summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig10
-rw-r--r--net/ipv4/af_inet.c36
-rw-r--r--net/ipv4/datagram.c4
-rw-r--r--net/ipv4/fib_frontend.c4
-rw-r--r--net/ipv4/fib_semantics.c10
-rw-r--r--net/ipv4/fib_trie.c6
-rw-r--r--net/ipv4/igmp.c6
-rw-r--r--net/ipv4/inet_connection_sock.c2
-rw-r--r--net/ipv4/inet_hashtables.c96
-rw-r--r--net/ipv4/inet_timewait_sock.c15
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c4
-rw-r--r--net/ipv4/netfilter/ipt_rpfilter.c3
-rw-r--r--net/ipv4/netfilter/nft_fib_ipv4.c3
-rw-r--r--net/ipv4/nexthop.c2
-rw-r--r--net/ipv4/ping.c23
-rw-r--r--net/ipv4/route.c4
-rw-r--r--net/ipv4/tcp.c16
-rw-r--r--net/ipv4/tcp_bpf.c12
-rw-r--r--net/ipv4/tcp_cdg.c4
-rw-r--r--net/ipv4/tcp_input.c3
-rw-r--r--net/ipv4/tcp_ipv4.c29
-rw-r--r--net/ipv4/tcp_minisocks.c9
-rw-r--r--net/ipv4/tcp_ulp.c3
-rw-r--r--net/ipv4/udp.c14
-rw-r--r--net/ipv4/udp_bpf.c4
-rw-r--r--net/ipv4/udplite.c8
27 files changed, 212 insertions, 120 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index e983bb0c5012..2dfb12230f08 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -402,6 +402,16 @@ config INET_IPCOMP
If unsure, say Y.
+config INET_TABLE_PERTURB_ORDER
+ int "INET: Source port perturbation table size (as power of 2)" if EXPERT
+ default 16
+ help
+ Source port perturbation table size (as power of 2) for
+ RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm.
+
+ The default is almost always what you want.
+ Only change this if you know what you are doing.
+
config INET_XFRM_TUNNEL
tristate
select INET_TUNNEL
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e2c219382345..0da679411330 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -558,22 +558,27 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags)
{
struct sock *sk = sock->sk;
+ const struct proto *prot;
int err;
if (addr_len < sizeof(uaddr->sa_family))
return -EINVAL;
+
+ /* IPV6_ADDRFORM can change sk->sk_prot under us. */
+ prot = READ_ONCE(sk->sk_prot);
+
if (uaddr->sa_family == AF_UNSPEC)
- return sk->sk_prot->disconnect(sk, flags);
+ return prot->disconnect(sk, flags);
if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) {
- err = sk->sk_prot->pre_connect(sk, uaddr, addr_len);
+ err = prot->pre_connect(sk, uaddr, addr_len);
if (err)
return err;
}
if (data_race(!inet_sk(sk)->inet_num) && inet_autobind(sk))
return -EAGAIN;
- return sk->sk_prot->connect(sk, uaddr, addr_len);
+ return prot->connect(sk, uaddr, addr_len);
}
EXPORT_SYMBOL(inet_dgram_connect);
@@ -734,10 +739,11 @@ EXPORT_SYMBOL(inet_stream_connect);
int inet_accept(struct socket *sock, struct socket *newsock, int flags,
bool kern)
{
- struct sock *sk1 = sock->sk;
+ struct sock *sk1 = sock->sk, *sk2;
int err = -EINVAL;
- struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err, kern);
+ /* IPV6_ADDRFORM can change sk->sk_prot under us. */
+ sk2 = READ_ONCE(sk1->sk_prot)->accept(sk1, flags, &err, kern);
if (!sk2)
goto do_err;
@@ -748,6 +754,8 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags,
(TCPF_ESTABLISHED | TCPF_SYN_RECV |
TCPF_CLOSE_WAIT | TCPF_CLOSE)));
+ if (test_bit(SOCK_SUPPORT_ZC, &sock->flags))
+ set_bit(SOCK_SUPPORT_ZC, &newsock->flags);
sock_graft(sk2, newsock);
newsock->state = SS_CONNECTED;
@@ -825,12 +833,15 @@ ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
size_t size, int flags)
{
struct sock *sk = sock->sk;
+ const struct proto *prot;
if (unlikely(inet_send_prepare(sk)))
return -EAGAIN;
- if (sk->sk_prot->sendpage)
- return sk->sk_prot->sendpage(sk, page, offset, size, flags);
+ /* IPV6_ADDRFORM can change sk->sk_prot under us. */
+ prot = READ_ONCE(sk->sk_prot);
+ if (prot->sendpage)
+ return prot->sendpage(sk, page, offset, size, flags);
