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

Daniel Borkmann says:

====================
pull-request: bpf 2021-10-26

We've added 12 non-merge commits during the last 7 day(s) which contain
a total of 23 files changed, 118 insertions(+), 98 deletions(-).

The main changes are:

1) Fix potential race window in BPF tail call compatibility check, from Toke Høiland-Jørgensen.

2) Fix memory leak in cgroup fs due to missing cgroup_bpf_offline(), from Quanyang Wang.

3) Fix file descriptor reference counting in generic_map_update_batch(), from Xu Kuohai.

4) Fix bpf_jit_limit knob to the max supported limit by the arch's JIT, from Lorenz Bauer.

5) Fix BPF sockmap ->poll callbacks for UDP and AF_UNIX sockets, from Cong Wang and Yucong Sun.

6) Fix BPF sockmap concurrency issue in TCP on non-blocking sendmsg calls, from Liu Jian.

7) Fix build failure of INODE_STORAGE and TASK_STORAGE maps on !CONFIG_NET, from Tejun Heo.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf: Fix potential race in tail call compatibility check
  bpf: Move BPF_MAP_TYPE for INODE_STORAGE and TASK_STORAGE outside of CONFIG_NET
  selftests/bpf: Use recv_timeout() instead of retries
  net: Implement ->sock_is_readable() for UDP and AF_UNIX
  skmsg: Extract and reuse sk_msg_is_readable()
  net: Rename ->stream_memory_read to ->sock_is_readable
  tcp_bpf: Fix one concurrency problem in the tcp_bpf_send_verdict function
  cgroup: Fix memory leak caused by missing cgroup_bpf_offline
  bpf: Fix error usage of map_fd and fdget() in generic_map_update_batch()
  bpf: Prevent increasing bpf_jit_limit above max
  bpf: Define bpf_jit_alloc_exec_limit for arm64 JIT
  bpf: Define bpf_jit_alloc_exec_limit for riscv JIT
====================

Link: https://lore.kernel.org/r/20211026201920.11296-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

10 files changed, 42 insertions, 22 deletions

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 2d6249b28928..a86ef7e844f8 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -474,6 +474,20 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
 }
 EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
 
+bool sk_msg_is_readable(struct sock *sk)
+{
+	struct sk_psock *psock;
+	bool empty = true;
+
+	rcu_read_lock();
+	psock = sk_psock(sk);
+	if (likely(psock))
+		empty = list_empty(&psock->ingress_msg);
+	rcu_read_unlock();
+	return !empty;
+}
+EXPORT_SYMBOL_GPL(sk_msg_is_readable);
+
 static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
 						  struct sk_buff *skb)
 {
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index c8496c1142c9..5f88526ad61c 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -419,7 +419,7 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0600,
 		.proc_handler	= proc_dolongvec_minmax_bpf_restricted,
 		.extra1		= &long_one,
-		.extra2		= &long_max,
+		.extra2		= &bpf_jit_limit_max,
 	},
 #endif
 	{
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e8b48df73c85..f5c336f8b0c8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -486,10 +486,7 @@ static bool tcp_stream_is_readable(struct sock *sk, int target)
 {
 	if (tcp_epollin_ready(sk, target))
 		return true;
-
-	if (sk->sk_prot->stream_memory_read)
-		return sk->sk_prot->stream_memory_read(sk);
-	return false;
+	return sk_is_readable(sk);
 }
 
 /*
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index d3e9386b493e..5f4d6f45d87f 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -150,19 +150,6 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg,
 EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir);
 
 #ifdef CONFIG_BPF_SYSCALL
-static bool tcp_bpf_stream_read(const struct sock *sk)
-{
-	struct sk_psock *psock;
-	bool empty = true;
-
-	rcu_read_lock();
-	psock = sk_psock(sk);
-	if (likely(psock))
-		empty = list_empty(&psock->ingress_msg);
-	rcu_read_unlock();
-	return !empty;
-}
-
 static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
 			     long timeo)
 {
@@ -232,6 +219,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 	bool cork = false, enospc = sk_msg_full(msg);
 	struct sock *sk_redir;
 	u32 tosend, delta = 0;
+	u32 eval = __SK_NONE;
 	int ret;
 
