[Intel-gfx] [PATCH v2] vfio: fix deadlock between group lock and kvm lock

Liu, Yi L yi.l.liu at intel.com
Thu Feb 2 06:44:29 UTC 2023



> -----Original Message-----
> From: Alex Williamson <alex.williamson at redhat.com>
> Sent: Thursday, February 2, 2023 12:15 PM
> To: Liu, Yi L <yi.l.liu at intel.com>
> Cc: Matthew Rosato <mjrosato at linux.ibm.com>; pbonzini at redhat.com;
> jgg at nvidia.com; cohuck at redhat.com; farman at linux.ibm.com;
> pmorel at linux.ibm.com; borntraeger at linux.ibm.com;
> frankja at linux.ibm.com; imbrenda at linux.ibm.com; david at redhat.com;
> akrowiak at linux.ibm.com; jjherne at linux.ibm.com; pasic at linux.ibm.com;
> zhenyuw at linux.intel.com; Wang, Zhi A <zhi.a.wang at intel.com>;
> Christopherson,, Sean <seanjc at google.com>; Tian, Kevin
> <kevin.tian at intel.com>; linux-s390 at vger.kernel.org; kvm at vger.kernel.org;
> intel-gvt-dev at lists.freedesktop.org; intel-gfx at lists.freedesktop.org; linux-
> kernel at vger.kernel.org
> Subject: Re: [PATCH v2] vfio: fix deadlock between group lock and kvm lock
> 
> On Thu, 2 Feb 2023 03:46:59 +0000
> "Liu, Yi L" <yi.l.liu at intel.com> wrote:
> 
> > > From: Alex Williamson <alex.williamson at redhat.com>
> > > Sent: Thursday, February 2, 2023 7:28 AM
> > >
> > > On Wed,  1 Feb 2023 14:20:10 -0500
> > > Matthew Rosato <mjrosato at linux.ibm.com> wrote:
> > >
> > > > After 51cdc8bc120e, we have another deadlock scenario between the
> > > > kvm->lock and the vfio group_lock with two different codepaths
> acquiring
> > > > the locks in different order.  Specifically in vfio_open_device, vfio
> > > > holds the vfio group_lock when issuing device->ops->open_device but
> > > some
> > > > drivers (like vfio-ap) need to acquire kvm->lock during their
> open_device
> > > > routine;  Meanwhile, kvm_vfio_release will acquire the kvm->lock first
> > > > before calling vfio_file_set_kvm which will acquire the vfio group_lock.
> > > >
> > > > To resolve this, let's remove the need for the vfio group_lock from the
> > > > kvm_vfio_release codepath.  This is done by introducing a new
> spinlock to
> > > > protect modifications to the vfio group kvm pointer, and acquiring a
> kvm
> > > > ref from within vfio while holding this spinlock, with the reference held
> > > > until the last close for the device in question.
> > > >
> > > > Fixes: 51cdc8bc120e ("kvm/vfio: Fix potential deadlock on vfio
> group_lock")
> > > > Reported-by: Anthony Krowiak <akrowiak at linux.ibm.com>
> > > > Suggested-by: Jason Gunthorpe <jgg at nvidia.com>
> > > > Signed-off-by: Matthew Rosato <mjrosato at linux.ibm.com>
> > > > ---
> > > > Changes from v1:
> > > > * use spin_lock instead of spin_lock_irqsave (Jason)
> > > > * clear device->kvm_put as part of vfio_kvm_put_kvm (Yi)
> > > > * Re-arrange code to avoid referencing the group contents from
> within
> > > >   vfio_main (Kevin) which meant moving most of the code in this patch
> > > >   to group.c along with getting/dropping of the dev_set lock
> > > > ---
> > > >  drivers/vfio/group.c     | 90
> > > +++++++++++++++++++++++++++++++++++++---
> > > >  drivers/vfio/vfio.h      |  1 +
> > > >  drivers/vfio/vfio_main.c | 11 ++---
> > > >  include/linux/vfio.h     |  2 +-
> > > >  4 files changed, 91 insertions(+), 13 deletions(-)
> > > >
> > > > diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c
> > > > index bb24b2f0271e..52f434861294 100644
> > > > --- a/drivers/vfio/group.c
> > > > +++ b/drivers/vfio/group.c
> > > > @@ -13,6 +13,9 @@
> > > >  #include <linux/vfio.h>
> > > >  #include <linux/iommufd.h>
> > > >  #include <linux/anon_inodes.h>
> > > > +#ifdef CONFIG_HAVE_KVM
> > > > +#include <linux/kvm_host.h>
> > > > +#endif
> > > >  #include "vfio.h"
> > > >
> > > >  static struct vfio {
> > > > @@ -154,6 +157,55 @@ static int
