diff mbox series

[v6,5/8] RDMA/rxe: Replace global variable with sock lookup functions

Message ID 20230623095749.485873-6-yanjun.zhu@intel.com (mailing list archive)
State Superseded
Headers show
Series Fix the problem that rxe can not work in net namespace | expand

Commit Message

Zhu Yanjun June 23, 2023, 9:57 a.m. UTC 
From: Zhu Yanjun <yanjun.zhu@linux.dev>

Originally a global variable is to keep the sock of udp listening
on port 4791. In fact, sock lookup functions can be used to get
the sock.

Tested-by: Rain River <rain.1986.08.12@gmail.com>
Signed-off-by: Zhu Yanjun <yanjun.zhu@linux.dev>
---
 drivers/infiniband/sw/rxe/rxe.c       |  1 +
 drivers/infiniband/sw/rxe/rxe_net.c   | 58 ++++++++++++++++++++-------
 drivers/infiniband/sw/rxe/rxe_net.h   |  5 ---
 drivers/infiniband/sw/rxe/rxe_verbs.h |  1 +
 4 files changed, 45 insertions(+), 20 deletions(-)
diff mbox series

Patch

diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index ac7e7b0a9dc9..c9b3125b26d0 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -74,6 +74,7 @@  static void rxe_init_device_param(struct rxe_dev *rxe)
 			rxe->ndev->dev_addr);
 
 	rxe->max_ucontext			= RXE_MAX_UCONTEXT;
+	rxe->l_sk6				= NULL;
 }
 
 /* initialize port attributes */
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 3c58764339a0..85ca842f3bad 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -18,8 +18,6 @@ 
 #include "rxe_net.h"
 #include "rxe_loc.h"
 
-static struct rxe_recv_sockets recv_sockets;
-
 static struct dst_entry *rxe_find_route4(struct rxe_qp *qp,
 					 struct net_device *ndev,
 					 struct in_addr *saddr,
@@ -51,6 +49,23 @@  static struct dst_entry *rxe_find_route6(struct rxe_qp *qp,
 {
 	struct dst_entry *ndst;
 	struct flowi6 fl6 = { { 0 } };
+	struct rxe_dev *rxe;
+
+	rxe = rxe_get_dev_from_net(ndev);
+	if (!rxe->l_sk6) {
+		struct sock *sk;
+
+		rcu_read_lock();
+		sk = udp6_lib_lookup(&init_net, NULL, 0, &in6addr_any, htons(ROCE_V2_UDP_DPORT), 0);
+		rcu_read_unlock();
+		if (!sk) {
+			rxe_dbg_qp(qp, "file: %s +%d, error\n", __FILE__, __LINE__);
+			return (struct dst_entry *)sk;
+		}
+		__sock_put(sk);
+		rxe->l_sk6 = sk->sk_socket;
+	}
+
 
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_oif = ndev->ifindex;
@@ -58,8 +73,8 @@  static struct dst_entry *rxe_find_route6(struct rxe_qp *qp,
 	memcpy(&fl6.daddr, daddr, sizeof(*daddr));
 	fl6.flowi6_proto = IPPROTO_UDP;
 
-	ndst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(recv_sockets.sk6->sk),
-					       recv_sockets.sk6->sk, &fl6,
+	ndst = ipv6_stub->ipv6_dst_lookup_flow(dev_net(ndev),
+					       rxe->l_sk6->sk, &fl6,
 					       NULL);
 	if (IS_ERR(ndst)) {
 		rxe_dbg_qp(qp, "no route to %pI6\n", daddr);
@@ -537,15 +552,33 @@  int rxe_net_add(const char *ibdev_name, struct net_device *ndev)
 #define SK_REF_FOR_TUNNEL	2
 void rxe_net_del(struct ib_device *dev)
 {
-	if (refcount_read(&recv_sockets.sk6->sk->sk_refcnt) > SK_REF_FOR_TUNNEL)
-		__sock_put(recv_sockets.sk6->sk);
+	struct sock *sk;
+
+	rcu_read_lock();
+	sk = udp4_lib_lookup(&init_net, 0, 0, htonl(INADDR_ANY), htons(ROCE_V2_UDP_DPORT), 0);
+	rcu_read_unlock();
+	if (!sk)
+		return;
+
+	__sock_put(sk);
+
+	if (refcount_read(&sk->sk_refcnt) > SK_REF_FOR_TUNNEL)
+		__sock_put(sk);
 	else
-		rxe_release_udp_tunnel(recv_sockets.sk6);
+		rxe_release_udp_tunnel(sk->sk_socket);
+
+	rcu_read_lock();
+	sk = udp6_lib_lookup(&init_net, NULL, 0, &in6addr_any, htons(ROCE_V2_UDP_DPORT), 0);
+	rcu_read_unlock();
+	if (!sk)
+		return;
+
+	__sock_put(sk);
 
-	if (refcount_read(&recv_sockets.sk4->sk->sk_refcnt) > SK_REF_FOR_TUNNEL)
-		__sock_put(recv_sockets.sk4->sk);
+	if (refcount_read(&sk->sk_refcnt) > SK_REF_FOR_TUNNEL)
+		__sock_put(sk);
 	else
-		rxe_release_udp_tunnel(recv_sockets.sk4);
+		rxe_release_udp_tunnel(sk->sk_socket);
 }
 #undef SK_REF_FOR_TUNNEL
 
@@ -655,10 +688,8 @@  static int rxe_net_ipv4_init(void)
 	sock = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), false);
 	if (IS_ERR(sock)) {
 		pr_err("Failed to create IPv4 UDP tunnel\n");
-		recv_sockets.sk4 = NULL;
 		return -1;
 	}
-	recv_sockets.sk4 = sock;
 
 	return 0;
 }
@@ -678,17 +709,14 @@  static int rxe_net_ipv6_init(void)
 
 	sock = rxe_setup_udp_tunnel(&init_net, htons(ROCE_V2_UDP_DPORT), true);
 	if (PTR_ERR(sock) == -EAFNOSUPPORT) {
-		recv_sockets.sk6 = NULL;
 		pr_warn("IPv6 is not supported, can not create a UDPv6 socket\n");
 		return 0;
 	}
 
 	if (IS_ERR(sock)) {
-		recv_sockets.sk6 = NULL;
 		pr_err("Failed to create IPv6 UDP tunnel\n");
 		return -1;
 	}
-	recv_sockets.sk6 = sock;
 #endif
 	return 0;
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_net.h b/drivers/infiniband/sw/rxe/rxe_net.h
index f48f22f3353b..027b20e1bab6 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.h
+++ b/drivers/infiniband/sw/rxe/rxe_net.h
@@ -11,11 +11,6 @@ 
 #include <net/if_inet6.h>
 #include <linux/module.h>
 
-struct rxe_recv_sockets {
-	struct socket *sk4;
-	struct socket *sk6;
-};
-
 int rxe_net_add(const char *ibdev_name, struct net_device *ndev);
 void rxe_net_del(struct ib_device *dev);
 
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index 26a20f088692..0aa3817770a5 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -382,6 +382,7 @@  struct rxe_dev {
 
 	struct rxe_port		port;
 	struct crypto_shash	*tfm;
+	struct socket		*l_sk6;
 };
 
 static inline void rxe_counter_inc(struct rxe_dev *rxe, enum rxe_counters index)