aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/fib_semantics.c13
-rw-r--r--net/ipv4/igmp.c12
-rw-r--r--net/ipv4/inet_connection_sock.c4
-rw-r--r--net/ipv4/ip_sockglue.c45
-rw-r--r--net/ipv4/netfilter/nf_defrag_ipv4.c5
-rw-r--r--net/ipv4/netfilter/nf_nat_pptp.c2
-rw-r--r--net/ipv4/raw.c8
-rw-r--r--net/ipv4/sysctl_net_ipv4.c4
-rw-r--r--net/ipv4/tcp.c21
-rw-r--r--net/ipv4/tcp_diag.c2
-rw-r--r--net/ipv4/tcp_ipv4.c16
-rw-r--r--net/ipv4/tcp_minisocks.c3
12 files changed, 78 insertions, 57 deletions
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 3e87447e65c7..d97268e8ff10 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -923,14 +923,21 @@ static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst ||
fib_prefsrc != cfg->fc_dst) {
u32 tb_id = cfg->fc_table;
+ int rc;
if (tb_id == RT_TABLE_MAIN)
tb_id = RT_TABLE_LOCAL;
- if (inet_addr_type_table(cfg->fc_nlinfo.nl_net,
- fib_prefsrc, tb_id) != RTN_LOCAL) {
- return false;
+ rc = inet_addr_type_table(cfg->fc_nlinfo.nl_net,
+ fib_prefsrc, tb_id);
+
+ if (rc != RTN_LOCAL && tb_id != RT_TABLE_LOCAL) {
+ rc = inet_addr_type_table(cfg->fc_nlinfo.nl_net,
+ fib_prefsrc, RT_TABLE_LOCAL);
}
+
+ if (rc != RTN_LOCAL)
+ return false;
}
return true;
}
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 64aaf3522a59..6baf36e11808 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2392,11 +2392,11 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf,
struct ip_sf_socklist *psl;
struct net *net = sock_net(sk);
+ ASSERT_RTNL();
+
if (!ipv4_is_multicast(addr))
return -EINVAL;
- rtnl_lock();
-
imr.imr_multiaddr.s_addr = msf->imsf_multiaddr;
imr.imr_address.s_addr = msf->imsf_interface;
imr.imr_ifindex = 0;
@@ -2417,7 +2417,6 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf,
goto done;
msf->imsf_fmode = pmc->sfmode;
psl = rtnl_dereference(pmc->sflist);
- rtnl_unlock();
if (!psl) {
len = 0;
count = 0;
@@ -2436,7 +2435,6 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf,
return -EFAULT;
return 0;
done:
- rtnl_unlock();
return err;
}
@@ -2450,6 +2448,8 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
struct inet_sock *inet = inet_sk(sk);
struct ip_sf_socklist *psl;
+ ASSERT_RTNL();
+
psin = (struct sockaddr_in *)&gsf->gf_group;
if (psin->sin_family != AF_INET)
return -EINVAL;
@@ -2457,8 +2457,6 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
if (!ipv4_is_multicast(addr))
return -EINVAL;
- rtnl_lock();
-
err = -EADDRNOTAVAIL;
for_each_pmc_rtnl(inet, pmc) {
@@ -2470,7 +2468,6 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
goto done;
gsf->gf_fmode = pmc->sfmode;
psl = rtnl_dereference(pmc->sflist);
- rtnl_unlock();
count = psl ? psl->sl_count : 0;
copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc;
gsf->gf_numsrc = count;
@@ -2490,7 +2487,6 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
}
return 0;
done:
- rtnl_unlock();
return err;
}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 1feb15f23de8..46b9c887bede 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -563,7 +563,7 @@ static void reqsk_timer_handler(unsigned long data)
int max_retries, thresh;
u8 defer_accept;
- if (sk_listener->sk_state != TCP_LISTEN)
+ if (sk_state_load(sk_listener) != TCP_LISTEN)
goto drop;
max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
@@ -749,7 +749,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
* It is OK, because this socket enters to hash table only
* after validation is complete.
*/
- sk->sk_state = TCP_LISTEN;
+ sk_state_store(sk, TCP_LISTEN);
if (!sk->sk_prot->get_port(sk, inet->inet_num)) {
inet->inet_sport = htons(inet->inet_num);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index c3c359ad66e3..5f73a7c03e27 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1251,11 +1251,22 @@ EXPORT_SYMBOL(compat_ip_setsockopt);
* the _received_ ones. The set sets the _sent_ ones.
