*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp.c,v 1.216 2002/02/01 22:01:04 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
#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>
#include <linux/random.h>
#include <linux/bootmem.h>
+#include <linux/highmem.h>
+#include <linux/swap.h>
#include <linux/cache.h>
#include <linux/err.h>
#include <linux/crypto.h>
int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
-DEFINE_SNMP_STAT(struct tcp_mib, tcp_statistics) __read_mostly;
-
-atomic_t tcp_orphan_count = ATOMIC_INIT(0);
-
+struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);
int sysctl_tcp_mem[3] __read_mostly;
EXPORT_SYMBOL(sysctl_tcp_wmem);
atomic_t tcp_memory_allocated; /* Current allocated memory. */
-atomic_t tcp_sockets_allocated; /* Current number of TCP sockets. */
-
EXPORT_SYMBOL(tcp_memory_allocated);
+
+/*
+ * Current number of TCP sockets.
+ */
+struct percpu_counter tcp_sockets_allocated;
EXPORT_SYMBOL(tcp_sockets_allocated);
/*
EXPORT_SYMBOL(tcp_memory_pressure);
-void tcp_enter_memory_pressure(void)
+void tcp_enter_memory_pressure(struct sock *sk)
{
if (!tcp_memory_pressure) {
- NET_INC_STATS(LINUX_MIB_TCPMEMORYPRESSURES);
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES);
tcp_memory_pressure = 1;
}
}
EXPORT_SYMBOL(tcp_enter_memory_pressure);
+/* Convert seconds to retransmits based on initial and max timeout */
+static u8 secs_to_retrans(int seconds, int timeout, int rto_max)
+{
+ u8 res = 0;
+
+ if (seconds > 0) {
+ int period = timeout;
+
+ res = 1;
+ while (seconds > period && res < 255) {
+ res++;
+ timeout <<= 1;
+ if (timeout > rto_max)
+ timeout = rto_max;
+ period += timeout;
+ }
+ }
+ return res;
+}
+
+/* Convert retransmits to seconds based on initial and max timeout */
+static int retrans_to_secs(u8 retrans, int timeout, int rto_max)
+{
+ int period = 0;
+
+ if (retrans > 0) {
+ period = timeout;
+ while (--retrans) {
+ timeout <<= 1;
+ if (timeout > rto_max)
+ timeout = rto_max;
+ period += timeout;
+ }
+ }
+ return period;
+}
+
/*
* Wait for a TCP event.
*
struct sock *sk = sock->sk;
struct tcp_sock *tp = tcp_sk(sk);
- poll_wait(file, sk->sk_sleep, wait);
+ sock_poll_wait(file, sk->sk_sleep, wait);
if (sk->sk_state == TCP_LISTEN)
return inet_csk_listen_poll(sk);
/* Socket is not locked. We are protected from async events
- by poll logic and correct handling of state changes
- made by another threads is impossible in any case.
+ * by poll logic and correct handling of state changes
+ * made by other threads is impossible in any case.
*/
mask = 0;
* in state CLOSE_WAIT. One solution is evident --- to set POLLHUP
* if and only if shutdown has been made in both directions.