return sock_no_sendpage(sock, page, offset, size, flags);
}
EXPORT_SYMBOL(inet_sendpage);
@@ -1219,7 +1230,6 @@ EXPORT_SYMBOL(inet_unregister_protosw);
static int inet_sk_reselect_saddr(struct sock *sk)
{
- struct inet_bind_hashbucket *prev_addr_hashbucket;
struct inet_sock *inet = inet_sk(sk);
__be32 old_saddr = inet->inet_saddr;
__be32 daddr = inet->inet_daddr;
@@ -1249,16 +1259,8 @@ static int inet_sk_reselect_saddr(struct sock *sk)
return 0;
}
- prev_addr_hashbucket =
- inet_bhashfn_portaddr(tcp_or_dccp_get_hashinfo(sk), sk,
- sock_net(sk), inet->inet_num);
-
- inet->inet_saddr = inet->inet_rcv_saddr = new_saddr;
-
- err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk);
+ err = inet_bhash2_update_saddr(sk, &new_saddr, AF_INET);
if (err) {
- inet->inet_saddr = old_saddr;
- inet->inet_rcv_saddr = old_saddr;
ip_rt_put(rt);
return err;
}
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 405a8c2aea64..4d1af0cd7d99 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -70,10 +70,10 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
}
inet->inet_daddr = fl4->daddr;
inet->inet_dport = usin->sin_port;
- reuseport_has_conns(sk, true);
+ reuseport_has_conns_set(sk);
sk->sk_state = TCP_ESTABLISHED;
sk_set_txhash(sk);
- inet->inet_id = prandom_u32();
+ inet->inet_id = get_random_u16();
sk_dst_set(sk, &rt->dst);
err = 0;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 943edf4ad4db..f361d3d56be2 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -389,7 +389,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
dev_match = dev_match || (res.type == RTN_LOCAL &&
dev == net->loopback_dev);
if (dev_match) {
- ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK;
+ ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
return ret;
}
if (no_addr)
@@ -401,7 +401,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
ret = 0;
if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
if (res.type == RTN_UNICAST)
- ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK;
+ ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
}
return ret;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 2dc97583d279..f721c308248b 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -888,13 +888,13 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
return 1;
}
+ /* cannot match on nexthop object attributes */
+ if (fi->nh)
+ return 1;
+
if (cfg->fc_oif || cfg->fc_gw_family) {
struct fib_nh *nh;
- /* cannot match on nexthop object attributes */
- if (fi->nh)
- return 1;
-
nh = fib_info_nh(fi, 0);
if (cfg->fc_encap) {
if (fib_encap_match(net, cfg->fc_encap_type,
@@ -1231,7 +1231,7 @@ static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh,
nh->fib_nh_dev = in_dev->dev;
netdev_hold(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC);
- nh->fib_nh_scope = RT_SCOPE_LINK;
+ nh->fib_nh_scope = RT_SCOPE_HOST;
if (!netif_carrier_ok(nh->fib_nh_dev))
nh->fib_nh_flags |= RTNH_F_LINKDOWN;
err = 0;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 452ff177e4da..74d403dbd2b4 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -126,7 +126,7 @@ struct key_vector {
/* This list pointer if valid if (pos | bits) == 0 (LEAF) */
struct hlist_head leaf;
/* This array is valid if (pos | bits) > 0 (TNODE) */
- struct key_vector __rcu *tnode[0];
+ DECLARE_FLEX_ARRAY(struct key_vector __rcu *, tnode);
};
};
@@ -1381,8 +1381,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
/* The alias was already inserted, so the node must exist. */
l = l ? l : fib_find_node(t, &tp, key);
- if (WARN_ON_ONCE(!l))
+ if (WARN_ON_ONCE(!l)) {
+ err = -ENOENT;
goto out_free_new_fa;
+ }
if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) ==
new_fa) {
