netdev - [PATCH bpf-next 4/8] tcp: seq_file: Add listening_get

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20210625200511.726185-1-kafai@fb.com>
Date:   Fri, 25 Jun 2021 13:05:11 -0700
From:   Martin KaFai Lau <kafai@...com>
To:     <bpf@...r.kernel.org>
CC:     Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        Eric Dumazet <edumazet@...gle.com>, <kernel-team@...com>,
        Neal Cardwell <ncardwell@...gle.com>, <netdev@...r.kernel.org>,
        Yonghong Song <yhs@...com>, Yuchung Cheng <ycheng@...gle.com>
Subject: [PATCH bpf-next 4/8] tcp: seq_file: Add listening_get_first()

The current listening_get_next() is overloaded by passing
NULL to the 2nd arg, like listening_get_next(seq, NULL), to
mean get_first().

This patch moves some logic from the listening_get_next() into
a new function listening_get_first().  It will be equivalent
to the current established_get_first() and established_get_next()
setup.  get_first() is to find a non empty bucket and return
the first sk.  get_next() is to find the next sk of the current
bucket and then resorts to get_first() if the current bucket is
exhausted.

The next patch is to move the listener seq_file iteration from
listening_hash (port only) to lhash2 (port+addr).
Separating out listening_get_first() from listening_get_next()
here will make the following lhash2 changes cleaner and easier to
follow.

Signed-off-by: Martin KaFai Lau <kafai@...com>
---
 net/ipv4/tcp_ipv4.c | 59 ++++++++++++++++++++++++++++++---------------
 1 file changed, 39 insertions(+), 20 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ca55e87f6cc9..693bda155876 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2288,10 +2288,38 @@ static bool seq_sk_match(struct seq_file *seq, const struct sock *sk)
 		net_eq(sock_net(sk), seq_file_net(seq)));
 }
 
-/*
- * Get next listener socket follow cur.  If cur is NULL, get first socket
- * starting from bucket given in st->bucket; when st->bucket is zero the
- * very first socket in the hash table is returned.
+/* Find a non empty bucket (starting from st->bucket)
+ * and return the first sk from it.
+ */
+static void *listening_get_first(struct seq_file *seq)
+{
+	struct tcp_iter_state *st = seq->private;
+
+	st->offset = 0;
+	for (; st->bucket < INET_LHTABLE_SIZE; st->bucket++) {
+		struct inet_listen_hashbucket *ilb;
+		struct hlist_nulls_node *node;
+		struct sock *sk;
+
+		ilb = &tcp_hashinfo.listening_hash[st->bucket];
+		if (hlist_nulls_empty(&ilb->nulls_head))
+			continue;
+
+		spin_lock(&ilb->lock);
+		sk_nulls_for_each(sk, node, &ilb->nulls_head) {
+			if (seq_sk_match(seq, sk))
+				return sk;
+		}
+		spin_unlock(&ilb->lock);
+	}
+
+	return NULL;
+}
+
+/* Find the next sk of "cur" within the same bucket (i.e. st->bucket).
+ * If "cur" is the last one in the st->bucket,
+ * call listening_get_first() to return the first sk of the next
+ * non empty bucket.
  */
 static void *listening_get_next(struct seq_file *seq, void *cur)
 {
@@ -2300,29 +2328,20 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
 	struct hlist_nulls_node *node;
 	struct sock *sk = cur;
 
-	if (!sk) {
-get_head:
-		ilb = &tcp_hashinfo.listening_hash[st->bucket];
-		spin_lock(&ilb->lock);
-		sk = sk_nulls_head(&ilb->nulls_head);
-		st->offset = 0;
-		goto get_sk;
-	}
-	ilb = &tcp_hashinfo.listening_hash[st->bucket];
 	++st->num;
 	++st->offset;
 
 	sk = sk_nulls_next(sk);
-get_sk:
+
 	sk_nulls_for_each_from(sk, node) {
 		if (seq_sk_match(seq, sk))
 			return sk;
 	}
+
+	ilb = &tcp_hashinfo.listening_hash[st->bucket];
 	spin_unlock(&ilb->lock);
-	st->offset = 0;
-	if (++st->bucket < INET_LHTABLE_SIZE)
-		goto get_head;
-	return NULL;
+	++st->bucket;
+	return listening_get_first(seq);
 }
 
 static void *listening_get_idx(struct seq_file *seq, loff_t *pos)
@@ -2332,7 +2351,7 @@ static void *listening_get_idx(struct seq_file *seq, loff_t *pos)
 
 	st->bucket = 0;
 	st->offset = 0;
-	rc = listening_get_next(seq, NULL);
+	rc = listening_get_first(seq);
 
 	while (rc && *pos) {
 		rc = listening_get_next(seq, rc);
@@ -2440,7 +2459,7 @@ static void *tcp_seek_last_pos(struct seq_file *seq)
 		if (st->bucket >= INET_LHTABLE_SIZE)
 			break;
 		st->state = TCP_SEQ_STATE_LISTENING;
-		rc = listening_get_next(seq, NULL);
+		rc = listening_get_first(seq);
 		while (offset-- && rc && bucket == st->bucket)
 			rc = listening_get_next(seq, rc);
 		if (rc)
-- 
2.30.2