_info *fs_info, long nr_to_scan)
 	if (atomic64_cmpxchg(&fs_info->em_shrinker_nr_to_scan, 0, nr_to_scan) != 0)
 		return;
 
-	queue_work(system_unbound_wq, &fs_info->em_shrinker_work);
+	queue_work(system_dfl_wq, &fs_info->em_shrinker_work);
 }
 
 void btrfs_init_extent_map_shrinker_work(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 0481c693ac2e..c573d80550ad 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -1830,7 +1830,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info,
 							  space_info->flags,
 							  orig_bytes, flush,
 							  "enospc");
-				queue_work(system_unbound_wq, async_work);
+				queue_work(system_dfl_wq, async_work);
 			}
 		} else {
 			list_add_tail(&ticket.list,
@@ -1847,7 +1847,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info,
 		    need_preemptive_reclaim(fs_info, space_info)) {
 			trace_btrfs_trigger_flush(fs_info, space_info->flags,
 						  orig_bytes, flush, "preempt");
-			queue_work(system_unbound_wq,
+			queue_work(system_dfl_wq,
 				   &fs_info->preempt_reclaim_work);
 		}
 	}
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index f426276e2b6b..71cf9be75c42 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -2521,7 +2521,7 @@ void btrfs_schedule_zone_finish_bg(struct btrfs_block_group *bg,
 	refcount_inc(&eb->refs);
 	bg->last_eb = eb;
 	INIT_WORK(&bg->zone_finish_work, btrfs_zone_finish_endio_workfn);
-	queue_work(system_unbound_wq, &bg->zone_finish_work);
+	queue_work(system_dfl_wq, &bg->zone_finish_work);
 }
 
 void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg)
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 70dc9467f6a0..db6c2db68f96 100644
--- 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/coredump.c b/fs/coredump.c
index 60bc9685e149..0d9a5d07a75d 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -635,7 +635,7 @@ static int umh_coredump_setup(struct subprocess_info *info, struct cred *new)
 
 		/*
 		 * Usermode helpers are childen of either
-		 * system_unbound_wq or of kthreadd. So we know that
+		 * system_dfl_wq or of kthreadd. So we know that
 		 * we're starting off with a clean file descriptor
 		 * table. So we should always be able to use
 		 * COREDUMP_PIDFD_NUMBER as our file descriptor value.
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index e4373bce1bc2..9a0b6c2b6b01 100644
--- 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
index 4887c8a05318..a44d16da7187 100644
--- 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/ext4/mballoc.c b/fs/ext4/mballoc.c
index 5898d92ba19f..8b18802e83eb 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3995,7 +3995,7 @@ void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid)
 		list_splice_tail(&freed_data_list, &sbi->s_discard_list);
 		spin_unlock(&sbi->s_md_lock);
 		if (wake)
-			queue_work(system_unbound_wq, &sbi->s_discard_work);
+			queue_work(system_dfl_wq, &sbi->s_discard_work);
 	} else {
 		list_for_each_entry_safe(entry, tmp, &freed_data_list, efd_list)
 			kmem_cache_free(ext4_free_data_cachep, entry);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index b6768ef3daa6..815be2bbb1c4 100644
--- 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;
@@ -2442,7 +2442,7 @@ static int dirtytime_interval_handler(const struct ctl_table *table, int write,
 
 	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (ret == 0 && write)
-		mod_delayed_work(system_wq, &dirtytime_work, 0);
+		mod_delayed_work(system_percpu_wq, &dirtytime_work, 0);
 	return ret;
 }
 
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 5150aa25e64b..66a1ba8c56b5 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -119,7 +119,7 @@ void fuse_check_timeout(struct work_struct *work)
 	    goto abort_conn;
 
 out:
-	queue_delayed_work(system_wq, &fc->timeout.work,
+	queue_delayed_work(system_percpu_wq, &fc->timeout.work,
 			   fuse_timeout_timer_freq);
 	return;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index fdecd5a90dee..7485a41af892 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1273,7 +1273,7 @@ static void set_request_timeout(struct fuse_conn *fc, unsigned int timeout)
 {
 	fc->timeout.req_timeout = secs_to_jiffies(timeout);
 	INIT_DELAYED_WORK(&fc->timeout.work, fuse_check_timeout);
-	queue_delayed_work(system_wq, &fc->timeout.work,
+	queue_delayed_work(system_percpu_wq, &fc->timeout.work,
 			   fuse_timeout_timer_freq);
 }
 
