Merge branch 'perf/urgent' into perf/core

Conflicts:
	tools/perf/builtin-record.c
	tools/perf/builtin-top.c
	tools/perf/perf.h
	tools/perf/util/top.h

Merge reason: resolve these cherry-picking conflicts.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

12 files changed, 68 insertions, 50 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index aa2a2c7..d183262 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -409,7 +409,7 @@ config INET_TCP_DIAG
 
 config INET_UDP_DIAG
 	tristate "UDP: socket monitoring interface"
-	depends on INET_DIAG
+	depends on INET_DIAG && (IPV6 || IPV6=n)
 	default n
 	---help---
 	  Support for UDP socket monitoring interface used by the ss tool.
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 59402be..63e4989 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -863,7 +863,8 @@ static int arp_process(struct sk_buff *skb)
 			if (addr_type == RTN_UNICAST  &&
 			    (arp_fwd_proxy(in_dev, dev, rt) ||
 			     arp_fwd_pvlan(in_dev, dev, rt, sip, tip) ||
-			     pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) {
+			     (rt->dst.dev != dev &&
+			      pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))) {
 				n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
 				if (n)
 					neigh_release(n);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 6b3ca5b..38673d2 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -65,7 +65,7 @@
    it is infeasible task. The most general solutions would be
    to keep skb->encapsulation counter (sort of local ttl),
    and silently drop packet when it expires. It is a good
-   solution, but it supposes maintaing new variable in ALL
+   solution, but it supposes maintaining new variable in ALL
    skb, even if no tunneling is used.
 
    Current solution: xmit_recursion breaks dead loops. This is a percpu
@@ -91,14 +91,14 @@
 
    One of them is to parse packet trying to detect inner encapsulation
    made by our node. It is difficult or even impossible, especially,
-   taking into account fragmentation. TO be short, tt is not solution at all.
+   taking into account fragmentation. TO be short, ttl is not solution at all.
 
    Current solution: The solution was UNEXPECTEDLY SIMPLE.
    We force DF flag on tunnels with preconfigured hop limit,
    that is ALL. :-) Well, it does not remove the problem completely,
    but exponential growth of network traffic is changed to linear
    (branches, that exceed pmtu are pruned) and tunnel mtu
-   fastly degrades to value <68, where looping stops.
+   rapidly degrades to value <68, where looping stops.
    Yes, it is not good if there exists a router in the loop,
    which does not force DF, even when encapsulating packets have DF set.
    But it is not our problem! Nobody could accuse us, we made
@@ -457,8 +457,8 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
    GRE tunnels with enabled checksum. Tell them "thank you".
 
    Well, I wonder, rfc1812 was written by Cisco employee,
-   what the hell these idiots break standrads established
-   by themself???
+   what the hell these idiots break standards established
+   by themselves???
  */
 
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 1e60f76..42dd1a9 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -573,8 +573,8 @@ void ip_forward_options(struct sk_buff *skb)
 		}
 		if (srrptr + 3 <= srrspace) {
 			opt->is_changed = 1;
-			ip_rt_get_source(&optptr[srrptr-1], skb, rt);
 			ip_hdr(skb)->daddr = opt->nexthop;
+			ip_rt_get_source(&optptr[srrptr-1], skb, rt);
 			optptr[2] = srrptr+4;
 		} else if (net_ratelimit())
 			printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n");
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index aea5a19..b072386 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -630,6 +630,7 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	pr_debug("ping_recvmsg(sk=%p,sk->num=%u)\n", isk, isk->inet_num);
 
+	err = -EOPNOTSUPP;
 	if (flags & MSG_OOB)
 		goto out;
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 4cb9cd2..7a7724d 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -778,7 +778,6 @@ EXPORT_SYMBOL_GPL(net_ipv4_ctl_path);
 static __net_init int ipv4_sysctl_init_net(struct net *net)
 {
 	struct ctl_table *table;
-	unsigned long limit;
 
 	table = ipv4_net_table;
 	if (!net_eq(net, &init_net)) {
@@ -815,11 +814,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 	net->ipv4.sysctl_rt_cache_rebuild_count = 4;
 
 	tcp_init_mem(net);
-	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;
 
