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.c153
1 files changed, 79 insertions, 74 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6596b4feeddc..6c11eece262c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -282,7 +282,7 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);
-int sysctl_tcp_mem[3] __read_mostly;
+long sysctl_tcp_mem[3] __read_mostly;
int sysctl_tcp_wmem[3] __read_mostly;
int sysctl_tcp_rmem[3] __read_mostly;
@@ -290,7 +290,7 @@ EXPORT_SYMBOL(sysctl_tcp_mem);
EXPORT_SYMBOL(sysctl_tcp_rmem);
EXPORT_SYMBOL(sysctl_tcp_wmem);
-atomic_t tcp_memory_allocated; /* Current allocated memory. */
+atomic_long_t tcp_memory_allocated; /* Current allocated memory. */
EXPORT_SYMBOL(tcp_memory_allocated);
/*
@@ -315,7 +315,6 @@ struct tcp_splice_state {
* is strict, actions are advisory and have some latency.
*/
int tcp_memory_pressure __read_mostly;
-
EXPORT_SYMBOL(tcp_memory_pressure);
void tcp_enter_memory_pressure(struct sock *sk)
@@ -325,7 +324,6 @@ void tcp_enter_memory_pressure(struct sock *sk)
tcp_memory_pressure = 1;
}
}
-
EXPORT_SYMBOL(tcp_enter_memory_pressure);
/* Convert seconds to retransmits based on initial and max timeout */
@@ -388,8 +386,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
*/
mask = 0;
- if (sk->sk_err)
- mask = POLLERR;
/*
* POLLHUP is certainly not done right. But poll() doesn't
@@ -453,13 +449,20 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
mask |= POLLOUT | POLLWRNORM;
}
- }
+ } else
+ mask |= POLLOUT | POLLWRNORM;
if (tp->urg_data & TCP_URG_VALID)
mask |= POLLPRI;
}
+ /* This barrier is coupled with smp_wmb() in tcp_reset() */
+ smp_rmb();
+ if (sk->sk_err)
+ mask |= POLLERR;
+
return mask;
}
+EXPORT_SYMBOL(tcp_poll);
int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
@@ -508,10 +511,11 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
return put_user(answ, (int __user *)arg);
}
+EXPORT_SYMBOL(tcp_ioctl);
static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb)
{
- TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH;
+ TCP_SKB_CB(skb)->flags |= TCPHDR_PSH;
tp->pushed_seq = tp->write_seq;
}
@@ -527,7 +531,7 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
skb->csum = 0;
tcb->seq = tcb->end_seq = tp->write_seq;
- tcb->flags = TCPCB_FLAG_ACK;
+ tcb->flags = TCPHDR_ACK;
tcb->sacked = 0;
skb_header_release(skb);
tcp_add_write_queue_tail(sk, skb);
@@ -608,6 +612,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
ssize_t spliced;
int ret;
+ sock_rps_record_flow(sk);
/*
* We can't seek on a socket input
*/
@@ -675,6 +680,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
return ret;
}
+EXPORT_SYMBOL(tcp_splice_read);
struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
{
@@ -815,7 +821,7 @@ new_segment:
skb_shinfo(skb)->gso_segs = 0;
if (!copied)
- TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_PSH;
+ TCP_SKB_CB(skb)->flags &= ~TCPHDR_PSH;
copied += copy;
poffset += copy;
@@ -856,15 +862,15 @@ out_err:
return sk_stream_error(sk, flags, err);
}
-ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset,
- size_t size, int flags)
+int tcp_sendpage(struct sock *sk, struct page *page, int offset,
+ size_t size, int flags)
{
ssize_t res;
- struct sock *sk = sock->sk;
if (!(sk->sk_route_caps & NETIF_F_SG) ||
!(sk->sk_route_caps & NETIF_F_ALL_CSUM))
- return sock_no_sendpage(sock, page, offset, size, flags);
+ return sock_no_sendpage(sk->sk_socket, page, offset, size,
+ flags);
lock_sock(sk);
TCP_CHECK_TIMER(sk);
@@ -873,6 +879,7 @@ ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset,
release_sock(sk);
return res;
}
+EXPORT_SYMBOL(tcp_sendpage);
#define TCP_PAGE(sk) (sk->sk_sndmsg_page)
#define TCP_OFF(sk) (sk->sk_sndmsg_off)
