summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/esp4.c5
-rw-r--r--net/ipv4/fib_semantics.c7
-rw-r--r--net/ipv4/igmp.c9
-rw-r--r--net/ipv4/inet_hashtables.c42
-rw-r--r--net/ipv4/ip_gre.c16
-rw-r--r--net/ipv4/ip_tunnel.c9
-rw-r--r--net/ipv4/netfilter/nf_flow_table_ipv4.c0
-rw-r--r--net/ipv4/ping.c12
-rw-r--r--net/ipv4/route.c1
-rw-r--r--net/ipv4/syncookies.c8
-rw-r--r--net/ipv4/tcp_input.c15
-rw-r--r--net/ipv4/tcp_minisocks.c2
-rw-r--r--net/ipv4/tcp_output.c1
-rw-r--r--net/ipv4/tcp_rate.c11
14 files changed, 95 insertions, 43 deletions
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 70e6c87fbe3d..d747166bb291 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -446,7 +446,6 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
struct page *page;
struct sk_buff *trailer;
int tailen = esp->tailen;
- unsigned int allocsz;
/* this is non-NULL only with TCP/UDP Encapsulation */
if (x->encap) {
@@ -456,8 +455,8 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
return err;
}
- allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES);
- if (allocsz > ESP_SKB_FRAG_MAXSIZE)
+ if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
+ ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
goto cow;
if (!skb_cloned(skb)) {
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index cc8e84ef2ae4..ccb62038f6a4 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -889,8 +889,13 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
}
if (cfg->fc_oif || cfg->fc_gw_family) {
- struct fib_nh *nh = fib_info_nh(fi, 0);
+ 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,
cfg->fc_encap, nh, cfg, extack))
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 2ad3c7b42d6d..1d9e6d5e9a76 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2403,9 +2403,10 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
/* decrease mem now to avoid the memleak warning */
atomic_sub(struct_size(psl, sl_addr, psl->sl_max),
&sk->sk_omem_alloc);
- kfree_rcu(psl, rcu);
}
rcu_assign_pointer(pmc->sflist, newpsl);
+ if (psl)
+ kfree_rcu(psl, rcu);
psl = newpsl;
}
rv = 1; /* > 0 for insert logic below if sl_count is 0 */
@@ -2507,11 +2508,13 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex)
/* decrease mem now to avoid the memleak warning */
atomic_sub(struct_size(psl, sl_addr, psl->sl_max),
&sk->sk_omem_alloc);
- kfree_rcu(psl, rcu);
- } else
+ } else {
(void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode,
0, NULL, 0);
+ }
rcu_assign_pointer(pmc->sflist, newpsl);
+ if (psl)
+ kfree_rcu(psl, rcu);
pmc->sfmode = msf->imsf_fmode;
err = 0;
done:
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 17440840a791..a5d57fa679ca 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -504,7 +504,7 @@ not_unique:
return -EADDRNOTAVAIL;
}
-static u32 inet_sk_port_offset(const struct sock *sk)
+static u64 inet_sk_port_offset(const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
@@ -726,15 +726,17 @@ EXPORT_SYMBOL_GPL(inet_unhash);
* 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,
- * we use 256 instead to really give more isolation and
- * privacy, this only consumes 1 KB of kernel memory.
+ * 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.
*/
-#define INET_TABLE_PERTURB_SHIFT 8
-static u32 table_perturb[1 << INET_TABLE_PERTURB_SHIFT];
+#define INET_TABLE_PERTURB_SHIFT 16
+#define INET_TABLE_PERTURB_SIZE (1 << INET_TABLE_PERTURB_SHIFT)
+static u32 *table_perturb;
int __inet_hash_connect(struct inet_timewait_death_row *death_row,
- struct sock *sk, u32 port_offset,
+ struct sock *sk, u64 port_offset,
int (*check_established)(struct inet_timewait_death_row *,
struct sock *, __u16, struct inet_timewait_sock **))
{
@@ -774,10 +776,13 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
if (likely(remaining > 1))
remaining &= ~1U;
- net_get_random_once(table_perturb, sizeof(table_perturb));
- index = hash_32(port_offset, INET_TABLE_PERTURB_SHIFT);
+ net_get_random_once(table_perturb,
+ INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb));
+ index = port_offset & (INET_TABLE_PERTURB_SIZE - 1);
+
+ offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32);
+ offset %= remaining;
- offset = (READ_ONCE(table_perturb[index]) + port_offset) % remaining;
/* In first pass we try ports of @low parity.
* inet_csk_get_port() does the opposite choice.
*/
@@ -831,11 +836,12 @@ next_port:
return -EADDRNOTAVAIL;
ok:
- /* If our first attempt found a candidate, skip next candidate
- * in 1/16 of cases to add some noise.