 more_data:
@@ -275,13 +263,24 @@ more_data:
 	case __SK_REDIRECT:
 		sk_redir = psock->sk_redir;
 		sk_msg_apply_bytes(psock, tosend);
+		if (!psock->apply_bytes) {
+			/* Clean up before releasing the sock lock. */
+			eval = psock->eval;
+			psock->eval = __SK_NONE;
+			psock->sk_redir = NULL;
+		}
 		if (psock->cork) {
 			cork = true;
 			psock->cork = NULL;
 		}
 		sk_msg_return(sk, msg, tosend);
 		release_sock(sk);
+
 		ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
+
+		if (eval == __SK_REDIRECT)
+			sock_put(sk_redir);
+
 		lock_sock(sk);
 		if (unlikely(ret < 0)) {
 			int free = sk_msg_free_nocharge(sk, msg);
@@ -479,7 +478,7 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
 	prot[TCP_BPF_BASE].unhash		= sock_map_unhash;
 	prot[TCP_BPF_BASE].close		= sock_map_close;
 	prot[TCP_BPF_BASE].recvmsg		= tcp_bpf_recvmsg;
-	prot[TCP_BPF_BASE].stream_memory_read	= tcp_bpf_stream_read;
+	prot[TCP_BPF_BASE].sock_is_readable	= sk_msg_is_readable;
 
 	prot[TCP_BPF_TX]			= prot[TCP_BPF_BASE];
 	prot[TCP_BPF_TX].sendmsg		= tcp_bpf_sendmsg;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8536b2a7210b..2fffcf2b54f3 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2867,6 +2867,9 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	    !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
 		mask &= ~(EPOLLIN | EPOLLRDNORM);
 
+	/* psock ingress_msg queue should not contain any bad checksum frames */
+	if (sk_is_readable(sk))
+		mask |= EPOLLIN | EPOLLRDNORM;
 	return mask;
 
 }
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 7a1d5f473878..bbe6569c9ad3 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -114,6 +114,7 @@ static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
 	*prot        = *base;
 	prot->close  = sock_map_close;
 	prot->recvmsg = udp_bpf_recvmsg;
+	prot->sock_is_readable = sk_msg_is_readable;
 }
 
 static void udp_bpf_check_v6_needs_rebuild(struct proto *ops)
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index fde56ff49163..9ab81db8a654 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -681,12 +681,12 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
 
 	prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE];
 	prot[TLS_BASE][TLS_SW].recvmsg		  = tls_sw_recvmsg;
-	prot[TLS_BASE][TLS_SW].stream_memory_read = tls_sw_stream_read;
+	prot[TLS_BASE][TLS_SW].sock_is_readable   = tls_sw_sock_is_readable;
 	prot[TLS_BASE][TLS_SW].close		  = tls_sk_proto_close;
 
 	prot[TLS_SW][TLS_SW] = prot[TLS_SW][TLS_BASE];
 	prot[TLS_SW][TLS_SW].recvmsg		= tls_sw_recvmsg;
-	prot[TLS_SW][TLS_SW].stream_memory_read	= tls_sw_stream_read;
+	prot[TLS_SW][TLS_SW].sock_is_readable   = tls_sw_sock_is_readable;
 	prot[TLS_SW][TLS_SW].close		= tls_sk_proto_close;
 
 #ifdef CONFIG_TLS_DEVICE
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 4feb95e34b64..d5d09bd817b7 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -2026,7 +2026,7 @@ splice_read_end:
 	return copied ? : err;
 }
 
-bool tls_sw_stream_read(const struct sock *sk)
+bool tls_sw_sock_is_readable(struct sock *sk)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 89f9e85ae970..78e08e82c08c 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -3052,6 +3052,8 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
 	/* readable? */
 	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
+	if (sk_is_readable(sk))
+		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Connection-based need to check for termination and startup */
 	if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
@@ -3091,6 +3093,8 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 	/* readable? */
 	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
+	if (sk_is_readable(sk))
+		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Connection-based need to check for termination and startup */
 	if (sk->sk_type == SOCK_SEQPACKET) {
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index b927e2baae50..452376c6f419 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -102,6 +102,7 @@ static void unix_dgram_bpf_rebuild_protos(struct proto *prot, const struct proto
 	*prot        = *base;
 	prot->close  = sock_map_close;
 	prot->recvmsg = unix_bpf_recvmsg;
+	prot->sock_is_readable = sk_msg_is_readable;
 }
 
 static void unix_stream_bpf_rebuild_protos(struct proto *prot,
@@ -110,6 +111,7 @@ static void unix_stream_bpf_rebuild_protos(struct proto *prot,
 	*prot        = *base;
 	prot->close  = sock_map_close;
 	prot->recvmsg = unix_bpf_recvmsg;
+	prot->sock_is_readable = sk_msg_is_readable;
 	prot->unhash  = sock_map_unhash;
 }