PCI: Fix runtime PM race with PME polling

Testing that a device is not currently in a low power state provides no
guarantees that the device is not imminently transitioning to such a state.
Increment the PM usage counter before accessing the device.  Since we don't
wish to wake the device for PME polling, do so only if the device is
already active by using pm_runtime_get_if_active().

Link: https://lore.kernel.org/r/20230803171233.3810944-3-alex.williamson@redhat.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 60230da957e0c4b1d4481a191dfa709600f2b48b..bc266f290b2c4e2655ffc162f0facbfb20d1f1c4 100644 (file)
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2415,10 +2415,13 @@ static void pci_pme_list_scan(struct work_struct *work)
 
        mutex_lock(&pci_pme_list_mutex);
        list_for_each_entry_safe(pme_dev, n, &pci_pme_list, list) {
-               if (pme_dev->dev->pme_poll) {
-                       struct pci_dev *bridge;
+               struct pci_dev *pdev = pme_dev->dev;
+
+               if (pdev->pme_poll) {
+                       struct pci_dev *bridge = pdev->bus->self;
+                       struct device *dev = &pdev->dev;
+                       int pm_status;
 
-                       bridge = pme_dev->dev->bus->self;
                        /*
                         * If bridge is in low power state, the
                         * configuration space of subordinate devices
@@ -2426,14 +2429,20 @@ static void pci_pme_list_scan(struct work_struct *work)
                         */
                        if (bridge && bridge->current_state != PCI_D0)
                                continue;
+
                        /*
-                        * If the device is in D3cold it should not be
-                        * polled either.
+                        * If the device is in a low power state it
+                        * should not be polled either.
                         */
-                       if (pme_dev->dev->current_state == PCI_D3cold)
+                       pm_status = pm_runtime_get_if_active(dev, true);
+                       if (!pm_status)
                                continue;
 
-                       pci_pme_wakeup(pme_dev->dev, NULL);
+                       if (pdev->current_state != PCI_D3cold)
+                               pci_pme_wakeup(pdev, NULL);
+
+                       if (pm_status > 0)
+                               pm_runtime_put(dev);
                } else {
                        list_del(&pme_dev->list);
                        kfree(pme_dev);