vdpa/mlx5: Fix suspend/resume index restoration

When we suspend the VM, the VDPA interface will be reset. When the VM is
resumed again, clear_virtqueues() will clear the available and used
indices resulting in hardware virqtqueue objects becoming out of sync.
We can avoid this function alltogether since qemu will clear them if
required, e.g. when the VM went through a reboot.

Moreover, since the hw available and used indices should always be
identical on query and should be restored to the same value same value
for virtqueues that complete in order, we set the single value provided
by set_vq_state(). In get_vq_state() we return the value of hardware
used index.

Fixes: b35ccebe3ef7 ("vdpa/mlx5: Restore the hardware used index after change map")
Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices")
Signed-off-by: Eli Cohen <elic@nvidia.com>
Link: https://lore.kernel.org/r/20210408091047.4269-6-elic@nvidia.com
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>

1 files changed, 8 insertions, 13 deletions

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 6fe61fc5779067..4d2809c7d4e32f 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1169,6 +1169,7 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m
 		return;
 	}
 	mvq->avail_idx = attr.available_index;
+	mvq->used_idx = attr.used_index;
 }
 
 static void suspend_vqs(struct mlx5_vdpa_net *ndev)
@@ -1426,6 +1427,7 @@ static int mlx5_vdpa_set_vq_state(struct vdpa_device *vdev, u16 idx,
 		return -EINVAL;
 	}
 
+	mvq->used_idx = state->avail_index;
 	mvq->avail_idx = state->avail_index;
 	return 0;
 }
@@ -1443,7 +1445,11 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa
 	 * that cares about emulating the index after vq is stopped.
 	 */
 	if (!mvq->initialized) {
-		state->avail_index = mvq->avail_idx;
+		/* Firmware returns a wrong value for the available index.
+		 * Since both values should be identical, we take the value of
+		 * used_idx which is reported correctly.
+		 */
+		state->avail_index = mvq->used_idx;
 		return 0;
 	}
 
@@ -1452,7 +1458,7 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa
 		mlx5_vdpa_warn(mvdev, "failed to query virtqueue\n");
 		return err;
 	}
-	state->avail_index = attr.available_index;
+	state->avail_index = attr.used_index;
 	return 0;
 }
 
@@ -1540,16 +1546,6 @@ static void teardown_virtqueues(struct mlx5_vdpa_net *ndev)
 	}
 }
 
-static void clear_virtqueues(struct mlx5_vdpa_net *ndev)
-{
-	int i;
-
-	for (i = ndev->mvdev.max_vqs - 1; i >= 0; i--) {
-		ndev->vqs[i].avail_idx = 0;
-		ndev->vqs[i].used_idx = 0;
-	}
-}
-
 /* TODO: cross-endian support */
 static inline bool mlx5_vdpa_is_little_endian(struct mlx5_vdpa_dev *mvdev)
 {
@@ -1785,7 +1781,6 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status)
 	if (!status) {
 		mlx5_vdpa_info(mvdev, "performing device reset\n");
 		teardown_driver(ndev);
-		clear_virtqueues(ndev);
 		mlx5_vdpa_destroy_mr(&ndev->mvdev);
 		ndev->mvdev.status = 0;
 		ndev->mvdev.mlx_features = 0;