@@ -897,10 +904,9 @@ static inline int select_size(struct sock *sk, int sg)
return tmp;
}
-int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
+int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t size)
{
- struct sock *sk = sock->sk;
struct iovec *iov;
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
@@ -937,7 +943,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
sg = sk->sk_route_caps & NETIF_F_SG;
while (--iovlen >= 0) {
- int seglen = iov->iov_len;
+ size_t seglen = iov->iov_len;
unsigned char __user *from = iov->iov_base;
iov++;
@@ -1061,7 +1067,7 @@ new_segment:
}
if (!copied)
- TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_PSH;
+ TCP_SKB_CB(skb)->flags &= ~TCPHDR_PSH;
tp->write_seq += copy;
TCP_SKB_CB(skb)->end_seq += copy;
@@ -1121,6 +1127,7 @@ out_err:
release_sock(sk);
return err;
}
+EXPORT_SYMBOL(tcp_sendmsg);
/*
* Handle reading urgent data. BSD has very simple semantics for
@@ -1186,7 +1193,7 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
- KERN_INFO "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
+ "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt);
#endif
@@ -1380,6 +1387,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
tcp_cleanup_rbuf(sk, copied);
return copied;
}
+EXPORT_SYMBOL(tcp_read_sock);
/*
* This routine copies from a sock struct into the user buffer.
@@ -1469,10 +1477,9 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
* shouldn't happen.
*/
if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
- KERN_INFO "recvmsg bug: copied %X "
- "seq %X rcvnxt %X fl %X\n", *seq,
- TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
- flags))
+ "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n",
+ *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
+ flags))
break;
offset = *seq - TCP_SKB_CB(skb)->seq;
@@ -1482,10 +1489,9 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
goto found_ok_skb;
if (tcp_hdr(skb)->fin)
goto found_fin_ok;
- WARN(!(flags & MSG_PEEK), KERN_INFO "recvmsg bug 2: "
- "copied %X seq %X rcvnxt %X fl %X\n",
- *seq, TCP_SKB_CB(skb)->seq,
- tp->rcv_nxt, flags);
+ WARN(!(flags & MSG_PEEK),
+ "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n",
+ *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags);
}
/* Well, if we have backlog, try to process it now yet. */
@@ -1774,6 +1780,7 @@ recv_urg:
err = tcp_recv_urg(sk, msg, len, flags);
goto out;
}
+EXPORT_SYMBOL(tcp_recvmsg);
void tcp_set_state(struct sock *sk, int state)
{
@@ -1866,6 +1873,7 @@ void tcp_shutdown(struct sock *sk, int how)
tcp_send_fin(sk);
}
}
+EXPORT_SYMBOL(tcp_shutdown);
void tcp_close(struct sock *sk, long timeout)
{
@@ -1898,6 +1906,10 @@ void tcp_close(struct sock *sk, long timeout)
sk_mem_reclaim(sk);
+ /* If socket has been already reset (e.g. in tcp_reset()) - kill it. */
+ if (sk->sk_state == TCP_CLOSE)
+ goto adjudge_to_death;
+
/* As outlined in RFC 2525, section 2.17, we send a RST here because
* data was lost. To witness the awful effects of the old behavior of
* always doing a FIN, run an older 2.1.x kernel or 2.0.x, start a bulk
@@ -2001,11 +2013,8 @@ adjudge_to_death:
}
}
if (sk->sk_state != TCP_CLOSE) {
- int orphan_count = percpu_counter_read_positive(
- sk->sk_prot->orphan_count);
-
sk_mem_reclaim(sk);
- if (tcp_too_many_orphans(sk, orphan_count)) {
+ if (tcp_too_many_orphans(sk, 0)) {
if (net_ratelimit())
printk(KERN_INFO "TCP: too many of orphaned "
"sockets\n");
@@ -2025,6 +2034,7 @@ out:
local_bh_enable();
sock_put(sk);
}
+EXPORT_SYMBOL(tcp_close);
/* These states need RST on ABORT according to RFC793 */
@@ -2098,6 +2108,7 @@ int tcp_disconnect(struct sock *sk, int flags)
sk->sk_error_report(sk);
return err;
}
+EXPORT_SYMBOL(tcp_disconnect);
/*
* Socket option code for TCP.
@@ -2175,6 +2186,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
GFP_KERNEL);
if (cvp == NULL)
return -ENOMEM;
+
+ kref_init(&cvp->kref);
}
lock_sock(sk);
tp->rx_opt.cookie_in_always =
@@ -2189,12 +2202,11 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
*/
kref_put(&tp->cookie_values->kref,
tcp_cookie_values_release);
- kref_init(&cvp->kref);
- tp->cookie_values = cvp;
} else {
cvp = tp->cookie_values;
}
}
+
if (cvp != NULL) {
cvp->cookie_desired = ctd.tcpct_cookie_desired;
@@ -2208,6 +2220,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
cvp->s_data_desired = ctd.tcpct_s_data_desired;
cvp->s_data_constant = 0; /* false */
}
+
+ tp->cookie_values = cvp;
}
release_sock(sk);
return err;
@@ -2230,7 +2244,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
/* Values greater than interface MTU won't take effect. However
* at the point when this call is done we typically don't yet
* know which interface is going to be used */
- if (val < 8 || val > MAX_TCP_WINDOW) {
+ if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) {
err = -EINVAL;
break;
}
@@ -2376,7 +2390,12 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
err = tp->af_specific->md5_parse(sk, optval, optlen);
break;
#endif
-
+ case TCP_USER_TIMEOUT:
+ /* Cap the max timeout in ms TCP will retry/retrans
+ * before giving up and aborting (ETIMEDOUT) a connection.
+ */
+ icsk->icsk_user_timeout = msecs_to_jiffies(val);
+ break;
default:
err = -ENOPROTOOPT;
break;
@@ -2396,6 +2415,7 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
optval, optlen);
return do_tcp_setsockopt(sk, level, optname, optval, optlen);
}
+EXPORT_SYMBOL(tcp_setsockopt);
#ifdef CONFIG_COMPAT
int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
@@ -2406,7 +2426,6 @@ int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
optval, optlen);
return do_tcp_setsockopt(sk, level, optname, optval, optlen);
}
-
EXPORT_SYMBOL(compat_tcp_setsockopt);
#endif
@@ -2472,7 +2491,6 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_total_retrans = tp->total_retrans;
}
-
EXPORT_SYMBOL_GPL(tcp_get_info);
static int do_tcp_getsockopt(struct sock *sk, int level,
@@ -2590,6 +2608,16 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
return -EFAULT;
return 0;
}
+ case TCP_THIN_LINEAR_TIMEOUTS:
+ val = tp->thin_lto;
+ break;
+ case TCP_THIN_DUPACK:
+ val = tp->thin_dupack;
+ break;
+
+ case TCP_USER_TIMEOUT:
+ val = jiffies_to_msecs(icsk->icsk_user_timeout);
+ break;
default:
return -ENOPROTOOPT;
}
@@ -2611,6 +2639,7 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
optval, optlen);
return do_tcp_getsockopt(sk, level, optname, optval, optlen);
}
+EXPORT_SYMBOL(tcp_getsockopt);
#ifdef CONFIG_COMPAT
int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
@@ -2621,7 +2650,6 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
optval, optlen);
return do_tcp_getsockopt(sk, level, optname, optval, optlen);
}
-
EXPORT_SYMBOL(compat_tcp_getsockopt);
#endif
@@ -2858,7 +2886,6 @@ void tcp_free_md5sig_pool(void)
if (pool)
__tcp_free_md5sig_pool(pool);
}
-
EXPORT_SYMBOL(tcp_free_md5sig_pool);
static struct tcp_md5sig_pool * __percpu *
@@ -2934,7 +2961,6 @@ retry:
}
return pool;
}
-
EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
@@ -2958,7 +2984,7 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
spin_unlock(&tcp_md5sig_pool_lock);
if (p)
- return *per_cpu_ptr(p, smp_processor_id());
+ return *this_cpu_ptr(p);
local_bh_enable();
return NULL;
@@ -2986,7 +3012,6 @@ int tcp_md5_hash_header(struct tcp_md5sig_pool *hp,
th->check = old_checksum;
return err;
}
-
EXPORT_SYMBOL(tcp_md5_hash_header);
int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
@@ -2999,6 +3024,7 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
const unsigned 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;
sg_init_table(&sg, 1);
@@ -3013,9 +3039,12 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
return 1;
}
+ skb_walk_frags(skb, frag_iter)
+ if (tcp_md5_hash_skb_data(hp, frag_iter, 0))
+ return 1;
+
return 0;
}
-
EXPORT_SYMBOL(tcp_md5_hash_skb_data);
int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, struct tcp_md5sig_key *key)
@@ -3025,7 +3054,6 @@ int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, struct tcp_md5sig_key *key)
sg_init_one(&sg, key->key, key->keylen);
return crypto_hash_update(&hp->md5_desc, &sg, key->keylen);
}
-
EXPORT_SYMBOL(tcp_md5_hash_key);
#endif
@@ -3192,7 +3220,7 @@ void __init tcp_init(void)
{
struct sk_buff *skb = NULL;
unsigned long nr_pages, limit;
- int order, i, max_share;
+ int i, max_share, cnt;
unsigned long jiffy = jiffies;
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
@@ -3241,22 +3269,12 @@ void __init tcp_init(void)
INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain);
}
- /* Try to be a bit smarter and adjust defaults depending
- * on available memory.
- */
- for (order = 0; ((1 << order) << PAGE_SHIFT) <
- (tcp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket));
- order++)
- ;
- if (order >= 4) {
- tcp_death_row.sysctl_max_tw_buckets = 180000;
- sysctl_tcp_max_orphans = 4096 << (order - 4);
- sysctl_max_syn_backlog = 1024;
- } else if (order < 3) {
- tcp_death_row.sysctl_max_tw_buckets >>= (3 - order);
- sysctl_tcp_max_orphans >>= (3 - order);
- sysctl_max_syn_backlog = 128;
- }
+
+ cnt = tcp_hashinfo.ehash_mask + 1;
+
+ tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
+ sysctl_tcp_max_orphans = cnt / 2;
+ sysctl_max_syn_backlog = max(128, cnt / 256);
/* Set the pressure threshold to be a fraction of global memory that
* is up to 1/2 at 256 MB, decreasing toward zero with the amount of
@@ -3297,16 +3315,3 @@ void __init tcp_init(void)
tcp_secret_retiring = &tcp_secret_two;
tcp_secret_secondary = &tcp_secret_two;
}
-
-EXPORT_SYMBOL(tcp_close);
-EXPORT_SYMBOL(tcp_disconnect);
-EXPORT_SYMBOL(tcp_getsockopt);
-EXPORT_SYMBOL(tcp_ioctl);
-EXPORT_SYMBOL(tcp_poll);
-EXPORT_SYMBOL(tcp_read_sock);
-EXPORT_SYMBOL(tcp_recvmsg);
-EXPORT_SYMBOL(tcp_sendmsg);
-EXPORT_SYMBOL(tcp_splice_read);
-EXPORT_SYMBOL(tcp_sendpage);
-EXPORT_SYMBOL(tcp_setsockopt);
-EXPORT_SYMBOL(tcp_shutdown);
generated by cgit v1.2.3 (git 2.39.0) at 2025-12-17 19:33:43 +0300