*/
+static bool getsockopt_needs_rtnl(int optname)
+{
+ switch (optname) {
+ case IP_MSFILTER:
+ case MCAST_MSFILTER:
+ return true;
+ }
+ return false;
+}
+
static int do_ip_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen, unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
- int val;
+ bool needs_rtnl = getsockopt_needs_rtnl(optname);
+ int val, err = 0;
int len;
if (level != SOL_IP)
@@ -1269,6 +1280,8 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
if (len < 0)
return -EINVAL;
+ if (needs_rtnl)
+ rtnl_lock();
lock_sock(sk);
switch (optname) {
@@ -1386,39 +1399,35 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_MSFILTER:
{
struct ip_msfilter msf;
- int err;
if (len < IP_MSFILTER_SIZE(0)) {
- release_sock(sk);
- return -EINVAL;
+ err = -EINVAL;
+ goto out;
}
if (copy_from_user(&msf, optval, IP_MSFILTER_SIZE(0))) {
- release_sock(sk);
- return -EFAULT;
+ err = -EFAULT;
+ goto out;
}
err = ip_mc_msfget(sk, &msf,
(struct ip_msfilter __user *)optval, optlen);
- release_sock(sk);
- return err;
+ goto out;
}
case MCAST_MSFILTER:
{
struct group_filter gsf;
- int err;
if (len < GROUP_FILTER_SIZE(0)) {
- release_sock(sk);
- return -EINVAL;
+ err = -EINVAL;
+ goto out;
}
if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0))) {
- release_sock(sk);
- return -EFAULT;
+ err = -EFAULT;
+ goto out;
}
err = ip_mc_gsfget(sk, &gsf,
(struct group_filter __user *)optval,
optlen);
- release_sock(sk);
- return err;
+ goto out;
}
case IP_MULTICAST_ALL:
val = inet->mc_all;
@@ -1485,6 +1494,12 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
return -EFAULT;
}
return 0;
+
+out:
+ release_sock(sk);
+ if (needs_rtnl)
+ rtnl_unlock();
+ return err;
}
int ip_getsockopt(struct sock *sk, int level,
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 0e5591c2ee9f..6fb869f646bf 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -67,10 +67,9 @@ static unsigned int ipv4_conntrack_defrag(void *priv,
const struct nf_hook_state *state)
{
struct sock *sk = skb->sk;
- struct inet_sock *inet = inet_sk(skb->sk);
- if (sk && (sk->sk_family == PF_INET) &&
- inet->nodefrag)
+ if (sk && sk_fullsock(sk) && (sk->sk_family == PF_INET) &&
+ inet_sk(sk)->nodefrag)
return NF_ACCEPT;
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c
index 657d2307f031..b3ca21b2ba9b 100644
--- a/net/ipv4/netfilter/nf_nat_pptp.c
+++ b/net/ipv4/netfilter/nf_nat_pptp.c
@@ -45,7 +45,7 @@ static void pptp_nat_expected(struct nf_conn *ct,
struct net *net = nf_ct_net(ct);
const struct nf_conn *master = ct->master;
struct nf_conntrack_expect *other_exp;
- struct nf_conntrack_tuple t;
+ struct nf_conntrack_tuple t = {};
const struct nf_ct_pptp_master *ct_pptp_info;
const struct nf_nat_pptp *nat_pptp_info;
struct nf_nat_range range;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 8c0d0bdc2a7c..63e5be0abd86 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -406,10 +406,12 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
ip_select_ident(net, skb, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
+ skb->transport_header += iphlen;
+ if (iph->protocol == IPPROTO_ICMP &&
+ length >= iphlen + sizeof(struct icmphdr))
+ icmp_out_count(net, ((struct icmphdr *)
+ skb_transport_header(skb))->type);
}
- if (iph->protocol == IPPROTO_ICMP)
- icmp_out_count(net, ((struct icmphdr *)
- skb_transport_header(skb))->type);
err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
net, sk, skb, NULL, rt->dst.dev,
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 25300c5e283b..a0bd7a55193e 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -48,14 +48,14 @@ static void set_local_port_range(struct net *net, int range[2])
{
bool same_parity = !((range[0] ^ range[1]) & 1);
- write_seqlock(&net->ipv4.ip_local_ports.lock);
+ write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
if (same_parity && !net->ipv4.ip_local_ports.warned) {
net->ipv4.ip_local_ports.warned = true;
pr_err_ratelimited("ip_local_port_range: prefer different parity for start/end values.\n");
}
net->ipv4.ip_local_ports.range[0] = range[0];
net->ipv4.ip_local_ports.range[1] = range[1];
- write_sequnlock(&net->ipv4.ip_local_ports.lock);
+ write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
}
/* Validate changes from /proc interface. */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0cfa7c0c1e80..c1728771cf89 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -451,11 +451,14 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
unsigned int mask;
struct sock *sk = sock->sk;
const struct tcp_sock *tp = tcp_sk(sk);
+ int state;
sock_rps_record_flow(sk);
sock_poll_wait(file, sk_sleep(sk), wait);
