summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/icmp.c23
-rw-r--r--net/ipv4/igmp.c2
-rw-r--r--net/ipv4/ip_output.c5
-rw-r--r--net/ipv4/route.c46
-rw-r--r--net/ipv4/tcp_ipv4.c9
-rw-r--r--net/ipv4/tcp_output.c1
6 files changed, 62 insertions, 24 deletions
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index c16c199d9cd9..0a9fb3d2ba90 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -460,6 +460,23 @@ static int icmp_multipath_hash_skb(const struct sk_buff *skb)
#endif
+/*
+ * The device used for looking up which routing table to use for sending an ICMP
+ * error is preferably the source whenever it is set, which should ensure the
+ * icmp error can be sent to the source host, else lookup using the routing
+ * table of the destination device, else use the main routing table (index 0).
+ */
+static struct net_device *icmp_get_route_lookup_dev(struct sk_buff *skb)
+{
+ struct net_device *route_lookup_dev = NULL;
+
+ if (skb->dev)
+ route_lookup_dev = skb->dev;
+ else if (skb_dst(skb))
+ route_lookup_dev = skb_dst(skb)->dev;
+ return route_lookup_dev;
+}
+
static struct rtable *icmp_route_lookup(struct net *net,
struct flowi4 *fl4,
struct sk_buff *skb_in,
@@ -468,6 +485,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
int type, int code,
struct icmp_bxm *param)
{
+ struct net_device *route_lookup_dev;
struct rtable *rt, *rt2;
struct flowi4 fl4_dec;
int err;
@@ -481,7 +499,8 @@ static struct rtable *icmp_route_lookup(struct net *net,
fl4->flowi4_proto = IPPROTO_ICMP;
fl4->fl4_icmp_type = type;
fl4->fl4_icmp_code = code;
- fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev);
+ route_lookup_dev = icmp_get_route_lookup_dev(skb_in);
+ fl4->flowi4_oif = l3mdev_master_ifindex(route_lookup_dev);
security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
rt = __ip_route_output_key_hash(net, fl4,
@@ -506,7 +525,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
if (err)
goto relookup_failed;
- if (inet_addr_type_dev_table(net, skb_dst(skb_in)->dev,
+ if (inet_addr_type_dev_table(net, route_lookup_dev,
fl4_dec.saddr) == RTN_LOCAL) {
rt2 = __ip_route_output_key(net, &fl4_dec);
if (IS_ERR(rt2))
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index c67efa3e79dd..7b0bbda676b3 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2631,6 +2631,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u
rv = 1;
} else if (im) {
if (src_addr) {
+ spin_lock_bh(&im->lock);
for (psf = im->sources; psf; psf = psf->sf_next) {
if (psf->sf_inaddr == src_addr)
break;
@@ -2641,6 +2642,7 @@ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u
im->sfcount[MCAST_EXCLUDE];
else
rv = im->sfcount[MCAST_EXCLUDE] != 0;
+ spin_unlock_bh(&im->lock);
} else
rv = 1; /* unspecified source; tentatively allow */
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e808227c58d6..477540b3d320 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -376,8 +376,9 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4)
{
BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) !=
offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr));
- memcpy(&iph->saddr, &fl4->saddr,
- sizeof(fl4->saddr) + sizeof(fl4->daddr));
+
+ iph->saddr = fl4->saddr;
+ iph->daddr = fl4->daddr;
}
/* Note: skb->sk can be different from sk, in case of tunnels */
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 2ab2289d97a0..ed6483181676 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -597,18 +597,25 @@ static void fnhe_flush_routes(struct fib_nh_exception *fnhe)
}
}
-static struct fib_nh_exception *fnhe_oldest(struct fnhe_hash_bucket *hash)
+static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash)
{
- struct fib_nh_exception *fnhe, *oldest;
