brain-hackers_pepepper-mirror
/
linux-brain
mirror of https://github.com/brain-hackers/linux-brain.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

rds: Changing IP address internal representation to struct in6_addr 

This patch changes the internal representation of an IP address to use
struct in6_addr.  IPv4 address is stored as an IPv4 mapped address.
All the functions which take an IP address as argument are also
changed to use struct in6_addr.  But RDS socket layer is not modified
such that it still does not accept IPv6 address from an application.
And RDS layer does not accept nor initiate IPv6 connections.

v2: Fixed sparse warnings.

Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Ka-Cheong Poon 2018-07-23 20:51:21 -07:00 committed by David S. Miller
parent a6c90dd321
commit eee2fa6ab3
23 changed files with 864 additions and 370 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

140
net/rds/af_rds.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -35,6 +35,7 @@
#include <linux/kernel.h> #include <linux/kernel.h>
#include <linux/gfp.h> #include <linux/gfp.h>
#include <linux/in.h> #include <linux/in.h>
#include <linux/ipv6.h>
#include <linux/poll.h> #include <linux/poll.h>
#include <net/sock.h> #include <net/sock.h>
@ -113,26 +114,63 @@ void rds_wake_sk_sleep(struct rds_sock *rs)
static int rds_getname(struct socket *sock, struct sockaddr *uaddr, static int rds_getname(struct socket *sock, struct sockaddr *uaddr,
int peer) int peer)
{ {
struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
struct rds_sock *rs = rds_sk_to_rs(sock->sk); struct rds_sock *rs = rds_sk_to_rs(sock->sk);
struct sockaddr_in6 *sin6;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); struct sockaddr_in *sin;
int uaddr_len;
/* racey, don't care */ /* racey, don't care */
if (peer) { if (peer) {
if (!rs->rs_conn_addr) if (ipv6_addr_any(&rs->rs_conn_addr))
return -ENOTCONN; return -ENOTCONN;
sin->sin_port = rs->rs_conn_port; if (ipv6_addr_v4mapped(&rs->rs_conn_addr)) {
sin->sin_addr.s_addr = rs->rs_conn_addr; sin = (struct sockaddr_in *)uaddr;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
sin->sin_family = AF_INET;
sin->sin_port = rs->rs_conn_port;
sin->sin_addr.s_addr = rs->rs_conn_addr_v4;
uaddr_len = sizeof(*sin);
} else {
sin6 = (struct sockaddr_in6 *)uaddr;
sin6->sin6_family = AF_INET6;
sin6->sin6_port = rs->rs_conn_port;
sin6->sin6_addr = rs->rs_conn_addr;
sin6->sin6_flowinfo = 0;
/* scope_id is the same as in the bound address. */
sin6->sin6_scope_id = rs->rs_bound_scope_id;
uaddr_len = sizeof(*sin6);
}
} else { } else {
sin->sin_port = rs->rs_bound_port; /* If socket is not yet bound, set the return address family
sin->sin_addr.s_addr = rs->rs_bound_addr; * to be AF_UNSPEC (value 0) and the address size to be that
* of an IPv4 address.
*/
if (ipv6_addr_any(&rs->rs_bound_addr)) {
sin = (struct sockaddr_in *)uaddr;
memset(sin, 0, sizeof(*sin));
sin->sin_family = AF_UNSPEC;
return sizeof(*sin);
}
if (ipv6_addr_v4mapped(&rs->rs_bound_addr)) {
sin = (struct sockaddr_in *)uaddr;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
sin->sin_family = AF_INET;
sin->sin_port = rs->rs_bound_port;
sin->sin_addr.s_addr = rs->rs_bound_addr_v4;
uaddr_len = sizeof(*sin);
} else {
sin6 = (struct sockaddr_in6 *)uaddr;
sin6->sin6_family = AF_INET6;
sin6->sin6_port = rs->rs_bound_port;
sin6->sin6_addr = rs->rs_bound_addr;
sin6->sin6_flowinfo = 0;
sin6->sin6_scope_id = rs->rs_bound_scope_id;
uaddr_len = sizeof(*sin6);
}
} }
sin->sin_family = AF_INET; return uaddr_len;
return sizeof(*sin);
} }
/* /*
@ -203,11 +241,12 @@ static int rds_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval, static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval,
int len) int len)
{ {
struct sockaddr_in6 sin6;
struct sockaddr_in sin; struct sockaddr_in sin;
int ret = 0; int ret = 0;
/* racing with another thread binding seems ok here */ /* racing with another thread binding seems ok here */
if (rs->rs_bound_addr == 0) { if (ipv6_addr_any(&rs->rs_bound_addr)) {
ret = -ENOTCONN; /* XXX not a great errno */ ret = -ENOTCONN; /* XXX not a great errno */
goto out; goto out;
} }
@ -215,14 +254,23 @@ static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval,
if (len < sizeof(struct sockaddr_in)) { if (len < sizeof(struct sockaddr_in)) {
ret = -EINVAL; ret = -EINVAL;
goto out; goto out;
} else if (len < sizeof(struct sockaddr_in6)) {
/* Assume IPv4 */
if (copy_from_user(&sin, optval, sizeof(struct sockaddr_in))) {
ret = -EFAULT;
goto out;
}
ipv6_addr_set_v4mapped(sin.sin_addr.s_addr, &sin6.sin6_addr);
sin6.sin6_port = sin.sin_port;
} else {
if (copy_from_user(&sin6, optval,
sizeof(struct sockaddr_in6))) {
ret = -EFAULT;
goto out;
}
} }
if (copy_from_user(&sin, optval, sizeof(sin))) { rds_send_drop_to(rs, &sin6);
ret = -EFAULT;
goto out;
}
rds_send_drop_to(rs, &sin);
out: out:
return ret; return ret;
} }
@ -435,31 +483,41 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags) int addr_len, int flags)
{ {
struct sock *sk = sock->sk; struct sock *sk = sock->sk;
struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; struct sockaddr_in *sin;
struct rds_sock *rs = rds_sk_to_rs(sk); struct rds_sock *rs = rds_sk_to_rs(sk);
int ret = 0; int ret = 0;
lock_sock(sk); lock_sock(sk);
if (addr_len != sizeof(struct sockaddr_in)) { switch (addr_len) {
case sizeof(struct sockaddr_in):
sin = (struct sockaddr_in *)uaddr;
if (sin->sin_family != AF_INET) {
ret = -EAFNOSUPPORT;
break;
}
if (sin->sin_addr.s_addr == htonl(INADDR_ANY)) {
ret = -EDESTADDRREQ;
break;
}
if (IN_MULTICAST(ntohl(sin->sin_addr.s_addr)) ||
sin->sin_addr.s_addr == htonl(INADDR_BROADCAST)) {
ret = -EINVAL;
break;
}
ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &rs->rs_conn_addr);
rs->rs_conn_port = sin->sin_port;
break;
case sizeof(struct sockaddr_in6):
ret = -EPROTONOSUPPORT;
break;
default:
ret = -EINVAL; ret = -EINVAL;
goto out; break;
} }
if (sin->sin_family != AF_INET) {
ret = -EAFNOSUPPORT;
goto out;
}
if (sin->sin_addr.s_addr == htonl(INADDR_ANY)) {
ret = -EDESTADDRREQ;
goto out;
}
rs->rs_conn_addr = sin->sin_addr.s_addr;
rs->rs_conn_port = sin->sin_port;
out:
release_sock(sk); release_sock(sk);
return ret; return ret;
} }
@ -578,8 +636,10 @@ static void rds_sock_inc_info(struct socket *sock, unsigned int len,
list_for_each_entry(inc, &rs->rs_recv_queue, i_item) { list_for_each_entry(inc, &rs->rs_recv_queue, i_item) {
total++; total++;
if (total <= len) if (total <= len)
rds_inc_info_copy(inc, iter, inc->i_saddr, rds_inc_info_copy(inc, iter,
rs->rs_bound_addr, 1); inc->i_saddr.s6_addr32[3],
rs->rs_bound_addr_v4,
1);
} }
read_unlock(&rs->rs_recv_lock); read_unlock(&rs->rs_recv_lock);
@ -608,8 +668,8 @@ static void rds_sock_info(struct socket *sock, unsigned int len,
list_for_each_entry(rs, &rds_sock_list, rs_item) { list_for_each_entry(rs, &rds_sock_list, rs_item) {
sinfo.sndbuf = rds_sk_sndbuf(rs); sinfo.sndbuf = rds_sk_sndbuf(rs);
sinfo.rcvbuf = rds_sk_rcvbuf(rs); sinfo.rcvbuf = rds_sk_rcvbuf(rs);
sinfo.bound_addr = rs->rs_bound_addr; sinfo.bound_addr = rs->rs_bound_addr_v4;
sinfo.connected_addr = rs->rs_conn_addr; sinfo.connected_addr = rs->rs_conn_addr_v4;
sinfo.bound_port = rs->rs_bound_port; sinfo.bound_port = rs->rs_bound_port;
sinfo.connected_port = rs->rs_conn_port; sinfo.connected_port = rs->rs_conn_port;
sinfo.inum = sock_i_ino(rds_rs_to_sk(rs)); sinfo.inum = sock_i_ino(rds_rs_to_sk(rs));

91
net/rds/bind.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -33,6 +33,7 @@
#include <linux/kernel.h> #include <linux/kernel.h>
#include <net/sock.h> #include <net/sock.h>
#include <linux/in.h> #include <linux/in.h>
#include <linux/ipv6.h>
#include <linux/if_arp.h> #include <linux/if_arp.h>
#include <linux/jhash.h> #include <linux/jhash.h>
#include <linux/ratelimit.h> #include <linux/ratelimit.h>
@ -42,42 +43,58 @@ static struct rhashtable bind_hash_table;
static const struct rhashtable_params ht_parms = { static const struct rhashtable_params ht_parms = {
.nelem_hint = 768, .nelem_hint = 768,
.key_len = sizeof(u64), .key_len = RDS_BOUND_KEY_LEN,
.key_offset = offsetof(struct rds_sock, rs_bound_key), .key_offset = offsetof(struct rds_sock, rs_bound_key),
.head_offset = offsetof(struct rds_sock, rs_bound_node), .head_offset = offsetof(struct rds_sock, rs_bound_node),
.max_size = 16384, .max_size = 16384,
.min_size = 1024, .min_size = 1024,
}; };
/* Create a key for the bind hash table manipulation. Port is in network byte
* order.
*/
static inline void __rds_create_bind_key(u8 *key, const struct in6_addr *addr,
__be16 port, __u32 scope_id)
{
memcpy(key, addr, sizeof(*addr));
key += sizeof(*addr);
memcpy(key, &port, sizeof(port));
key += sizeof(port);
memcpy(key, &scope_id, sizeof(scope_id));
}
/* /*
* Return the rds_sock bound at the given local address. * Return the rds_sock bound at the given local address.
* *
* The rx path can race with rds_release. We notice if rds_release() has * The rx path can race with rds_release. We notice if rds_release() has
* marked this socket and don't return a rs ref to the rx path. * marked this socket and don't return a rs ref to the rx path.
*/ */
struct rds_sock *rds_find_bound(__be32 addr, __be16 port) struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port,
__u32 scope_id)
{ {
u64 key = ((u64)addr << 32) | port; u8 key[RDS_BOUND_KEY_LEN];
struct rds_sock *rs; struct rds_sock *rs;
rs = rhashtable_lookup_fast(&bind_hash_table, &key, ht_parms); __rds_create_bind_key(key, addr, port, scope_id);
rs = rhashtable_lookup_fast(&bind_hash_table, key, ht_parms);
if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD))
rds_sock_addref(rs); rds_sock_addref(rs);
else else
rs = NULL; rs = NULL;
rdsdebug("returning rs %p for %pI4:%u\n", rs, &addr, rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr,
ntohs(port)); ntohs(port));
return rs; return rs;
} }
/* returns -ve errno or +ve port */ /* returns -ve errno or +ve port */
static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port) static int rds_add_bound(struct rds_sock *rs, const struct in6_addr *addr,
__be16 *port, __u32 scope_id)
{ {
int ret = -EADDRINUSE; int ret = -EADDRINUSE;
u16 rover, last; u16 rover, last;
u64 key; u8 key[RDS_BOUND_KEY_LEN];
if (*port != 0) { if (*port != 0) {
rover = be16_to_cpu(*port); rover = be16_to_cpu(*port);
@ -95,12 +112,13 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
if (rover == RDS_FLAG_PROBE_PORT) if (rover == RDS_FLAG_PROBE_PORT)
continue; continue;
key = ((u64)addr << 32) | cpu_to_be16(rover); __rds_create_bind_key(key, addr, cpu_to_be16(rover),
if (rhashtable_lookup_fast(&bind_hash_table, &key, ht_parms)) scope_id);
if (rhashtable_lookup_fast(&bind_hash_table, key, ht_parms))
continue; continue;
rs->rs_bound_key = key; memcpy(rs->rs_bound_key, key, sizeof(rs->rs_bound_key));
rs->rs_bound_addr = addr; rs->rs_bound_addr = *addr;
net_get_random_once(&rs->rs_hash_initval, net_get_random_once(&rs->rs_hash_initval,
sizeof(rs->rs_hash_initval)); sizeof(rs->rs_hash_initval));
rs->rs_bound_port = cpu_to_be16(rover); rs->rs_bound_port = cpu_to_be16(rover);
@ -114,7 +132,7 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
rs, &addr, (int)ntohs(*port)); rs, &addr, (int)ntohs(*port));
break; break;
} else { } else {
rs->rs_bound_addr = 0; rs->rs_bound_addr = in6addr_any;
rds_sock_put(rs); rds_sock_put(rs);
ret = -ENOMEM; ret = -ENOMEM;
break; break;
@ -127,44 +145,61 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
void rds_remove_bound(struct rds_sock *rs) void rds_remove_bound(struct rds_sock *rs)
{ {
if (!rs->rs_bound_addr) if (ipv6_addr_any(&rs->rs_bound_addr))
return; return;
rdsdebug("rs %p unbinding from %pI4:%d\n", rdsdebug("rs %p unbinding from %pI6c:%d\n",
rs, &rs->rs_bound_addr, rs, &rs->rs_bound_addr,
ntohs(rs->rs_bound_port)); ntohs(rs->rs_bound_port));
rhashtable_remove_fast(&bind_hash_table, &rs->rs_bound_node, ht_parms); rhashtable_remove_fast(&bind_hash_table, &rs->rs_bound_node, ht_parms);
rds_sock_put(rs); rds_sock_put(rs);
rs->rs_bound_addr = 0; rs->rs_bound_addr = in6addr_any;
} }
int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{ {
struct sock *sk = sock->sk; struct sock *sk = sock->sk;
struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
struct rds_sock *rs = rds_sk_to_rs(sk); struct rds_sock *rs = rds_sk_to_rs(sk);
struct in6_addr v6addr, *binding_addr;
struct rds_transport *trans; struct rds_transport *trans;
__u32 scope_id = 0;
int ret = 0; int ret = 0;
__be16 port;
/* We only allow an RDS socket to be bound to an IPv4 address. IPv6
* address support will be added later.
*/
if (addr_len == sizeof(struct sockaddr_in)) {
struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
if (sin->sin_family != AF_INET ||
sin->sin_addr.s_addr == htonl(INADDR_ANY))
return -EINVAL;
ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &v6addr);
binding_addr = &v6addr;
port = sin->sin_port;
} else if (addr_len == sizeof(struct sockaddr_in6)) {
return -EPROTONOSUPPORT;
} else {
return -EINVAL;
}
lock_sock(sk); lock_sock(sk);
if (addr_len != sizeof(struct sockaddr_in) || /* RDS socket does not allow re-binding. */
sin->sin_family != AF_INET || if (!ipv6_addr_any(&rs->rs_bound_addr)) {
rs->rs_bound_addr ||
sin->sin_addr.s_addr == htonl(INADDR_ANY)) {
ret = -EINVAL; ret = -EINVAL;
goto out; goto out;
} }
ret = rds_add_bound(rs, sin->sin_addr.s_addr, &sin->sin_port); ret = rds_add_bound(rs, binding_addr, &port, scope_id);
if (ret) if (ret)
goto out; goto out;
if (rs->rs_transport) { /* previously bound */ if (rs->rs_transport) { /* previously bound */
trans = rs->rs_transport; trans = rs->rs_transport;
if (trans->laddr_check(sock_net(sock->sk), if (trans->laddr_check(sock_net(sock->sk),
sin->sin_addr.s_addr) != 0) { binding_addr, scope_id) != 0) {
ret = -ENOPROTOOPT; ret = -ENOPROTOOPT;
rds_remove_bound(rs); rds_remove_bound(rs);
} else { } else {
@ -172,13 +207,13 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
} }
goto out; goto out;
} }
trans = rds_trans_get_preferred(sock_net(sock->sk), trans = rds_trans_get_preferred(sock_net(sock->sk), binding_addr,
sin->sin_addr.s_addr); scope_id);
if (!trans) { if (!trans) {
ret = -EADDRNOTAVAIL; ret = -EADDRNOTAVAIL;
rds_remove_bound(rs); rds_remove_bound(rs);
pr_info_ratelimited("RDS: %s could not find a transport for %pI4, load rds_tcp or rds_rdma?\n", pr_info_ratelimited("RDS: %s could not find a transport for %pI6c, load rds_tcp or rds_rdma?\n",
__func__, &sin->sin_addr.s_addr); __func__, binding_addr);
goto out; goto out;
} }

