net: replace use of system_wq with system_percpu_wq

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.

system_unbound_wq should be the default workqueue so as not to enforce
locality constraints for random work whenever it's not required.

Adding system_dfl_wq to encourage its use when unbound work should be used.

The old system_unbound_wq will be kept for a few release cycles.

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
Link: https://patch.msgid.link/20250918142427.309519-3-marco.crivellari@suse.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/sfc/efx_channels.c

@@ -1281,7 +1281,7 @@ static int efx_poll(struct napi_struct *napi, int budget)
 		time = jiffies - channel->rfs_last_expiry;
 		/* Would our quota be >= 20? */
 		if (channel->rfs_filter_count * time >= 600 * HZ)
-			mod_delayed_work(system_wq, &channel->filter_work, 0);
+			mod_delayed_work(system_percpu_wq, &channel->filter_work, 0);
 #endif
 
 		/* There is no race here; although napi_disable() will

drivers/net/ethernet/sfc/siena/efx_channels.c

@@ -1300,7 +1300,7 @@ static int efx_poll(struct napi_struct *napi, int budget)
 		time = jiffies - channel->rfs_last_expiry;
 		/* Would our quota be >= 20? */
 		if (channel->rfs_filter_count * time >= 600 * HZ)
-			mod_delayed_work(system_wq, &channel->filter_work, 0);
+			mod_delayed_work(system_percpu_wq, &channel->filter_work, 0);
 #endif
 
 		/* There is no race here; although napi_disable() will

drivers/net/phy/sfp.c

@@ -911,7 +911,7 @@ static void sfp_soft_start_poll(struct sfp *sfp)
 
 	if (sfp->state_soft_mask & (SFP_F_LOS | SFP_F_TX_FAULT) &&
 	    !sfp->need_poll)
-		mod_delayed_work(system_wq, &sfp->poll, poll_jiffies);
+		mod_delayed_work(system_percpu_wq, &sfp->poll, poll_jiffies);
 	mutex_unlock(&sfp->st_mutex);
 }
 
@@ -1682,7 +1682,7 @@ static void sfp_hwmon_probe(struct work_struct *work)
 	err = sfp_read(sfp, true, 0, &sfp->diag, sizeof(sfp->diag));
 	if (err < 0) {
 		if (sfp->hwmon_tries--) {
-			mod_delayed_work(system_wq, &sfp->hwmon_probe,
+			mod_delayed_work(system_percpu_wq, &sfp->hwmon_probe,
 					 T_PROBE_RETRY_SLOW);
 		} else {
 			dev_warn(sfp->dev, "hwmon probe failed: %pe\n",
@@ -1709,7 +1709,7 @@ static void sfp_hwmon_probe(struct work_struct *work)
 static int sfp_hwmon_insert(struct sfp *sfp)
 {
 	if (sfp->have_a2 && sfp->id.ext.diagmon & SFP_DIAGMON_DDM) {
-		mod_delayed_work(system_wq, &sfp->hwmon_probe, 1);
+		mod_delayed_work(system_percpu_wq, &sfp->hwmon_probe, 1);
 		sfp->hwmon_tries = R_PROBE_RETRY_SLOW;
 	}
 
@@ -2563,7 +2563,7 @@ static void sfp_sm_module(struct sfp *sfp, unsigned int event)
 		/* Force a poll to re-read the hardware signal state after
 		 * sfp_sm_mod_probe() changed state_hw_mask.
 		 */
-		mod_delayed_work(system_wq, &sfp->poll, 1);
+		mod_delayed_work(system_percpu_wq, &sfp->poll, 1);
 
 		err = sfp_hwmon_insert(sfp);
 		if (err)
@@ -3008,7 +3008,7 @@ static void sfp_poll(struct work_struct *work)
 	// it's unimportant if we race while reading this.
 	if (sfp->state_soft_mask & (SFP_F_LOS | SFP_F_TX_FAULT) ||
 	    sfp->need_poll)
-		mod_delayed_work(system_wq, &sfp->poll, poll_jiffies);
+		mod_delayed_work(system_percpu_wq, &sfp->poll, poll_jiffies);
 }
 
 static struct sfp *sfp_alloc(struct device *dev)
@@ -3178,7 +3178,7 @@ static int sfp_probe(struct platform_device *pdev)
 	}
 
 	if (sfp->need_poll)
-		mod_delayed_work(system_wq, &sfp->poll, poll_jiffies);
+		mod_delayed_work(system_percpu_wq, &sfp->poll, poll_jiffies);
 