> vfio_group_ioctl_set_container(struct
> > > vfio_group *group,
> > > >  	return ret;
> > > >  }
> > > >
> > > > +#ifdef CONFIG_HAVE_KVM
> > > > +static bool vfio_kvm_get_kvm_safe(struct vfio_device *device,
> struct
> > > kvm *kvm)
> > >
> > > I'm tempted to name these vfio_device_get_kvm_safe() and only pass
> the
> > > vfio_device, where of course we can get the kvm pointer from the
> group
> > > internally.
> > >
> > > > +{
> > > > +	void (*pfn)(struct kvm *kvm);
> > > > +	bool (*fn)(struct kvm *kvm);
> > > > +	bool ret;
> > > > +
> > >
> > > We should assert_lockdep_held(&device->dev_set->lock) in both of
> these
> > > since that seems to be what's protecting device->kvm and
> > > device->put_kvm.
> > >
> > > If we change as above to get the kvm pointer from the group within this
> > > function, we can also move the kvm_ref_lock here, which seems to
> > > simplify the caller quite a bit.
> > >
> > > > +	pfn = symbol_get(kvm_put_kvm);
> > > > +	if (WARN_ON(!pfn))
> > > > +		return false;
> > > > +
> > > > +	fn = symbol_get(kvm_get_kvm_safe);
> > > > +	if (WARN_ON(!fn)) {
> > > > +		symbol_put(kvm_put_kvm);
> > > > +		return false;
> > > > +	}
> > > > +
> > > > +	ret = fn(kvm);
> > > > +	if (ret)
> > > > +		device->put_kvm = pfn;
> > > > +	else
> > > > +		symbol_put(kvm_put_kvm);
> > > > +
> > > > +	symbol_put(kvm_get_kvm_safe);
> > > > +
> > > > +	return ret;
> > > > +}
> > > > +
> > > > +static void vfio_kvm_put_kvm(struct vfio_device *device)
> > > > +{
> > > > +	if (WARN_ON(!device->kvm || !device->put_kvm))
> > > > +		return;
> > >
> > > It simplifies the caller if we can use this even in the !device->kvm
> > > case.
> > >
> > > > +
> > > > +	device->put_kvm(device->kvm);
> > > > +	device->put_kvm = NULL;
> > > > +	symbol_put(kvm_put_kvm);
> > > > +}
> > > > +
> > > > +#else
> > > > +static bool vfio_kvm_get_kvm_safe(struct vfio_device *device,
> struct
> > > kvm *kvm)
> > > > +{
> > > > +	return false;
> > > > +}
> > > > +
> > > > +static void vfio_kvm_put_kvm(struct vfio_device *device)
> > > > +{
> > > > +}
> > > > +#endif
> > > > +
> > > >  static int vfio_device_group_open(struct vfio_device *device)
> > > >  {
> > > >  	int ret;
> > > > @@ -164,14 +216,32 @@ static int vfio_device_group_open(struct
> > > vfio_device *device)
> > > >  		goto out_unlock;
> > > >  	}
> > > >
> > > > +	mutex_lock(&device->dev_set->lock);
> > > > +
> > > >  	/*
> > > > -	 * Here we pass the KVM pointer with the group under the lock.  If
> > > the
> > > > -	 * device driver will use it, it must obtain a reference and release it
> > > > -	 * during close_device.
> > > > +	 * Before the first device open, get the KVM pointer currently
> > > > +	 * associated with the group (if there is one) and obtain a reference
> > > > +	 * now that will be held until the open_count reaches 0 again.  Save
> > > > +	 * the pointer in the device for use by drivers.
> > > >  	 */
> > > > +	if (device->open_count == 0) {
> > > > +		spin_lock(&device->group->kvm_ref_lock);
> > > > +		if (device->group->kvm &&
> > > > +		    vfio_kvm_get_kvm_safe(device, device->group->kvm))
> > > > +			device->kvm = device->group->kvm;
> > > > +		spin_unlock(&device->group->kvm_ref_lock);
> > > > +	}
> > > > +
> > > >  	ret = vfio_device_open(device, device->group->iommufd,
> > > >  			       device->group->kvm);
> > >
> > > We're using device->group->kvm outside of kvm_ref_lock here, it
> should
> > > be using device->kvm.
> >
> > Existing code set device->kvm in the vfio_device_first_open() which is
> > called by vfio_device_open(). After above change, seems not necessary
> > to pass kvm pointer into the call chain. Isn't it?
> 
> Yes, we can get it from the device.  I didn't check how much this
> bloats the patch though.  As a fix, it might make sense to save that
> refactoring for a follow-on patch.  Thanks,

