summaryrefslogtreecommitdiff
path: root/net/rds
diff options
context:
space:
mode:
Diffstat (limited to 'net/rds')
-rw-r--r--net/rds/cong.c4
-rw-r--r--net/rds/ib_cm.c2
-rw-r--r--net/rds/ib_recv.c2
-rw-r--r--net/rds/page.c4
-rw-r--r--net/rds/tcp.c3
-rw-r--r--net/rds/tcp.h4
-rw-r--r--net/rds/tcp_connect.c8
-rw-r--r--net/rds/tcp_listen.c54
8 files changed, 56 insertions, 25 deletions
diff --git a/net/rds/cong.c b/net/rds/cong.c
index e6144b8246fd..6641bcf7c185 100644
--- a/net/rds/cong.c
+++ b/net/rds/cong.c
@@ -299,7 +299,7 @@ void rds_cong_set_bit(struct rds_cong_map *map, __be16 port)
i = be16_to_cpu(port) / RDS_CONG_MAP_PAGE_BITS;
off = be16_to_cpu(port) % RDS_CONG_MAP_PAGE_BITS;
- __set_bit_le(off, (void *)map->m_page_addrs[i]);
+ set_bit_le(off, (void *)map->m_page_addrs[i]);
}
void rds_cong_clear_bit(struct rds_cong_map *map, __be16 port)
@@ -313,7 +313,7 @@ void rds_cong_clear_bit(struct rds_cong_map *map, __be16 port)
i = be16_to_cpu(port) / RDS_CONG_MAP_PAGE_BITS;
off = be16_to_cpu(port) % RDS_CONG_MAP_PAGE_BITS;
- __clear_bit_le(off, (void *)map->m_page_addrs[i]);
+ clear_bit_le(off, (void *)map->m_page_addrs[i]);
}
static int rds_cong_test_bit(struct rds_cong_map *map, __be16 port)
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 8764970f0c24..310cabce2311 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -194,7 +194,7 @@ static void rds_ib_cm_fill_conn_param(struct rds_connection *conn,
dp->dp_protocol_major = RDS_PROTOCOL_MAJOR(protocol_version);
dp->dp_protocol_minor = RDS_PROTOCOL_MINOR(protocol_version);
dp->dp_protocol_minor_mask = cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS);
- dp->dp_ack_seq = rds_ib_piggyb_ack(ic);
+ dp->dp_ack_seq = cpu_to_be64(rds_ib_piggyb_ack(ic));
/* Advertise flow control */
if (ic->i_flowctl) {
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 977fb86065b7..abc8cc805e8d 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -796,7 +796,7 @@ static void rds_ib_cong_recv(struct rds_connection *conn,
addr = kmap_atomic(sg_page(&frag->f_sg));
- src = addr + frag_off;
+ src = addr + frag->f_sg.offset + frag_off;
dst = (void *)map->m_page_addrs[map_page] + map_off;
for (k = 0; k < to_copy; k += 8) {
/* Record ports that became uncongested, ie
diff --git a/net/rds/page.c b/net/rds/page.c
index 616f21f4e7d7..e2b5a5832d3d 100644
--- a/net/rds/page.c
+++ b/net/rds/page.c
@@ -135,8 +135,8 @@ int rds_page_remainder_alloc(struct scatterlist *scat, unsigned long bytes,
if (rem->r_offset != 0)
rds_stats_inc(s_page_remainder_hit);
- rem->r_offset += bytes;
- if (rem->r_offset == PAGE_SIZE) {
+ rem->r_offset += ALIGN(bytes, 8);
+ if (rem->r_offset >= PAGE_SIZE) {
__free_page(rem->r_page);
rem->r_page = NULL;
}
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 61ed2a8764ba..86187dad1440 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -127,7 +127,7 @@ void rds_tcp_restore_callbacks(struct socket *sock,
/*
* This is the only path that sets tc->t_sock. Send and receive trust that
- * it is set. The RDS_CONN_CONNECTED bit protects those paths from being
+ * it is set. The RDS_CONN_UP bit protects those paths from being
* called while it isn't set.
