kernel/git/next/linux-next.git/drivers/vhost, branch akpm

vringh: iterate on iotlb_translate to handle large translations

2022-06-27T12:05:35+00:00

iotlb_translate() can return -ENOBUFS if the bio_vec is not big enough to contain all the ranges for translation. This can happen for example if the VMM maps a large bounce buffer, without using hugepages, that requires more than 16 ranges to translate the addresses. To handle this case, let's extend iotlb_translate() to also return the number of bytes successfully translated. In copy_from_iotlb()/copy_to_iotlb() loops by calling iotlb_translate() several times until we complete the translation. Signed-off-by: Stefano Garzarella Message-Id: <20220624075656.13997-1-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin

vhost-vdpa: uAPI to suspend the device

2022-06-27T12:05:35+00:00

The ioctl adds support for suspending the device from userspace. This is a must before getting virtqueue indexes (base) for live migration, since the device could modify them after userland gets them. There are individual ways to perform that action for some devices (VHOST_NET_SET_BACKEND, VHOST_VSOCK_SET_RUNNING, ...) but there was no way to perform it for any vhost device (and, in particular, vhost-vdpa). After a successful return of the ioctl call the device must not process more virtqueue descriptors. The device can answer to read or writes of config fields as if it were not suspended. In particular, writing to "queue_enable" with a value of 1 will not make the device start processing buffers of the virtqueue. Signed-off-by: Eugenio Pérez Message-Id: <20220623160738.632852-4-eperezma@redhat.com> Signed-off-by: Michael S. Tsirkin

vhost-vdpa: introduce SUSPEND backend feature bit

2022-06-27T12:05:35+00:00

Userland knows if it can suspend the device or not by checking this feature bit. It's only offered if the vdpa driver backend implements the suspend() operation callback, and to offer it or userland to ack it if the backend does not offer that callback is an error. Signed-off-by: Eugenio Pérez Message-Id: <20220623160738.632852-3-eperezma@redhat.com> Signed-off-by: Michael S. Tsirkin

vhost-vdpa: call vhost_vdpa_cleanup during the release

2022-06-27T12:05:35+00:00

Before commit 3d5698793897 ("vhost-vdpa: introduce asid based IOTLB") we call vhost_vdpa_iotlb_free() during the release to clean all regions mapped in the iotlb. That commit removed vhost_vdpa_iotlb_free() and added vhost_vdpa_cleanup() to do some cleanup, including deleting all mappings, but we forgot to call it in vhost_vdpa_release(). This causes that if an application does not remove all mappings explicitly (or it crashes), the mappings remain in the iotlb and subsequent applications may fail if they map the same addresses. Calling vhost_vdpa_cleanup() also fixes a memory leak since we are not freeing `v->vdev.vqs` during the release from the same commit. Since vhost_vdpa_cleanup() calls vhost_dev_cleanup() we can remove its call from vhost_vdpa_release(). Fixes: 3d5698793897 ("vhost-vdpa: introduce asid based IOTLB") Cc: gautam.dawar@xilinx.com Signed-off-by: Stefano Garzarella Message-Id: <20220622151407.51232-1-sgarzare@redhat.com> Signed-off-by: Michael S. Tsirkin Tested-by: Eugenio Pérez Acked-by: Jason Wang

vdpa: make get_vq_group and set_group_asid optional

2022-06-09T04:26:35+00:00

This patch makes get_vq_group and set_group_asid optional. This is needed to unbreak the vDPA parent that doesn't support multiple address spaces. Cc: Gautam Dawar Fixes: aaca8373c4b1 ("vhost-vdpa: support ASID based IOTLB API") Signed-off-by: Jason Wang Message-Id: <20220609041901.2029-1-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin

vringh: Fix loop descriptors check in the indirect cases

2022-06-08T12:56:03+00:00

We should use size of descriptor chain to test loop condition in the indirect case. And another statistical count is also introduced for indirect descriptors to avoid conflict with the statistical count of direct descriptors. Fixes: f87d0fbb5798 ("vringh: host-side implementation of virtio rings.") Signed-off-by: Xie Yongji Signed-off-by: Fam Zheng Message-Id: <20220505100910.137-1-xieyongji@bytedance.com> Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang

vhost: rename vhost_work_dev_flush

2022-05-31T16:45:10+00:00

This patch renames vhost_work_dev_flush to just vhost_dev_flush to relfect that it flushes everything on the device and that drivers don't know/care that polls are based on vhost_works. Drivers just flush the entire device and polls, and works for vhost-scsi management TMFs and IO net virtqueues, etc all are flushed. Signed-off-by: Mike Christie Acked-by: Jason Wang Reviewed-by: Stefano Garzarella Message-Id: <20220517180850.198915-9-michael.christie@oracle.com> Signed-off-by: Michael S. Tsirkin

vhost-test: drop flush after vhost_dev_cleanup

2022-05-31T16:45:10+00:00

The flush after vhost_dev_cleanup is not needed because: 1. It doesn't do anything. vhost_dev_cleanup will stop the worker thread so the flush call will just return since the worker has not device. 2. It's not needed. The comment about jobs re-queueing themselves does not look correct because handle_vq does not requeue work. Signed-off-by: Mike Christie Acked-by: Jason Wang Message-Id: <20220517180850.198915-8-michael.christie@oracle.com> Signed-off-by: Michael S. Tsirkin

vhost-scsi: drop flush after vhost_dev_cleanup

2022-05-31T16:45:10+00:00

The flush after vhost_dev_cleanup is not needed because: 1. It doesn't do anything. vhost_dev_cleanup will stop the worker thread so the flush call will just return since the worker has not device. 2. It's not needed for the re-queue case. vhost_scsi_evt_handle_kick grabs the mutex and if the backend is NULL will return without queueing a work. vhost_scsi_clear_endpoint will set the backend to NULL under the vq->mutex then drops the mutex and does a flush. So we know when vhost_scsi_clear_endpoint has dropped the mutex after clearing the backend no evt related work will be able to requeue. The flush would then make sure any queued evts are run and return. Signed-off-by: Mike Christie Acked-by: Jason Wang Message-Id: <20220517180850.198915-7-michael.christie@oracle.com> Signed-off-by: Michael S. Tsirkin

vhost_vsock: simplify vhost_vsock_flush()

2022-05-31T16:45:10+00:00

vhost_vsock_flush() calls vhost_work_dev_flush(vsock->vqs[i].poll.dev) before vhost_work_dev_flush(&vsock->dev). This seems pointless as vsock->vqs[i].poll.dev is the same as &vsock->dev and several flushes in a row doesn't do anything useful, one is just enough. Signed-off-by: Andrey Ryabinin Reviewed-by: Stefano Garzarella Signed-off-by: Mike Christie Acked-by: Jason Wang Message-Id: <20220517180850.198915-6-michael.christie@oracle.com> Signed-off-by: Michael S. Tsirkin