[PATCH v2 3/6] PCI: hv: serialize the present/eject work items

[Dexuan Cui]

When we hot-remove the device, we first receive a PCI_EJECT message and
then receive a PCI_BUS_RELATIONS message with bus_rel->device_count == 0.

The first message is offloaded to hv_eject_device_work(), and the second
is offloaded to pci_devices_present_work(). Both the paths can be running
list_del(&hpdev->list_entry), causing general protection fault, because
system_wq can run them concurrently.

The patch eliminates the race condition.

Signed-off-by: Dexuan Cui <de...@microsoft.com>
Tested-by: Adrian Suhov <v-ads...@microsoft.com>
Tested-by: Chris Valean <v-chv...@microsoft.com>
Cc: Vitaly Kuznetsov <vkuzn...@redhat.com>
Cc: Jack Morgenstein <ja...@mellanox.com>
Cc: sta...@vger.kernel.org
Cc: Stephen Hemminger <sthem...@microsoft.com>
Cc: K. Y. Srinivasan <k...@microsoft.com>
---
 drivers/pci/host/pci-hyperv.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/host/pci-hyperv.c b/drivers/pci/host/pci-hyperv.c
index 04edb24c92ee..aaee41faf55f 100644
--- a/drivers/pci/host/pci-hyperv.c
+++ b/drivers/pci/host/pci-hyperv.c
@@ -461,6 +461,8 @@ struct hv_pcibus_device {
        struct retarget_msi_interrupt retarget_msi_interrupt_params;
 
        spinlock_t retarget_msi_interrupt_lock;
+
+       struct workqueue_struct *wq;
 };
 
 /*
@@ -1770,7 +1772,7 @@ static void hv_pci_devices_present(struct 
hv_pcibus_device *hbus,
        spin_unlock_irqrestore(&hbus->device_list_lock, flags);
 
        get_hvpcibus(hbus);
-       schedule_work(&dr_wrk->wrk);
+       queue_work(hbus->wq, &dr_wrk->wrk);
 }
 
 /**
@@ -1845,7 +1847,7 @@ static void hv_pci_eject_device(struct hv_pci_dev *hpdev)
        get_pcichild(hpdev, hv_pcidev_ref_pnp);
        INIT_WORK(&hpdev->wrk, hv_eject_device_work);
        get_hvpcibus(hpdev->hbus);
-       schedule_work(&hpdev->wrk);
+       queue_work(hpdev->hbus->wq, &hpdev->wrk);
 }
 
 /**
@@ -2460,11 +2462,17 @@ static int hv_pci_probe(struct hv_device *hdev,
        spin_lock_init(&hbus->retarget_msi_interrupt_lock);
        sema_init(&hbus->enum_sem, 1);
        init_completion(&hbus->remove_event);
+       hbus->wq = alloc_ordered_workqueue("hv_pci_%x", 0,
+                                          hbus->sysdata.domain);
+       if (!hbus->wq) {
+               ret = -ENOMEM;
+               goto free_bus;
+       }
 
        ret = vmbus_open(hdev->channel, pci_ring_size, pci_ring_size, NULL, 0,
                         hv_pci_onchannelcallback, hbus);
        if (ret)
-               goto free_bus;
+               goto destroy_wq;
 
        hv_set_drvdata(hdev, hbus);
 
@@ -2533,6 +2541,8 @@ static int hv_pci_probe(struct hv_device *hdev,
        hv_free_config_window(hbus);
 close:
        vmbus_close(hdev->channel);
+destroy_wq:
+       destroy_workqueue(hbus->wq);
 free_bus:
        free_page((unsigned long)hbus);
        return ret;
@@ -2612,6 +2622,7 @@ static int hv_pci_remove(struct hv_device *hdev)
        irq_domain_free_fwnode(hbus->sysdata.fwnode);
        put_hvpcibus(hbus);
        wait_for_completion(&hbus->remove_event);
+       destroy_workqueue(hbus->wq);
        free_page((unsigned long)hbus);
        return 0;
 }
-- 
2.7.4