23
net/rds/cong.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2007 Oracle. All rights reserved. * Copyright (c) 2007, 2017 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -101,7 +101,7 @@ static DEFINE_RWLOCK(rds_cong_monitor_lock);
static DEFINE_SPINLOCK(rds_cong_lock); static DEFINE_SPINLOCK(rds_cong_lock);
static struct rb_root rds_cong_tree = RB_ROOT; static struct rb_root rds_cong_tree = RB_ROOT;
static struct rds_cong_map *rds_cong_tree_walk(__be32 addr, static struct rds_cong_map *rds_cong_tree_walk(const struct in6_addr *addr,
struct rds_cong_map *insert) struct rds_cong_map *insert)
{ {
struct rb_node **p = &rds_cong_tree.rb_node; struct rb_node **p = &rds_cong_tree.rb_node;
@ -109,12 +109,15 @@ static struct rds_cong_map *rds_cong_tree_walk(__be32 addr,
struct rds_cong_map *map; struct rds_cong_map *map;
while (*p) { while (*p) {
int diff;
parent = *p; parent = *p;
map = rb_entry(parent, struct rds_cong_map, m_rb_node); map = rb_entry(parent, struct rds_cong_map, m_rb_node);
if (addr < map->m_addr) diff = rds_addr_cmp(addr, &map->m_addr);
if (diff < 0)
p = &(*p)->rb_left; p = &(*p)->rb_left;
else if (addr > map->m_addr) else if (diff > 0)
p = &(*p)->rb_right; p = &(*p)->rb_right;
else else
return map; return map;
@ -132,7 +135,7 @@ static struct rds_cong_map *rds_cong_tree_walk(__be32 addr,
* these bitmaps in the process getting pointers to them. The bitmaps are only * these bitmaps in the process getting pointers to them. The bitmaps are only
* ever freed as the module is removed after all connections have been freed. * ever freed as the module is removed after all connections have been freed.
*/ */
static struct rds_cong_map *rds_cong_from_addr(__be32 addr) static struct rds_cong_map *rds_cong_from_addr(const struct in6_addr *addr)
{ {
struct rds_cong_map *map; struct rds_cong_map *map;
struct rds_cong_map *ret = NULL; struct rds_cong_map *ret = NULL;
@ -144,7 +147,7 @@ static struct rds_cong_map *rds_cong_from_addr(__be32 addr)
if (!map) if (!map)
return NULL; return NULL;
map->m_addr = addr; map->m_addr = *addr;
init_waitqueue_head(&map->m_waitq); init_waitqueue_head(&map->m_waitq);
INIT_LIST_HEAD(&map->m_conn_list); INIT_LIST_HEAD(&map->m_conn_list);
@ -171,7 +174,7 @@ out:
kfree(map); kfree(map);
} }
rdsdebug("map %p for addr %x\n", ret, be32_to_cpu(addr)); rdsdebug("map %p for addr %pI6c\n", ret, addr);
return ret; return ret;
} }
@ -202,8 +205,8 @@ void rds_cong_remove_conn(struct rds_connection *conn)
int rds_cong_get_maps(struct rds_connection *conn) int rds_cong_get_maps(struct rds_connection *conn)
{ {
conn->c_lcong = rds_cong_from_addr(conn->c_laddr); conn->c_lcong = rds_cong_from_addr(&conn->c_laddr);
conn->c_fcong = rds_cong_from_addr(conn->c_faddr); conn->c_fcong = rds_cong_from_addr(&conn->c_faddr);
if (!(conn->c_lcong && conn->c_fcong)) if (!(conn->c_lcong && conn->c_fcong))
return -ENOMEM; return -ENOMEM;
@ -353,7 +356,7 @@ void rds_cong_remove_socket(struct rds_sock *rs)
/* update congestion map for now-closed port */ /* update congestion map for now-closed port */
spin_lock_irqsave(&rds_cong_lock, flags); spin_lock_irqsave(&rds_cong_lock, flags);
map = rds_cong_tree_walk(rs->rs_bound_addr, NULL); map = rds_cong_tree_walk(&rs->rs_bound_addr, NULL);
spin_unlock_irqrestore(&rds_cong_lock, flags); spin_unlock_irqrestore(&rds_cong_lock, flags);
if (map && rds_cong_test_bit(map, rs->rs_bound_port)) { if (map && rds_cong_test_bit(map, rs->rs_bound_port)) {

132
net/rds/connection.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -34,7 +34,8 @@
#include <linux/list.h> #include <linux/list.h>
#include <linux/slab.h> #include <linux/slab.h>
#include <linux/export.h> #include <linux/export.h>
#include <net/inet_hashtables.h> #include <net/ipv6.h>
#include <net/inet6_hashtables.h>
#include "rds.h" #include "rds.h"
#include "loop.h" #include "loop.h"
@ -49,18 +50,21 @@ static unsigned long rds_conn_count;
static struct hlist_head rds_conn_hash[RDS_CONNECTION_HASH_ENTRIES]; static struct hlist_head rds_conn_hash[RDS_CONNECTION_HASH_ENTRIES];
static struct kmem_cache *rds_conn_slab; static struct kmem_cache *rds_conn_slab;
static struct hlist_head *rds_conn_bucket(__be32 laddr, __be32 faddr) static struct hlist_head *rds_conn_bucket(const struct in6_addr *laddr,
const struct in6_addr *faddr)
{ {
static u32 rds6_hash_secret __read_mostly;
static u32 rds_hash_secret __read_mostly; static u32 rds_hash_secret __read_mostly;
unsigned long hash; u32 lhash, fhash, hash;
net_get_random_once(&rds_hash_secret, sizeof(rds_hash_secret)); net_get_random_once(&rds_hash_secret, sizeof(rds_hash_secret));
net_get_random_once(&rds6_hash_secret, sizeof(rds6_hash_secret));
lhash = (__force u32)laddr->s6_addr32[3];
fhash = __ipv6_addr_jhash(faddr, rds6_hash_secret);
hash = __inet6_ehashfn(lhash, 0, fhash, 0, rds_hash_secret);
/* Pass NULL, don't need struct net for hash */
hash = __inet_ehashfn(be32_to_cpu(laddr), 0,
be32_to_cpu(faddr), 0,
rds_hash_secret);
return &rds_conn_hash[hash & RDS_CONNECTION_HASH_MASK]; return &rds_conn_hash[hash & RDS_CONNECTION_HASH_MASK];
} }
@ -72,20 +76,25 @@ static struct hlist_head *rds_conn_bucket(__be32 laddr, __be32 faddr)
/* rcu read lock must be held or the connection spinlock */ /* rcu read lock must be held or the connection spinlock */
static struct rds_connection *rds_conn_lookup(struct net *net, static struct rds_connection *rds_conn_lookup(struct net *net,
struct hlist_head *head, struct hlist_head *head,
__be32 laddr, __be32 faddr, const struct in6_addr *laddr,
struct rds_transport *trans) const struct in6_addr *faddr,
struct rds_transport *trans,
int dev_if)
{ {
struct rds_connection *conn, *ret = NULL; struct rds_connection *conn, *ret = NULL;
hlist_for_each_entry_rcu(conn, head, c_hash_node) { hlist_for_each_entry_rcu(conn, head, c_hash_node) {
if (conn->c_faddr == faddr && conn->c_laddr == laddr && if (ipv6_addr_equal(&conn->c_faddr, faddr) &&
conn->c_trans == trans && net == rds_conn_net(conn)) { ipv6_addr_equal(&conn->c_laddr, laddr) &&
conn->c_trans == trans &&
net == rds_conn_net(conn) &&
conn->c_dev_if == dev_if) {
ret = conn; ret = conn;
break; break;
} }
} }
rdsdebug("returning conn %p for %pI4 -> %pI4\n", ret, rdsdebug("returning conn %p for %pI6c -> %pI6c\n", ret,
&laddr, &faddr); laddr, faddr);
return ret; return ret;
} }
@ -99,8 +108,8 @@ static void rds_conn_path_reset(struct rds_conn_path *cp)
{ {
struct rds_connection *conn = cp->cp_conn; struct rds_connection *conn = cp->cp_conn;
rdsdebug("connection %pI4 to %pI4 reset\n", rdsdebug("connection %pI6c to %pI6c reset\n",
&conn->c_laddr, &conn->c_faddr); &conn->c_laddr, &conn->c_faddr);
rds_stats_inc(s_conn_reset); rds_stats_inc(s_conn_reset);
rds_send_path_reset(cp); rds_send_path_reset(cp);
@ -142,9 +151,12 @@ static void __rds_conn_path_init(struct rds_connection *conn,
* are torn down as the module is removed, if ever. * are torn down as the module is removed, if ever.
*/ */
static struct rds_connection *__rds_conn_create(struct net *net, static struct rds_connection *__rds_conn_create(struct net *net,
__be32 laddr, __be32 faddr, const struct in6_addr *laddr,
struct rds_transport *trans, gfp_t gfp, const struct in6_addr *faddr,
int is_outgoing) struct rds_transport *trans,
gfp_t gfp,
int is_outgoing,
int dev_if)
{ {
struct rds_connection *conn, *parent = NULL; struct rds_connection *conn, *parent = NULL;
struct hlist_head *head = rds_conn_bucket(laddr, faddr); struct hlist_head *head = rds_conn_bucket(laddr, faddr);
@ -154,9 +166,12 @@ static struct rds_connection *__rds_conn_create(struct net *net,
int npaths = (trans->t_mp_capable ? RDS_MPATH_WORKERS : 1); int npaths = (trans->t_mp_capable ? RDS_MPATH_WORKERS : 1);
rcu_read_lock(); rcu_read_lock();
conn = rds_conn_lookup(net, head, laddr, faddr, trans); conn = rds_conn_lookup(net, head, laddr, faddr, trans, dev_if);
if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport && if (conn &&
laddr == faddr && !is_outgoing) { conn->c_loopback &&
conn->c_trans != &rds_loop_transport &&
ipv6_addr_equal(laddr, faddr) &&
!is_outgoing) {
/* This is a looped back IB connection, and we're /* This is a looped back IB connection, and we're
* called by the code handling the incoming connect. * called by the code handling the incoming connect.
* We need a second connection object into which we * We need a second connection object into which we
@ -181,8 +196,10 @@ static struct rds_connection *__rds_conn_create(struct net *net,
} }
INIT_HLIST_NODE(&conn->c_hash_node); INIT_HLIST_NODE(&conn->c_hash_node);
conn->c_laddr = laddr; conn->c_laddr = *laddr;
conn->c_faddr = faddr; conn->c_isv6 = !ipv6_addr_v4mapped(laddr);
conn->c_faddr = *faddr;
conn->c_dev_if = dev_if;
rds_conn_net_set(conn, net); rds_conn_net_set(conn, net);
@ -199,7 +216,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,
* can bind to the destination address then we'd rather the messages * can bind to the destination address then we'd rather the messages
* flow through loopback rather than either transport. * flow through loopback rather than either transport.
*/ */
loop_trans = rds_trans_get_preferred(net, faddr); loop_trans = rds_trans_get_preferred(net, faddr, conn->c_dev_if);
if (loop_trans) { if (loop_trans) {
rds_trans_put(loop_trans); rds_trans_put(loop_trans);
conn->c_loopback = 1; conn->c_loopback = 1;
@ -233,10 +250,10 @@ static struct rds_connection *__rds_conn_create(struct net *net,
goto out; goto out;
} }
rdsdebug("allocated conn %p for %pI4 -> %pI4 over %s %s\n", rdsdebug("allocated conn %p for %pI6c -> %pI6c over %s %s\n",
conn, &laddr, &faddr, conn, laddr, faddr,
strnlen(trans->t_name, sizeof(trans->t_name)) ? trans->t_name : strnlen(trans->t_name, sizeof(trans->t_name)) ?
"[unknown]", is_outgoing ? "(outgoing)" : ""); trans->t_name : "[unknown]", is_outgoing ? "(outgoing)" : "");
/* /*
* Since we ran without holding the conn lock, someone could * Since we ran without holding the conn lock, someone could
@ -262,7 +279,8 @@ static struct rds_connection *__rds_conn_create(struct net *net,
/* Creating normal conn */ /* Creating normal conn */
struct rds_connection *found; struct rds_connection *found;
found = rds_conn_lookup(net, head, laddr, faddr, trans); found = rds_conn_lookup(net, head, laddr, faddr, trans,
dev_if);
if (found) { if (found) {
struct rds_conn_path *cp; struct rds_conn_path *cp;
int i; int i;
@ -295,18 +313,22 @@ out:
} }
struct rds_connection *rds_conn_create(struct net *net, struct rds_connection *rds_conn_create(struct net *net,
__be32 laddr, __be32 faddr, const struct in6_addr *laddr,
struct rds_transport *trans, gfp_t gfp) const struct in6_addr *faddr,
struct rds_transport *trans, gfp_t gfp,
int dev_if)
{ {
return __rds_conn_create(net, laddr, faddr, trans, gfp, 0); return __rds_conn_create(net, laddr, faddr, trans, gfp, 0, dev_if);
} }
EXPORT_SYMBOL_GPL(rds_conn_create); EXPORT_SYMBOL_GPL(rds_conn_create);
struct rds_connection *rds_conn_create_outgoing(struct net *net, struct rds_connection *rds_conn_create_outgoing(struct net *net,
__be32 laddr, __be32 faddr, const struct in6_addr *laddr,
struct rds_transport *trans, gfp_t gfp) const struct in6_addr *faddr,
struct rds_transport *trans,
gfp_t gfp, int dev_if)
{ {
return __rds_conn_create(net, laddr, faddr, trans, gfp, 1); return __rds_conn_create(net, laddr, faddr, trans, gfp, 1, dev_if);
} }
EXPORT_SYMBOL_GPL(rds_conn_create_outgoing); EXPORT_SYMBOL_GPL(rds_conn_create_outgoing);
@ -502,12 +524,17 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len,
/* XXX too lazy to maintain counts.. */ /* XXX too lazy to maintain counts.. */
list_for_each_entry(rm, list, m_conn_item) { list_for_each_entry(rm, list, m_conn_item) {
__be32 laddr;
__be32 faddr;
total++; total++;
laddr = conn->c_laddr.s6_addr32[3];
faddr = conn->c_faddr.s6_addr32[3];
if (total <= len) if (total <= len)
rds_inc_info_copy(&rm->m_inc, rds_inc_info_copy(&rm->m_inc,
iter, iter,
conn->c_laddr, laddr,
conn->c_faddr, faddr,
0); 0);
} }
@ -584,7 +611,6 @@ static void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
struct hlist_head *head; struct hlist_head *head;
struct rds_connection *conn; struct rds_connection *conn;
size_t i; size_t i;
int j;
rcu_read_lock(); rcu_read_lock();
@ -595,17 +621,20 @@ static void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
i++, head++) { i++, head++) {
hlist_for_each_entry_rcu(conn, head, c_hash_node) { hlist_for_each_entry_rcu(conn, head, c_hash_node) {
struct rds_conn_path *cp; struct rds_conn_path *cp;
int npaths;
npaths = (conn->c_trans->t_mp_capable ? /* XXX We only copy the information from the first
RDS_MPATH_WORKERS : 1); * path for now. The problem is that if there are
for (j = 0; j < npaths; j++) { * more than one underlying paths, we cannot report
cp = &conn->c_path[j]; * information of all of them using the existing
* API. For example, there is only one next_tx_seq,
* which path's next_tx_seq should we report? It is
* a bug in the design of MPRDS.
*/
cp = conn->c_path;
/* XXX no cp_lock usage.. */ /* XXX no cp_lock usage.. */
if (!visitor(cp, buffer)) if (!visitor(cp, buffer))
continue; continue;
}
/* We copy as much as we can fit in the buffer, /* We copy as much as we can fit in the buffer,
* but we count all items so that the caller * but we count all items so that the caller
@ -624,12 +653,13 @@ static void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer) static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
{ {
struct rds_info_connection *cinfo = buffer; struct rds_info_connection *cinfo = buffer;
struct rds_connection *conn = cp->cp_conn;
cinfo->next_tx_seq = cp->cp_next_tx_seq; cinfo->next_tx_seq = cp->cp_next_tx_seq;
cinfo->next_rx_seq = cp->cp_next_rx_seq; cinfo->next_rx_seq = cp->cp_next_rx_seq;
cinfo->laddr = cp->cp_conn->c_laddr; cinfo->laddr = conn->c_laddr.s6_addr32[3];
cinfo->faddr = cp->cp_conn->c_faddr; cinfo->faddr = conn->c_faddr.s6_addr32[3];
strncpy(cinfo->transport, cp->cp_conn->c_trans->t_name, strncpy(cinfo->transport, conn->c_trans->t_name,
sizeof(cinfo->transport)); sizeof(cinfo->transport));
cinfo->flags = 0; cinfo->flags = 0;