 	net->ipv4.ipv4_hdr = register_net_sysctl_table(net,
 			net_ipv4_ctl_path, table);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 06373b4..22ef5f9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1876,6 +1876,20 @@ 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("TCP: too many orphaned sockets\n");
+	if (out_of_socket_memory && net_ratelimit())
+		pr_info("TCP: 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 +2029,7 @@ 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),
@@ -3218,7 +3229,6 @@ __setup("thash_entries=", set_thash_entries);
 
 void tcp_init_mem(struct net *net)
 {
-	/* Set per-socket limits to no more than 1/128 the pressure threshold */
 	unsigned long limit = nr_free_buffer_pages() / 8;
 	limit = max(limit, 128UL);
 	net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3;
@@ -3230,7 +3240,8 @@ void __init tcp_init(void)
 {
 	struct sk_buff *skb = NULL;
 	unsigned long limit;
-	int i, max_share, cnt;
+	int max_share, cnt;
+	unsigned int i;
 	unsigned long jiffy = jiffies;
 
 	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
@@ -3273,7 +3284,7 @@ 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);
@@ -3287,7 +3298,8 @@ void __init tcp_init(void)
 	sysctl_max_syn_backlog = max(128, cnt / 256);
 
 	tcp_init_mem(&init_net);
-	limit = nr_free_buffer_pages() / 8;
+	/* 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);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 976034f..53c8ce40 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1307,25 +1307,26 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
 	return in_sack;
 }
 
-static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk,
-			  struct tcp_sacktag_state *state,
+/* Mark the given newly-SACKed range as such, adjusting counters and hints. */
+static u8 tcp_sacktag_one(struct sock *sk,
+			  struct tcp_sacktag_state *state, u8 sacked,
+			  u32 start_seq, u32 end_seq,
 			  int dup_sack, int pcount)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	u8 sacked = TCP_SKB_CB(skb)->sacked;
 	int fack_count = state->fack_count;
 
 	/* Account D-SACK for retransmitted packet. */
 	if (dup_sack && (sacked & TCPCB_RETRANS)) {
 		if (tp->undo_marker && tp->undo_retrans &&
-		    after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker))
+		    after(end_seq, tp->undo_marker))
 			tp->undo_retrans--;
 		if (sacked & TCPCB_SACKED_ACKED)
 			state->reord = min(fack_count, state->reord);
 	}
 
 	/* Nothing to do; acked frame is about to be dropped (was ACKed). */
-	if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
+	if (!after(end_seq, tp->snd_una))
 		return sacked;
 
 	if (!(sacked & TCPCB_SACKED_ACKED)) {
@@ -1344,13 +1345,13 @@ static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk,
 				/* New sack for not retransmitted frame,
 				 * which was in hole. It is reordering.
 				 */
-				if (before(TCP_SKB_CB(skb)->seq,
+				if (before(start_seq,
 					   tcp_highest_sack_seq(tp)))
 					state->reord = min(fack_count,
 							   state->reord);
 
 				/* SACK enhanced F-RTO (RFC4138; Appendix B) */
-				if (!after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark))
+				if (!after(end_seq, tp->frto_highmark))
 					state->flag |= FLAG_ONLY_ORIG_SACKED;
 			}
 
@@ -1368,8 +1369,7 @@ static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk,
 
 		/* Lost marker hint past SACKed? Tweak RFC3517 cnt */
 		if (!tcp_is_fack(tp) && (tp->lost_skb_hint != NULL) &&
-		    before(TCP_SKB_CB(skb)->seq,
-			   TCP_SKB_CB(tp->lost_skb_hint)->seq))
+		    before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq))
 			tp->lost_cnt_hint += pcount;
 
 		if (fack_count > tp->fackets_out)
@@ -1388,6 +1388,9 @@ static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk,
 	return sacked;
 }
 
+/* Shift newly-SACKed bytes from this skb to the immediately previous
+ * already-SACKed sk_buff. Mark the newly-SACKed bytes as such.
+ */
 static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 			   struct tcp_sacktag_state *state,
 			   unsigned int pcount, int shifted, int mss,
@@ -1395,10 +1398,13 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *prev = tcp_write_queue_prev(sk, skb);
+	u32 start_seq = TCP_SKB_CB(skb)->seq;	/* start of newly-SACKed */
+	u32 end_seq = start_seq + shifted;	/* end of newly-SACKed */
 
