All of lore.kernel.org
 help / color / mirror / Atom feed
From: Joe Stringer <joe@wand.net.nz>
To: bpf@vger.kernel.org
Cc: netdev@vger.kernel.org, daniel@iogearbox.net, ast@kernel.org,
	eric.dumazet@gmail.com, lmb@cloudflare.com, kafai@fb.com
Subject: [PATCHv2 bpf-next 3/5] net: Track socket refcounts in skb_steal_sock()
Date: Tue, 24 Mar 2020 22:57:43 -0700	[thread overview]
Message-ID: <20200325055745.10710-4-joe@wand.net.nz> (raw)
In-Reply-To: <20200325055745.10710-1-joe@wand.net.nz>

Refactor the UDP/TCP handlers slightly to allow skb_steal_sock() to make
the determination of whether the socket is reference counted in the case
where it is prefetched by earlier logic such as early_demux or
dst_sk_prefetch.

Signed-off-by: Joe Stringer <joe@wand.net.nz>
---
v2: Initial version
---
 include/net/inet6_hashtables.h |  3 +--
 include/net/inet_hashtables.h  |  3 +--
 include/net/sock.h             | 10 +++++++++-
 net/ipv4/udp.c                 |  6 ++++--
 net/ipv6/udp.c                 |  9 ++++++---
 5 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index fe96bf247aac..81b965953036 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -85,9 +85,8 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
 					      int iif, int sdif,
 					      bool *refcounted)
 {
-	struct sock *sk = skb_steal_sock(skb);
+	struct sock *sk = skb_steal_sock(skb, refcounted);
 
-	*refcounted = true;
 	if (sk)
 		return sk;
 
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index d0019d3395cf..ad64ba6a057f 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -379,10 +379,9 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
 					     const int sdif,
 					     bool *refcounted)
 {
-	struct sock *sk = skb_steal_sock(skb);
+	struct sock *sk = skb_steal_sock(skb, refcounted);
 	const struct iphdr *iph = ip_hdr(skb);
 
-	*refcounted = true;
 	if (sk)
 		return sk;
 
diff --git a/include/net/sock.h b/include/net/sock.h
index 2613d21a667a..1ca2e808cb8e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2533,15 +2533,23 @@ skb_sk_is_prefetched(struct sk_buff *skb)
 	return skb->destructor == sock_pfree;
 }
 
-static inline struct sock *skb_steal_sock(struct sk_buff *skb)
+/**
+ * skb_steal_sock
+ * @skb to steal the socket from
+ * @refcounted is set to true if the socket is reference-counted
+ */
+static inline struct sock *
+skb_steal_sock(struct sk_buff *skb, bool *refcounted)
 {
 	if (skb->sk) {
 		struct sock *sk = skb->sk;
 
+		*refcounted = true;
 		skb->destructor = NULL;
 		skb->sk = NULL;
 		return sk;
 	}
+	*refcounted = false;
 	return NULL;
 }
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 2633fc231593..b4035021bbd3 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2288,6 +2288,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	struct rtable *rt = skb_rtable(skb);
 	__be32 saddr, daddr;
 	struct net *net = dev_net(skb->dev);
+	bool refcounted;
 
 	/*
 	 *  Validate the packet.
@@ -2313,7 +2314,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (udp4_csum_init(skb, uh, proto))
 		goto csum_error;
 
-	sk = skb_steal_sock(skb);
+	sk = skb_steal_sock(skb, &refcounted);
 	if (sk) {
 		struct dst_entry *dst = skb_dst(skb);
 		int ret;
@@ -2322,7 +2323,8 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 			udp_sk_rx_dst_set(sk, dst);
 
 		ret = udp_unicast_rcv_skb(sk, skb, uh);
-		sock_put(sk);
+		if (refcounted)
+			sock_put(sk);
 		return ret;
 	}
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 5dc439a391fe..7d4151747340 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -843,6 +843,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	struct net *net = dev_net(skb->dev);
 	struct udphdr *uh;
 	struct sock *sk;
+	bool refcounted;
 	u32 ulen = 0;
 