 	/* We could have an issue in cases no Tx disable pin is available or
 	 * wired as modules using a laser as their light source will continue to

net/bridge/br_cfm.c

@@ -134,7 +134,7 @@ static void ccm_rx_timer_start(struct br_cfm_peer_mep *peer_mep)
 	 * of the configured CC 'expected_interval'
 	 * in order to detect CCM defect after 3.25 interval.
 	 */
-	queue_delayed_work(system_wq, &peer_mep->ccm_rx_dwork,
+	queue_delayed_work(system_percpu_wq, &peer_mep->ccm_rx_dwork,
 			   usecs_to_jiffies(interval_us / 4));
 }
 
@@ -285,7 +285,7 @@ static void ccm_tx_work_expired(struct work_struct *work)
 		ccm_frame_tx(skb);
 
 	interval_us = interval_to_us(mep->cc_config.exp_interval);
-	queue_delayed_work(system_wq, &mep->ccm_tx_dwork,
+	queue_delayed_work(system_percpu_wq, &mep->ccm_tx_dwork,
 			   usecs_to_jiffies(interval_us));
 }
 
@@ -809,7 +809,7 @@ int br_cfm_cc_ccm_tx(struct net_bridge *br, const u32 instance,
 	 * to send first frame immediately
 	 */
 	mep->ccm_tx_end = jiffies + usecs_to_jiffies(tx_info->period * 1000000);
-	queue_delayed_work(system_wq, &mep->ccm_tx_dwork, 0);
+	queue_delayed_work(system_percpu_wq, &mep->ccm_tx_dwork, 0);
 
 save:
 	mep->cc_ccm_tx_info = *tx_info;

net/bridge/br_mrp.c

@@ -341,7 +341,7 @@ static void br_mrp_test_work_expired(struct work_struct *work)
 out:
 	rcu_read_unlock();
 
-	queue_delayed_work(system_wq, &mrp->test_work,
+	queue_delayed_work(system_percpu_wq, &mrp->test_work,
 			   usecs_to_jiffies(mrp->test_interval));
 }
 
@@ -418,7 +418,7 @@ static void br_mrp_in_test_work_expired(struct work_struct *work)
 out:
 	rcu_read_unlock();
 
-	queue_delayed_work(system_wq, &mrp->in_test_work,
+	queue_delayed_work(system_percpu_wq, &mrp->in_test_work,
 			   usecs_to_jiffies(mrp->in_test_interval));
 }
 
@@ -725,7 +725,7 @@ int br_mrp_start_test(struct net_bridge *br,
 	mrp->test_max_miss = test->max_miss;
 	mrp->test_monitor = test->monitor;
 	mrp->test_count_miss = 0;
-	queue_delayed_work(system_wq, &mrp->test_work,
+	queue_delayed_work(system_percpu_wq, &mrp->test_work,
 			   usecs_to_jiffies(test->interval));
 
 	return 0;
@@ -865,7 +865,7 @@ int br_mrp_start_in_test(struct net_bridge *br,
 	mrp->in_test_end = jiffies + usecs_to_jiffies(in_test->period);
 	mrp->in_test_max_miss = in_test->max_miss;
 	mrp->in_test_count_miss = 0;
-	queue_delayed_work(system_wq, &mrp->in_test_work,
+	queue_delayed_work(system_percpu_wq, &mrp->in_test_work,
 			   usecs_to_jiffies(in_test->interval));
 
 	return 0;

net/ceph/mon_client.c

@@ -314,7 +314,7 @@ static void __schedule_delayed(struct ceph_mon_client *monc)
 		delay = CEPH_MONC_PING_INTERVAL;
 
 	dout("__schedule_delayed after %lu\n", delay);
-	mod_delayed_work(system_wq, &monc->delayed_work,
+	mod_delayed_work(system_percpu_wq, &monc->delayed_work,
 			 round_jiffies_relative(delay));
 }
 

net/core/skmsg.c

@@ -876,7 +876,7 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
 	sk_psock_stop(psock);
 
