PCI: Add WQ_PERCPU to alloc_workqueue() users

Currently work items enqueued by schedule_delayed_work() use "system_wq" (a
per-CPU wq), while queue_delayed_work() uses 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 consistency 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 continues the effort to refactor workqueue APIs, which began with the
introduction of new workqueues and a new alloc_workqueue() flag in:

  128ea9f ("workqueue: Add system_percpu_wq and system_dfl_wq")
  930c2ea ("workqueue: Add new WQ_PERCPU flag")

Add WQ_PERCPU to explicitly request alloc_workqueue() to be per-CPU when
WQ_UNBOUND has not been specified.

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.

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

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
[bhelgaas: squash similar commits]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://patch.msgid.link/20251107142526.234685-1-marco.crivellari@suse.com
Link: https://patch.msgid.link/20251107142835.237636-1-marco.crivellari@suse.com
Link: https://patch.msgid.link/20251107143108.240025-1-marco.crivellari@suse.com
Link: https://patch.msgid.link/20251107143335.242342-1-marco.crivellari@suse.com
Link: https://patch.msgid.link/20251107143624.244978-1-marco.crivellari@suse.com

Author: DispatchCode

drivers/pci/endpoint/functions/pci-epf-mhi.c

@@ -686,7 +686,7 @@ static int pci_epf_mhi_dma_init(struct pci_epf_mhi *epf_mhi)
 		goto err_release_tx;
 	}
 
-	epf_mhi->dma_wq = alloc_workqueue("pci_epf_mhi_dma_wq", 0, 0);
+	epf_mhi->dma_wq = alloc_workqueue("pci_epf_mhi_dma_wq", WQ_PERCPU, 0);
 	if (!epf_mhi->dma_wq) {
 		ret = -ENOMEM;
 		goto err_release_rx;

drivers/pci/endpoint/functions/pci-epf-ntb.c

@@ -2124,8 +2124,8 @@ static int __init epf_ntb_init(void)
 {
 	int ret;
 
-	kpcintb_workqueue = alloc_workqueue("kpcintb", WQ_MEM_RECLAIM |
-					    WQ_HIGHPRI, 0);
+	kpcintb_workqueue = alloc_workqueue("kpcintb",
+				    WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU, 0);
 	ret = pci_epf_register_driver(&epf_ntb_driver);
 	if (ret) {
 		destroy_workqueue(kpcintb_workqueue);

drivers/pci/endpoint/functions/pci-epf-test.c

@@ -1188,7 +1188,7 @@ static int __init pci_epf_test_init(void)
 	int ret;
 
 	kpcitest_workqueue = alloc_workqueue("kpcitest",
-					     WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
+				    WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU, 0);
 	if (!kpcitest_workqueue) {
 		pr_err("Failed to allocate the kpcitest work queue\n");
 		return -ENOMEM;

drivers/pci/endpoint/functions/pci-epf-vntb.c

@@ -1651,8 +1651,8 @@ static int __init epf_ntb_init(void)
 {
 	int ret;
 
-	kpcintb_workqueue = alloc_workqueue("kpcintb", WQ_MEM_RECLAIM |
-					    WQ_HIGHPRI, 0);
+	kpcintb_workqueue = alloc_workqueue("kpcintb",
+				    WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU, 0);
 	ret = pci_epf_register_driver(&epf_ntb_driver);
 	if (ret) {
 		destroy_workqueue(kpcintb_workqueue);

drivers/pci/hotplug/pnv_php.c

@@ -802,7 +802,7 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn)
 	}
 
 	/* Allocate workqueue for this slot's interrupt handling */
-	php_slot->wq = alloc_workqueue("pciehp-%s", 0, 0, php_slot->name);
+	php_slot->wq = alloc_workqueue("pciehp-%s", WQ_PERCPU, 0, php_slot->name);
 	if (!php_slot->wq) {
 		SLOT_WARN(php_slot, "Cannot alloc workqueue\n");
 		kfree(php_slot->name);

drivers/pci/hotplug/shpchp_core.c

@@ -80,7 +80,8 @@ static int init_slots(struct controller *ctrl)
 		slot->device = ctrl->slot_device_offset + i;
 		slot->number = ctrl->first_slot + (ctrl->slot_num_inc * i);
 
-		slot->wq = alloc_workqueue("shpchp-%d", 0, 0, slot->number);
+		slot->wq = alloc_workqueue("shpchp-%d", WQ_PERCPU, 0,
+					   slot->number);
 		if (!slot->wq) {
 			retval = -ENOMEM;
 			goto error_slot;