* Actually, it is interesting to look how Solaris and DUX
- * solve this dilemma. I would prefer, if PULLHUP were maskable,
+ * solve this dilemma. I would prefer, if POLLHUP were maskable,
* then we could set it on SND_SHUTDOWN. BTW examples given
* in Stevens' books assume exactly this behaviour, it explains
- * why PULLHUP is incompatible with POLLOUT. --ANK
+ * why POLLHUP is incompatible with POLLOUT. --ANK
*
* NOTE. Check for TCP_CLOSE is added. The goal is to prevent
* blocking on fresh not-connected or disconnected socket. --ANK
/* Connected? */
if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV)) {
+ int target = sock_rcvlowat(sk, 0, INT_MAX);
+
+ if (tp->urg_seq == tp->copied_seq &&
+ !sock_flag(sk, SOCK_URGINLINE) &&
+ tp->urg_data)
+ target--;
+
/* Potential race condition. If read of tp below will
* escape above sk->sk_state, we can be illegally awaken
* in SYN_* states. */
- if ((tp->rcv_nxt != tp->copied_seq) &&
- (tp->urg_seq != tp->copied_seq ||
- tp->rcv_nxt != tp->copied_seq + 1 ||
- sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data))
+ if (tp->rcv_nxt - tp->copied_seq >= target)
mask |= POLLIN | POLLRDNORM;
if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
!tp->urg_data ||
before(tp->urg_seq, tp->copied_seq) ||
!before(tp->urg_seq, tp->rcv_nxt)) {
+ struct sk_buff *skb;
+
answ = tp->rcv_nxt - tp->copied_seq;
/* Subtract 1, if FIN is in queue. */
- if (answ && !skb_queue_empty(&sk->sk_receive_queue))
- answ -=
- tcp_hdr((struct sk_buff *)sk->sk_receive_queue.prev)->fin;
+ skb = skb_peek_tail(&sk->sk_receive_queue);
+ if (answ && skb)
+ answ -= tcp_hdr(skb)->fin;
} else
answ = tp->urg_seq - tp->copied_seq;
release_sock(sk);
static inline void tcp_mark_urg(struct tcp_sock *tp, int flags,
struct sk_buff *skb)
{
- if (flags & MSG_OOB) {
- tp->urg_mode = 1;
+ if (flags & MSG_OOB)
tp->snd_up = tp->write_seq;
- }
}
static inline void tcp_push(struct sock *sk, int flags, int mss_now,
unsigned int offset, size_t len)
{
struct tcp_splice_state *tss = rd_desc->arg.data;
+ int ret;
- return skb_splice_bits(skb, offset, tss->pipe, tss->len, tss->flags);
+ ret = skb_splice_bits(skb, offset, tss->pipe, min(rd_desc->count, len),
+ tss->flags);
+ if (ret > 0)
+ rd_desc->count -= ret;
+ return ret;
}
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,
+ .count = tss->len,
};
return tcp_read_sock(sk, &rd_desc, tcp_splice_data_recv);
lock_sock(sk);
- timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK);
+ timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK);
while (tss.len) {
ret = __tcp_splice_read(sk, &tss);
if (ret < 0)
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) {
tss.len -= ret;
spliced += ret;
+ if (!timeo)
+ break;
release_sock(sk);
lock_sock(sk);
if (sk->sk_err || sk->sk_state == TCP_CLOSE ||
- (sk->sk_shutdown & RCV_SHUTDOWN) || !timeo ||
+ (sk->sk_shutdown & RCV_SHUTDOWN) ||
signal_pending(current))
break;
}
}
__kfree_skb(skb);
} else {
- sk->sk_prot->enter_memory_pressure();
+ sk->sk_prot->enter_memory_pressure(sk);
sk_stream_moderate_sndbuf(sk);
}
return NULL;
}
+static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
+ int large_allowed)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ u32 xmit_size_goal, old_size_goal;
+
+ xmit_size_goal = mss_now;
+
+ if (large_allowed && sk_can_gso(sk)) {
+ xmit_size_goal = ((sk->sk_gso_max_size - 1) -
+ inet_csk(sk)->icsk_af_ops->net_header_len -
+ inet_csk(sk)->icsk_ext_hdr_len -
+ tp->tcp_header_len);
+
+ xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
+
+ /* We try hard to avoid divides here */
+ old_size_goal = tp->xmit_size_goal_segs * mss_now;
+
+ if (likely(old_size_goal <= xmit_size_goal &&
+ old_size_goal + mss_now > xmit_size_goal)) {
+ xmit_size_goal = old_size_goal;
+ } else {
+ tp->xmit_size_goal_segs = xmit_size_goal / mss_now;
+ xmit_size_goal = tp->xmit_size_goal_segs * mss_now;
+ }
+ }
+
