X-Git-Url: https://git.openpandora.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=net%2Fipv4%2Ftcp.c;h=a803bfc22fd1b35c099caa68fbf5dedd5d74b10f;hb=a0eee8681a9bc21d3f83260a8ceb3fa30236b189;hp=34f5db1e1c8b85110192c881e17c7fd11c01d633;hpb=c125d5e846894043361c0c89c1140be8fd6600b7;p=pandora-kernel.git

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 34f5db1e1c8b..a803bfc22fd1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -481,14 +481,12 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 			 !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. */
-			skb = skb_peek_tail(&sk->sk_receive_queue);
-			if (answ && skb)
-				answ -= tcp_hdr(skb)->fin;
+			/* Subtract 1, if FIN was received */
+			if (answ && sock_flag(sk, SOCK_DONE))
+				answ--;
 		} else
 			answ = tp->urg_seq - tp->copied_seq;
 		release_sock(sk);
@@ -661,6 +659,12 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 				ret = -EAGAIN;
 				break;
 			}
+			/* if __tcp_splice_read() got nothing while we have
+			 * an skb in receive queue, we do not want to loop.
+			 * This might happen with URG data.
+			 */
+			if (!skb_queue_empty(&sk->sk_receive_queue))
+				break;
 			sk_wait_data(sk, &timeo);
 			if (signal_pending(current)) {
 				ret = sock_intr_errno(timeo);
@@ -701,11 +705,12 @@ 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->reserved_tailroom = skb->end - skb->tail - size;
 			return skb;
 		}
 		__kfree_skb(skb);
@@ -850,8 +855,7 @@ 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;
@@ -860,7 +864,7 @@ wait_for_memory:
 	}
 
 out:
-	if (copied)
+	if (copied && !(flags & MSG_SENDPAGE_NOTLAST))
 		tcp_push(sk, flags, mss_now, tp->nonagle);
 	return copied;
 
@@ -995,10 +999,9 @@ 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;
@@ -1588,8 +1591,14 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		}
 
 #ifdef CONFIG_NET_DMA
-		if (tp->ucopy.dma_chan)
-			dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+		if (tp->ucopy.dma_chan) {
+			if (tp->rcv_wnd == 0 &&
+			    !skb_queue_empty(&sk->sk_async_wait_queue)) {
+				tcp_service_net_dma(sk, true);
+				tcp_cleanup_rbuf(sk, copied);
+			} else
+				dma_async_memcpy_issue_pending(tp->ucopy.dma_chan);
+		}
 #endif
 		if (copied >= target) {
 			/* Do not sleep, just process backlog. */
@@ -2097,6 +2106,10 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tcp_clear_retrans(tp);
 	inet_csk_delack_init(sk);
+	/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
+	 * issue in __tcp_select_window()
+	 */
+	icsk->icsk_ack.rcv_mss = TCP_MIN_MSS;
 	tcp_init_send_head(sk);
 	memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
 	__sk_dst_reset(sk);
@@ -2392,7 +2405,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		/* Cap the max timeout in ms TCP will retry/retrans
 		 * before giving up and aborting (ETIMEDOUT) a connection.
 		 */
-		icsk->icsk_user_timeout = msecs_to_jiffies(val);
+		if (val < 0)
+			err = -EINVAL;
+		else
+			icsk->icsk_user_timeout = msecs_to_jiffies(val);
 		break;
 	default:
 		err = -ENOPROTOOPT;
@@ -2855,104 +2871,42 @@ int tcp_gro_complete(struct sk_buff *skb)
 EXPORT_SYMBOL(tcp_gro_complete);
 
 #ifdef CONFIG_TCP_MD5SIG
-static unsigned long tcp_md5sig_users;
-static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool;
-static DEFINE_SPINLOCK(tcp_md5sig_pool_lock);
+static DEFINE_PER_CPU(struct tcp_md5sig_pool, tcp_md5sig_pool);
+static DEFINE_MUTEX(tcp_md5sig_mutex);
+static bool tcp_md5sig_pool_populated = false;
 
-static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool)
+static void __tcp_alloc_md5sig_pool(void)
 {
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
-		struct tcp_md5sig_pool *p = per_cpu_ptr(pool, cpu);
-
-		if (p->md5_desc.tfm)
-			crypto_free_hash(p->md5_desc.tfm);
-	}
-	free_percpu(pool);
-}
-
-void tcp_free_md5sig_pool(void)
-{
-	struct tcp_md5sig_pool __percpu *pool = NULL;
+		if (!per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm) {
+			struct crypto_hash *hash;
 
