* TCP_CLOSE socket is finished
*/
-#include <linux/config.h>
+#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/poll.h>
#include <linux/init.h>
-#include <linux/smp_lock.h>
#include <linux/fs.h>
+#include <linux/skbuff.h>
+#include <linux/splice.h>
+#include <linux/net.h>
+#include <linux/socket.h>
#include <linux/random.h>
#include <linux/bootmem.h>
#include <linux/cache.h>
+#include <linux/err.h>
+#include <linux/crypto.h>
#include <net/icmp.h>
#include <net/tcp.h>
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/netdma.h>
+#include <net/sock.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
-int sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
+int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
DEFINE_SNMP_STAT(struct tcp_mib, tcp_statistics) __read_mostly;
EXPORT_SYMBOL(tcp_memory_allocated);
EXPORT_SYMBOL(tcp_sockets_allocated);
+/*
+ * TCP splice context
+ */
+struct tcp_splice_state {
+ struct pipe_inode_info *pipe;
+ size_t len;
+ unsigned int flags;
+};
+
/*
* Pressure flag: try to collapse.
* Technical note: it is used by multiple contexts non atomically.
- * All the sk_stream_mem_schedule() is of this nature: accounting
+ * All the __sk_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)
{
- skb->csum = 0;
- TCP_SKB_CB(skb)->seq = tp->write_seq;
- TCP_SKB_CB(skb)->end_seq = tp->write_seq;
- TCP_SKB_CB(skb)->flags = TCPCB_FLAG_ACK;
- TCP_SKB_CB(skb)->sacked = 0;
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
+
+ skb->csum = 0;
+ tcb->seq = tcb->end_seq = tp->write_seq;
+ tcb->flags = TCPCB_FLAG_ACK;
+ tcb->sacked = 0;
skb_header_release(skb);
- __skb_queue_tail(&sk->sk_write_queue, skb);
- sk_charge_skb(sk, skb);
- if (!sk->sk_send_head)
- sk->sk_send_head = skb;
+ tcp_add_write_queue_tail(sk, skb);
+ sk->sk_wmem_queued += skb->truesize;
+ sk_mem_charge(sk, skb->truesize);
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,
if (flags & MSG_OOB) {
tp->urg_mode = 1;
tp->snd_up = tp->write_seq;
- TCP_SKB_CB(skb)->sacked |= TCPCB_URG;
}
}
-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);
}
}
+static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
+ unsigned int offset, size_t len)
+{
+ struct tcp_splice_state *tss = rd_desc->arg.data;
+
+ return skb_splice_bits(skb, offset, tss->pipe, tss->len, tss->flags);
+}
+
+static int __tcp_splice_read(struct sock *sk, struct tcp_splice_state *tss)
+{
+ /* Store TCP splice context information in read_descriptor_t. */
+ read_descriptor_t rd_desc = {
+ .arg.data = tss,
+ };
+
+ return tcp_read_sock(sk, &rd_desc, tcp_splice_data_recv);
+}
+
+/**
+ * tcp_splice_read - splice data from TCP socket to a pipe
+ * @sock: socket to splice from
+ * @ppos: position (not valid)
+ * @pipe: pipe to splice to
+ * @len: number of bytes to splice
+ * @flags: splice modifier flags
+ *
+ * Description:
+ * Will read pages from given socket and fill them into a pipe.
+ *
+ **/
+ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
+{
+ struct sock *sk = sock->sk;
+ struct tcp_splice_state tss = {
+ .pipe = pipe,
+ .len = len,
+ .flags = flags,
+ };
+ long timeo;
+ ssize_t spliced;
+ int ret;
+
+ /*
+ * We can't seek on a socket input
+ */
+ if (unlikely(*ppos))
+ return -ESPIPE;
+
+ ret = spliced = 0;
+
+ lock_sock(sk);
+
+ timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK);
+ while (tss.len) {
+ ret = __tcp_splice_read(sk, &tss);
+ if (ret < 0)
+ break;
+ else if (!ret) {
+ if (spliced)
+ break;
+ if (flags & SPLICE_F_NONBLOCK) {
+ ret = -EAGAIN;
+ break;
+ }
+ if (sock_flag(sk, SOCK_DONE))
+ break;
+ if (sk->sk_err) {
+ ret = sock_error(sk);
+ break;
+ }
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
+ break;
+ if (sk->sk_state == TCP_CLOSE) {
+ /*
+ * This occurs when user tries to read
+ * from never connected socket.
