Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2020-01-15

The following pull-request contains BPF updates for your *net* tree.

We've added 12 non-merge commits during the last 9 day(s) which contain
a total of 13 files changed, 95 insertions(+), 43 deletions(-).

The main changes are:

1) Fix refcount leak for TCP time wait and request sockets for socket lookup
   related BPF helpers, from Lorenz Bauer.

2) Fix wrong verification of ARSH instruction under ALU32, from Daniel Borkmann.

3) Batch of several sockmap and related TLS fixes found while operating
   more complex BPF programs with Cilium and OpenSSL, from John Fastabend.

4) Fix sockmap to read psock's ingress_msg queue before regular sk_receive_queue()
   to avoid purging data upon teardown, from Lingpeng Chen.

5) Fix printing incorrect pointer in bpftool's btf_dump_ptr() in order to properly
   dump a BPF map's value with BTF, from Martin KaFai Lau.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 63 insertions, 30 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 28b3c258188c..538f6a735a19 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2231,10 +2231,10 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
 	/* First find the starting scatterlist element */
 	i = msg->sg.start;
 	do {
+		offset += len;
 		len = sk_msg_elem(msg, i)->length;
 		if (start < offset + len)
 			break;
-		offset += len;
 		sk_msg_iter_var_next(i);
 	} while (i != msg->sg.end);
 
@@ -2346,7 +2346,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
 	   u32, len, u64, flags)
 {
 	struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge;
-	u32 new, i = 0, l, space, copy = 0, offset = 0;
+	u32 new, i = 0, l = 0, space, copy = 0, offset = 0;
 	u8 *raw, *to, *from;
 	struct page *page;
 
@@ -2356,11 +2356,11 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
 	/* First find the starting scatterlist element */
 	i = msg->sg.start;
 	do {
+		offset += l;
 		l = sk_msg_elem(msg, i)->length;
 
 		if (start < offset + l)
 			break;
-		offset += l;
 		sk_msg_iter_var_next(i);
 	} while (i != msg->sg.end);
 
@@ -2415,6 +2415,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start,
 
 		sk_msg_iter_var_next(i);
 		sg_unmark_end(psge);
+		sg_unmark_end(&rsge);
 		sk_msg_iter_next(msg, end);
 	}
 
@@ -2506,7 +2507,7 @@ static void sk_msg_shift_right(struct sk_msg *msg, int i)
 BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
 	   u32, len, u64, flags)
 {
-	u32 i = 0, l, space, offset = 0;
+	u32 i = 0, l = 0, space, offset = 0;
 	u64 last = start + len;
 	int pop;
 
@@ -2516,11 +2517,11 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start,
 	/* First find the starting scatterlist element */
 	i = msg->sg.start;
 	do {
+		offset += l;
 		l = sk_msg_elem(msg, i)->length;
 
 		if (start < offset + l)
 			break;
-		offset += l;
 		sk_msg_iter_var_next(i);
 	} while (i != msg->sg.end);
 
@@ -5318,8 +5319,7 @@ __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 	if (sk) {
 		sk = sk_to_full_sk(sk);
 		if (!sk_fullsock(sk)) {
-			if (!sock_flag(sk, SOCK_RCU_FREE))
-				sock_gen_put(sk);
+			sock_gen_put(sk);
 			return NULL;
 		}
 	}
@@ -5356,8 +5356,7 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 	if (sk) {
 		sk = sk_to_full_sk(sk);
 		if (!sk_fullsock(sk)) {
-			if (!sock_flag(sk, SOCK_RCU_FREE))
-				sock_gen_put(sk);
+			sock_gen_put(sk);
 			return NULL;
 		}
 	}
@@ -5424,7 +5423,8 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
 
 BPF_CALL_1(bpf_sk_release, struct sock *, sk)
 {
-	if (!sock_flag(sk, SOCK_RCU_FREE))
+	/* Only full sockets have sk->sk_flags. */
+	if (!sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE))
 		sock_gen_put(sk);
 	return 0;
 }
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index ded2d5227678..3866d7e20c07 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -594,6 +594,8 @@ EXPORT_SYMBOL_GPL(sk_psock_destroy);
 
 void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
 {
+	sock_owned_by_me(sk);
+
 	sk_psock_cork_free(psock);
 	sk_psock_zap_ingress(psock);
 
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index eb114ee419b6..8998e356f423 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -241,8 +241,11 @@ static void sock_map_free(struct bpf_map *map)
 		struct sock *sk;
 
 		sk = xchg(psk, NULL);
-		if (sk)
+		if (sk) {
+			lock_sock(sk);
 			sock_map_unref(sk, psk);
+			release_sock(sk);
+		}
 	}
 	raw_spin_unlock_bh(&stab->lock);
 	rcu_read_unlock();
@@ -862,7 +865,9 @@ static void sock_hash_free(struct bpf_map *map)
 		raw_spin_lock_bh(&bucket->lock);
 		hlist_for_each_entry_safe(elem, node, &bucket->head, node) {
 			hlist_del_rcu(&elem->node);
+			lock_sock(elem->sk);
 			sock_map_unref(elem->sk, elem);
+			release_sock(elem->sk);
 		}
 		raw_spin_unlock_bh(&bucket->lock);
 	}
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index e38705165ac9..8a01428f80c1 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -121,14 +121,14 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	struct sk_psock *psock;
 	int copied, ret;
 
