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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-08-13

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

The main changes are:

1) Add driver XDP support for veth. This can be used in conjunction with
   redirect of another XDP program e.g. sitting on NIC so the xdp_frame
   can be forwarded to the peer veth directly without modification,
   from Toshiaki.

2) Add a new BPF map type REUSEPORT_SOCKARRAY and prog type SK_REUSEPORT
   in order to provide more control and visibility on where a SO_REUSEPORT
   sk should be located, and the latter enables to directly select a sk
   from the bpf map. This also enables map-in-map for application migration
   use cases, from Martin.

3) Add a new BPF helper bpf_skb_ancestor_cgroup_id() that returns the id
   of cgroup v2 that is the ancestor of the cgroup associated with the
   skb at the ancestor_level, from Andrey.

4) Implement BPF fs map pretty-print support based on BTF data for regular
   hash table and LRU map, from Yonghong.

5) Decouple the ability to attach BTF for a map from the key and value
   pretty-printer in BPF fs, and enable further support of BTF for maps for
   percpu and LPM trie, from Daniel.

6) Implement a better BPF sample of using XDP's CPU redirect feature for
   load balancing SKB processing to remote CPU. The sample implements the
   same XDP load balancing as Suricata does which is symmetric hash based
   on IP and L4 protocol, from Jesper.

7) Revert adding NULL pointer check with WARN_ON_ONCE() in __xdp_return()'s
   critical path as it is ensured that the allocator is present, from Björn.
====================

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

4 files changed, 51 insertions, 6 deletions

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 5f43f7a70fe6..6def0351bcc3 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -108,6 +108,7 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
 		    u32 banned_flags);
 bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
 			  bool match_wildcard);
+bool inet_rcv_saddr_any(const struct sock *sk);
 void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr);
 void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr);
 
diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h
index 0054b3a9b923..8a5f70c7cdf2 100644
--- a/include/net/sock_reuseport.h
+++ b/include/net/sock_reuseport.h
@@ -5,25 +5,36 @@
 #include <linux/filter.h>
 #include <linux/skbuff.h>
 #include <linux/types.h>
+#include <linux/spinlock.h>
 #include <net/sock.h>
 
+extern spinlock_t reuseport_lock;
+
 struct sock_reuseport {
 	struct rcu_head		rcu;
 
 	u16			max_socks;	/* length of socks */
 	u16			num_socks;	/* elements in socks */
+	/* The last synq overflow event timestamp of this
+	 * reuse->socks[] group.
+	 */
+	unsigned int		synq_overflow_ts;
+	/* ID stays the same even after the size of socks[] grows. */
+	unsigned int		reuseport_id;
+	bool			bind_inany;
 	struct bpf_prog __rcu	*prog;		/* optional BPF sock selector */
 	struct sock		*socks[0];	/* array of sock pointers */
 };
 
-extern int reuseport_alloc(struct sock *sk);
-extern int reuseport_add_sock(struct sock *sk, struct sock *sk2);
+extern int reuseport_alloc(struct sock *sk, bool bind_inany);
+extern int reuseport_add_sock(struct sock *sk, struct sock *sk2,
+			      bool bind_inany);
 extern void reuseport_detach_sock(struct sock *sk);
 extern struct sock *reuseport_select_sock(struct sock *sk,
 					  u32 hash,
 					  struct sk_buff *skb,
 					  int hdr_len);
-extern struct bpf_prog *reuseport_attach_prog(struct sock *sk,
-					      struct bpf_prog *prog);
+extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog);
+int reuseport_get_id(struct sock_reuseport *reuse);
 
 #endif  /* _SOCK_REUSEPORT_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index d769dc20359b..d196901c9dba 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -36,6 +36,7 @@
 #include <net/inet_hashtables.h>
 #include <net/checksum.h>
 #include <net/request_sock.h>
+#include <net/sock_reuseport.h>
 #include <net/sock.h>
 #include <net/snmp.h>
 #include <net/ip.h>
@@ -473,9 +474,22 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
  */
 static inline void tcp_synq_overflow(const struct sock *sk)
 {
-	unsigned int last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	unsigned int last_overflow;
 	unsigned int now = jiffies;
 
+	if (sk->sk_reuseport) {
+		struct sock_reuseport *reuse;
+
+		reuse = rcu_dereference(sk->sk_reuseport_cb);
+		if (likely(reuse)) {
+			last_overflow = READ_ONCE(reuse->synq_overflow_ts);
+			if (time_after32(now, last_overflow + HZ))
+				WRITE_ONCE(reuse->synq_overflow_ts, now);
+			return;
+		}
+	}
+
+	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
 	if (time_after32(now, last_overflow + HZ))
 		tcp_sk(sk)->rx_opt.ts_recent_stamp = now;
 }
@@ -483,9 +497,21 @@ static inline void tcp_synq_overflow(const struct sock *sk)
 /* syncookies: no recent synqueue overflow on this listening socket? */
 static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
 {
-	unsigned int last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	unsigned int last_overflow;
 	unsigned int now = jiffies;
 
+	if (sk->sk_reuseport) {
+		struct sock_reuseport *reuse;
+
+		reuse = rcu_dereference(sk->sk_reuseport_cb);
+		if (likely(reuse)) {
+			last_overflow = READ_ONCE(reuse->synq_overflow_ts);
+			return time_after32(now, last_overflow +
+					    TCP_SYNCOOKIE_VALID);
+		}
+	}
+
+	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
 	return time_after32(now, last_overflow + TCP_SYNCOOKIE_VALID);
 }
 
diff --git a/include/net/xdp.h b/include/net/xdp.h
index fcb033f51d8c..76b95256c266 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -84,6 +84,13 @@ struct xdp_frame {
 	struct net_device *dev_rx; /* used by cpumap */
 };
 
+/* Clear kernel pointers in xdp_frame */
+static inline void xdp_scrub_frame(struct xdp_frame *frame)
+{
+	frame->data = NULL;
+	frame->dev_rx = NULL;
+}
+
 /* Convert xdp_buff to xdp_frame */
 static inline
 struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp)