netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Tariq Toukan <tariqt@nvidia.com>
To: Eric Dumazet <edumazet@google.com>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	Andrew Lunn <andrew+netdev@lunn.ch>,
	"David S. Miller" <davem@davemloft.net>
Cc: Saeed Mahameed <saeed@kernel.org>, Gal Pressman <gal@nvidia.com>,
	"Leon Romanovsky" <leon@kernel.org>,
	Saeed Mahameed <saeedm@nvidia.com>,
	"Tariq Toukan" <tariqt@nvidia.com>,
	Mark Bloch <mbloch@nvidia.com>, <netdev@vger.kernel.org>,
	<linux-rdma@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
	Alexandre Cassen <acassen@corp.free.fr>,
	"Leon Romanovsky" <leonro@nvidia.com>
Subject: [PATCH net-next V2 1/2] net/mlx5e: Support routed networks during IPsec MACs initialization
Date: Tue, 22 Jul 2025 17:23:47 +0300	[thread overview]
Message-ID: <1753194228-333722-2-git-send-email-tariqt@nvidia.com> (raw)
In-Reply-To: <1753194228-333722-1-git-send-email-tariqt@nvidia.com>

From: Alexandre Cassen <acassen@corp.free.fr>

Remote IPsec tunnel endpoint may refer to a network segment that is
not directly connected to the host. In such a case, IPsec tunnel
endpoints are connected to a router and reachable via a routing path.
In IPsec packet offload mode, HW is initialized with the MAC address
of both IPsec tunnel endpoints.

Extend the current IPsec init MACs procedure to resolve nexthop for
routed networks. Direct neighbour lookup and probe is still used
for directly connected networks and as a fallback mechanism if fib
lookup fails.

Signed-off-by: Alexandre Cassen <acassen@corp.free.fr>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ipsec.c       | 82 ++++++++++++++++++-
 1 file changed, 80 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 77f61cd28a79..00e77c71e201 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -36,6 +36,7 @@
 #include <linux/inetdevice.h>
 #include <linux/netdevice.h>
 #include <net/netevent.h>
+#include <net/ipv6_stubs.h>
 
 #include "en.h"
 #include "eswitch.h"
@@ -259,9 +260,15 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 				  struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
 	struct mlx5_core_dev *mdev = mlx5e_ipsec_sa2dev(sa_entry);
+	struct mlx5e_ipsec_addr *addrs = &attrs->addrs;
 	struct net_device *netdev = sa_entry->dev;
+	struct xfrm_state *x = sa_entry->x;
+	struct dst_entry *rt_dst_entry;
+	struct flowi4 fl4 = {};
+	struct flowi6 fl6 = {};
 	struct neighbour *n;
 	u8 addr[ETH_ALEN];
+	struct rtable *rt;
 	const void *pkey;
 	u8 *dst, *src;
 
@@ -274,18 +281,89 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	case XFRM_DEV_OFFLOAD_IN:
 		src = attrs->dmac;
 		dst = attrs->smac;
-		pkey = &attrs->addrs.saddr.a4;
+
+		switch (addrs->family) {
+		case AF_INET:
+			fl4.flowi4_proto = x->sel.proto;
+			fl4.daddr = addrs->saddr.a4;
+			fl4.saddr = addrs->daddr.a4;
+			pkey = &addrs->saddr.a4;
+			break;
+		case AF_INET6:
+			fl6.flowi6_proto = x->sel.proto;
+			memcpy(fl6.daddr.s6_addr32, addrs->saddr.a6, 16);
+			memcpy(fl6.saddr.s6_addr32, addrs->daddr.a6, 16);
+			pkey = &addrs->saddr.a6;
+			break;
+		default:
+			return;
+		}
 		break;
 	case XFRM_DEV_OFFLOAD_OUT:
 		src = attrs->smac;
 		dst = attrs->dmac;
-		pkey = &attrs->addrs.daddr.a4;
+		switch (addrs->family) {
+		case AF_INET:
+			fl4.flowi4_proto = x->sel.proto;
+			fl4.daddr = addrs->daddr.a4;
+			fl4.saddr = addrs->saddr.a4;
+			pkey = &addrs->daddr.a4;
+			break;
+		case AF_INET6:
+			fl6.flowi6_proto = x->sel.proto;
+			memcpy(fl6.daddr.s6_addr32, addrs->daddr.a6, 16);
+			memcpy(fl6.saddr.s6_addr32, addrs->saddr.a6, 16);
+			pkey = &addrs->daddr.a6;
+			break;
+		default:
+			return;
+		}
 		break;
 	default:
 		return;
 	}
 
 	ether_addr_copy(src, addr);
+
+	/* Destination can refer to a routed network, so perform FIB lookup
+	 * to resolve nexthop and get its MAC. Neighbour resolution is used as
+	 * fallback.
+	 */
+	switch (addrs->family) {
+	case AF_INET:
+		rt = ip_route_output_key(dev_net(netdev), &fl4);
+		if (IS_ERR(rt))
+			goto neigh;
+
+		if (rt->rt_type != RTN_UNICAST) {
+			ip_rt_put(rt);
+			goto neigh;
+		}
+		rt_dst_entry = &rt->dst;
+		break;
+	case AF_INET6:
+		rt_dst_entry = ipv6_stub->ipv6_dst_lookup_flow(
+			dev_net(netdev), NULL, &fl6, NULL);
+		if (IS_ERR(rt_dst_entry))
+			goto neigh;
+		break;
+	default:
+		return;
+	}
+
+	n = dst_neigh_lookup(rt_dst_entry, pkey);
+	if (!n) {
+		dst_release(rt_dst_entry);
+		goto neigh;
+	}
+
+	neigh_ha_snapshot(addr, n, netdev);
+	ether_addr_copy(dst, addr);
+	dst_release(rt_dst_entry);
+	neigh_release(n);
+	return;
+
+neigh:
 	n = neigh_lookup(&arp_tbl, pkey, netdev);
 	if (!n) {
 		n = neigh_create(&arp_tbl, pkey, netdev);
-- 
2.31.1


  reply	other threads:[~2025-07-22 14:24 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-07-22 14:23 [PATCH net-next V2 0/2] net/mlx5e: misc changes 2025-07-22 Tariq Toukan
2025-07-22 14:23 ` Tariq Toukan [this message]
2025-07-23  6:52   ` [PATCH net-next V2 1/2] net/mlx5e: Support routed networks during IPsec MACs initialization Michal Swiatkowski
2025-07-23  7:10     ` Leon Romanovsky
2025-07-22 14:23 ` [PATCH net-next V2 2/2] net/mlx5e: Expose TIS via devlink tx reporter diagnose Tariq Toukan
2025-07-23  6:56   ` Michal Swiatkowski
2025-07-25 23:26 ` [PATCH net-next V2 0/2] net/mlx5e: misc changes 2025-07-22 patchwork-bot+netdevbpf

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=1753194228-333722-2-git-send-email-tariqt@nvidia.com \
    --to=tariqt@nvidia.com \
    --cc=acassen@corp.free.fr \
    --cc=andrew+netdev@lunn.ch \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=gal@nvidia.com \
    --cc=kuba@kernel.org \
    --cc=leon@kernel.org \
    --cc=leonro@nvidia.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=mbloch@nvidia.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=saeed@kernel.org \
    --cc=saeedm@nvidia.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;
as well as URLs for NNTP newsgroup(s).