PCI: Add pci_try_reset_function(), pci_try_reset_slot(), pci_try_reset_bus()

When doing a function/slot/bus reset PCI grabs the device_lock for each
device to block things like suspend and driver probes, but call paths exist
where this lock may already be held.  This creates an opportunity for
deadlock.  For instance, vfio allows userspace to issue resets so long as
it owns the device(s).  If a driver unbind .remove callback races with
userspace issuing a reset, we have a deadlock as userspace gets stuck
waiting on device_lock while another thread has device_lock and waits for
.remove to complete.  To resolve this, we can make a version of the reset
interfaces which use trylock.  With this, we can safely attempt a reset and
return error to userspace if there is contention.

[bhelgaas: the deadlock happens when A (userspace) has a file descriptor for
the device, and B waits in this path:

  driver_detach
    device_lock                     # take device_lock
    __device_release_driver
      pci_device_remove             # pci_bus_type.remove
        vfio_pci_remove             # pci_driver .remove
          vfio_del_group_dev
            wait_event(vfio.release_q, !vfio_dev_present)   # wait (holding device_lock)

Now B is stuck until A gives up the file descriptor.  If A tries to acquire
device_lock for any reason, we deadlock because A is waiting for B to release
the lock, and B is waiting for A to release the file descriptor.]

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
(cherry picked from commit 61cf16d8bd38c3dc52033ea75d5b1f8368514a17)
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
LTC-Bugzilla: #104951

2 files changed, 158 insertions, 0 deletions

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 761af26e573a2f..e9c0815d890fb6 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3331,6 +3331,18 @@ static void pci_dev_lock(struct pci_dev *dev)
 	device_lock(&dev->dev);
 }
 
+/* Return 1 on successful lock, 0 on contention */
+static int pci_dev_trylock(struct pci_dev *dev)
+{
+	if (pci_cfg_access_trylock(dev)) {
+		if (device_trylock(&dev->dev))
+			return 1;
+		pci_cfg_access_unlock(dev);
+	}
+
+	return 0;
+}
+
 static void pci_dev_unlock(struct pci_dev *dev)
 {
 	device_unlock(&dev->dev);
@@ -3474,6 +3486,34 @@ int pci_reset_function(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_reset_function);
 
+/**
+ * pci_try_reset_function - quiesce and reset a PCI device function
+ * @dev: PCI device to reset
+ *
+ * Same as above, except return -EAGAIN if unable to lock device.
+ */
+int pci_try_reset_function(struct pci_dev *dev)
+{
+	int rc;
+
+	rc = pci_dev_reset(dev, 1);
+	if (rc)
+		return rc;
+
+	pci_dev_save_and_disable(dev);
+
+	if (pci_dev_trylock(dev)) {
+		rc = __pci_dev_reset(dev, 0);
+		pci_dev_unlock(dev);
+	} else
+		rc = -EAGAIN;
+
+	pci_dev_restore(dev);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pci_try_reset_function);
+
 /* Lock devices from the top of the tree down */
 static void pci_bus_lock(struct pci_bus *bus)
 {
@@ -3498,6 +3538,32 @@ static void pci_bus_unlock(struct pci_bus *bus)
 	}
 }
 
+/* Return 1 on successful lock, 0 on contention */
+static int pci_bus_trylock(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		if (!pci_dev_trylock(dev))
+			goto unlock;
+		if (dev->subordinate) {
+			if (!pci_bus_trylock(dev->subordinate)) {
+				pci_dev_unlock(dev);
+				goto unlock;
+			}
+		}
+	}
+	return 1;
+
+unlock:
+	list_for_each_entry_continue_reverse(dev, &bus->devices, bus_list) {
+		if (dev->subordinate)
+			pci_bus_unlock(dev->subordinate);
+		pci_dev_unlock(dev);
+	}
+	return 0;
+}
+
 /* Lock devices from the top of the tree down */
 static void pci_slot_lock(struct pci_slot *slot)
 {
@@ -3526,6 +3592,37 @@ static void pci_slot_unlock(struct pci_slot *slot)
 	}
 }
 
