Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Eli Cohen <elic@nvidia.com>
To:     <mst@redhat.com>, <jasowang@redhat.com>, <si-wei.liu@oracle.com>,
        <linux-kernel@vger.kernel.org>,
        <virtualization@lists.linux-foundation.org>,
        <netdev@vger.kernel.org>
CC:     <elic@nvidia.com>
Subject: [PATCH 1/2] vdpa/mlx5: Fix suspend/resume index restoration
Date:   Tue, 16 Feb 2021 18:20:01 +0200
Message-ID: <20210216162001.83541-1-elic@nvidia.com>
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Content-Type: text/plain
Precedence: bulk

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: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices=
")
Signed-off-by: Eli Cohen <elic@nvidia.com>
---
 drivers/vdpa/mlx5/net/mlx5_vnet.c | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 deletions(-)

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5=
_vnet.c
index b8e9d525d66c..a51b0f86afe2 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, st=
ruct mlx5_vdpa_virtqueue *m
 		return;
 	}
 	mvq->avail_idx =3D attr.available_index;
+	mvq->used_idx =3D attr.used_index;
 }
=20
 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;
 	}
=20
+	mvq->used_idx =3D state->avail_index;
 	mvq->avail_idx =3D state->avail_index;
 	return 0;
 }
@@ -1443,7 +1445,7 @@ 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 =3D mvq->avail_idx;
+		state->avail_index =3D mvq->used_idx;
 		return 0;
 	}
=20
@@ -1452,7 +1454,7 @@ 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 =3D attr.available_index;
+	state->avail_index =3D attr.used_index;
 	return 0;
 }
=20
@@ -1532,16 +1534,6 @@ static void teardown_virtqueues(struct mlx5_vdpa_net=
 *ndev)
 	}
 }
=20
-static void clear_virtqueues(struct mlx5_vdpa_net *ndev)
-{
-	int i;
-
-	for (i =3D ndev->mvdev.max_vqs - 1; i >=3D 0; i--) {
-		ndev->vqs[i].avail_idx =3D 0;
-		ndev->vqs[i].used_idx =3D 0;
-	}
-}
-
 /* TODO: cross-endian support */
 static inline bool mlx5_vdpa_is_little_endian(struct mlx5_vdpa_dev *mvdev)
 {
@@ -1777,7 +1769,6 @@ 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 =3D 0;
 		++mvdev->generation;
--=20
2.29.2