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>

10 files changed, 231 insertions, 11 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index cd8790d2c6ed..523481a3471b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -23,7 +23,7 @@ struct bpf_prog;
 struct bpf_map;
 struct sock;
 struct seq_file;
-struct btf;
+struct btf_type;
 
 /* map is generic key/value storage optionally accesible by eBPF programs */
 struct bpf_map_ops {
@@ -48,8 +48,9 @@ struct bpf_map_ops {
 	u32 (*map_fd_sys_lookup_elem)(void *ptr);
 	void (*map_seq_show_elem)(struct bpf_map *map, void *key,
 				  struct seq_file *m);
-	int (*map_check_btf)(const struct bpf_map *map, const struct btf *btf,
-			     u32 key_type_id, u32 value_type_id);
+	int (*map_check_btf)(const struct bpf_map *map,
+			     const struct btf_type *key_type,
+			     const struct btf_type *value_type);
 };
 
 struct bpf_map {
@@ -118,9 +119,13 @@ static inline bool bpf_map_offload_neutral(const struct bpf_map *map)
 
 static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
 {
-	return map->ops->map_seq_show_elem && map->ops->map_check_btf;
+	return map->btf && map->ops->map_seq_show_elem;
 }
 
+int map_check_no_btf(const struct bpf_map *map,
+		     const struct btf_type *key_type,
+		     const struct btf_type *value_type);
+
 extern const struct bpf_map_ops bpf_map_offload_ops;
 
 /* function argument constraints */
@@ -524,6 +529,7 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
 }
 
 struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type);
+int array_map_alloc_check(union bpf_attr *attr);
 
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
@@ -769,6 +775,33 @@ static inline void __xsk_map_flush(struct bpf_map *map)
 }
 #endif
 
+#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
+void bpf_sk_reuseport_detach(struct sock *sk);
+int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
+				       void *value);
+int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
+				       void *value, u64 map_flags);
+#else
+static inline void bpf_sk_reuseport_detach(struct sock *sk)
+{
+}
+
+#ifdef CONFIG_BPF_SYSCALL
+static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map,
+						     void *key, void *value)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map,
+						     void *key, void *value,
+						     u64 map_flags)
+{
+	return -EOPNOTSUPP;
+}
+#endif /* CONFIG_BPF_SYSCALL */
+#endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */
+
 /* verifier prototypes for helper functions called from eBPF programs */
 extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
 extern const struct bpf_func_proto bpf_map_update_elem_proto;
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index add08be53b6f..cd26c090e7c0 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -29,6 +29,9 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
 #ifdef CONFIG_BPF_LIRC_MODE2
 BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2)
 #endif
+#ifdef CONFIG_INET
+BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport)
+#endif
 
 BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops)
@@ -60,4 +63,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
 #if defined(CONFIG_XDP_SOCKETS)
 BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
 #endif
+#ifdef CONFIG_INET
+BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops)
+#endif
 #endif
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c9fdf6f57913..32c553556bbd 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -554,6 +554,36 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp,
 }
 
 /**
+ * cgroup_ancestor - find ancestor of cgroup
+ * @cgrp: cgroup to find ancestor of
+ * @ancestor_level: level of ancestor to find starting from root
+ *
+ * Find ancestor of cgroup at specified level starting from root if it exists
+ * and return pointer to it. Return NULL if @cgrp doesn't have ancestor at
+ * @ancestor_level.
+ *
+ * This function is safe to call as long as @cgrp is accessible.
+ */
+static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp,
+					     int ancestor_level)
+{
+	struct cgroup *ptr;
+
+	if (cgrp->level < ancestor_level)
+		return NULL;
+
+	for (ptr = cgrp;
+	     ptr && ptr->level > ancestor_level;
+	     ptr = cgroup_parent(ptr))
+		;
+
+	if (ptr && ptr->level == ancestor_level)
+		return ptr;
+
+	return NULL;
+}
+
+/**
  * task_under_cgroup_hierarchy - test task's membership of cgroup ancestry
  * @task: the task to be tested
  * @ancestor: possible ancestor of @task's cgroup
diff --git a/include/linux/filter.h b/include/linux/filter.h
index c73dd7396886..5d565c50bcb2 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -32,6 +32,7 @@ struct seccomp_data;
 struct bpf_prog_aux;
 struct xdp_rxq_info;
 struct xdp_buff;
+struct sock_reuseport;
 
 /* ArgX, context and stack frame pointer register positions. Note,
  * Arg1, Arg2, Arg3, etc are used as argument mappings of function
@@ -537,6 +538,20 @@ struct sk_msg_buff {
 	struct list_head list;
 };
 
+struct bpf_redirect_info {
+	u32 ifindex;
+	u32 flags;
+	struct bpf_map *map;
+	struct bpf_map *map_to_flush;
+	unsigned long   map_owner;
+	u32 kern_flags;
+};
+
+DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
+
+/* flags for bpf_redirect_info kern_flags */
+#define BPF_RI_F_RF_NO_DIRECT	BIT(0)	/* no napi_direct on return_frame */
+
 /* Compute the linear packet data range [data, data_end) which
  * will be accessed by various program types (cls_bpf, act_bpf,
  * lwt, ...). Subsystems allowing direct data access must (!)
@@ -738,6 +753,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
 int sk_attach_bpf(u32 ufd, struct sock *sk);
 int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk);
 int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk);
+void sk_reuseport_prog_free(struct bpf_prog *prog);
 int sk_detach_filter(struct sock *sk);
 int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
 		  unsigned int len);
@@ -765,6 +781,27 @@ static inline bool bpf_dump_raw_ok(void)
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
 