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index df0660d818ac..81be3e0f0e70 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -213,7 +213,7 @@ static void igmp_stop_timer(struct ip_mc_list *im)
/* It must be called with locked im->lock */
static void igmp_start_timer(struct ip_mc_list *im, int max_delay)
{
- int tv = prandom_u32() % max_delay;
+ int tv = prandom_u32_max(max_delay);
im->tm_running = 1;
if (!mod_timer(&im->timer, jiffies+tv+2))
@@ -222,7 +222,7 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay)
static void igmp_gq_start_timer(struct in_device *in_dev)
{
- int tv = prandom_u32() % in_dev->mr_maxdelay;
+ int tv = prandom_u32_max(in_dev->mr_maxdelay);
unsigned long exp = jiffies + tv + 2;
if (in_dev->mr_gq_running &&
@@ -236,7 +236,7 @@ static void igmp_gq_start_timer(struct in_device *in_dev)
static void igmp_ifc_start_timer(struct in_device *in_dev, int delay)
{
- int tv = prandom_u32() % delay;
+ int tv = prandom_u32_max(delay);
if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2))
in_dev_hold(in_dev);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index ebca860e113f..4e84ed21d16f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -314,7 +314,7 @@ other_half_scan:
if (likely(remaining > 1))
remaining &= ~1U;
- offset = prandom_u32() % remaining;
+ offset = prandom_u32_max(remaining);
/* __inet_hash_connect() favors ports having @low parity
* We do the opposite to not pollute connect() users.
*/
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index a0ad34e4f044..3cec471a2cd2 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -858,34 +858,80 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in
return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)];
}
-int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk)
+static void inet_update_saddr(struct sock *sk, void *saddr, int family)
+{
+ if (family == AF_INET) {
+ inet_sk(sk)->inet_saddr = *(__be32 *)saddr;
+ sk_rcv_saddr_set(sk, inet_sk(sk)->inet_saddr);
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ else {
+ sk->sk_v6_rcv_saddr = *(struct in6_addr *)saddr;
+ }
+#endif
+}
+
+static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset)
{
struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
+ struct inet_bind_hashbucket *head, *head2;
struct inet_bind2_bucket *tb2, *new_tb2;
int l3mdev = inet_sk_bound_l3mdev(sk);
- struct inet_bind_hashbucket *head2;
int port = inet_sk(sk)->inet_num;
struct net *net = sock_net(sk);
+ int bhash;
+
+ if (!inet_csk(sk)->icsk_bind2_hash) {
+ /* Not bind()ed before. */
+ if (reset)
+ inet_reset_saddr(sk);
+ else
+ inet_update_saddr(sk, saddr, family);
+
+ return 0;
+ }
/* Allocate a bind2 bucket ahead of time to avoid permanently putting
* the bhash2 table in an inconsistent state if a new tb2 bucket
* allocation fails.
*/
new_tb2 = kmem_cache_alloc(hinfo->bind2_bucket_cachep, GFP_ATOMIC);
- if (!new_tb2)
+ if (!new_tb2) {
+ if (reset) {
+ /* The (INADDR_ANY, port) bucket might have already
+ * been freed, then we cannot fixup icsk_bind2_hash,
+ * so we give up and unlink sk from bhash/bhash2 not
+ * to leave inconsistency in bhash2.
+ */
+ inet_put_port(sk);
+ inet_reset_saddr(sk);
+ }
+
return -ENOMEM;
+ }
+ bhash = inet_bhashfn(net, port, hinfo->bhash_size);
+ head = &hinfo->bhash[bhash];
head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);
- if (prev_saddr) {
- spin_lock_bh(&prev_saddr->lock);
- __sk_del_bind2_node(sk);
- inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep,
- inet_csk(sk)->icsk_bind2_hash);
- spin_unlock_bh(&prev_saddr->lock);
- }
+ /* If we change saddr locklessly, another thread
+ * iterating over bhash might see corrupted address.