+ return max(xmit_size_goal, mss_now);
+}
+
+static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
+{
+ int mss_now;
+
+ mss_now = tcp_current_mss(sk);
+ *size_goal = tcp_xmit_size_goal(sk, mss_now, !(flags & MSG_OOB));
+
+ return mss_now;
+}
+
static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffset,
size_t psize, int flags)
{
clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
- mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));
- size_goal = tp->xmit_size_goal;
+ mss_now = tcp_send_mss(sk, &size_goal, flags);
copied = 0;
err = -EPIPE;
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
- goto do_error;
+ goto out_err;
while (psize > 0) {
struct sk_buff *skb = tcp_write_queue_tail(sk);
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)) {
if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
goto do_error;
- mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));
- size_goal = tp->xmit_size_goal;
+ mss_now = tcp_send_mss(sk, &size_goal, flags);
}
out:
/* This should be in poll */
clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
- mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));
- size_goal = tp->xmit_size_goal;
+ mss_now = tcp_send_mss(sk, &size_goal, flags);
/* Ok commence sending. */
iovlen = msg->msg_iovlen;
err = -EPIPE;
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
- goto do_error;
+ goto out_err;
while (--iovlen >= 0) {
int seglen = iov->iov_len;
iov++;
while (seglen > 0) {
- int copy;
+ int copy = 0;
+ int max = size_goal;
skb = tcp_write_queue_tail(sk);
+ if (tcp_send_head(sk)) {
+ if (skb->ip_summed == CHECKSUM_NONE)
+ max = mss_now;
+ copy = max - skb->len;
+ }
- if (!tcp_send_head(sk) ||
- (copy = size_goal - skb->len) <= 0) {
-
+ if (copy <= 0) {
new_segment:
/* Allocate new segment. If the interface is SG,
* allocate skb fitting to single page.
skb_entail(sk, skb);
copy = size_goal;
+ max = size_goal;
}
/* Try to append data to the end of skb. */
if ((seglen -= copy) == 0 && iovlen == 0)
goto out;
- if (skb->len < mss_now || (flags & MSG_OOB))
+ if (skb->len < max || (flags & MSG_OOB))
continue;
if (forced_push(tp)) {
if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
goto do_error;
- mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));
- size_goal = tp->xmit_size_goal;
+ mss_now = tcp_send_mss(sk, &size_goal, flags);
}
}
* this, no blocking and very strange errors 8)
*/
-static int tcp_recv_urg(struct sock *sk, long timeo,
- struct msghdr *msg, int len, int flags,
- int *addr_len)
+static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags)
{
struct tcp_sock *tp = tcp_sk(sk);
#if TCP_DEBUG
struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
- BUG_TRAP(!skb || before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq));
+ WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
+ KERN_INFO "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
+ tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt);
#endif
if (inet_csk_ack_scheduled(sk)) {
struct sk_buff *skb;
struct tcp_sock *tp = tcp_sk(sk);
- NET_INC_STATS_USER(LINUX_MIB_TCPPREQUEUED);
+ NET_INC_STATS_USER(sock_net(sk), LINUX_MIB_TCPPREQUEUED);
/* RX process wants to run with disabled BHs, though it is not
* necessary */
local_bh_disable();
while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
- sk->sk_backlog_rcv(sk, skb);
+ sk_backlog_rcv(sk, skb);
local_bh_enable();
/* Clear memory counter. */
return -ENOTCONN;
while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) {
if (offset < skb->len) {
- size_t used, len;
+ int used;
+ size_t len;
len = skb->len - offset;
/* Stop reading if we hit a patch of urgent data */
copied += used;
offset += used;
}
- if (offset != skb->len)
+ /*
+ * If recv_actor drops the lock (e.g. TCP splice
+ * receive) the skb pointer might be invalid when
+ * getting here: tcp_collapse might have deleted it
+ * while aggregating skbs from the socket queue.
