Keep track of all the vfio_devices that have been added to the device set
and use this list in vfio_pci_try_bus_reset() instead of trying to work
backwards from the pci_device.
The dev_set->lock directly prevents devices from joining/leaving the set,
which further implies the pci_device cannot change drivers or that the
vfio_device be freed, eliminating the need for get/put's.
Completeness of the device set can be directly measured by checking if
every PCI device in the reset group is also in the device set - which
proves that VFIO drivers are attached to everything.
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@xxxxxxxxxx>
---
drivers/vfio/pci/vfio_pci.c | 110 ++++++++++++++----------------------
drivers/vfio/vfio.c | 10 ++++
include/linux/vfio.h | 2 +
3 files changed, 53 insertions(+), 69 deletions(-)
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 22774e447b5f4a..fbc20f6d2dd412 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -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);
@@ -2139,34 +2142,17 @@ 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)
+static int vfio_pci_check_all_devices_bound(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;
+ struct vfio_device_set *dev_set = data;
+ struct vfio_device *cur;
- 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;
- }
+ lockdep_assert_held(&dev_set->lock);
- devs->devices[devs->cur_index++] = vdev;
- return 0;
+ list_for_each_entry(cur, &dev_set->device_list, dev_set_list)
+ if (cur->dev == &pdev->dev)
+ return 0;
+ return -EBUSY;
}
static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data)
@@ -2210,8 +2196,7 @@ static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data)
* needs_reset (such as by lack of FLR support)
* Then attempt to perform that bus or slot reset. Callers are required
* to hold vdev->dev_set->lock, protecting the bus/slot reset group from
- * concurrent opens. A vfio_device reference is acquired for each device
- * to prevent unbinds during the reset operation.
+ * concurrent opens.
*
* 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
@@ -2220,61 +2205,48 @@ static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data)
*/
static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev)
{
- struct vfio_devices devs = { .cur_index = 0 };
- int i = 0, ret = -EINVAL;
- bool slot = false;
- struct vfio_pci_device *tmp;
-
- if (!pci_probe_reset_slot(vdev->pdev->slot))
- slot = true;
- else if (pci_probe_reset_bus(vdev->pdev->bus))
- return;
+ struct vfio_device_set *dev_set = vdev->vdev.dev_set;
+ struct vfio_pci_device *to_reset = NULL;
+ struct vfio_pci_device *cur;
+ int ret;
- if (vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_count_devs,
- &i, slot) || !i)
+ if (pci_probe_reset_slot(vdev->pdev->slot) &&
+ pci_probe_reset_bus(vdev->pdev->bus))
return;
- devs.max_index = i;
- devs.devices = kcalloc(i, sizeof(struct vfio_device *), GFP_KERNEL);
- if (!devs.devices)
- return;
+ lockdep_assert_held(&vdev->vdev.dev_set->lock);
- if (vfio_pci_for_each_slot_or_bus(vdev->pdev,
- vfio_pci_get_unused_devs,
- &devs, slot))
- goto put_devs;
+ /* All VFIO devices have a closed FD */
+ list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list)
+ if (cur->vdev.open_count)
+ return;
+
+ /* All devices in the group to be reset need VFIO devices */
+ if (vfio_pci_for_each_slot_or_bus(
+ vdev->pdev, vfio_pci_check_all_devices_bound, dev_set,
+ !pci_probe_reset_slot(vdev->pdev->slot)))
+ return;
/* 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);
+ list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) {
+ if (cur->needs_reset) {
+ to_reset = cur;
break;
}
}
+ if (!to_reset)
+ return;
-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;
+ ret = pci_reset_bus(to_reset->pdev);
+ if (ret)
+ return;
- if (tmp != vdev && !disable_idle_d3)
- vfio_pci_set_power_state(tmp, PCI_D3hot);
- }
+ list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) {
+ cur->needs_reset = false;
- vfio_device_put(&tmp->vdev);
+ if (cur != to_reset && !disable_idle_d3)
+ vfio_pci_set_power_state(cur, PCI_D3hot);
}
-
- kfree(devs.devices);
}
static void __exit vfio_pci_cleanup(void)
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 8572d943320214..7e352d68b1b01d 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -129,7 +129,12 @@ int vfio_assign_device_set(struct vfio_device *device, void *set_id)
if (dev_set) {
dev_set->device_count++;
xa_unlock(&vfio_device_set_xa);
+
+ mutex_lock(&dev_set->lock);
device->dev_set = dev_set;
+ list_add_tail(&device->dev_set_list, &dev_set->device_list);
+ mutex_unlock(&dev_set->lock);
+
if (dev_set != alloc_dev_set)
kfree(alloc_dev_set);
return 0;
@@ -143,6 +148,7 @@ int vfio_assign_device_set(struct vfio_device *device, void *set_id)
if (!alloc_dev_set)
return -ENOMEM;
mutex_init(&alloc_dev_set->lock);
+ INIT_LIST_HEAD(&alloc_dev_set->device_list);
alloc_dev_set->set_id = set_id;
goto again;
}
@@ -155,6 +161,10 @@ static void vfio_release_device_set(struct vfio_device *device)
if (!dev_set)
return;
+ mutex_lock(&dev_set->lock);
+ list_del(&device->dev_set_list);
+ mutex_unlock(&dev_set->lock);
+
xa_lock(&vfio_device_set_xa);
dev_set->device_count--;
if (!dev_set->device_count) {
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 128b4db00adc57..f0e6a72875e471 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -23,6 +23,7 @@
struct vfio_device_set {
void *set_id;
struct mutex lock;
+ struct list_head device_list;
unsigned int device_count;
};
@@ -31,6 +32,7 @@ struct vfio_device {
const struct vfio_device_ops *ops;
struct vfio_group *group;
struct vfio_device_set *dev_set;
+ struct list_head dev_set_list;
/* Members below here are private, not for driver use */
refcount_t refcount;
--
2.32.0