17
net/rds/ib.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -296,8 +296,8 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn,
if (conn->c_trans != &rds_ib_transport) if (conn->c_trans != &rds_ib_transport)
return 0; return 0;
iinfo->src_addr = conn->c_laddr; iinfo->src_addr = conn->c_laddr.s6_addr32[3];
iinfo->dst_addr = conn->c_faddr; iinfo->dst_addr = conn->c_faddr.s6_addr32[3];
memset(&iinfo->src_gid, 0, sizeof(iinfo->src_gid)); memset(&iinfo->src_gid, 0, sizeof(iinfo->src_gid));
memset(&iinfo->dst_gid, 0, sizeof(iinfo->dst_gid)); memset(&iinfo->dst_gid, 0, sizeof(iinfo->dst_gid));
@ -341,7 +341,8 @@ static void rds_ib_ic_info(struct socket *sock, unsigned int len,
* allowed to influence which paths have priority. We could call userspace * allowed to influence which paths have priority. We could call userspace
* asserting this policy "routing". * asserting this policy "routing".
*/ */
static int rds_ib_laddr_check(struct net *net, __be32 addr) static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr,
__u32 scope_id)
{ {
int ret; int ret;
struct rdma_cm_id *cm_id; struct rdma_cm_id *cm_id;
@ -357,7 +358,7 @@ static int rds_ib_laddr_check(struct net *net, __be32 addr)
memset(&sin, 0, sizeof(sin)); memset(&sin, 0, sizeof(sin));
sin.sin_family = AF_INET; sin.sin_family = AF_INET;
sin.sin_addr.s_addr = addr; sin.sin_addr.s_addr = addr->s6_addr32[3];
/* rdma_bind_addr will only succeed for IB & iWARP devices */ /* rdma_bind_addr will only succeed for IB & iWARP devices */
ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin); ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
@ -367,9 +368,9 @@ static int rds_ib_laddr_check(struct net *net, __be32 addr)
cm_id->device->node_type != RDMA_NODE_IB_CA) cm_id->device->node_type != RDMA_NODE_IB_CA)
ret = -EADDRNOTAVAIL; ret = -EADDRNOTAVAIL;
rdsdebug("addr %pI4 ret %d node type %d\n", rdsdebug("addr %pI6c ret %d node type %d\n",
&addr, ret, addr, ret,
cm_id->device ? cm_id->device->node_type : -1); cm_id->device ? cm_id->device->node_type : -1);
rdma_destroy_id(cm_id); rdma_destroy_id(cm_id);

51
net/rds/ib.h
View File

@ -57,16 +57,44 @@ struct rds_ib_refill_cache {
struct list_head *ready; struct list_head *ready;
}; };
/* This is the common structure for the IB private data exchange in setting up
* an RDS connection. The exchange is different for IPv4 and IPv6 connections.
* The reason is that the address size is different and the addresses
* exchanged are in the beginning of the structure. Hence it is not possible
* for interoperability if same structure is used.
*/
struct rds_ib_conn_priv_cmn {
u8 ricpc_protocol_major;
u8 ricpc_protocol_minor;
__be16 ricpc_protocol_minor_mask; /* bitmask */
__be32 ricpc_reserved1;
__be64 ricpc_ack_seq;
__be32 ricpc_credit; /* non-zero enables flow ctl */
};
struct rds_ib_connect_private { struct rds_ib_connect_private {
/* Add new fields at the end, and don't permute existing fields. */ /* Add new fields at the end, and don't permute existing fields. */
__be32 dp_saddr; __be32 dp_saddr;
__be32 dp_daddr; __be32 dp_daddr;
u8 dp_protocol_major; struct rds_ib_conn_priv_cmn dp_cmn;
u8 dp_protocol_minor; };
__be16 dp_protocol_minor_mask; /* bitmask */
__be32 dp_reserved1; struct rds6_ib_connect_private {
__be64 dp_ack_seq; /* Add new fields at the end, and don't permute existing fields. */
__be32 dp_credit; /* non-zero enables flow ctl */ struct in6_addr dp_saddr;
struct in6_addr dp_daddr;
struct rds_ib_conn_priv_cmn dp_cmn;
};
#define dp_protocol_major dp_cmn.ricpc_protocol_major
#define dp_protocol_minor dp_cmn.ricpc_protocol_minor
#define dp_protocol_minor_mask dp_cmn.ricpc_protocol_minor_mask
#define dp_ack_seq dp_cmn.ricpc_ack_seq
#define dp_credit dp_cmn.ricpc_credit
union rds_ib_conn_priv {
struct rds_ib_connect_private ricp_v4;
struct rds6_ib_connect_private ricp_v6;
}; };
struct rds_ib_send_work { struct rds_ib_send_work {
@ -351,8 +379,8 @@ void rds_ib_listen_stop(void);
__printf(2, 3) __printf(2, 3)
void __rds_ib_conn_error(struct rds_connection *conn, const char *, ...); void __rds_ib_conn_error(struct rds_connection *conn, const char *, ...);
int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
struct rdma_cm_event *event); struct rdma_cm_event *event, bool isv6);
int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id); int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6);
void rds_ib_cm_connect_complete(struct rds_connection *conn, void rds_ib_cm_connect_complete(struct rds_connection *conn,
struct rdma_cm_event *event); struct rdma_cm_event *event);
@ -361,7 +389,8 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn,
__rds_ib_conn_error(conn, KERN_WARNING "RDS/IB: " fmt) __rds_ib_conn_error(conn, KERN_WARNING "RDS/IB: " fmt)
/* ib_rdma.c */ /* ib_rdma.c */
int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr); int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev,
struct in6_addr *ipaddr);
void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn); void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn);
void rds_ib_remove_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn); void rds_ib_remove_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn);
void rds_ib_destroy_nodev_conns(void); void rds_ib_destroy_nodev_conns(void);

