similar to: [PATCH] vdpa/mlx5: should keep avail_index despite device status

On 2020/7/16 ??3:23, Eli Cohen wrote: > Add a front end VDPA driver that registers in the VDPA bus and provides > networking to a guest. The VDPA driver creates the necessary resources > on the VF it is driving such that data path will be offloaded. > > Notifications are being communicated through the driver. > > Currently, only VFs are supported. In subsequent patches we will

On 2020/7/16 ??7:54, Eli Cohen wrote: > On Thu, Jul 16, 2020 at 05:14:32PM +0800, Jason Wang wrote: >>> +static void suspend_vqs(struct mlx5_vdpa_net *ndev) >>> +{ >>> + int i; >>> + >>> + for (i = 0; i < MLX5_MAX_SUPPORTED_VQS; i++) >>> + suspend_vq(ndev, &ndev->vqs[i]); >> >> In teardown_virtqueues() it has a check

A firmware error is triggered when configuring a 9k MTU on the PF after switching to switchdev mode and then using a vdpa device with larger (1k) rings: mlx5_cmd_out_err: CREATE_GENERAL_OBJECT(0xa00) op_mod(0xd) failed, status bad resource(0x5), syndrome (0xf6db90), err(-22) This is due to the fact that the hw VQ size parameters are computed based on the umem_1/2/3_buffer_param_a/b capabilities

On 2020/7/19 ??3:49, Eli Cohen wrote: > On Fri, Jul 17, 2020 at 04:57:29PM +0800, Jason Wang wrote: >>> Looks like checking intialized is enough. Will fix this. >>>>> + >>>>> +static void mlx5_vdpa_set_vq_ready(struct vdpa_device *vdev, u16 idx, bool ready) >>>>> +{ >>>>> + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);

Otherwise the virtqueue object to instate could point to invalid address that was unmapped from the MTT: mlx5_core 0000:41:04.2: mlx5_cmd_out_err:782:(pid 8321): CREATE_GENERAL_OBJECT(0xa00) op_mod(0xd) failed, status bad parameter(0x3), syndrome (0x5fa1c), err(-22) Fixes: cae15c2ed8e6 ("vdpa/mlx5: Implement susupend virtqueue callback") Cc: Eli Cohen <elic at nvidia.com>

On Wed, Feb 15, 2023 at 9:31 AM Si-Wei Liu <si-wei.liu at oracle.com> wrote: > > Otherwise the virtqueue object to instate could point to invalid address > that was unmapped from the MTT: > > mlx5_core 0000:41:04.2: mlx5_cmd_out_err:782:(pid 8321): > CREATE_GENERAL_OBJECT(0xa00) op_mod(0xd) failed, status > bad parameter(0x3), syndrome (0x5fa1c), err(-22) > >

On 2/15/2023 8:48 PM, Jason Wang wrote: > On Wed, Feb 15, 2023 at 9:31 AM Si-Wei Liu <si-wei.liu at oracle.com> wrote: >> Otherwise the virtqueue object to instate could point to invalid address >> that was unmapped from the MTT: >> >> mlx5_core 0000:41:04.2: mlx5_cmd_out_err:782:(pid 8321): >> CREATE_GENERAL_OBJECT(0xa00) op_mod(0xd) failed, status

On Mon, Apr 3, 2023 at 2:47?PM Eli Cohen <elic at nvidia.com> wrote: > > > On 03/04/2023 8:01, Jason Wang wrote: > > On Sun, Apr 2, 2023 at 10:15?PM Eli Cohen <elic at nvidia.com> wrote: > >> Current code ignores link state updates if VIRTIO_NET_F_STATUS was not > >> negotiated. However, link state updates could be received before feature > >>

On 2020/7/16 ??3:23, Eli Cohen wrote: > Currently, get_vq_state() is used only to pass the available index value > of a vq. Extend the struct to return status on the VQ to the caller. > For now, define VQ_STATE_NOT_READY. In the future it will be extended to > include other infomration. > > Modify current vdpa driver to update this field. > > Reviewed-by: Parav Pandit