+ */
+ if (!sock_flag(sk, SOCK_DONE))
+ ret = -ENOTCONN;
+ break;
+ }
+ if (!timeo) {
+ ret = -EAGAIN;
+ break;
+ }
+ sk_wait_data(sk, &timeo);
+ if (signal_pending(current)) {
+ ret = sock_intr_errno(timeo);
+ break;
+ }
+ continue;
+ }
+ tss.len -= ret;
+ spliced += ret;
+
+ release_sock(sk);
+ lock_sock(sk);
+
+ if (sk->sk_err || sk->sk_state == TCP_CLOSE ||
+ (sk->sk_shutdown & RCV_SHUTDOWN) || !timeo ||
+ signal_pending(current))
+ break;
+ }
+
+ release_sock(sk);
+
+ if (spliced)
+ return spliced;
+
+ return ret;
+}
+
+struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
+{
+ struct sk_buff *skb;
+
+ /* The TCP header must be at least 32-bit aligned. */
+ size = ALIGN(size, 4);
+
+ skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp);
+ if (skb) {
+ if (sk_wmem_schedule(sk, skb->truesize)) {
+ /*
+ * Make sure that we have exactly size bytes
+ * available to the caller, no more, no less.
+ */
+ skb_reserve(skb, skb_tailroom(skb) - size);
+ return skb;
+ }
+ __kfree_skb(skb);
+ } else {
+ sk->sk_prot->enter_memory_pressure();
+ sk_stream_moderate_sndbuf(sk);
+ }
+ return NULL;
+}
+
static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffset,
size_t psize, int flags)
{
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;
- skb = sk_stream_alloc_pskb(sk, 0, 0,
- sk->sk_allocation);
+ skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation);
if (!skb)
goto wait_for_memory;
- skb_entail(sk, tp, skb);
+ skb_entail(sk, skb);
copy = size_goal;
}
tcp_mark_push(tp, skb);
goto new_segment;
}
- if (!sk_stream_wmem_schedule(sk, copy))
+ if (!sk_wmem_schedule(sk, copy))
goto wait_for_memory;
-
+
if (can_coalesce) {
skb_shinfo(skb)->frags[i - 1].size += copy;
} else {
skb->data_len += copy;
skb->truesize += copy;
sk->sk_wmem_queued += copy;
- sk->sk_forward_alloc -= copy;
- skb->ip_summed = CHECKSUM_HW;
+ sk_mem_charge(sk, copy);
+ skb->ip_summed = CHECKSUM_PARTIAL;
tp->write_seq += copy;
TCP_SKB_CB(skb)->end_seq += copy;
- skb_shinfo(skb)->tso_segs = 0;
+ skb_shinfo(skb)->gso_segs = 0;
if (!copied)
TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_PSH;
if (!(psize -= copy))
goto out;
- if (skb->len < mss_now || (flags & MSG_OOB))
+ if (skb->len < size_goal || (flags & MSG_OOB))
continue;
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) {
- if (sk->sk_route_caps & NETIF_F_TSO)
+ if (sk_can_gso(sk))
tmp = 0;
else {
int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER);
return tmp;
}
-int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, 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;
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),
- 0, sk->sk_allocation);
+ skb = sk_stream_alloc_skb(sk, select_size(sk),
+ sk->sk_allocation);
if (!skb)
goto wait_for_memory;
* Check whether we can use HW checksum.
*/
if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
- skb->ip_summed = CHECKSUM_HW;
+ skb->ip_summed = CHECKSUM_PARTIAL;
- skb_entail(sk, tp, skb);
+ skb_entail(sk, skb);
copy = size_goal;
}
if (copy > PAGE_SIZE - off)
copy = PAGE_SIZE - off;
- if (!sk_stream_wmem_schedule(sk, copy))
+ if (!sk_wmem_schedule(sk, copy))
goto wait_for_memory;
if (!page) {
tp->write_seq += copy;
TCP_SKB_CB(skb)->end_seq += copy;
- skb_shinfo(skb)->tso_segs = 0;
+ skb_shinfo(skb)->gso_segs = 0;
from += copy;
copied += copy;
if ((seglen -= copy) == 0 && iovlen == 0)
goto out;
- if (skb->len < mss_now || (flags & MSG_OOB))
+ if (skb->len < size_goal || (flags & MSG_OOB))
continue;
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);
- sk_stream_free_skb(sk, skb);
+ 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_wmem_free_skb(sk, skb);
}
do_error:
* receive buffer and there was a small segment
* in queue.