+ struct fib_nh_exception __rcu **fnhe_p, **oldest_p;
+ struct fib_nh_exception *fnhe, *oldest = NULL;
- oldest = rcu_dereference(hash->chain);
- for (fnhe = rcu_dereference(oldest->fnhe_next); fnhe;
- fnhe = rcu_dereference(fnhe->fnhe_next)) {
- if (time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp))
+ for (fnhe_p = &hash->chain; ; fnhe_p = &fnhe->fnhe_next) {
+ fnhe = rcu_dereference_protected(*fnhe_p,
+ lockdep_is_held(&fnhe_lock));
+ if (!fnhe)
+ break;
+ if (!oldest ||
+ time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) {
oldest = fnhe;
+ oldest_p = fnhe_p;
+ }
}
fnhe_flush_routes(oldest);
- return oldest;
+ *oldest_p = oldest->fnhe_next;
+ kfree_rcu(oldest, rcu);
}
static inline u32 fnhe_hashfun(__be32 daddr)
@@ -685,16 +692,21 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
if (rt)
fill_route_from_fnhe(rt, fnhe);
} else {
- if (depth > FNHE_RECLAIM_DEPTH)
- fnhe = fnhe_oldest(hash);
- else {
- fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC);
- if (!fnhe)
- goto out_unlock;
-
- fnhe->fnhe_next = hash->chain;
- rcu_assign_pointer(hash->chain, fnhe);
+ /* Randomize max depth to avoid some side channels attacks. */
+ int max_depth = FNHE_RECLAIM_DEPTH +
+ prandom_u32_max(FNHE_RECLAIM_DEPTH);
+
+ while (depth > max_depth) {
+ fnhe_remove_oldest(hash);
+ depth--;
}
+
+ fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC);
+ if (!fnhe)
+ goto out_unlock;
+
+ fnhe->fnhe_next = hash->chain;
+
fnhe->fnhe_genid = genid;
fnhe->fnhe_daddr = daddr;
fnhe->fnhe_gw = gw;
@@ -702,6 +714,8 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
fnhe->fnhe_mtu_locked = lock;
fnhe->fnhe_expires = expires;
+ rcu_assign_pointer(hash->chain, fnhe);
+
/* Exception created; mark the cached routes for the nexthop
* stale, so anyone caching it rechecks if this exception
* applies to them.
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3826745a160e..f9d55dd2dec8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -277,7 +277,7 @@ void tcp_v4_mtu_reduced(struct sock *sk)
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
return;
- mtu = tcp_sk(sk)->mtu_info;
+ mtu = READ_ONCE(tcp_sk(sk)->mtu_info);
dst = inet_csk_update_pmtu(sk, mtu);
if (!dst)
return;
@@ -444,7 +444,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
if (sk->sk_state == TCP_LISTEN)
goto out;
- tp->mtu_info = info;
+ WRITE_ONCE(tp->mtu_info, info);
if (!sock_owned_by_user(sk)) {
tcp_v4_mtu_reduced(sk);
} else {
@@ -2033,6 +2033,7 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos)
static void *tcp_seek_last_pos(struct seq_file *seq)
{
struct tcp_iter_state *st = seq->private;
+ int bucket = st->bucket;
int offset = st->offset;
int orig_num = st->num;
void *rc = NULL;
@@ -2043,7 +2044,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq)
break;
st->state = TCP_SEQ_STATE_LISTENING;
rc = listening_get_next(seq, NULL);
- while (offset-- && rc)
+ while (offset-- && rc && bucket == st->bucket)
rc = listening_get_next(seq, rc);
if (rc)
break;
@@ -2054,7 +2055,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq)
if (st->bucket > tcp_hashinfo.ehash_mask)
break;
rc = established_get_first(seq);
- while (offset-- && rc)
+ while (offset-- && rc && bucket == st->bucket)
rc = established_get_next(seq, rc);
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index db037082e6f2..3f061bbf842a 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1353,6 +1353,7 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu)
return __tcp_mtu_to_mss(sk, pmtu) -
(tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr));
}
+EXPORT_SYMBOL(tcp_mtu_to_mss);
/* Inverse of above */
int tcp_mss_to_mtu(struct sock *sk, int mss)
generated by cgit v1.2.3 (git 2.0.4) at 2024-05-02 00:28:57 +0000