Merge tag 'v3.4' with SCSI updates, needed for subsequent firewire-sbp2 changes

Linux 3.4

8 files changed, 53 insertions, 27 deletions

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index bce36f1a37b4..30b88d7b4bd6 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1370,6 +1370,8 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
 
 			if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
 				continue;
+			if (fi->fib_dead)
+				continue;
 			if (fa->fa_info->fib_scope < flp->flowi4_scope)
 				continue;
 			fib_alias_accessed(fa);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 8d25a1c557eb..8f8db724bfaf 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -141,7 +141,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 			goto rtattr_failure;
 
 	if (icsk == NULL) {
-		r->idiag_rqueue = r->idiag_wqueue = 0;
+		handler->idiag_get_info(sk, r, NULL);
 		goto out;
 	}
 
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index de9da21113a1..cf73cc70ed2d 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -74,16 +74,24 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 
 	iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
 	if (iph == NULL)
-		return -NF_DROP;
+		return -NF_ACCEPT;
 
 	/* Conntrack defragments packets, we might still see fragments
 	 * inside ICMP packets though. */
 	if (iph->frag_off & htons(IP_OFFSET))
-		return -NF_DROP;
+		return -NF_ACCEPT;
 
 	*dataoff = nhoff + (iph->ihl << 2);
 	*protonum = iph->protocol;
 
+	/* Check bogus IP headers */
+	if (*dataoff > skb->len) {
+		pr_debug("nf_conntrack_ipv4: bogus IPv4 packet: "
+			 "nhoff %u, ihl %u, skblen %u\n",
+			 nhoff, iph->ihl << 2, skb->len);
+		return -NF_ACCEPT;
+	}
+
 	return NF_ACCEPT;
 }
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5d54ed30e821..6589e11d57b6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -701,11 +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);
@@ -850,8 +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;
@@ -995,10 +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;
@@ -1452,7 +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);
@@ -1667,7 +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(
@@ -3243,7 +3242,7 @@ void __init tcp_init(void)
 {
 	struct sk_buff *skb = NULL;
 	unsigned long limit;
-	int max_share, cnt;
+	int max_rshare, max_wshare, cnt;
 	unsigned int i;
 	unsigned long jiffy = jiffies;
 
@@ -3302,17 +3301,17 @@ void __init tcp_init(void)
 
 	tcp_init_mem(&init_net);
 	/* Set per-socket limits to no more than 1/128 the pressure threshold */
-	limit = nr_free_buffer_pages() << (PAGE_SHIFT - 10);
-	limit = max(limit, 128UL);
-	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);
 
 	pr_info("Hash tables configured (established %u bind %u)\n",
 		tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e886e2f7fa8d..257b61789eeb 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -85,7 +85,7 @@ int sysctl_tcp_ecn __read_mostly = 2;
 EXPORT_SYMBOL(sysctl_tcp_ecn);
 int sysctl_tcp_dsack __read_mostly = 1;
 int sysctl_tcp_app_win __read_mostly = 31;
-int sysctl_tcp_adv_win_scale __read_mostly = 2;
+int sysctl_tcp_adv_win_scale __read_mostly = 1;
 EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
 
 int sysctl_tcp_stdurg __read_mostly;
@@ -335,6 +335,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 			incr = __tcp_grow_window(sk, skb);
 
 		if (incr) {
+			incr = max_t(int, incr, 2 * skb->len);
 			tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr,
 					       tp->window_clamp);
 			inet_csk(sk)->icsk_ack.quick |= 1;
@@ -474,8 +475,11 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
 		if (!win_dep) {
 			m -= (new_sample >> 3);
 			new_sample += m;
-		} else if (m < new_sample)
-			new_sample = m << 3;
+		} else {
+			m <<= 3;
+			if (m < new_sample)
+				new_sample = m;
+		}
 	} else {
 		/* No previous measure. */
 		new_sample = m << 3;
@@ -491,7 +495,7 @@ static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp)
 		goto new_measure;
 	if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq))
 		return;
-	tcp_rcv_rtt_update(tp, jiffies - tp->rcv_rtt_est.time, 1);
+	tcp_rcv_rtt_update(tp, tcp_time_stamp - tp->rcv_rtt_est.time, 1);
 
 new_measure:
 	tp->rcv_rtt_est.seq = tp->rcv_nxt + tp->rcv_wnd;
@@ -2864,11 +2868,14 @@ static inline void tcp_complete_cwr(struct sock *sk)
 
 	/* Do not moderate cwnd if it's already undone in cwr or recovery. */
 	if (tp->undo_marker) {
-		if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR)
+		if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR) {
 			tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
-		else /* PRR */
+			tp->snd_cwnd_stamp = tcp_time_stamp;
+		} else if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH) {
+			/* PRR algorithm. */
 			tp->snd_cwnd = tp->snd_ssthresh;
-		tp->snd_cwnd_stamp = tcp_time_stamp;
+			tp->snd_cwnd_stamp = tcp_time_stamp;
+		}
 	}
 	tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR);
 }
@@ -5225,7 +5232,7 @@ static int tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb,
 		return 0;
 
 	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 && skb_csum_unnecessary(skb)) {
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3a25cf743f8b..0cb86ceb652f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1730,7 +1730,7 @@ process:
 #ifdef CONFIG_NET_DMA
 		struct tcp_sock *tp = tcp_sk(sk);
 		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)
 			ret = tcp_v4_do_rcv(sk, skb);
 		else
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 364784a91939..7ac6423117ad 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1096,6 +1096,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 	eat = min_t(int, len, skb_headlen(skb));
 	if (eat) {
 		__skb_pull(skb, eat);
+		skb->avail_size -= eat;
 		len -= eat;
 		if (!len)
 			return;
@@ -2060,7 +2061,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
 		/* Punt if not enough space exists in the first SKB for
 		 * the data in the second
 		 */
-		if (skb->len > skb_tailroom(to))
+		if (skb->len > skb_availroom(to))
 			break;
 
 		if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp)))
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 8a949f19deb6..a7f86a3cd502 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -146,9 +146,17 @@ static int udp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
 	return udp_dump_one(&udp_table, in_skb, nlh, req);
 }
 
+static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
+		void *info)
+{
+	r->idiag_rqueue = sk_rmem_alloc_get(sk);
+	r->idiag_wqueue = sk_wmem_alloc_get(sk);
+}
+
 static const struct inet_diag_handler udp_diag_handler = {
 	.dump		 = udp_diag_dump,
 	.dump_one	 = udp_diag_dump_one,
+	.idiag_get_info  = udp_diag_get_info,
 	.idiag_type	 = IPPROTO_UDP,
 };
 
@@ -167,6 +175,7 @@ static int udplite_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *
 static const struct inet_diag_handler udplite_diag_handler = {
 	.dump		 = udplite_diag_dump,
 	.dump_one	 = udplite_diag_dump_one,
+	.idiag_get_info  = udp_diag_get_info,
 	.idiag_type	 = IPPROTO_UDPLITE,
 };