tcp: do_tcp_sendpages() must try to push data out on oom conditions

[linux-flexiantxendom0-3.2.10.git] / net / ipv4 / tcp.c

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9bcdec3..6589e11 100644 (file)
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -245,6 +245,8 @@
  *     TCP_CLOSE               socket is finished
  */
 
+#define pr_fmt(fmt) "TCP: " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -699,11 +701,12 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
        skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp);
        if (skb) {
                if (sk_wmem_schedule(sk, skb->truesize)) {
+                       skb_reserve(skb, sk->sk_prot->max_header);
                        /*
                         * Make sure that we have exactly size bytes
                         * available to the caller, no more, no less.
                         */
-                       skb_reserve(skb, skb_tailroom(skb) - size);
+                       skb->avail_size = size;
                        return skb;
                }
                __kfree_skb(skb);
@@ -848,8 +851,7 @@ new_segment:
 wait_for_sndbuf:
                set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
-               if (copied)
-                       tcp_push(sk, 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;
@@ -858,7 +860,7 @@ wait_for_memory:
        }
 
 out:
-       if (copied)
+       if (copied && !(flags & MSG_SENDPAGE_NOTLAST))
                tcp_push(sk, flags, mss_now, tp->nonagle);
        return copied;
 
@@ -993,10 +995,9 @@ new_segment:
                                copy = seglen;
 
                        /* Where to copy to? */
-                       if (skb_tailroom(skb) > 0) {
+                       if (skb_availroom(skb) > 0) {
                                /* We have some space in skb head. Superb! */
-                               if (copy > skb_tailroom(skb))
-                                       copy = skb_tailroom(skb);
+                               copy = min_t(int, copy, skb_availroom(skb));
                                err = skb_add_data_nocache(sk, skb, from, copy);
                                if (err)
                                        goto do_fault;
@@ -1450,7 +1451,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                if ((available < target) &&
                    (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
                    !sysctl_tcp_low_latency &&
-                   dma_find_channel(DMA_MEMCPY)) {
+                   net_dma_find_channel()) {
                        preempt_enable_no_resched();
                        tp->ucopy.pinned_list =
                                        dma_pin_iovec_pages(msg->msg_iov, len);
@@ -1665,7 +1666,7 @@ do_prequeue:
                if (!(flags & MSG_TRUNC)) {
 #ifdef CONFIG_NET_DMA
                        if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-                               tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
+                               tp->ucopy.dma_chan = net_dma_find_channel();
 
                        if (tp->ucopy.dma_chan) {
                                tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec(
@@ -1675,7 +1676,8 @@ do_prequeue:
 
                                if (tp->ucopy.dma_cookie < 0) {
 
-                                       printk(KERN_ALERT "dma_cookie < 0\n");
+                                       pr_alert("%s: dma_cookie < 0\n",
+                                                __func__);
 
                                        /* Exception. Bailout! */
                                        if (!copied)
@@ -1876,6 +1878,20 @@ void tcp_shutdown(struct sock *sk, int how)
 }
 EXPORT_SYMBOL(tcp_shutdown);
 
+bool tcp_check_oom(struct sock *sk, int shift)
+{
+       bool too_many_orphans, out_of_socket_memory;
+
+       too_many_orphans = tcp_too_many_orphans(sk, shift);
+       out_of_socket_memory = tcp_out_of_memory(sk);
+
+       if (too_many_orphans && net_ratelimit())
+               pr_info("too many orphaned sockets\n");
+       if (out_of_socket_memory && net_ratelimit())
+               pr_info("out of memory -- consider tuning tcp_mem\n");
+       return too_many_orphans || out_of_socket_memory;
+}
+
 void tcp_close(struct sock *sk, long timeout)
 {
        struct sk_buff *skb;
@@ -2015,10 +2031,7 @@ adjudge_to_death:
        }
        if (sk->sk_state != TCP_CLOSE) {
                sk_mem_reclaim(sk);
-               if (tcp_too_many_orphans(sk, 0)) {
-                       if (net_ratelimit())
-                               printk(KERN_INFO "TCP: too many of orphaned "
-                                      "sockets\n");
+               if (tcp_check_oom(sk, 0)) {
                        tcp_set_state(sk, TCP_CLOSE);
                        tcp_send_active_reset(sk, GFP_ATOMIC);
                        NET_INC_STATS_BH(sock_net(sk),
@@ -3216,11 +3229,21 @@ static int __init set_thash_entries(char *str)
 }
 __setup("thash_entries=", set_thash_entries);
 
+void tcp_init_mem(struct net *net)
+{
+       unsigned long limit = nr_free_buffer_pages() / 8;
+       limit = max(limit, 128UL);
+       net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3;
+       net->ipv4.sysctl_tcp_mem[1] = limit;
+       net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2;
+}
+
 void __init tcp_init(void)
 {
        struct sk_buff *skb = NULL;
        unsigned long limit;
-       int i, max_share, cnt;
+       int max_rshare, max_wshare, cnt;
+       unsigned int i;
        unsigned long jiffy = jiffies;
 
        BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
@@ -3263,7 +3286,7 @@ void __init tcp_init(void)
                                        &tcp_hashinfo.bhash_size,
                                        NULL,
                                        64 * 1024);
-       tcp_hashinfo.bhash_size = 1 << tcp_hashinfo.bhash_size;
+       tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size;
        for (i = 0; i < tcp_hashinfo.bhash_size; i++) {
                spin_lock_init(&tcp_hashinfo.bhash[i].lock);
                INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain);
@@ -3276,22 +3299,22 @@ void __init tcp_init(void)
        sysctl_tcp_max_orphans = cnt / 2;
        sysctl_max_syn_backlog = max(128, cnt / 256);
 
+       tcp_init_mem(&init_net);
        /* Set per-socket limits to no more than 1/128 the pressure threshold */
-       limit = ((unsigned long)init_net.ipv4.sysctl_tcp_mem[1])
-               << (PAGE_SHIFT - 7);
-       max_share = min(4UL*1024*1024, limit);
+       limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7);
+       max_wshare = min(4UL*1024*1024, limit);
+       max_rshare = min(6UL*1024*1024, limit);
 
        sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;
        sysctl_tcp_wmem[1] = 16*1024;
-       sysctl_tcp_wmem[2] = max(64*1024, max_share);
+       sysctl_tcp_wmem[2] = max(64*1024, max_wshare);
 
        sysctl_tcp_rmem[0] = SK_MEM_QUANTUM;
        sysctl_tcp_rmem[1] = 87380;
-       sysctl_tcp_rmem[2] = max(87380, max_share);
+       sysctl_tcp_rmem[2] = max(87380, max_rshare);
 
-       printk(KERN_INFO "TCP: Hash tables configured "
-              "(established %u bind %u)\n",
-              tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
+       pr_info("Hash tables configured (established %u bind %u)\n",
+               tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
 
        tcp_register_congestion_control(&tcp_reno);