1 files changed, 87 insertions, 28 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index fc54a48fde1e..0b491bf03db4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -5,8 +5,6 @@
  *
  *              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>
@@ -255,11 +253,14 @@
 #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>
@@ -276,8 +277,6 @@
 
 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);
 
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
@@ -315,10 +314,10 @@ int tcp_memory_pressure __read_mostly;
 
 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;
         }
 }
@@ -343,8 +342,8 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
                 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;
@@ -370,10 +369,10 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
          * 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
@@ -648,7 +647,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
                 }
                 __kfree_skb(skb);
         } else {
-                sk->sk_prot->enter_memory_pressure();
+                sk->sk_prot->enter_memory_pressure(sk);
                 sk_stream_moderate_sndbuf(sk);
         }
         return NULL;
@@ -1152,7 +1151,7 @@ static void tcp_prequeue_process(struct sock *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 */
@@ -1206,7 +1205,8 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
                 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 */
@@ -1473,7 +1473,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
                         /* __ 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;
                         }
@@ -1484,7 +1484,7 @@ do_prequeue:
                                 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;
                                 }
@@ -1599,7 +1599,7 @@ skip_copy:
                         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;
                         }
@@ -1666,12 +1666,12 @@ void tcp_set_state(struct sock *sk, int state)
         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 &&
@@ -1680,7 +1680,7 @@ void tcp_set_state(struct sock *sk, int state)
                 /* fall through */
         default:
                 if (oldstate==TCP_ESTABLISHED)
-                        TCP_DEC_STATS(TCP_MIB_CURRESTAB);
+                        TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB);
         }
 
         /* Change state AFTER socket is unhashed to avoid closed
@@ -1791,13 +1791,13 @@ void tcp_close(struct sock *sk, long timeout)
          */
         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);
         } 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.
@@ -1869,7 +1869,8 @@ adjudge_to_death:
                 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);
 
@@ -1891,7 +1892,8 @@ adjudge_to_death:
                                        "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);
                 }
         }
 
@@ -2586,12 +2588,69 @@ void __tcp_put_md5sig_pool(void)
 }
 
 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);
+                TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
 
         tcp_set_state(sk, TCP_CLOSE);
         tcp_clear_xmit_timers(sk);
@@ -2620,7 +2679,7 @@ __setup("thash_entries=", set_thash_entries);
 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));
@@ -2689,8 +2748,9 @@ void __init tcp_init(void)
          * 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;
@@ -2727,4 +2787,3 @@ EXPORT_SYMBOL(tcp_splice_read);
 EXPORT_SYMBOL(tcp_sendpage);
 EXPORT_SYMBOL(tcp_setsockopt);
 EXPORT_SYMBOL(tcp_shutdown);
-EXPORT_SYMBOL(tcp_statistics);