| Message ID | 20230213151348.56451-8-yi.l.liu@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Add vfio_device cdev for iommufd support | expand |
On Mon, 13 Feb 2023 07:13:40 -0800 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> > Signed-off-by: Yi Liu <yi.l.liu@intel.com> > Reviewed-by: Kevin Tian <kevin.tian@intel.com> > --- > drivers/vfio/vfio.h | 1 + > drivers/vfio/vfio_main.c | 34 +++++++++++++++++++++++++++++++++- > 2 files changed, 34 insertions(+), 1 deletion(-) > > diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h > index 11e56fe079a1..d56cdb114024 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 c517252aba19..2267057240bd 100644 > --- a/drivers/vfio/vfio_main.c > +++ b/drivers/vfio/vfio_main.c > @@ -476,7 +476,15 @@ int vfio_device_open(struct vfio_device_file *df) > device->open_count--; > } > > - return ret; > + if (ret) > + return ret; > + > + /* > + * Paired with smp_load_acquire() in vfio_device_fops::ioctl/ > + * read/write/mmap > + */ > + smp_store_release(&df->access_granted, true); > + return 0; > } > > void vfio_device_close(struct vfio_device_file *df) > @@ -1104,8 +1112,14 @@ static long vfio_device_fops_unl_ioctl(struct file *filep, > { > struct vfio_device_file *df = filep->private_data; > struct vfio_device *device = df->device; > + bool access; > int ret; > > + /* Paired with smp_store_release() in vfio_device_open() */ > + access = smp_load_acquire(&df->access_granted); > + if (!access) > + return -EINVAL; > + Nit, if (!smp_load_acquire(&df->access_granted)) ... Thanks, Alex > ret = vfio_device_pm_runtime_get(device); > if (ret) > return ret; > @@ -1132,6 +1146,12 @@ 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; > + bool access; > + > + /* Paired with smp_store_release() in vfio_device_open() */ > + access = smp_load_acquire(&df->access_granted); > + if (!access) > + return -EINVAL; > > if (unlikely(!device->ops->read)) > return -EINVAL; > @@ -1145,6 +1165,12 @@ static ssize_t vfio_device_fops_write(struct file *filep, > { > struct vfio_device_file *df = filep->private_data; > struct vfio_device *device = df->device; > + bool access; > + > + /* Paired with smp_store_release() in vfio_device_open() */ > + access = smp_load_acquire(&df->access_granted); > + if (!access) > + return -EINVAL; > > if (unlikely(!device->ops->write)) > return -EINVAL; > @@ -1156,6 +1182,12 @@ 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; > + bool access; > + > + /* Paired with smp_store_release() in vfio_device_open() */ > + access = smp_load_acquire(&df->access_granted); > + if (!access) > + return -EINVAL; > > if (unlikely(!device->ops->mmap)) > return -EINVAL;
> From: Alex Williamson <alex.williamson@redhat.com> > Sent: Wednesday, February 15, 2023 6:47 AM > > On Mon, 13 Feb 2023 07:13:40 -0800 > 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> > > Signed-off-by: Yi Liu <yi.l.liu@intel.com> > > Reviewed-by: Kevin Tian <kevin.tian@intel.com> > > --- > > drivers/vfio/vfio.h | 1 + > > drivers/vfio/vfio_main.c | 34 +++++++++++++++++++++++++++++++++- > > 2 files changed, 34 insertions(+), 1 deletion(-) > > > > diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h > > index 11e56fe079a1..d56cdb114024 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 c517252aba19..2267057240bd 100644 > > --- a/drivers/vfio/vfio_main.c > > +++ b/drivers/vfio/vfio_main.c > > @@ -476,7 +476,15 @@ int vfio_device_open(struct vfio_device_file *df) > > device->open_count--; > > } > > > > - return ret; > > + if (ret) > > + return ret; > > + > > + /* > > + * Paired with smp_load_acquire() in vfio_device_fops::ioctl/ > > + * read/write/mmap > > + */ > > + smp_store_release(&df->access_granted, true); > > + return 