*/
- (copied > 0 && (icsk->icsk_ack.pending & ICSK_ACK_PUSHED) &&
- !icsk->icsk_ack.pingpong && !atomic_read(&sk->sk_rmem_alloc)))
+ (copied > 0 &&
+ ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) ||
+ ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) &&
+ !icsk->icsk_ack.pingpong)) &&
+ !atomic_read(&sk->sk_rmem_alloc)))
time_to_ack = 1;
}
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;
}
break;
}
used = recv_actor(desc, skb, offset, len);
- if (used <= len) {
+ if (used < 0) {
+ if (!copied)
+ copied = used;
+ break;
+ } else if (used <= len) {
seq += used;
copied += used;
offset += used;
if (offset != skb->len)
break;
}
- if (skb->h.th->fin) {
+ if (tcp_hdr(skb)->fin) {
sk_eat_skb(sk, skb, 0);
++seq;
break;
tcp_rcv_space_adjust(sk);
/* Clean up data we have read: This will do ACK frames. */
- if (copied)
+ if (copied > 0)
tcp_cleanup_rbuf(sk, copied);
return copied;
}
long timeo;
struct task_struct *user_recv = NULL;
int copied_early = 0;
+ struct sk_buff *skb;
lock_sock(sk);
#ifdef CONFIG_NET_DMA
tp->ucopy.dma_chan = NULL;
preempt_disable();
- if ((len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
- !sysctl_tcp_low_latency && __get_cpu_var(softnet_data.net_dma)) {
- preempt_enable_no_resched();
- tp->ucopy.pinned_list = dma_pin_iovec_pages(msg->msg_iov, len);
- } else
- preempt_enable_no_resched();
+ skb = skb_peek_tail(&sk->sk_receive_queue);
+ {
+ int available = 0;
+
+ if (skb)
+ available = TCP_SKB_CB(skb)->seq + skb->len - (*seq);
+ if ((available < target) &&
+ (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
+ !sysctl_tcp_low_latency &&
+ __get_cpu_var(softnet_data).net_dma) {
+ preempt_enable_no_resched();
+ tp->ucopy.pinned_list =
+ dma_pin_iovec_pages(msg->msg_iov, len);
+ } else {
+ preempt_enable_no_resched();
+ }
+ }
#endif
do {
- struct sk_buff *skb;
u32 offset;
/* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */
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;
if ((flags & MSG_PEEK) && peek_seq != tp->copied_seq) {
if (net_ratelimit())
printk(KERN_DEBUG "TCP(%s:%d): Application bug, race in MSG_PEEK.\n",
- current->comm, current->pid);
+ current->comm, task_pid_nr(current));
peek_seq = tp->copied_seq;
}
continue;
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);
#ifdef CONFIG_NET_DMA
if (tp->ucopy.dma_chan) {
- struct sk_buff *skb;
dma_cookie_t done, used;
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);
}
goto out;
}
+void tcp_set_state(struct sock *sk, int state)
+{
+ int oldstate = sk->sk_state;
+
+ switch (state) {
+ case TCP_ESTABLISHED:
+ if (oldstate != TCP_ESTABLISHED)
+ TCP_INC_STATS(TCP_MIB_CURRESTAB);
+ break;
+
+ case TCP_CLOSE:
+ if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED)
+ TCP_INC_STATS(TCP_MIB_ESTABRESETS);
+
+ sk->sk_prot->unhash(sk);
+ if (inet_csk(sk)->icsk_bind_hash &&
+ !(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
+ inet_put_port(sk);
+ /* fall through */
+ default:
+ if (oldstate==TCP_ESTABLISHED)
+ TCP_DEC_STATS(TCP_MIB_CURRESTAB);
+ }
+
+ /* Change state AFTER socket is unhashed to avoid closed
+ * socket sitting in hash tables.