65 lines diff file. 😊 follow-on path works well.

diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c
index bb24b2f0271e..9e04e55c838f 100644
--- a/drivers/vfio/group.c
+++ b/drivers/vfio/group.c
@@ -169,8 +169,7 @@ static int vfio_device_group_open(struct vfio_device *device)
 	 * device driver will use it, it must obtain a reference and release it
 	 * during close_device.
 	 */
-	ret = vfio_device_open(device, device->group->iommufd,
-			       device->group->kvm);
+	ret = vfio_device_open(device, device->group->iommufd);
 
 out_unlock:
 	mutex_unlock(&device->group->group_lock);
diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
index f8219a438bfb..4ece6cb4cf2e 100644
--- a/drivers/vfio/vfio.h
+++ b/drivers/vfio/vfio.h
@@ -19,7 +19,7 @@ struct vfio_container;
 void vfio_device_put_registration(struct vfio_device *device);
 bool vfio_device_try_get_registration(struct vfio_device *device);
 int vfio_device_open(struct vfio_device *device,
-		     struct iommufd_ctx *iommufd, struct kvm *kvm);
+		     struct iommufd_ctx *iommufd);
 void vfio_device_close(struct vfio_device *device,
 		       struct iommufd_ctx *iommufd);
 
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 5177bb061b17..45a7d6d38e2e 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -345,7 +345,7 @@ static bool vfio_assert_device_open(struct vfio_device *device)
 }
 
 static int vfio_device_first_open(struct vfio_device *device,
-				  struct iommufd_ctx *iommufd, struct kvm *kvm)
+				  struct iommufd_ctx *iommufd)
 {
 	int ret;
 
@@ -361,7 +361,6 @@ static int vfio_device_first_open(struct vfio_device *device,
 	if (ret)
 		goto err_module_put;
 
-	device->kvm = kvm;
 	if (device->ops->open_device) {
 		ret = device->ops->open_device(device);
 		if (ret)
@@ -396,14 +395,14 @@ static void vfio_device_last_close(struct vfio_device *device,
 }
 
 int vfio_device_open(struct vfio_device *device,
-		     struct iommufd_ctx *iommufd, struct kvm *kvm)
+		     struct iommufd_ctx *iommufd)
 {
 	int ret = 0;
 
 	mutex_lock(&device->dev_set->lock);
 	device->open_count++;
 	if (device->open_count == 1) {
-		ret = vfio_device_first_open(device, iommufd, kvm);
+		ret = vfio_device_first_open(device, iommufd);
 		if (ret)
 			device->open_count--;
 	}


More information about the Intel-gfx mailing list