 	BUG_ON(!pcount);
 
-	if (skb == tp->lost_skb_hint)
+	/* Adjust hint for FACK. Non-FACK is handled in tcp_sacktag_one(). */
+	if (tcp_is_fack(tp) && (skb == tp->lost_skb_hint))
 		tp->lost_cnt_hint += pcount;
 
 	TCP_SKB_CB(prev)->end_seq += shifted;
@@ -1424,8 +1430,11 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 		skb_shinfo(skb)->gso_type = 0;
 	}
 
-	/* We discard results */
-	tcp_sacktag_one(skb, sk, state, dup_sack, pcount);
+	/* Adjust counters and hints for the newly sacked sequence range but
+	 * discard the return value since prev is already marked.
+	 */
+	tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
+			start_seq, end_seq, dup_sack, pcount);
 
 	/* Difference in this won't matter, both ACKed by the same cumul. ACK */
 	TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS);
@@ -1664,10 +1673,14 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
 			break;
 
 		if (in_sack) {
-			TCP_SKB_CB(skb)->sacked = tcp_sacktag_one(skb, sk,
-								  state,
-								  dup_sack,
-								  tcp_skb_pcount(skb));
+			TCP_SKB_CB(skb)->sacked =
+				tcp_sacktag_one(sk,
+						state,
+						TCP_SKB_CB(skb)->sacked,
+						TCP_SKB_CB(skb)->seq,
+						TCP_SKB_CB(skb)->end_seq,
+						dup_sack,
+						tcp_skb_pcount(skb));
 
 			if (!before(TCP_SKB_CB(skb)->seq,
 				    tcp_highest_sack_seq(tp)))
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 337ba4c..94d683a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -651,6 +651,11 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 				      arg.iov[0].iov_len, IPPROTO_TCP, 0);
 	arg.csumoffset = offsetof(struct tcphdr, check) / 2;
 	arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0;
+	/* When socket is gone, all binding information is lost.
+	 * routing might fail in this case. using iif for oif to
+	 * make sure we can deliver it
+	 */
+	arg.bound_dev_if = sk ? sk->sk_bound_dev_if : inet_iif(skb);
 
 	net = dev_net(skb_dst(skb)->dev);
 	arg.tos = ip_hdr(skb)->tos;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index a516d1e..cd2e072 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -77,10 +77,7 @@ static int tcp_out_of_resources(struct sock *sk, int do_reset)
 	if (sk->sk_err_soft)
 		shift++;
 
-	if (tcp_too_many_orphans(sk, shift)) {
-		if (net_ratelimit())
-			printk(KERN_INFO "Out of socket memory\n");
-
+	if (tcp_check_oom(sk, shift)) {
 		/* Catch exceptional cases, when connection requires reset.
 		 *      1. Last segment was sent recently. */
 		if ((s32)(tcp_time_stamp - tp->lsndtime) <= TCP_TIMEWAIT_LEN ||
diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c
index 6341818..e3db3f9 100644
--- a/net/ipv4/xfrm4_mode_beet.c
+++ b/net/ipv4/xfrm4_mode_beet.c
@@ -110,10 +110,7 @@ static int xfrm4_beet_input(struct xfrm_state *x, struct sk_buff *skb)
 
 	skb_push(skb, sizeof(*iph));
 	skb_reset_network_header(skb);
-
-	memmove(skb->data - skb->mac_len, skb_mac_header(skb),
-		skb->mac_len);
-	skb_set_mac_header(skb, -skb->mac_len);
+	skb_mac_header_rebuild(skb);
 
 	xfrm4_beet_make_header(skb);
 
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 534972e..ed4bf11 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -66,7 +66,6 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 
 static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 {
-	const unsigned char *old_mac;
 	int err = -EINVAL;
 
 	if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP)
@@ -84,10 +83,9 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
 	if (!(x->props.flags & XFRM_STATE_NOECN))
 		ipip_ecn_decapsulate(skb);
 
-	old_mac = skb_mac_header(skb);
-	skb_set_mac_header(skb, -skb->mac_len);
-	memmove(skb_mac_header(skb), old_mac, skb->mac_len);
 	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+
 	err = 0;
 
 out: