#include <linux/fs.h>
#include <linux/random.h>
#include <linux/bootmem.h>
+#include <linux/cache.h>
#include <net/icmp.h>
#include <net/tcp.h>
EXPORT_SYMBOL_GPL(tcp_orphan_count);
-int sysctl_tcp_mem[3];
-int sysctl_tcp_wmem[3] = { 4 * 1024, 16 * 1024, 128 * 1024 };
-int sysctl_tcp_rmem[3] = { 4 * 1024, 87380, 87380 * 2 };
+int sysctl_tcp_mem[3] __read_mostly;
+int sysctl_tcp_wmem[3] __read_mostly;
+int sysctl_tcp_rmem[3] __read_mostly;
EXPORT_SYMBOL(sysctl_tcp_mem);
EXPORT_SYMBOL(sysctl_tcp_rmem);
if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE)
mask |= POLLHUP;
if (sk->sk_shutdown & RCV_SHUTDOWN)
- mask |= POLLIN | POLLRDNORM;
+ mask |= POLLIN | POLLRDNORM | POLLRDHUP;
/* Connected? */
if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV)) {
* calculation of whether or not we must ACK for the sake of
* a window update.
*/
-static void cleanup_rbuf(struct sock *sk, int copied)
+void tcp_cleanup_rbuf(struct sock *sk, int copied)
{
struct tcp_sock *tp = tcp_sk(sk);
int time_to_ack = 0;
break;
}
if (skb->h.th->fin) {
- sk_eat_skb(sk, skb);
+ sk_eat_skb(sk, skb, 0);
++seq;
break;
}
- sk_eat_skb(sk, skb);
+ sk_eat_skb(sk, skb, 0);
if (!desc->count)
break;
}
/* Clean up data we have read: This will do ACK frames. */
if (copied)
- cleanup_rbuf(sk, copied);
+ tcp_cleanup_rbuf(sk, copied);
return copied;
}
}
}
- cleanup_rbuf(sk, copied);
+ tcp_cleanup_rbuf(sk, copied);
if (!sysctl_tcp_low_latency && tp->ucopy.task == user_recv) {
/* Install new reader */
if (skb->h.th->fin)
goto found_fin_ok;
if (!(flags & MSG_PEEK))
- sk_eat_skb(sk, skb);
+ sk_eat_skb(sk, skb, 0);
continue;
found_fin_ok:
/* Process the FIN. */
++*seq;
if (!(flags & MSG_PEEK))
- sk_eat_skb(sk, skb);
+ sk_eat_skb(sk, skb, 0);
break;
} while (len > 0);
*/
/* Clean up data we have read: This will do ACK frames. */
- cleanup_rbuf(sk, copied);
+ tcp_cleanup_rbuf(sk, copied);
TCP_CHECK_TIMER(sk);
release_sock(sk);
{
struct sk_buff *skb;
int data_was_unread = 0;
+ int state;
lock_sock(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
sk_stream_wait_close(sk, timeout);
adjudge_to_death:
+ state = sk->sk_state;
+ sock_hold(sk);
+ sock_orphan(sk);
+ atomic_inc(sk->sk_prot->orphan_count);
+
/* It is the last release_sock in its life. It will remove backlog. */
release_sock(sk);
bh_lock_sock(sk);
BUG_TRAP(!sock_owned_by_user(sk));
- sock_hold(sk);
- sock_orphan(sk);
+ /* Have we already been destroyed by a softirq or backlog? */
+ if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE)
+ goto out;
/* This is a (useful) BSD violating of the RFC. There is a
* problem with TCP as specified in that the other end could
if (tmo > TCP_TIMEWAIT_LEN) {
inet_csk_reset_keepalive_timer(sk, tcp_fin_time(sk));
} else {
- atomic_inc(sk->sk_prot->orphan_count);
tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
goto out;
}
NET_INC_STATS_BH(LINUX_MIB_TCPABORTONMEMORY);
}
}
- atomic_inc(sk->sk_prot->orphan_count);
if (sk->sk_state == TCP_CLOSE)
inet_csk_destroy_sock(sk);
/*
* Socket option code for TCP.