+ */
+ skb = tcp_recv_skb(sk, seq-1, &offset);
+ if (!skb || (offset+1 != skb->len))
break;
}
if (tcp_hdr(skb)->fin) {
struct task_struct *user_recv = NULL;
int copied_early = 0;
struct sk_buff *skb;
+ u32 urg_hole = 0;
lock_sock(sk);
if ((available < target) &&
(len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
!sysctl_tcp_low_latency &&
- __get_cpu_var(softnet_data).net_dma) {
+ dma_find_channel(DMA_MEMCPY)) {
preempt_enable_no_resched();
tp->ucopy.pinned_list =
dma_pin_iovec_pages(msg->msg_iov, len);
/* Next get a buffer. */
- skb = skb_peek(&sk->sk_receive_queue);
- do {
- if (!skb)
- break;
-
+ skb_queue_walk(&sk->sk_receive_queue, skb) {
/* Now that we have two receive queues this
* shouldn't happen.
*/
- if (before(*seq, TCP_SKB_CB(skb)->seq)) {
- printk(KERN_INFO "recvmsg bug: copied %X "
- "seq %X\n", *seq, TCP_SKB_CB(skb)->seq);
+ 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))
break;
- }
+
offset = *seq - TCP_SKB_CB(skb)->seq;
if (tcp_hdr(skb)->syn)
offset--;
goto found_ok_skb;
if (tcp_hdr(skb)->fin)
goto found_fin_ok;
- BUG_TRAP(flags & MSG_PEEK);
- skb = skb->next;
- } while (skb != (struct sk_buff *)&sk->sk_receive_queue);
+ 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);
+ }
/* Well, if we have backlog, try to process it now yet. */
sk->sk_state == TCP_CLOSE ||
(sk->sk_shutdown & RCV_SHUTDOWN) ||
!timeo ||
- signal_pending(current) ||
- (flags & MSG_PEEK))
+ signal_pending(current))
break;
} else {
if (sock_flag(sk, SOCK_DONE))
tp->ucopy.len = len;
- BUG_TRAP(tp->copied_seq == tp->rcv_nxt ||
- (flags & (MSG_PEEK | MSG_TRUNC)));
+ WARN_ON(tp->copied_seq != tp->rcv_nxt &&
+ !(flags & (MSG_PEEK | MSG_TRUNC)));
/* Ugly... If prequeue is not empty, we have to
* process it before releasing socket, otherwise
/* __ Restore normal policy in scheduler __ */
if ((chunk = len - tp->ucopy.len) != 0) {
- NET_ADD_STATS_USER(LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, chunk);
+ NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, chunk);
len -= chunk;
copied += chunk;
}
tcp_prequeue_process(sk);
if ((chunk = len - tp->ucopy.len) != 0) {
- NET_ADD_STATS_USER(LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
+ NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
len -= chunk;
copied += chunk;
}
}
}
- if ((flags & MSG_PEEK) && peek_seq != tp->copied_seq) {
+ if ((flags & MSG_PEEK) &&
+ (peek_seq - copied - urg_hole != tp->copied_seq)) {
if (net_ratelimit())
printk(KERN_DEBUG "TCP(%s:%d): Application bug, race in MSG_PEEK.\n",
current->comm, task_pid_nr(current));
if (!urg_offset) {
if (!sock_flag(sk, SOCK_URGINLINE)) {
++*seq;
+ urg_hole++;
offset++;
used--;
if (!used)
if (!(flags & MSG_TRUNC)) {
#ifdef CONFIG_NET_DMA
if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
- tp->ucopy.dma_chan = get_softnet_dma();
+ tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
if (tp->ucopy.dma_chan) {
tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec(
tcp_prequeue_process(sk);
if (copied > 0 && (chunk = len - tp->ucopy.len) != 0) {
- NET_ADD_STATS_USER(LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
+ NET_ADD_STATS_USER(sock_net(sk), LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, chunk);
len -= chunk;
copied += chunk;
}
/* Safe to free early-copied skbs now */
__skb_queue_purge(&sk->sk_async_wait_queue);
- dma_chan_put(tp->ucopy.dma_chan);
tp->ucopy.dma_chan = NULL;
}
if (tp->ucopy.pinned_list) {
return err;
recv_urg:
- err = tcp_recv_urg(sk, timeo, msg, len, flags, addr_len);
+ err = tcp_recv_urg(sk, msg, len, flags);
goto out;
}
switch (state) {
