bpf.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jakub Sitnicki <jakub@cloudflare.com>
To: bpf@vger.kernel.org
Cc: netdev@vger.kernel.org, kernel-team@cloudflare.com,
	John Fastabend <john.fastabend@gmail.com>,
	Lorenz Bauer <lmb@cloudflare.com>, Martin Lau <kafai@fb.com>
Subject: [PATCH bpf-next v7 04/11] bpf, sockmap: Allow inserting listening TCP sockets into sockmap
Date: Tue, 18 Feb 2020 17:10:16 +0000	[thread overview]
Message-ID: <20200218171023.844439-5-jakub@cloudflare.com> (raw)
In-Reply-To: <20200218171023.844439-1-jakub@cloudflare.com>

In order for sockmap/sockhash types to become generic collections for
storing TCP sockets we need to loosen the checks during map update, while
tightening the checks in redirect helpers.

Currently sock{map,hash} require the TCP socket to be in established state,
which prevents inserting listening sockets.

Change the update pre-checks so the socket can also be in listening state.

Since it doesn't make sense to redirect with sock{map,hash} to listening
sockets, add appropriate socket state checks to BPF redirect helpers too.

Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
---
 net/core/sock_map.c                     | 59 ++++++++++++++++++-------
 tools/testing/selftests/bpf/test_maps.c |  6 +--
 2 files changed, 45 insertions(+), 20 deletions(-)

diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 3a7a96ab088a..dd92a3556d73 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -391,7 +391,8 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx,
 static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops)
 {
 	return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB ||
-	       ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB;
+	       ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB ||
+	       ops->op == BPF_SOCK_OPS_TCP_LISTEN_CB;
 }
 
 static bool sock_map_sk_is_suitable(const struct sock *sk)
@@ -400,6 +401,16 @@ static bool sock_map_sk_is_suitable(const struct sock *sk)
 	       sk->sk_protocol == IPPROTO_TCP;
 }
 
+static bool sock_map_sk_state_allowed(const struct sock *sk)
+{
+	return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN);
+}
+
+static bool sock_map_redirect_allowed(const struct sock *sk)
+{
+	return sk->sk_state != TCP_LISTEN;
+}
+
 static int sock_map_update_elem(struct bpf_map *map, void *key,
 				void *value, u64 flags)
 {
@@ -423,7 +434,7 @@ static int sock_map_update_elem(struct bpf_map *map, void *key,
 	}
 
 	sock_map_sk_acquire(sk);
-	if (sk->sk_state != TCP_ESTABLISHED)
+	if (!sock_map_sk_state_allowed(sk))
 		ret = -EOPNOTSUPP;
 	else
 		ret = sock_map_update_common(map, idx, sk, flags);
@@ -460,13 +471,17 @@ BPF_CALL_4(bpf_sk_redirect_map, struct sk_buff *, skb,
 	   struct bpf_map *, map, u32, key, u64, flags)
 {
 	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
+	struct sock *sk;
 
 	if (unlikely(flags & ~(BPF_F_INGRESS)))
 		return SK_DROP;
-	tcb->bpf.flags = flags;
-	tcb->bpf.sk_redir = __sock_map_lookup_elem(map, key);
-	if (!tcb->bpf.sk_redir)
+
+	sk = __sock_map_lookup_elem(map, key);
+	if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
 		return SK_DROP;
+
+	tcb->bpf.flags = flags;
+	tcb->bpf.sk_redir = sk;
 	return SK_PASS;
 }
 
@@ -483,12 +498,17 @@ const struct bpf_func_proto bpf_sk_redirect_map_proto = {
 BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg,
 	   struct bpf_map *, map, u32, key, u64, flags)
 {
+	struct sock *sk;
+
 	if (unlikely(flags & ~(BPF_F_INGRESS)))
 		return SK_DROP;
-	msg->flags = flags;
-	msg->sk_redir = __sock_map_lookup_elem(map, key);
-	if (!msg->sk_redir)
+
+	sk = __sock_map_lookup_elem(map, key);
+	if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
 		return SK_DROP;
+
+	msg->flags = flags;
+	msg->sk_redir = sk;
 	return SK_PASS;
 }
 
@@ -748,7 +768,7 @@ static int sock_hash_update_elem(struct bpf_map *map, void *key,
 	}
 
 	sock_map_sk_acquire(sk);
-	if (sk->sk_state != TCP_ESTABLISHED)
+	if (!sock_map_sk_state_allowed(sk))
 		ret = -EOPNOTSUPP;
 	else
 		ret = sock_hash_update_common(map, key, sk, flags);
@@ -916,13 +936,17 @@ BPF_CALL_4(bpf_sk_redirect_hash, struct sk_buff *, skb,
 	   struct bpf_map *, map, void *, key, u64, flags)
 {
 	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
+	struct sock *sk;
 
 	if (unlikely(flags & ~(BPF_F_INGRESS)))
 		return SK_DROP;
-	tcb->bpf.flags = flags;
-	tcb->bpf.sk_redir = __sock_hash_lookup_elem(map, key);
-	if (!tcb->bpf.sk_redir)
+
+	sk = __sock_hash_lookup_elem(map, key);
+	if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
 		return SK_DROP;
+
+	tcb->bpf.flags = flags;
+	tcb->bpf.sk_redir = sk;
 	return SK_PASS;
 }
 
