bpf: tcp: Fix use-after-free in bpf_iter_tcp_established_batch()

[ Upstream commit e5fd3f514e ]

reqsk_queue_hash_req() publishes a TCP_NEW_SYN_RECV request_sock onto
the ehash chain, drops the bucket lock, and only afterwards sets
rsk_refcnt to 3.

Lockless readers such as __inet_lookup_established() handle this with
refcount_inc_not_zero(), but bpf_iter_tcp_established_batch() uses plain
sock_hold() while holding the bucket lock, on the assumption that the
lock guarantees sk_refcnt > 0. That assumption does not hold for
request_sock:

  CPU 0                                CPU 1
  -----                                -----
  tcp_conn_request()
   reqsk_queue_hash_req()
    inet_ehash_insert(req)
     spin_lock(bucket)
     __sk_nulls_add_node_rcu(req)      // rsk_refcnt == 0
     spin_unlock(bucket)
                                       bpf_iter_tcp_established_batch()
                                        spin_lock(bucket)
                                        sock_hold(req)   <-- addition on 0
                                        spin_unlock(bucket)
    refcount_set(&req->rsk_refcnt, 3)  // clobbers saturated value

which surfaces as:

  refcount_t: addition on 0; use-after-free.
  WARNING: lib/refcount.c:25 at refcount_warn_saturate+0x48/0x90, CPU#1
  Call Trace:
   bpf_iter_tcp_established_batch+0x14e/0x170
   bpf_iter_tcp_batch+0x53/0x200
   bpf_iter_tcp_seq_next+0x27/0x70
   bpf_seq_read+0x107/0x410
   vfs_read+0xb9/0x380

The iterator's stolen reference is lost when the publishing CPU's
refcount_set() overwrites the count, leaving the socket one reference
short. When the last legitimate owner drops its reference the reqsk is
freed while still reachable, leading to use-after-free.

This reproduces in seconds with tcp_syncookies=0, a handful of threads
doing connect()/close() to a local listener while others read an
iter/tcp link in a tight loop.

Use refcount_inc_not_zero() and skip the socket on failure. A skipped
socket is still part of the bucket, so keep counting it in expected.
The reallocations are sized from expected, and a request sock whose
refcount gets published while the lock is held across the last realloc
must already have room.

A skipped socket is counted in expected but never batched, so end_sk
can be short of expected on a batch that is actually complete. Decide
completeness by whether the walk left any socket behind instead. The
WARN after the locked realloc checks the same, replacing an
end_sk == expected check that could not hold on that path since
commit cdec67a489 ("bpf: tcp: Make sure iter->batch always
contains a full bucket snapshot").

If every matching socket in a bucket is mid-init (refcount 0), end_sk
stays 0. Advance to the next bucket rather than returning a batch entry
that was never filled this round.

Fixes: 04c7820b77 ("bpf: tcp: Bpf iter batching and lock_sock")
Assisted-by: Claude:unspecified
Signed-off-by: Jose Fernandez (Anthropic) <jose.fernandez@linux.dev>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://lore.kernel.org/bpf/20260730-bpf-iter-tcp-refcnt-v3-1-754b9c8a6717@linux.dev
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

net/ipv4/tcp_ipv4.c

@@ -3219,24 +3219,24 @@ static unsigned int bpf_iter_tcp_established_batch(struct seq_file *seq,
 {
 	struct bpf_tcp_iter_state *iter = seq->private;
 	struct hlist_nulls_node *node;
-	unsigned int expected = 1;
-	struct sock *sk;
+	struct sock *sk = *start_sk;
+	unsigned int expected = 0;
 
-	sock_hold(*start_sk);
-	iter->batch[iter->end_sk++].sk = *start_sk;
-
-	sk = sk_nulls_next(*start_sk);
 	*start_sk = NULL;
 	sk_nulls_for_each_from(sk, node) {
-		if (seq_sk_match(seq, sk)) {
-			if (iter->end_sk < iter->max_sk) {
-				sock_hold(sk);
-				iter->batch[iter->end_sk++].sk = sk;
-			} else if (!*start_sk) {
-				/* Remember where we left off. */
-				*start_sk = sk;
-			}
-			expected++;
+		if (!seq_sk_match(seq, sk))
+			continue;
+		expected++;
+		if (iter->end_sk < iter->max_sk) {
+			/* reqsk_queue_hash_req() inserts with sk_refcnt == 0
+			 * and refcount_set()s it after the bucket lock drops.
+			 */
+			if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
+				continue;
+			iter->batch[iter->end_sk++].sk = sk;
+		} else if (!*start_sk) {
+			/* Remember where we left off. */
+			*start_sk = sk;
 		}
 	}
 
@@ -3274,12 +3274,13 @@ static struct sock *bpf_iter_tcp_batch(struct seq_file *seq)
 	struct sock *sk;
 	int err;
 
+again:
 	sk = bpf_iter_tcp_resume(seq);
 	if (!sk)
 		return NULL; /* Done */
 
 	expected = bpf_iter_fill_batch(seq, &sk);
-	if (likely(iter->end_sk == expected))
+	if (likely(!sk))
 		goto done;
 
 	/* Batch size was too small. */
@@ -3298,7 +3299,7 @@ static struct sock *bpf_iter_tcp_batch(struct seq_file *seq)
 		return NULL; /* Done */
 
 	expected = bpf_iter_fill_batch(seq, &sk);
-	if (likely(iter->end_sk == expected))
+	if (likely(!sk))
 		goto done;
 
 	/* Batch size was still too small. Hold onto the lock while we try
@@ -3311,10 +3312,14 @@ static struct sock *bpf_iter_tcp_batch(struct seq_file *seq)
 		return ERR_PTR(err);
 	}
 
-	expected = bpf_iter_fill_batch(seq, &sk);
-	WARN_ON_ONCE(iter->end_sk != expected);
+	bpf_iter_fill_batch(seq, &sk);
+	WARN_ON_ONCE(sk);
 done:
 	bpf_iter_tcp_unlock_bucket(seq);
+	if (unlikely(!iter->end_sk)) {
+		++iter->state.bucket;
+		goto again;
+	}
 	return iter->batch[0].sk;
 }