 	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
@@ -879,7 +880,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		goto csum_error;
 
 	/* Check if the socket is already available, e.g. due to early demux */
-	sk = skb_steal_sock(skb);
+	sk = skb_steal_sock(skb, &refcounted);
 	if (sk) {
 		struct dst_entry *dst = skb_dst(skb);
 		int ret;
@@ -888,12 +889,14 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 			udp6_sk_rx_dst_set(sk, dst);
 
 		if (!uh->check && !udp_sk(sk)->no_check6_rx) {
-			sock_put(sk);
+			if (refcounted)
+				sock_put(sk);
 			goto report_csum_error;
 		}
 
 		ret = udp6_unicast_rcv_skb(sk, skb, uh);
-		sock_put(sk);
+		if (refcounted)
+			sock_put(sk);
 		return ret;
 	}
 
-- 
2.20.1


  parent reply	other threads:[~2020-03-25  5:58 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-25  5:57 [PATCHv2 bpf-next 0/5] Add bpf_sk_assign eBPF helper Joe Stringer
2020-03-25  5:57 ` [PATCHv2 bpf-next 1/5] bpf: Add socket assign support Joe Stringer
2020-03-26  6:23   ` Martin KaFai Lau
2020-03-26  6:31     ` Joe Stringer
2020-03-26 10:24   ` Lorenz Bauer
2020-03-26 22:52     ` Joe Stringer
2020-03-27  2:40       ` Joe Stringer
2020-03-25  5:57 ` [PATCHv2 bpf-next 2/5] bpf: Prefetch established socket destinations Joe Stringer
2020-03-26 21:11   ` Alexei Starovoitov
2020-03-26 21:45     ` Joe Stringer
2020-03-25  5:57 ` Joe Stringer [this message]
2020-03-25  5:57 ` [PATCHv2 bpf-next 4/5] bpf: Don't refcount LISTEN sockets in sk_assign() Joe Stringer
2020-03-25 10:29   ` Lorenz Bauer
2020-03-25 20:46     ` Joe Stringer
2020-03-26 10:20       ` Lorenz Bauer
2020-03-26 21:37         ` Joe Stringer
2020-03-25  5:57 ` [PATCHv2 bpf-next 5/5] selftests: bpf: add test for sk_assign Joe Stringer
2020-03-25 10:35   ` Lorenz Bauer
2020-03-25 20:55     ` Joe Stringer
2020-03-26  6:25       ` Martin KaFai Lau
2020-03-26  6:38         ` Joe Stringer
2020-03-26 23:39           ` Joe Stringer
2020-03-25 18:17   ` Yonghong Song
2020-03-25 21:20     ` Joe Stringer
2020-03-25 22:00       ` Yonghong Song
2020-03-25 23:07         ` Joe Stringer
2020-03-26 10:13     ` Lorenz Bauer
2020-03-26 21:07       ` call for bpf progs. " Alexei Starovoitov
2020-03-26 23:14         ` Yonghong Song
2020-03-27 10:02         ` Lorenz Bauer
2020-03-27 16:08           ` Alexei Starovoitov
2020-03-27 19:06         ` Joe Stringer
2020-03-27 20:16           ` Daniel Borkmann
2020-03-27 22:24             ` Alexei Starovoitov
2020-03-28  0:17           ` Andrii Nakryiko
2020-03-26  2:04   ` Andrii Nakryiko
2020-03-26  2:16   ` Andrii Nakryiko
2020-03-26  5:28     ` Joe Stringer
2020-03-26  6:31       ` Martin KaFai Lau
2020-03-26 19:36       ` Andrii Nakryiko
2020-03-26 21:38         ` Joe Stringer

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=20200325055745.10710-4-joe@wand.net.nz \
    --to=joe@wand.net.nz \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=eric.dumazet@gmail.com \
    --cc=kafai@fb.com \
    --cc=lmb@cloudflare.com \
    --cc=netdev@vger.kernel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.