-	spin_lock_bh(&tcp_md5sig_pool_lock);
-	if (--tcp_md5sig_users == 0) {
-		pool = tcp_md5sig_pool;
-		tcp_md5sig_pool = NULL;
+			hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
+			if (IS_ERR_OR_NULL(hash))
+				return;
+			per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm = hash;
+		}
 	}
-	spin_unlock_bh(&tcp_md5sig_pool_lock);
-	if (pool)
-		__tcp_free_md5sig_pool(pool);
+	/* before setting tcp_md5sig_pool_populated, we must commit all writes
+	 * to memory. See smp_rmb() in tcp_get_md5sig_pool()
+	 */
+	smp_wmb();
+	tcp_md5sig_pool_populated = true;
 }
-EXPORT_SYMBOL(tcp_free_md5sig_pool);
 
-static struct tcp_md5sig_pool __percpu *
-__tcp_alloc_md5sig_pool(struct sock *sk)
+bool tcp_alloc_md5sig_pool(void)
 {
-	int cpu;
-	struct tcp_md5sig_pool __percpu *pool;
+	if (unlikely(!tcp_md5sig_pool_populated)) {
+		mutex_lock(&tcp_md5sig_mutex);
 
-	pool = alloc_percpu(struct tcp_md5sig_pool);
-	if (!pool)
-		return NULL;
+		if (!tcp_md5sig_pool_populated)
+			__tcp_alloc_md5sig_pool();
 
-	for_each_possible_cpu(cpu) {
-		struct crypto_hash *hash;
-
-		hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
-		if (!hash || IS_ERR(hash))
-			goto out_free;
-
-		per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash;
-	}
-	return pool;
-out_free:
-	__tcp_free_md5sig_pool(pool);
-	return NULL;
-}
-
-struct tcp_md5sig_pool __percpu *tcp_alloc_md5sig_pool(struct sock *sk)
-{
-	struct tcp_md5sig_pool __percpu *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 __percpu *p;
-
-		p = __tcp_alloc_md5sig_pool(sk);
-		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);
-		}
+		mutex_unlock(&tcp_md5sig_mutex);
 	}
-	return pool;
+	return tcp_md5sig_pool_populated;
 }
 EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
 
@@ -2966,31 +2920,18 @@ EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
  */
 struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
 {
-	struct tcp_md5sig_pool __percpu *p;
-
 	local_bh_disable();
 
-	spin_lock(&tcp_md5sig_pool_lock);
-	p = tcp_md5sig_pool;
-	if (p)
-		tcp_md5sig_users++;
-	spin_unlock(&tcp_md5sig_pool_lock);
-
-	if (p)
-		return this_cpu_ptr(p);
-
+	if (tcp_md5sig_pool_populated) {
+		/* coupled with smp_wmb() in __tcp_alloc_md5sig_pool() */
+		smp_rmb();
+		return this_cpu_ptr(&tcp_md5sig_pool);
+	}
 	local_bh_enable();
 	return NULL;
 }
 EXPORT_SYMBOL(tcp_get_md5sig_pool);
 
-void tcp_put_md5sig_pool(void)
-{
-	local_bh_enable();
-	tcp_free_md5sig_pool();
-}
-EXPORT_SYMBOL(tcp_put_md5sig_pool);
-
 int tcp_md5_hash_header(struct tcp_md5sig_pool *hp,
 			const struct tcphdr *th)
 {
@@ -3029,8 +2970,11 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
 
 	for (i = 0; i < shi->nr_frags; ++i) {
 		const struct skb_frag_struct *f = &shi->frags[i];
-		struct page *page = skb_frag_page(f);
-		sg_set_page(&sg, page, skb_frag_size(f), f->page_offset);
+		unsigned int offset = f->page_offset;
+		struct page *page = skb_frag_page(f) + (offset >> PAGE_SHIFT);
+
+		sg_set_page(&sg, page, skb_frag_size(f),
+			    offset_in_page(offset));
 		if (crypto_hash_update(desc, &sg, skb_frag_size(f)))
 			return 1;
 	}
@@ -3216,9 +3160,10 @@ void __init tcp_init(void)
 {
 	struct sk_buff *skb = NULL;
 	unsigned long limit;
-	int i, max_share, cnt;
+	int i, max_rshare, max_wshare, cnt;
 	unsigned long jiffy = jiffies;
 
+	BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE);
 	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
 
 	percpu_counter_init(&tcp_sockets_allocated, 0);
@@ -3280,15 +3225,16 @@ void __init tcp_init(void)
 
 	/* 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);
+	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",