RE: [PATCH v3] vfio: fix deadlock between group lock and kvm lock

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

 



Hi Matthew,

> From: Matthew Rosato <mjrosato@xxxxxxxxxxxxx>
> Sent: Friday, February 3, 2023 12:25 AM
> 
> 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@xxxxxxxxxxxxx>
> Suggested-by: Jason Gunthorpe <jgg@xxxxxxxxxx>
> Signed-off-by: Matthew Rosato <mjrosato@xxxxxxxxxxxxx>
> ---
> Changes from v2:
> * Relocate the new functions back to vfio_main and externalize to call
>   from group (Kevin) since cdev will need this too
> * s/vfio_kvm_*_kvm/vfio_device_*_kvm/ and only pass device as input.
>   Handle new kvm_ref_lock directly inside vfio_device_get_kvm (Alex)
> * Add assert_lockdep_held for dev_set lock (Alex)
> * Internalize error paths for vfio_device_get_kvm_safe and now return
>   void - either device->kvm is set with a ref taken or is NULL (Alex)
> * Other flow suggestions to make the call path cleaner - Thanks! (Alex)
> * Can't pass group->kvm to vfio_device_open, as it references the value
>   outside of new lock.  Pass device->kvm to minimize changes in this
>   fix (Alex, Yi)
> 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     | 32 ++++++++++++++----
>  drivers/vfio/vfio.h      | 14 ++++++++
>  drivers/vfio/vfio_main.c | 70
> ++++++++++++++++++++++++++++++++++++----
>  include/linux/vfio.h     |  2 +-
>  4 files changed, 103 insertions(+), 15 deletions(-)
> 
> diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c
> index bb24b2f0271e..7fed4233ca23 100644
> --- a/drivers/vfio/group.c
> +++ b/drivers/vfio/group.c
> @@ -164,13 +164,23 @@ 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.
>  	 */
> -	ret = vfio_device_open(device, device->group->iommufd,
> -			       device->group->kvm);
> +	if (device->open_count == 0)
> +		vfio_device_get_kvm_safe(device);
> +
> +	ret = vfio_device_open(device, device->group->iommufd, device-
> >kvm);
> +
> +	if (device->open_count == 0)
> +		vfio_device_put_kvm(device);
> +
> +	mutex_unlock(&device->dev_set->lock);
> 
>  out_unlock:
>  	mutex_unlock(&device->group->group_lock);
> @@ -180,7 +190,14 @@ static int vfio_device_group_open(struct
> vfio_device *device)
>  void vfio_device_group_close(struct vfio_device *device)
>  {
>  	mutex_lock(&device->group->group_lock);
> +	mutex_lock(&device->dev_set->lock);
> +
>  	vfio_device_close(device, device->group->iommufd);
> +
> +	if (device->open_count == 0)
> +		vfio_device_put_kvm(device);
> +
> +	mutex_unlock(&device->dev_set->lock);
>  	mutex_unlock(&device->group->group_lock);
>  }
> 
> @@ -450,6 +467,7 @@ static struct vfio_group *vfio_group_alloc(struct
> iommu_group *iommu_group,
> 
>  	refcount_set(&group->drivers, 1);
>  	mutex_init(&group->group_lock);
> +	spin_lock_init(&group->kvm_ref_lock);
>  	INIT_LIST_HEAD(&group->device_list);
>  	mutex_init(&group->device_lock);
>  	group->iommu_group = iommu_group;
> @@ -803,9 +821,9 @@ void vfio_file_set_kvm(struct file *file, struct kvm
> *kvm)
>  	if (!vfio_file_is_group(file))
>  		return;
> 
> -	mutex_lock(&group->group_lock);
> +	spin_lock(&group->kvm_ref_lock);
>  	group->kvm = kvm;
> -	mutex_unlock(&group->group_lock);
> +	spin_unlock(&group->kvm_ref_lock);
>  }
>  EXPORT_SYMBOL_GPL(vfio_file_set_kvm);
> 
> diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
> index f8219a438bfb..20d715b0a3a8 100644
> --- a/drivers/vfio/vfio.h
> +++ b/drivers/vfio/vfio.h
> @@ -74,6 +74,7 @@ struct vfio_group {
>  	struct file			*opened_file;
>  	struct blocking_notifier_head	notifier;
>  	struct iommufd_ctx		*iommufd;
> +	spinlock_t			kvm_ref_lock;
>  };
> 
>  int vfio_device_set_group(struct vfio_device *device,
> @@ -251,4 +252,17 @@ extern bool vfio_noiommu __read_mostly;
>  enum { vfio_noiommu = false };
>  #endif
> 
> +#ifdef CONFIG_HAVE_KVM
> +void vfio_device_get_kvm_safe(struct vfio_device *device);
> +void vfio_device_put_kvm(struct vfio_device *device);
> +#else
> +static inline void vfio_device_get_kvm_safe(struct vfio_device *device)
> +{
> +}
> +
> +static inline void vfio_device_put_kvm(struct vfio_device *device)
> +{
> +}
> +#endif
> +
>  #endif
> diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
> index 5177bb061b17..4762550e9f42 100644
> --- a/drivers/vfio/vfio_main.c
> +++ b/drivers/vfio/vfio_main.c
> @@ -16,6 +16,9 @@
>  #include <linux/fs.h>
>  #include <linux/idr.h>
>  #include <linux/iommu.h>
> +#ifdef CONFIG_HAVE_KVM
> +#include <linux/kvm_host.h>
> +#endif
>  #include <linux/list.h>
>  #include <linux/miscdevice.h>
>  #include <linux/module.h>
> @@ -338,6 +341,62 @@ void vfio_unregister_group_dev(struct vfio_device
> *device)
>  }
>  EXPORT_SYMBOL_GPL(vfio_unregister_group_dev);
> 
> +#ifdef CONFIG_HAVE_KVM
> +void vfio_device_get_kvm_safe(struct vfio_device *device)
> +{
> +	void (*pfn)(struct kvm *kvm);
> +	bool (*fn)(struct kvm *kvm);
> +	bool ret;
> +
> +	lockdep_assert_held(&device->dev_set->lock);
> +
> +	spin_lock(&device->group->kvm_ref_lock);
> +	if (!device->group->kvm)
> +		goto unlock;
> +
> +	pfn = symbol_get(kvm_put_kvm);
> +	if (WARN_ON(!pfn))
> +		goto unlock;
> +
> +	fn = symbol_get(kvm_get_kvm_safe);
> +	if (WARN_ON(!fn)) {
> +		symbol_put(kvm_put_kvm);
> +		goto unlock;
> +	}
> +
> +	ret = fn(device->group->kvm);
> +	symbol_put(kvm_get_kvm_safe);
> +	if (!ret) {
> +		symbol_put(kvm_put_kvm);
> +		goto unlock;
> +	}
> +
> +	device->put_kvm = pfn;
> +	device->kvm = device->group->kvm;
> +
> +unlock:
> +	spin_unlock(&device->group->kvm_ref_lock);
> +}
> +
> +void vfio_device_put_kvm(struct vfio_device *device)
> +{
> +	lockdep_assert_held(&device->dev_set->lock);
> +
> +	if (!device->kvm)
> +		return;
> +
> +	if (WARN_ON(!device->put_kvm))
> +		goto clear;
> +
> +	device->put_kvm(device->kvm);
> +	device->put_kvm = NULL;
> +	symbol_put(kvm_put_kvm);
> +
> +clear:
> +	device->kvm = NULL;
> +}
> +#endif
> +
>  /* true if the vfio_device has open_device() called but not close_device()
> */
>  static bool vfio_assert_device_open(struct vfio_device *device)
>  {
> @@ -361,7 +420,6 @@ static int vfio_device_first_open(struct vfio_device
> *device,
>  	if (ret)
>  		goto err_module_put;
> 
> -	device->kvm = kvm;