-	if (unlikely(flags & MSG_ERRQUEUE))
-		return inet_recv_error(sk, msg, len, addr_len);
-	if (!skb_queue_empty(&sk->sk_receive_queue))
-		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
-
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
 		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return inet_recv_error(sk, msg, len, addr_len);
+	if (!skb_queue_empty(&sk->sk_receive_queue) &&
+	    sk_psock_queue_empty(psock))
+		return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
 	lock_sock(sk);
 msg_bytes_ready:
 	copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags);
@@ -139,7 +139,7 @@ msg_bytes_ready:
 		timeo = sock_rcvtimeo(sk, nonblock);
 		data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err);
 		if (data) {
-			if (skb_queue_empty(&sk->sk_receive_queue))
+			if (!sk_psock_queue_empty(psock))
 				goto msg_bytes_ready;
 			release_sock(sk);
 			sk_psock_put(sk, psock);
@@ -315,10 +315,7 @@ more_data:
 		 */
 		delta = msg->sg.size;
 		psock->eval = sk_psock_msg_verdict(sk, psock, msg);
-		if (msg->sg.size < delta)
-			delta -= msg->sg.size;
-		else
-			delta = 0;
+		delta -= msg->sg.size;
 	}
 
 	if (msg->cork_bytes &&
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 12ab5db2b71c..38d3ad141161 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -99,17 +99,19 @@ void tcp_get_available_ulp(char *buf, size_t maxlen)
 	rcu_read_unlock();
 }
 
-void tcp_update_ulp(struct sock *sk, struct proto *proto)
+void tcp_update_ulp(struct sock *sk, struct proto *proto,
+		    void (*write_space)(struct sock *sk))
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	if (!icsk->icsk_ulp_ops) {
+		sk->sk_write_space = write_space;
 		sk->sk_prot = proto;
 		return;
 	}
 
 	if (icsk->icsk_ulp_ops->update)
-		icsk->icsk_ulp_ops->update(sk, proto);
+		icsk->icsk_ulp_ops->update(sk, proto, write_space);
 }
 
 void tcp_cleanup_ulp(struct sock *sk)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index dac24c7aa7d4..94774c0e5ff3 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -732,15 +732,19 @@ out:
 	return rc;
 }
 
-static void tls_update(struct sock *sk, struct proto *p)
+static void tls_update(struct sock *sk, struct proto *p,
+		       void (*write_space)(struct sock *sk))
 {
 	struct tls_context *ctx;
 
 	ctx = tls_get_ctx(sk);
-	if (likely(ctx))
+	if (likely(ctx)) {
+		ctx->sk_write_space = write_space;
 		ctx->sk_proto = p;
-	else
+	} else {
 		sk->sk_prot = p;
+		sk->sk_write_space = write_space;
+	}
 }
 
 static int tls_get_info(const struct sock *sk, struct sk_buff *skb)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 5c7c00429f8e..c98e602a1a2d 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -680,12 +680,32 @@ static int tls_push_record(struct sock *sk, int flags,
 
 	split_point = msg_pl->apply_bytes;
 	split = split_point && split_point < msg_pl->sg.size;
+	if (unlikely((!split &&
+		      msg_pl->sg.size +
+		      prot->overhead_size > msg_en->sg.size) ||
+		     (split &&
+		      split_point +
+		      prot->overhead_size > msg_en->sg.size))) {
+		split = true;
+		split_point = msg_en->sg.size;
+	}
 	if (split) {
 		rc = tls_split_open_record(sk, rec, &tmp, msg_pl, msg_en,
 					   split_point, prot->overhead_size,
 					   &orig_end);
 		if (rc < 0)
 			return rc;
+		/* This can happen if above tls_split_open_record allocates
+		 * a single large encryption buffer instead of two smaller
+		 * ones. In this case adjust pointers and continue without
+		 * split.
+		 */
+		if (!msg_pl->sg.size) {
+			tls_merge_open_record(sk, rec, tmp, orig_end);
+			msg_pl = &rec->msg_plaintext;
+			msg_en = &rec->msg_encrypted;
+			split = false;
+		}
 		sk_msg_trim(sk, msg_en, msg_pl->sg.size +
 			    prot->overhead_size);
 	}
@@ -707,6 +727,12 @@ static int tls_push_record(struct sock *sk, int flags,
 		sg_mark_end(sk_msg_elem(msg_pl, i));
 	}
 
+	if (msg_pl->sg.end < msg_pl->sg.start) {
+		sg_chain(&msg_pl->sg.data[msg_pl->sg.start],
+			 MAX_SKB_FRAGS - msg_pl->sg.start + 1,
+			 msg_pl->sg.data);
+	}
+
 	i = msg_pl->sg.start;
 	sg_chain(rec->sg_aead_in, 2, &msg_pl->sg.data[i]);
 
@@ -781,10 +807,7 @@ more_data:
 	if (psock->eval == __SK_NONE) {
 		delta = msg->sg.size;
 		psock->eval = sk_psock_msg_verdict(sk, psock, msg);
-		if (delta < msg->sg.size)
-			delta -= msg->sg.size;
-		else
-			delta = 0;
+		delta -= msg->sg.size;
 	}
 	if (msg->cork_bytes && msg->cork_bytes > msg->sg.size &&
 	    !enospc && !full_record) {