From: Saeed Mahameed <saeedm@mellanox.com>
To: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org, Or Gerlitz <ogerlitz@mellanox.com>,
Saeed Mahameed <saeedm@mellanox.com>
Subject: [net-next 06/12] net/mlx5e: Support SRIOV TC encapsulation offloads for IPv6 tunnels
Date: Tue, 24 Jan 2017 22:16:46 +0200 [thread overview]
Message-ID: <20170124201652.2920-7-saeedm@mellanox.com> (raw)
In-Reply-To: <20170124201652.2920-1-saeedm@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Add the missing parts for offloading IPv6 tunnels. This includes
route and neigh lookups and construnction of the IPv6 tunnel headers.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Hadar Hen Zion <hadarh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 159 ++++++++++++++++++++++--
1 file changed, 151 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 3d0dbfb018ca..640f10f2e994 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -718,6 +718,47 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
return 0;
}
+static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
+ struct net_device *mirred_dev,
+ struct net_device **out_dev,
+ struct flowi6 *fl6,
+ struct neighbour **out_n,
+ int *out_ttl)
+{
+ struct neighbour *n = NULL;
+ struct dst_entry *dst;
+
+#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
+ struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+ int ret;
+
+ dst = ip6_route_output(dev_net(mirred_dev), NULL, fl6);
+ if (dst->error) {
+ ret = dst->error;
+ dst_release(dst);
+ return ret;
+ }
+
+ *out_ttl = ip6_dst_hoplimit(dst);
+
+ /* if the egress device isn't on the same HW e-switch, we use the uplink */
+ if (!switchdev_port_same_parent_id(priv->netdev, dst->dev))
+ *out_dev = mlx5_eswitch_get_uplink_netdev(esw);
+ else
+ *out_dev = dst->dev;
+#else
+ return -EOPNOTSUPP;
+#endif
+
+ n = dst_neigh_lookup(dst, &fl6->daddr);
+ dst_release(dst);
+ if (!n)
+ return -ENOMEM;
+
+ *out_n = n;
+ return 0;
+}
+
static int gen_vxlan_header_ipv4(struct net_device *out_dev,
char buf[],
unsigned char h_dest[ETH_ALEN],
@@ -754,6 +795,41 @@ static int gen_vxlan_header_ipv4(struct net_device *out_dev,
return encap_size;
}
+static int gen_vxlan_header_ipv6(struct net_device *out_dev,
+ char buf[],
+ unsigned char h_dest[ETH_ALEN],
+ int ttl,
+ struct in6_addr *daddr,
+ struct in6_addr *saddr,
+ __be16 udp_dst_port,
+ __be32 vx_vni)
+{
+ int encap_size = VXLAN_HLEN + sizeof(struct ipv6hdr) + ETH_HLEN;
+ struct ethhdr *eth = (struct ethhdr *)buf;
+ struct ipv6hdr *ip6h = (struct ipv6hdr *)((char *)eth + sizeof(struct ethhdr));
+ struct udphdr *udp = (struct udphdr *)((char *)ip6h + sizeof(struct ipv6hdr));
+ struct vxlanhdr *vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr));
+
+ memset(buf, 0, encap_size);
+
+ ether_addr_copy(eth->h_dest, h_dest);
+ ether_addr_copy(eth->h_source, out_dev->dev_addr);
+ eth->h_proto = htons(ETH_P_IPV6);
+
+ ip6_flow_hdr(ip6h, 0, 0);
+ /* the HW fills up ipv6 payload len */
+ ip6h->nexthdr = IPPROTO_UDP;
+ ip6h->hop_limit = ttl;
+ ip6h->daddr = *daddr;
+ ip6h->saddr = *saddr;
+
+ udp->dest = udp_dst_port;
+ vxh->vx_flags = VXLAN_HF_VNI;
+ vxh->vx_vni = vxlan_vni_field(vx_vni);
+
+ return encap_size;
+}
+
static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
struct net_device *mirred_dev,
struct mlx5_encap_entry *e,
@@ -821,6 +897,75 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
return err;
}
+static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
+ struct net_device *mirred_dev,
+ struct mlx5_encap_entry *e,
+ struct net_device **out_dev)
+
+{
+ int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
+ struct ip_tunnel_key *tun_key = &e->tun_info.key;
+ int encap_size, err, ttl = 0;
+ struct neighbour *n = NULL;
+ struct flowi6 fl6 = {};
+ char *encap_header;
+
+ encap_header = kzalloc(max_encap_size, GFP_KERNEL);
+ if (!encap_header)
+ return -ENOMEM;
+
+ switch (e->tunnel_type) {
+ case MLX5_HEADER_TYPE_VXLAN:
+ fl6.flowi6_proto = IPPROTO_UDP;
+ fl6.fl6_dport = tun_key->tp_dst;
