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

Daniel Borkmann says:

====================
pull-request: bpf-next 2020-03-13

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

We've added 86 non-merge commits during the last 12 day(s) which contain
a total of 107 files changed, 5771 insertions(+), 1700 deletions(-).

The main changes are:

1) Add modify_return attach type which allows to attach to a function via
   BPF trampoline and is run after the fentry and before the fexit programs
   and can pass a return code to the original caller, from KP Singh.

2) Generalize BPF's kallsyms handling and add BPF trampoline and dispatcher
   objects to be visible in /proc/kallsyms so they can be annotated in
   stack traces, from Jiri Olsa.

3) Extend BPF sockmap to allow for UDP next to existing TCP support in order
   in order to enable this for BPF based socket dispatch, from Lorenz Bauer.

4) Introduce a new bpftool 'prog profile' command which attaches to existing
   BPF programs via fentry and fexit hooks and reads out hardware counters
   during that period, from Song Liu. Example usage:

   bpftool prog profile id 337 duration 3 cycles instructions llc_misses

        4228 run_cnt
     3403698 cycles                                              (84.08%)
     3525294 instructions   #  1.04 insn per cycle               (84.05%)
          13 llc_misses     #  3.69 LLC misses per million isns  (83.50%)

5) Batch of improvements to libbpf, bpftool and BPF selftests. Also addition
   of a new bpf_link abstraction to keep in particular BPF tracing programs
   attached even when the applicaion owning them exits, from Andrii Nakryiko.

6) New bpf_get_current_pid_tgid() helper for tracing to perform PID filtering
   and which returns the PID as seen by the init namespace, from Carlos Neira.

7) Refactor of RISC-V JIT code to move out common pieces and addition of a
   new RV32G BPF JIT compiler, from Luke Nelson.

8) Add gso_size context member to __sk_buff in order to be able to know whether
   a given skb is GSO or not, from Willem de Bruijn.

9) Add a new bpf_xdp_output() helper which reuses XDP's existing perf RB output
   implementation but can be called from tracepoint programs, from Eelco Chaudron.
====================

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

4 files changed, 68 insertions, 107 deletions

diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 9d97bace13c8..9e1a186a3671 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -61,6 +61,7 @@ obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
 obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
 obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
 obj-$(CONFIG_NET_SOCK_MSG) += tcp_bpf.o
+obj-$(CONFIG_BPF_STREAM_PARSER) += udp_bpf.o
 obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
 
 obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 7d6e1b75d4d4..fe7b4fbc31c1 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -528,57 +528,7 @@ out_err:
 	return copied ? copied : err;
 }
 
-static void tcp_bpf_remove(struct sock *sk, struct sk_psock *psock)
-{
-	struct sk_psock_link *link;
-
-	while ((link = sk_psock_link_pop(psock))) {
-		sk_psock_unlink(sk, link);
-		sk_psock_free_link(link);
-	}
-}
-
-static void tcp_bpf_unhash(struct sock *sk)
-{
-	void (*saved_unhash)(struct sock *sk);
-	struct sk_psock *psock;
-
-	rcu_read_lock();
-	psock = sk_psock(sk);
-	if (unlikely(!psock)) {
-		rcu_read_unlock();
-		if (sk->sk_prot->unhash)
-			sk->sk_prot->unhash(sk);
-		return;
-	}
-
-	saved_unhash = psock->saved_unhash;
-	tcp_bpf_remove(sk, psock);
-	rcu_read_unlock();
-	saved_unhash(sk);
-}
-
-static void tcp_bpf_close(struct sock *sk, long timeout)
-{
-	void (*saved_close)(struct sock *sk, long timeout);
-	struct sk_psock *psock;
-
-	lock_sock(sk);
-	rcu_read_lock();
-	psock = sk_psock(sk);
-	if (unlikely(!psock)) {
-		rcu_read_unlock();
-		release_sock(sk);
-		return sk->sk_prot->close(sk, timeout);
-	}
-
-	saved_close = psock->saved_close;
-	tcp_bpf_remove(sk, psock);
-	rcu_read_unlock();
-	release_sock(sk);
-	saved_close(sk, timeout);
-}
-
+#ifdef CONFIG_BPF_STREAM_PARSER
 enum {
 	TCP_BPF_IPV4,
 	TCP_BPF_IPV6,
@@ -599,8 +549,8 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
 				   struct proto *base)
 {
 	prot[TCP_BPF_BASE]			= *base;
-	prot[TCP_BPF_BASE].unhash		= tcp_bpf_unhash;
-	prot[TCP_BPF_BASE].close		= tcp_bpf_close;
+	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;
 
@@ -629,28 +579,6 @@ static int __init tcp_bpf_v4_build_proto(void)
 }
 core_initcall(tcp_bpf_v4_build_proto);
 