Since you've deleted the only usage of kvm pointer in this function, I
guess you can remove the kvm parameter from vfio_device_open()
and vfio_device_first_open(). :-) if it makes this patch too big, may
just have another patch to do it.

Regards,
Yi Liu
>  	if (device->ops->open_device) {
>  		ret = device->ops->open_device(device);
>  		if (ret)
> @@ -370,7 +428,6 @@ static int vfio_device_first_open(struct vfio_device
> *device,
>  	return 0;
> 
>  err_unuse_iommu:
> -	device->kvm = NULL;
>  	if (iommufd)
>  		vfio_iommufd_unbind(device);
>  	else
> @@ -387,7 +444,6 @@ static void vfio_device_last_close(struct vfio_device
> *device,
> 
>  	if (device->ops->close_device)
>  		device->ops->close_device(device);
> -	device->kvm = NULL;
>  	if (iommufd)
>  		vfio_iommufd_unbind(device);
>  	else
> @@ -400,14 +456,14 @@ int vfio_device_open(struct vfio_device *device,
>  {
>  	int ret = 0;
> 
> -	mutex_lock(&device->dev_set->lock);
> +	lockdep_assert_held(&device->dev_set->lock);
> +
>  	device->open_count++;
>  	if (device->open_count == 1) {
>  		ret = vfio_device_first_open(device, iommufd, kvm);
>  		if (ret)
>  			device->open_count--;
>  	}
> -	mutex_unlock(&device->dev_set->lock);
> 
>  	return ret;
>  }
> @@ -415,12 +471,12 @@ int vfio_device_open(struct vfio_device *device,
>  void vfio_device_close(struct vfio_device *device,
>  		       struct iommufd_ctx *iommufd)
>  {
> -	mutex_lock(&device->dev_set->lock);
> +	lockdep_assert_held(&device->dev_set->lock);
> +
>  	vfio_assert_device_open(device);
>  	if (device->open_count == 1)
>  		vfio_device_last_close(device, iommufd);
>  	device->open_count--;
> -	mutex_unlock(&device->dev_set->lock);
>  }
> 
>  /*
> diff --git a/include/linux/vfio.h b/include/linux/vfio.h
> index 35be78e9ae57..87ff862ff555 100644
> --- a/include/linux/vfio.h
> +++ b/include/linux/vfio.h
> @@ -46,7 +46,6 @@ struct vfio_device {
>  	struct vfio_device_set *dev_set;
>  	struct list_head dev_set_list;
>  	unsigned int migration_flags;
> -	/* Driver must reference the kvm during open_device or never
> touch it */
>  	struct kvm *kvm;
> 
>  	/* Members below here are private, not for driver use */
> @@ -58,6 +57,7 @@ struct vfio_device {
>  	struct list_head group_next;
>  	struct list_head iommu_entry;
>  	struct iommufd_access *iommufd_access;
> +	void (*put_kvm)(struct kvm *kvm);
>  #if IS_ENABLED(CONFIG_IOMMUFD)
>  	struct iommufd_device *iommufd_device;
>  	struct iommufd_ctx *iommufd_ictx;
> --
> 2.39.1





[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Index of Archives]     [Kernel Development]     [Kernel Newbies]     [IDE]     [Security]     [Git]     [Netfilter]     [Bugtraq]     [Yosemite Info]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux ATA RAID]     [Samba]     [Linux Media]     [Device Mapper]

  Powered by Linux