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index 0727f60ad028..9d65719353fa 100644
--- 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
index c770006f8889..aa15183f9a16 100644
--- 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/netfs/misc.c b/fs/netfs/misc.c
index 20748bcfbf59..486166460e17 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -321,7 +321,7 @@ void netfs_wake_collector(struct netfs_io_request *rreq)
 {
 	if (test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags) &&
 	    !test_bit(NETFS_RREQ_RETRYING, &rreq->flags)) {
-		queue_work(system_unbound_wq, &rreq->work);
+		queue_work(system_dfl_wq, &rreq->work);
 	} else {
 		trace_netfs_rreq(rreq, netfs_rreq_trace_wake_queue);
 		wake_up(&rreq->waitq);
diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c
index 40a1c7d6f6e0..b8c4918d3dcd 100644
--- a/fs/netfs/objects.c
+++ b/fs/netfs/objects.c
@@ -169,7 +169,7 @@ void netfs_put_request(struct netfs_io_request *rreq, enum netfs_rreq_ref_trace
 		dead = __refcount_dec_and_test(&rreq->ref, &r);
 		trace_netfs_rreq_ref(debug_id, r - 1, what);
 		if (dead)
-			WARN_ON(!queue_work(system_unbound_wq, &rreq->cleanup_work));
+			WARN_ON(!queue_work(system_dfl_wq, &rreq->cleanup_work));
 	}
 }
 
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 7f1ec9c67ff2..f9a3a1fbf44c 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -335,7 +335,7 @@ static int param_set_nfs_timeout(const char *val, const struct kernel_param *kp)
 			num *= HZ;
 		*((int *)kp->arg) = num;
 		if (!list_empty(&nfs_automount_list))
-			mod_delayed_work(system_wq, &nfs_automount_task, num);
+			mod_delayed_work(system_percpu_wq, &nfs_automount_task, num);
 	} else {
 		*((int *)kp->arg) = -1*HZ;
 		cancel_delayed_work(&nfs_automount_task);
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index db3811af0796..18ae614e5a6c 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -122,7 +122,7 @@ nfs4_schedule_state_renewal(struct nfs_client *clp)
 		timeout = 5 * HZ;
 	dprintk("%s: requeueing work. Lease period = %ld\n",
 			__func__, (timeout + HZ - 1) / HZ);
-	mod_delayed_work(system_wq, &clp->cl_renewd, timeout);
+	mod_delayed_work(system_percpu_wq, &clp->cl_renewd, timeout);
 	set_bit(NFS_CS_RENEWD, &clp->cl_res_state);
 	spin_unlock(&clp->cl_lock);
 }
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 732abf6b92a5..85ca663c052c 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -113,7 +113,7 @@ static void
 nfsd_file_schedule_laundrette(void)
 {
 	if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags))
-		queue_delayed_work(system_unbound_wq, &nfsd_filecache_laundrette,
+		queue_delayed_work(system_dfl_wq, &nfsd_filecache_laundrette,
 				   NFSD_LAUNDRETTE_DELAY);
 }
 
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 798340db69d7..55a03bb05aa1 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -428,7 +428,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
 		conn->destroy_next = connector_destroy_list;
 		connector_destroy_list = conn;
 		spin_unlock(&destroy_lock);
-		queue_work(system_unbound_wq, &connector_reaper_work);
+		queue_work(system_dfl_wq, &connector_reaper_work);
 	}
 	/*
 	 * Note that we didn't update flags telling whether inode cares about
@@ -439,7 +439,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
 	spin_lock(&destroy_lock);
 	list_add(&mark->g_list, &destroy_list);
 	spin_unlock(&destroy_lock);
-	queue_delayed_work(system_unbound_wq, &reaper_work,
+	queue_delayed_work(system_dfl_wq, &reaper_work,
 			   FSNOTIFY_REAPER_DELAY);
 }
 EXPORT_SYMBOL_GPL(fsnotify_put_mark);
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 2018501b2249..2347a50f079b 100644
--- 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
index 807e2b758a5c..cccaa1d6fbba 100644
--- 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/quota/dquot.c b/fs/quota/dquot.c
index df4a9b348769..afa15a214538 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -881,7 +881,7 @@ void dqput(struct dquot *dquot)
 	put_releasing_dquots(dquot);
 	atomic_dec(&dquot->dq_count);
 	spin_unlock(&dq_list_lock);
-	queue_delayed_work(system_unbound_wq, &quota_release_work, 1);
+	queue_delayed_work(system_dfl_wq, &quota_release_work, 1);
 }
 EXPORT_SYMBOL(dqput);
 
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index b0e84ca5d268..dcb39d1b5958 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1895,7 +1895,9 @@ 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;
@@ -1923,28 +1925,32 @@ 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
index 72b00ca6e455..4a71f46d7020 100644
--- 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
index 74dfb6496095..5df138fc6004 100644
--- a/fs/smb/server/transport_rdma.c
+++ b/fs/smb/server/transport_rdma.c
@@ -2242,7 +2242,8 @@ 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
index b49a3b550736..f4fa0e93c463 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -2251,7 +2251,8 @@ 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
index affc307eb6a6..f0c47b9afb8c 100644
--- 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
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 a05ff68748dc..70ee2d55e4f1 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;