From: Bob Pearson <rpearsonhpe@gmail.com>
To: jgg@nvidia.com, yanjun.zhu@linux.dev, linux-rdma@vger.kernel.org,
netdev@vger.kernel.org, dsahern@kernel.org,
rain.1986.08.12@gmail.com
Cc: Bob Pearson <rpearsonhpe@gmail.com>
Subject: [PATCH for-next v6 3/7] RDMA/rxe: Register IP mcast address
Date: Thu, 7 Dec 2023 13:29:04 -0600 [thread overview]
Message-ID: <20231207192907.10113-4-rpearsonhpe@gmail.com> (raw)
In-Reply-To: <20231207192907.10113-1-rpearsonhpe@gmail.com>
Currently the rdma_rxe driver does not receive mcast packets at all.
Add code to rxe_mcast_add() and rxe_mcast_del() to register/deregister
the IP mcast address. This is required for mcast traffic to reach the
rxe driver when coming from an external source.
Fixes: 8700e3e7c485 ("Soft RoCE driver")
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
---
drivers/infiniband/sw/rxe/rxe_mcast.c | 119 +++++++++++++++++++++-----
drivers/infiniband/sw/rxe/rxe_net.c | 2 +-
drivers/infiniband/sw/rxe/rxe_net.h | 1 +
drivers/infiniband/sw/rxe/rxe_verbs.h | 1 +
4 files changed, 102 insertions(+), 21 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_mcast.c b/drivers/infiniband/sw/rxe/rxe_mcast.c
index 86cc2e18a7fd..5236761892dd 100644
--- a/drivers/infiniband/sw/rxe/rxe_mcast.c
+++ b/drivers/infiniband/sw/rxe/rxe_mcast.c
@@ -19,38 +19,116 @@
* mcast packets in the rxe receive path.
*/
+#include <linux/igmp.h>
+
#include "rxe.h"
-/**
- * rxe_mcast_add - add multicast address to rxe device
- * @rxe: rxe device object
- * @mgid: multicast address as a gid
- *
- * Returns 0 on success else an error
- */
-static int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid)
+static int rxe_mcast_add6(struct rxe_dev *rxe, union ib_gid *mgid)
{
+ struct in6_addr *addr6 = (struct in6_addr *)mgid;
+ struct sock *sk = recv_sockets.sk6->sk;
unsigned char ll_addr[ETH_ALEN];
+ int err;
+
+ lock_sock(sk);
+ rtnl_lock();
+ err = ipv6_sock_mc_join(sk, rxe->ndev->ifindex, addr6);
+ rtnl_unlock();
+ release_sock(sk);
+ if (err && err != -EADDRINUSE)
+ goto err_out;
ipv6_eth_mc_map((struct in6_addr *)mgid->raw, ll_addr);
+ err = dev_mc_add(rxe->ndev, ll_addr);
+ if (err)
+ goto err_drop;
+
+ return 0;
- return dev_mc_add(rxe->ndev, ll_addr);
+err_drop:
+ lock_sock(sk);
+ rtnl_lock();
+ ipv6_sock_mc_drop(sk, rxe->ndev->ifindex, addr6);
+ rtnl_unlock();
+ release_sock(sk);
+err_out:
+ return err;
}
-/**
- * rxe_mcast_del - delete multicast address from rxe device
- * @rxe: rxe device object
- * @mgid: multicast address as a gid
- *
- * Returns 0 on success else an error
- */
-static int rxe_mcast_del(struct rxe_dev *rxe, union ib_gid *mgid)
+static int rxe_mcast_add(struct rxe_mcg *mcg)
{
+ struct rxe_dev *rxe = mcg->rxe;
+ union ib_gid *mgid = &mcg->mgid;
unsigned char ll_addr[ETH_ALEN];
+ struct ip_mreqn imr = {};
+ int err;
+
+ if (mcg->is_ipv6)
+ return rxe_mcast_add6(rxe, mgid);
+
+ imr.imr_multiaddr = *(struct in_addr *)(mgid->raw + 12);
+ imr.imr_ifindex = rxe->ndev->ifindex;
+ rtnl_lock();
+ err = ip_mc_join_group(recv_sockets.sk4->sk, &imr);
+ rtnl_unlock();
+ if (err && err != -EADDRINUSE)
+ goto err_out;
+
+ ip_eth_mc_map(imr.imr_multiaddr.s_addr, ll_addr);
+ err = dev_mc_add(rxe->ndev, ll_addr);
+ if (err)
+ goto err_leave;
+
+ return 0;
+
+err_leave:
+ rtnl_lock();
+ ip_mc_leave_group(recv_sockets.sk4->sk, &imr);
+ rtnl_unlock();
+err_out:
+ return err;
+}
+
+static int rxe_mcast_del6(struct rxe_dev *rxe, union ib_gid *mgid)
+{
+ struct sock *sk = recv_sockets.sk6->sk;
+ unsigned char ll_addr[ETH_ALEN];
+ int err, err2;
ipv6_eth_mc_map((struct in6_addr *)mgid->raw, ll_addr);
+ err = dev_mc_del(rxe->ndev, ll_addr);
+
+ lock_sock(sk);
+ rtnl_lock();
+ err2 = ipv6_sock_mc_drop(sk, rxe->ndev->ifindex,
+ (struct in6_addr *)mgid);
+ rtnl_unlock();
+ release_sock(sk);
+
+ return err ?: err2;
+}
+
