net: add rx_sk to trace_kfree_skb

skb does not include enough information to find out receiving
sockets/services and netns/containers on packet drops. In theory
skb->dev tells about netns, but it can get cleared/reused, e.g. by TCP
stack for OOO packet lookup. Similarly, skb->sk often identifies a local
sender, and tells nothing about a receiver.

Allow passing an extra receiving socket to the tracepoint to improve
the visibility on receiving drops.

Signed-off-by: Yan Zhai <yan@cloudflare.com>
Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 15 insertions, 9 deletions

diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 07e0715628ec..b877133cd93a 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -24,13 +24,14 @@ DEFINE_DROP_REASON(FN, FN)
 TRACE_EVENT(kfree_skb,
 
 	TP_PROTO(struct sk_buff *skb, void *location,
-		 enum skb_drop_reason reason),
+		 enum skb_drop_reason reason, struct sock *rx_sk),
 
-	TP_ARGS(skb, location, reason),
+	TP_ARGS(skb, location, reason, rx_sk),
 
 	TP_STRUCT__entry(
 		__field(void *,		skbaddr)
 		__field(void *,		location)
+		__field(void *,		rx_sk)
 		__field(unsigned short,	protocol)
 		__field(enum skb_drop_reason,	reason)
 	),
@@ -38,12 +39,14 @@ TRACE_EVENT(kfree_skb,
 	TP_fast_assign(
 		__entry->skbaddr = skb;
 		__entry->location = location;
+		__entry->rx_sk = rx_sk;
 		__entry->protocol = ntohs(skb->protocol);
 		__entry->reason = reason;
 	),
 
-	TP_printk("skbaddr=%p protocol=%u location=%pS reason: %s",
-		  __entry->skbaddr, __entry->protocol, __entry->location,
+	TP_printk("skbaddr=%p rx_sk=%p protocol=%u location=%pS reason: %s",
+		  __entry->skbaddr, __entry->rx_sk, __entry->protocol,
+		  __entry->location,
 		  __print_symbolic(__entry->reason,
 				   DEFINE_DROP_REASON(FN, FNe)))
 );
diff --git a/net/core/dev.c b/net/core/dev.c
index c361a7b69da8..093d82bf0e28 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5234,7 +5234,7 @@ static __latent_entropy void net_tx_action(struct softirq_action *h)
 				trace_consume_skb(skb, net_tx_action);
 			else
 				trace_kfree_skb(skb, net_tx_action,
-						get_kfree_skb_cb(skb)->reason);
+						get_kfree_skb_cb(skb)->reason, NULL);
 
 			if (skb->fclone != SKB_FCLONE_UNAVAILABLE)
 				__kfree_skb(skb);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 430ed18f8584..2e0ae3328232 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -109,7 +109,8 @@ static u32 net_dm_queue_len = 1000;
 struct net_dm_alert_ops {
 	void (*kfree_skb_probe)(void *ignore, struct sk_buff *skb,
 				void *location,
-				enum skb_drop_reason reason);
+				enum skb_drop_reason reason,
+				struct sock *rx_sk);
 	void (*napi_poll_probe)(void *ignore, struct napi_struct *napi,
 				int work, int budget);
 	void (*work_item_func)(struct work_struct *work);
@@ -264,7 +265,8 @@ out:
 
 static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb,
 				void *location,
-				enum skb_drop_reason reason)
+				enum skb_drop_reason reason,
+				struct sock *rx_sk)
 {
 	trace_drop_common(skb, location);
 }
@@ -491,7 +493,8 @@ static const struct net_dm_alert_ops net_dm_alert_summary_ops = {
 static void net_dm_packet_trace_kfree_skb_hit(void *ignore,
 					      struct sk_buff *skb,
 					      void *location,
-					      enum skb_drop_reason reason)
+					      enum skb_drop_reason reason,
+					      struct sock *rx_sk)
 {
 	ktime_t tstamp = ktime_get_real();
 	struct per_cpu_dm_data *data;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c8ac79851cd6..8973db4eabd4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1203,7 +1203,7 @@ bool __kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason)
 	if (reason == SKB_CONSUMED)
 		trace_consume_skb(skb, __builtin_return_address(0));
 	else
-		trace_kfree_skb(skb, __builtin_return_address(0), reason);
+		trace_kfree_skb(skb, __builtin_return_address(0), reason, NULL);
 	return true;
 }