| Message ID | 20230227111135.61728-8-yi.l.liu@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Add vfio_device cdev for iommufd support | expand |
On Mon, Feb 27, 2023 at 03:11:23AM -0800, Yi Liu wrote: > Allow the vfio_device file to be in a state where the device FD is > opened but the device cannot be used by userspace (i.e. its .open_device() > hasn't been called). This inbetween state is not used when the device > FD is spawned from the group FD, however when we create the device FD > directly by opening a cdev it will be opened in the blocked state. > > The reason for the inbetween state is that userspace only gets a FD but > doesn't gain access permission until binding the FD to an iommufd. So in > the blocked state, only the bind operation is allowed. Completing bind > will allow user to further access the device. > > This is implemented by adding a flag in struct vfio_device_file to mark > the blocked state and using a simple smp_load_acquire() to obtain the > flag value and serialize all the device setup with the thread accessing > this device. > > Following this lockless scheme, it can safely handle the device FD > unbound->bound but it cannot handle bound->unbound. To allow this we'd > need to add a lock on all the vfio ioctls which seems costly. So once > device FD is bound, it remains bound until the FD is closed. > > Suggested-by: Jason Gunthorpe <jgg@nvidia.com> > Signed-off-by: Yi Liu <yi.l.liu@intel.com> > Reviewed-by: Kevin Tian <kevin.tian@intel.com> > --- > drivers/vfio/group.c | 6 ++++++ > drivers/vfio/vfio.h | 1 + > drivers/vfio/vfio_main.c | 16 ++++++++++++++++ > 3 files changed, 23 insertions(+) Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> Jason
> From: Liu, Yi L <yi.l.liu@intel.com> > Sent: Monday, February 27, 2023 7:11 PM > > Allow the vfio_device file to be in a state where the device FD is > opened but the device cannot be used by userspace (i.e. its .open_device() > hasn't been called). This inbetween state is not used when the device > FD is spawned from the group FD, however when we create the device FD > directly by opening a cdev it will be opened in the blocked state. > > The reason for the inbetween state is that userspace only gets a FD but > doesn't gain access permission until binding the FD to an iommufd. So in > the blocked state, only the bind operation is allowed. Completing bind > will allow user to further access the device. > > This is implemented by adding a flag in struct vfio_device_file to mark > the blocked state and using a simple smp_load_acquire() to obtain the > flag value and serialize all the device setup with the thread accessing > this device. > > Following this lockless scheme, it can safely handle the device FD > unbound->bound but it cannot handle bound->unbound. To allow this we'd > need to add a lock on all the vfio ioctls which seems costly. So once > device FD is bound, it remains bound until the FD is closed. > > Suggested-by: Jason Gunthorpe <jgg@nvidia.com> > Signed-off-by: Yi Liu <yi.l.liu@intel.com> > Reviewed-by: Kevin Tian <kevin.tian@intel.com> > --- > drivers/vfio/group.c | 6 ++++++ > drivers/vfio/vfio.h | 1 + > drivers/vfio/vfio_main.c | 16 ++++++++++++++++ > 3 files changed, 23 insertions(+) > > diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c > index 960b1bcb606b..d8771d585cb1 100644 > --- a/drivers/vfio/group.c > +++ b/drivers/vfio/group.c > @@ -197,6 +197,12 @@ static int vfio_device_group_open(struct > vfio_device_file *df) > if (device->open_count == 0) > vfio_device_put_kvm(device); > > + /* > + * Paired with smp_load_acquire() in vfio_device_fops::ioctl/ > + * read/write/mmap > + */ > + smp_store_release(&df->access_granted, true); > + A bug. If ret is false, it should not set df->access_granted. Would be fixed in the next version. Regards, Yi Liu > mutex_unlock(&device->dev_set->lock); > > out_unlock: > diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h > index 7c1ea870d8f3..2e3cb284711d 100644 > --- a/drivers/vfio/vfio.h > +++ b/drivers/vfio/vfio.h > @@ -18,6 +18,7 @@ struct vfio_container; > > struct vfio_device_file { > struct vfio_device *device; > + bool access_granted; > spinlock_t kvm_ref_lock; /* protect kvm field */ > struct kvm *kvm; > struct iommufd_ctx *iommufd; /* protected by struct > vfio_device_set::lock */ > diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c > index 609700748082..d16ac573e290 100644 > --- a/drivers/vfio/vfio_main.c > +++ b/drivers/vfio/vfio_main.c > @@ -1106,6 +1106,10 @@ static long vfio_device_fops_unl_ioctl(struct file > *filep, > struct vfio_device *device = df->device; > int ret; > > + /* Paired with smp_store_release() in vfio_device_group_open() > */ > + if (!smp_load_acquire(&df->access_granted)) > + return -EINVAL; > + > ret = vfio_device_pm_runtime_get(device); > if (ret) > return ret; > @@ -1133,6 +1137,10 @@ static ssize_t vfio_device_fops_read(struct file > *filep, char __user *buf, > struct vfio_device_file *df = filep->private_data; > struct vfio_device *device = df->device; > > + /* Paired with smp_store_release() in vfio_device_group_open() > */ > + if (!smp_load_acquire(&df->access_granted)) > + return -EINVAL; > + > if (unlikely(!device->ops->read)) > return -EINVAL; > > @@ -1146,6 +1154,10 @@ static ssize_t vfio_device_fops_write(struct file > *filep, > struct vfio_device_file *df = filep->private_data; > struct vfio_device *device = df->device; > > + /* Paired with smp_store_release() in vfio_device_group_open() > */ > + if (!smp_load_acquire(&df->access_granted)) > + return -EINVAL; > + > if (unlikely(!device->ops->write)) > return -EINVAL; > > @@ -1157,6 +1169,10 @@ static int vfio_device_fops_mmap(struct file > *filep, struct vm_area_struct *vma) > struct vfio_device_file *df = filep->private_data; > struct vfio_device *device = df->device; > > + /* Paired with smp_store_release() in vfio_device_group_open() > */ > + if (!smp_load_acquire(&df->access_granted)) > + return -EINVAL; > + > if (unlikely(!device->ops->mmap)) > return -EINVAL; > > -- > 2.34.1
diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c index 960b1bcb606b..d8771d585cb1 100644 --- a/drivers/vfio/group.c +++ b/drivers/vfio/group.c @@ -197,6 +197,12 @@ static int vfio_device_group_open(struct vfio_device_file *df) if (device->open_count == 0) vfio_device_put_kvm(device); + /* + * Paired with smp_load_acquire() in vfio_device_fops::ioctl/ + * read/write/mmap + */ + smp_store_release(&df->access_granted, true); + mutex_unlock(&device->dev_set->lock); out_unlock: diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h index 7c1ea870d8f3..2e3cb284711d 100644 --- a/drivers/vfio/vfio.h +++ b/drivers/vfio/vfio.h @@ -18,6 +18,7 @@ struct vfio_container; struct vfio_device_file { struct vfio_device *device; + bool access_granted; spinlock_t kvm_ref_lock; /* protect kvm field */ struct kvm *kvm; struct iommufd_ctx *iommufd; /* protected by struct vfio_device_set::lock */ diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index 609700748082..d16ac573e290 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -1106,6 +1106,10 @@ static long vfio_device_fops_unl_ioctl(struct file *filep, struct vfio_device *device = df->device; int ret; + /* Paired with smp_store_release() in vfio_device_group_open() */ + if (!smp_load_acquire(&df->access_granted)) + return -EINVAL; + ret = vfio_device_pm_runtime_get(device); if (ret) return ret; @@ -1133,6 +1137,10 @@ static ssize_t vfio_device_fops_read(struct file *filep, char __user *buf, struct vfio_device_file *df = filep->private_data; struct vfio_device *device = df->device; + /* Paired with smp_store_release() in vfio_device_group_open() */ + if (!smp_load_acquire(&df->access_granted)) + return -EINVAL; + if (unlikely(!device->ops->read)) return -EINVAL; @@ -1146,6 +1154,10 @@ static ssize_t vfio_device_fops_write(struct file *filep, struct vfio_device_file *df = filep->private_data; struct vfio_device *device = df->device; + /* Paired with smp_store_release() in vfio_device_group_open() */ + if (!smp_load_acquire(&df->access_granted)) + return -EINVAL; + if (unlikely(!device->ops->write)) return -EINVAL; @@ -1157,6 +1169,10 @@ static int vfio_device_fops_mmap(struct file *filep, struct vm_area_struct *vma) struct vfio_device_file *df = filep->private_data; struct vfio_device *device = df->device; + /* Paired with smp_store_release() in vfio_device_group_open() */ + if (!smp_load_acquire(&df->access_granted)) + return -EINVAL; + if (unlikely(!device->ops->mmap)) return -EINVAL;