Merge branch 'tcp_drop_reason'

Menglong Dong says:

====================
net: add skb drop reasons to TCP packet receive

In the commit c504e5c2f964 ("net: skb: introduce kfree_skb_reason()"),
we added the support of reporting the reasons of skb drops to kfree_skb
tracepoint. And in this series patches, reasons for skb drops are added
to TCP layer (both TCPv4 and TCPv6 are considered).
Following functions are processed:

tcp_v4_rcv()
tcp_v6_rcv()
tcp_v4_inbound_md5_hash()
tcp_v6_inbound_md5_hash()
tcp_add_backlog()
tcp_v4_do_rcv()
tcp_v6_do_rcv()
tcp_rcv_established()
tcp_data_queue()
tcp_data_queue_ofo()

The functions we handled are mostly for packet ingress, as skb drops
hardly happens in the egress path of TCP layer. However, it's a little
complex for TCP state processing, as I find that it's hard to report skb
drop reasons to where it is freed. For example, when skb is dropped in
tcp_rcv_state_process(), the reason can be caused by the call of
tcp_v4_conn_request(), and it's hard to return a drop reason from
tcp_v4_conn_request(). So such cases are skipped  for this moment.

Following new drop reasons are introduced (what they mean can be see
in the document for them):

/* SKB_DROP_REASON_TCP_MD5* corresponding to LINUX_MIB_TCPMD5* */
SKB_DROP_REASON_TCP_MD5NOTFOUND
SKB_DROP_REASON_TCP_MD5UNEXPECTED
SKB_DROP_REASON_TCP_MD5FAILURE
SKB_DROP_REASON_SOCKET_BACKLOG
SKB_DROP_REASON_TCP_FLAGS
SKB_DROP_REASON_TCP_ZEROWINDOW
SKB_DROP_REASON_TCP_OLD_DATA
SKB_DROP_REASON_TCP_OVERWINDOW
/* corresponding to LINUX_MIB_TCPOFOMERGE */
SKB_DROP_REASON_TCP_OFOMERGE

Here is a example to get TCP packet drop reasons from ftrace:

$ echo 1 > /sys/kernel/debug/tracing/events/skb/kfree_skb/enable
$ cat /sys/kernel/debug/tracing/trace
$ <idle>-0       [036] ..s1.   647.428165: kfree_skb: skbaddr=000000004d037db6 protocol=2048 location=0000000074cd1243 reason: NO_SOCKET
$ <idle>-0       [020] ..s2.   639.676674: kfree_skb: skbaddr=00000000bcbfa42d protocol=2048 location=00000000bfe89d35 reason: PROTO_MEM

From the reason 'PROTO_MEM' we can know that the skb is dropped because
the memory configured in net.ipv4.tcp_mem is up to the limition.

Changes since v2:
- remove the 'inline' of tcp_drop() in the 1th patch, as Jakub
  suggested

Changes since v1:
- enrich the document for this series patches in the cover letter,
  as Eric suggested
- fix compile warning report by Jakub in the 6th patch
- let NO_SOCKET trump the XFRM failure in the 2th and 3th patches
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 32 insertions, 10 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 92e65d56dc2c..2088f93fa37b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4684,10 +4684,16 @@ static bool tcp_ooo_try_coalesce(struct sock *sk,
 	return res;
 }
 
-static void tcp_drop(struct sock *sk, struct sk_buff *skb)
+static void tcp_drop_reason(struct sock *sk, struct sk_buff *skb,
+			    enum skb_drop_reason reason)
 {
 	sk_drops_add(sk, skb);
-	__kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
+}
+
+static void tcp_drop(struct sock *sk, struct sk_buff *skb)
+{
+	tcp_drop_reason(sk, skb, SKB_DROP_REASON_NOT_SPECIFIED);
 }
 
 /* This one checks to see if we can put data from the
@@ -4773,7 +4779,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);
 		sk->sk_data_ready(sk);
-		tcp_drop(sk, skb);
+		tcp_drop_reason(sk, skb, SKB_DROP_REASON_PROTO_MEM);
 		return;
 	}
 
