> From: Matthew Rosato <mjros...@linux.ibm.com>
> Sent: Wednesday, February 1, 2023 4:07 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 <akrow...@linux.ibm.com>
> Suggested-by: Jason Gunthorpe <j...@nvidia.com>
> Signed-off-by: Matthew Rosato <mjros...@linux.ibm.com>
> ---
> drivers/vfio/group.c | 14 +++----
> drivers/vfio/vfio.h | 5 ++-
> drivers/vfio/vfio_main.c | 88
> ++++++++++++++++++++++++++++++++++++----
> include/linux/vfio.h | 2 +-
> 4 files changed, 88 insertions(+), 21 deletions(-)
>
> diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c
> index bb24b2f0271e..8f67d33e0e8d 100644
> --- a/drivers/vfio/group.c
> +++ b/drivers/vfio/group.c
> @@ -164,13 +164,7 @@ static int vfio_device_group_open(struct
> vfio_device *device)
> goto out_unlock;
> }
>
> - /*
> - * 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.
> - */
> - ret = vfio_device_open(device, device->group->iommufd,
> - device->group->kvm);
> + ret = vfio_device_open(device, device->group);
>
> out_unlock:
> mutex_unlock(&device->group->group_lock);
> @@ -450,6 +444,7 @@ 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;
> @@ -799,13 +794,14 @@
> EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent);
> void vfio_file_set_kvm(struct file *file, struct kvm *kvm)
> {
> struct vfio_group *group = file->private_data;
> + unsigned long flags;
>
> if (!vfio_file_is_group(file))
> return;
>
> - mutex_lock(&group->group_lock);
> + spin_lock_irqsave(&group->kvm_ref_lock, flags);
> group->kvm = kvm;
> - mutex_unlock(&group->group_lock);
> + spin_unlock_irqrestore(&group->kvm_ref_lock, flags);
> }
> EXPORT_SYMBOL_GPL(vfio_file_set_kvm);
>
> diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
> index f8219a438bfb..d153ad35de24 100644
> --- a/drivers/vfio/vfio.h
> +++ b/drivers/vfio/vfio.h
> @@ -15,11 +15,11 @@ struct iommufd_ctx;
> struct iommu_group;
> struct vfio_device;
> struct vfio_container;
> +struct vfio_group;
>
> 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);
> +int vfio_device_open(struct vfio_device *device, struct vfio_group
> *group);
> void vfio_device_close(struct vfio_device *device,
> struct iommufd_ctx *iommufd);
>
> @@ -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,
> diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
> index 5177bb061b17..b0defb0d0d87 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>
> @@ -344,9 +347,59 @@ static bool vfio_assert_device_open(struct
> vfio_device *device)
> return !WARN_ON_ONCE(!READ_ONCE(device->open_count));
> }
>
> +#ifdef CONFIG_HAVE_KVM
> +static bool vfio_kvm_get_kvm_safe(struct vfio_device *device, struct kvm
> *kvm)
> +{
> + void (*pfn)(struct kvm *kvm);
> + bool (*fn)(struct kvm *kvm);
> + bool ret;
> +
> + 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;
> +
> + device->put_kvm(device->kvm);
> + 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_first_open(struct vfio_device *device,
> - struct iommufd_ctx *iommufd, struct kvm
> *kvm)
> + struct vfio_group *group)
> {
> + struct iommufd_ctx *iommufd = group->iommufd;
> + unsigned long flags;
> int ret;
>
> lockdep_assert_held(&device->dev_set->lock);
> @@ -361,16 +414,30 @@ static int vfio_device_first_open(struct
> vfio_device *device,
> if (ret)
> goto err_module_put;
>
> - device->kvm = kvm;
> + /*
> + * 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. Save the pointer in the device for use by
> + * drivers.
> + */
> + spin_lock_irqsave(&group->kvm_ref_lock, flags);
> + if (group->kvm && vfio_kvm_get_kvm_safe(device, group->kvm))
> + device->kvm = group->kvm;
> + spin_unlock_irqrestore(&group->kvm_ref_lock, flags);
> +
> if (device->ops->open_device) {
> ret = device->ops->open_device(device);
> if (ret)
> - goto err_unuse_iommu;
> + goto err_put_kvm;
> }
> return 0;
>
> -err_unuse_iommu:
> - device->kvm = NULL;
> +err_put_kvm:
> + if (device->kvm) {
> + vfio_kvm_put_kvm(device);
> + device->put_kvm = NULL;
Can "device->put_kvm = NULL;" be part of vfio_kvm_put_kvm()?
Regards,
Yi Liu
