BPF Archive on lore.kernel.org
 help / color / 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: [PATCHv3 bpf-next 3/5] bpf: Don't refcount LISTEN sockets in sk_assign()
Date: Thu, 26 Mar 2020 21:25:54 -0700
Message-ID: <20200327042556.11560-4-joe@wand.net.nz> (raw)
In-Reply-To: <20200327042556.11560-1-joe@wand.net.nz>

Avoid taking a reference on listen sockets by checking the socket type
in the sk_assign and in the corresponding skb_steal_sock() code in the
the transport layer, and by ensuring that the prefetch free (sock_pfree)
function uses the same logic to check whether the socket is refcounted.

Suggested-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Joe Stringer <joe@wand.net.nz>
---
v3: No changes
v2: Initial version
---
 include/net/sock.h | 25 +++++++++++++++++--------
 net/core/filter.c  |  6 +++---
 net/core/sock.c    |  3 ++-
 3 files changed, 22 insertions(+), 12 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 1ca2e808cb8e..3ec1865f173e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2533,6 +2533,21 @@ skb_sk_is_prefetched(struct sk_buff *skb)
 	return skb->destructor == sock_pfree;
 }
 
+/* This helper checks if a socket is a full socket,
+ * ie _not_ a timewait or request socket.
+ */
+static inline bool sk_fullsock(const struct sock *sk)
+{
+	return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);
+}
+
+static inline bool
+sk_is_refcounted(struct sock *sk)
+{
+	/* Only full sockets have sk->sk_flags. */
+	return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE);
+}
+
 /**
  * skb_steal_sock
  * @skb to steal the socket from
@@ -2545,6 +2560,8 @@ skb_steal_sock(struct sk_buff *skb, bool *refcounted)
 		struct sock *sk = skb->sk;
 
 		*refcounted = true;
+		if (skb_sk_is_prefetched(skb))
+			*refcounted = sk_is_refcounted(sk);
 		skb->destructor = NULL;
 		skb->sk = NULL;
 		return sk;
@@ -2553,14 +2570,6 @@ skb_steal_sock(struct sk_buff *skb, bool *refcounted)
 	return NULL;
 }
 
-/* This helper checks if a socket is a full socket,
- * ie _not_ a timewait or request socket.
- */
-static inline bool sk_fullsock(const struct sock *sk)
-{
-	return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);
-}
-
 /* Checks if this SKB belongs to an HW offloaded socket
  * and whether any SW fallbacks are required based on dev.
  * Check decrypted mark in case skb_orphan() cleared socket.
diff --git a/net/core/filter.c b/net/core/filter.c
index 2bcc29c1a595..fb73e6452c91 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5343,8 +5343,7 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
 
 BPF_CALL_1(bpf_sk_release, struct sock *, sk)
 {
-	/* Only full sockets have sk->sk_flags. */
-	if (!sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE))
+	if (sk_is_refcounted(sk))
 		sock_gen_put(sk);
 	return 0;
 }
@@ -5870,7 +5869,8 @@ BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags)
 		return -ENETUNREACH;
 	if (unlikely(sk->sk_reuseport))
 		return -ESOCKTNOSUPPORT;
-	if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
+	if (sk_is_refcounted(sk) &&
+	    unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
 		return -ENOENT;
 
 	skb_orphan(skb);
diff --git a/net/core/sock.c b/net/core/sock.c
index cfaf60267360..a2ab79446f59 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2076,7 +2076,8 @@ EXPORT_SYMBOL(sock_efree);
  */
 void sock_pfree(struct sk_buff *skb)
 {
-	sock_edemux(skb);
+	if (sk_is_refcounted(skb->sk))
+		sock_edemux(skb);
 }
 EXPORT_SYMBOL(sock_pfree);
 
-- 
2.20.1


  parent reply index

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-27  4:25 [PATCHv3 bpf-next 0/5] Add bpf_sk_assign eBPF helper Joe Stringer
2020-03-27  4:25 ` [PATCHv3 bpf-next 1/5] bpf: Add socket assign support Joe Stringer
2020-03-27 18:44   ` Martin KaFai Lau
2020-03-27  4:25 ` [PATCHv3 bpf-next 2/5] net: Track socket refcounts in skb_steal_sock() Joe Stringer
2020-03-27 18:45   ` Martin KaFai Lau
2020-03-27  4:25 ` Joe Stringer [this message]
2020-03-27 14:26   ` [PATCHv3 bpf-next 3/5] bpf: Don't refcount LISTEN sockets in sk_assign() Jamal Hadi Salim
2020-03-27 17:38     ` Joe Stringer
2020-03-27 18:29       ` Jamal Hadi Salim
2020-03-27  4:25 ` [PATCHv3 bpf-next 4/5] selftests: bpf: add test for sk_assign Joe Stringer
2020-03-27  4:25 ` [PATCHv3 bpf-next 5/5] selftests: bpf: Extend sk_assign tests for UDP Joe Stringer
     [not found]   ` <CACAyw9-GOw5tkR8n6p7Kct9-wq4B-9ka-X8R2V8uZv8VWUY5UQ@mail.gmail.com>
2020-03-27 19:37     ` Joe Stringer
2020-03-27  5:02 ` [PATCHv3 bpf-next 0/5] Add bpf_sk_assign eBPF helper Alexei Starovoitov
2020-03-27  5:42   ` Eric Dumazet
2020-03-27 14:13 ` Jamal Hadi Salim
2020-03-27 17:43   ` Joe Stringer
2020-03-27 18:34     ` Jamal Hadi Salim
2020-03-27 18:46 ` Martin KaFai Lau
2020-03-27 21:05   ` Joe Stringer
2020-03-28 17:25     ` Daniel Borkmann
2020-03-28 17:42       ` 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=20200327042556.11560-4-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

BPF Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/bpf/0 bpf/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 bpf bpf/ https://lore.kernel.org/bpf \
		bpf@vger.kernel.org
	public-inbox-index bpf

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.bpf


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git