vfio/pci: Change vfio_pci_try_bus_reset() to use the dev_set

vfio_pci_try_bus_reset() is triggering a reset of the entire_dev set if
any device within it has accumulated a needs_reset. This reset can only be
done once all of the drivers operating the PCI devices to be reset are in
a known safe state.

Make this clearer by directly operating on the dev_set instead of the
vfio_pci_device. Rename the function to vfio_pci_dev_set_try_reset().

Use the device list inside the dev_set to check that all drivers are in a
safe state instead of working backwards from the pci_device.

The dev_set->lock directly prevents devices from joining/leaving the set,
or changing their state, which further implies the pci_device cannot
change drivers or that the vfio_device be freed, eliminating the need for
get/put's.

If a pci_device to be reset is not in the dev_set then the reset cannot be
used as we can't know what the state of that driver is. Directly measure
this by checking that every pci_device is in the dev_set - which
effectively proves that VFIO drivers are attached to everything.

Remove the odd interaction around vfio_pci_set_power_state() - have the
only caller avoid its redundant vfio_pci_set_power_state() instead of
avoiding it inside vfio_pci_dev_set_try_reset().

This restructuring corrects a call to pci_dev_driver() without holding the
device_lock() and removes a hard wiring to &vfio_pci_driver.

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Link: https://lore.kernel.org/r/9-v4-9ea22c5e6afb+1adf-vfio_reflck_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

drivers/vfio/pci/vfio_pci.c

@@ -223,7 +223,7 @@ static void vfio_pci_probe_mmaps(struct vfio_pci_device *vdev)
 	}
 }
 
-static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev);
+static bool vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set);
 static void vfio_pci_disable(struct vfio_pci_device *vdev);
 static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data);
 
@@ -404,6 +404,9 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
 	struct vfio_pci_ioeventfd *ioeventfd, *ioeventfd_tmp;
 	int i, bar;
 
+	/* For needs_reset */
+	lockdep_assert_held(&vdev->vdev.dev_set->lock);
+
 	/* Stop the device from further DMA */
 	pci_clear_master(pdev);
 
@@ -487,9 +490,7 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
 out:
 	pci_disable_device(pdev);
 
-	vfio_pci_try_bus_reset(vdev);
+	if (!vfio_pci_dev_set_try_reset(vdev->vdev.dev_set) && !disable_idle_d3)
-
-	if (!disable_idle_d3)
 		vfio_pci_set_power_state(vdev, PCI_D3hot);
 }
 
@@ -2145,36 +2146,6 @@ static struct pci_driver vfio_pci_driver = {
 	.err_handler		= &vfio_err_handlers,
 };
 
-static int vfio_pci_get_unused_devs(struct pci_dev *pdev, void *data)
-{
-	struct vfio_devices *devs = data;
-	struct vfio_device *device;
-	struct vfio_pci_device *vdev;
-
-	if (devs->cur_index == devs->max_index)
-		return -ENOSPC;
-
-	device = vfio_device_get_from_dev(&pdev->dev);
-	if (!device)
-		return -EINVAL;
-
-	if (pci_dev_driver(pdev) != &vfio_pci_driver) {
-		vfio_device_put(device);
-		return -EBUSY;
-	}
-
-	vdev = container_of(device, struct vfio_pci_device, vdev);
-
-	/* Fault if the device is not unused */
-	if (device->open_count) {
-		vfio_device_put(device);
-		return -EBUSY;
-	}
-
-	devs->devices[devs->cur_index++] = vdev;
-	return 0;
-}
-
 static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data)
 {
 	struct vfio_devices *devs = data;
@@ -2208,79 +2179,98 @@ static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data)
 	return 0;
 }
 
