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

Pull bpf fixes from Daniel Borkmann::

 - Fix several issues for BPF LPM trie map which were found by syzbot
   and during addition of new test cases (Hou Tao)

 - Fix a missing process_iter_arg register type check in the BPF
   verifier (Kumar Kartikeya Dwivedi, Tao Lyu)

 - Fix several correctness gaps in the BPF verifier when interacting
   with the BPF stack without CAP_PERFMON (Kumar Kartikeya Dwivedi,
   Eduard Zingerman, Tao Lyu)

 - Fix OOB BPF map writes when deleting elements for the case of xsk map
   as well as devmap (Maciej Fijalkowski)

 - Fix xsk sockets to always clear DMA mapping information when
   unmapping the pool (Larysa Zaremba)

 - Fix sk_mem_uncharge logic in tcp_bpf_sendmsg to only uncharge after
   sent bytes have been finalized (Zijian Zhang)

 - Fix BPF sockmap with vsocks which was missing a queue check in poll
   and sockmap cleanup on close (Michal Luczaj)

 - Fix tools infra to override makefile ARCH variable if defined but
   empty, which addresses cross-building tools. (Björn Töpel)

 - Fix two resolve_btfids build warnings on unresolved bpf_lsm symbols
   (Thomas Weißschuh)

 - Fix a NULL pointer dereference in bpftool (Amir Mohammadi)

 - Fix BPF selftests to check for CONFIG_PREEMPTION instead of
   CONFIG_PREEMPT (Sebastian Andrzej Siewior)

* tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf: (31 commits)
  selftests/bpf: Add more test cases for LPM trie
  selftests/bpf: Move test_lpm_map.c to map_tests
  bpf: Use raw_spinlock_t for LPM trie
  bpf: Switch to bpf mem allocator for LPM trie
  bpf: Fix exact match conditions in trie_get_next_key()
  bpf: Handle in-place update for full LPM trie correctly
  bpf: Handle BPF_EXIST and BPF_NOEXIST for LPM trie
  bpf: Remove unnecessary kfree(im_node) in lpm_trie_update_elem
  bpf: Remove unnecessary check when updating LPM trie
  selftests/bpf: Add test for narrow spill into 64-bit spilled scalar
  selftests/bpf: Add test for reading from STACK_INVALID slots
  selftests/bpf: Introduce __caps_unpriv annotation for tests
  bpf: Fix narrow scalar spill onto 64-bit spilled scalar slots
  bpf: Don't mark STACK_INVALID as STACK_MISC in mark_stack_slot_misc
  samples/bpf: Remove unnecessary -I flags from libbpf EXTRA_CFLAGS
  bpf: Zero index arg error string for dynptr and iter
  selftests/bpf: Add tests for iter arg check
  bpf: Ensure reg is PTR_TO_STACK in process_iter_arg
  tools: Override makefile ARCH variable if defined, but empty
  selftests/bpf: Add apply_bytes test to test_txmsg_redir_wait_sndmem in test_sockmap
  ...

4 files changed, 50 insertions, 38 deletions

diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 370993c03d31..99cef92e6290 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -441,7 +441,6 @@ more_data:
 			cork = true;
 			psock->cork = NULL;
 		}
-		sk_msg_return(sk, msg, tosend);
 		release_sock(sk);
 
 		origsize = msg->sg.size;
@@ -453,8 +452,9 @@ more_data:
 			sock_put(sk_redir);
 
 		lock_sock(sk);
+		sk_mem_uncharge(sk, sent);
 		if (unlikely(ret < 0)) {
-			int free = sk_msg_free_nocharge(sk, msg);
+			int free = sk_msg_free(sk, msg);
 
 			if (!cork)
 				*copied -= free;
@@ -468,7 +468,7 @@ more_data:
 		break;
 	case __SK_DROP:
 	default:
-		sk_msg_free_partial(sk, msg, tosend);
+		sk_msg_free(sk, msg);
 		sk_msg_apply_bytes(psock, tosend);
 		*copied -= (tosend + delta);
 		return -EACCES;
@@ -484,11 +484,8 @@ more_data:
 		}
 		if (msg &&
 		    msg->sg.data[msg->sg.start].page_link &&
-		    msg->sg.data[msg->sg.start].length) {
-			if (eval == __SK_REDIRECT)
-				sk_mem_charge(sk, tosend - sent);
+		    msg->sg.data[msg->sg.start].length)
 			goto more_data;
-		}
 	}
 	return ret;
 }
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 25b28b1434f5..5cf8109f672a 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -117,12 +117,14 @@
 static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr);
 static void vsock_sk_destruct(struct sock *sk);
 static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+static void vsock_close(struct sock *sk, long timeout);
 