On 2020/7/20 ??3:14, Eli Cohen wrote: > Modify get_vq_state() so it returns an error code. In case of hardware > acceleration, the available index may be retrieved from the device, an > operation that can possibly fail. > > Reviewed-by: Parav Pandit <parav at mellanox.com> > Signed-off-by: Eli Cohen <eli at mellanox.com> Acked-by: Jason Wang <jasowang at

On 2020/8/5 ??12:20, Eli Cohen wrote: > Modify get_vq_state() so it returns an error code. In case of hardware > acceleration, the available index may be retrieved from the device, an > operation that can possibly fail. > > Reviewed-by: Parav Pandit <parav at mellanox.com> > Signed-off-by: Eli Cohen <eli at mellanox.com> Acked-by: Jason Wang <jasowang at

Today, mlx5_vdpa gets started by preallocate 1:1 DMA mapping at device creation time, while this 1:1 mapping will be implicitly destroyed when the first .set_map call is invoked. Everytime when the .reset callback is invoked, any mapping left behind will be dropped then reset back to the initial 1:1 DMA mapping. In order to reduce excessive memory mapping cost during live migration, it is

On 3/20/2023 4:49 AM, Eli Cohen wrote: > Extend the possible list for features that can be supported by firmware. > Note that different versions of firmware may or may not support these > features. The driver is made aware of them by querying the firmware. > > While doing this, improve the code so we use enum names instead of hard > coded numerical values. > > The new

On Wed, Mar 15, 2023 at 3:28?PM Eli Cohen <elic at nvidia.com> wrote: > > Extend the possible list for features that can be supported by firmware. > Note that different versions of firmware may or may not support these > features. The driver is made aware of them by querying the firmware. > > While doing this, improve the code so we use enum names instead of hard > coded

Commit 653055b9acd4 ("vhost-vdpa: support get/set backend features") introduces two malfunction backend features ioctls: 1) the ioctls was blindly added to vring ioctl instead of vdpa device ioctl 2) vhost_set_backend_features() was called when dev mutex has already been held which will lead a deadlock This patch fixes the above issues. Cc: Eli Cohen <elic at nvidia.com>

Commit 653055b9acd4 ("vhost-vdpa: support get/set backend features") introduces two malfunction backend features ioctls: 1) the ioctls was blindly added to vring ioctl instead of vdpa device ioctl 2) vhost_set_backend_features() was called when dev mutex has already been held which will lead a deadlock This patch fixes the above issues. Cc: Eli Cohen <elic at nvidia.com>

? 2023/1/19 17:14, Eugenio Perez Martin ??: > On Thu, Jan 19, 2023 at 4:16 AM Jason Wang <jasowang at redhat.com> wrote: >> On Thu, Jan 19, 2023 at 12:44 AM Eugenio P?rez <eperezma at redhat.com> wrote: >>> vdpasim_queue_ready calls vringh_init_iotlb, which resets split indexes. >>> But it can be called after setting a ring base with >>>

On Thu, Sep 24, 2020 at 11:21:02AM +0800, Jason Wang wrote: > Commit 653055b9acd4 ("vhost-vdpa: support get/set backend features") > introduces two malfunction backend features ioctls: > > 1) the ioctls was blindly added to vring ioctl instead of vdpa device > ioctl > 2) vhost_set_backend_features() was called when dev mutex has already > been held which will

On 2020/7/20 ??3:14, Eli Cohen wrote: > Add a front end VDPA driver that registers in the VDPA bus and provides > networking to a guest. The VDPA driver creates the necessary resources > on the VF it is driving such that data path will be offloaded. > > Notifications are being communicated through the driver. > > Currently, only VFs are supported. In subsequent patches we will

----- Original Message ----- > This commit introduced vhost_vdpa_set/get_backend_features() to > resolve these issues: > (1)In vhost_vdpa ioctl SET_BACKEND_FEATURES path, currect code > would try to acquire vhost dev mutex twice > (first shown in vhost_vdpa_unlocked_ioctl), which can lead > to a dead lock issue. > (2)SET_BACKEND_FEATURES was blindly added to vring ioctl