* All the sk_stream_mem_schedule() is of this nature: accounting
* is strict, actions are advisory and have some latency.
*/
-int tcp_memory_pressure;
+int tcp_memory_pressure __read_mostly;
EXPORT_SYMBOL(tcp_memory_pressure);
/* Subtract 1, if FIN is in queue. */
if (answ && !skb_queue_empty(&sk->sk_receive_queue))
answ -=
- ((struct sk_buff *)sk->sk_receive_queue.prev)->h.th->fin;
+ tcp_hdr((struct sk_buff *)sk->sk_receive_queue.prev)->fin;
} else
answ = tp->urg_seq - tp->copied_seq;
release_sock(sk);
break;
default:
return -ENOIOCTLCMD;
- };
+ }
return put_user(answ, (int __user *)arg);
}
return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1));
}
-static inline void skb_entail(struct sock *sk, struct tcp_sock *tp,
- struct sk_buff *skb)
+static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
{
+ struct tcp_sock *tp = tcp_sk(sk);
struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
skb->csum = 0;
tcb->flags = TCPCB_FLAG_ACK;
tcb->sacked = 0;
skb_header_release(skb);
- __skb_queue_tail(&sk->sk_write_queue, skb);
+ tcp_add_write_queue_tail(sk, skb);
sk_charge_skb(sk, skb);
- if (!sk->sk_send_head)
- sk->sk_send_head = skb;
if (tp->nonagle & TCP_NAGLE_PUSH)
- tp->nonagle &= ~TCP_NAGLE_PUSH;
+ tp->nonagle &= ~TCP_NAGLE_PUSH;
}
static inline void tcp_mark_urg(struct tcp_sock *tp, int flags,
}
}
-static inline void tcp_push(struct sock *sk, struct tcp_sock *tp, int flags,
- int mss_now, int nonagle)
+static inline void tcp_push(struct sock *sk, int flags, int mss_now,
+ int nonagle)
{
- if (sk->sk_send_head) {
- struct sk_buff *skb = sk->sk_write_queue.prev;
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (tcp_send_head(sk)) {
+ struct sk_buff *skb = tcp_write_queue_tail(sk);
if (!(flags & MSG_MORE) || forced_push(tp))
tcp_mark_push(tp, skb);
tcp_mark_urg(tp, flags, skb);
- __tcp_push_pending_frames(sk, tp, mss_now,
+ __tcp_push_pending_frames(sk, mss_now,
(flags & MSG_MORE) ? TCP_NAGLE_CORK : nonagle);
}
}
goto do_error;
while (psize > 0) {
- struct sk_buff *skb = sk->sk_write_queue.prev;
+ struct sk_buff *skb = tcp_write_queue_tail(sk);
struct page *page = pages[poffset / PAGE_SIZE];
int copy, i, can_coalesce;
int offset = poffset % PAGE_SIZE;
int size = min_t(size_t, psize, PAGE_SIZE - offset);
- if (!sk->sk_send_head || (copy = size_goal - skb->len) <= 0) {
+ if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0) {
new_segment:
if (!sk_stream_memory_free(sk))
goto wait_for_sndbuf;
if (!skb)
goto wait_for_memory;
- skb_entail(sk, tp, skb);
+ skb_entail(sk, skb);
copy = size_goal;
}
}
if (!sk_stream_wmem_schedule(sk, copy))
goto wait_for_memory;
-
+
if (can_coalesce) {
skb_shinfo(skb)->frags[i - 1].size += copy;
} else {
if (forced_push(tp)) {
tcp_mark_push(tp, skb);
- __tcp_push_pending_frames(sk, tp, mss_now, TCP_NAGLE_PUSH);
- } else if (skb == sk->sk_send_head)
+ __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
+ } else if (skb == tcp_send_head(sk))
tcp_push_one(sk, mss_now);
continue;
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
if (copied)
- tcp_push(sk, tp, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
+ tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
goto do_error;
out:
if (copied)
- tcp_push(sk, tp, flags, mss_now, tp->nonagle);
+ tcp_push(sk, flags, mss_now, tp->nonagle);
return copied;
do_error:
#define TCP_PAGE(sk) (sk->sk_sndmsg_page)
#define TCP_OFF(sk) (sk->sk_sndmsg_off)
-static inline int select_size(struct sock *sk, struct tcp_sock *tp)
+static inline int select_size(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
int tmp = tp->mss_cache;
if (sk->sk_route_caps & NETIF_F_SG) {
while (seglen > 0) {
int copy;
- skb = sk->sk_write_queue.prev;
+ skb = tcp_write_queue_tail(sk);
- if (!sk->sk_send_head ||
+ if (!tcp_send_head(sk) ||
(copy = size_goal - skb->len) <= 0) {
new_segment:
if (!sk_stream_memory_free(sk))
goto wait_for_sndbuf;
- skb = sk_stream_alloc_pskb(sk, select_size(sk, tp),
+ skb = sk_stream_alloc_pskb(sk, select_size(sk),
0, sk->sk_allocation);
if (!skb)
goto wait_for_memory;
if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
skb->ip_summed = CHECKSUM_PARTIAL;
- skb_entail(sk, tp, skb);
+ skb_entail(sk, skb);
copy = size_goal;
}
if (forced_push(tp)) {
tcp_mark_push(tp, skb);
- __tcp_push_pending_frames(sk, tp, mss_now, TCP_NAGLE_PUSH);
- } else if (skb == sk->sk_send_head)
+ __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
+ } else if (skb == tcp_send_head(sk))
tcp_push_one(sk, mss_now);
continue;
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
if (copied)
- tcp_push(sk, tp, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
+ tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
goto do_error;
out:
if (copied)
- tcp_push(sk, tp, flags, mss_now, tp->nonagle);
+ tcp_push(sk, flags, mss_now, tp->nonagle);
TCP_CHECK_TIMER(sk);
release_sock(sk);
return copied;
do_fault:
if (!skb->len) {
- if (sk->sk_send_head == skb)
- sk->sk_send_head = NULL;
- __skb_unlink(skb, &sk->sk_write_queue);
+ tcp_unlink_write_queue(skb, sk);
+ /* It is the one place in all of TCP, except connection
+ * reset, where we can be unlinking the send_head.
+ */
+ tcp_check_send_head(sk, skb);
sk_stream_free_skb(sk, skb);
}
skb_queue_walk(&sk->sk_receive_queue, skb) {
offset = seq - TCP_SKB_CB(skb)->seq;
- if (skb->h.th->syn)
+ if (tcp_hdr(skb)->syn)
offset--;
- if (offset < skb->len || skb->h.th->fin) {
+ if (offset < skb->len || tcp_hdr(skb)->fin) {
*off = offset;
return skb;
}
if (offset != skb->len)
break;
}
- if (skb->h.th->fin) {
+ if (tcp_hdr(skb)->fin) {
sk_eat_skb(sk, skb, 0);
++seq;
break;
break;
}
offset = *seq - TCP_SKB_CB(skb)->seq;
- if (skb->h.th->syn)
+ if (tcp_hdr(skb)->syn)
offset--;
if (offset < skb->len)
goto found_ok_skb;
- if (skb->h.th->fin)
+ if (tcp_hdr(skb)->fin)
goto found_fin_ok;
BUG_TRAP(flags & MSG_PEEK);
skb = skb->next;
skip_copy:
if (tp->urg_data && after(tp->copied_seq, tp->urg_seq)) {
tp->urg_data = 0;
- tcp_fast_path_check(sk, tp);
+ tcp_fast_path_check(sk);
}
if (used + offset < skb->len)
continue;
- if (skb->h.th->fin)
+ if (tcp_hdr(skb)->fin)
goto found_fin_ok;
if (!(flags & MSG_PEEK)) {
sk_eat_skb(sk, skb, copied_early);
dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
while (dma_async_memcpy_complete(tp->ucopy.dma_chan,
- tp->ucopy.dma_cookie, &done,
- &used) == DMA_IN_PROGRESS) {
+ tp->ucopy.dma_cookie, &done,
+ &used) == DMA_IN_PROGRESS) {
/* do partial cleanup of sk_async_wait_queue */
while ((skb = skb_peek(&sk->sk_async_wait_queue)) &&
(dma_async_is_complete(skb->dma_cookie, done,
- used) == DMA_SUCCESS)) {
+ used) == DMA_SUCCESS)) {
__skb_dequeue(&sk->sk_async_wait_queue);
kfree_skb(skb);
}
*/
while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq -
- skb->h.th->fin;
+ tcp_hdr(skb)->fin;
data_was_unread += len;
__kfree_skb(skb);
}
tcp_clear_xmit_timers(sk);
__skb_queue_purge(&sk->sk_receive_queue);
- sk_stream_writequeue_purge(sk);
+ tcp_write_queue_purge(sk);
__skb_queue_purge(&tp->out_of_order_queue);
#ifdef CONFIG_NET_DMA
__skb_queue_purge(&sk->sk_async_wait_queue);
tcp_set_ca_state(sk, TCP_CA_Open);
tcp_clear_retrans(tp);
inet_csk_delack_init(sk);
- sk->sk_send_head = NULL;
+ tcp_init_send_head(sk);
tp->rx_opt.saw_tstamp = 0;
tcp_sack_reset(&tp->rx_opt);
__sk_dst_reset(sk);
* for currently queued segments.
*/
tp->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH;
- tcp_push_pending_frames(sk, tp);
+ tcp_push_pending_frames(sk);
} else {
tp->nonagle &= ~TCP_NAGLE_OFF;
}
tp->nonagle &= ~TCP_NAGLE_CORK;
if (tp->nonagle&TCP_NAGLE_OFF)
tp->nonagle |= TCP_NAGLE_PUSH;
- tcp_push_pending_frames(sk, tp);
+ tcp_push_pending_frames(sk);
}
break;
default:
err = -ENOPROTOOPT;
break;
- };
+ }
+
release_sock(sk);
return err;
}
info->tcpi_options |= TCPI_OPT_WSCALE;
info->tcpi_snd_wscale = tp->rx_opt.snd_wscale;
info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale;
- }
+ }
if (tp->ecn_flags&TCP_ECN_OK)
info->tcpi_options |= TCPI_OPT_ECN;
return 0;
default:
return -ENOPROTOOPT;
- };
+ }
if (put_user(len, optlen))
return -EFAULT;
if (!pskb_may_pull(skb, sizeof(*th)))
goto out;
- th = skb->h.th;
+ th = tcp_hdr(skb);
thlen = th->doff * 4;
if (thlen < sizeof(*th))
goto out;
delta = htonl(oldlen + (thlen + len));
skb = segs;
- th = skb->h.th;
+ th = tcp_hdr(skb);
seq = ntohl(th->seq);
do {
th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
(__force u32)delta));
if (skb->ip_summed != CHECKSUM_PARTIAL)
- th->check = csum_fold(csum_partial(skb->h.raw, thlen,
- skb->csum));
+ th->check =
+ csum_fold(csum_partial(skb_transport_header(skb),
+ thlen, skb->csum));
seq += len;
skb = skb->next;
- th = skb->h.th;
+ th = tcp_hdr(skb);
th->seq = htonl(seq);
th->cwr = 0;
} while (skb->next);
- delta = htonl(oldlen + (skb->tail - skb->h.raw) + skb->data_len);
+ delta = htonl(oldlen + (skb->tail - skb->transport_header) +
+ skb->data_len);
th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
(__force u32)delta));
if (skb->ip_summed != CHECKSUM_PARTIAL)
- th->check = csum_fold(csum_partial(skb->h.raw, thlen,
- skb->csum));
+ th->check = csum_fold(csum_partial(skb_transport_header(skb),
+ thlen, skb->csum));
out:
return segs;
{
struct tcp_md5sig_pool **pool = NULL;
- spin_lock(&tcp_md5sig_pool_lock);
+ spin_lock_bh(&tcp_md5sig_pool_lock);
if (--tcp_md5sig_users == 0) {
pool = tcp_md5sig_pool;
tcp_md5sig_pool = NULL;
}
- spin_unlock(&tcp_md5sig_pool_lock);
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
if (pool)
__tcp_free_md5sig_pool(pool);
}
int alloc = 0;
retry:
- spin_lock(&tcp_md5sig_pool_lock);
+ spin_lock_bh(&tcp_md5sig_pool_lock);
pool = tcp_md5sig_pool;
if (tcp_md5sig_users++ == 0) {
alloc = 1;
- spin_unlock(&tcp_md5sig_pool_lock);
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
} else if (!pool) {
tcp_md5sig_users--;
- spin_unlock(&tcp_md5sig_pool_lock);
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
cpu_relax();
goto retry;
} else
- spin_unlock(&tcp_md5sig_pool_lock);
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
if (alloc) {
/* we cannot hold spinlock here because this may sleep. */
struct tcp_md5sig_pool **p = __tcp_alloc_md5sig_pool();
- spin_lock(&tcp_md5sig_pool_lock);
+ spin_lock_bh(&tcp_md5sig_pool_lock);
if (!p) {
tcp_md5sig_users--;
- spin_unlock(&tcp_md5sig_pool_lock);
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
return NULL;
}
pool = tcp_md5sig_pool;
if (pool) {
/* oops, it has already been assigned. */
- spin_unlock(&tcp_md5sig_pool_lock);
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
__tcp_free_md5sig_pool(p);
} else {
tcp_md5sig_pool = pool = p;
- spin_unlock(&tcp_md5sig_pool_lock);
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
}
}
return pool;
struct tcp_md5sig_pool *__tcp_get_md5sig_pool(int cpu)
{
struct tcp_md5sig_pool **p;
- spin_lock(&tcp_md5sig_pool_lock);
+ spin_lock_bh(&tcp_md5sig_pool_lock);
p = tcp_md5sig_pool;
if (p)
tcp_md5sig_users++;
- spin_unlock(&tcp_md5sig_pool_lock);
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
return (p ? *per_cpu_ptr(p, cpu) : NULL);
}
EXPORT_SYMBOL(__tcp_put_md5sig_pool);
#endif
+void tcp_done(struct sock *sk)
+{
+ if(sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
+ TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS);
+
+ tcp_set_state(sk, TCP_CLOSE);
+ tcp_clear_xmit_timers(sk);
+
+ sk->sk_shutdown = SHUTDOWN_MASK;
+
+ if (!sock_flag(sk, SOCK_DEAD))
+ sk->sk_state_change(sk);
+ else
+ inet_csk_destroy_sock(sk);
+}
+EXPORT_SYMBOL_GPL(tcp_done);
+
extern void __skb_cb_too_small_for_tcp(int, int);
extern struct tcp_congestion_ops tcp_reno;
&tcp_hashinfo.ehash_size,
NULL,
0);
- tcp_hashinfo.ehash_size = (1 << tcp_hashinfo.ehash_size) >> 1;
- for (i = 0; i < (tcp_hashinfo.ehash_size << 1); i++) {
+ tcp_hashinfo.ehash_size = 1 << tcp_hashinfo.ehash_size;
+ for (i = 0; i < tcp_hashinfo.ehash_size; i++) {
rwlock_init(&tcp_hashinfo.ehash[i].lock);
INIT_HLIST_HEAD(&tcp_hashinfo.ehash[i].chain);
+ INIT_HLIST_HEAD(&tcp_hashinfo.ehash[i].twchain);
}
tcp_hashinfo.bhash =
sysctl_max_syn_backlog = 128;
}
- /* Allow no more than 3/4 kernel memory (usually less) allocated to TCP */
- sysctl_tcp_mem[0] = (1536 / sizeof (struct inet_bind_hashbucket)) << order;
- sysctl_tcp_mem[1] = sysctl_tcp_mem[0] * 4 / 3;
+ /* 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
+ * memory, with a floor of 128 pages.
+ */
+ limit = min(nr_all_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT);
+ limit = (limit * (nr_all_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11);
+ limit = max(limit, 128UL);
+ sysctl_tcp_mem[0] = limit / 4 * 3;
+ sysctl_tcp_mem[1] = limit;
sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;
+ /* Set per-socket limits to no more than 1/128 the pressure threshold */
limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7);
max_share = min(4UL*1024*1024, limit);
printk(KERN_INFO "TCP: Hash tables configured "
"(established %d bind %d)\n",
- tcp_hashinfo.ehash_size << 1, tcp_hashinfo.bhash_size);
+ tcp_hashinfo.ehash_size, tcp_hashinfo.bhash_size);
tcp_register_congestion_control(&tcp_reno);
}
git.openpandora.org / pandora-kernel.git / blobdiff