Merge tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Pull BPF fixes from Daniel Borkmann:

 - Fix BPF verifier to preserve full pointer state for commuted
   scalar += pointer arithmetic (Yiyang Chen, Eduard Zingerman)

 - Fix a use-after-free of request sockets in the BPF TCP iterator
   batching (Jose Fernandez)

 - Fix a use-after-free of sk_redir in the BPF sockmap send verdict
   path (Chengfeng Ye)

 - Fix a netns reference imbalance in the BPF conntrack kfuncs
   (Chengfeng Ye)

 - Fix bpf_get_fsverity_digest() dynptr assumptions and silent
   digest truncation (Eric Biggers)

 - Fix bpf_tcp_{gen,check}_syncookie to check sk_state before
   sk_protocol to make sure it is a full socket (Luxiao Xu)

 - Fix rqspinlock to reset the tail when preserving the queue
   on deadlock (Kumar Kartikeya Dwivedi)

* tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  rqspinlock: Reset tail when preserving queue on deadlock
  bpf: Check sk_state before sk_protocol in bpf_tcp_*_syncookie
  fsverity: Fix silent truncation in bpf_get_fsverity_digest()
  fsverity: Fix bpf_get_fsverity_digest() dynptr assumptions
  bpf: tcp: Fix use-after-free in bpf_iter_tcp_established_batch()
  bpf: Fix netns reference imbalance in conntrack kfuncs
  bpf, sockmap: Fix sk_redir use-after-free in send verdict
  selftests/bpf: Cover commuted pointer state propagation
  bpf: Propagate untrusted pointer state in commuted arithmetic
  bpf: Preserve pointer state for commuted arithmetic
  bpf: Simplify sanitize_err() signature

4 files changed, 76 insertions, 45 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 11bb0d236822..16845987b244 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7684,7 +7684,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 		return -EINVAL;
 
 	/* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */
-	if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
+	if (sk->sk_state != TCP_LISTEN || sk->sk_protocol != IPPROTO_TCP)
 		return -EINVAL;
 
 	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies))
@@ -7757,7 +7757,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len,
 	if (unlikely(!sk || th_len < sizeof(*th) || th_len != th->doff * 4))
 		return -EINVAL;
 
-	if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
+	if (sk->sk_state != TCP_LISTEN || sk->sk_protocol != IPPROTO_TCP)
 		return -EINVAL;
 
 	if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies))
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index a30475afb6f8..2e234d155b5e 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -469,6 +469,7 @@ more_data:
 	case __SK_REDIRECT:
 		redir_ingress = psock->redir_ingress;
 		sk_redir = psock->sk_redir;
+		sock_hold(sk_redir);
 		sk_msg_apply_bytes(psock, tosend);
 		if (!psock->apply_bytes) {
 			/* Clean up before releasing the sock lock. */
@@ -489,6 +490,7 @@ more_data:
 
 		if (eval == __SK_REDIRECT)
 			sock_put(sk_redir);
+		sock_put(sk_redir);
 
 		lock_sock(sk);
 		sk_mem_uncharge(sk, sent);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b8887cdd66c5..7f413f509d7d 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3078,24 +3078,24 @@ 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;
-
-	sock_hold(*start_sk);
-	iter->batch[iter->end_sk++].sk = *start_sk;
+	struct sock *sk = *start_sk;
+	unsigned int expected = 0;
 
-	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;
 		}
 	}
 
@@ -3133,12 +3133,13 @@ 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. */
@@ -3157,7 +3158,7 @@ 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
@@ -3170,10 +3171,14 @@ 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;
 }
 
diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c
index f98d1d4b42c3..c2df7c948281 100644
--- a/net/netfilter/nf_conntrack_bpf.c
+++ b/net/netfilter/nf_conntrack_bpf.c
@@ -122,42 +122,54 @@ __bpf_nf_ct_alloc_entry(struct net *net, struct bpf_sock_tuple *bpf_tuple,
 	struct nf_conntrack_tuple otuple, rtuple;
 	struct nf_conntrack_zone ct_zone;
 	struct nf_conn *ct;
+	u8 ct_zone_dir = 0;
+	u16 ct_zone_id;
+	s32 netns_id;
+	u8 l4proto;
 	int err;
 
 	if (!(opts_len == NF_BPF_CT_OPTS_SZ || opts_len == 12))
 		return ERR_PTR(-EINVAL);
+
+	netns_id = READ_ONCE(opts->netns_id);
+	l4proto = READ_ONCE(opts->l4proto);
+	ct_zone_id = READ_ONCE(opts->ct_zone_id);
 	if (opts_len == NF_BPF_CT_OPTS_SZ) {
-		if (opts->reserved[0] || opts->reserved[1] || opts->reserved[2])
+		ct_zone_dir = READ_ONCE(opts->ct_zone_dir);
+		if (READ_ONCE(opts->reserved[0]) ||
+		    READ_ONCE(opts->reserved[1]) ||
+		    READ_ONCE(opts->reserved[2]))
 			return ERR_PTR(-EINVAL);
 	} else {
-		if (opts->ct_zone_id)
+		if (ct_zone_id)
 			return ERR_PTR(-EINVAL);
 	}
 