+static int vfio_pci_is_device_in_set(struct pci_dev *pdev, void *data)
+{
+	struct vfio_device_set *dev_set = data;
+	struct vfio_device *cur;
+
+	list_for_each_entry(cur, &dev_set->device_list, dev_set_list)
+		if (cur->dev == &pdev->dev)
+			return 0;
+	return -EBUSY;
+}
+
 /*
- * If a bus or slot reset is available for the provided device and:
+ * vfio-core considers a group to be viable and will create a vfio_device even
+ * if some devices are bound to drivers like pci-stub or pcieport. Here we
+ * require all PCI devices to be inside our dev_set since that ensures they stay
+ * put and that every driver controlling the device can co-ordinate with the
+ * device reset.
+ *
+ * Returns the pci_dev to pass to pci_reset_bus() if every PCI device to be
+ * reset is inside the dev_set, and pci_reset_bus() can succeed. NULL otherwise.
+ */
+static struct pci_dev *
+vfio_pci_dev_set_resettable(struct vfio_device_set *dev_set)
+{
+	struct pci_dev *pdev;
+
+	lockdep_assert_held(&dev_set->lock);
+
+	/*
+	 * By definition all PCI devices in the dev_set share the same PCI
+	 * reset, so any pci_dev will have the same outcomes for
+	 * pci_probe_reset_*() and pci_reset_bus().
+	 */
+	pdev = list_first_entry(&dev_set->device_list, struct vfio_pci_device,
+				vdev.dev_set_list)->pdev;
+
+	/* pci_reset_bus() is supported */
+	if (pci_probe_reset_slot(pdev->slot) && pci_probe_reset_bus(pdev->bus))
+		return NULL;
+
+	if (vfio_pci_for_each_slot_or_bus(pdev, vfio_pci_is_device_in_set,
+					  dev_set,
+					  !pci_probe_reset_slot(pdev->slot)))
+		return NULL;
+	return pdev;
+}
+
+static bool vfio_pci_dev_set_needs_reset(struct vfio_device_set *dev_set)
+{
+	struct vfio_pci_device *cur;
+	bool needs_reset = false;
+
+	list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) {
+		/* No VFIO device in the set can have an open device FD */
+		if (cur->vdev.open_count)
+			return false;
+		needs_reset |= cur->needs_reset;
+	}
+	return needs_reset;
+}
+
+/*
+ * If a bus or slot reset is available for the provided dev_set and:
  *  - All of the devices affected by that bus or slot reset are unused
- *    (!refcnt)
  *  - At least one of the affected devices is marked dirty via
  *    needs_reset (such as by lack of FLR support)
- * Then attempt to perform that bus or slot reset.  Callers are required
+ * Then attempt to perform that bus or slot reset.
- * to hold vdev->dev_set->lock, protecting the bus/slot reset group from
+ * Returns true if the dev_set was reset.
- * concurrent opens.  A vfio_device reference is acquired for each device
- * to prevent unbinds during the reset operation.
- *
- * NB: vfio-core considers a group to be viable even if some devices are
- * bound to drivers like pci-stub or pcieport.  Here we require all devices
- * to be bound to vfio_pci since that's the only way we can be sure they
- * stay put.
  */
-static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev)
+static bool vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set)
 {
-	struct vfio_devices devs = { .cur_index = 0 };
+	struct vfio_pci_device *cur;
-	int i = 0, ret = -EINVAL;
+	struct pci_dev *pdev;
-	bool slot = false;
+	int ret;
-	struct vfio_pci_device *tmp;
 
-	if (!pci_probe_reset_slot(vdev->pdev->slot))
+	if (!vfio_pci_dev_set_needs_reset(dev_set))
-		slot = true;
+		return false;
-	else if (pci_probe_reset_bus(vdev->pdev->bus))
-		return;
 
-	if (vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_count_devs,
+	pdev = vfio_pci_dev_set_resettable(dev_set);
-					  &i, slot) || !i)
+	if (!pdev)
-		return;
+		return false;
 
-	devs.max_index = i;
+	ret = pci_reset_bus(pdev);
-	devs.devices = kcalloc(i, sizeof(struct vfio_device *), GFP_KERNEL);
+	if (ret)
-	if (!devs.devices)
+		return false;
-		return;
 
-	if (vfio_pci_for_each_slot_or_bus(vdev->pdev,
+	list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) {
-					  vfio_pci_get_unused_devs,
+		cur->needs_reset = false;
-					  &devs, slot))
+		if (!disable_idle_d3)
-		goto put_devs;
+			vfio_pci_set_power_state(cur, PCI_D3hot);
-
-	/* Does at least one need a reset? */
-	for (i = 0; i < devs.cur_index; i++) {
-		tmp = devs.devices[i];
-		if (tmp->needs_reset) {
-			ret = pci_reset_bus(vdev->pdev);
-			break;
 	}
-	}
+	return true;
-
-put_devs:
-	for (i = 0; i < devs.cur_index; i++) {
-		tmp = devs.devices[i];
-
-		/*
-		 * If reset was successful, affected devices no longer need
-		 * a reset and we should return all the collateral devices
-		 * to low power.  If not successful, we either didn't reset
-		 * the bus or timed out waiting for it, so let's not touch
-		 * the power state.
-		 */
-		if (!ret) {
-			tmp->needs_reset = false;
-
-			if (tmp != vdev && !disable_idle_d3)
-				vfio_pci_set_power_state(tmp, PCI_D3hot);
-		}
-
-		vfio_device_put(&tmp->vdev);
-	}
-
-	kfree(devs.devices);
 }
 
 static void __exit vfio_pci_cleanup(void)