@@ -939,12 +963,17 @@ const struct bpf_func_proto bpf_sk_redirect_hash_proto = {
 BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg,
 	   struct bpf_map *, map, void *, key, u64, flags)
 {
+	struct sock *sk;
+
 	if (unlikely(flags & ~(BPF_F_INGRESS)))
 		return SK_DROP;
-	msg->flags = flags;
-	msg->sk_redir = __sock_hash_lookup_elem(map, key);
-	if (!msg->sk_redir)
+
+	sk = __sock_hash_lookup_elem(map, key);
+	if (unlikely(!sk || !sock_map_redirect_allowed(sk)))
 		return SK_DROP;
+
+	msg->flags = flags;
+	msg->sk_redir = sk;
 	return SK_PASS;
 }
 
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 02eae1e864c2..c6766b2cff85 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -756,11 +756,7 @@ static void test_sockmap(unsigned int tasks, void *data)
 	/* Test update without programs */
 	for (i = 0; i < 6; i++) {
 		err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY);
-		if (i < 2 && !err) {
-			printf("Allowed update sockmap '%i:%i' not in ESTABLISHED\n",
-			       i, sfd[i]);
-			goto out_sockmap;
-		} else if (i >= 2 && err) {
+		if (err) {
 			printf("Failed noprog update sockmap '%i:%i'\n",
 			       i, sfd[i]);
 			goto out_sockmap;
-- 
2.24.1


  parent reply	other threads:[~2020-02-18 17:10 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-18 17:10 [PATCH bpf-next v7 00/11] Extend SOCKMAP/SOCKHASH to store listening sockets Jakub Sitnicki
2020-02-18 17:10 ` [PATCH bpf-next v7 01/11] net, sk_msg: Annotate lockless access to sk_prot on clone Jakub Sitnicki
2020-02-18 17:10 ` [PATCH bpf-next v7 02/11] net, sk_msg: Clear sk_user_data pointer on clone if tagged Jakub Sitnicki
2020-02-18 17:10 ` [PATCH bpf-next v7 03/11] tcp_bpf: Don't let child socket inherit parent protocol ops on copy Jakub Sitnicki
2020-02-21  3:28   ` John Fastabend
2020-02-18 17:10 ` Jakub Sitnicki [this message]
2020-02-21  3:33   ` [PATCH bpf-next v7 04/11] bpf, sockmap: Allow inserting listening TCP sockets into sockmap John Fastabend
2020-02-18 17:10 ` [PATCH bpf-next v7 05/11] bpf, sockmap: Don't set up upcalls and progs for listening sockets Jakub Sitnicki
2020-02-21  3:42   ` John Fastabend
2020-02-18 17:10 ` [PATCH bpf-next v7 06/11] bpf, sockmap: Return socket cookie on lookup from syscall Jakub Sitnicki
2020-02-21  3:45   ` John Fastabend
2020-02-18 17:10 ` [PATCH bpf-next v7 07/11] bpf, sockmap: Let all kernel-land lookup values in SOCKMAP/SOCKHASH Jakub Sitnicki
2020-02-21  3:46   ` John Fastabend
2020-02-18 17:10 ` [PATCH bpf-next v7 08/11] bpf: Allow selecting reuseport socket from a SOCKMAP/SOCKHASH Jakub Sitnicki
2020-02-18 17:10 ` [PATCH bpf-next v7 09/11] net: Generate reuseport group ID on group creation Jakub Sitnicki
2020-02-18 17:10 ` [PATCH bpf-next v7 10/11] selftests/bpf: Extend SK_REUSEPORT tests to cover SOCKMAP/SOCKHASH Jakub Sitnicki
2020-02-21  3:52   ` John Fastabend
2020-02-18 17:10 ` [PATCH bpf-next v7 11/11] selftests/bpf: Tests for sockmap/sockhash holding listening sockets Jakub Sitnicki
2020-02-21  3:56   ` John Fastabend
2020-02-21 21:41 ` [PATCH bpf-next v7 00/11] Extend SOCKMAP/SOCKHASH to store " Daniel Borkmann
2020-02-22  0:47   ` Alexei Starovoitov
2020-02-22 13:49     ` Jakub Sitnicki
2020-02-23 21:43       ` Alexei Starovoitov
2020-02-24 13:59         ` Jakub Sitnicki

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=20200218171023.844439-5-jakub@cloudflare.com \
    --to=jakub@cloudflare.com \
    --cc=bpf@vger.kernel.org \
    --cc=john.fastabend@gmail.com \
    --cc=kafai@fb.com \
    --cc=kernel-team@cloudflare.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).