299
net/rds/ib_cm.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -35,6 +35,7 @@
#include <linux/slab.h> #include <linux/slab.h>
#include <linux/vmalloc.h> #include <linux/vmalloc.h>
#include <linux/ratelimit.h> #include <linux/ratelimit.h>
#include <net/addrconf.h>
#include "rds_single_path.h" #include "rds_single_path.h"
#include "rds.h" #include "rds.h"
@ -95,25 +96,45 @@ rds_ib_tune_rnr(struct rds_ib_connection *ic, struct ib_qp_attr *attr)
*/ */
void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_event *event) void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_event *event)
{ {
const struct rds_ib_connect_private *dp = NULL;
struct rds_ib_connection *ic = conn->c_transport_data; struct rds_ib_connection *ic = conn->c_transport_data;
const union rds_ib_conn_priv *dp = NULL;
struct ib_qp_attr qp_attr; struct ib_qp_attr qp_attr;
__be64 ack_seq = 0;
__be32 credit = 0;
u8 major = 0;
u8 minor = 0;
int err; int err;
if (event->param.conn.private_data_len >= sizeof(*dp)) { dp = event->param.conn.private_data;
dp = event->param.conn.private_data; if (conn->c_isv6) {
if (event->param.conn.private_data_len >=
/* make sure it isn't empty data */ sizeof(struct rds6_ib_connect_private)) {
if (dp->dp_protocol_major) { major = dp->ricp_v6.dp_protocol_major;
rds_ib_set_protocol(conn, minor = dp->ricp_v6.dp_protocol_minor;
RDS_PROTOCOL(dp->dp_protocol_major, credit = dp->ricp_v6.dp_credit;
dp->dp_protocol_minor)); /* dp structure start is not guaranteed to be 8 bytes
rds_ib_set_flow_control(conn, be32_to_cpu(dp->dp_credit)); * aligned. Since dp_ack_seq is 64-bit extended load
* operations can be used so go through get_unaligned
* to avoid unaligned errors.
*/
ack_seq = get_unaligned(&dp->ricp_v6.dp_ack_seq);
} }
} else if (event->param.conn.private_data_len >=
sizeof(struct rds_ib_connect_private)) {
major = dp->ricp_v4.dp_protocol_major;
minor = dp->ricp_v4.dp_protocol_minor;
credit = dp->ricp_v4.dp_credit;
ack_seq = get_unaligned(&dp->ricp_v4.dp_ack_seq);
}
/* make sure it isn't empty data */
if (major) {
rds_ib_set_protocol(conn, RDS_PROTOCOL(major, minor));
rds_ib_set_flow_control(conn, be32_to_cpu(credit));
} }
if (conn->c_version < RDS_PROTOCOL(3, 1)) { if (conn->c_version < RDS_PROTOCOL(3, 1)) {
pr_notice("RDS/IB: Connection <%pI4,%pI4> version %u.%u no longer supported\n", pr_notice("RDS/IB: Connection <%pI6c,%pI6c> version %u.%u no longer supported\n",
&conn->c_laddr, &conn->c_faddr, &conn->c_laddr, &conn->c_faddr,
RDS_PROTOCOL_MAJOR(conn->c_version), RDS_PROTOCOL_MAJOR(conn->c_version),
RDS_PROTOCOL_MINOR(conn->c_version)); RDS_PROTOCOL_MINOR(conn->c_version));
@ -121,7 +142,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
rds_conn_destroy(conn); rds_conn_destroy(conn);
return; return;
} else { } else {
pr_notice("RDS/IB: %s conn connected <%pI4,%pI4> version %u.%u%s\n", pr_notice("RDS/IB: %s conn connected <%pI6c,%pI6c> version %u.%u%s\n",
ic->i_active_side ? "Active" : "Passive", ic->i_active_side ? "Active" : "Passive",
&conn->c_laddr, &conn->c_faddr, &conn->c_laddr, &conn->c_faddr,
RDS_PROTOCOL_MAJOR(conn->c_version), RDS_PROTOCOL_MAJOR(conn->c_version),
@ -150,7 +171,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
printk(KERN_NOTICE "ib_modify_qp(IB_QP_STATE, RTS): err=%d\n", err); printk(KERN_NOTICE "ib_modify_qp(IB_QP_STATE, RTS): err=%d\n", err);
/* update ib_device with this local ipaddr */ /* update ib_device with this local ipaddr */
err = rds_ib_update_ipaddr(ic->rds_ibdev, conn->c_laddr); err = rds_ib_update_ipaddr(ic->rds_ibdev, &conn->c_laddr);
if (err) if (err)
printk(KERN_ERR "rds_ib_update_ipaddr failed (%d)\n", printk(KERN_ERR "rds_ib_update_ipaddr failed (%d)\n",
err); err);
@ -158,14 +179,8 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
/* If the peer gave us the last packet it saw, process this as if /* If the peer gave us the last packet it saw, process this as if
* we had received a regular ACK. */ * we had received a regular ACK. */
if (dp) { if (dp) {
/* dp structure start is not guaranteed to be 8 bytes aligned. if (ack_seq)
* Since dp_ack_seq is 64-bit extended load operations can be rds_send_drop_acked(conn, be64_to_cpu(ack_seq),
* used so go through get_unaligned to avoid unaligned errors.
*/
__be64 dp_ack_seq = get_unaligned(&dp->dp_ack_seq);
if (dp_ack_seq)
rds_send_drop_acked(conn, be64_to_cpu(dp_ack_seq),
NULL); NULL);
} }
@ -173,11 +188,12 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
} }
static void rds_ib_cm_fill_conn_param(struct rds_connection *conn, static void rds_ib_cm_fill_conn_param(struct rds_connection *conn,
struct rdma_conn_param *conn_param, struct rdma_conn_param *conn_param,
struct rds_ib_connect_private *dp, union rds_ib_conn_priv *dp,
u32 protocol_version, u32 protocol_version,
u32 max_responder_resources, u32 max_responder_resources,
u32 max_initiator_depth) u32 max_initiator_depth,
bool isv6)
{ {
struct rds_ib_connection *ic = conn->c_transport_data; struct rds_ib_connection *ic = conn->c_transport_data;
struct rds_ib_device *rds_ibdev = ic->rds_ibdev; struct rds_ib_device *rds_ibdev = ic->rds_ibdev;
@ -193,24 +209,49 @@ static void rds_ib_cm_fill_conn_param(struct rds_connection *conn,
if (dp) { if (dp) {
memset(dp, 0, sizeof(*dp)); memset(dp, 0, sizeof(*dp));
dp->dp_saddr = conn->c_laddr; if (isv6) {
dp->dp_daddr = conn->c_faddr; dp->ricp_v6.dp_saddr = conn->c_laddr;
dp->dp_protocol_major = RDS_PROTOCOL_MAJOR(protocol_version); dp->ricp_v6.dp_daddr = conn->c_faddr;
dp->dp_protocol_minor = RDS_PROTOCOL_MINOR(protocol_version); dp->ricp_v6.dp_protocol_major =
dp->dp_protocol_minor_mask = cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS); RDS_PROTOCOL_MAJOR(protocol_version);
dp->dp_ack_seq = cpu_to_be64(rds_ib_piggyb_ack(ic)); dp->ricp_v6.dp_protocol_minor =
RDS_PROTOCOL_MINOR(protocol_version);
dp->ricp_v6.dp_protocol_minor_mask =
cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS);
dp->ricp_v6.dp_ack_seq =
cpu_to_be64(rds_ib_piggyb_ack(ic));
conn_param->private_data = &dp->ricp_v6;
conn_param->private_data_len = sizeof(dp->ricp_v6);
} else {
dp->ricp_v4.dp_saddr = conn->c_laddr.s6_addr32[3];
dp->ricp_v4.dp_daddr = conn->c_faddr.s6_addr32[3];
dp->ricp_v4.dp_protocol_major =
RDS_PROTOCOL_MAJOR(protocol_version);
dp->ricp_v4.dp_protocol_minor =
RDS_PROTOCOL_MINOR(protocol_version);
dp->ricp_v4.dp_protocol_minor_mask =
cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS);
dp->ricp_v4.dp_ack_seq =
cpu_to_be64(rds_ib_piggyb_ack(ic));
conn_param->private_data = &dp->ricp_v4;
conn_param->private_data_len = sizeof(dp->ricp_v4);
}
/* Advertise flow control */ /* Advertise flow control */
if (ic->i_flowctl) { if (ic->i_flowctl) {
unsigned int credits; unsigned int credits;
credits = IB_GET_POST_CREDITS(atomic_read(&ic->i_credits)); credits = IB_GET_POST_CREDITS
dp->dp_credit = cpu_to_be32(credits); (atomic_read(&ic->i_credits));
atomic_sub(IB_SET_POST_CREDITS(credits), &ic->i_credits); if (isv6)
dp->ricp_v6.dp_credit = cpu_to_be32(credits);
else
dp->ricp_v4.dp_credit = cpu_to_be32(credits);
atomic_sub(IB_SET_POST_CREDITS(credits),
&ic->i_credits);
} }
conn_param->private_data = dp;
conn_param->private_data_len = sizeof(*dp);
} }
} }
@ -349,7 +390,7 @@ static void rds_ib_qp_event_handler(struct ib_event *event, void *data)
break; break;
default: default:
rdsdebug("Fatal QP Event %u (%s) " rdsdebug("Fatal QP Event %u (%s) "
"- connection %pI4->%pI4, reconnecting\n", "- connection %pI6c->%pI6c, reconnecting\n",
event->event, ib_event_msg(event->event), event->event, ib_event_msg(event->event),
&conn->c_laddr, &conn->c_faddr); &conn->c_laddr, &conn->c_faddr);
rds_conn_drop(conn); rds_conn_drop(conn);
@ -580,11 +621,13 @@ out:
return ret; return ret;
} }
static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event) static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event, bool isv6)
{ {
const struct rds_ib_connect_private *dp = event->param.conn.private_data; const union rds_ib_conn_priv *dp = event->param.conn.private_data;
u16 common; u8 data_len, major, minor;
u32 version = 0; u32 version = 0;
__be16 mask;
u16 common;
/* /*
* rdma_cm private data is odd - when there is any private data in the * rdma_cm private data is odd - when there is any private data in the
@ -603,51 +646,126 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event)
return 0; return 0;
} }
if (isv6) {
data_len = sizeof(struct rds6_ib_connect_private);
major = dp->ricp_v6.dp_protocol_major;
minor = dp->ricp_v6.dp_protocol_minor;
mask = dp->ricp_v6.dp_protocol_minor_mask;
} else {
data_len = sizeof(struct rds_ib_connect_private);
major = dp->ricp_v4.dp_protocol_major;
minor = dp->ricp_v4.dp_protocol_minor;
mask = dp->ricp_v4.dp_protocol_minor_mask;
}
/* Even if len is crap *now* I still want to check it. -ASG */ /* Even if len is crap *now* I still want to check it. -ASG */
if (event->param.conn.private_data_len < sizeof (*dp) || if (event->param.conn.private_data_len < data_len || major == 0)
dp->dp_protocol_major == 0)
return RDS_PROTOCOL_3_0; return RDS_PROTOCOL_3_0;
common = be16_to_cpu(dp->dp_protocol_minor_mask) & RDS_IB_SUPPORTED_PROTOCOLS; common = be16_to_cpu(mask) & RDS_IB_SUPPORTED_PROTOCOLS;
if (dp->dp_protocol_major == 3 && common) { if (major == 3 && common) {
version = RDS_PROTOCOL_3_0; version = RDS_PROTOCOL_3_0;
while ((common >>= 1) != 0) while ((common >>= 1) != 0)
version++; version++;
} else } else {
printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI4 using incompatible protocol version %u.%u\n", if (isv6)
&dp->dp_saddr, printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI6c using incompatible protocol version %u.%u\n",
dp->dp_protocol_major, &dp->ricp_v6.dp_saddr, major, minor);
dp->dp_protocol_minor); else
printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI4 using incompatible protocol version %u.%u\n",
&dp->ricp_v4.dp_saddr, major, minor);
}
return version; return version;
} }
/* Given an IPv6 address, find the IB net_device which hosts that address and
* return its index. This is used by the rds_ib_cm_handle_connect() code to
* find the interface index of where an incoming request comes from when
* the request is using a link local address.
*
* Note one problem in this search. It is possible that two interfaces have
* the same link local address. Unfortunately, this cannot be solved unless
* the underlying layer gives us the interface which an incoming RDMA connect
* request comes from.
*/
static u32 __rds_find_ifindex(struct net *net, const struct in6_addr *addr)
{
struct net_device *dev;
int idx = 0;
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
if (dev->type == ARPHRD_INFINIBAND &&
ipv6_chk_addr(net, addr, dev, 0)) {
idx = dev->ifindex;
break;
}
}
rcu_read_unlock();
return idx;
}
int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
struct rdma_cm_event *event) struct rdma_cm_event *event, bool isv6)
{ {
__be64 lguid = cm_id->route.path_rec->sgid.global.interface_id; __be64 lguid = cm_id->route.path_rec->sgid.global.interface_id;
__be64 fguid = cm_id->route.path_rec->dgid.global.interface_id; __be64 fguid = cm_id->route.path_rec->dgid.global.interface_id;
const struct rds_ib_connect_private *dp = event->param.conn.private_data; const struct rds_ib_conn_priv_cmn *dp_cmn;
struct rds_ib_connect_private dp_rep;
struct rds_connection *conn = NULL; struct rds_connection *conn = NULL;
struct rds_ib_connection *ic = NULL; struct rds_ib_connection *ic = NULL;
struct rdma_conn_param conn_param; struct rdma_conn_param conn_param;
const union rds_ib_conn_priv *dp;
union rds_ib_conn_priv dp_rep;
struct in6_addr s_mapped_addr;
struct in6_addr d_mapped_addr;
const struct in6_addr *saddr6;
const struct in6_addr *daddr6;
int destroy = 1;
u32 ifindex = 0;
u32 version; u32 version;
int err = 1, destroy = 1; int err = 1;
/* Check whether the remote protocol version matches ours. */ /* Check whether the remote protocol version matches ours. */
version = rds_ib_protocol_compatible(event); version = rds_ib_protocol_compatible(event, isv6);
if (!version) if (!version)
goto out; goto out;
rdsdebug("saddr %pI4 daddr %pI4 RDSv%u.%u lguid 0x%llx fguid " dp = event->param.conn.private_data;
"0x%llx\n", &dp->dp_saddr, &dp->dp_daddr, if (isv6) {
dp_cmn = &dp->ricp_v6.dp_cmn;
saddr6 = &dp->ricp_v6.dp_saddr;
daddr6 = &dp->ricp_v6.dp_daddr;
/* If the local address is link local, need to find the
* interface index in order to create a proper RDS
* connection.
*/
if (ipv6_addr_type(daddr6) & IPV6_ADDR_LINKLOCAL) {
/* Using init_net for now .. */
ifindex = __rds_find_ifindex(&init_net, daddr6);
/* No index found... Need to bail out. */
if (ifindex == 0) {
err = -EOPNOTSUPP;
goto out;
}
}
} else {
dp_cmn = &dp->ricp_v4.dp_cmn;
ipv6_addr_set_v4mapped(dp->ricp_v4.dp_saddr, &s_mapped_addr);
ipv6_addr_set_v4mapped(dp->ricp_v4.dp_daddr, &d_mapped_addr);
saddr6 = &s_mapped_addr;
daddr6 = &d_mapped_addr;
}
rdsdebug("saddr %pI6c daddr %pI6c RDSv%u.%u lguid 0x%llx fguid "
"0x%llx\n", saddr6, daddr6,
RDS_PROTOCOL_MAJOR(version), RDS_PROTOCOL_MINOR(version), RDS_PROTOCOL_MAJOR(version), RDS_PROTOCOL_MINOR(version),
(unsigned long long)be64_to_cpu(lguid), (unsigned long long)be64_to_cpu(lguid),
(unsigned long long)be64_to_cpu(fguid)); (unsigned long long)be64_to_cpu(fguid));
/* RDS/IB is not currently netns aware, thus init_net */ /* RDS/IB is not currently netns aware, thus init_net */
conn = rds_conn_create(&init_net, dp->dp_daddr, dp->dp_saddr, conn = rds_conn_create(&init_net, daddr6, saddr6,
&rds_ib_transport, GFP_KERNEL); &rds_ib_transport, GFP_KERNEL, ifindex);
if (IS_ERR(conn)) { if (IS_ERR(conn)) {
rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn)); rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn));
conn = NULL; conn = NULL;
@ -678,12 +796,13 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
ic = conn->c_transport_data; ic = conn->c_transport_data;
rds_ib_set_protocol(conn, version); rds_ib_set_protocol(conn, version);
rds_ib_set_flow_control(conn, be32_to_cpu(dp->dp_credit)); rds_ib_set_flow_control(conn, be32_to_cpu(dp_cmn->ricpc_credit));
/* If the peer gave us the last packet it saw, process this as if /* If the peer gave us the last packet it saw, process this as if
* we had received a regular ACK. */ * we had received a regular ACK. */
if (dp->dp_ack_seq) if (dp_cmn->ricpc_ack_seq)
rds_send_drop_acked(conn, be64_to_cpu(dp->dp_ack_seq), NULL); rds_send_drop_acked(conn, be64_to_cpu(dp_cmn->ricpc_ack_seq),
NULL);
BUG_ON(cm_id->context); BUG_ON(cm_id->context);
BUG_ON(ic->i_cm_id); BUG_ON(ic->i_cm_id);
@ -702,8 +821,8 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
} }
rds_ib_cm_fill_conn_param(conn, &conn_param, &dp_rep, version, rds_ib_cm_fill_conn_param(conn, &conn_param, &dp_rep, version,
event->param.conn.responder_resources, event->param.conn.responder_resources,
event->param.conn.initiator_depth); event->param.conn.initiator_depth, isv6);
/* rdma_accept() calls rdma_reject() internally if it fails */ /* rdma_accept() calls rdma_reject() internally if it fails */
if (rdma_accept(cm_id, &conn_param)) if (rdma_accept(cm_id, &conn_param))
@ -718,12 +837,12 @@ out:
} }
int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id) int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6)
{ {
struct rds_connection *conn = cm_id->context; struct rds_connection *conn = cm_id->context;
struct rds_ib_connection *ic = conn->c_transport_data; struct rds_ib_connection *ic = conn->c_transport_data;
struct rdma_conn_param conn_param; struct rdma_conn_param conn_param;
struct rds_ib_connect_private dp; union rds_ib_conn_priv dp;
int ret; int ret;
/* If the peer doesn't do protocol negotiation, we must /* If the peer doesn't do protocol negotiation, we must
@ -738,7 +857,7 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id)
} }
rds_ib_cm_fill_conn_param(conn, &conn_param, &dp, RDS_PROTOCOL_VERSION, rds_ib_cm_fill_conn_param(conn, &conn_param, &dp, RDS_PROTOCOL_VERSION,
UINT_MAX, UINT_MAX); UINT_MAX, UINT_MAX, isv6);
ret = rdma_connect(cm_id, &conn_param); ret = rdma_connect(cm_id, &conn_param);
if (ret) if (ret)
rds_ib_conn_error(conn, "rdma_connect failed (%d)\n", ret); rds_ib_conn_error(conn, "rdma_connect failed (%d)\n", ret);
@ -758,13 +877,17 @@ out:
int rds_ib_conn_path_connect(struct rds_conn_path *cp) int rds_ib_conn_path_connect(struct rds_conn_path *cp)
{ {
struct rds_connection *conn = cp->cp_conn; struct rds_connection *conn = cp->cp_conn;
struct rds_ib_connection *ic = conn->c_transport_data; struct sockaddr_storage src, dest;
struct sockaddr_in src, dest; rdma_cm_event_handler handler;
struct rds_ib_connection *ic;
int ret; int ret;
ic = conn->c_transport_data;
/* XXX I wonder what affect the port space has */ /* XXX I wonder what affect the port space has */
/* delegate cm event handler to rdma_transport */ /* delegate cm event handler to rdma_transport */
ic->i_cm_id = rdma_create_id(&init_net, rds_rdma_cm_event_handler, conn, handler = rds_rdma_cm_event_handler;
ic->i_cm_id = rdma_create_id(&init_net, handler, conn,
RDMA_PS_TCP, IB_QPT_RC); RDMA_PS_TCP, IB_QPT_RC);
if (IS_ERR(ic->i_cm_id)) { if (IS_ERR(ic->i_cm_id)) {
ret = PTR_ERR(ic->i_cm_id); ret = PTR_ERR(ic->i_cm_id);
@ -775,13 +898,33 @@ int rds_ib_conn_path_connect(struct rds_conn_path *cp)
rdsdebug("created cm id %p for conn %p\n", ic->i_cm_id, conn); rdsdebug("created cm id %p for conn %p\n", ic->i_cm_id, conn);
src.sin_family = AF_INET; if (ipv6_addr_v4mapped(&conn->c_faddr)) {
src.sin_addr.s_addr = (__force u32)conn->c_laddr; struct sockaddr_in *sin;
src.sin_port = (__force u16)htons(0);
dest.sin_family = AF_INET; sin = (struct sockaddr_in *)&src;
dest.sin_addr.s_addr = (__force u32)conn->c_faddr; sin->sin_family = AF_INET;
dest.sin_port = (__force u16)htons(RDS_PORT); sin->sin_addr.s_addr = conn->c_laddr.s6_addr32[3];
sin->sin_port = 0;
sin = (struct sockaddr_in *)&dest;
sin->sin_family = AF_INET;
sin->sin_addr.s_addr = conn->c_faddr.s6_addr32[3];
sin->sin_port = htons(RDS_PORT);
} else {
struct sockaddr_in6 *sin6;
sin6 = (struct sockaddr_in6 *)&src;
sin6->sin6_family = AF_INET6;
sin6->sin6_addr = conn->c_laddr;
sin6->sin6_port = 0;
sin6->sin6_scope_id = conn->c_dev_if;
sin6 = (struct sockaddr_in6 *)&dest;
sin6->sin6_family = AF_INET6;
sin6->sin6_addr = conn->c_faddr;
sin6->sin6_port = htons(RDS_CM_PORT);
sin6->sin6_scope_id = conn->c_dev_if;
}
ret = rdma_resolve_addr(ic->i_cm_id, (struct sockaddr *)&src, ret = rdma_resolve_addr(ic->i_cm_id, (struct sockaddr *)&src,
(struct sockaddr *)&dest, (struct sockaddr *)&dest,