case TCP_ESTABLISHED:
if (oldstate != TCP_ESTABLISHED)
- TCP_INC_STATS(TCP_MIB_CURRESTAB);
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
break;
case TCP_CLOSE:
if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED)
- TCP_INC_STATS(TCP_MIB_ESTABRESETS);
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_ESTABRESETS);
sk->sk_prot->unhash(sk);
if (inet_csk(sk)->icsk_bind_hash &&
inet_put_port(sk);
/* fall through */
default:
- if (oldstate==TCP_ESTABLISHED)
- TCP_DEC_STATS(TCP_MIB_CURRESTAB);
+ if (oldstate == TCP_ESTABLISHED)
+ TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
}
/* Change state AFTER socket is unhashed to avoid closed
sk->sk_state = state;
#ifdef STATE_TRACE
- SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n",sk, statename[oldstate],statename[state]);
+ SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]);
#endif
}
EXPORT_SYMBOL_GPL(tcp_set_state);
/*
* Shutdown the sending side of a connection. Much like close except
- * that we don't receive shut down or set_sock_flag(sk, SOCK_DEAD).
+ * that we don't receive shut down or sock_set_flag(sk, SOCK_DEAD).
*/
void tcp_shutdown(struct sock *sk, int how)
*/
if (data_was_unread) {
/* Unread data was tossed, zap the connection. */
- NET_INC_STATS_USER(LINUX_MIB_TCPABORTONCLOSE);
+ NET_INC_STATS_USER(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE);
tcp_set_state(sk, TCP_CLOSE);
- tcp_send_active_reset(sk, GFP_KERNEL);
+ tcp_send_active_reset(sk, sk->sk_allocation);
} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
/* Check zero linger _after_ checking for unread data. */
sk->sk_prot->disconnect(sk, 0);
- NET_INC_STATS_USER(LINUX_MIB_TCPABORTONDATA);
+ NET_INC_STATS_USER(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
} else if (tcp_close_state(sk)) {
/* We FIN if the application ate all the data before
* zapping the connection.
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);
*/
local_bh_disable();
bh_lock_sock(sk);
- BUG_TRAP(!sock_owned_by_user(sk));
+ WARN_ON(sock_owned_by_user(sk));
+
+ percpu_counter_inc(sk->sk_prot->orphan_count);
/* Have we already been destroyed by a softirq or backlog? */
if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE)
if (tp->linger2 < 0) {
tcp_set_state(sk, TCP_CLOSE);
tcp_send_active_reset(sk, GFP_ATOMIC);
- NET_INC_STATS_BH(LINUX_MIB_TCPABORTONLINGER);
+ NET_INC_STATS_BH(sock_net(sk),
+ LINUX_MIB_TCPABORTONLINGER);
} else {
const int tmo = tcp_fin_time(sk);
}
}
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,
- atomic_read(sk->sk_prot->orphan_count))) {
+ if (tcp_too_many_orphans(sk, orphan_count)) {
if (net_ratelimit())
printk(KERN_INFO "TCP: too many of orphaned "
"sockets\n");
tcp_set_state(sk, TCP_CLOSE);
tcp_send_active_reset(sk, GFP_ATOMIC);
- NET_INC_STATS_BH(LINUX_MIB_TCPABORTONMEMORY);
+ NET_INC_STATS_BH(sock_net(sk),
+ LINUX_MIB_TCPABORTONMEMORY);
}
}
__skb_queue_purge(&sk->sk_async_wait_queue);
#endif
- inet->dport = 0;
+ inet->inet_dport = 0;
if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
inet_reset_saddr(sk);
tp->snd_cwnd = 2;
icsk->icsk_probes_out = 0;
tp->packets_out = 0;
- tp->snd_ssthresh = 0x7fffffff;
+ tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_cnt = 0;
tp->bytes_acked = 0;
+ tp->window_clamp = 0;
tcp_set_ca_state(sk, TCP_CA_Open);
tcp_clear_retrans(tp);
inet_csk_delack_init(sk);
memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
__sk_dst_reset(sk);
- BUG_TRAP(!inet->num || icsk->icsk_bind_hash);
+ WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
sk->sk_error_report(sk);
return err;
* Socket option code for TCP.