*/
-int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
- int optlen)
+static int do_tcp_setsockopt(struct sock *sk, int level,
+ int optname, char __user *optval, int optlen)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
int val;
int err = 0;
- if (level != SOL_TCP)
- return icsk->icsk_af_ops->setsockopt(sk, level, optname,
- optval, optlen);
-
/* This is a string value all the others are int's */
if (optname == TCP_CONGESTION) {
char name[TCP_CA_NAME_MAX];
(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) &&
inet_csk_ack_scheduled(sk)) {
icsk->icsk_ack.pending |= ICSK_ACK_PUSHED;
- cleanup_rbuf(sk, 1);
+ tcp_cleanup_rbuf(sk, 1);
if (!(val & 1))
icsk->icsk_ack.pingpong = 1;
}
return err;
}
+int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
+ int optlen)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ if (level != SOL_TCP)
+ return icsk->icsk_af_ops->setsockopt(sk, level, optname,
+ optval, optlen);
+ return do_tcp_setsockopt(sk, level, optname, optval, optlen);
+}
+
+#ifdef CONFIG_COMPAT
+int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int optlen)
+{
+ if (level != SOL_TCP)
+ return inet_csk_compat_setsockopt(sk, level, optname,
+ optval, optlen);
+ return do_tcp_setsockopt(sk, level, optname, optval, optlen);
+}
+
+EXPORT_SYMBOL(compat_tcp_setsockopt);
+#endif
+
/* Return information about state of tcp endpoint in API format. */
void tcp_get_info(struct sock *sk, struct tcp_info *info)
{
EXPORT_SYMBOL_GPL(tcp_get_info);
-int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
- int __user *optlen)
+static int do_tcp_getsockopt(struct sock *sk, int level,
+ int optname, char __user *optval, int __user *optlen)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
int val, len;
- if (level != SOL_TCP)
- return icsk->icsk_af_ops->getsockopt(sk, level, optname,
- optval, optlen);
-
if (get_user(len, optlen))
return -EFAULT;
return 0;
}
+int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
+ int __user *optlen)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ if (level != SOL_TCP)
+ return icsk->icsk_af_ops->getsockopt(sk, level, optname,
+ optval, optlen);
+ return do_tcp_getsockopt(sk, level, optname, optval, optlen);
+}
+
+#ifdef CONFIG_COMPAT
+int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int __user *optlen)
+{
+ if (level != SOL_TCP)
+ return inet_csk_compat_getsockopt(sk, level, optname,
+ optval, optlen);
+ return do_tcp_getsockopt(sk, level, optname, optval, optlen);
+}
+
+EXPORT_SYMBOL(compat_tcp_getsockopt);
+#endif
extern void __skb_cb_too_small_for_tcp(int, int);
extern struct tcp_congestion_ops tcp_reno;
void __init tcp_init(void)
{
struct sk_buff *skb = NULL;
- int order, i;
+ unsigned long limit;
+ int order, i, max_share;
if (sizeof(struct tcp_skb_cb) > sizeof(skb->cb))
__skb_cb_too_small_for_tcp(sizeof(struct tcp_skb_cb),
sysctl_tcp_mem[1] = 1024 << order;
sysctl_tcp_mem[2] = 1536 << order;
- if (order < 3) {
- sysctl_tcp_wmem[2] = 64 * 1024;
- sysctl_tcp_rmem[0] = PAGE_SIZE;
- sysctl_tcp_rmem[1] = 43689;
- sysctl_tcp_rmem[2] = 2 * 43689;
- }
+ limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7);
+ max_share = min(4UL*1024*1024, limit);
+
+ sysctl_tcp_wmem[0] = SK_STREAM_MEM_QUANTUM;
+ sysctl_tcp_wmem[1] = 16*1024;
+ sysctl_tcp_wmem[2] = max(64*1024, max_share);
+
+ sysctl_tcp_rmem[0] = SK_STREAM_MEM_QUANTUM;
+ sysctl_tcp_rmem[1] = 87380;
+ sysctl_tcp_rmem[2] = max(87380, max_share);
printk(KERN_INFO "TCP: Hash tables configured "
"(established %d bind %d)\n",
projects / deliverable / linux.git / blobdiff