+ */
+ sk->sk_state = state;
+
+#ifdef STATE_TRACE
+ SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n",sk, statename[oldstate],statename[state]);
+#endif
+}
+EXPORT_SYMBOL_GPL(tcp_set_state);
+
/*
* State processing on a close. This implements the state shift for
* sending our FIN frame. Note that we only send a FIN for some
*/
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);
}
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
- /* As outlined in draft-ietf-tcpimpl-prob-03.txt, section
- * 3.10, 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 GET in an FTP client, suspend the process, wait
- * for the client to advertise a zero window, then kill -9
- * the FTP client, wheee... Note: timeout is always zero
- * in such a case.
+ /* 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
+ * GET in an FTP client, suspend the process, wait for the client to
+ * advertise a zero window, then kill -9 the FTP client, wheee...
+ * Note: timeout is always zero in such a case.
*/
if (data_was_unread) {
/* Unread data was tossed, zap the connection. */
const int tmo = tcp_fin_time(sk);
if (tmo > TCP_TIMEWAIT_LEN) {
- inet_csk_reset_keepalive_timer(sk, tcp_fin_time(sk));
+ inet_csk_reset_keepalive_timer(sk,
+ tmo - TCP_TIMEWAIT_LEN);
} else {
tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
goto out;
}
}
if (sk->sk_state != TCP_CLOSE) {
- sk_stream_mem_reclaim(sk);
- if (atomic_read(sk->sk_prot->orphan_count) > sysctl_tcp_max_orphans ||
- (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
- atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2])) {
+ sk_mem_reclaim(sk);
+ if (tcp_too_many_orphans(sk,
+ atomic_read(sk->sk_prot->orphan_count))) {
if (net_ratelimit())
printk(KERN_INFO "TCP: too many of orphaned "
"sockets\n");
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;
- tp->rx_opt.saw_tstamp = 0;
- tcp_sack_reset(&tp->rx_opt);
+ tcp_init_send_head(sk);
+ memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
__sk_dst_reset(sk);
BUG_TRAP(!inet->num || icsk->icsk_bind_hash);
* 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;
}
break;
+#ifdef CONFIG_TCP_MD5SIG
+ case TCP_MD5SIG:
+ /* Read the IP->Key mappings from userspace */
+ err = tp->af_specific->md5_parse(sk, optval, optlen);
+ break;
+#endif
+
default:
err = -ENOPROTOOPT;
break;
- };
+ }
+
release_sock(sk);
return err;
}
if (tp->rx_opt.tstamp_ok)
info->tcpi_options |= TCPI_OPT_TIMESTAMPS;
- if (tp->rx_opt.sack_ok)
+ if (tcp_is_sack(tp))
info->tcpi_options |= TCPI_OPT_SACK;
if (tp->rx_opt.wscale_ok) {
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;
info->tcpi_snd_mss = tp->mss_cache;
info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss;
- info->tcpi_unacked = tp->packets_out;
- info->tcpi_sacked = tp->sacked_out;
+ if (sk->sk_state == TCP_LISTEN) {
+ info->tcpi_unacked = sk->sk_ack_backlog;
+ info->tcpi_sacked = sk->sk_max_ack_backlog;
+ } else {
+ info->tcpi_unacked = tp->packets_out;
+ info->tcpi_sacked = tp->sacked_out;
+ }
info->tcpi_lost = tp->lost_out;
info->tcpi_retrans = tp->retrans_out;
info->tcpi_fackets = tp->fackets_out;
return 0;
default:
return -ENOPROTOOPT;
- };
+ }
if (put_user(len, optlen))
return -EFAULT;
EXPORT_SYMBOL(compat_tcp_getsockopt);
#endif
-extern void __skb_cb_too_small_for_tcp(int, int);
+struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features)
