net: 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 change adds a new WQ_PERCPU flag at the network subsystem, 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://patch.msgid.link/20250918142427.309519-4-marco.crivellari@suse.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/can/spi/hi311x.c

@@ -770,7 +770,8 @@ static int hi3110_open(struct net_device *net)
 		goto out_close;
 	}
 
-	priv->wq = alloc_workqueue("hi3110_wq", WQ_FREEZABLE | WQ_MEM_RECLAIM,
+	priv->wq = alloc_workqueue("hi3110_wq",
+				   WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU,
 				   0);
 	if (!priv->wq) {
 		ret = -ENOMEM;

drivers/net/can/spi/mcp251x.c

@@ -1378,7 +1378,8 @@ static int mcp251x_can_probe(struct spi_device *spi)
 	if (ret)
 		goto out_clk;
 
-	priv->wq = alloc_workqueue("mcp251x_wq", WQ_FREEZABLE | WQ_MEM_RECLAIM,
+	priv->wq = alloc_workqueue("mcp251x_wq",
+				   WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU,
 				   0);
 	if (!priv->wq) {
 		ret = -ENOMEM;

drivers/net/ethernet/cavium/liquidio/lio_core.c

@@ -472,7 +472,7 @@ int setup_rx_oom_poll_fn(struct net_device *netdev)
 		q_no = lio->linfo.rxpciq[q].s.q_no;
 		wq = &lio->rxq_status_wq[q_no];
 		wq->wq = alloc_workqueue("rxq-oom-status",
-					 WQ_MEM_RECLAIM, 0);
+					 WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 		if (!wq->wq) {
 			dev_err(&oct->pci_dev->dev, "unable to create cavium rxq oom status wq\n");
 			return -ENOMEM;

drivers/net/ethernet/cavium/liquidio/lio_main.c

@@ -526,7 +526,8 @@ static inline int setup_link_status_change_wq(struct net_device *netdev)
 	struct octeon_device *oct = lio->oct_dev;
 
 	lio->link_status_wq.wq = alloc_workqueue("link-status",
-						 WQ_MEM_RECLAIM, 0);
+						 WQ_MEM_RECLAIM | WQ_PERCPU,
+						 0);
 	if (!lio->link_status_wq.wq) {
 		dev_err(&oct->pci_dev->dev, "unable to create cavium link status wq\n");
 		return -1;
@@ -659,7 +660,8 @@ static inline int setup_sync_octeon_time_wq(struct net_device *netdev)
 	struct octeon_device *oct = lio->oct_dev;
 
 	lio->sync_octeon_time_wq.wq =
-		alloc_workqueue("update-octeon-time", WQ_MEM_RECLAIM, 0);
+		alloc_workqueue("update-octeon-time",
+				WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!lio->sync_octeon_time_wq.wq) {
 		dev_err(&oct->pci_dev->dev, "Unable to create wq to update octeon time\n");
 		return -1;
@@ -1734,7 +1736,7 @@ static inline int setup_tx_poll_fn(struct net_device *netdev)
 	struct octeon_device *oct = lio->oct_dev;
 
 	lio->txq_status_wq.wq = alloc_workqueue("txq-status",
-						WQ_MEM_RECLAIM, 0);
+						WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!lio->txq_status_wq.wq) {
 		dev_err(&oct->pci_dev->dev, "unable to create cavium txq status wq\n");
 		return -1;

drivers/net/ethernet/cavium/liquidio/lio_vf_main.c

@@ -304,7 +304,8 @@ static int setup_link_status_change_wq(struct net_device *netdev)
 	struct octeon_device *oct = lio->oct_dev;
 
 	lio->link_status_wq.wq = alloc_workqueue("link-status",
-						 WQ_MEM_RECLAIM, 0);
+						 WQ_MEM_RECLAIM | WQ_PERCPU,
+						 0);
 	if (!lio->link_status_wq.wq) {
 		dev_err(&oct->pci_dev->dev, "unable to create cavium link status wq\n");
 		return -1;

drivers/net/ethernet/cavium/liquidio/request_manager.c

@@ -132,7 +132,7 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 	oct->fn_list.setup_iq_regs(oct, iq_no);
 
 	oct->check_db_wq[iq_no].wq = alloc_workqueue("check_iq_db",
-						     WQ_MEM_RECLAIM,
+						     WQ_MEM_RECLAIM | WQ_PERCPU,
 						     0);
 	if (!oct->check_db_wq[iq_no].wq) {
 		vfree(iq->request_list);

drivers/net/ethernet/cavium/liquidio/response_manager.c

@@ -39,7 +39,8 @@ int octeon_setup_response_list(struct octeon_device *oct)
 	}
 	spin_lock_init(&oct->cmd_resp_wqlock);
 