+/* Return 1 on successful lock, 0 on contention */
+static int pci_slot_trylock(struct pci_slot *slot)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &slot->bus->devices, bus_list) {
+		if (!dev->slot || dev->slot != slot)
+			continue;
+		if (!pci_dev_trylock(dev))
+			goto unlock;
+		if (dev->subordinate) {
+			if (!pci_bus_trylock(dev->subordinate)) {
+				pci_dev_unlock(dev);
+				goto unlock;
+			}
+		}
+	}
+	return 1;
+
+unlock:
+	list_for_each_entry_continue_reverse(dev,
+					     &slot->bus->devices, bus_list) {
+		if (!dev->slot || dev->slot != slot)
+			continue;
+		if (dev->subordinate)
+			pci_bus_unlock(dev->subordinate);
+		pci_dev_unlock(dev);
+	}
+	return 0;
+}
+
 /* Save and disable devices from the top of the tree down */
 static void pci_bus_save_and_disable(struct pci_bus *bus)
 {
@@ -3649,6 +3746,35 @@ int pci_reset_slot(struct pci_slot *slot)
 }
 EXPORT_SYMBOL_GPL(pci_reset_slot);
 
+/**
+ * pci_try_reset_slot - Try to reset a PCI slot
+ * @slot: PCI slot to reset
+ *
+ * Same as above except return -EAGAIN if the slot cannot be locked
+ */
+int pci_try_reset_slot(struct pci_slot *slot)
+{
+	int rc;
+
+	rc = pci_slot_reset(slot, 1);
+	if (rc)
+		return rc;
+
+	pci_slot_save_and_disable(slot);
+
+	if (pci_slot_trylock(slot)) {
+		might_sleep();
+		rc = pci_reset_hotplug_slot(slot->hotplug, 0);
+		pci_slot_unlock(slot);
+	} else
+		rc = -EAGAIN;
+
+	pci_slot_restore(slot);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pci_try_reset_slot);
+
 static int pci_bus_reset(struct pci_bus *bus, int probe)
 {
 	if (!bus->self)
@@ -3708,6 +3834,35 @@ int pci_reset_bus(struct pci_bus *bus)
 EXPORT_SYMBOL_GPL(pci_reset_bus);
 
 /**
+ * pci_try_reset_bus - Try to reset a PCI bus
+ * @bus: top level PCI bus to reset
+ *
+ * Same as above except return -EAGAIN if the bus cannot be locked
+ */
+int pci_try_reset_bus(struct pci_bus *bus)
+{
+	int rc;
+
+	rc = pci_bus_reset(bus, 1);
+	if (rc)
+		return rc;
+
+	pci_bus_save_and_disable(bus);
+
+	if (pci_bus_trylock(bus)) {
+		might_sleep();
+		pci_reset_bridge_secondary_bus(bus->self);
+		pci_bus_unlock(bus);
+	} else
+		rc = -EAGAIN;
+
+	pci_bus_restore(bus);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pci_try_reset_bus);
+
+/**
  * pcix_get_max_mmrbc - get PCI-X maximum designed memory read byte count
  * @dev: PCI device to query
  *
diff --git a/include/linux/pci.h b/include/linux/pci.h
index da6a0d0c4cb14f..032cec280d36a5 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -923,10 +923,13 @@ int pcie_set_mps(struct pci_dev *dev, int mps);
 int __pci_reset_function(struct pci_dev *dev);
 int __pci_reset_function_locked(struct pci_dev *dev);
 int pci_reset_function(struct pci_dev *dev);
+int pci_try_reset_function(struct pci_dev *dev);
 int pci_probe_reset_slot(struct pci_slot *slot);
 int pci_reset_slot(struct pci_slot *slot);
+int pci_try_reset_slot(struct pci_slot *slot);
 int pci_probe_reset_bus(struct pci_bus *bus);
 int pci_reset_bus(struct pci_bus *bus);
+int pci_try_reset_bus(struct pci_bus *bus);
 void pci_reset_bridge_secondary_bus(struct pci_dev *dev);
 void pci_update_resource(struct pci_dev *dev, int resno);
 int __must_check pci_assign_resource(struct pci_dev *dev, int i);