+static int rxe_mcast_del(struct rxe_mcg *mcg)
+{
+ struct rxe_dev *rxe = mcg->rxe;
+ union ib_gid *mgid = &mcg->mgid;
+ unsigned char ll_addr[ETH_ALEN];
+ struct ip_mreqn imr = {};
+ int err, err2;
+
+ if (mcg->is_ipv6)
+ return rxe_mcast_del6(rxe, mgid);
+
+ imr.imr_multiaddr = *(struct in_addr *)(mgid->raw + 12);
+ imr.imr_ifindex = rxe->ndev->ifindex;
+ ip_eth_mc_map(imr.imr_multiaddr.s_addr, ll_addr);
+ err = dev_mc_del(rxe->ndev, ll_addr);
+
+ rtnl_lock();
+ err2 = ip_mc_leave_group(recv_sockets.sk4->sk, &imr);
+ rtnl_unlock();
- return dev_mc_del(rxe->ndev, ll_addr);
+ return err ?: err2;
}
/**
@@ -164,6 +242,7 @@ static void __rxe_init_mcg(struct rxe_dev *rxe, union ib_gid *mgid,
{
kref_init(&mcg->ref_cnt);
memcpy(&mcg->mgid, mgid, sizeof(mcg->mgid));
+ mcg->is_ipv6 = !ipv6_addr_v4mapped((struct in6_addr *)mgid);
INIT_LIST_HEAD(&mcg->qp_list);
mcg->rxe = rxe;
@@ -225,7 +304,7 @@ static struct rxe_mcg *rxe_get_mcg(struct rxe_dev *rxe, union ib_gid *mgid)
spin_unlock_bh(&rxe->mcg_lock);
/* add mcast address outside of lock */
- err = rxe_mcast_add(rxe, mgid);
+ err = rxe_mcast_add(mcg);
if (!err)
return mcg;
@@ -273,7 +352,7 @@ static void __rxe_destroy_mcg(struct rxe_mcg *mcg)
static void rxe_destroy_mcg(struct rxe_mcg *mcg)
{
/* delete mcast address outside of lock */
- rxe_mcast_del(mcg->rxe, &mcg->mgid);
+ rxe_mcast_del(mcg);
spin_lock_bh(&mcg->rxe->mcg_lock);
__rxe_destroy_mcg(mcg);
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 58c3f3759bf0..b481f8da2002 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -18,7 +18,7 @@
#include "rxe_net.h"
#include "rxe_loc.h"
-static struct rxe_recv_sockets recv_sockets;
+struct rxe_recv_sockets recv_sockets;
static struct dst_entry *rxe_find_route4(struct rxe_qp *qp,
struct net_device *ndev,
diff --git a/drivers/infiniband/sw/rxe/rxe_net.h b/drivers/infiniband/sw/rxe/rxe_net.h
index 45d80d00f86b..89cee7d5340f 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.h
+++ b/drivers/infiniband/sw/rxe/rxe_net.h
@@ -15,6 +15,7 @@ struct rxe_recv_sockets {
struct socket *sk4;
struct socket *sk6;
};
+extern struct rxe_recv_sockets recv_sockets;
int rxe_net_add(const char *ibdev_name, struct net_device *ndev);
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index ccb9d19ffe8a..7be9e6232dd9 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -352,6 +352,7 @@ struct rxe_mcg {
atomic_t qp_num;
u32 qkey;
u16 pkey;
+ bool is_ipv6;
};
struct rxe_mca {
--
2.40.1
next prev parent reply other threads:[~2023-12-07 19:30 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-12-07 19:29 [PATCH for-next v6 0/7] RDMA/rxe: Make multicast work Bob Pearson
2023-12-07 19:29 ` [PATCH for-next v6 1/7] RDMA/rxe: Cleanup rxe_ah/av_chk_attr Bob Pearson
2023-12-07 19:29 ` [PATCH for-next v6 2/7] RDMA/rxe: Fix sending of mcast packets Bob Pearson
2023-12-07 19:29 ` Bob Pearson [this message]
2023-12-08 13:52 ` [PATCH for-next v6 3/7] RDMA/rxe: Register IP mcast address Zhu Yanjun
2023-12-08 15:51 ` David Ahern
2023-12-08 15:50 ` David Ahern
2023-12-09 11:32 ` Zhu Yanjun
2023-12-11 0:56 ` Bob Pearson
2023-12-11 2:01 ` David Ahern
2023-12-07 19:29 ` [PATCH for-next v6 4/7] RDMA/rxe: Let rxe_lookup_mcg use rcu_read_lock Bob Pearson
2023-12-07 19:29 ` [PATCH for-next v6 5/7] RDMA/rxe: Split multicast lock Bob Pearson
2023-12-07 19:29 ` [PATCH for-next v6 6/7] RDMA/rxe: Cleanup mcg lifetime Bob Pearson
2023-12-07 19:29 ` [PATCH for-next v6 7/7] RDMA/rxe: Add module parameters for mcast limits Bob Pearson
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=20231207192907.10113-4-rpearsonhpe@gmail.com \
--to=rpearsonhpe@gmail.com \
--cc=dsahern@kernel.org \
--cc=jgg@nvidia.com \
--cc=linux-rdma@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=rain.1986.08.12@gmail.com \
--cc=yanjun.zhu@linux.dev \
/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).