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+
+ fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
+ fl6.daddr = tun_key->u.ipv6.dst;
+ fl6.saddr = tun_key->u.ipv6.src;
+
+ err = mlx5e_route_lookup_ipv6(priv, mirred_dev, out_dev,
+ &fl6, &n, &ttl);
+ if (err)
+ goto out;
+
+ if (!(n->nud_state & NUD_VALID)) {
+ pr_warn("%s: can't offload, neighbour to %pI6 invalid\n", __func__, &fl6.daddr);
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+
+ e->n = n;
+ e->out_dev = *out_dev;
+
+ neigh_ha_snapshot(e->h_dest, n, *out_dev);
+
+ switch (e->tunnel_type) {
+ case MLX5_HEADER_TYPE_VXLAN:
+ encap_size = gen_vxlan_header_ipv6(*out_dev, encap_header,
+ e->h_dest, ttl,
+ &fl6.daddr,
+ &fl6.saddr, tun_key->tp_dst,
+ tunnel_id_to_key32(tun_key->tun_id));
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+
+ err = mlx5_encap_alloc(priv->mdev, e->tunnel_type,
+ encap_size, encap_header, &e->encap_id);
+out:
+ if (err && n)
+ neigh_release(n);
+ kfree(encap_header);
+ return err;
+}
+
static int mlx5e_attach_encap(struct mlx5e_priv *priv,
struct ip_tunnel_info *tun_info,
struct net_device *mirred_dev,
@@ -831,7 +976,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
struct ip_tunnel_key *key = &tun_info->key;
struct mlx5_encap_entry *e;
struct net_device *out_dev;
- int tunnel_type, err;
+ int tunnel_type, err = -EOPNOTSUPP;
uintptr_t hash_key;
bool found = false;
@@ -856,12 +1001,6 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
return -EOPNOTSUPP;
}
- if (family == AF_INET6) {
- netdev_warn(priv->netdev,
- "IPv6 tunnel encap offload isn't supported\n");
- return -EOPNOTSUPP;
- }
-
hash_key = hash_encap_info(key);
hash_for_each_possible_rcu(esw->offloads.encap_tbl, e,
@@ -885,7 +1024,11 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
e->tunnel_type = tunnel_type;
INIT_LIST_HEAD(&e->flows);
- err = mlx5e_create_encap_header_ipv4(priv, mirred_dev, e, &out_dev);
+ if (family == AF_INET)
+ err = mlx5e_create_encap_header_ipv4(priv, mirred_dev, e, &out_dev);
+ else if (family == AF_INET6)
+ err = mlx5e_create_encap_header_ipv6(priv, mirred_dev, e, &out_dev);
+
if (err)
goto out_err;
--
2.11.0
next prev parent reply other threads:[~2017-01-24 20:17 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-01-24 20:16 [pull request][net-next 00/12] Mellanox mlx5 updates 2017-01-24 Saeed Mahameed
2017-01-24 20:16 ` [net-next 01/12] net/mlx5: Use exact encap header size for the FW input buffer Saeed Mahameed
2017-01-24 20:16 ` [net-next 02/12] net/mlx5e: Add TC offloads matching on IPv6 encapsulation headers Saeed Mahameed
2017-01-24 20:16 ` [net-next 03/12] net/mlx5e: TC ipv4 tunnel encap offload cosmetic changes Saeed Mahameed
2017-01-24 20:16 ` [net-next 04/12] net/mlx5e: Use the full tunnel key info for encapsulation offload house-keeping Saeed Mahameed
2017-01-24 20:16 ` [net-next 05/12] net/mlx5e: Maximize ip tunnel key usage on the TC offloading path Saeed Mahameed
2017-01-24 20:16 ` Saeed Mahameed [this message]
2017-01-24 20:16 ` [net-next 07/12] net/mlx5: E-Switch, Enlarge the FDB size for the switchdev mode Saeed Mahameed
2017-01-24 20:16 ` [net-next 08/12] net/mlx5: Add support for setting VF min rate Saeed Mahameed
2017-01-24 20:16 ` [net-next 09/12] net/mlx5: Push min-inline mode resolution helper into the core Saeed Mahameed
2017-01-24 20:16 ` [net-next 10/12] IB/mlx5: Enable Eth VFs to query their min-inline value for user-space Saeed Mahameed
2017-01-24 20:16 ` [net-next 11/12] net/mlx5e: Reduce memory consumption on kdump kernel Saeed Mahameed
2017-01-24 20:16 ` [net-next 12/12] net/mlx5e: CQE compression control code reuse Saeed Mahameed
2017-01-25 17:52 ` [pull request][net-next 00/12] Mellanox mlx5 updates 2017-01-24 David Miller
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=20170124201652.2920-7-saeedm@mellanox.com \
--to=saeedm@mellanox.com \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.org \
--cc=ogerlitz@mellanox.com \
/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