15
net/rds/ib_rdma.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -100,18 +100,19 @@ static void rds_ib_remove_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr)
kfree_rcu(to_free, rcu); kfree_rcu(to_free, rcu);
} }
int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr) int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev,
struct in6_addr *ipaddr)
{ {
struct rds_ib_device *rds_ibdev_old; struct rds_ib_device *rds_ibdev_old;
rds_ibdev_old = rds_ib_get_device(ipaddr); rds_ibdev_old = rds_ib_get_device(ipaddr->s6_addr32[3]);
if (!rds_ibdev_old) if (!rds_ibdev_old)
return rds_ib_add_ipaddr(rds_ibdev, ipaddr); return rds_ib_add_ipaddr(rds_ibdev, ipaddr->s6_addr32[3]);
if (rds_ibdev_old != rds_ibdev) { if (rds_ibdev_old != rds_ibdev) {
rds_ib_remove_ipaddr(rds_ibdev_old, ipaddr); rds_ib_remove_ipaddr(rds_ibdev_old, ipaddr->s6_addr32[3]);
rds_ib_dev_put(rds_ibdev_old); rds_ib_dev_put(rds_ibdev_old);
return rds_ib_add_ipaddr(rds_ibdev, ipaddr); return rds_ib_add_ipaddr(rds_ibdev, ipaddr->s6_addr32[3]);
} }
rds_ib_dev_put(rds_ibdev_old); rds_ib_dev_put(rds_ibdev_old);
@ -544,7 +545,7 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
struct rds_ib_connection *ic = rs->rs_conn->c_transport_data; struct rds_ib_connection *ic = rs->rs_conn->c_transport_data;
int ret; int ret;
rds_ibdev = rds_ib_get_device(rs->rs_bound_addr); rds_ibdev = rds_ib_get_device(rs->rs_bound_addr.s6_addr32[3]);
if (!rds_ibdev) { if (!rds_ibdev) {
ret = -ENODEV; ret = -ENODEV;
goto out; goto out;

18
net/rds/ib_recv.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -266,7 +266,7 @@ static struct rds_ib_incoming *rds_ib_refill_one_inc(struct rds_ib_connection *i
rds_ib_stats_inc(s_ib_rx_total_incs); rds_ib_stats_inc(s_ib_rx_total_incs);
} }
INIT_LIST_HEAD(&ibinc->ii_frags); INIT_LIST_HEAD(&ibinc->ii_frags);
rds_inc_init(&ibinc->ii_inc, ic->conn, ic->conn->c_faddr); rds_inc_init(&ibinc->ii_inc, ic->conn, &ic->conn->c_faddr);
return ibinc; return ibinc;
} }
@ -418,7 +418,7 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp)
ret = ib_post_recv(ic->i_cm_id->qp, &recv->r_wr, &failed_wr); ret = ib_post_recv(ic->i_cm_id->qp, &recv->r_wr, &failed_wr);
if (ret) { if (ret) {
rds_ib_conn_error(conn, "recv post on " rds_ib_conn_error(conn, "recv post on "
"%pI4 returned %d, disconnecting and " "%pI6c returned %d, disconnecting and "
"reconnecting\n", &conn->c_faddr, "reconnecting\n", &conn->c_faddr,
ret); ret);
break; break;
@ -848,7 +848,7 @@ static void rds_ib_process_recv(struct rds_connection *conn,
if (data_len < sizeof(struct rds_header)) { if (data_len < sizeof(struct rds_header)) {
rds_ib_conn_error(conn, "incoming message " rds_ib_conn_error(conn, "incoming message "
"from %pI4 didn't include a " "from %pI6c didn't include a "
"header, disconnecting and " "header, disconnecting and "
"reconnecting\n", "reconnecting\n",
&conn->c_faddr); &conn->c_faddr);
@ -861,7 +861,7 @@ static void rds_ib_process_recv(struct rds_connection *conn,
/* Validate the checksum. */ /* Validate the checksum. */
if (!rds_message_verify_checksum(ihdr)) { if (!rds_message_verify_checksum(ihdr)) {
rds_ib_conn_error(conn, "incoming message " rds_ib_conn_error(conn, "incoming message "
"from %pI4 has corrupted header - " "from %pI6c has corrupted header - "
"forcing a reconnect\n", "forcing a reconnect\n",
&conn->c_faddr); &conn->c_faddr);
rds_stats_inc(s_recv_drop_bad_checksum); rds_stats_inc(s_recv_drop_bad_checksum);
@ -941,10 +941,10 @@ static void rds_ib_process_recv(struct rds_connection *conn,
ic->i_recv_data_rem = 0; ic->i_recv_data_rem = 0;
ic->i_ibinc = NULL; ic->i_ibinc = NULL;
if (ibinc->ii_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP) if (ibinc->ii_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP) {
rds_ib_cong_recv(conn, ibinc); rds_ib_cong_recv(conn, ibinc);
else { } else {
rds_recv_incoming(conn, conn->c_faddr, conn->c_laddr, rds_recv_incoming(conn, &conn->c_faddr, &conn->c_laddr,
&ibinc->ii_inc, GFP_ATOMIC); &ibinc->ii_inc, GFP_ATOMIC);
state->ack_next = be64_to_cpu(hdr->h_sequence); state->ack_next = be64_to_cpu(hdr->h_sequence);
state->ack_next_valid = 1; state->ack_next_valid = 1;
@ -988,7 +988,7 @@ void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic,
} else { } else {
/* We expect errors as the qp is drained during shutdown */ /* We expect errors as the qp is drained during shutdown */
if (rds_conn_up(conn) || rds_conn_connecting(conn)) if (rds_conn_up(conn) || rds_conn_connecting(conn))
rds_ib_conn_error(conn, "recv completion on <%pI4,%pI4> had status %u (%s), disconnecting and reconnecting\n", rds_ib_conn_error(conn, "recv completion on <%pI6c,%pI6c> had status %u (%s), disconnecting and reconnecting\n",
&conn->c_laddr, &conn->c_faddr, &conn->c_laddr, &conn->c_faddr,
wc->status, wc->status,
ib_wc_status_msg(wc->status)); ib_wc_status_msg(wc->status));

10
net/rds/ib_send.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -305,7 +305,7 @@ void rds_ib_send_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc)
/* We expect errors as the qp is drained during shutdown */ /* We expect errors as the qp is drained during shutdown */
if (wc->status != IB_WC_SUCCESS && rds_conn_up(conn)) { if (wc->status != IB_WC_SUCCESS && rds_conn_up(conn)) {
rds_ib_conn_error(conn, "send completion on <%pI4,%pI4> had status %u (%s), disconnecting and reconnecting\n", rds_ib_conn_error(conn, "send completion on <%pI6c,%pI6c> had status %u (%s), disconnecting and reconnecting\n",
&conn->c_laddr, &conn->c_faddr, wc->status, &conn->c_laddr, &conn->c_faddr, wc->status,
ib_wc_status_msg(wc->status)); ib_wc_status_msg(wc->status));
} }
@ -730,7 +730,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm,
first, &first->s_wr, ret, failed_wr); first, &first->s_wr, ret, failed_wr);
BUG_ON(failed_wr != &first->s_wr); BUG_ON(failed_wr != &first->s_wr);
if (ret) { if (ret) {
printk(KERN_WARNING "RDS/IB: ib_post_send to %pI4 " printk(KERN_WARNING "RDS/IB: ib_post_send to %pI6c "
"returned %d\n", &conn->c_faddr, ret); "returned %d\n", &conn->c_faddr, ret);
rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc); rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc);
rds_ib_sub_signaled(ic, nr_sig); rds_ib_sub_signaled(ic, nr_sig);
@ -827,7 +827,7 @@ int rds_ib_xmit_atomic(struct rds_connection *conn, struct rm_atomic_op *op)
send, &send->s_atomic_wr, ret, failed_wr); send, &send->s_atomic_wr, ret, failed_wr);
BUG_ON(failed_wr != &send->s_atomic_wr.wr); BUG_ON(failed_wr != &send->s_atomic_wr.wr);
if (ret) { if (ret) {
printk(KERN_WARNING "RDS/IB: atomic ib_post_send to %pI4 " printk(KERN_WARNING "RDS/IB: atomic ib_post_send to %pI6c "
"returned %d\n", &conn->c_faddr, ret); "returned %d\n", &conn->c_faddr, ret);
rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc); rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc);
rds_ib_sub_signaled(ic, nr_sig); rds_ib_sub_signaled(ic, nr_sig);
@ -967,7 +967,7 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op)
first, &first->s_rdma_wr.wr, ret, failed_wr); first, &first->s_rdma_wr.wr, ret, failed_wr);
BUG_ON(failed_wr != &first->s_rdma_wr.wr); BUG_ON(failed_wr != &first->s_rdma_wr.wr);
if (ret) { if (ret) {
printk(KERN_WARNING "RDS/IB: rdma ib_post_send to %pI4 " printk(KERN_WARNING "RDS/IB: rdma ib_post_send to %pI6c "
"returned %d\n", &conn->c_faddr, ret); "returned %d\n", &conn->c_faddr, ret);
rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc); rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc);
rds_ib_sub_signaled(ic, nr_sig); rds_ib_sub_signaled(ic, nr_sig);

7
net/rds/loop.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -35,6 +35,7 @@
#include <linux/in.h> #include <linux/in.h>
#include <net/net_namespace.h> #include <net/net_namespace.h>
#include <net/netns/generic.h> #include <net/netns/generic.h>
#include <linux/ipv6.h>
#include "rds_single_path.h" #include "rds_single_path.h"
#include "rds.h" #include "rds.h"
@ -88,11 +89,11 @@ static int rds_loop_xmit(struct rds_connection *conn, struct rds_message *rm,
BUG_ON(hdr_off || sg || off); BUG_ON(hdr_off || sg || off);
rds_inc_init(&rm->m_inc, conn, conn->c_laddr); rds_inc_init(&rm->m_inc, conn, &conn->c_laddr);
/* For the embedded inc. Matching put is in loop_inc_free() */ /* For the embedded inc. Matching put is in loop_inc_free() */
rds_message_addref(rm); rds_message_addref(rm);
rds_recv_incoming(conn, conn->c_laddr, conn->c_faddr, &rm->m_inc, rds_recv_incoming(conn, &conn->c_laddr, &conn->c_faddr, &rm->m_inc,
GFP_KERNEL); GFP_KERNEL);
rds_send_drop_acked(conn, be64_to_cpu(rm->m_inc.i_hdr.h_sequence), rds_send_drop_acked(conn, be64_to_cpu(rm->m_inc.i_hdr.h_sequence),

6
net/rds/rdma.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2007 Oracle. All rights reserved. * Copyright (c) 2007, 2017 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -183,7 +183,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
long i; long i;
int ret; int ret;
if (rs->rs_bound_addr == 0 || !rs->rs_transport) { if (ipv6_addr_any(&rs->rs_bound_addr) || !rs->rs_transport) {
ret = -ENOTCONN; /* XXX not a great errno */ ret = -ENOTCONN; /* XXX not a great errno */
goto out; goto out;
} }
@ -574,7 +574,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
args = CMSG_DATA(cmsg); args = CMSG_DATA(cmsg);
if (rs->rs_bound_addr == 0) { if (ipv6_addr_any(&rs->rs_bound_addr)) {
ret = -ENOTCONN; /* XXX not a great errno */ ret = -ENOTCONN; /* XXX not a great errno */
goto out_ret; goto out_ret;
} }