*/
static int do_tcp_setsockopt(struct sock *sk, int level,
- int optname, char __user *optval, int optlen)
+ int optname, char __user *optval, unsigned int optlen)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
return -EINVAL;
val = strncpy_from_user(name, optval,
- min(TCP_CA_NAME_MAX-1, optlen));
+ min_t(long, TCP_CA_NAME_MAX-1, optlen));
if (val < 0)
return -EFAULT;
name[val] = 0;
break;
case TCP_DEFER_ACCEPT:
- if (val < 0) {
- err = -EINVAL;
- } else {
- if (val > MAX_TCP_ACCEPT_DEFERRED)
- val = MAX_TCP_ACCEPT_DEFERRED;
- icsk->icsk_accept_queue.rskq_defer_accept = val;
- }
+ /* Translate value in seconds to number of retransmits */
+ icsk->icsk_accept_queue.rskq_defer_accept =
+ secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
+ TCP_RTO_MAX / HZ);
break;
case TCP_WINDOW_CLAMP:
}
int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
- int optlen)
+ unsigned int optlen)
{
struct inet_connection_sock *icsk = inet_csk(sk);
#ifdef CONFIG_COMPAT
int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
+ char __user *optval, unsigned int optlen)
{
if (level != SOL_TCP)
return inet_csk_compat_setsockopt(sk, level, optname,
val = !!(tp->nonagle&TCP_NAGLE_CORK);
break;
case TCP_KEEPIDLE:
- val = (tp->keepalive_time ? : sysctl_tcp_keepalive_time) / HZ;
+ val = keepalive_time_when(tp) / HZ;
break;
case TCP_KEEPINTVL:
- val = (tp->keepalive_intvl ? : sysctl_tcp_keepalive_intvl) / HZ;
+ val = keepalive_intvl_when(tp) / HZ;
break;
case TCP_KEEPCNT:
- val = tp->keepalive_probes ? : sysctl_tcp_keepalive_probes;
+ val = keepalive_probes(tp);
break;
case TCP_SYNCNT:
val = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
val = (val ? : sysctl_tcp_fin_timeout) / HZ;
break;
case TCP_DEFER_ACCEPT:
- val = icsk->icsk_accept_queue.rskq_defer_accept;
+ val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,
+ TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ);
break;
case TCP_WINDOW_CLAMP:
val = tp->window_clamp;
unsigned int seq;
__be32 delta;
unsigned int oldlen;
- unsigned int len;
+ unsigned int mss;
if (!pskb_may_pull(skb, sizeof(*th)))
goto out;
oldlen = (u16)~skb->len;
__skb_pull(skb, thlen);
+ mss = skb_shinfo(skb)->gso_size;
+ if (unlikely(skb->len <= mss))
+ goto out;
+
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 |
!(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;
if (IS_ERR(segs))
goto out;
- len = skb_shinfo(skb)->gso_size;
- delta = htonl(oldlen + (thlen + len));
+ delta = htonl(oldlen + (thlen + mss));
skb = segs;
th = tcp_hdr(skb);
csum_fold(csum_partial(skb_transport_header(skb),
thlen, skb->csum));
- seq += len;
+ seq += mss;
skb = skb->next;
th = tcp_hdr(skb);
}
EXPORT_SYMBOL(tcp_tso_segment);
+struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+{
+ struct sk_buff **pp = NULL;
+ struct sk_buff *p;
+ struct tcphdr *th;
+ struct tcphdr *th2;
+ unsigned int len;
+ unsigned int thlen;
+ unsigned int flags;
+ unsigned int mss = 1;
+ unsigned int hlen;
+ unsigned int off;
+ int flush = 1;
+ int i;
+
+ off = skb_gro_offset(skb);
+ hlen = off + sizeof(*th);
+ th = skb_gro_header_fast(skb, off);
