Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   menglong8.dong@gmail.com
To:     dsahern@kernel.org
Cc:     rostedt@goodmis.org, mingo@redhat.com, davem@davemloft.net,
        kuba@kernel.org, yoshfuji@linux-ipv6.org, imagedong@tencent.com,
        edumazet@google.com, alobakin@pm.me, cong.wang@bytedance.com,
        paulb@nvidia.com, talalahmad@google.com, keescook@chromium.org,
        ilias.apalodimas@linaro.org, memxor@gmail.com,
        flyingpeng@tencent.com, mengensun@tencent.com,
        daniel@iogearbox.net, yajun.deng@linux.dev, roopa@nvidia.com,
        linux-kernel@vger.kernel.org, netdev@vger.kernel.org
Subject: [PATCH net-next v2 1/3] net: ip: add skb drop reasons for ip egress path
Date:   Fri, 25 Feb 2022 15:17:37 +0800
Message-Id: <20220225071739.1956657-2-imagedong@tencent.com>
In-Reply-To: <20220225071739.1956657-1-imagedong@tencent.com>
References: <20220225071739.1956657-1-imagedong@tencent.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Menglong Dong <imagedong@tencent.com>

Replace kfree_skb() which is used in the packet egress path of IP layer
with kfree_skb_reason(). Functions that are involved include:

__ip_queue_xmit()
ip_finish_output()
ip_mc_finish_output()
ip6_output()
ip6_finish_output()
ip6_finish_output2()

Following new drop reasons are introduced:

SKB_DROP_REASON_IP_OUTNOROUTES
SKB_DROP_REASON_BPF_CGROUP_EGRESS
SKB_DROP_REASON_IPV6DSIABLED
SKB_DROP_REASON_NEIGH_CREATEFAIL

Reviewed-by: Mengen Sun <mengensun@tencent.com>
Reviewed-by: Hao Peng <flyingpeng@tencent.com>
Signed-off-by: Menglong Dong <imagedong@tencent.com>
---
v2:
- introduce SKB_DROP_REASON_NEIGH_CREATEFAIL for neigh entry create
  failure
- replace SKB_DROP_REASON_IP_OUTNOROUTES with
  SKB_DROP_REASON_NEIGH_CREATEFAIL in ip6_finish_output2(), as I think
  it's more suitable
---
 include/linux/skbuff.h     | 9 +++++++++
 include/trace/events/skb.h | 5 +++++
 net/ipv4/ip_output.c       | 8 ++++----
 net/ipv6/ip6_output.c      | 6 +++---
 4 files changed, 21 insertions(+), 7 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index a3e90efe6586..c99b944dc712 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -380,6 +380,15 @@ enum skb_drop_reason {
 					 * the ofo queue, corresponding to
 					 * LINUX_MIB_TCPOFOMERGE
 					 */
+	SKB_DROP_REASON_IP_OUTNOROUTES,	/* route lookup failed */
+	SKB_DROP_REASON_BPF_CGROUP_EGRESS,	/* dropped by
+						 * BPF_PROG_TYPE_CGROUP_SKB
+						 * eBPF program
+						 */
+	SKB_DROP_REASON_IPV6DSIABLED,	/* IPv6 is disabled on the device */
+	SKB_DROP_REASON_NEIGH_CREATEFAIL,	/* failed to create neigh
+						 * entry
+						 */
 	SKB_DROP_REASON_MAX,
 };
 
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 2ab7193313aa..38a6e4e3ff9a 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -37,6 +37,11 @@
 	EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA)		\
 	EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW)	\
 	EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE)		\
+	EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES)	\
+	EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS,			\
+	   BPF_CGROUP_EGRESS)					\
+	EM(SKB_DROP_REASON_IPV6DSIABLED, IPV6DSIABLED)		\
+	EM(SKB_DROP_REASON_NEIGH_CREATEFAIL, NEIGH_CREATEFAIL)	\
 	EMe(SKB_DROP_REASON_MAX, MAX)
 
 #undef EM
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 0c0574eb5f5b..7f618f72fb42 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -233,7 +233,7 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s
 
 	net_dbg_ratelimited("%s: No header cache and no neighbour!\n",
 			    __func__);
-	kfree_skb(skb);
+	kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL);
 	return -EINVAL;
 }
 
@@ -317,7 +317,7 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk
 	case NET_XMIT_CN:
 		return __ip_finish_output(net, sk, skb) ? : ret;
 	default:
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS);
 		return ret;
 	}
 }
@@ -337,7 +337,7 @@ static int ip_mc_finish_output(struct net *net, struct sock *sk,
 	case NET_XMIT_SUCCESS:
 		break;
 	default:
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS);
 		return ret;
 	}
 
@@ -536,7 +536,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
 no_route:
 	rcu_read_unlock();
 	IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
-	kfree_skb(skb);
+	kfree_skb_reason(skb, SKB_DROP_REASON_IP_OUTNOROUTES);
 	return -EHOSTUNREACH;
 }
 EXPORT_SYMBOL(__ip_queue_xmit);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 3286b64ec03d..ac40ce464c64 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -130,7 +130,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 	rcu_read_unlock_bh();
 
 	IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTNOROUTES);
-	kfree_skb(skb);
+	kfree_skb_reason(skb, SKB_DROP_REASON_NEIGH_CREATEFAIL);
 	return -EINVAL;
 }
 
@@ -202,7 +202,7 @@ static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *s
 	case NET_XMIT_CN:
 		return __ip6_finish_output(net, sk, skb) ? : ret;
 	default:
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_BPF_CGROUP_EGRESS);
 		return ret;
 	}
 }
@@ -217,7 +217,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 
 	if (unlikely(idev->cnf.disable_ipv6)) {
 		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_IPV6DSIABLED);
 		return 0;
 	}
 
-- 
2.35.1