| Message ID | 20230327094047.47215-9-yi.l.liu@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Add vfio_device cdev for iommufd support | expand |
On Mon, 27 Mar 2023 02:40:31 -0700 Yi Liu <yi.l.liu@intel.com> 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> > Reviewed-by: Kevin Tian <kevin.tian@intel.com> > Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> > Tested-by: Terrence Xu <terrence.xu@intel.com> > Tested-by: Nicolin Chen <nicolinc@nvidia.com> > Tested-by: Matthew Rosato <mjrosato@linux.ibm.com> > Signed-off-by: Yi Liu <yi.l.liu@intel.com> > --- > drivers/vfio/group.c | 11 ++++++++++- > drivers/vfio/vfio.h | 1 + > drivers/vfio/vfio_main.c | 41 ++++++++++++++++++++++++++++++++++------ > 3 files changed, 46 insertions(+), 7 deletions(-) > > diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c > index 9a7b2765eef6..4f267ae7bebc 100644 > --- a/drivers/vfio/group.c > +++ b/drivers/vfio/group.c > @@ -194,9 +194,18 @@ static int vfio_device_group_open(struct vfio_device_file *df) > df->iommufd = device->group->iommufd; > > ret = vfio_device_open(df); > - if (ret) > + if (ret) { > df->iommufd = NULL; > + goto out_put_kvm; > + } > + > + /* > + * Paired with smp_load_acquire() in vfio_device_fops::ioctl/ > + * read/write/mmap > + */ > + smp_store_release(&df->access_granted, true); > > +out_put_kvm: > if (device->open_count == 0) > vfio_device_put_kvm(device); > > diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h > index cffc08f5a6f1..854f2c97cb9a 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 2ea6cb6d03c7..b515bbda4c74 100644 > --- a/drivers/vfio/vfio_main.c > +++ b/drivers/vfio/vfio_main.c > @@ -1114,6 +1114,10 @@ static long vfio_device_fops_unl_ioctl(struct file *filep, > struct vfio_device *device = df->device; > int ret; > > + /* Paired with smp_store_release() following vfio_device_open() */ > + if (!smp_load_acquire(&df->access_granted)) > + return -EINVAL; > + > ret = vfio_device_pm_runtime_get(device); > if (ret) > return ret; > @@ -1141,6 +1145,10 @@ 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() following vfio_device_open() */ > + if (!smp_load_acquire(&df->access_granted)) > + return -EINVAL; > + > if (unlikely(!device->ops->read)) > return -EINVAL; > > @@ -1154,6 +1162,10 @@ 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() following vfio_device_open() */ > + if (!smp_load_acquire(&df->access_granted)) > + return -EINVAL; > + > if (unlikely(!device->ops->write)) > return -EINVAL; > > @@ -1165,6 +1177,10 @@ 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() following vfio_device_open() */ > + if (!smp_load_acquire(&df->access_granted)) > + return -EINVAL; > + > if (unlikely(!device->ops->mmap)) > return -EINVAL; > > @@ -1201,6 +1217,24 @@ bool vfio_file_is_valid(struct file *file) > } > EXPORT_SYMBOL_GPL(vfio_file_is_valid); > > +/* > + * Return true if the input file is a vfio device file and has opened > + * the input device. Otherwise, return false. > + */ > +static bool vfio_file_has_device_access(struct file *file, > + struct vfio_device *device) > +{ > + struct vfio_device *vdev = vfio_device_from_file(file); > + struct vfio_device_file *df; > + > + if (!vdev || vdev != device) > + return false; > + > + df = file->private_data; > + > + return READ_ONCE(df->access_granted); Why did we change from smp_load_acquire() to READ_ONCE() here? Thanks, Alex > +} > + > /** > * vfio_file_has_dev - True if the VFIO file is a handle for device > * @file: VFIO file to check > @@ -1211,17 +1245,12 @@ EXPORT_SYMBOL_GPL(vfio_file_is_valid); > bool vfio_file_has_dev(struct file *file, struct vfio_device *device) > { > struct vfio_group *group; > - struct vfio_device *vdev; > > group = vfio_group_from_file(file); > if (group) > return vfio_group_has_dev(group, device); > > - vdev = vfio_device_from_file(file); > - if (vdev) > - return vdev == device; > - > - return false; > + return vfio_file_has_device_access(file, device); > } > EXPORT_SYMBOL_GPL(vfio_file_has_dev); >