 	INIT_RCU_WORK(&psock->rwork, sk_psock_destroy);
-	queue_rcu_work(system_wq, &psock->rwork);
+	queue_rcu_work(system_percpu_wq, &psock->rwork);
 }
 EXPORT_SYMBOL_GPL(sk_psock_drop);
 

net/devlink/core.c

@@ -320,7 +320,7 @@ static void devlink_release(struct work_struct *work)
 void devlink_put(struct devlink *devlink)
 {
 	if (refcount_dec_and_test(&devlink->refcount))
-		queue_rcu_work(system_wq, &devlink->rwork);
+		queue_rcu_work(system_percpu_wq, &devlink->rwork);
 }
 
 struct devlink *devlinks_xa_find_get(struct net *net, unsigned long *indexp)

net/ipv4/inet_fragment.c

@@ -183,7 +183,7 @@ static void fqdir_work_fn(struct work_struct *work)
 	rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL);
 
 	if (llist_add(&fqdir->free_list, &fqdir_free_list))
-		queue_delayed_work(system_wq, &fqdir_free_work, HZ);
+		queue_delayed_work(system_percpu_wq, &fqdir_free_work, HZ);
 }
 
 int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net)

net/netfilter/nf_conntrack_ecache.c

@@ -301,7 +301,7 @@ void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state)
 		net->ct.ecache_dwork_pending = true;
 	} else if (state == NFCT_ECACHE_DESTROY_SENT) {
 		if (!hlist_nulls_empty(&cnet->ecache.dying_list))
-			mod_delayed_work(system_wq, &cnet->ecache.dwork, 0);
+			mod_delayed_work(system_percpu_wq, &cnet->ecache.dwork, 0);
 		else
 			net->ct.ecache_dwork_pending = false;
 	}

net/openvswitch/dp_notify.c

@@ -75,7 +75,7 @@ static int dp_device_event(struct notifier_block *unused, unsigned long event,
 
 		/* schedule vport destroy, dev_put and genl notification */
 		ovs_net = net_generic(dev_net(dev), ovs_net_id);
-		queue_work(system_wq, &ovs_net->dp_notify_work);
+		queue_work(system_percpu_wq, &ovs_net->dp_notify_work);
 	}
 
 	return NOTIFY_DONE;

net/rfkill/input.c

@@ -159,7 +159,7 @@ static void rfkill_schedule_global_op(enum rfkill_sched_op op)
 	rfkill_op_pending = true;
 	if (op == RFKILL_GLOBAL_OP_EPO && !rfkill_is_epo_lock_active()) {
 		/* bypass the limiter for EPO */
-		mod_delayed_work(system_wq, &rfkill_op_work, 0);
+		mod_delayed_work(system_percpu_wq, &rfkill_op_work, 0);
 		rfkill_last_scheduled = jiffies;
 	} else
 		rfkill_schedule_ratelimited();

net/smc/smc_core.c

@@ -85,7 +85,7 @@ static void smc_lgr_schedule_free_work(struct smc_link_group *lgr)
 	 * otherwise there is a risk of out-of-sync link groups.
 	 */
 	if (!lgr->freeing) {
-		mod_delayed_work(system_wq, &lgr->free_work,
+		mod_delayed_work(system_percpu_wq, &lgr->free_work,
 				 (!lgr->is_smcd && lgr->role == SMC_CLNT) ?
 						SMC_LGR_FREE_DELAY_CLNT :
 						SMC_LGR_FREE_DELAY_SERV);

net/vmw_vsock/af_vsock.c

@@ -1649,7 +1649,7 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
 			 * reschedule it, then ungrab the socket refcount to
 			 * keep it balanced.
 			 */
-			if (mod_delayed_work(system_wq, &vsk->connect_work,
+			if (mod_delayed_work(system_percpu_wq, &vsk->connect_work,
 					     timeout))
 				sock_put(sk);