From: jony-one <yan2228598786@gmail.com>
To: kuba@kernel.org
Cc: edumazet@google.com, rostedt@goodmis.org, mingo@redhat.com,
davem@davemloft.net, yoshfuji@linux-ipv6.org, dsahern@kernel.org,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
hengqi.chen@gmail.com, yhs@fb.com,
jony-one <yan2228598786@gmail.com>
Subject: [PATCH] net/mlx4: tcp_drop replace of tcp_drop_new
Date: Sat, 21 Aug 2021 08:53:27 -0700 [thread overview]
Message-ID: <20210821155327.251284-1-yan2228598786@gmail.com> (raw)
We never know why we are deleting a tcp packet when we delete it,
and the tcp_drop_new() function can effectively solve this problem.
The tcp_drop_new() will learn from the specified status code why the
packet was deleted, and the caller from whom the packet was deleted.
The kernel should be a little more open to data that is about to be
destroyed and useless, and users should be able to keep track of it.
Signed-off-by: jony-one <yan2228598786@gmail.com>
---
include/trace/events/tcp.h | 51 ++++++++++++++++++++++++++++++++++++++
net/ipv4/tcp_input.c | 29 ++++++++++++++--------
2 files changed, 69 insertions(+), 11 deletions(-)
diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index 521059d8d..5a0478440 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -371,6 +371,57 @@ DEFINE_EVENT(tcp_event_skb, tcp_bad_csum,
TP_ARGS(skb)
);
+/*
+ * tcp event whit argument sk, skb, reason
+ */
+TRACE_EVENT(tcp_drop_new,
+
+ TP_PROTO(struct sock *sk, struct sk_buff *skb, const char *reason),
+
+ TP_ARGS(sk, skb, reason),
+
+ TP_STRUCT__entry(
+ __field(const void *, skbaddr)
+ __field(const void *, skaddr)
+ __string(reason, reason)
+ __field(int, state)
+ __field(__u16, sport)
+ __field(__u16, dport)
+ __array(__u8, saddr, 4)
+ __array(__u8, daddr, 4)
+ __array(__u8, saddr_v6, 16)
+ __array(__u8, daddr_v6, 16)
+ ),
+
+ TP_fast_assign(
+ struct inet_sock *inet = inet_sk(sk);
+ __be32 *p32;
+
+ __assign_str(reason, reason);
+
+ __entry->skbaddr = skb;
+ __entry->skaddr = sk;
+ __entry->state = sk->sk_state;
+
+ __entry->sport = ntohs(inet->inet_sport);
+ __entry->dport = ntohs(inet->inet_dport);
+
+ p32 = (__be32 *) __entry->saddr;
+ *p32 = inet->inet_saddr;
+
+ p32 = (__be32 *) __entry->daddr;
+ *p32 = inet->inet_daddr;
+
+ TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr,
+ sk->sk_v6_rcv_saddr, sk->sk_v6_daddr);
+ ),
+
+ TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s reason=%s",
+ __entry->sport, __entry->dport, __entry->saddr, __entry->daddr,
+ __entry->saddr_v6, __entry->daddr_v6,
+ show_tcp_state_name(__entry->state), __get_str(reason))
+);
+
#endif /* _TRACE_TCP_H */
/* This part must be outside protection */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 149ceb5c9..988989e25 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4649,6 +4649,13 @@ static void tcp_drop(struct sock *sk, struct sk_buff *skb)
__kfree_skb(skb);
}
+static void tcp_drop_new(struct sock *sk, struct sk_buff *skb, const char *reason)
+{
+ trace_tcp_drop_new(sk, skb, reason);
+ sk_drops_add(sk, skb);
+ __kfree_skb(skb);
+}
+
/* This one checks to see if we can put data from the
* out_of_order queue into the receive_queue.
*/
@@ -4676,7 +4683,7 @@ static void tcp_ofo_queue(struct sock *sk)
rb_erase(&skb->rbnode, &tp->out_of_order_queue);
if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) {
- tcp_drop(sk, skb);
+ tcp_drop_new(sk, skb, __func__);
continue;
}
@@ -4732,7 +4739,7 @@ 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_new(sk, skb, __func__);
return;
}
@@ -4795,7 +4802,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
/* All the bits are present. Drop. */
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPOFOMERGE);
- tcp_drop(sk, skb);
+ tcp_drop_new(sk, skb, __func__);
skb = NULL;
tcp_dsack_set(sk, seq, end_seq);
goto add_sack;
@@ -4814,7 +4821,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
TCP_SKB_CB(skb1)->end_seq);
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPOFOMERGE);
- tcp_drop(sk, skb1);
+ tcp_drop_new(sk, skb1, __func__);
goto merge_right;
}
} else if (tcp_ooo_try_coalesce(sk, skb1,
@@ -4842,7 +4849,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
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_new(sk, skb1, __func__);
}
/* If there is no skb after us, we are the last_skb ! */
if (!skb1)
@@ -5019,7 +5026,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
inet_csk_schedule_ack(sk);
drop:
- tcp_drop(sk, skb);
+ tcp_drop_new(sk, skb, __func__);
return;
}
@@ -5276,7 +5283,7 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
prev = rb_prev(node);
rb_erase(node, &tp->out_of_order_queue);
goal -= rb_to_skb(node)->truesize;
- tcp_drop(sk, rb_to_skb(node));
+ tcp_drop_new(sk, rb_to_skb(node), __func__);
if (!prev || goal <= 0) {
sk_mem_reclaim(sk);
if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
@@ -5701,7 +5708,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
return true;
discard:
- tcp_drop(sk, skb);
+ tcp_drop_new(sk, skb, __func__);
return false;
}
@@ -5905,7 +5912,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
discard:
- tcp_drop(sk, skb);
+ tcp_drop_new(sk, skb, __func__);
}
EXPORT_SYMBOL(tcp_rcv_established);
@@ -6196,7 +6203,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
TCP_DELACK_MAX, TCP_RTO_MAX);
discard:
- tcp_drop(sk, skb);
+ tcp_drop_new(sk, skb, __func__);
return 0;
} else {
tcp_send_ack(sk);
@@ -6568,7 +6575,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
if (!queued) {
discard:
- tcp_drop(sk, skb);
+ tcp_drop_new(sk, skb, __func__);
}
return 0;
}
--
2.25.1
next reply other threads:[~2021-08-21 15:54 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-21 15:53 jony-one [this message]
2021-08-23 0:21 ` Yonghong Song
2021-08-23 19:06 ` Cong Wang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210821155327.251284-1-yan2228598786@gmail.com \
--to=yan2228598786@gmail.com \
--cc=davem@davemloft.net \
--cc=dsahern@kernel.org \
--cc=edumazet@google.com \
--cc=hengqi.chen@gmail.com \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=rostedt@goodmis.org \
--cc=yhs@fb.com \
--cc=yoshfuji@linux-ipv6.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®