+{
+ struct sk_buff *segs = ERR_PTR(-EINVAL);
+ struct tcphdr *th;
+ unsigned thlen;
+ unsigned int seq;
+ __be32 delta;
+ unsigned int oldlen;
+ unsigned int len;
+
+ if (!pskb_may_pull(skb, sizeof(*th)))
+ goto out;
+
+ th = tcp_hdr(skb);
+ thlen = th->doff * 4;
+ if (thlen < sizeof(*th))
+ goto out;
+
+ if (!pskb_may_pull(skb, thlen))
+ goto out;
+
+ oldlen = (u16)~skb->len;
+ __skb_pull(skb, thlen);
+
+ if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
+ /* Packet is from an untrusted source, reset gso_segs. */
+ int type = skb_shinfo(skb)->gso_type;
+ int mss;
+
+ if (unlikely(type &
+ ~(SKB_GSO_TCPV4 |
+ SKB_GSO_DODGY |
+ SKB_GSO_TCP_ECN |
+ SKB_GSO_TCPV6 |
+ 0) ||
+ !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
+ goto out;
+
+ mss = skb_shinfo(skb)->gso_size;
+ skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
+
+ segs = NULL;
+ goto out;
+ }
+
+ segs = skb_segment(skb, features);
+ if (IS_ERR(segs))
+ goto out;
+
+ len = skb_shinfo(skb)->gso_size;
+ delta = htonl(oldlen + (thlen + len));
+
+ skb = segs;
+ th = tcp_hdr(skb);
+ seq = ntohl(th->seq);
+
+ do {
+ th->fin = th->psh = 0;
+
+ 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_transport_header(skb),
+ thlen, skb->csum));
+
+ seq += len;
+ skb = skb->next;
+ th = tcp_hdr(skb);
+
+ th->seq = htonl(seq);
+ th->cwr = 0;
+ } while (skb->next);
+
+ 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_transport_header(skb),
+ thlen, skb->csum));
+
+out:
+ return segs;
+}
+EXPORT_SYMBOL(tcp_tso_segment);
+
+#ifdef CONFIG_TCP_MD5SIG
+static unsigned long tcp_md5sig_users;
+static struct tcp_md5sig_pool **tcp_md5sig_pool;
+static DEFINE_SPINLOCK(tcp_md5sig_pool_lock);
+
+static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool **pool)
+{
+ int cpu;
+ for_each_possible_cpu(cpu) {
+ struct tcp_md5sig_pool *p = *per_cpu_ptr(pool, cpu);
+ if (p) {
+ if (p->md5_desc.tfm)
+ crypto_free_hash(p->md5_desc.tfm);
+ kfree(p);
+ p = NULL;
+ }
+ }
+ free_percpu(pool);
+}
+
+void tcp_free_md5sig_pool(void)
+{
+ struct tcp_md5sig_pool **pool = NULL;
+
+ spin_lock_bh(&tcp_md5sig_pool_lock);
+ if (--tcp_md5sig_users == 0) {
+ pool = tcp_md5sig_pool;
+ tcp_md5sig_pool = NULL;
+ }
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
+ if (pool)
+ __tcp_free_md5sig_pool(pool);
+}
+
+EXPORT_SYMBOL(tcp_free_md5sig_pool);
+
+static struct tcp_md5sig_pool **__tcp_alloc_md5sig_pool(void)
+{
+ int cpu;
+ struct tcp_md5sig_pool **pool;
+
+ pool = alloc_percpu(struct tcp_md5sig_pool *);
+ if (!pool)
+ return NULL;
+
+ for_each_possible_cpu(cpu) {
+ struct tcp_md5sig_pool *p;
+ struct crypto_hash *hash;
+
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (!p)
+ goto out_free;
+ *per_cpu_ptr(pool, cpu) = p;
+
+ hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
+ if (!hash || IS_ERR(hash))
+ goto out_free;
+
+ p->md5_desc.tfm = hash;
+ }
+ return pool;
+out_free:
+ __tcp_free_md5sig_pool(pool);
+ return NULL;
+}
+
+struct tcp_md5sig_pool **tcp_alloc_md5sig_pool(void)
+{
+ struct tcp_md5sig_pool **pool;
+ int alloc = 0;
+
+retry:
+ spin_lock_bh(&tcp_md5sig_pool_lock);
+ pool = tcp_md5sig_pool;
+ if (tcp_md5sig_users++ == 0) {
+ alloc = 1;
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
+ } else if (!pool) {
+ tcp_md5sig_users--;
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