56
net/rds/rdma_transport.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2009 Oracle. All rights reserved. * Copyright (c) 2009, 2018 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -39,8 +39,9 @@
static struct rdma_cm_id *rds_rdma_listen_id; static struct rdma_cm_id *rds_rdma_listen_id;
int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
struct rdma_cm_event *event) struct rdma_cm_event *event,
bool isv6)
{ {
/* this can be null in the listening path */ /* this can be null in the listening path */
struct rds_connection *conn = cm_id->context; struct rds_connection *conn = cm_id->context;
@ -72,7 +73,7 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
switch (event->event) { switch (event->event) {
case RDMA_CM_EVENT_CONNECT_REQUEST: case RDMA_CM_EVENT_CONNECT_REQUEST:
ret = trans->cm_handle_connect(cm_id, event); ret = trans->cm_handle_connect(cm_id, event, isv6);
break; break;
case RDMA_CM_EVENT_ADDR_RESOLVED: case RDMA_CM_EVENT_ADDR_RESOLVED:
@ -90,7 +91,7 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
ibic = conn->c_transport_data; ibic = conn->c_transport_data;
if (ibic && ibic->i_cm_id == cm_id) if (ibic && ibic->i_cm_id == cm_id)
ret = trans->cm_initiate_connect(cm_id); ret = trans->cm_initiate_connect(cm_id, isv6);
else else
rds_conn_drop(conn); rds_conn_drop(conn);
} }
@ -116,14 +117,14 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
case RDMA_CM_EVENT_DISCONNECTED: case RDMA_CM_EVENT_DISCONNECTED:
rdsdebug("DISCONNECT event - dropping connection " rdsdebug("DISCONNECT event - dropping connection "
"%pI4->%pI4\n", &conn->c_laddr, "%pI6c->%pI6c\n", &conn->c_laddr,
&conn->c_faddr); &conn->c_faddr);
rds_conn_drop(conn); rds_conn_drop(conn);
break; break;
case RDMA_CM_EVENT_TIMEWAIT_EXIT: case RDMA_CM_EVENT_TIMEWAIT_EXIT:
if (conn) { if (conn) {
pr_info("RDS: RDMA_CM_EVENT_TIMEWAIT_EXIT event: dropping connection %pI4->%pI4\n", pr_info("RDS: RDMA_CM_EVENT_TIMEWAIT_EXIT event: dropping connection %pI6c->%pI6c\n",
&conn->c_laddr, &conn->c_faddr); &conn->c_laddr, &conn->c_faddr);
rds_conn_drop(conn); rds_conn_drop(conn);
} }
@ -146,13 +147,20 @@ out:
return ret; return ret;
} }
static int rds_rdma_listen_init(void) int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
struct rdma_cm_event *event)
{
return rds_rdma_cm_event_handler_cmn(cm_id, event, false);
}
static int rds_rdma_listen_init_common(rdma_cm_event_handler handler,
struct sockaddr *sa,
struct rdma_cm_id **ret_cm_id)
{ {
struct sockaddr_in sin;
struct rdma_cm_id *cm_id; struct rdma_cm_id *cm_id;
int ret; int ret;
cm_id = rdma_create_id(&init_net, rds_rdma_cm_event_handler, NULL, cm_id = rdma_create_id(&init_net, handler, NULL,
RDMA_PS_TCP, IB_QPT_RC); RDMA_PS_TCP, IB_QPT_RC);
if (IS_ERR(cm_id)) { if (IS_ERR(cm_id)) {
ret = PTR_ERR(cm_id); ret = PTR_ERR(cm_id);
@ -161,15 +169,11 @@ static int rds_rdma_listen_init(void)
return ret; return ret;
} }
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = (__force u32)htonl(INADDR_ANY);
sin.sin_port = (__force u16)htons(RDS_PORT);
/* /*
* XXX I bet this binds the cm_id to a device. If we want to support * XXX I bet this binds the cm_id to a device. If we want to support
* fail-over we'll have to take this into consideration. * fail-over we'll have to take this into consideration.
*/ */
ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin); ret = rdma_bind_addr(cm_id, sa);
if (ret) { if (ret) {
printk(KERN_ERR "RDS/RDMA: failed to setup listener, " printk(KERN_ERR "RDS/RDMA: failed to setup listener, "
"rdma_bind_addr() returned %d\n", ret); "rdma_bind_addr() returned %d\n", ret);
@ -185,7 +189,7 @@ static int rds_rdma_listen_init(void)
rdsdebug("cm %p listening on port %u\n", cm_id, RDS_PORT); rdsdebug("cm %p listening on port %u\n", cm_id, RDS_PORT);
rds_rdma_listen_id = cm_id; *ret_cm_id = cm_id;
cm_id = NULL; cm_id = NULL;
out: out:
if (cm_id) if (cm_id)
@ -193,6 +197,26 @@ out:
return ret; return ret;
} }
/* Initialize the RDS RDMA listeners. We create two listeners for
* compatibility reason. The one on RDS_PORT is used for IPv4
* requests only. The one on RDS_CM_PORT is used for IPv6 requests
* only. So only IPv6 enabled RDS module will communicate using this
* port.
*/
static int rds_rdma_listen_init(void)
{
int ret;
struct sockaddr_in sin;
sin.sin_family = PF_INET;
sin.sin_addr.s_addr = htonl(INADDR_ANY);
sin.sin_port = htons(RDS_PORT);
ret = rds_rdma_listen_init_common(rds_rdma_cm_event_handler,
(struct sockaddr *)&sin,
&rds_rdma_listen_id);
return ret;
}
static void rds_rdma_listen_stop(void) static void rds_rdma_listen_stop(void)
{ {
if (rds_rdma_listen_id) { if (rds_rdma_listen_id) {

70
net/rds/rds.h
View File

@ -10,6 +10,7 @@
#include <linux/rds.h> #include <linux/rds.h>
#include <linux/rhashtable.h> #include <linux/rhashtable.h>
#include <linux/refcount.h> #include <linux/refcount.h>
#include <linux/in6.h>
#include "info.h" #include "info.h"
@ -30,6 +31,7 @@
* userspace from listening. * userspace from listening.
*/ */
#define RDS_PORT 18634 #define RDS_PORT 18634
#define RDS_CM_PORT 16385
#ifdef ATOMIC64_INIT #ifdef ATOMIC64_INIT
#define KERNEL_HAS_ATOMIC64 #define KERNEL_HAS_ATOMIC64
@ -61,7 +63,7 @@ void rdsdebug(char *fmt, ...)
struct rds_cong_map { struct rds_cong_map {
struct rb_node m_rb_node; struct rb_node m_rb_node;
__be32 m_addr; struct in6_addr m_addr;
wait_queue_head_t m_waitq; wait_queue_head_t m_waitq;
struct list_head m_conn_list; struct list_head m_conn_list;
unsigned long m_page_addrs[RDS_CONG_MAP_PAGES]; unsigned long m_page_addrs[RDS_CONG_MAP_PAGES];
@ -136,11 +138,13 @@ struct rds_conn_path {
/* One rds_connection per RDS address pair */ /* One rds_connection per RDS address pair */
struct rds_connection { struct rds_connection {
struct hlist_node c_hash_node; struct hlist_node c_hash_node;
__be32 c_laddr; struct in6_addr c_laddr;
__be32 c_faddr; struct in6_addr c_faddr;
int c_dev_if; /* c_laddrs's interface index */
unsigned int c_loopback:1, unsigned int c_loopback:1,
c_isv6:1,
c_ping_triggered:1, c_ping_triggered:1,
c_pad_to_32:30; c_pad_to_32:29;
int c_npaths; int c_npaths;
struct rds_connection *c_passive; struct rds_connection *c_passive;
struct rds_transport *c_trans; struct rds_transport *c_trans;
@ -269,7 +273,7 @@ struct rds_incoming {
struct rds_conn_path *i_conn_path; struct rds_conn_path *i_conn_path;
struct rds_header i_hdr; struct rds_header i_hdr;
unsigned long i_rx_jiffies; unsigned long i_rx_jiffies;
__be32 i_saddr; struct in6_addr i_saddr;
rds_rdma_cookie_t i_rdma_cookie; rds_rdma_cookie_t i_rdma_cookie;
struct timeval i_rx_tstamp; struct timeval i_rx_tstamp;
@ -386,7 +390,7 @@ struct rds_message {
struct list_head m_conn_item; struct list_head m_conn_item;
struct rds_incoming m_inc; struct rds_incoming m_inc;
u64 m_ack_seq; u64 m_ack_seq;
__be32 m_daddr; struct in6_addr m_daddr;
unsigned long m_flags; unsigned long m_flags;
/* Never access m_rs without holding m_rs_lock. /* Never access m_rs without holding m_rs_lock.
@ -519,7 +523,8 @@ struct rds_transport {
t_mp_capable:1; t_mp_capable:1;
unsigned int t_type; unsigned int t_type;
int (*laddr_check)(struct net *net, __be32 addr); int (*laddr_check)(struct net *net, const struct in6_addr *addr,
__u32 scope_id);
int (*conn_alloc)(struct rds_connection *conn, gfp_t gfp); int (*conn_alloc)(struct rds_connection *conn, gfp_t gfp);
void (*conn_free)(void *data); void (*conn_free)(void *data);
int (*conn_path_connect)(struct rds_conn_path *cp); int (*conn_path_connect)(struct rds_conn_path *cp);
@ -535,8 +540,8 @@ struct rds_transport {
void (*inc_free)(struct rds_incoming *inc); void (*inc_free)(struct rds_incoming *inc);
int (*cm_handle_connect)(struct rdma_cm_id *cm_id, int (*cm_handle_connect)(struct rdma_cm_id *cm_id,
struct rdma_cm_event *event); struct rdma_cm_event *event, bool isv6);
int (*cm_initiate_connect)(struct rdma_cm_id *cm_id); int (*cm_initiate_connect)(struct rdma_cm_id *cm_id, bool isv6);
void (*cm_connect_complete)(struct rds_connection *conn, void (*cm_connect_complete)(struct rds_connection *conn,
struct rdma_cm_event *event); struct rdma_cm_event *event);
@ -551,6 +556,12 @@ struct rds_transport {
bool (*t_unloading)(struct rds_connection *conn); bool (*t_unloading)(struct rds_connection *conn);
}; };
/* Bind hash table key length. It is the sum of the size of a struct
* in6_addr, a scope_id and a port.
*/
#define RDS_BOUND_KEY_LEN \
(sizeof(struct in6_addr) + sizeof(__u32) + sizeof(__be16))
struct rds_sock { struct rds_sock {
struct sock rs_sk; struct sock rs_sk;
@ -562,10 +573,14 @@ struct rds_sock {
* support. * support.
*/ */
struct rhash_head rs_bound_node; struct rhash_head rs_bound_node;
u64 rs_bound_key; u8 rs_bound_key[RDS_BOUND_KEY_LEN];
__be32 rs_bound_addr; struct sockaddr_in6 rs_bound_sin6;
__be32 rs_conn_addr; #define rs_bound_addr rs_bound_sin6.sin6_addr
__be16 rs_bound_port; #define rs_bound_addr_v4 rs_bound_sin6.sin6_addr.s6_addr32[3]
#define rs_bound_port rs_bound_sin6.sin6_port
#define rs_bound_scope_id rs_bound_sin6.sin6_scope_id
struct in6_addr rs_conn_addr;
#define rs_conn_addr_v4 rs_conn_addr.s6_addr32[3]
__be16 rs_conn_port; __be16 rs_conn_port;
struct rds_transport *rs_transport; struct rds_transport *rs_transport;
@ -701,7 +716,8 @@ extern wait_queue_head_t rds_poll_waitq;
/* bind.c */ /* bind.c */
int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
void rds_remove_bound(struct rds_sock *rs); void rds_remove_bound(struct rds_sock *rs);
struct rds_sock *rds_find_bound(__be32 addr, __be16 port); struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port,
__u32 scope_id);
int rds_bind_lock_init(void); int rds_bind_lock_init(void);
void rds_bind_lock_destroy(void); void rds_bind_lock_destroy(void);
@ -725,11 +741,15 @@ extern u32 rds_gen_num;
int rds_conn_init(void); int rds_conn_init(void);
void rds_conn_exit(void); void rds_conn_exit(void);
struct rds_connection *rds_conn_create(struct net *net, struct rds_connection *rds_conn_create(struct net *net,
__be32 laddr, __be32 faddr, const struct in6_addr *laddr,
struct rds_transport *trans, gfp_t gfp); const struct in6_addr *faddr,
struct rds_transport *trans, gfp_t gfp,
int dev_if);
struct rds_connection *rds_conn_create_outgoing(struct net *net, struct rds_connection *rds_conn_create_outgoing(struct net *net,
__be32 laddr, __be32 faddr, const struct in6_addr *laddr,
struct rds_transport *trans, gfp_t gfp); const struct in6_addr *faddr,
struct rds_transport *trans,
gfp_t gfp, int dev_if);
void rds_conn_shutdown(struct rds_conn_path *cpath); void rds_conn_shutdown(struct rds_conn_path *cpath);
void rds_conn_destroy(struct rds_connection *conn); void rds_conn_destroy(struct rds_connection *conn);
void rds_conn_drop(struct rds_connection *conn); void rds_conn_drop(struct rds_connection *conn);
@ -840,11 +860,12 @@ void rds_page_exit(void);
/* recv.c */ /* recv.c */
void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn,
__be32 saddr); struct in6_addr *saddr);
void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *conn, void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *conn,
__be32 saddr); struct in6_addr *saddr);
void rds_inc_put(struct rds_incoming *inc); void rds_inc_put(struct rds_incoming *inc);
void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr, void rds_recv_incoming(struct rds_connection *conn, struct in6_addr *saddr,
struct in6_addr *daddr,
struct rds_incoming *inc, gfp_t gfp); struct rds_incoming *inc, gfp_t gfp);
int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
int msg_flags); int msg_flags);
@ -859,7 +880,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len);
void rds_send_path_reset(struct rds_conn_path *conn); void rds_send_path_reset(struct rds_conn_path *conn);
int rds_send_xmit(struct rds_conn_path *cp); int rds_send_xmit(struct rds_conn_path *cp);
struct sockaddr_in; struct sockaddr_in;
void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest); void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in6 *dest);
typedef int (*is_acked_func)(struct rds_message *rm, uint64_t ack); typedef int (*is_acked_func)(struct rds_message *rm, uint64_t ack);
void rds_send_drop_acked(struct rds_connection *conn, u64 ack, void rds_send_drop_acked(struct rds_connection *conn, u64 ack,
is_acked_func is_acked); is_acked_func is_acked);
@ -946,11 +967,14 @@ void rds_send_worker(struct work_struct *);
void rds_recv_worker(struct work_struct *); void rds_recv_worker(struct work_struct *);
void rds_connect_path_complete(struct rds_conn_path *conn, int curr); void rds_connect_path_complete(struct rds_conn_path *conn, int curr);
void rds_connect_complete(struct rds_connection *conn); void rds_connect_complete(struct rds_connection *conn);
int rds_addr_cmp(const struct in6_addr *a1, const struct in6_addr *a2);
/* transport.c */ /* transport.c */
void rds_trans_register(struct rds_transport *trans); void rds_trans_register(struct rds_transport *trans);
void rds_trans_unregister(struct rds_transport *trans); void rds_trans_unregister(struct rds_transport *trans);
struct rds_transport *rds_trans_get_preferred(struct net *net, __be32 addr); struct rds_transport *rds_trans_get_preferred(struct net *net,
const struct in6_addr *addr,
__u32 scope_id);
void rds_trans_put(struct rds_transport *trans); void rds_trans_put(struct rds_transport *trans);
unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter, unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter,
unsigned int avail); unsigned int avail);

