summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp.c')
-rw-r--r--net/ipv4/tcp.c125
1 files changed, 69 insertions, 56 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8a18aeca7ab0..f035440c475a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -243,7 +243,7 @@
#define pr_fmt(fmt) "TCP: " fmt
-#include <crypto/hash.h>
+#include <crypto/md5.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
@@ -253,7 +253,6 @@
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/skbuff.h>
-#include <linux/scatterlist.h>
#include <linux/splice.h>
#include <linux/net.h>
#include <linux/socket.h>
@@ -425,7 +424,6 @@ void tcp_md5_destruct_sock(struct sock *sk)
tcp_clear_md5_list(sk);
kfree(rcu_replace_pointer(tp->md5sig_info, NULL, 1));
static_branch_slow_dec_deferred(&tcp_md5_needed);
- tcp_md5_release_sigpool();
}
}
EXPORT_IPV6_MOD_GPL(tcp_md5_destruct_sock);
@@ -928,7 +926,8 @@ struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp,
}
__kfree_skb(skb);
} else {
- sk->sk_prot->enter_memory_pressure(sk);
+ if (!sk->sk_bypass_prot_mem)
+ tcp_enter_memory_pressure(sk);
sk_stream_moderate_sndbuf(sk);
}
return NULL;
@@ -1062,7 +1061,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied,
}
}
flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
- err = __inet_stream_connect(sk->sk_socket, uaddr,
+ err = __inet_stream_connect(sk->sk_socket, (struct sockaddr_unsized *)uaddr,
msg->msg_namelen, flags, 1);
/* fastopen_req could already be freed in __inet_stream_connect
* if the connection times out or gets rst
@@ -1557,8 +1556,10 @@ void __tcp_cleanup_rbuf(struct sock *sk, int copied)
time_to_ack = true;
}
}
- if (time_to_ack)
+ if (time_to_ack) {
+ tcp_mstamp_refresh(tp);
tcp_send_ack(sk);
+ }
}
void tcp_cleanup_rbuf(struct sock *sk, int copied)
@@ -2586,7 +2587,7 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb,
if (err)
goto out;
- atomic_long_inc(&niov->pp_ref_count);
+ atomic_long_inc(&niov->desc.pp_ref_count);
tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag);
sent += copy;
@@ -3583,9 +3584,12 @@ static int tcp_repair_options_est(struct sock *sk, sockptr_t optbuf,
DEFINE_STATIC_KEY_FALSE(tcp_tx_delay_enabled);
EXPORT_IPV6_MOD(tcp_tx_delay_enabled);
-static void tcp_enable_tx_delay(void)
+static void tcp_enable_tx_delay(struct sock *sk, int val)
{
- if (!static_branch_unlikely(&tcp_tx_delay_enabled)) {
+ struct tcp_sock *tp = tcp_sk(sk);
+ s32 delta = (val - tp->tcp_tx_delay) << 3;
+
+ if (val && !static_branch_unlikely(&tcp_tx_delay_enabled)) {
static int __tcp_tx_delay_enabled = 0;
if (cmpxchg(&__tcp_tx_delay_enabled, 0, 1) == 0) {
@@ -3593,6 +3597,22 @@ static void tcp_enable_tx_delay(void)
pr_info("TCP_TX_DELAY enabled\n");
}
}
+ /* If we change tcp_tx_delay on a live flow, adjust tp->srtt_us,
+ * tp->rtt_min, icsk_rto and sk->sk_pacing_rate.
+ * This is best effort.
+ */
+ if (delta && sk->sk_state == TCP_ESTABLISHED) {
+ s64 srtt = (s64)tp->srtt_us + delta;
+
+ tp->srtt_us = clamp_t(s64, srtt, 1, ~0U);
+
+ /* Note: does not deal with non zero icsk_backoff */
+ tcp_set_rto(sk);
+
+ minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U);
+
+ tcp_update_pacing_rate(sk);
+ }
}
/* When set indicates to always queue non-full frames. Later the user clears
@@ -4119,8 +4139,12 @@ ao_parse:
tp->recvmsg_inq = val;
break;
case TCP_TX_DELAY:
- if (val)
- tcp_enable_tx_delay();
+ /* tp->srtt_us is u32, and is shifted by 3 */
+ if (val < 0 || val >= (1U << (31 - 3))) {
+ err = -EINVAL;
+ break;
+ }
+ tcp_enable_tx_delay(sk, val);
WRITE_ONCE(tp->tcp_tx_delay, val);
break;
default:
@@ -4815,52 +4839,45 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
EXPORT_IPV6_MOD(tcp_getsockopt);
#ifdef CONFIG_TCP_MD5SIG
-int tcp_md5_sigpool_id = -1;
-EXPORT_IPV6_MOD_GPL(tcp_md5_sigpool_id);
-
-int tcp_md5_alloc_sigpool(void)
+void tcp_md5_hash_skb_data(struct md5_ctx *ctx, const struct sk_buff *skb,
+ unsigned int header_len)
{
- size_t scratch_size;
- int ret;
+ const unsigned int head_data_len = skb_headlen(skb) > header_len ?
