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:   Si-Wei Liu <si-wei.liu@oracle.com>
To:     mst@redhat.com, jasowang@redhat.com, elic@nvidia.com
Cc:     linux-kernel@vger.kernel.org,
        virtualization@lists.linux-foundation.org, netdev@vger.kernel.org,
        si-wei.liu@oracle.com
Subject: [PATCH v3 1/1] vdpa/mlx5: fix feature negotiation across device reset
Date:   Wed, 28 Apr 2021 21:48:54 -0400
Message-Id: <1619660934-30910-2-git-send-email-si-wei.liu@oracle.com>
In-Reply-To: <1619660934-30910-1-git-send-email-si-wei.liu@oracle.com>
References: <1619660934-30910-1-git-send-email-si-wei.liu@oracle.com>
Precedence: bulk

The mlx_features denotes the capability for which
set of virtio features is supported by device. In
principle, this field needs not be cleared during
virtio device reset, as this capability is static
and does not change across reset.

In fact, the current code seems to wrongly assume
that mlx_features can be reloaded or updated on
device reset thru the .get_features op. However,
the userspace VMM may save a copy of previously
advertised backend feature capability and won't
need to get it again on reset. In that event, all
virtio features reset to zero thus getting disabled
upon device reset. This ends up with guest holding
a mismatched view of available features with the
VMM/host's. For instance, the guest may assume
the presence of tx checksum offload feature across
reboot, however, since the feature is left disabled
on reset, frames with bogus partial checksum are
transmitted on the wire.

The fix is to retain the features capability on
reset, and get it only once from firmware on the
vdpa_dev_add path.

Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices")
Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Acked-by: Eli Cohen <elic@nvidia.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/vdpa/mlx5/net/mlx5_vnet.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 25533db..624f521 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1492,16 +1492,8 @@ static u64 mlx_to_vritio_features(u16 dev_features)
 static u64 mlx5_vdpa_get_features(struct vdpa_device *vdev)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
-	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
-	u16 dev_features;
 
-	dev_features = MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, device_features_bits_mask);
-	ndev->mvdev.mlx_features = mlx_to_vritio_features(dev_features);
-	if (MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, virtio_version_1_0))
-		ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_F_VERSION_1);
-	ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_F_ACCESS_PLATFORM);
-	print_features(mvdev, ndev->mvdev.mlx_features, false);
-	return ndev->mvdev.mlx_features;
+	return mvdev->mlx_features;
 }
 
 static int verify_min_features(struct mlx5_vdpa_dev *mvdev, u64 features)
@@ -1783,7 +1775,6 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status)
 		teardown_driver(ndev);
 		mlx5_vdpa_destroy_mr(&ndev->mvdev);
 		ndev->mvdev.status = 0;
-		ndev->mvdev.mlx_features = 0;
 		++mvdev->generation;
 		return;
 	}
@@ -1902,6 +1893,19 @@ static int mlx5_get_vq_irq(struct vdpa_device *vdv, u16 idx)
 	.free = mlx5_vdpa_free,
 };
 
+static void query_virtio_features(struct mlx5_vdpa_net *ndev)
+{
+	struct mlx5_vdpa_dev *mvdev = &ndev->mvdev;
+	u16 dev_features;
+
+	dev_features = MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, device_features_bits_mask);
+	mvdev->mlx_features = mlx_to_vritio_features(dev_features);
+	if (MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, virtio_version_1_0))
+		mvdev->mlx_features |= BIT_ULL(VIRTIO_F_VERSION_1);
+	mvdev->mlx_features |= BIT_ULL(VIRTIO_F_ACCESS_PLATFORM);
+	print_features(mvdev, mvdev->mlx_features, false);
+}
+
 static int query_mtu(struct mlx5_core_dev *mdev, u16 *mtu)
 {
 	u16 hw_mtu;
@@ -2009,6 +2013,7 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name)
 	init_mvqs(ndev);
 	mutex_init(&ndev->reslock);
 	config = &ndev->config;
+	query_virtio_features(ndev);
 	err = query_mtu(mdev, &ndev->mtu);
 	if (err)
 		goto err_mtu;
-- 
1.8.3.1