In the case of fast device addition/removal, it's possible that hv_eject_device_work() can start to run before create_root_hv_pci_bus() starts to run; as a result, the pci_get_domain_bus_and_slot() in hv_eject_device_work() can return a 'pdev' of NULL, and hv_eject_device_work() can remove the 'hpdev', and immediately send a message PCI_EJECTION_COMPLETE to the host, and the host immediately unassigns the PCI device from the guest; meanwhile, create_root_hv_pci_bus() and the PCI device driver can be probing the dead PCI device and reporting timeout errors.
Fix the issue by adding a per-bus mutex 'state_lock' and grabbing the mutex before powering on the PCI bus in hv_pci_enter_d0(): when hv_eject_device_work() starts to run, it's able to find the 'pdev' and call pci_stop_and_remove_bus_device(pdev): if the PCI device driver has loaded, the PCI device driver's probe() function is already called in create_root_hv_pci_bus() -> pci_bus_add_devices(), and now hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to call the PCI device driver's remove() function and remove the device reliably; if the PCI device driver hasn't loaded yet, the function call hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to remove the PCI device reliably and the PCI device driver's probe() function won't be called; if the PCI device driver's probe() is already running (e.g., systemd-udev is loading the PCI device driver), it must be holding the per-device lock, and after the probe() finishes and releases the lock, hv_eject_device_work() -> pci_stop_and_remove_bus_device() is able to proceed to remove the device reliably.
Fixes: 4daace0d8ce8 ("PCI: hv: Add paravirtual PCI front-end for Microsoft Hyper-V VMs") Signed-off-by: Dexuan Cui decui@microsoft.com Reviewed-by: Michael Kelley mikelley@microsoft.com Acked-by: Lorenzo Pieralisi lpieralisi@kernel.org Cc: stable@vger.kernel.org ---
v2: Removed the "debug code". Fixed the "goto out" in hv_pci_resume() [Michael Kelley] Added Cc:stable
v3: Added Michael's Reviewed-by.
v4: Added Lorenzo's Acked-by.
drivers/pci/controller/pci-hyperv.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-)
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 1a5296fad1c48..2d93d0c4f10db 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -489,7 +489,10 @@ struct hv_pcibus_device { struct fwnode_handle *fwnode; /* Protocol version negotiated with the host */ enum pci_protocol_version_t protocol_version; + + struct mutex state_lock; enum hv_pcibus_state state; + struct hv_device *hdev; resource_size_t low_mmio_space; resource_size_t high_mmio_space; @@ -2605,6 +2608,8 @@ static void pci_devices_present_work(struct work_struct *work) if (!dr) return;
+ mutex_lock(&hbus->state_lock); + /* First, mark all existing children as reported missing. */ spin_lock_irqsave(&hbus->device_list_lock, flags); list_for_each_entry(hpdev, &hbus->children, list_entry) { @@ -2686,6 +2691,8 @@ static void pci_devices_present_work(struct work_struct *work) break; }
+ mutex_unlock(&hbus->state_lock); + kfree(dr); }
@@ -2834,6 +2841,8 @@ static void hv_eject_device_work(struct work_struct *work) hpdev = container_of(work, struct hv_pci_dev, wrk); hbus = hpdev->hbus;
+ mutex_lock(&hbus->state_lock); + /* * Ejection can come before or after the PCI bus has been set up, so * attempt to find it and tear down the bus state, if it exists. This @@ -2870,6 +2879,8 @@ static void hv_eject_device_work(struct work_struct *work) put_pcichild(hpdev); put_pcichild(hpdev); /* hpdev has been freed. Do not use it any more. */ + + mutex_unlock(&hbus->state_lock); }
/** @@ -3636,6 +3647,7 @@ static int hv_pci_probe(struct hv_device *hdev, return -ENOMEM;
hbus->bridge = bridge; + mutex_init(&hbus->state_lock); hbus->state = hv_pcibus_init; hbus->wslot_res_allocated = -1;
@@ -3745,9 +3757,11 @@ static int hv_pci_probe(struct hv_device *hdev, if (ret) goto free_irq_domain;
+ mutex_lock(&hbus->state_lock); + ret = hv_pci_enter_d0(hdev); if (ret) - goto free_irq_domain; + goto release_state_lock;
ret = hv_pci_allocate_bridge_windows(hbus); if (ret) @@ -3765,12 +3779,15 @@ static int hv_pci_probe(struct hv_device *hdev, if (ret) goto free_windows;
+ mutex_unlock(&hbus->state_lock); return 0;
free_windows: hv_pci_free_bridge_windows(hbus); exit_d0: (void) hv_pci_bus_exit(hdev, true); +release_state_lock: + mutex_unlock(&hbus->state_lock); free_irq_domain: irq_domain_remove(hbus->irq_domain); free_fwnode: @@ -4020,20 +4037,26 @@ static int hv_pci_resume(struct hv_device *hdev) if (ret) goto out;
+ mutex_lock(&hbus->state_lock); + ret = hv_pci_enter_d0(hdev); if (ret) - goto out; + goto release_state_lock;
ret = hv_send_resources_allocated(hdev); if (ret) - goto out; + goto release_state_lock;
prepopulate_bars(hbus);
hv_pci_restore_msi_state(hbus);
hbus->state = hv_pcibus_installed; + mutex_unlock(&hbus->state_lock); return 0; + +release_state_lock: + mutex_unlock(&hbus->state_lock); out: vmbus_close(hdev->channel); return ret;