+ /* Here we want to add a little bit of randomness to the next source
+ * port that will be chosen. We use a max() with a random here so that
+ * on low contention the randomness is maximal and on high contention
+ * it may be inexistent.
*/
- if (!i && !(prandom_u32() % 16))
- i = 2;
+ i = max_t(int, i, (prandom_u32() & 7) * 2);
WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2);
/* Head lock still held and bh's disabled */
@@ -859,7 +865,7 @@ ok:
int inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk)
{
- u32 port_offset = 0;
+ u64 port_offset = 0;
if (!inet_sk(sk)->inet_num)
port_offset = inet_sk_port_offset(sk);
@@ -909,6 +915,12 @@ void __init inet_hashinfo2_init(struct inet_hashinfo *h, const char *name,
low_limit,
high_limit);
init_hashinfo_lhash2(h);
+
+ /* this one is used for source ports of outgoing connections */
+ table_perturb = kmalloc_array(INET_TABLE_PERTURB_SIZE,
+ sizeof(*table_perturb), GFP_KERNEL);
+ if (!table_perturb)
+ panic("TCP: failed to alloc table_perturb");
}
int inet_hashinfo2_init_mod(struct inet_hashinfo *h)
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 99db2e41ed10..aacee9dd771b 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -459,14 +459,12 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
__be16 proto)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
-
- if (tunnel->parms.o_flags & TUNNEL_SEQ)
- tunnel->o_seqno++;
+ __be16 flags = tunnel->parms.o_flags;
/* Push GRE header. */
gre_build_header(skb, tunnel->tun_hlen,
- tunnel->parms.o_flags, proto, tunnel->parms.o_key,
- htonl(tunnel->o_seqno));
+ flags, proto, tunnel->parms.o_key,
+ (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0);
ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol);
}
@@ -504,7 +502,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev,
(TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ);
gre_build_header(skb, tunnel_hlen, flags, proto,
tunnel_id_to_key32(tun_info->key.tun_id),
- (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0);
+ (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0);
ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen);
@@ -581,7 +579,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
}
gre_build_header(skb, 8, TUNNEL_SEQ,
- proto, 0, htonl(tunnel->o_seqno++));
+ proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno)));
ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen);
@@ -605,8 +603,8 @@ static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
key = &info->key;
ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src,
tunnel_id_to_key32(key->tun_id),
- key->tos & ~INET_ECN_MASK, 0, skb->mark,
- skb_get_hash(skb));
+ key->tos & ~INET_ECN_MASK, dev_net(dev), 0,
+ skb->mark, skb_get_hash(skb));
rt = ip_route_output_key(dev_net(dev), &fl4);
if (IS_ERR(rt))
return PTR_ERR(rt);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 5a473319d3a5..94017a8c3994 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -294,8 +294,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr,
iph->saddr, tunnel->parms.o_key,
- RT_TOS(iph->tos), tunnel->parms.link,
- tunnel->fwmark, 0);
+ RT_TOS(iph->tos), dev_net(dev),
+ tunnel->parms.link, tunnel->fwmark, 0);
rt = ip_route_output_key(tunnel->net, &fl4);
if (!IS_ERR(rt)) {
@@ -570,7 +570,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
}
ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src,
tunnel_id_to_key32(key->tun_id), RT_TOS(tos),
- 0, skb->mark, skb_get_hash(skb));
+ dev_net(dev), 0, skb->mark, skb_get_hash(skb));
if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
goto tx_error;
@@ -726,7 +726,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
}
ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr,
- tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
+ tunnel->parms.o_key, RT_TOS(tos),
+ dev_net(dev), tunnel->parms.link,
tunnel->fwmark, skb_get_hash(skb));
if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c
deleted file mode 100644
index e69de29bb2d1..000000000000
--- a/net/ipv4/netfilter/nf_flow_table_ipv4.c
+++ /dev/null
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 3ee947557b88..aa9a11b20d18 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -305,6 +305,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
struct net *net = sock_net(sk);
if (sk->sk_family == AF_INET) {
struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
+ u32 tb_id = RT_TABLE_LOCAL;
int chk_addr_ret;
if (addr_len < sizeof(*addr))
@@ -318,7 +319,8 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));
- chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr);
+ tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id;
+ chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id);
if (!inet_addr_valid_or_nonlocal(net, inet_sk(sk),
addr->sin_addr.s_addr,
@@ -355,6 +357,14 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
return -ENODEV;
}
}
+
+ if (!dev && sk->sk_bound_dev_if) {
+ dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