0; > > } > > > > void vfio_device_close(struct vfio_device_file *df) > > @@ -1104,8 +1112,14 @@ static long vfio_device_fops_unl_ioctl(struct > file *filep, > > { > > struct vfio_device_file *df = filep->private_data; > > struct vfio_device *device = df->device; > > + bool access; > > int ret; > > > > + /* Paired with smp_store_release() in vfio_device_open() */ > > + access = smp_load_acquire(&df->access_granted); > > + if (!access) > > + return -EINVAL; > > + > > Nit, > > if (!smp_load_acquire(&df->access_granted)) > ... Got it. also updated other similar lines. > Thanks, > Alex > > > ret = vfio_device_pm_runtime_get(device); > > if (ret) > > return ret; > > @@ -1132,6 +1146,12 @@ 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; > > + bool access; > > + > > + /* Paired with smp_store_release() in vfio_device_open() */ > > + access = smp_load_acquire(&df->access_granted); > > + if (!access) > > + return -EINVAL; > > > > if (unlikely(!device->ops->read)) > > return -EINVAL; > > @@ -1145,6 +1165,12 @@ static ssize_t vfio_device_fops_write(struct file > *filep, > > { > > struct vfio_device_file *df = filep->private_data; > > struct vfio_device *device = df->device; > > + bool access; > > + > > + /* Paired with smp_store_release() in vfio_device_open() */ > > + access = smp_load_acquire(&df->access_granted); > > + if (!access) > > + return -EINVAL; > > > > if (unlikely(!device->ops->write)) > > return -EINVAL; > > @@ -1156,6 +1182,12 @@ 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; > > + bool access; > > + > > + /* Paired with smp_store_release() in vfio_device_open() */ > > + access = smp_load_acquire(&df->access_granted); > > + if (!access) > > + return -EINVAL; > > > > if (unlikely(!device->ops->mmap)) > > return -EINVAL; Regards, Yi Liu
diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h index 11e56fe079a1..d56cdb114024 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 c517252aba19..2267057240bd 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -476,7 +476,15 @@ int vfio_device_open(struct vfio_device_file *df) device->open_count--; } - return ret; + if (ret) + return ret; + + /* + * Paired with smp_load_acquire() in vfio_device_fops::ioctl/ + * read/write/mmap + */ + smp_store_release(&df->access_granted, true); + return 0; } void vfio_device_close(struct vfio_device_file *df) @@ -1104,8 +1112,14 @@ static long vfio_device_fops_unl_ioctl(struct file *filep, { struct vfio_device_file *df = filep->private_data; struct vfio_device *device = df->device; + bool access; int ret; + /* Paired with smp_store_release() in vfio_device_open() */ + access = smp_load_acquire(&df->access_granted); + if (!access) + return -EINVAL; + ret = vfio_device_pm_runtime_get(device); if (ret) return ret; @@ -1132,6 +1146,12 @@ 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; + bool access; + + /* Paired with smp_store_release() in vfio_device_open() */ + access = smp_load_acquire(&df->access_granted); + if (!access) + return -EINVAL; if (unlikely(!device->ops->read)) return -EINVAL; @@ -1145,6 +1165,12 @@ static ssize_t vfio_device_fops_write(struct file *filep, { struct vfio_device_file *df = filep->private_data; struct vfio_device *device = df->device; + bool access; + + /* Paired with smp_store_release() in vfio_device_open() */ + access = smp_load_acquire(&df->access_granted); + if (!access) + return -EINVAL; if (unlikely(!device->ops->write)) return -EINVAL; @@ -1156,6 +1182,12 @@ 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; + bool access; + + /* Paired with smp_store_release() in vfio_device_open() */ + access = smp_load_acquire(&df->access_granted); + if (!access) + return -EINVAL; if (unlikely(!device->ops->mmap)) return -EINVAL;