[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] [PATCH v4 2/5] xen/pciback: Don't deadlock when unbinding.



On Fri, Jul 11, 2014 at 05:02:01PM -0400, Konrad Rzeszutek Wilk wrote:
> > >--- a/drivers/xen/xen-pciback/pci_stub.c
> > >+++ b/drivers/xen/xen-pciback/pci_stub.c
> > >@@ -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.
> > 
> > Should we assert that the lock is being held?
> 
> Yes of course we should. Thank you!

How about this:

From 388a03c598218dac8bfeb6c5bf3992e0d1e37d1e Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
Date: Tue, 8 Jul 2014 11:12:02 -0400
Subject: [PATCH] xen/pciback: Don't deadlock when unbinding.

As commit 0a9fd0152929db372ff61b0d6c280fdd34ae8bdb
'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.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
---
[v2: Per David Vrabel's suggestion - use lockless version of reset]
[v3: Per Boris suggestion add assertion mechanism]
---
 drivers/xen/xen-pciback/passthrough.c |  9 +++++++--
 drivers/xen/xen-pciback/pci_stub.c    | 12 ++++++------
 drivers/xen/xen-pciback/pciback.h     |  7 ++++---
 drivers/xen/xen-pciback/vpci.c        |  9 +++++++--
 drivers/xen/xen-pciback/xenbus.c      |  2 +-
 5 files changed, 25 insertions(+), 14 deletions(-)

diff --git a/drivers/xen/xen-pciback/passthrough.c 
b/drivers/xen/xen-pciback/passthrough.c
index 828dddc..d0c3fb4 100644
--- a/drivers/xen/xen-pciback/passthrough.c
+++ b/drivers/xen/xen-pciback/passthrough.c
@@ -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)
diff --git a/drivers/xen/xen-pciback/pci_stub.c 
b/drivers/xen/xen-pciback/pci_stub.c
index d57a173..8293fbb 100644
--- a/drivers/xen/xen-pciback/pci_stub.c
+++ b/drivers/xen/xen-pciback/pci_stub.c
@@ -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);
diff --git a/drivers/xen/xen-pciback/pciback.h 
b/drivers/xen/xen-pciback/pciback.h
index f72af87..58e38d5 100644
--- a/drivers/xen/xen-pciback/pciback.h
+++ b/drivers/xen/xen-pciback/pciback.h
@@ -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 *
diff --git a/drivers/xen/xen-pciback/vpci.c b/drivers/xen/xen-pciback/vpci.c
index 51afff9..2fdfcb9 100644
--- a/drivers/xen/xen-pciback/vpci.c
+++ b/drivers/xen/xen-pciback/vpci.c
@@ -145,7 +145,7 @@ out:
 }
 
 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)
diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c
index 4a7e6e0..b3318fd 100644
--- a/drivers/xen/xen-pciback/xenbus.c
+++ b/drivers/xen/xen-pciback/xenbus.c
@@ -290,7 +290,7 @@ 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;
-- 
1.9.3


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.