> From: Alex Williamson <alex.williamson@redhat.com> > Sent: Wednesday, March 29, 2023 5:34 AM > > On Mon, 27 Mar 2023 02:40:31 -0700 > Yi Liu <yi.l.liu@intel.com> 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> > > Reviewed-by: Kevin Tian <kevin.tian@intel.com> > > Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> > > Tested-by: Terrence Xu <terrence.xu@intel.com> > > Tested-by: Nicolin Chen <nicolinc@nvidia.com> > > Tested-by: Matthew Rosato <mjrosato@linux.ibm.com> > > Signed-off-by: Yi Liu <yi.l.liu@intel.com> > > --- > > drivers/vfio/group.c | 11 ++++++++++- > > drivers/vfio/vfio.h | 1 + > > drivers/vfio/vfio_main.c | 41 ++++++++++++++++++++++++++++++++++--- > --- > > 3 files changed, 46 insertions(+), 7 deletions(-) > > > > diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c > > index 9a7b2765eef6..4f267ae7bebc 100644 > > --- a/drivers/vfio/group.c > > +++ b/drivers/vfio/group.c > > @@ -194,9 +194,18 @@ static int vfio_device_group_open(struct > vfio_device_file *df) > > df->iommufd = device->group->iommufd; > > > > ret = vfio_device_open(df); > > - if (ret) > > + if (ret) { > > df->iommufd = NULL; > > + goto out_put_kvm; > > + } > > + > > + /* > > + * Paired with smp_load_acquire() in vfio_device_fops::ioctl/ > > + * read/write/mmap > > + */ > > + smp_store_release(&df->access_granted, true); > > > > +out_put_kvm: > > if (device->open_count == 0) > > vfio_device_put_kvm(device); > > > > diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h > > index cffc08f5a6f1..854f2c97cb9a 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 2ea6cb6d03c7..b515bbda4c74 100644 > > --- a/drivers/vfio/vfio_main.c > > +++ b/drivers/vfio/vfio_main.c > > @@ -1114,6 +1114,10 @@ static long vfio_device_fops_unl_ioctl(struct > file *filep, > > struct vfio_device *device = df->device; > > int ret; > > > > + /* Paired with smp_store_release() following vfio_device_open() */ > > + if (!smp_load_acquire(&df->access_granted)) > > + return -EINVAL; > > + > > ret = vfio_device_pm_runtime_get(device); > > if (ret) > > return ret; > > @@ -1141,6 +1145,10 @@ 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() following vfio_device_open() */ > > + if (!smp_load_acquire(&df->access_granted)) > > + return -EINVAL; > > + > > if (unlikely(!device->ops->read)) > > return -EINVAL; > > > > @@ -1154,6 +1162,10 @@ 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() following vfio_device_open() */ > > + if (!smp_load_acquire(&df->access_granted)) > > + return -EINVAL; > > + > > if (unlikely(!device->ops->write)) > > return -EINVAL; > > > > @@ -1165,6 +1177,10 @@ 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() following vfio_device_open() */ > > + if (!smp_load_acquire(&df->access_granted)) > > + return -EINVAL; > > + > > if (unlikely(!device->ops->mmap)) > > return -EINVAL; > > > > @@ -1201,6 +1217,24 @@ bool vfio_file_is_valid(struct file *file) > > } > > EXPORT_SYMBOL_GPL(vfio_file_is_valid); > > > > +/* > > + * Return true if the input file is a vfio device file and has opened > > + * the input device. Otherwise, return false. > > + */ > > +static bool vfio_file_has_device_access(struct file *file, > > + struct vfio_device *device) > > +{ > > + struct vfio_device *vdev = vfio_device_from_file(file); > > + struct vfio_device_file *df; > > + > > + if (!vdev || vdev != device) > > + return false; > > + > > + df = file->private_data; > > + > > + return READ_ONCE(df->access_granted); > > Why did we change from smp_load_acquire() to READ_ONCE() here? > Thanks, It should still use smp_load_acquire(). When this is added, its major usage is under the dev_set->lock, so it is functionally