xen/pciback: Don't deadlock when unbinding.

As commit 0a9fd01529
'xen/pciback: Document the entry points for 'pcistub_put_pci_dev''
explained there are four entry points in this function.
Two of them are when the user fiddles in the SysFS to
unbind a device which might be in use by a guest or not.

Both 'unbind' states will cause a deadlock as the the PCI lock has
already been taken, which then pci_device_reset tries to take.

We can simplify this by requiring that all callers of
pcistub_put_pci_dev MUST hold the device lock. And then
we can just call the lockless version of pci_device_reset.

To make it even simpler we will modify xen_pcibk_release_pci_dev
to quality whether it should take a lock or not - as it ends
up calling xen_pcibk_release_pci_dev and needs to hold the lock.

Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
This commit is contained in:
Konrad Rzeszutek Wilk 2014-12-03 16:40:26 -05:00 committed by David Vrabel
parent 2c3fc8d26d
commit e8801a7418
5 changed files with 33 additions and 16 deletions

View file

@ -69,7 +69,7 @@ static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev,
}
static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
struct pci_dev *dev)
struct pci_dev *dev, bool lock)
{
struct passthrough_dev_data *dev_data = pdev->pci_dev_data;
struct pci_dev_entry *dev_entry, *t;
@ -87,8 +87,13 @@ static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
mutex_unlock(&dev_data->lock);
if (found_dev)
if (found_dev) {
if (lock)
device_lock(&found_dev->dev);
pcistub_put_pci_dev(found_dev);
if (lock)
device_unlock(&found_dev->dev);
}
}
static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
@ -156,8 +161,11 @@ static void __xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
struct pci_dev_entry *dev_entry, *t;
list_for_each_entry_safe(dev_entry, t, &dev_data->dev_list, list) {
struct pci_dev *dev = dev_entry->dev;
list_del(&dev_entry->list);
pcistub_put_pci_dev(dev_entry->dev);
device_lock(&dev->dev);
pcistub_put_pci_dev(dev);
device_unlock(&dev->dev);
kfree(dev_entry);
}

View file

@ -250,6 +250,8 @@ struct pci_dev *pcistub_get_pci_dev(struct xen_pcibk_device *pdev,
* - 'echo BDF > unbind' with a guest still using it. See pcistub_remove
*
* As such we have to be careful.
*
* To make this easier, the caller has to hold the device lock.
*/
void pcistub_put_pci_dev(struct pci_dev *dev)
{
@ -276,11 +278,8 @@ void pcistub_put_pci_dev(struct pci_dev *dev)
/* Cleanup our device
* (so it's ready for the next domain)
*/
/* This is OK - we are running from workqueue context
* and want to inhibit the user from fiddling with 'reset'
*/
pci_reset_function(dev);
lockdep_assert_held(&dev->dev.mutex);
__pci_reset_function_locked(dev);
pci_restore_state(dev);
/* This disables the device. */
@ -567,7 +566,8 @@ static void pcistub_remove(struct pci_dev *dev)
/* N.B. This ends up calling pcistub_put_pci_dev which ends up
* doing the FLR. */
xen_pcibk_release_pci_dev(found_psdev->pdev,
found_psdev->dev);
found_psdev->dev,
false /* caller holds the lock. */);
}
spin_lock_irqsave(&pcistub_devices_lock, flags);

View file

@ -99,7 +99,8 @@ struct xen_pcibk_backend {
unsigned int *domain, unsigned int *bus,
unsigned int *devfn);
int (*publish)(struct xen_pcibk_device *pdev, publish_pci_root_cb cb);
void (*release)(struct xen_pcibk_device *pdev, struct pci_dev *dev);
void (*release)(struct xen_pcibk_device *pdev, struct pci_dev *dev,
bool lock);
int (*add)(struct xen_pcibk_device *pdev, struct pci_dev *dev,
int devid, publish_pci_dev_cb publish_cb);
struct pci_dev *(*get)(struct xen_pcibk_device *pdev,
@ -122,10 +123,10 @@ static inline int xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev,
}
static inline void xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
struct pci_dev *dev)
struct pci_dev *dev, bool lock)
{
if (xen_pcibk_backend && xen_pcibk_backend->release)
return xen_pcibk_backend->release(pdev, dev);
return xen_pcibk_backend->release(pdev, dev, lock);
}
static inline struct pci_dev *

View file

@ -145,7 +145,7 @@ static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev,
}
static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
struct pci_dev *dev)
struct pci_dev *dev, bool lock)
{
int slot;
struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
@ -169,8 +169,13 @@ static void __xen_pcibk_release_pci_dev(struct xen_pcibk_device *pdev,
out:
mutex_unlock(&vpci_dev->lock);
if (found_dev)
if (found_dev) {
if (lock)
device_lock(&found_dev->dev);
pcistub_put_pci_dev(found_dev);
if (lock)
device_unlock(&found_dev->dev);
}
}
static int __xen_pcibk_init_devices(struct xen_pcibk_device *pdev)
@ -208,8 +213,11 @@ static void __xen_pcibk_release_devices(struct xen_pcibk_device *pdev)
struct pci_dev_entry *e, *tmp;
list_for_each_entry_safe(e, tmp, &vpci_dev->dev_list[slot],
list) {
struct pci_dev *dev = e->dev;
list_del(&e->list);
pcistub_put_pci_dev(e->dev);
device_lock(&dev->dev);
pcistub_put_pci_dev(dev);
device_unlock(&dev->dev);
kfree(e);
}
}

View file

@ -291,7 +291,7 @@ static int xen_pcibk_remove_device(struct xen_pcibk_device *pdev,
/* N.B. This ends up calling pcistub_put_pci_dev which ends up
* doing the FLR. */
xen_pcibk_release_pci_dev(pdev, dev);
xen_pcibk_release_pci_dev(pdev, dev, true /* use the lock. */);
out:
return err;