-static void tcp_bpf_update_sk_prot(struct sock *sk, struct sk_psock *psock)
-{
-	int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
-	int config = psock->progs.msg_parser   ? TCP_BPF_TX   : TCP_BPF_BASE;
-
-	sk_psock_update_proto(sk, psock, &tcp_bpf_prots[family][config]);
-}
-
-static void tcp_bpf_reinit_sk_prot(struct sock *sk, struct sk_psock *psock)
-{
-	int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
-	int config = psock->progs.msg_parser   ? TCP_BPF_TX   : TCP_BPF_BASE;
-
-	/* Reinit occurs when program types change e.g. TCP_BPF_TX is removed
-	 * or added requiring sk_prot hook updates. We keep original saved
-	 * hooks in this case.
-	 *
-	 * Pairs with lockless read in sk_clone_lock().
-	 */
-	WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]);
-}
-
 static int tcp_bpf_assert_proto_ops(struct proto *ops)
 {
 	/* In order to avoid retpoline, we make assumptions when we call
@@ -662,36 +590,21 @@ static int tcp_bpf_assert_proto_ops(struct proto *ops)
 	       ops->sendpage == tcp_sendpage ? 0 : -ENOTSUPP;
 }
 
-void tcp_bpf_reinit(struct sock *sk)
+struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
 {
-	struct sk_psock *psock;
-
-	sock_owned_by_me(sk);
-
-	rcu_read_lock();
-	psock = sk_psock(sk);
-	tcp_bpf_reinit_sk_prot(sk, psock);
-	rcu_read_unlock();
-}
+	int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
+	int config = psock->progs.msg_parser   ? TCP_BPF_TX   : TCP_BPF_BASE;
 
-int tcp_bpf_init(struct sock *sk)
-{
-	struct proto *ops = READ_ONCE(sk->sk_prot);
-	struct sk_psock *psock;
+	if (!psock->sk_proto) {
+		struct proto *ops = READ_ONCE(sk->sk_prot);
 
-	sock_owned_by_me(sk);
+		if (tcp_bpf_assert_proto_ops(ops))
+			return ERR_PTR(-EINVAL);
 
-	rcu_read_lock();
-	psock = sk_psock(sk);
-	if (unlikely(!psock || psock->sk_proto ||
-		     tcp_bpf_assert_proto_ops(ops))) {
-		rcu_read_unlock();
-		return -EINVAL;
+		tcp_bpf_check_v6_needs_rebuild(sk, ops);
 	}
-	tcp_bpf_check_v6_needs_rebuild(sk, ops);
-	tcp_bpf_update_sk_prot(sk, psock);
-	rcu_read_unlock();
-	return 0;
+
+	return &tcp_bpf_prots[family][config];
 }
 
 /* If a child got cloned from a listening socket that had tcp_bpf
@@ -707,3 +620,4 @@ void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
 	if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE])
 		newsk->sk_prot = sk->sk_prot_creator;
 }
+#endif /* CONFIG_BPF_STREAM_PARSER */
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 2703f24c5d1a..7c27aa629af1 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -105,13 +105,6 @@ void tcp_update_ulp(struct sock *sk, struct proto *proto,
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
-	if (!icsk->icsk_ulp_ops) {
-		sk->sk_write_space = write_space;
-		/* Pairs with lockless read in sk_clone_lock() */
-		WRITE_ONCE(sk->sk_prot, proto);
-		return;
-	}
-
 	if (icsk->icsk_ulp_ops->update)
 		icsk->icsk_ulp_ops->update(sk, proto, write_space);
 }
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
new file mode 100644
index 000000000000..eddd973e6575
--- /dev/null
+++ b/net/ipv4/udp_bpf.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Cloudflare Ltd https://cloudflare.com */
+
+#include <linux/skmsg.h>
+#include <net/sock.h>
+#include <net/udp.h>
+
+enum {
+	UDP_BPF_IPV4,
+	UDP_BPF_IPV6,
+	UDP_BPF_NUM_PROTS,
+};
+
+static struct proto *udpv6_prot_saved __read_mostly;
+static DEFINE_SPINLOCK(udpv6_prot_lock);
+static struct proto udp_bpf_prots[UDP_BPF_NUM_PROTS];
+
+static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
+{
+	*prot        = *base;
+	prot->unhash = sock_map_unhash;
+	prot->close  = sock_map_close;
+}
+
+static void udp_bpf_check_v6_needs_rebuild(struct sock *sk, struct proto *ops)
+{
+	if (sk->sk_family == AF_INET6 &&
+	    unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) {
+		spin_lock_bh(&udpv6_prot_lock);
+		if (likely(ops != udpv6_prot_saved)) {
+			udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV6], ops);
+			smp_store_release(&udpv6_prot_saved, ops);
+		}
+		spin_unlock_bh(&udpv6_prot_lock);
+	}
+}
+
+static int __init udp_bpf_v4_build_proto(void)
+{
+	udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV4], &udp_prot);
+	return 0;
+}
+core_initcall(udp_bpf_v4_build_proto);
+
+struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
+{
+	int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6;
+
+	if (!psock->sk_proto)
+		udp_bpf_check_v6_needs_rebuild(sk, READ_ONCE(sk->sk_prot));
+
+	return &udp_bpf_prots[family];
+}