+ cpu_relax();
+ goto retry;
+ } else
+ 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_bh(&tcp_md5sig_pool_lock);
+ if (!p) {
+ tcp_md5sig_users--;
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
+ return NULL;
+ }
+ pool = tcp_md5sig_pool;
+ if (pool) {
+ /* oops, it has already been assigned. */
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
+ __tcp_free_md5sig_pool(p);
+ } else {
+ tcp_md5sig_pool = pool = p;
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
+ }
+ }
+ return pool;
+}
+
+EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
+
+struct tcp_md5sig_pool *__tcp_get_md5sig_pool(int cpu)
+{
+ struct tcp_md5sig_pool **p;
+ spin_lock_bh(&tcp_md5sig_pool_lock);
+ p = tcp_md5sig_pool;
+ if (p)
+ tcp_md5sig_users++;
+ spin_unlock_bh(&tcp_md5sig_pool_lock);
+ return (p ? *per_cpu_ptr(p, cpu) : NULL);
+}
+
+EXPORT_SYMBOL(__tcp_get_md5sig_pool);
+
+void __tcp_put_md5sig_pool(void)
+{
+ tcp_free_md5sig_pool();
+}
+
+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 struct tcp_congestion_ops tcp_reno;
static __initdata unsigned long thash_entries;
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),
- sizeof(skb->cb));
+ BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
tcp_hashinfo.bind_bucket_cachep =
kmem_cache_create("tcp_bind_bucket",
sizeof(struct inet_bind_bucket), 0,
- SLAB_HWCACHE_ALIGN, NULL, NULL);
- if (!tcp_hashinfo.bind_bucket_cachep)
- panic("tcp_init: Cannot alloc tcp_bind_bucket cache.");
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
/* Size and allocate the main established and bind bucket
* hash tables.
thash_entries,
(num_physpages >= 128 * 1024) ?
13 : 15,
- HASH_HIGHMEM,
+ 0,
&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++) {
- rwlock_init(&tcp_hashinfo.ehash[i].lock);
+ thash_entries ? 0 : 512 * 1024);
+ tcp_hashinfo.ehash_size = 1 << tcp_hashinfo.ehash_size;
+ for (i = 0; i < tcp_hashinfo.ehash_size; i++) {
INIT_HLIST_HEAD(&tcp_hashinfo.ehash[i].chain);
+ INIT_HLIST_HEAD(&tcp_hashinfo.ehash[i].twchain);
}
-
+ if (inet_ehash_locks_alloc(&tcp_hashinfo))
+ panic("TCP: failed to alloc ehash_locks");
tcp_hashinfo.bhash =
alloc_large_system_hash("TCP bind",
sizeof(struct inet_bind_hashbucket),
tcp_hashinfo.ehash_size,
(num_physpages >= 128 * 1024) ?
13 : 15,
- HASH_HIGHMEM,
+ 0,
&tcp_hashinfo.bhash_size,
NULL,
64 * 1024);
order++)
;
if (order >= 4) {
- sysctl_local_port_range[0] = 32768;
- sysctl_local_port_range[1] = 61000;
tcp_death_row.sysctl_max_tw_buckets = 180000;
sysctl_tcp_max_orphans = 4096 << (order - 4);
sysctl_max_syn_backlog = 1024;
} else if (order < 3) {
- sysctl_local_port_range[0] = 1024 * (3 - order);
tcp_death_row.sysctl_max_tw_buckets >>= (3 - order);
sysctl_tcp_max_orphans >>= (3 - order);
sysctl_max_syn_backlog = 128;
}
- sysctl_tcp_mem[0] = 768 << order;
- sysctl_tcp_mem[1] = 1024 << order;
- sysctl_tcp_mem[2] = 1536 << order;
-
+ /* 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);
- sysctl_tcp_wmem[0] = SK_STREAM_MEM_QUANTUM;
+ sysctl_tcp_wmem[0] = SK_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[0] = SK_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",
- tcp_hashinfo.ehash_size << 1, tcp_hashinfo.bhash_size);
+ tcp_hashinfo.ehash_size, tcp_hashinfo.bhash_size);
tcp_register_congestion_control(&tcp_reno);
}
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);