+ if (skb_gro_header_hard(skb, hlen)) {
+ th = skb_gro_header_slow(skb, hlen, off);
+ if (unlikely(!th))
+ goto out;
+ }
+
+ thlen = th->doff * 4;
+ if (thlen < sizeof(*th))
+ goto out;
+
+ hlen = off + thlen;
+ if (skb_gro_header_hard(skb, hlen)) {
+ th = skb_gro_header_slow(skb, hlen, off);
+ if (unlikely(!th))
+ goto out;
+ }
+
+ skb_gro_pull(skb, thlen);
+
+ len = skb_gro_len(skb);
+ flags = tcp_flag_word(th);
+
+ for (; (p = *head); head = &p->next) {
+ if (!NAPI_GRO_CB(p)->same_flow)
+ continue;
+
+ th2 = tcp_hdr(p);
+
+ if (*(u32 *)&th->source ^ *(u32 *)&th2->source) {
+ NAPI_GRO_CB(p)->same_flow = 0;
+ continue;
+ }
+
+ goto found;
+ }
+
+ goto out_check_final;
+
+found:
+ flush = NAPI_GRO_CB(p)->flush;
+ flush |= flags & TCP_FLAG_CWR;
+ flush |= (flags ^ tcp_flag_word(th2)) &
+ ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH);
+ flush |= th->ack_seq ^ th2->ack_seq;
+ for (i = sizeof(*th); i < thlen; i += 4)
+ flush |= *(u32 *)((u8 *)th + i) ^
+ *(u32 *)((u8 *)th2 + i);
+
+ mss = skb_shinfo(p)->gso_size;
+
+ flush |= (len - 1) >= mss;
+ flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
+
+ if (flush || skb_gro_receive(head, skb)) {
+ mss = 1;
+ goto out_check_final;
+ }
+
+ p = *head;
+ th2 = tcp_hdr(p);
+ tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH);
+
+out_check_final:
+ flush = len < mss;
+ flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST |
+ TCP_FLAG_SYN | TCP_FLAG_FIN);
+
+ if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
+ pp = head;
+
+out:
+ NAPI_GRO_CB(skb)->flush |= flush;
+
+ return pp;
+}
+EXPORT_SYMBOL(tcp_gro_receive);
+
+int tcp_gro_complete(struct sk_buff *skb)
+{
+ struct tcphdr *th = tcp_hdr(skb);
+
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct tcphdr, check);
+ skb->ip_summed = CHECKSUM_PARTIAL;
+
+ skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+
+ if (th->cwr)
+ skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
+
+ return 0;
+}
+EXPORT_SYMBOL(tcp_gro_complete);
+
#ifdef CONFIG_TCP_MD5SIG
static unsigned long tcp_md5sig_users;
static struct tcp_md5sig_pool **tcp_md5sig_pool;
EXPORT_SYMBOL(tcp_free_md5sig_pool);
-static struct tcp_md5sig_pool **__tcp_alloc_md5sig_pool(void)
+static struct tcp_md5sig_pool **__tcp_alloc_md5sig_pool(struct sock *sk)
{
int cpu;
struct tcp_md5sig_pool **pool;
struct tcp_md5sig_pool *p;
struct crypto_hash *hash;
- p = kzalloc(sizeof(*p), GFP_KERNEL);
+ p = kzalloc(sizeof(*p), sk->sk_allocation);
if (!p)
goto out_free;
*per_cpu_ptr(pool, cpu) = p;
return NULL;
}
-struct tcp_md5sig_pool **tcp_alloc_md5sig_pool(void)
+struct tcp_md5sig_pool **tcp_alloc_md5sig_pool(struct sock *sk)
{
struct tcp_md5sig_pool **pool;
int alloc = 0;
if (alloc) {
/* we cannot hold spinlock here because this may sleep. */
- struct tcp_md5sig_pool **p = __tcp_alloc_md5sig_pool();
+ struct tcp_md5sig_pool **p = __tcp_alloc_md5sig_pool(sk);
spin_lock_bh(&tcp_md5sig_pool_lock);
if (!p) {
tcp_md5sig_users--;
}
EXPORT_SYMBOL(__tcp_put_md5sig_pool);
+
+int tcp_md5_hash_header(struct tcp_md5sig_pool *hp,
+ struct tcphdr *th)
+{
+ struct scatterlist sg;