+ */
+ spin_lock_bh(&head->lock);
- spin_lock_bh(&head2->lock);
+ spin_lock(&head2->lock);
+ __sk_del_bind2_node(sk);
+ inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash);
+ spin_unlock(&head2->lock);
+
+ if (reset)
+ inet_reset_saddr(sk);
+ else
+ inet_update_saddr(sk, saddr, family);
+
+ head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);
+
+ spin_lock(&head2->lock);
tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk);
if (!tb2) {
tb2 = new_tb2;
@@ -893,26 +939,40 @@ int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct soc
}
sk_add_bind2_node(sk, &tb2->owners);
inet_csk(sk)->icsk_bind2_hash = tb2;
- spin_unlock_bh(&head2->lock);
+ spin_unlock(&head2->lock);
+
+ spin_unlock_bh(&head->lock);
if (tb2 != new_tb2)
kmem_cache_free(hinfo->bind2_bucket_cachep, new_tb2);
return 0;
}
+
+int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family)
+{
+ return __inet_bhash2_update_saddr(sk, saddr, family, false);
+}
EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr);
+void inet_bhash2_reset_saddr(struct sock *sk)
+{
+ if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+ __inet_bhash2_update_saddr(sk, NULL, 0, true);
+}
+EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr);
+
/* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm
* Note that we use 32bit integers (vs RFC 'short integers')
* because 2^16 is not a multiple of num_ephemeral and this
* property might be used by clever attacker.
+ *
* RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though
- * attacks were since demonstrated, thus we use 65536 instead to really
- * give more isolation and privacy, at the expense of 256kB of kernel
- * memory.
+ * attacks were since demonstrated, thus we use 65536 by default instead
+ * to really give more isolation and privacy, at the expense of 256kB
+ * of kernel memory.
*/
-#define INET_TABLE_PERTURB_SHIFT 16
-#define INET_TABLE_PERTURB_SIZE (1 << INET_TABLE_PERTURB_SHIFT)
+#define INET_TABLE_PERTURB_SIZE (1 << CONFIG_INET_TABLE_PERTURB_ORDER)
static u32 *table_perturb;
int __inet_hash_connect(struct inet_timewait_death_row *death_row,
@@ -1037,7 +1097,7 @@ ok:
* on low contention the randomness is maximal and on high contention
* it may be inexistent.
*/
- i = max_t(int, i, (prandom_u32() & 7) * 2);
+ i = max_t(int, i, prandom_u32_max(8) * 2);
WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2);
/* Head lock still held and bh's disabled */
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 71d3bb0abf6c..66fc940f9521 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -268,8 +268,21 @@ restart_rcu:
rcu_read_lock();
restart:
sk_nulls_for_each_rcu(sk, node, &head->chain) {
- if (sk->sk_state != TCP_TIME_WAIT)
+ if (sk->sk_state != TCP_TIME_WAIT) {
+ /* A kernel listener socket might not hold refcnt for net,
+ * so reqsk_timer_handler() could be fired after net is
+ * freed. Userspace listener and reqsk never exist here.
+ */
+ if (unlikely(sk->sk_state == TCP_NEW_SYN_RECV &&
+ hashinfo->pernet)) {
+ struct request_sock *req = inet_reqsk(sk);
+
+ inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req);
+ }
+
continue;
+ }
+
tw = inet_twsk(sk);
if ((tw->tw_family != family) ||
refcount_read(&twsk_net(tw)->ns.count))
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 1ae83ad629b2..922c87ef1ab5 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -172,7 +172,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
* Avoid using the hashed IP ident generator.
*/
if (sk->sk_protocol == IPPROTO_TCP)
- iph->id = (__force __be16)prandom_u32();
+ iph->id = (__force __be16)get_random_u16();
else
__ip_select_ident(net, iph, 1);
}
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index f8e176c77d1c..b3cc416ed292 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -435,7 +435,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
switch (ctinfo) {
case IP_CT_NEW:
- ct->mark = hash;
+ WRITE_ONCE(ct->mark, hash);
break;
case IP_CT_RELATED:
case IP_CT_RELATED_REPLY:
@@ -452,7 +452,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
#ifdef DEBUG
nf_ct_dump_tuple_ip(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
#endif
- pr_debug("hash=%u ct_hash=%u ", hash, ct->mark);
+ pr_debug("hash=%u ct_hash=%u ", hash, READ_ONCE(ct->mark));
if (!clusterip_responsible(cipinfo->config, hash)) {
pr_debug("not responsible\n");
return NF_DROP;
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index 8183bbcabb4a..ded5bef02f77 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -77,7 +77,8 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
flow.flowi4_tos = iph->tos & IPTOS_RT_MASK;
flow.flowi4_scope = RT_SCOPE_UNIVERSE;
- flow.flowi4_oif = l3mdev_master_ifindex_rcu(xt_in(par));
+ flow.flowi4_l3mdev = l3mdev_master_ifindex_rcu(xt_in(par));
+ flow.flowi4_uid = sock_net_uid(xt_net(par), NULL);
return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert;
}
diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index 7ade04ff972d..fc65d69f23e1 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -65,6 +65,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
struct flowi4 fl4 = {
.flowi4_scope = RT_SCOPE_UNIVERSE,
.flowi4_iif = LOOPBACK_IFINDEX,
+ .flowi4_uid = sock_net_uid(nft_net(pkt), NULL),
};
const struct net_device *oif;
const struct net_device *found;
@@ -84,7 +85,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
oif = NULL;
if (priv->flags & NFTA_FIB_F_IIF)
- fl4.flowi4_oif = l3mdev_master_ifindex_rcu(oif);
+ fl4.flowi4_l3mdev = l3mdev_master_ifindex_rcu(oif);
if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 853a75a8fbaf..d8ef05347fd9 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -2534,7 +2534,7 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh,
if (!err) {
nh->nh_flags = fib_nh->fib_nh_flags;
fib_info_update_nhc_saddr(net, &fib_nh->nh_common,
- fib_nh->fib_nh_scope);
+ !fib_nh->fib_nh_scope ? 0 : fib_nh->fib_nh_scope - 1);
} else {
fib_nh_release(net, fib_nh);
}
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 517042caf6dc..bde333b24837 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -617,21 +617,9 @@ int ping_getfrag(void *from, char *to,
{
struct pingfakehdr *pfh = from;
- if (offset == 0) {
- fraglen -= sizeof(struct icmphdr);
- if (fraglen < 0)
- BUG();
- if (!csum_and_copy_from_iter_full(to + sizeof(struct icmphdr),
- fraglen, &pfh->wcheck,
- &pfh->msg->msg_iter))
- return -EFAULT;
- } else if (offset < sizeof(struct icmphdr)) {
- BUG();
- } else {
- if (!csum_and_copy_from_iter_full(to, fraglen, &pfh->wcheck,
- &pfh->msg->msg_iter))
- return -EFAULT;
- }
+ if (!csum_and_copy_from_iter_full(to, fraglen, &pfh->wcheck,
+ &pfh->msg->msg_iter))
+ return -EFAULT;
#if IS_ENABLED(CONFIG_IPV6)
/* For IPv6, checksum each skb as we go along, as expected by
@@ -639,7 +627,7 @@ int ping_getfrag(void *from, char *to,
* wcheck, it will be finalized in ping_v4_push_pending_frames.