+ if (!dev) {
+ rcu_read_unlock();
+ return -ENODEV;
+ }
+ }
has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev,
scoped);
rcu_read_unlock();
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 98c6f3429593..57abd27e842c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1753,6 +1753,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
#endif
RT_CACHE_STAT_INC(in_slow_mc);
+ skb_dst_drop(skb);
skb_dst_set(skb, &rth->dst);
return 0;
}
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 2cb3b852d148..f33c31dd7366 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -281,6 +281,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt,
EXPORT_SYMBOL(cookie_ecn_ok);
struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
+ const struct tcp_request_sock_ops *af_ops,
struct sock *sk,
struct sk_buff *skb)
{
@@ -297,6 +298,10 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
return NULL;
treq = tcp_rsk(req);
+
+ /* treq->af_specific might be used to perform TCP_MD5 lookup */
+ treq->af_specific = af_ops;
+
treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
#if IS_ENABLED(CONFIG_MPTCP)
treq->is_mptcp = sk_is_mptcp(sk);
@@ -364,7 +369,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
goto out;
ret = NULL;
- req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb);
+ req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops,
+ &tcp_request_sock_ipv4_ops, sk, skb);
if (!req)
goto out;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2088f93fa37b..60f99e9fb6d1 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3867,7 +3867,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
tcp_process_tlp_ack(sk, ack, flag);
if (tcp_ack_is_dubious(sk, flag)) {
- if (!(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP))) {
+ if (!(flag & (FLAG_SND_UNA_ADVANCED |
+ FLAG_NOT_DUP | FLAG_DSACKING_ACK))) {
num_dupack = 1;
/* Consider if pure acks were aggregated in tcp_add_backlog() */
if (!(flag & FLAG_DATA))
@@ -5454,7 +5455,17 @@ static void tcp_new_space(struct sock *sk)
INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk);
}
-static void tcp_check_space(struct sock *sk)
+/* Caller made space either from:
+ * 1) Freeing skbs in rtx queues (after tp->snd_una has advanced)
+ * 2) Sent skbs from output queue (and thus advancing tp->snd_nxt)
+ *
+ * We might be able to generate EPOLLOUT to the application if:
+ * 1) Space consumed in output/rtx queues is below sk->sk_sndbuf/2
+ * 2) notsent amount (tp->write_seq - tp->snd_nxt) became
+ * small enough that tcp_stream_memory_free() decides it
+ * is time to generate EPOLLOUT.
+ */
+void tcp_check_space(struct sock *sk)
{
/* pairs with tcp_poll() */
smp_mb();
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 6366df7aaf2a..6854bb1fb32b 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -531,7 +531,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
newtp->tsoffset = treq->ts_off;
#ifdef CONFIG_TCP_MD5SIG
newtp->md5sig_info = NULL; /*XXX*/
- if (newtp->af_specific->md5_lookup(sk, newsk))
+ if (treq->af_specific->req_md5_lookup(sk, req_to_sk(req)))
newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
#endif
if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9ede847f4199..1ca2f28c9981 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -82,6 +82,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT,
tcp_skb_pcount(skb));
+ tcp_check_space(sk);
}
/* SND.NXT, if window was not shrunk or the amount of shrunk was less than one
diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c
index fbab921670cc..9a8e014d9b5b 100644
--- a/net/ipv4/tcp_rate.c
+++ b/net/ipv4/tcp_rate.c
@@ -74,27 +74,32 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb)
*
* If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is
* called multiple times. We favor the information from the most recently
- * sent skb, i.e., the skb with the highest prior_delivered count.
+ * sent skb, i.e., the skb with the most recently sent time and the highest
+ * sequence.
*/
void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
struct rate_sample *rs)
{
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
+ u64 tx_tstamp;
if (!scb->tx.delivered_mstamp)
return;
+ tx_tstamp = tcp_skb_timestamp_us(skb);
if (!rs->prior_delivered ||
- after(scb->tx.delivered, rs->prior_delivered)) {
+ tcp_skb_sent_after(tx_tstamp, tp->first_tx_mstamp,
+ scb->end_seq, rs->last_end_seq)) {
rs->prior_delivered_ce = scb->tx.delivered_ce;
rs->prior_delivered = scb->tx.delivered;
rs->prior_mstamp = scb->tx.delivered_mstamp;
rs->is_app_limited = scb->tx.is_app_limited;
rs->is_retrans = scb->sacked & TCPCB_RETRANS;
+ rs->last_end_seq = scb->end_seq;
/* Record send time of most recently ACKed packet: */
- tp->first_tx_mstamp = tcp_skb_timestamp_us(skb);
+ tp->first_tx_mstamp = tx_tstamp;
/* Find the duration of the "send phase" of this window: */
rs->interval_us = tcp_stamp_us_delta(tp->first_tx_mstamp,
scb->tx.first_tx_mstamp);
generated by cgit (git 2.34.1) at 2024-05-24 00:15:47 +0000