51
net/rds/recv.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -41,14 +41,14 @@
#include "rds.h" #include "rds.h"
void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn,
__be32 saddr) struct in6_addr *saddr)
{ {
int i; int i;
refcount_set(&inc->i_refcount, 1); refcount_set(&inc->i_refcount, 1);
INIT_LIST_HEAD(&inc->i_item); INIT_LIST_HEAD(&inc->i_item);
inc->i_conn = conn; inc->i_conn = conn;
inc->i_saddr = saddr; inc->i_saddr = *saddr;
inc->i_rdma_cookie = 0; inc->i_rdma_cookie = 0;
inc->i_rx_tstamp.tv_sec = 0; inc->i_rx_tstamp.tv_sec = 0;
inc->i_rx_tstamp.tv_usec = 0; inc->i_rx_tstamp.tv_usec = 0;
@ -59,13 +59,13 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn,
EXPORT_SYMBOL_GPL(rds_inc_init); EXPORT_SYMBOL_GPL(rds_inc_init);
void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *cp, void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *cp,
__be32 saddr) struct in6_addr *saddr)
{ {
refcount_set(&inc->i_refcount, 1); refcount_set(&inc->i_refcount, 1);
INIT_LIST_HEAD(&inc->i_item); INIT_LIST_HEAD(&inc->i_item);
inc->i_conn = cp->cp_conn; inc->i_conn = cp->cp_conn;
inc->i_conn_path = cp; inc->i_conn_path = cp;
inc->i_saddr = saddr; inc->i_saddr = *saddr;
inc->i_rdma_cookie = 0; inc->i_rdma_cookie = 0;
inc->i_rx_tstamp.tv_sec = 0; inc->i_rx_tstamp.tv_sec = 0;
inc->i_rx_tstamp.tv_usec = 0; inc->i_rx_tstamp.tv_usec = 0;
@ -110,7 +110,7 @@ static void rds_recv_rcvbuf_delta(struct rds_sock *rs, struct sock *sk,
now_congested = rs->rs_rcv_bytes > rds_sk_rcvbuf(rs); now_congested = rs->rs_rcv_bytes > rds_sk_rcvbuf(rs);
rdsdebug("rs %p (%pI4:%u) recv bytes %d buf %d " rdsdebug("rs %p (%pI6c:%u) recv bytes %d buf %d "
"now_cong %d delta %d\n", "now_cong %d delta %d\n",
rs, &rs->rs_bound_addr, rs, &rs->rs_bound_addr,
ntohs(rs->rs_bound_port), rs->rs_rcv_bytes, ntohs(rs->rs_bound_port), rs->rs_rcv_bytes,
@ -260,7 +260,7 @@ static void rds_start_mprds(struct rds_connection *conn)
struct rds_conn_path *cp; struct rds_conn_path *cp;
if (conn->c_npaths > 1 && if (conn->c_npaths > 1 &&
IS_CANONICAL(conn->c_laddr, conn->c_faddr)) { rds_addr_cmp(&conn->c_laddr, &conn->c_faddr) < 0) {
for (i = 0; i < conn->c_npaths; i++) { for (i = 0; i < conn->c_npaths; i++) {
cp = &conn->c_path[i]; cp = &conn->c_path[i];
rds_conn_path_connect_if_down(cp); rds_conn_path_connect_if_down(cp);
@ -284,7 +284,8 @@ static void rds_start_mprds(struct rds_connection *conn)
* conn. This lets loopback, who only has one conn for both directions, * conn. This lets loopback, who only has one conn for both directions,
* tell us which roles the addrs in the conn are playing for this message. * tell us which roles the addrs in the conn are playing for this message.
*/ */
void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr, void rds_recv_incoming(struct rds_connection *conn, struct in6_addr *saddr,
struct in6_addr *daddr,
struct rds_incoming *inc, gfp_t gfp) struct rds_incoming *inc, gfp_t gfp)
{ {
struct rds_sock *rs = NULL; struct rds_sock *rs = NULL;
@ -339,7 +340,8 @@ void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr,
if (rds_sysctl_ping_enable && inc->i_hdr.h_dport == 0) { if (rds_sysctl_ping_enable && inc->i_hdr.h_dport == 0) {
if (inc->i_hdr.h_sport == 0) { if (inc->i_hdr.h_sport == 0) {
rdsdebug("ignore ping with 0 sport from 0x%x\n", saddr); rdsdebug("ignore ping with 0 sport from %pI6c\n",
saddr);
goto out; goto out;
} }
rds_stats_inc(s_recv_ping); rds_stats_inc(s_recv_ping);
@ -362,7 +364,7 @@ void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr,
goto out; goto out;
} }
rs = rds_find_bound(daddr, inc->i_hdr.h_dport); rs = rds_find_bound(daddr, inc->i_hdr.h_dport, conn->c_dev_if);
if (!rs) { if (!rs) {
rds_stats_inc(s_recv_drop_no_sock); rds_stats_inc(s_recv_drop_no_sock);
goto out; goto out;
@ -625,6 +627,7 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
struct rds_sock *rs = rds_sk_to_rs(sk); struct rds_sock *rs = rds_sk_to_rs(sk);
long timeo; long timeo;
int ret = 0, nonblock = msg_flags & MSG_DONTWAIT; int ret = 0, nonblock = msg_flags & MSG_DONTWAIT;
DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
struct rds_incoming *inc = NULL; struct rds_incoming *inc = NULL;
@ -673,7 +676,7 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
break; break;
} }
rdsdebug("copying inc %p from %pI4:%u to user\n", inc, rdsdebug("copying inc %p from %pI6c:%u to user\n", inc,
&inc->i_conn->c_faddr, &inc->i_conn->c_faddr,
ntohs(inc->i_hdr.h_sport)); ntohs(inc->i_hdr.h_sport));
ret = inc->i_conn->c_trans->inc_copy_to_user(inc, &msg->msg_iter); ret = inc->i_conn->c_trans->inc_copy_to_user(inc, &msg->msg_iter);
@ -707,12 +710,26 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
rds_stats_inc(s_recv_delivered); rds_stats_inc(s_recv_delivered);
if (sin) { if (msg->msg_name) {
sin->sin_family = AF_INET; if (ipv6_addr_v4mapped(&inc->i_saddr)) {
sin->sin_port = inc->i_hdr.h_sport; sin = (struct sockaddr_in *)msg->msg_name;
sin->sin_addr.s_addr = inc->i_saddr;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); sin->sin_family = AF_INET;
msg->msg_namelen = sizeof(*sin); sin->sin_port = inc->i_hdr.h_sport;
sin->sin_addr.s_addr =
inc->i_saddr.s6_addr32[3];
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
msg->msg_namelen = sizeof(*sin);
} else {
sin6 = (struct sockaddr_in6 *)msg->msg_name;
sin6->sin6_family = AF_INET6;
sin6->sin6_port = inc->i_hdr.h_sport;
sin6->sin6_addr = inc->i_saddr;
sin6->sin6_flowinfo = 0;
sin6->sin6_scope_id = rs->rs_bound_scope_id;
msg->msg_namelen = sizeof(*sin6);
}
} }
break; break;
} }

67
net/rds/send.c
View File

@ -709,7 +709,7 @@ void rds_send_drop_acked(struct rds_connection *conn, u64 ack,
} }
EXPORT_SYMBOL_GPL(rds_send_drop_acked); EXPORT_SYMBOL_GPL(rds_send_drop_acked);
void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest) void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in6 *dest)
{ {
struct rds_message *rm, *tmp; struct rds_message *rm, *tmp;
struct rds_connection *conn; struct rds_connection *conn;
@ -721,8 +721,9 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
spin_lock_irqsave(&rs->rs_lock, flags); spin_lock_irqsave(&rs->rs_lock, flags);
list_for_each_entry_safe(rm, tmp, &rs->rs_send_queue, m_sock_item) { list_for_each_entry_safe(rm, tmp, &rs->rs_send_queue, m_sock_item) {
if (dest && (dest->sin_addr.s_addr != rm->m_daddr || if (dest &&
dest->sin_port != rm->m_inc.i_hdr.h_dport)) (!ipv6_addr_equal(&dest->sin6_addr, &rm->m_daddr) ||
dest->sin6_port != rm->m_inc.i_hdr.h_dport))
continue; continue;
list_move(&rm->m_sock_item, &list); list_move(&rm->m_sock_item, &list);
@ -1059,8 +1060,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
{ {
struct sock *sk = sock->sk; struct sock *sk = sock->sk;
struct rds_sock *rs = rds_sk_to_rs(sk); struct rds_sock *rs = rds_sk_to_rs(sk);
DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
__be32 daddr;
__be16 dport; __be16 dport;
struct rds_message *rm = NULL; struct rds_message *rm = NULL;
struct rds_connection *conn; struct rds_connection *conn;
@ -1069,10 +1070,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
int nonblock = msg->msg_flags & MSG_DONTWAIT; int nonblock = msg->msg_flags & MSG_DONTWAIT;
long timeo = sock_sndtimeo(sk, nonblock); long timeo = sock_sndtimeo(sk, nonblock);
struct rds_conn_path *cpath; struct rds_conn_path *cpath;
struct in6_addr daddr;
__u32 scope_id = 0;
size_t total_payload_len = payload_len, rdma_payload_len = 0; size_t total_payload_len = payload_len, rdma_payload_len = 0;
bool zcopy = ((msg->msg_flags & MSG_ZEROCOPY) && bool zcopy = ((msg->msg_flags & MSG_ZEROCOPY) &&
sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY)); sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY));
int num_sgs = ceil(payload_len, PAGE_SIZE); int num_sgs = ceil(payload_len, PAGE_SIZE);
int namelen;
/* Mirror Linux UDP mirror of BSD error message compatibility */ /* Mirror Linux UDP mirror of BSD error message compatibility */
/* XXX: Perhaps MSG_MORE someday */ /* XXX: Perhaps MSG_MORE someday */
@ -1081,27 +1085,59 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
goto out; goto out;
} }
if (msg->msg_namelen) { namelen = msg->msg_namelen;
/* XXX fail non-unicast destination IPs? */ if (namelen != 0) {
if (msg->msg_namelen < sizeof(*usin) || usin->sin_family != AF_INET) { if (namelen < sizeof(*usin)) {
ret = -EINVAL;
goto out;
}
switch (namelen) {
case sizeof(*usin):
if (usin->sin_family != AF_INET ||
usin->sin_addr.s_addr == htonl(INADDR_ANY) ||
usin->sin_addr.s_addr == htonl(INADDR_BROADCAST) ||
IN_MULTICAST(ntohl(usin->sin_addr.s_addr))) {
ret = -EINVAL;
goto out;
}
ipv6_addr_set_v4mapped(usin->sin_addr.s_addr, &daddr);
dport = usin->sin_port;
break;
case sizeof(*sin6): {
ret = -EPROTONOSUPPORT;
goto out;
}
default:
ret = -EINVAL; ret = -EINVAL;
goto out; goto out;
} }
daddr = usin->sin_addr.s_addr;
dport = usin->sin_port;
} else { } else {
/* We only care about consistency with ->connect() */ /* We only care about consistency with ->connect() */
lock_sock(sk); lock_sock(sk);
daddr = rs->rs_conn_addr; daddr = rs->rs_conn_addr;
dport = rs->rs_conn_port; dport = rs->rs_conn_port;
scope_id = rs->rs_bound_scope_id;
release_sock(sk); release_sock(sk);
} }
lock_sock(sk); lock_sock(sk);
if (daddr == 0 || rs->rs_bound_addr == 0) { if (ipv6_addr_any(&rs->rs_bound_addr) || ipv6_addr_any(&daddr)) {
release_sock(sk); release_sock(sk);
ret = -ENOTCONN; /* XXX not a great errno */ ret = -ENOTCONN;
goto out; goto out;
} else if (namelen != 0) {
/* Cannot send to an IPv4 address using an IPv6 source
* address and cannot send to an IPv6 address using an
* IPv4 source address.
*/
if (ipv6_addr_v4mapped(&daddr) ^
ipv6_addr_v4mapped(&rs->rs_bound_addr)) {
release_sock(sk);
ret = -EOPNOTSUPP;
goto out;
}
} }
release_sock(sk); release_sock(sk);
@ -1155,13 +1191,14 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
/* rds_conn_create has a spinlock that runs with IRQ off. /* rds_conn_create has a spinlock that runs with IRQ off.
* Caching the conn in the socket helps a lot. */ * Caching the conn in the socket helps a lot. */
if (rs->rs_conn && rs->rs_conn->c_faddr == daddr) if (rs->rs_conn && ipv6_addr_equal(&rs->rs_conn->c_faddr, &daddr))
conn = rs->rs_conn; conn = rs->rs_conn;
else { else {
conn = rds_conn_create_outgoing(sock_net(sock->sk), conn = rds_conn_create_outgoing(sock_net(sock->sk),
rs->rs_bound_addr, daddr, &rs->rs_bound_addr, &daddr,
rs->rs_transport, rs->rs_transport,
sock->sk->sk_allocation); sock->sk->sk_allocation,
scope_id);
if (IS_ERR(conn)) { if (IS_ERR(conn)) {
ret = PTR_ERR(conn); ret = PTR_ERR(conn);
goto out; goto out;

32
net/rds/tcp.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -37,6 +37,8 @@
#include <net/tcp.h> #include <net/tcp.h>
#include <net/net_namespace.h> #include <net/net_namespace.h>
#include <net/netns/generic.h> #include <net/netns/generic.h>
#include <net/tcp.h>
#include <net/addrconf.h>
#include "rds.h" #include "rds.h"
#include "tcp.h" #include "tcp.h"
@ -262,9 +264,33 @@ out:
spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags); spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags);
} }
static int rds_tcp_laddr_check(struct net *net, __be32 addr) static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr,
__u32 scope_id)
{ {
if (inet_addr_type(net, addr) == RTN_LOCAL) struct net_device *dev = NULL;
int ret;
if (ipv6_addr_v4mapped(addr)) {
if (inet_addr_type(net, addr->s6_addr32[3]) == RTN_LOCAL)
return 0;
return -EADDRNOTAVAIL;
}
/* If the scope_id is specified, check only those addresses
* hosted on the specified interface.
*/
if (scope_id != 0) {
rcu_read_lock();
dev = dev_get_by_index_rcu(net, scope_id);
/* scope_id is not valid... */
if (!dev) {
rcu_read_unlock();
return -EADDRNOTAVAIL;
}
rcu_read_unlock();
}
ret = ipv6_chk_addr(net, addr, dev, 0);
if (ret)
return 0; return 0;
return -EADDRNOTAVAIL; return -EADDRNOTAVAIL;
} }