 /* Protocol family. */
 struct proto vsock_proto = {
 	.name = "AF_VSOCK",
 	.owner = THIS_MODULE,
 	.obj_size = sizeof(struct vsock_sock),
+	.close = vsock_close,
 #ifdef CONFIG_BPF_SYSCALL
 	.psock_update_sk_prot = vsock_bpf_update_proto,
 #endif
@@ -797,39 +799,37 @@ static bool sock_type_connectible(u16 type)
 
 static void __vsock_release(struct sock *sk, int level)
 {
-	if (sk) {
-		struct sock *pending;
-		struct vsock_sock *vsk;
-
-		vsk = vsock_sk(sk);
-		pending = NULL;	/* Compiler warning. */
+	struct vsock_sock *vsk;
+	struct sock *pending;
 
-		/* When "level" is SINGLE_DEPTH_NESTING, use the nested
-		 * version to avoid the warning "possible recursive locking
-		 * detected". When "level" is 0, lock_sock_nested(sk, level)
-		 * is the same as lock_sock(sk).
-		 */
-		lock_sock_nested(sk, level);
+	vsk = vsock_sk(sk);
+	pending = NULL;	/* Compiler warning. */
 
-		if (vsk->transport)
-			vsk->transport->release(vsk);
-		else if (sock_type_connectible(sk->sk_type))
-			vsock_remove_sock(vsk);
+	/* When "level" is SINGLE_DEPTH_NESTING, use the nested
+	 * version to avoid the warning "possible recursive locking
+	 * detected". When "level" is 0, lock_sock_nested(sk, level)
+	 * is the same as lock_sock(sk).
+	 */
+	lock_sock_nested(sk, level);
 
-		sock_orphan(sk);
-		sk->sk_shutdown = SHUTDOWN_MASK;
+	if (vsk->transport)
+		vsk->transport->release(vsk);
+	else if (sock_type_connectible(sk->sk_type))
+		vsock_remove_sock(vsk);
 
-		skb_queue_purge(&sk->sk_receive_queue);
+	sock_orphan(sk);
+	sk->sk_shutdown = SHUTDOWN_MASK;
 
-		/* Clean up any sockets that never were accepted. */
-		while ((pending = vsock_dequeue_accept(sk)) != NULL) {
-			__vsock_release(pending, SINGLE_DEPTH_NESTING);
-			sock_put(pending);
-		}
+	skb_queue_purge(&sk->sk_receive_queue);
 
-		release_sock(sk);
-		sock_put(sk);
+	/* Clean up any sockets that never were accepted. */
+	while ((pending = vsock_dequeue_accept(sk)) != NULL) {
+		__vsock_release(pending, SINGLE_DEPTH_NESTING);
+		sock_put(pending);
 	}
+
+	release_sock(sk);
+	sock_put(sk);
 }
 
 static void vsock_sk_destruct(struct sock *sk)
@@ -901,9 +901,22 @@ void vsock_data_ready(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(vsock_data_ready);
 
+/* Dummy callback required by sockmap.
+ * See unconditional call of saved_close() in sock_map_close().
+ */
+static void vsock_close(struct sock *sk, long timeout)
+{
+}
+
 static int vsock_release(struct socket *sock)
 {
-	__vsock_release(sock->sk, 0);
+	struct sock *sk = sock->sk;
+
+	if (!sk)
+		return 0;
+
+	sk->sk_prot->close(sk, 0);
+	__vsock_release(sk, 0);
 	sock->sk = NULL;
 	sock->state = SS_FREE;
 
@@ -1054,6 +1067,9 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock,
 		mask |= EPOLLRDHUP;
 	}
 
+	if (sk_is_readable(sk))
+		mask |= EPOLLIN | EPOLLRDNORM;
+
 	if (sock->type == SOCK_DGRAM) {
 		/* For datagram sockets we can read if there is something in
 		 * the queue and write as long as the socket isn't shutdown for
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index ae71da7d2cd6..1f7975b49657 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -387,10 +387,9 @@ void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs)
 		return;
 	}
 
-	if (!refcount_dec_and_test(&dma_map->users))
-		return;
+	if (refcount_dec_and_test(&dma_map->users))
+		__xp_dma_unmap(dma_map, attrs);
 
-	__xp_dma_unmap(dma_map, attrs);
 	kvfree(pool->dma_pages);
 	pool->dma_pages = NULL;
 	pool->dma_pages_cnt = 0;
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index e1c526f97ce3..afa457506274 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -224,7 +224,7 @@ static long xsk_map_delete_elem(struct bpf_map *map, void *key)
 	struct xsk_map *m = container_of(map, struct xsk_map, map);
 	struct xdp_sock __rcu **map_entry;
 	struct xdp_sock *old_xs;
-	int k = *(u32 *)key;
+	u32 k = *(u32 *)key;
 
 	if (k >= map->max_entries)
 		return -EINVAL;