linux-stable.git/drivers/vdpa, branch v6.7

pds_vdpa: set features order

2023-12-01T14:55:01+00:00

Fix up the order that the device and negotiated features
are checked to get a more reliable difference when things
get changed.

Signed-off-by: Shannon Nelson 
Message-Id: <20231110221802.46841-4-shannon.nelson@amd.com>
Signed-off-by: Michael S. Tsirkin 
Acked-by: Jason Wang

pds_vdpa: clear config callback when status goes to 0

2023-12-01T14:55:01+00:00

If the client driver is setting status to 0, something is
getting shutdown and possibly removed.  Make sure we clear
the config_cb so that it doesn't end up crashing when
trying to call a bogus callback.

Signed-off-by: Shannon Nelson 
Message-Id: <20231110221802.46841-3-shannon.nelson@amd.com>
Signed-off-by: Michael S. Tsirkin 
Acked-by: Jason Wang

pds_vdpa: fix up format-truncation complaint

2023-12-01T14:55:01+00:00

Our friendly kernel test robot has recently been pointing out
some format-truncation issues.  Here's a fix for one of them.

Reported-by: kernel test robot 
Closes: https://lore.kernel.org/oe-kbuild-all/202311040109.RfgJoE7L-lkp@intel.com/
Signed-off-by: Shannon Nelson 
Message-Id: <20231110221802.46841-2-shannon.nelson@amd.com>
Signed-off-by: Michael S. Tsirkin 
Acked-by: Jason Wang

vdpa/mlx5: preserve CVQ vringh index

2023-12-01T14:52:03+00:00

mlx5_vdpa does not preserve userland's view of vring base for the control
queue in the following sequence:

ioctl VHOST_SET_VRING_BASE
ioctl VHOST_VDPA_SET_STATUS VIRTIO_CONFIG_S_DRIVER_OK
  mlx5_vdpa_set_status()
    setup_cvq_vring()
      vringh_init_iotlb()
        vringh_init_kern()
          vrh->last_avail_idx = 0;
ioctl VHOST_GET_VRING_BASE

To fix, restore the value of cvq->vring.last_avail_idx after calling
vringh_init_iotlb.

Fixes: 5262912ef3cf ("vdpa/mlx5: Add support for control VQ and MAC setting")

Signed-off-by: Steve Sistare 
Acked-by: Eugenio Pérez 
Acked-by: Jason Wang 
Message-Id: <1699014387-194368-1-git-send-email-steven.sistare@oracle.com>
Signed-off-by: Michael S. Tsirkin

vdpa_sim_blk: allocate the buffer zeroed

2023-11-01T13:31:16+00:00

Deleting and recreating a device can lead to having the same
content as the old device, so let's always allocate buffers
completely zeroed out.

Fixes: abebb16254b3 ("vdpa_sim_blk: support shared backend")
Suggested-by: Qing Wang 
Signed-off-by: Stefano Garzarella 
Message-Id: <20231031144339.121453-1-sgarzare@redhat.com>
Signed-off-by: Michael S. Tsirkin 
Acked-by: Eugenio Pérez 
Acked-by: Jason Wang

vdpa_sim: implement .reset_map support

2023-11-01T13:20:00+00:00

In order to reduce excessive memory mapping cost in live migration and
VM reboot, it is desirable to decouple the vhost-vdpa IOTLB abstraction
from the virtio device life cycle, i.e. mappings can be kept intact
across virtio device reset. Leverage the .reset_map callback, which is
meant to destroy the iotlb on the given ASID and recreate the 1:1
passthrough/identity mapping. To be consistent, the mapping on device
creation is initiailized to passthrough/identity with PA 1:1 mapped as
IOVA. With this the device .reset op doesn't have to maintain and clean
up memory mappings by itself.

Additionally, implement .compat_reset to cater for older userspace,
which may wish to see mapping to be cleared during reset.

Signed-off-by: Si-Wei Liu 
Tested-by: Stefano Garzarella 
Message-Id: <1697880319-4937-8-git-send-email-si-wei.liu@oracle.com>
Signed-off-by: Michael S. Tsirkin 
Tested-by: Lei Yang

vdpa/mlx5: implement .reset_map driver op

2023-11-01T13:20:00+00:00

Since commit 6f5312f80183 ("vdpa/mlx5: Add support for running with
virtio_vdpa"), mlx5_vdpa starts with preallocate 1:1 DMA MR at device
creation time. This 1:1 DMA MR will be implicitly destroyed while the
first .set_map call is invoked, in which case callers like vhost-vdpa
will start to set up custom mappings. When the .reset callback is
invoked, the custom mappings will be cleared and the 1:1 DMA MR will be
re-created.

In order to reduce excessive memory mapping cost in live migration, it
is desirable to decouple the vhost-vdpa IOTLB abstraction from the
virtio device life cycle, i.e. mappings can be kept around intact across
virtio device reset. Leverage the .reset_map callback, which is meant to
destroy the regular MR (including cvq mapping) on the given ASID and
recreate the initial DMA mapping. That way, the device .reset op runs
free from having to maintain and clean up memory mappings by itself.

Additionally, implement .compat_reset to cater for older userspace,
which may wish to see mapping to be cleared during reset.

Co-developed-by: Dragos Tatulea 
Signed-off-by: Dragos Tatulea 
Signed-off-by: Si-Wei Liu 
Message-Id: <1697880319-4937-7-git-send-email-si-wei.liu@oracle.com>
Signed-off-by: Michael S. Tsirkin 
Tested-by: Lei Yang

vduse: make vduse_class constant

2023-11-01T13:19:59+00:00

Now that the driver core allows for struct class to be in read-only
memory, we should make all 'class' structures declared at build time
placing them into read-only memory, instead of having to be dynamically
allocated at runtime.

Cc: "Michael S. Tsirkin" 
Cc: Jason Wang 
Cc: Xuan Zhuo 
Cc: Xie Yongji 
Signed-off-by: Greg Kroah-Hartman 
Message-Id: <2023100643-tricolor-citizen-6c2d@gregkh>
Signed-off-by: Michael S. Tsirkin 
Reviewed-by: Xie Yongji 
Acked-by: Jason Wang

mlx5_vdpa: offer VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK

2023-11-01T13:19:58+00:00

Offer this backend feature as mlx5 is compatible with it. It allows it
to do live migration with CVQ, dynamically switching between passthrough
and shadow virtqueue.

Signed-off-by: Eugenio Pérez 
Message-Id: <20230703142514.363256-1-eperezma@redhat.com>
Signed-off-by: Michael S. Tsirkin

vdpa/mlx5: Update cvq iotlb mapping on ASID change

2023-11-01T13:19:57+00:00

For the following sequence:
- cvq group is in ASID 0
- .set_map(1, cvq_iotlb)
- .set_group_asid(cvq_group, 1)

... the cvq mapping from ASID 0 will be used. This is not always correct
behaviour.

This patch adds support for the above mentioned flow by saving the iotlb
on each .set_map and updating the cvq iotlb with it on a cvq group change.

Acked-by: Jason Wang 
Acked-by: Eugenio Pérez 
Signed-off-by: Dragos Tatulea 
Message-Id: <20231018171456.1624030-18-dtatulea@nvidia.com>
Signed-off-by: Michael S. Tsirkin 
Reviewed-by: Si-Wei Liu 
Tested-by: Si-Wei Liu 
Tested-by: Lei Yang