- if (sk->sk_state == TCP_LISTEN)
+
+ state = sk_state_load(sk);
+ if (state == TCP_LISTEN)
return inet_csk_listen_poll(sk);
/* Socket is not locked. We are protected from async events
@@ -492,14 +495,14 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
* NOTE. Check for TCP_CLOSE is added. The goal is to prevent
* blocking on fresh not-connected or disconnected socket. --ANK
*/
- if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE)
+ if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
mask |= POLLHUP;
if (sk->sk_shutdown & RCV_SHUTDOWN)
mask |= POLLIN | POLLRDNORM | POLLRDHUP;
/* Connected or passive Fast Open socket? */
- if (sk->sk_state != TCP_SYN_SENT &&
- (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk)) {
+ if (state != TCP_SYN_SENT &&
+ (state != TCP_SYN_RECV || tp->fastopen_rsk)) {
int target = sock_rcvlowat(sk, 0, INT_MAX);
if (tp->urg_seq == tp->copied_seq &&
@@ -507,9 +510,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
tp->urg_data)
target++;
- /* Potential race condition. If read of tp below will
- * escape above sk->sk_state, we can be illegally awaken
- * in SYN_* states. */
if (tp->rcv_nxt - tp->copied_seq >= target)
mask |= POLLIN | POLLRDNORM;
@@ -1934,7 +1934,7 @@ void tcp_set_state(struct sock *sk, int state)
/* Change state AFTER socket is unhashed to avoid closed
* socket sitting in hash tables.
*/
- sk->sk_state = state;
+ sk_state_store(sk, state);
#ifdef STATE_TRACE
SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]);
@@ -2644,7 +2644,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
if (sk->sk_type != SOCK_STREAM)
return;
- info->tcpi_state = sk->sk_state;
+ info->tcpi_state = sk_state_load(sk);
+
info->tcpi_ca_state = icsk->icsk_ca_state;
info->tcpi_retransmits = icsk->icsk_retransmits;
info->tcpi_probes = icsk->icsk_probes_out;
@@ -2672,7 +2673,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_snd_mss = tp->mss_cache;
info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss;
- if (sk->sk_state == TCP_LISTEN) {
+ if (info->tcpi_state == TCP_LISTEN) {
info->tcpi_unacked = sk->sk_ack_backlog;
info->tcpi_sacked = sk->sk_max_ack_backlog;
} else {
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 479f34946177..b31604086edd 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -21,7 +21,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
{
struct tcp_info *info = _info;
- if (sk->sk_state == TCP_LISTEN) {
+ if (sk_state_load(sk) == TCP_LISTEN) {
r->idiag_rqueue = sk->sk_ack_backlog;
r->idiag_wqueue = sk->sk_max_ack_backlog;
} else if (sk->sk_type == SOCK_STREAM) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1c2648bbac4b..ba09016d1bfd 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1326,6 +1326,8 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
if (__inet_inherit_port(sk, newsk) < 0)
goto put_and_exit;
*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+ if (*own_req)
+ tcp_move_syn(newtp, req);
return newsk;
@@ -2156,6 +2158,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
__u16 destp = ntohs(inet->inet_dport);
__u16 srcp = ntohs(inet->inet_sport);
int rx_queue;
+ int state;
if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
@@ -2173,17 +2176,18 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
timer_expires = jiffies;
}
- if (sk->sk_state == TCP_LISTEN)
+ state = sk_state_load(sk);
+ if (state == TCP_LISTEN)
rx_queue = sk->sk_ack_backlog;
else
- /*
- * because we dont lock socket, we might find a transient negative value
+ /* Because we don't lock the socket,
+ * we might find a transient negative value.
*/
rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
"%08X %5u %8d %lu %d %pK %lu %lu %u %u %d",
- i, src, srcp, dest, destp, sk->sk_state,
+ i, src, srcp, dest, destp, state,
tp->write_seq - tp->snd_una,
rx_queue,
timer_active,
@@ -2197,8 +2201,8 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
jiffies_to_clock_t(icsk->icsk_ack.ato),
(icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
tp->snd_cwnd,
- sk->sk_state == TCP_LISTEN ?
- (fastopenq ? fastopenq->max_qlen : 0) :
+ state == TCP_LISTEN ?
+ fastopenq->max_qlen :
(tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh));
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 3575dd1e5b67..ac6b1961ffeb 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -551,9 +551,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
newtp->rack.mstamp.v64 = 0;
newtp->rack.advanced = 0;
- newtp->saved_syn = req->saved_syn;
- req->saved_syn = NULL;
-
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_PASSIVEOPENS);
}
return newsk;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.