34
net/rds/tcp_connect.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -66,7 +66,8 @@ void rds_tcp_state_change(struct sock *sk)
* RDS connection as RDS_CONN_UP until the reconnect, * RDS connection as RDS_CONN_UP until the reconnect,
* to avoid RDS datagram loss. * to avoid RDS datagram loss.
*/ */
if (!IS_CANONICAL(cp->cp_conn->c_laddr, cp->cp_conn->c_faddr) && if (rds_addr_cmp(&cp->cp_conn->c_laddr,
&cp->cp_conn->c_faddr) >= 0 &&
rds_conn_path_transition(cp, RDS_CONN_CONNECTING, rds_conn_path_transition(cp, RDS_CONN_CONNECTING,
RDS_CONN_ERROR)) { RDS_CONN_ERROR)) {
rds_conn_path_drop(cp, false); rds_conn_path_drop(cp, false);
@ -88,7 +89,9 @@ out:
int rds_tcp_conn_path_connect(struct rds_conn_path *cp) int rds_tcp_conn_path_connect(struct rds_conn_path *cp)
{ {
struct socket *sock = NULL; struct socket *sock = NULL;
struct sockaddr_in src, dest; struct sockaddr_in sin;
struct sockaddr *addr;
int addrlen;
int ret; int ret;
struct rds_connection *conn = cp->cp_conn; struct rds_connection *conn = cp->cp_conn;
struct rds_tcp_connection *tc = cp->cp_transport_data; struct rds_tcp_connection *tc = cp->cp_transport_data;
@ -112,30 +115,33 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp)
rds_tcp_tune(sock); rds_tcp_tune(sock);
src.sin_family = AF_INET; sin.sin_family = AF_INET;
src.sin_addr.s_addr = (__force u32)conn->c_laddr; sin.sin_addr.s_addr = conn->c_laddr.s6_addr32[3];
src.sin_port = (__force u16)htons(0); sin.sin_port = 0;
addr = (struct sockaddr *)&sin;
addrlen = sizeof(sin);
ret = sock->ops->bind(sock, (struct sockaddr *)&src, sizeof(src)); ret = sock->ops->bind(sock, addr, addrlen);
if (ret) { if (ret) {
rdsdebug("bind failed with %d at address %pI4\n", rdsdebug("bind failed with %d at address %pI6c\n",
ret, &conn->c_laddr); ret, &conn->c_laddr);
goto out; goto out;
} }
dest.sin_family = AF_INET; sin.sin_family = AF_INET;
dest.sin_addr.s_addr = (__force u32)conn->c_faddr; sin.sin_addr.s_addr = conn->c_faddr.s6_addr32[3];
dest.sin_port = (__force u16)htons(RDS_TCP_PORT); sin.sin_port = htons(RDS_TCP_PORT);
addr = (struct sockaddr *)&sin;
addrlen = sizeof(sin);
/* /*
* once we call connect() we can start getting callbacks and they * once we call connect() we can start getting callbacks and they
* own the socket * own the socket
*/ */
rds_tcp_set_callbacks(sock, cp); rds_tcp_set_callbacks(sock, cp);
ret = sock->ops->connect(sock, (struct sockaddr *)&dest, sizeof(dest), ret = sock->ops->connect(sock, addr, addrlen, O_NONBLOCK);
O_NONBLOCK);
rdsdebug("connect to address %pI4 returned %d\n", &conn->c_faddr, ret); rdsdebug("connect to address %pI6c returned %d\n", &conn->c_faddr, ret);
if (ret == -EINPROGRESS) if (ret == -EINPROGRESS)
ret = 0; ret = 0;
if (ret == 0) { if (ret == 0) {

18
net/rds/tcp_listen.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006, 2018 Oracle. All rights reserved. * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -83,13 +83,12 @@ static
struct rds_tcp_connection *rds_tcp_accept_one_path(struct rds_connection *conn) struct rds_tcp_connection *rds_tcp_accept_one_path(struct rds_connection *conn)
{ {
int i; int i;
bool peer_is_smaller = IS_CANONICAL(conn->c_faddr, conn->c_laddr);
int npaths = max_t(int, 1, conn->c_npaths); int npaths = max_t(int, 1, conn->c_npaths);
/* for mprds, all paths MUST be initiated by the peer /* for mprds, all paths MUST be initiated by the peer
* with the smaller address. * with the smaller address.
*/ */
if (!peer_is_smaller) { if (rds_addr_cmp(&conn->c_faddr, &conn->c_laddr) >= 0) {
/* Make sure we initiate at least one path if this /* Make sure we initiate at least one path if this
* has not already been done; rds_start_mprds() will * has not already been done; rds_start_mprds() will
* take care of additional paths, if necessary. * take care of additional paths, if necessary.
@ -164,13 +163,16 @@ int rds_tcp_accept_one(struct socket *sock)
inet = inet_sk(new_sock->sk); inet = inet_sk(new_sock->sk);
rdsdebug("accepted tcp %pI4:%u -> %pI4:%u\n", rdsdebug("accepted tcp %pI6c:%u -> %pI6c:%u\n",
&inet->inet_saddr, ntohs(inet->inet_sport), &new_sock->sk->sk_v6_rcv_saddr, ntohs(inet->inet_sport),
&inet->inet_daddr, ntohs(inet->inet_dport)); &new_sock->sk->sk_v6_daddr, ntohs(inet->inet_dport));
conn = rds_conn_create(sock_net(sock->sk), conn = rds_conn_create(sock_net(sock->sk),
inet->inet_saddr, inet->inet_daddr, &new_sock->sk->sk_v6_rcv_saddr,
&rds_tcp_transport, GFP_KERNEL); &new_sock->sk->sk_v6_daddr,
&rds_tcp_transport, GFP_KERNEL,
new_sock->sk->sk_bound_dev_if);
if (IS_ERR(conn)) { if (IS_ERR(conn)) {
ret = PTR_ERR(conn); ret = PTR_ERR(conn);
goto out; goto out;

9
net/rds/tcp_recv.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -179,7 +179,7 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
tc->t_tinc = tinc; tc->t_tinc = tinc;
rdsdebug("alloced tinc %p\n", tinc); rdsdebug("alloced tinc %p\n", tinc);
rds_inc_path_init(&tinc->ti_inc, cp, rds_inc_path_init(&tinc->ti_inc, cp,
cp->cp_conn->c_faddr); &cp->cp_conn->c_faddr);
tinc->ti_inc.i_rx_lat_trace[RDS_MSG_RX_HDR] = tinc->ti_inc.i_rx_lat_trace[RDS_MSG_RX_HDR] =
local_clock(); local_clock();
@ -239,8 +239,9 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
if (tinc->ti_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP) if (tinc->ti_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP)
rds_tcp_cong_recv(conn, tinc); rds_tcp_cong_recv(conn, tinc);
else else
rds_recv_incoming(conn, conn->c_faddr, rds_recv_incoming(conn, &conn->c_faddr,
conn->c_laddr, &tinc->ti_inc, &conn->c_laddr,
&tinc->ti_inc,
arg->gfp); arg->gfp);
tc->t_tinc_hdr_rem = sizeof(struct rds_header); tc->t_tinc_hdr_rem = sizeof(struct rds_header);

4
net/rds/tcp_send.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -153,7 +153,7 @@ out:
* an incoming RST. * an incoming RST.
*/ */
if (rds_conn_path_up(cp)) { if (rds_conn_path_up(cp)) {
pr_warn("RDS/tcp: send to %pI4 on cp [%d]" pr_warn("RDS/tcp: send to %pI6c on cp [%d]"
"returned %d, " "returned %d, "
"disconnecting and reconnecting\n", "disconnecting and reconnecting\n",
&conn->c_faddr, cp->cp_index, ret); &conn->c_faddr, cp->cp_index, ret);

69
net/rds/threads.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -82,8 +82,8 @@ void rds_connect_path_complete(struct rds_conn_path *cp, int curr)
return; return;
} }
rdsdebug("conn %p for %pI4 to %pI4 complete\n", rdsdebug("conn %p for %pI6c to %pI6c complete\n",
cp->cp_conn, &cp->cp_conn->c_laddr, &cp->cp_conn->c_faddr); cp->cp_conn, &cp->cp_conn->c_laddr, &cp->cp_conn->c_faddr);
cp->cp_reconnect_jiffies = 0; cp->cp_reconnect_jiffies = 0;
set_bit(0, &cp->cp_conn->c_map_queued); set_bit(0, &cp->cp_conn->c_map_queued);
@ -125,13 +125,13 @@ void rds_queue_reconnect(struct rds_conn_path *cp)
unsigned long rand; unsigned long rand;
struct rds_connection *conn = cp->cp_conn; struct rds_connection *conn = cp->cp_conn;
rdsdebug("conn %p for %pI4 to %pI4 reconnect jiffies %lu\n", rdsdebug("conn %p for %pI6c to %pI6c reconnect jiffies %lu\n",
conn, &conn->c_laddr, &conn->c_faddr, conn, &conn->c_laddr, &conn->c_faddr,
cp->cp_reconnect_jiffies); cp->cp_reconnect_jiffies);
/* let peer with smaller addr initiate reconnect, to avoid duels */ /* let peer with smaller addr initiate reconnect, to avoid duels */
if (conn->c_trans->t_type == RDS_TRANS_TCP && if (conn->c_trans->t_type == RDS_TRANS_TCP &&
!IS_CANONICAL(conn->c_laddr, conn->c_faddr)) rds_addr_cmp(&conn->c_laddr, &conn->c_faddr) >= 0)
return; return;
set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags);
@ -145,7 +145,7 @@ void rds_queue_reconnect(struct rds_conn_path *cp)
} }
get_random_bytes(&rand, sizeof(rand)); get_random_bytes(&rand, sizeof(rand));
rdsdebug("%lu delay %lu ceil conn %p for %pI4 -> %pI4\n", rdsdebug("%lu delay %lu ceil conn %p for %pI6c -> %pI6c\n",
rand % cp->cp_reconnect_jiffies, cp->cp_reconnect_jiffies, rand % cp->cp_reconnect_jiffies, cp->cp_reconnect_jiffies,
conn, &conn->c_laddr, &conn->c_faddr); conn, &conn->c_laddr, &conn->c_faddr);
rcu_read_lock(); rcu_read_lock();
@ -167,14 +167,14 @@ void rds_connect_worker(struct work_struct *work)
int ret; int ret;
if (cp->cp_index > 0 && if (cp->cp_index > 0 &&
!IS_CANONICAL(cp->cp_conn->c_laddr, cp->cp_conn->c_faddr)) rds_addr_cmp(&cp->cp_conn->c_laddr, &cp->cp_conn->c_faddr) >= 0)
return; return;
clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags); clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags);
ret = rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_CONNECTING); ret = rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_CONNECTING);
if (ret) { if (ret) {
ret = conn->c_trans->conn_path_connect(cp); ret = conn->c_trans->conn_path_connect(cp);
rdsdebug("conn %p for %pI4 to %pI4 dispatched, ret %d\n", rdsdebug("conn %p for %pI6c to %pI6c dispatched, ret %d\n",
conn, &conn->c_laddr, &conn->c_faddr, ret); conn, &conn->c_laddr, &conn->c_faddr, ret);
if (ret) { if (ret) {
if (rds_conn_path_transition(cp, if (rds_conn_path_transition(cp,
@ -259,3 +259,50 @@ int rds_threads_init(void)
return 0; return 0;
} }
/* Compare two IPv6 addresses. Return 0 if the two addresses are equal.
* Return 1 if the first is greater. Return -1 if the second is greater.
*/
int rds_addr_cmp(const struct in6_addr *addr1,
const struct in6_addr *addr2)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
const __be64 *a1, *a2;
u64 x, y;
a1 = (__be64 *)addr1;
a2 = (__be64 *)addr2;
if (*a1 != *a2) {
if (be64_to_cpu(*a1) < be64_to_cpu(*a2))
return -1;
else
return 1;
} else {
x = be64_to_cpu(*++a1);
y = be64_to_cpu(*++a2);
if (x < y)
return -1;
else if (x > y)
return 1;
else
return 0;
}
#else
u32 a, b;
int i;
for (i = 0; i < 4; i++) {
if (addr1->s6_addr32[i] != addr2->s6_addr32[i]) {
a = ntohl(addr1->s6_addr32[i]);
b = ntohl(addr2->s6_addr32[i]);
if (a < b)
return -1;
else if (a > b)
return 1;
}
}
return 0;
#endif
}
EXPORT_SYMBOL_GPL(rds_addr_cmp);

15
net/rds/transport.c
View File

@ -1,5 +1,5 @@
/* /*
* Copyright (c) 2006 Oracle. All rights reserved. * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
* *
* This software is available to you under a choice of one of two * This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU * licenses. You may choose to be licensed under the terms of the GNU
@ -33,6 +33,7 @@
#include <linux/kernel.h> #include <linux/kernel.h>
#include <linux/module.h> #include <linux/module.h>
#include <linux/in.h> #include <linux/in.h>
#include <linux/ipv6.h>
#include "rds.h" #include "rds.h"
#include "loop.h" #include "loop.h"
@ -75,20 +76,26 @@ void rds_trans_put(struct rds_transport *trans)
module_put(trans->t_owner); module_put(trans->t_owner);
} }
struct rds_transport *rds_trans_get_preferred(struct net *net, __be32 addr) struct rds_transport *rds_trans_get_preferred(struct net *net,
const struct in6_addr *addr,
__u32 scope_id)
{ {
struct rds_transport *ret = NULL; struct rds_transport *ret = NULL;
struct rds_transport *trans; struct rds_transport *trans;
unsigned int i; unsigned int i;
if (IN_LOOPBACK(ntohl(addr))) if (ipv6_addr_v4mapped(addr)) {
if (*(u_int8_t *)&addr->s6_addr32[3] == IN_LOOPBACKNET)
return &rds_loop_transport;
} else if (ipv6_addr_loopback(addr)) {
return &rds_loop_transport; return &rds_loop_transport;
}
down_read(&rds_trans_sem); down_read(&rds_trans_sem);
for (i = 0; i < RDS_TRANS_COUNT; i++) { for (i = 0; i < RDS_TRANS_COUNT; i++) {
trans = transports[i]; trans = transports[i];
if (trans && (trans->laddr_check(net, addr) == 0) && if (trans && (trans->laddr_check(net, addr, scope_id) == 0) &&
(!trans->t_owner || try_module_get(trans->t_owner))) { (!trans->t_owner || try_module_get(trans->t_owner))) {
ret = trans; ret = trans;
break; break;