+static inline bool xdp_return_frame_no_direct(void)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT;
+}
+
+static inline void xdp_set_return_frame_no_direct(void)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT;
+}
+
+static inline void xdp_clear_return_frame_no_direct(void)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT;
+}
+
 static inline int xdp_ok_fwd_dev(const struct net_device *fwd,
 				 unsigned int pktlen)
 {
@@ -798,6 +835,20 @@ void bpf_warn_invalid_xdp_action(u32 act);
 struct sock *do_sk_redirect_map(struct sk_buff *skb);
 struct sock *do_msg_redirect_map(struct sk_msg_buff *md);
 
+#ifdef CONFIG_INET
+struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
+				  struct bpf_prog *prog, struct sk_buff *skb,
+				  u32 hash);
+#else
+static inline struct sock *
+bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
+		     struct bpf_prog *prog, struct sk_buff *skb,
+		     u32 hash)
+{
+	return NULL;
+}
+#endif
+
 #ifdef CONFIG_BPF_JIT
 extern int bpf_jit_enable;
 extern int bpf_jit_harden;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7e237a63a70c..17a13e4785fc 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1038,6 +1038,7 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
 }
 
 struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src);
+void skb_headers_offset_update(struct sk_buff *skb, int off);
 int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask);
 struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority);
 void skb_copy_header(struct sk_buff *new, const struct sk_buff *old);
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)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index dd5758dc35d3..66917a4eba27 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -126,6 +126,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_XSKMAP,
 	BPF_MAP_TYPE_SOCKHASH,
 	BPF_MAP_TYPE_CGROUP_STORAGE,
+	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 };
 
 enum bpf_prog_type {
@@ -150,6 +151,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
 	BPF_PROG_TYPE_LWT_SEG6LOCAL,
 	BPF_PROG_TYPE_LIRC_MODE2,
+	BPF_PROG_TYPE_SK_REUSEPORT,
 };
 
 enum bpf_attach_type {
@@ -2091,6 +2093,24 @@ union bpf_attr {
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ *	Description
+ *		Return id of cgroup v2 that is ancestor of cgroup associated
+ *		with the *skb* at the *ancestor_level*.  The root cgroup is at
+ *		*ancestor_level* zero and each step down the hierarchy
+ *		increments the level. If *ancestor_level* == level of cgroup
+ *		associated with *skb*, then return value will be same as that
+ *		of **bpf_skb_cgroup_id**\ ().
+ *
+ *		The helper is useful to implement policies based on cgroups
+ *		that are upper in hierarchy than immediate cgroup associated
+ *		with *skb*.
+ *
+ *		The format of returned id and helper limitations are same as in
+ *		**bpf_skb_cgroup_id**\ ().
+ *	Return
+ *		The id is returned or 0 in case the id could not be retrieved.
+ *
  * u64 bpf_get_current_cgroup_id(void)
  * 	Return
  * 		A 64-bit integer containing the current cgroup id based
@@ -2113,6 +2133,14 @@ union bpf_attr {
  *		the shared data.
  *	Return
  *		Pointer to the local storage area.
+ *
+ * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
+ *	Description
+ *		Select a SO_REUSEPORT sk from a	BPF_MAP_TYPE_REUSEPORT_ARRAY map
+ *		It checks the selected sk is matching the incoming
+ *		request in the skb.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2196,7 +2224,9 @@ union bpf_attr {
 	FN(rc_keydown),			\
 	FN(skb_cgroup_id),		\
 	FN(get_current_cgroup_id),	\
-	FN(get_local_storage),
+	FN(get_local_storage),		\
+	FN(sk_select_reuseport),	\
+	FN(skb_ancestor_cgroup_id),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2413,6 +2443,30 @@ struct sk_msg_md {
 	__u32 local_port;	/* stored in host byte order */
 };
 
+struct sk_reuseport_md {
+	/*
+	 * Start of directly accessible data. It begins from
+	 * the tcp/udp header.
+	 */
+	void *data;
+	void *data_end;		/* End of directly accessible data */
+	/*
+	 * Total length of packet (starting from the tcp/udp header).
+	 * Note that the directly accessible bytes (data_end - data)
+	 * could be less than this "len".  Those bytes could be
+	 * indirectly read by a helper "bpf_skb_load_bytes()".
+	 */
+	__u32 len;
+	/*
+	 * Eth protocol in the mac header (network byte order). e.g.
+	 * ETH_P_IP(0x0800) and ETH_P_IPV6(0x86DD)
+	 */
+	__u32 eth_protocol;
+	__u32 ip_protocol;	/* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
+	__u32 bind_inany;	/* Is sock bound to an INANY address? */
+	__u32 hash;		/* A hash of the packet 4 tuples */
+};
+
 #define BPF_TAG_SIZE	8
 
 struct bpf_prog_info {