+ skb_headlen(skb) - header_len : 0;
+ const struct skb_shared_info *shi = skb_shinfo(skb);
+ struct sk_buff *frag_iter;
+ unsigned int i;
- scratch_size = sizeof(union tcp_md5sum_block) + sizeof(struct tcphdr);
- ret = tcp_sigpool_alloc_ahash("md5", scratch_size);
- if (ret >= 0) {
- /* As long as any md5 sigpool was allocated, the return
- * id would stay the same. Re-write the id only for the case
- * when previously all MD5 keys were deleted and this call
- * allocates the first MD5 key, which may return a different
- * sigpool id than was used previously.
- */
- WRITE_ONCE(tcp_md5_sigpool_id, ret); /* Avoids the compiler potentially being smart here */
- return 0;
- }
- return ret;
-}
+ md5_update(ctx, (const u8 *)tcp_hdr(skb) + header_len, head_data_len);
-void tcp_md5_release_sigpool(void)
-{
- tcp_sigpool_release(READ_ONCE(tcp_md5_sigpool_id));
-}
+ for (i = 0; i < shi->nr_frags; ++i) {
+ const skb_frag_t *f = &shi->frags[i];
+ u32 p_off, p_len, copied;
+ const void *vaddr;
+ struct page *p;
-void tcp_md5_add_sigpool(void)
-{
- tcp_sigpool_get(READ_ONCE(tcp_md5_sigpool_id));
+ skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f),
+ p, p_off, p_len, copied) {
+ vaddr = kmap_local_page(p);
+ md5_update(ctx, vaddr + p_off, p_len);
+ kunmap_local(vaddr);
+ }
+ }
+
+ skb_walk_frags(skb, frag_iter)
+ tcp_md5_hash_skb_data(ctx, frag_iter, 0);
}
+EXPORT_IPV6_MOD(tcp_md5_hash_skb_data);
-int tcp_md5_hash_key(struct tcp_sigpool *hp,
- const struct tcp_md5sig_key *key)
+void tcp_md5_hash_key(struct md5_ctx *ctx,
+ const struct tcp_md5sig_key *key)
{
u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */
- struct scatterlist sg;
-
- sg_init_one(&sg, key->key, keylen);
- ahash_request_set_crypt(hp->req, &sg, NULL, keylen);
/* We use data_race() because tcp_md5_do_add() might change
* key->key under us
*/
- return data_race(crypto_ahash_update(hp->req));
+ data_race(({ md5_update(ctx, key->key, keylen), 0; }));
}
EXPORT_IPV6_MOD(tcp_md5_hash_key);
@@ -4871,19 +4888,16 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
int family, int l3index, const __u8 *hash_location)
{
/* This gets called for each TCP segment that has TCP-MD5 option.
- * We have 3 drop cases:
- * o No MD5 hash and one expected.
- * o MD5 hash and we're not expecting one.
- * o MD5 hash and its wrong.
+ * We have 2 drop cases:
+ * o An MD5 signature is present, but we're not expecting one.
+ * o The MD5 signature is wrong.
*/
const struct tcp_sock *tp = tcp_sk(sk);
struct tcp_md5sig_key *key;
u8 newhash[16];
- int genhash;
key = tcp_md5_do_lookup(sk, l3index, saddr, family);
-
- if (!key && hash_location) {
+ if (!key) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
trace_tcp_hash_md5_unexpected(sk, skb);
return SKB_DROP_REASON_TCP_MD5UNEXPECTED;
@@ -4894,11 +4908,10 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
* IPv4-mapped case.
*/
if (family == AF_INET)
- genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb);
+ tcp_v4_md5_hash_skb(newhash, key, NULL, skb);
else
- genhash = tp->af_specific->calc_md5_hash(newhash, key,
- NULL, skb);
- if (genhash || memcmp(hash_location, newhash, 16) != 0) {
+ tp->af_specific->calc_md5_hash(newhash, key, NULL, skb);
+ if (memcmp(hash_location, newhash, 16) != 0) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
trace_tcp_hash_md5_mismatch(sk, skb);
return SKB_DROP_REASON_TCP_MD5FAILURE;
generated by cgit v1.2.3 (git 2.46.0) at 2025-12-04 11:10:41 +0000