*/
void rds_tcp_set_callbacks(struct socket *sock, struct rds_connection *conn)
@@ -216,6 +216,7 @@ static int rds_tcp_conn_alloc(struct rds_connection *conn, gfp_t gfp)
if (!tc)
return -ENOMEM;
+ mutex_init(&tc->t_conn_lock);
tc->t_sock = NULL;
tc->t_tinc = NULL;
tc->t_tinc_hdr_rem = sizeof(struct rds_header);
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index 64f873c0c6b6..41c228300525 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -12,6 +12,10 @@ struct rds_tcp_connection {
struct list_head t_tcp_node;
struct rds_connection *conn;
+ /* t_conn_lock synchronizes the connection establishment between
+ * rds_tcp_accept_one and rds_tcp_conn_connect
+ */
+ struct mutex t_conn_lock;
struct socket *t_sock;
void *t_orig_write_space;
void *t_orig_data_ready;
diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c
index 5cb16875c460..49a3fcfed360 100644
--- a/net/rds/tcp_connect.c
+++ b/net/rds/tcp_connect.c
@@ -78,7 +78,14 @@ int rds_tcp_conn_connect(struct rds_connection *conn)
struct socket *sock = NULL;
struct sockaddr_in src, dest;
int ret;
+ struct rds_tcp_connection *tc = conn->c_transport_data;
+
+ mutex_lock(&tc->t_conn_lock);
+ if (rds_conn_up(conn)) {
+ mutex_unlock(&tc->t_conn_lock);
+ return 0;
+ }
ret = sock_create_kern(rds_conn_net(conn), PF_INET,
SOCK_STREAM, IPPROTO_TCP, &sock);
if (ret < 0)
@@ -120,6 +127,7 @@ int rds_tcp_conn_connect(struct rds_connection *conn)
}
out:
+ mutex_unlock(&tc->t_conn_lock);
if (sock)
sock_release(sock);
return ret;
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 0936a4a32b47..be263cdf268b 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -76,7 +76,9 @@ int rds_tcp_accept_one(struct socket *sock)
struct rds_connection *conn;
int ret;
struct inet_sock *inet;
- struct rds_tcp_connection *rs_tcp;
+ struct rds_tcp_connection *rs_tcp = NULL;
+ int conn_state;
+ struct sock *nsk;
ret = sock_create_kern(sock_net(sock->sk), sock->sk->sk_family,
sock->sk->sk_type, sock->sk->sk_protocol,
@@ -115,28 +117,44 @@ int rds_tcp_accept_one(struct socket *sock)
* rds_tcp_state_change() will do that cleanup
*/
rs_tcp = (struct rds_tcp_connection *)conn->c_transport_data;
- if (rs_tcp->t_sock &&
- ntohl(inet->inet_saddr) < ntohl(inet->inet_daddr)) {
- struct sock *nsk = new_sock->sk;
-
- nsk->sk_user_data = NULL;
- nsk->sk_prot->disconnect(nsk, 0);
- tcp_done(nsk);
- new_sock = NULL;
- ret = 0;
- goto out;
- } else if (rs_tcp->t_sock) {
- rds_tcp_restore_callbacks(rs_tcp->t_sock, rs_tcp);
- conn->c_outgoing = 0;
- }
-
rds_conn_transition(conn, RDS_CONN_DOWN, RDS_CONN_CONNECTING);
+ mutex_lock(&rs_tcp->t_conn_lock);
+ conn_state = rds_conn_state(conn);
+ if (conn_state != RDS_CONN_CONNECTING && conn_state != RDS_CONN_UP)
+ goto rst_nsk;
+ if (rs_tcp->t_sock) {
+ /* Need to resolve a duelling SYN between peers.
+ * We have an outstanding SYN to this peer, which may
+ * potentially have transitioned to the RDS_CONN_UP state,
+ * so we must quiesce any send threads before resetting
+ * c_transport_data.
+ */
+ wait_event(conn->c_waitq,
+ !test_bit(RDS_IN_XMIT, &conn->c_flags));
+ if (ntohl(inet->inet_saddr) < ntohl(inet->inet_daddr)) {
+ goto rst_nsk;
+ } else if (rs_tcp->t_sock) {
+ rds_tcp_restore_callbacks(rs_tcp->t_sock, rs_tcp);
+ conn->c_outgoing = 0;
+ }
+ }
rds_tcp_set_callbacks(new_sock, conn);
- rds_connect_complete(conn);
+ rds_connect_complete(conn); /* marks RDS_CONN_UP */
+ new_sock = NULL;
+ ret = 0;
+ goto out;
+rst_nsk:
+ /* reset the newly returned accept sock and bail */
+ nsk = new_sock->sk;
+ rds_tcp_stats_inc(s_tcp_listen_closed_stale);
+ nsk->sk_user_data = NULL;
+ nsk->sk_prot->disconnect(nsk, 0);
+ tcp_done(nsk);
new_sock = NULL;
ret = 0;
-
out:
+ if (rs_tcp)
+ mutex_unlock(&rs_tcp->t_conn_lock);
if (new_sock)
sock_release(new_sock);
return ret;
generated by cgit v1.2.3 (git 2.0.4) at 2024-09-21 05:41:57 +0000