ok since the writer of the df->access_granted is also under the dev_set->lock. However, as an helper in vfio_core, it should use smp_load_acquire() otherwise needs to add lockdep to check if dev_set->lock is held. Thanks, Yi Liu > > > +} > > + > > /** > > * vfio_file_has_dev - True if the VFIO file is a handle for device > > * @file: VFIO file to check > > @@ -1211,17 +1245,12 @@ EXPORT_SYMBOL_GPL(vfio_file_is_valid); > > bool vfio_file_has_dev(struct file *file, struct vfio_device *device) > > { > > struct vfio_group *group; > > - struct vfio_device *vdev; > > > > group = vfio_group_from_file(file); > > if (group) > > return vfio_group_has_dev(group, device); > > > > - vdev = vfio_device_from_file(file); > > - if (vdev) > > - return vdev == device; > > - > > - return false; > > + return vfio_file_has_device_access(file, device); > > } > > EXPORT_SYMBOL_GPL(vfio_file_has_dev); > >
diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c index 9a7b2765eef6..4f267ae7bebc 100644 --- a/drivers/vfio/group.c +++ b/drivers/vfio/group.c @@ -194,9 +194,18 @@ static int vfio_device_group_open(struct vfio_device_file *df) df->iommufd = device->group->iommufd; ret = vfio_device_open(df); - if (ret) + if (ret) { df->iommufd = NULL; + goto out_put_kvm; + } + + /* + * Paired with smp_load_acquire() in vfio_device_fops::ioctl/ + * read/write/mmap + */ + smp_store_release(&df->access_granted, true); +out_put_kvm: if (device->open_count == 0) vfio_device_put_kvm(device); diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h index cffc08f5a6f1..854f2c97cb9a 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 2ea6cb6d03c7..b515bbda4c74 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -1114,6 +1114,10 @@ static long vfio_device_fops_unl_ioctl(struct file *filep, struct vfio_device *device = df->device; int ret; + /* Paired with smp_store_release() following vfio_device_open() */ + if (!smp_load_acquire(&df->access_granted)) + return -EINVAL; + ret = vfio_device_pm_runtime_get(device); if (ret) return ret; @@ -1141,6 +1145,10 @@ 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() following vfio_device_open() */ + if (!smp_load_acquire(&df->access_granted)) + return -EINVAL; + if (unlikely(!device->ops->read)) return -EINVAL; @@ -1154,6 +1162,10 @@ 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() following vfio_device_open() */ + if (!smp_load_acquire(&df->access_granted)) + return -EINVAL; + if (unlikely(!device->ops->write)) return -EINVAL; @@ -1165,6 +1177,10 @@ 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() following vfio_device_open() */ + if (!smp_load_acquire(&df->access_granted)) + return -EINVAL; + if (unlikely(!device->ops->mmap)) return -EINVAL; @@ -1201,6 +1217,24 @@ bool vfio_file_is_valid(struct file *file) } EXPORT_SYMBOL_GPL(vfio_file_is_valid); +/* + * Return true if the input file is a vfio device file and has opened + * the input device. Otherwise, return false. + */ +static bool vfio_file_has_device_access(struct file *file, + struct vfio_device *device) +{ + struct vfio_device *vdev = vfio_device_from_file(file); + struct vfio_device_file *df; + + if (!vdev || vdev != device) + return false; + + df = file->private_data; + + return READ_ONCE(df->access_granted); +} + /** * vfio_file_has_dev - True if the VFIO file is a handle for device * @file: VFIO file to check @@ -1211,17 +1245,12 @@ EXPORT_SYMBOL_GPL(vfio_file_is_valid); bool vfio_file_has_dev(struct file *file, struct vfio_device *device) { struct vfio_group *group; - struct vfio_device *vdev; group = vfio_group_from_file(file); if (group) return vfio_group_has_dev(group, device); - vdev = vfio_device_from_file(file); - if (vdev) - return vdev == device; - - return false; + return vfio_file_has_device_access(file, device); } EXPORT_SYMBOL_GPL(vfio_file_has_dev);