+ int err;
+
+ __sum16 old_checksum = th->check;
+ th->check = 0;
+ /* options aren't included in the hash */
+ sg_init_one(&sg, th, sizeof(struct tcphdr));
+ err = crypto_hash_update(&hp->md5_desc, &sg, sizeof(struct tcphdr));
+ th->check = old_checksum;
+ return err;
+}
+
+EXPORT_SYMBOL(tcp_md5_hash_header);
+
+int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
+ struct sk_buff *skb, unsigned header_len)
+{
+ struct scatterlist sg;
+ const struct tcphdr *tp = tcp_hdr(skb);
+ struct hash_desc *desc = &hp->md5_desc;
+ unsigned i;
+ 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);
+
+ sg_init_table(&sg, 1);
+
+ sg_set_buf(&sg, ((u8 *) tp) + header_len, head_data_len);
+ if (crypto_hash_update(desc, &sg, head_data_len))
+ return 1;
+
+ for (i = 0; i < shi->nr_frags; ++i) {
+ const struct skb_frag_struct *f = &shi->frags[i];
+ sg_set_page(&sg, f->page, f->size, f->page_offset);
+ if (crypto_hash_update(desc, &sg, f->size))
+ 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)
+{
+ struct scatterlist sg;
+
+ 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
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);
+ if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
+ TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
tcp_set_state(sk, TCP_CLOSE);
tcp_clear_xmit_timers(sk);
void __init tcp_init(void)
{
struct sk_buff *skb = NULL;
- unsigned long limit;
+ unsigned long nr_pages, limit;
int order, i, max_share;
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
+ percpu_counter_init(&tcp_sockets_allocated, 0);
+ percpu_counter_init(&tcp_orphan_count, 0);
tcp_hashinfo.bind_bucket_cachep =
kmem_cache_create("tcp_bind_bucket",
sizeof(struct inet_bind_bucket), 0,
alloc_large_system_hash("TCP established",
sizeof(struct inet_ehash_bucket),
thash_entries,
- (num_physpages >= 128 * 1024) ?
+ (totalram_pages >= 128 * 1024) ?
13 : 15,
0,
- &tcp_hashinfo.ehash_size,
NULL,
+ &tcp_hashinfo.ehash_mask,
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);
+ for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) {
+ INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i);
+ INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].twchain, i);
}
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) ?
+ tcp_hashinfo.ehash_mask + 1,
+ (totalram_pages >= 128 * 1024) ?
13 : 15,
0,
&tcp_hashinfo.bhash_size,
* 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);
+ nr_pages = totalram_pages - totalhigh_pages;
+ limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT);
+ limit = (limit * (nr_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_rmem[2] = max(87380, max_share);
printk(KERN_INFO "TCP: Hash tables configured "
- "(established %d bind %d)\n",
- tcp_hashinfo.ehash_size, tcp_hashinfo.bhash_size);
+ "(established %u bind %u)\n",
+ tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
tcp_register_congestion_control(&tcp_reno);
}
EXPORT_SYMBOL(tcp_sendpage);
EXPORT_SYMBOL(tcp_setsockopt);
EXPORT_SYMBOL(tcp_shutdown);
-EXPORT_SYMBOL(tcp_statistics);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff