virtualization.lists.linux-foundation.org archive mirror
 help / color / mirror / Atom feed
From: Parav Pandit <parav@nvidia.com>
To: <virtualization@lists.linux-foundation.org>
Cc: Si-Wei Liu <si-wei.liu@oracle.com>, elic@nvidia.com, mst@redhat.com
Subject: [PATCH linux-next v2 12/14] vdpa/mlx5: should exclude header length and fcs from mtu
Date: Tue, 6 Apr 2021 20:04:55 +0300	[thread overview]
Message-ID: <20210406170457.98481-13-parav@nvidia.com> (raw)
In-Reply-To: <20210406170457.98481-1-parav@nvidia.com>

From: Si-Wei Liu <si-wei.liu@oracle.com>

When feature VIRTIO_NET_F_MTU is negotiated on mlx5_vdpa,
22 extra bytes worth of MTU length is shown in guest.
This is because the mlx5_query_port_max_mtu API returns
the "hardware" MTU value, which does not just contain the
 Ethernet payload, but includes extra lengths starting
from the Ethernet header up to the FCS altogether.

Fix the MTU so packets won't get dropped silently.

Fixes: 1a86b377aa21 ("vdpa/mlx5: Add VDPA driver for supported mlx5 devices")
Signed-off-by: Si-Wei Liu <si-wei.liu@oracle.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Eli Cohen <elic@nvidia.com>
---
 drivers/vdpa/mlx5/core/mlx5_vdpa.h |  4 +++
 drivers/vdpa/mlx5/net/mlx5_vnet.c  | 42 +++++++++++++++++++++---------
 2 files changed, 34 insertions(+), 12 deletions(-)

diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index 08f742fd2409..b6cc53ba980c 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -4,9 +4,13 @@
 #ifndef __MLX5_VDPA_H__
 #define __MLX5_VDPA_H__
 
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
 #include <linux/vdpa.h>
 #include <linux/mlx5/driver.h>
 
+#define MLX5V_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)
+
 struct mlx5_vdpa_direct_mr {
 	u64 start;
 	u64 end;
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index c342cc9355e8..56d463d2be85 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -1526,17 +1526,8 @@ 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) |
-				     BIT_ULL(VIRTIO_NET_F_MAC);
-	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)
@@ -1834,7 +1825,6 @@ 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;
 	}
@@ -1990,6 +1980,33 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = {
 	.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) |
+				       BIT_ULL(VIRTIO_NET_F_MAC);
+	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;
+	int err;
+
+	err = mlx5_query_nic_vport_mtu(mdev, &hw_mtu);
+	if (err)
+		return err;
+
+	*mtu = hw_mtu - MLX5V_ETH_HARD_MTU;
+	return 0;
+}
+
 static int alloc_resources(struct mlx5_vdpa_net *ndev)
 {
 	struct mlx5_vdpa_net_resources *res = &ndev->res;
@@ -2084,7 +2101,8 @@ 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;
-	err = mlx5_query_nic_vport_mtu(mdev, &ndev->mtu);
+	query_virtio_features(ndev);
+	err = query_mtu(mdev, &ndev->mtu);
 	if (err)
 		goto err_mtu;
 
-- 
2.26.2

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization

  parent reply	other threads:[~2021-04-06 17:05 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-06 17:04 [PATCH linux-next v2 00/14] vdpa: Enable user to set mac address, mtu Parav Pandit
2021-04-06 17:04 ` [PATCH linux-next v2 01/14] vdpa: Follow kdoc comment style Parav Pandit
2021-04-07  3:08   ` Jason Wang
2021-04-06 17:04 ` [PATCH linux-next v2 02/14] " Parav Pandit
2021-04-07  3:09   ` Jason Wang
2021-04-06 17:04 ` [PATCH linux-next v2 03/14] vdpa: Introduce and use vdpa device get, set config, features helpers Parav Pandit
2021-04-07  3:18   ` [PATCH linux-next v2 03/14] vdpa: Introduce and use vdpa device get,set " Jason Wang
2021-04-07  3:52     ` Parav Pandit
2021-04-06 17:04 ` [PATCH linux-next v2 04/14] vdpa: Introduce query of device config layout Parav Pandit
2021-04-07  3:56   ` Jason Wang
2021-04-07  5:10     ` Parav Pandit
2021-04-07  7:12       ` Jason Wang
2021-04-08  6:23         ` Parav Pandit
2021-04-06 17:04 ` [PATCH linux-next v2 05/14] vdpa: Enable user to set mac and mtu of vdpa device Parav Pandit
2021-04-07  3:59   ` Jason Wang
2021-04-06 17:04 ` [PATCH linux-next v2 06/14] vdpa_sim_net: Enable user to set mac address and mtu Parav Pandit
2021-04-06 17:04 ` [PATCH linux-next v2 07/14] vdpa/mlx5: Use the correct dma device when registering memory Parav Pandit
2021-04-07  4:00   ` Jason Wang
2021-04-06 17:04 ` [PATCH linux-next v2 08/14] vdpa/mlx5: Retrieve BAR address suitable any function Parav Pandit
2021-04-07  5:32   ` Jason Wang
2021-04-06 17:04 ` [PATCH linux-next v2 09/14] vdpa/mlx5: Enable user to add/delete vdpa device Parav Pandit
2021-04-06 17:04 ` [PATCH linux-next v2 10/14] vdpa/mlx5: Support configuration of MAC Parav Pandit
2021-04-07  7:21   ` Jason Wang
2021-04-06 17:04 ` [PATCH linux-next v2 11/14] vdpa/mlx5: Forward only packets with allowed MAC address Parav Pandit
2021-04-06 17:04 ` Parav Pandit [this message]
2021-04-06 17:04 ` [PATCH linux-next v2 13/14] vdpa/mlx5: Fix suspend/resume index restoration Parav Pandit
2021-04-07  7:25   ` Jason Wang
     [not found]     ` <20210407101612.GB207753@mtl-vdi-166.wap.labs.mlnx>
2021-04-07 13:38       ` Michael S. Tsirkin
2021-04-06 17:04 ` [PATCH linux-next v2 14/14] vdpa/mlx5: Fix wrong use of bit numbers Parav Pandit
2021-04-07  7:25   ` Jason Wang
2021-04-07  7:28     ` Parav Pandit
2021-04-07  7:28 ` [PATCH linux-next v2 00/14] vdpa: Enable user to set mac address, mtu Jason Wang
2021-04-08  3:45   ` Parav Pandit

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210406170457.98481-13-parav@nvidia.com \
    --to=parav@nvidia.com \
    --cc=elic@nvidia.com \
    --cc=mst@redhat.com \
    --cc=si-wei.liu@oracle.com \
    --cc=virtualization@lists.linux-foundation.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).