*/
if (pfh->family == AF_INET6) {
- skb->csum = pfh->wcheck;
+ skb->csum = csum_block_add(skb->csum, pfh->wcheck, odd);
skb->ip_summed = CHECKSUM_NONE;
pfh->wcheck = 0;
}
@@ -842,7 +830,8 @@ back_from_confirm:
pfh.family = AF_INET;
err = ip_append_data(sk, &fl4, ping_getfrag, &pfh, len,
- 0, &ipc, &rt, msg->msg_flags);
+ sizeof(struct icmphdr), &ipc, &rt,
+ msg->msg_flags);
if (err)
ip_flush_pending_frames(sk);
else
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 795cbe1de912..cd1fa9f70f1a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3664,7 +3664,7 @@ static __net_init int rt_genid_init(struct net *net)
{
atomic_set(&net->ipv4.rt_genid, 0);
atomic_set(&net->fnhe_genid, 0);
- atomic_set(&net->ipv4.dev_addr_genid, get_random_int());
+ atomic_set(&net->ipv4.dev_addr_genid, get_random_u32());
return 0;
}
@@ -3719,7 +3719,7 @@ int __init ip_rt_init(void)
ip_idents = idents_hash;
- prandom_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents));
+ get_random_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents));
ip_tstamps = idents_hash + (ip_idents_mask + 1) * sizeof(*ip_idents);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0c51abeee172..4f2205756cfe 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -457,6 +457,7 @@ void tcp_init_sock(struct sock *sk)
WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]));
WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]));
+ set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
sk_sockets_allocated_inc(sk);
}
EXPORT_SYMBOL(tcp_init_sock);
@@ -3113,8 +3114,7 @@ int tcp_disconnect(struct sock *sk, int flags)
inet->inet_dport = 0;
- if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
- inet_reset_saddr(sk);
+ inet_bhash2_reset_saddr(sk);
sk->sk_shutdown = 0;
sock_reset_flag(sk, SOCK_DONE);
@@ -3646,7 +3646,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
case TCP_REPAIR_OPTIONS:
if (!tp->repair)
err = -EINVAL;
- else if (sk->sk_state == TCP_ESTABLISHED)
+ else if (sk->sk_state == TCP_ESTABLISHED && !tp->bytes_sent)
err = tcp_repair_options_est(sk, optval, optlen);
else
err = -EPERM;
@@ -3796,8 +3796,9 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
const struct inet_connection_sock *icsk = inet_csk(sk);
if (level != SOL_TCP)
- return icsk->icsk_af_ops->setsockopt(sk, level, optname,
- optval, optlen);
+ /* Paired with WRITE_ONCE() in do_ipv6_setsockopt() and tcp_v6_connect() */
+ return READ_ONCE(icsk->icsk_af_ops)->setsockopt(sk, level, optname,
+ optval, optlen);
return do_tcp_setsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(tcp_setsockopt);
@@ -4396,8 +4397,9 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
struct inet_connection_sock *icsk = inet_csk(sk);
if (level != SOL_TCP)
- return icsk->icsk_af_ops->getsockopt(sk, level, optname,
- optval, optlen);
+ /* Paired with WRITE_ONCE() in do_ipv6_setsockopt() and tcp_v6_connect() */
+ return READ_ONCE(icsk->icsk_af_ops)->getsockopt(sk, level, optname,
+ optval, optlen);
return do_tcp_getsockopt(sk, level, optname, USER_SOCKPTR(optval),
USER_SOCKPTR(optlen));
}
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index a1626afe87a1..cf9c3e8f7ccb 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -278,7 +278,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
{
bool cork = false, enospc = sk_msg_full(msg);
struct sock *sk_redir;
- u32 tosend, delta = 0;
+ u32 tosend, origsize, sent, delta = 0;
u32 eval = __SK_NONE;
int ret;
@@ -333,10 +333,12 @@ more_data:
cork = true;
psock->cork = NULL;
}
- sk_msg_return(sk, msg, msg->sg.size);
+ sk_msg_return(sk, msg, tosend);
release_sock(sk);
+ origsize = msg->sg.size;
ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
+ sent = origsize - msg->sg.size;
if (eval == __SK_REDIRECT)
sock_put(sk_redir);
@@ -375,7 +377,7 @@ more_data:
msg->sg.data[msg->sg.start].page_link &&
msg->sg.data[msg->sg.start].length) {
if (eval == __SK_REDIRECT)
- sk_mem_charge(sk, msg->sg.size);
+ sk_mem_charge(sk, tosend - sent);
goto more_data;
}
}
@@ -607,7 +609,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
} else {
sk->sk_write_space = psock->saved_write_space;
/* Pairs with lockless read in sk_clone_lock() */
- WRITE_ONCE(sk->sk_prot, psock->sk_proto);
+ sock_replace_proto(sk, psock->sk_proto);
}