-	if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS))
+	if (unlikely(netns_id < BPF_F_CURRENT_NETNS))
 		return ERR_PTR(-EINVAL);
 
-	err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, opts->l4proto,
+	err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, l4proto,
 				    IP_CT_DIR_ORIGINAL, &otuple);
 	if (err < 0)
 		return ERR_PTR(err);
 
-	err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, opts->l4proto,
+	err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, l4proto,
 				    IP_CT_DIR_REPLY, &rtuple);
 	if (err < 0)
 		return ERR_PTR(err);
 
-	if (opts->netns_id >= 0) {
-		net = get_net_ns_by_id(net, opts->netns_id);
+	if (netns_id >= 0) {
+		net = get_net_ns_by_id(net, netns_id);
 		if (unlikely(!net))
 			return ERR_PTR(-ENONET);
 	}
 
 	if (opts_len == NF_BPF_CT_OPTS_SZ) {
-		if (opts->ct_zone_dir == 0)
-			opts->ct_zone_dir = NF_CT_DEFAULT_ZONE_DIR;
-		nf_ct_zone_init(&ct_zone,
-				opts->ct_zone_id, opts->ct_zone_dir, 0);
+		if (ct_zone_dir == 0) {
+			ct_zone_dir = NF_CT_DEFAULT_ZONE_DIR;
+			opts->ct_zone_dir = ct_zone_dir;
+		}
+		nf_ct_zone_init(&ct_zone, ct_zone_id, ct_zone_dir, 0);
 	} else {
 		ct_zone = nf_ct_zone_dflt;
 	}
@@ -171,7 +183,7 @@ __bpf_nf_ct_alloc_entry(struct net *net, struct bpf_sock_tuple *bpf_tuple,
 	__nf_ct_set_timeout(ct, timeout * HZ);
 
 out:
-	if (opts->netns_id >= 0)
+	if (netns_id >= 0)
 		put_net(net);
 
 	return ct;
@@ -186,46 +198,58 @@ static struct nf_conn *__bpf_nf_ct_lookup(struct net *net,
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_zone ct_zone;
 	struct nf_conn *ct;
+	u8 ct_zone_dir = 0;
+	u16 ct_zone_id;
+	s32 netns_id;
+	u8 l4proto;
 	int err;
 
 	if (!opts || !bpf_tuple)
 		return ERR_PTR(-EINVAL);
 	if (!(opts_len == NF_BPF_CT_OPTS_SZ || opts_len == 12))
 		return ERR_PTR(-EINVAL);
+
+	netns_id = READ_ONCE(opts->netns_id);
+	l4proto = READ_ONCE(opts->l4proto);
+	ct_zone_id = READ_ONCE(opts->ct_zone_id);
 	if (opts_len == NF_BPF_CT_OPTS_SZ) {
-		if (opts->reserved[0] || opts->reserved[1] || opts->reserved[2])
+		ct_zone_dir = READ_ONCE(opts->ct_zone_dir);
+		if (READ_ONCE(opts->reserved[0]) ||
+		    READ_ONCE(opts->reserved[1]) ||
+		    READ_ONCE(opts->reserved[2]))
 			return ERR_PTR(-EINVAL);
 	} else {
-		if (opts->ct_zone_id)
+		if (ct_zone_id)
 			return ERR_PTR(-EINVAL);
 	}
-	if (unlikely(opts->l4proto != IPPROTO_TCP && opts->l4proto != IPPROTO_UDP))
+	if (unlikely(l4proto != IPPROTO_TCP && l4proto != IPPROTO_UDP))
 		return ERR_PTR(-EPROTO);
-	if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS))
+	if (unlikely(netns_id < BPF_F_CURRENT_NETNS))
 		return ERR_PTR(-EINVAL);
 
-	err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, opts->l4proto,
+	err = bpf_nf_ct_tuple_parse(bpf_tuple, tuple_len, l4proto,
 				    IP_CT_DIR_ORIGINAL, &tuple);
 	if (err < 0)
 		return ERR_PTR(err);
 
-	if (opts->netns_id >= 0) {
-		net = get_net_ns_by_id(net, opts->netns_id);
+	if (netns_id >= 0) {
+		net = get_net_ns_by_id(net, netns_id);
 		if (unlikely(!net))
 			return ERR_PTR(-ENONET);
 	}
 
 	if (opts_len == NF_BPF_CT_OPTS_SZ) {
-		if (opts->ct_zone_dir == 0)
-			opts->ct_zone_dir = NF_CT_DEFAULT_ZONE_DIR;
-		nf_ct_zone_init(&ct_zone,
-				opts->ct_zone_id, opts->ct_zone_dir, 0);
+		if (ct_zone_dir == 0) {
+			ct_zone_dir = NF_CT_DEFAULT_ZONE_DIR;
+			opts->ct_zone_dir = ct_zone_dir;
+		}
+		nf_ct_zone_init(&ct_zone, ct_zone_id, ct_zone_dir, 0);
 	} else {
 		ct_zone = nf_ct_zone_dflt;
 	}
 
 	hash = nf_conntrack_find_get(net, &ct_zone, &tuple);
-	if (opts->netns_id >= 0)
+	if (netns_id >= 0)
 		put_net(net);
 	if (!hash)
 		return ERR_PTR(-ENOENT);