summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_ipv4.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp_ipv4.c')
-rw-r--r--net/ipv4/tcp_ipv4.c102
1 files changed, 71 insertions, 31 deletions
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3708de2a6683..2259114c7242 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -86,7 +86,6 @@
int sysctl_tcp_tw_reuse __read_mostly;
int sysctl_tcp_low_latency __read_mostly;
-EXPORT_SYMBOL(sysctl_tcp_low_latency);
#ifdef CONFIG_TCP_MD5SIG
static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
@@ -814,8 +813,14 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
tcp_sk(sk)->snd_nxt;
+ /* RFC 7323 2.3
+ * The window field (SEG.WND) of every outgoing segment, with the
+ * exception of <SYN> segments, MUST be right-shifted by
+ * Rcv.Wind.Shift bits:
+ */
tcp_v4_send_ack(sock_net(sk), skb, seq,
- tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
+ tcp_rsk(req)->rcv_nxt,
+ req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp,
req->ts_recent,
0,
@@ -1018,27 +1023,28 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
GFP_KERNEL);
}
-static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
- __be32 daddr, __be32 saddr, int nbytes)
+static int tcp_v4_md5_hash_headers(struct tcp_md5sig_pool *hp,
+ __be32 daddr, __be32 saddr,
+ const struct tcphdr *th, int nbytes)
{
struct tcp4_pseudohdr *bp;
struct scatterlist sg;
+ struct tcphdr *_th;
- bp = &hp->md5_blk.ip4;
-
- /*
- * 1. the TCP pseudo-header (in the order: source IP address,
- * destination IP address, zero-padded protocol number, and
- * segment length)
- */
+ bp = hp->scratch;
bp->saddr = saddr;
bp->daddr = daddr;
bp->pad = 0;
bp->protocol = IPPROTO_TCP;
bp->len = cpu_to_be16(nbytes);
- sg_init_one(&sg, bp, sizeof(*bp));
- ahash_request_set_crypt(hp->md5_req, &sg, NULL, sizeof(*bp));
+ _th = (struct tcphdr *)(bp + 1);
+ memcpy(_th, th, sizeof(*th));
+ _th->check = 0;
+
+ sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th));
+ ahash_request_set_crypt(hp->md5_req, &sg, NULL,
+ sizeof(*bp) + sizeof(*th));
return crypto_ahash_update(hp->md5_req);
}
@@ -1055,9 +1061,7 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
if (crypto_ahash_init(req))
goto clear_hash;
- if (tcp_v4_md5_hash_pseudoheader(hp, daddr, saddr, th->doff << 2))
- goto clear_hash;
- if (tcp_md5_hash_header(hp, th))
+ if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, th->doff << 2))
goto clear_hash;
if (tcp_md5_hash_key(hp, key))
goto clear_hash;
@@ -1101,9 +1105,7 @@ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
if (crypto_ahash_init(req))
goto clear_hash;
- if (tcp_v4_md5_hash_pseudoheader(hp, daddr, saddr, skb->len))
- goto clear_hash;
- if (tcp_md5_hash_header(hp, th))
+ if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, skb->len))
goto clear_hash;
if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2))
goto clear_hash;
@@ -1172,6 +1174,7 @@ static bool tcp_v4_inbound_md5_hash(const struct sock *sk,
NULL, skb);
if (genhash || memcmp(hash_location, newhash, 16) != 0) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n",
&iph->saddr, ntohs(th->source),
&iph->daddr, ntohs(th->dest),
@@ -1192,7 +1195,6 @@ static void tcp_v4_init_req(struct request_sock *req,
sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
- ireq->no_srccheck = inet_sk(sk_listener)->transparent;
ireq->opt = tcp_v4_save_options(skb);
}
@@ -1534,6 +1536,49 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
}
EXPORT_SYMBOL(tcp_prequeue);
+bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
+{
+ u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf;
+
+ /* 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 += 64*1024;
+
+ /* In case all data was pulled from skb frags (in __pskb_pull_tail()),
+ * we can fix skb->truesize to its real value to avoid future drops.
+ * This is valid because skb is not yet charged to the socket.
+ * It has been noticed pure SACK packets were sometimes dropped
+ * (if cooked by drivers without copybreak feature).
+ */
+ if (!skb->data_len)
+ skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
+
+ if (unlikely(sk_add_backlog(sk, skb, limit))) {
+ bh_unlock_sock(sk);
+ __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP);
+ return true;
+ }
+ return false;
+}
+EXPORT_SYMBOL(tcp_add_backlog);
+
+int tcp_filter(struct sock *sk, struct sk_buff *skb)
+{
+ struct tcphdr *th = (struct tcphdr *)skb->data;
+ unsigned int eaten = skb->len;
+ int err;
+
+ err = sk_filter_trim_cap(sk, skb, th->doff * 4);
+ if (!err) {
+ eaten -= skb->len;
+ TCP_SKB_CB(skb)->end_seq -= eaten;
+ }
+ return err;
+}
+EXPORT_SYMBOL(tcp_filter);
+
/*
* From tcp_input.c
*/
@@ -1605,6 +1650,7 @@ process:
sk = req->rsk_listener;
if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) {
+ sk_drops_add(sk, skb);
reqsk_put(req);
goto discard_it;
}
@@ -1645,8 +1691,10 @@ process:
nf_reset(skb);
- if (sk_filter(sk, skb))
+ if (tcp_filter(sk, skb))
goto discard_and_relse;
+ th = (const struct tcphdr *)skb->data;
+ iph = ip_hdr(skb);
skb->dev = NULL;
@@ -1663,10 +1711,7 @@ process:
if (!sock_owned_by_user(sk)) {
if (!tcp_prequeue(sk, skb))
ret = tcp_v4_do_rcv(sk, skb);
- } else if (unlikely(sk_add_backlog(sk, skb,
- sk->sk_rcvbuf + sk->sk_sndbuf))) {
- bh_unlock_sock(sk);
- __NET_INC_STATS(net, LINUX_MIB_TCPBACKLOGDROP);
+ } else if (tcp_add_backlog(sk, skb)) {
goto discard_and_relse;
}
bh_unlock_sock(sk);
@@ -1815,7 +1860,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
tcp_write_queue_purge(sk);
/* Cleans up our, hopefully empty, out_of_order_queue. */
- __skb_queue_purge(&tp->out_of_order_queue);
+ skb_rbtree_purge(&tp->out_of_order_queue);
#ifdef CONFIG_TCP_MD5SIG
/* Clean up the MD5 key list, if any */
@@ -1842,9 +1887,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
local_bh_disable();
sk_sockets_allocated_dec(sk);
local_bh_enable();
-
- if (mem_cgroup_sockets_enabled && sk->sk_memcg)
- sock_release_memcg(sk);
}
EXPORT_SYMBOL(tcp_v4_destroy_sock);
@@ -1861,7 +1903,6 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
struct tcp_iter_state *st = seq->private;
struct net *net = seq_file_net(seq);
struct inet_listen_hashbucket *ilb;
- struct inet_connection_sock *icsk;
struct sock *sk = cur;
if (!sk) {
@@ -1883,7 +1924,6 @@ get_sk:
continue;
if (sk->sk_family == st->family)
return sk;
- icsk = inet_csk(sk);
}
spin_unlock_bh(&ilb->lock);
st->offset = 0;
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-17 07:00:47 +0000