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;
MIME-Version: 1.0
Message-ID: <1612993680-29454-3-git-send-email-si-wei.liu@oracle.com>
Date:   Wed, 10 Feb 2021 13:47:59 -0800 (PST)
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 v2 2/3] vdpa/mlx5: fix feature negotiation across device reset
References: <1612993680-29454-1-git-send-email-si-wei.liu@oracle.com>
In-Reply-To: <1612993680-29454-1-git-send-email-si-wei.liu@oracle.com>
Content-Type: text/plain; charset=ascii
Content-Transfer-Encoding: 7bit
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 may have the assumption
that mlx_features can be reloaded from firmware
via the .get_features ops after device is reset
(via the .set_status ops), which is unfortunately
not true. The userspace VMM might save a copy
of backend capable features and won't call into
kernel again to get it on reset. This causes all
virtio features getting disabled on newly created
virtqs after device reset, while guest would hold
mismatched view of available features. For e.g.,
the guest may still assume tx checksum offload
is available after reset and feature negotiation,
causing frames with bogus (incomplete) checksum
transmitted on the wire.

Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices")
Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.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 b8416c4..7c1f789 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1486,16 +1486,8 @@ 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)
@@ -1788,7 +1780,6 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status)
 		clear_virtqueues(ndev);
 		mlx5_vdpa_destroy_mr(&ndev->mvdev);
 		ndev->mvdev.status = 0;
-		ndev->mvdev.mlx_features = 0;
 		++mvdev->generation;
 		return;
 	}
@@ -1907,6 +1898,19 @@ 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;
@@ -2005,6 +2009,7 @@ static int mlx5v_probe(struct auxiliary_device *adev,
 	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