return 0;
}
@@ -620,7 +622,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
}
/* Pairs with lockless read in sk_clone_lock() */
- WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]);
+ sock_replace_proto(sk, &tcp_bpf_prots[family][config]);
return 0;
}
EXPORT_SYMBOL_GPL(tcp_bpf_update_proto);
diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c
index ddc7ba0554bd..ba4d98e510e0 100644
--- a/net/ipv4/tcp_cdg.c
+++ b/net/ipv4/tcp_cdg.c
@@ -243,7 +243,7 @@ static bool tcp_cdg_backoff(struct sock *sk, u32 grad)
struct cdg *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
- if (prandom_u32() <= nexp_u32(grad * backoff_factor))
+ if (get_random_u32() <= nexp_u32(grad * backoff_factor))
return false;
if (use_ineff) {
@@ -375,6 +375,7 @@ static void tcp_cdg_init(struct sock *sk)
struct cdg *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ ca->gradients = NULL;
/* We silently fall back to window = 1 if allocation fails. */
if (window > 1)
ca->gradients = kcalloc(window, sizeof(ca->gradients[0]),
@@ -388,6 +389,7 @@ static void tcp_cdg_release(struct sock *sk)
struct cdg *ca = inet_csk_ca(sk);
kfree(ca->gradients);
+ ca->gradients = NULL;
}
static struct tcp_congestion_ops tcp_cdg __read_mostly = {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bc2ea12221f9..0640453fce54 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2192,7 +2192,8 @@ void tcp_enter_loss(struct sock *sk)
*/
static bool tcp_check_sack_reneging(struct sock *sk, int flag)
{
- if (flag & FLAG_SACK_RENEGING) {
+ if (flag & FLAG_SACK_RENEGING &&
+ flag & FLAG_SND_UNA_ADVANCED) {
struct tcp_sock *tp = tcp_sk(sk);
unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4),
msecs_to_jiffies(10));
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6376ad915765..da46357f501b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -199,15 +199,14 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr,
/* This will initiate an outgoing connection. */
int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
- struct inet_bind_hashbucket *prev_addr_hashbucket = NULL;
struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
struct inet_timewait_death_row *tcp_death_row;
- __be32 daddr, nexthop, prev_sk_rcv_saddr;
struct inet_sock *inet = inet_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct ip_options_rcu *inet_opt;
struct net *net = sock_net(sk);
__be16 orig_sport, orig_dport;
+ __be32 daddr, nexthop;
struct flowi4 *fl4;
struct rtable *rt;
int err;
@@ -251,24 +250,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
if (!inet->inet_saddr) {
- if (inet_csk(sk)->icsk_bind2_hash) {
- prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo,
- sk, net, inet->inet_num);
- prev_sk_rcv_saddr = sk->sk_rcv_saddr;
- }
- inet->inet_saddr = fl4->saddr;
- }
-
- sk_rcv_saddr_set(sk, inet->inet_saddr);
-
- if (prev_addr_hashbucket) {
- err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk);
+ err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET);
if (err) {
- inet->inet_saddr = 0;
- sk_rcv_saddr_set(sk, prev_sk_rcv_saddr);
ip_rt_put(rt);
return err;
}
+ } else {
+ sk_rcv_saddr_set(sk, inet->inet_saddr);
}
if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) {
@@ -323,7 +311,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
inet->inet_daddr);
}
- inet->inet_id = prandom_u32();
+ inet->inet_id = get_random_u16();
if (tcp_fastopen_defer_connect(sk, &err))
return err;
@@ -343,6 +331,7 @@ failure:
* if necessary.
*/
tcp_set_state(sk, TCP_CLOSE);
+ inet_bhash2_reset_saddr(sk);
ip_rt_put(rt);
sk->sk_route_caps = 0;
inet->inet_dport = 0;
@@ -1543,7 +1532,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (inet_opt)
inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
- newinet->inet_id = prandom_u32();
+ newinet->inet_id = get_random_u16();
/* Set ToS of the new socket based upon the value of incoming SYN.
* ECT bits are set later in tcp_init_transfer().
@@ -1874,11 +1863,13 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
__skb_push(skb, hdrlen);
no_coalesce:
+ limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1);
+
/* Only socket owner can try to collapse/prune rx queues
* to reduce memory overhead, so add a little headroom here.
* Few sockets backlog are possibly concurrently non empty.
*/
- limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf) + 64*1024;
+ limit += 64 * 1024;
if (unlikely(sk_add_backlog(sk, skb, limit))) {
bh_unlock_sock(sk);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 79f30f026d89..c375f603a16c 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -353,13 +353,14 @@ void tcp_twsk_purge(struct list_head *net_exit_list, int family)
struct net *net;
list_for_each_entry(net, net_exit_list, exit_list) {
- /* The last refcount is decremented in tcp_sk_exit_batch() */
- if (refcount_read(&net->ipv4.tcp_death_row.tw_refcount) == 1)
- continue;
-
if (net->ipv4.tcp_death_row.hashinfo->pernet) {
+ /* Even if tw_refcount == 1, we must clean up kernel reqsk */
inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo, family);
} else if (!purged_once) {
+ /* The last refcount is decremented in tcp_sk_exit_batch() */
+ if (refcount_read(&net->ipv4.tcp_death_row.tw_refcount) == 1)
+ continue;
+
inet_twsk_purge(&tcp_hashinfo, family);
purged_once = true;
}
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 7c27aa629af1..9ae50b1bd844 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -136,6 +136,9 @@ static int __tcp_set_ulp(struct sock *sk, const struct tcp_ulp_ops *ulp_ops)
if (icsk->icsk_ulp_ops)
goto out_err;
+ if (sk->sk_socket)
+ clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
+
err = ulp_ops->init(sk);
if (err)
goto out_err;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d63118ce5900..6a320a614e54 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -246,7 +246,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
inet_get_local_port_range(net, &low, &high);
remaining = (high - low) + 1;
- rand = prandom_u32();
+ rand = get_random_u32();
first = reciprocal_scale(rand, remaining) + low;
/*
* force rand to be an odd multiple of UDP_HTABLE_SIZE
@@ -448,7 +448,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
result = lookup_reuseport(net, sk, skb,
saddr, sport, daddr, hnum);
/* Fall back to scoring if group has connections */
- if (result && !reuseport_has_conns(sk, false))
+ if (result && !reuseport_has_conns(sk))
return result;
result = result ? : sk;
@@ -1598,7 +1598,7 @@ drop:
}
EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb);
-void udp_destruct_sock(struct sock *sk)
+void udp_destruct_common(struct sock *sk)
{
/* reclaim completely the forward allocated memory */
struct udp_sock *up = udp_sk(sk);
@@ -1611,18 +1611,22 @@ void udp_destruct_sock(struct sock *sk)
kfree_skb(skb);
}
udp_rmem_release(sk, total, 0, true);
+}
+EXPORT_SYMBOL_GPL(udp_destruct_common);
+static void udp_destruct_sock(struct sock *sk)
+{
+ udp_destruct_common(sk);
inet_sock_destruct(sk);
}
-EXPORT_SYMBOL_GPL(udp_destruct_sock);
int udp_init_sock(struct sock *sk)
{
skb_queue_head_init(&udp_sk(sk)->reader_queue);
sk->sk_destruct = udp_destruct_sock;
+ set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
return 0;
}
-EXPORT_SYMBOL_GPL(udp_init_sock);
void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
{
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index ff15918b7bdc..e5dc91d0e079 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -141,14 +141,14 @@ int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
if (restore) {
sk->sk_write_space = psock->saved_write_space;
- WRITE_ONCE(sk->sk_prot, psock->sk_proto);
+ sock_replace_proto(sk, psock->sk_proto);
return 0;
}
if (sk->sk_family == AF_INET6)
udp_bpf_check_v6_needs_rebuild(psock->sk_proto);
- WRITE_ONCE(sk->sk_prot, &udp_bpf_prots[family]);
+ sock_replace_proto(sk, &udp_bpf_prots[family]);
return 0;
}
EXPORT_SYMBOL_GPL(udp_bpf_update_proto);
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 6e08a76ae1e7..e0c9cc39b81e 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -17,6 +17,14 @@
struct udp_table udplite_table __read_mostly;
EXPORT_SYMBOL(udplite_table);
+/* Designate sk as UDP-Lite socket */
+static int udplite_sk_init(struct sock *sk)
+{
+ udp_init_sock(sk);
+ udp_sk(sk)->pcflag = UDPLITE_BIT;
+ return 0;
+}
+
static int udplite_rcv(struct sk_buff *skb)
{
return __udp4_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE);
generated by cgit (git 2.34.1) at 2025-05-05 21:20:24 +0000