-	oct->dma_comp_wq.wq = alloc_workqueue("dma-comp", WQ_MEM_RECLAIM, 0);
+	oct->dma_comp_wq.wq = alloc_workqueue("dma-comp",
+					      WQ_MEM_RECLAIM | WQ_PERCPU, 0);
 	if (!oct->dma_comp_wq.wq) {
 		dev_err(&oct->pci_dev->dev, "failed to create wq thread\n");
 		return -ENOMEM;

drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c

@@ -4884,7 +4884,7 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 	priv->tx_tstamp_type = HWTSTAMP_TX_OFF;
 	priv->rx_tstamp = false;
 
-	priv->dpaa2_ptp_wq = alloc_workqueue("dpaa2_ptp_wq", 0, 0);
+	priv->dpaa2_ptp_wq = alloc_workqueue("dpaa2_ptp_wq", WQ_PERCPU, 0);
 	if (!priv->dpaa2_ptp_wq) {
 		err = -ENOMEM;
 		goto err_wq_alloc;

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c

@@ -12912,7 +12912,8 @@ static int __init hclge_init(void)
 {
 	pr_debug("%s is initializing\n", HCLGE_NAME);
 
-	hclge_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, HCLGE_NAME);
+	hclge_wq = alloc_workqueue("%s", WQ_UNBOUND, 0,
+				   HCLGE_NAME);
 	if (!hclge_wq) {
 		pr_err("%s: failed to create workqueue\n", HCLGE_NAME);
 		return -ENOMEM;

drivers/net/ethernet/intel/fm10k/fm10k_main.c

@@ -37,7 +37,7 @@ static int __init fm10k_init_module(void)
 	pr_info("%s\n", fm10k_copyright);
 
 	/* create driver workqueue */
-	fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
+	fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM | WQ_PERCPU, 0,
 					  fm10k_driver_name);
 	if (!fm10k_workqueue)
 		return -ENOMEM;

drivers/net/ethernet/intel/i40e/i40e_main.c

@@ -16617,7 +16617,7 @@ static int __init i40e_init_module(void)
 	 * since we need to be able to guarantee forward progress even under
 	 * memory pressure.
 	 */
-	i40e_wq = alloc_workqueue("%s", 0, 0, i40e_driver_name);
+	i40e_wq = alloc_workqueue("%s", WQ_PERCPU, 0, i40e_driver_name);
 	if (!i40e_wq) {
 		pr_err("%s: Failed to create workqueue\n", i40e_driver_name);
 		return -ENOMEM;

drivers/net/ethernet/marvell/octeontx2/af/cgx.c

@@ -2005,7 +2005,7 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	/* init wq for processing linkup requests */
 	INIT_WORK(&cgx->cgx_cmd_work, cgx_lmac_linkup_work);
-	cgx->cgx_cmd_workq = alloc_workqueue("cgx_cmd_workq", 0, 0);
+	cgx->cgx_cmd_workq = alloc_workqueue("cgx_cmd_workq", WQ_PERCPU, 0);
 	if (!cgx->cgx_cmd_workq) {
 		dev_err(dev, "alloc workqueue failed for cgx cmd");
 		err = -ENOMEM;

drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c

@@ -913,7 +913,7 @@ int rvu_mcs_init(struct rvu *rvu)
 	/* Initialize the wq for handling mcs interrupts */
 	INIT_LIST_HEAD(&rvu->mcs_intrq_head);
 	INIT_WORK(&rvu->mcs_intr_work, mcs_intr_handler_task);
-	rvu->mcs_intr_wq = alloc_workqueue("mcs_intr_wq", 0, 0);
+	rvu->mcs_intr_wq = alloc_workqueue("mcs_intr_wq", WQ_PERCPU, 0);
 	if (!rvu->mcs_intr_wq) {
 		dev_err(rvu->dev, "mcs alloc workqueue failed\n");
 		return -ENOMEM;

drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c

@@ -315,7 +315,7 @@ static int cgx_lmac_event_handler_init(struct rvu *rvu)
 	spin_lock_init(&rvu->cgx_evq_lock);
 	INIT_LIST_HEAD(&rvu->cgx_evq_head);
 	INIT_WORK(&rvu->cgx_evh_work, cgx_evhandler_task);
-	rvu->cgx_evh_wq = alloc_workqueue("rvu_evh_wq", 0, 0);
+	rvu->cgx_evh_wq = alloc_workqueue("rvu_evh_wq", WQ_PERCPU, 0);
 	if (!rvu->cgx_evh_wq) {
 		dev_err(rvu->dev, "alloc workqueue failed");
 		return -ENOMEM;

drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c

@@ -376,7 +376,7 @@ int rvu_rep_install_mcam_rules(struct rvu *rvu)
 	spin_lock_init(&rvu->rep_evtq_lock);
 	INIT_LIST_HEAD(&rvu->rep_evtq_head);
 	INIT_WORK(&rvu->rep_evt_work, rvu_rep_wq_handler);
-	rvu->rep_evt_wq = alloc_workqueue("rep_evt_wq", 0, 0);
+	rvu->rep_evt_wq = alloc_workqueue("rep_evt_wq", WQ_PERCPU, 0);
 	if (!rvu->rep_evt_wq) {
 		dev_err(rvu->dev, "REP workqueue allocation failed\n");
 		return -ENOMEM;

drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c

@@ -798,7 +798,8 @@ int cn10k_ipsec_init(struct net_device *netdev)
 	pf->ipsec.sa_size = sa_size;
 
 	INIT_WORK(&pf->ipsec.sa_work, cn10k_ipsec_sa_wq_handler);
-	pf->ipsec.sa_workq = alloc_workqueue("cn10k_ipsec_sa_workq", 0, 0);
+	pf->ipsec.sa_workq = alloc_workqueue("cn10k_ipsec_sa_workq",
+					     WQ_PERCPU, 0);
 	if (!pf->ipsec.sa_workq) {
 		netdev_err(pf->netdev, "SA alloc workqueue failed\n");
 		return -ENOMEM;

drivers/net/ethernet/marvell/prestera/prestera_main.c

@@ -1500,7 +1500,7 @@ EXPORT_SYMBOL(prestera_device_unregister);
 
 static int __init prestera_module_init(void)
 {
-	prestera_wq = alloc_workqueue("prestera", 0, 0);
+	prestera_wq = alloc_workqueue("prestera", WQ_PERCPU, 0);
 	if (!prestera_wq)
 		return -ENOMEM;
 

drivers/net/ethernet/marvell/prestera/prestera_pci.c

@@ -898,7 +898,7 @@ static int prestera_pci_probe(struct pci_dev *pdev,
 
 	dev_info(fw->dev.dev, "Prestera FW is ready\n");
 
-	fw->wq = alloc_workqueue("prestera_fw_wq", WQ_HIGHPRI, 1);
+	fw->wq = alloc_workqueue("prestera_fw_wq", WQ_HIGHPRI | WQ_PERCPU, 1);
 	if (!fw->wq) {
 		err = -ENOMEM;
 		goto err_wq_alloc;

drivers/net/ethernet/mellanox/mlxsw/core.c

@@ -886,7 +886,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 	if (!(mlxsw_core->bus->features & MLXSW_BUS_F_TXRX))
 		return 0;
 
-	emad_wq = alloc_workqueue("mlxsw_core_emad", 0, 0);
+	emad_wq = alloc_workqueue("mlxsw_core_emad", WQ_PERCPU, 0);
 	if (!emad_wq)
 		return -ENOMEM;
 	mlxsw_core->emad_wq = emad_wq;
@@ -3381,7 +3381,7 @@ static int __init mlxsw_core_module_init(void)
 	if (err)
 		return err;
 
-	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, 0, 0);
+	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, WQ_PERCPU, 0);
 	if (!mlxsw_wq) {
 		err = -ENOMEM;
 		goto err_alloc_workqueue;

drivers/net/ethernet/netronome/nfp/nfp_main.c

@@ -797,7 +797,7 @@ static int nfp_pci_probe(struct pci_dev *pdev,
 	pf->pdev = pdev;
 	pf->dev_info = dev_info;
 
-	pf->wq = alloc_workqueue("nfp-%s", 0, 2, pci_name(pdev));
+	pf->wq = alloc_workqueue("nfp-%s", WQ_PERCPU, 2, pci_name(pdev));
 	if (!pf->wq) {
 		err = -ENOMEM;
 		goto err_pci_priv_unset;