@@ -4836,7 +4842,8 @@ coalesce_done:
 				/* All the bits are present. Drop. */
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPOFOMERGE);
-				tcp_drop(sk, skb);
+				tcp_drop_reason(sk, skb,
+						SKB_DROP_REASON_TCP_OFOMERGE);
 				skb = NULL;
 				tcp_dsack_set(sk, seq, end_seq);
 				goto add_sack;
@@ -4855,7 +4862,8 @@ coalesce_done:
 						 TCP_SKB_CB(skb1)->end_seq);
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPOFOMERGE);
-				tcp_drop(sk, skb1);
+				tcp_drop_reason(sk, skb1,
+						SKB_DROP_REASON_TCP_OFOMERGE);
 				goto merge_right;
 			}
 		} else if (tcp_ooo_try_coalesce(sk, skb1,
@@ -4883,7 +4891,7 @@ merge_right:
 		tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq,
 				 TCP_SKB_CB(skb1)->end_seq);
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE);
-		tcp_drop(sk, skb1);
+		tcp_drop_reason(sk, skb1, SKB_DROP_REASON_TCP_OFOMERGE);
 	}
 	/* If there is no skb after us, we are the last_skb ! */
 	if (!skb1)
@@ -4982,6 +4990,7 @@ void tcp_data_ready(struct sock *sk)
 static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	enum skb_drop_reason reason;
 	bool fragstolen;
 	int eaten;
 
@@ -5000,6 +5009,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	skb_dst_drop(skb);
 	__skb_pull(skb, tcp_hdr(skb)->doff * 4);
 
+	reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	tp->rx_opt.dsack = 0;
 
 	/*  Queue data for delivery to the user.
@@ -5008,6 +5018,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	 */
 	if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) {
 		if (tcp_receive_window(tp) == 0) {
+			reason = SKB_DROP_REASON_TCP_ZEROWINDOW;
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP);
 			goto out_of_window;
 		}
@@ -5017,6 +5028,7 @@ queue_and_out:
 		if (skb_queue_len(&sk->sk_receive_queue) == 0)
 			sk_forced_mem_schedule(sk, skb->truesize);
 		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
+			reason = SKB_DROP_REASON_PROTO_MEM;
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
 			sk->sk_data_ready(sk);
 			goto drop;
@@ -5053,6 +5065,7 @@ queue_and_out:
 	if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) {
 		tcp_rcv_spurious_retrans(sk, skb);
 		/* A retransmit, 2nd most common case.  Force an immediate ack. */
+		reason = SKB_DROP_REASON_TCP_OLD_DATA;
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
 		tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
 
@@ -5060,13 +5073,16 @@ out_of_window:
 		tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
 		inet_csk_schedule_ack(sk);
 drop:
-		tcp_drop(sk, skb);
+		tcp_drop_reason(sk, skb, reason);
 		return;
 	}
 
 	/* Out of window. F.e. zero window probe. */
-	if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt + tcp_receive_window(tp)))
+	if (!before(TCP_SKB_CB(skb)->seq,
+		    tp->rcv_nxt + tcp_receive_window(tp))) {
+		reason = SKB_DROP_REASON_TCP_OVERWINDOW;
 		goto out_of_window;
+	}
 
 	if (before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
 		/* Partial packet, seq < rcv_next < end_seq */
@@ -5076,6 +5092,7 @@ drop:
 		 * remembering D-SACK for its head made in previous line.
 		 */
 		if (!tcp_receive_window(tp)) {
+			reason = SKB_DROP_REASON_TCP_ZEROWINDOW;
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP);
 			goto out_of_window;
 		}
@@ -5781,6 +5798,7 @@ discard:
  */
 void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 {
+	enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	const struct tcphdr *th = (const struct tcphdr *)skb->data;
 	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned int len = skb->len;
@@ -5869,6 +5887,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 				tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr;
 				return;
 			} else { /* Header too small */
+				reason = SKB_DROP_REASON_PKT_TOO_SMALL;
 				TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
 				goto discard;
 			}
@@ -5924,8 +5943,10 @@ slow_path:
 	if (len < (th->doff << 2) || tcp_checksum_complete(skb))
 		goto csum_error;
 
-	if (!th->ack && !th->rst && !th->syn)
+	if (!th->ack && !th->rst && !th->syn) {
+		reason = SKB_DROP_REASON_TCP_FLAGS;
 		goto discard;
+	}
 
 	/*
 	 *	Standard slow path.
@@ -5951,12 +5972,13 @@ step5:
 	return;
 
 csum_error:
+	reason = SKB_DROP_REASON_TCP_CSUM;
 	trace_tcp_bad_csum(skb);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
 
 discard:
-	tcp_drop(sk, skb);
+	tcp_drop_reason(sk, skb, reason);
 }
 EXPORT_SYMBOL(tcp_rcv_established);