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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-07-21

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

We've added 46 non-merge commits during the last 6 day(s) which contain
a total of 68 files changed, 4929 insertions(+), 526 deletions(-).

The main changes are:

1) Run BPF program on socket lookup, from Jakub.

2) Introduce cpumap, from Lorenzo.

3) s390 JIT fixes, from Ilya.

4) teach riscv JIT to emit compressed insns, from Luke.

5) use build time computed BTF ids in bpf iter, from Yonghong.
====================

Purely independent overlapping changes in both filter.h and xdp.h

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

8 files changed, 335 insertions, 27 deletions

diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h
index 47d5b0c708c9..722f799c1a2e 100644
--- a/include/linux/bpf-netns.h
+++ b/include/linux/bpf-netns.h
@@ -8,6 +8,7 @@
 enum netns_bpf_attach_type {
 	NETNS_BPF_INVALID = -1,
 	NETNS_BPF_FLOW_DISSECTOR = 0,
+	NETNS_BPF_SK_LOOKUP,
 	MAX_NETNS_BPF_ATTACH_TYPE
 };
 
@@ -17,6 +18,8 @@ to_netns_bpf_attach_type(enum bpf_attach_type attach_type)
 	switch (attach_type) {
 	case BPF_FLOW_DISSECTOR:
 		return NETNS_BPF_FLOW_DISSECTOR;
+	case BPF_SK_LOOKUP:
+		return NETNS_BPF_SK_LOOKUP;
 	default:
 		return NETNS_BPF_INVALID;
 	}
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c67c88ad35f8..bae557ff2da8 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -249,6 +249,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_INT,		/* pointer to int */
 	ARG_PTR_TO_LONG,	/* pointer to long */
 	ARG_PTR_TO_SOCKET,	/* pointer to bpf_sock (fullsock) */
+	ARG_PTR_TO_SOCKET_OR_NULL,	/* pointer to bpf_sock (fullsock) or NULL */
 	ARG_PTR_TO_BTF_ID,	/* pointer to in-kernel struct */
 	ARG_PTR_TO_ALLOC_MEM,	/* pointer to dynamically allocated memory */
 	ARG_PTR_TO_ALLOC_MEM_OR_NULL,	/* pointer to dynamically allocated memory or NULL */
@@ -667,6 +668,7 @@ struct bpf_jit_poke_descriptor {
 struct bpf_ctx_arg_aux {
 	u32 offset;
 	enum bpf_reg_type reg_type;
+	u32 btf_id;
 };
 
 struct bpf_prog_aux {
@@ -928,6 +930,9 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs,
 
 void bpf_prog_array_delete_safe(struct bpf_prog_array *progs,
 				struct bpf_prog *old_prog);
+int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index);
+int bpf_prog_array_update_at(struct bpf_prog_array *array, int index,
+			     struct bpf_prog *prog);
 int bpf_prog_array_copy_info(struct bpf_prog_array *array,
 			     u32 *prog_ids, u32 request_cnt,
 			     u32 *prog_cnt);
@@ -1272,6 +1277,7 @@ struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
 void __cpu_map_flush(void);
 int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
 		    struct net_device *dev_rx);
+bool cpu_map_prog_allowed(struct bpf_map *map);
 
 /* Return map's numa specified by userspace */
 static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
@@ -1432,6 +1438,11 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
 	return 0;
 }
 
+static inline bool cpu_map_prog_allowed(struct bpf_map *map)
+{
+	return false;
+}
+
 static inline struct bpf_prog *bpf_prog_get_type_path(const char *name,
 				enum bpf_prog_type type)
 {
@@ -1531,7 +1542,6 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map)
 
 struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr);
 void bpf_map_offload_map_free(struct bpf_map *map);
-void init_btf_sock_ids(struct btf *btf);
 #else
 static inline int bpf_prog_offload_init(struct bpf_prog *prog,
 					union bpf_attr *attr)
@@ -1557,9 +1567,6 @@ static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 static inline void bpf_map_offload_map_free(struct bpf_map *map)
 {
 }
-static inline void init_btf_sock_ids(struct btf *btf)
-{
-}
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
 #if defined(CONFIG_BPF_STREAM_PARSER)
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index a18ae82a298a..a52a5688418e 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -64,6 +64,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2,
 #ifdef CONFIG_INET
 BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport,
 	      struct sk_reuseport_md, struct sk_reuseport_kern)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SK_LOOKUP, sk_lookup,
+	      struct bpf_sk_lookup, struct bpf_sk_lookup_kern)
 #endif
 #if defined(CONFIG_BPF_JIT)
 BPF_PROG_TYPE(BPF_PROG_TYPE_STRUCT_OPS, bpf_struct_ops,
diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 1cdb56950ffe..4867d549e3c1 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -57,17 +57,20 @@ asm(							\
  * .zero 4
  *
  */
-#define __BTF_ID_LIST(name)				\
+#define __BTF_ID_LIST(name, scope)			\
 asm(							\
 ".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
-".local " #name ";                             \n"	\
+"." #scope " " #name ";                        \n"	\
 #name ":;                                      \n"	\
 ".popsection;                                  \n");	\
 
 #define BTF_ID_LIST(name)				\
-__BTF_ID_LIST(name)					\
+__BTF_ID_LIST(name, local)				\
 extern u32 name[];
 
+#define BTF_ID_LIST_GLOBAL(name)			\
+__BTF_ID_LIST(name, globl)
+
 /*
  * The BTF_ID_UNUSED macro defines 4 zero bytes.
  * It's used when we want to define 'unused' entry
@@ -90,7 +93,38 @@ asm(							\
 #define BTF_ID_LIST(name) static u32 name[5];
 #define BTF_ID(prefix, name)
 #define BTF_ID_UNUSED
+#define BTF_ID_LIST_GLOBAL(name) u32 name[1];
 
 #endif /* CONFIG_DEBUG_INFO_BTF */
 
+#ifdef CONFIG_NET
+/* Define a list of socket types which can be the argument for
+ * skc_to_*_sock() helpers. All these sockets should have
+ * sock_common as the first argument in its memory layout.
+ */
+#define BTF_SOCK_TYPE_xxx \
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET, inet_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_CONN, inet_connection_sock)	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_REQ, inet_request_sock)	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_INET_TW, inet_timewait_sock)	\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_REQ, request_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK, sock)				\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCK_COMMON, sock_common)		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP, tcp_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_REQ, tcp_request_sock)		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP_TW, tcp_timewait_sock)		\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_TCP6, tcp6_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock)
+
+enum {
+#define BTF_SOCK_TYPE(name, str) name,
+BTF_SOCK_TYPE_xxx
+#undef BTF_SOCK_TYPE
+MAX_BTF_SOCK_TYPE,
+};
+
+extern u32 btf_sock_ids[];
+#endif
+
 #endif
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 4d049c8e1fbe..1c6b6d982bf4 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1278,4 +1278,151 @@ struct bpf_sockopt_kern {
 
 int copy_bpf_fprog_from_user(struct sock_fprog *dst, void __user *src, int len);
 
+struct bpf_sk_lookup_kern {
+	u16		family;
+	u16		protocol;
+	struct {
+		__be32 saddr;
+		__be32 daddr;
+	} v4;
+	struct {
+		const struct in6_addr *saddr;
+		const struct in6_addr *daddr;
+	} v6;
+	__be16		sport;
+	u16		dport;
+	struct sock	*selected_sk;
+	bool		no_reuseport;
+};
+
+extern struct static_key_false bpf_sk_lookup_enabled;
+
+/* Runners for BPF_SK_LOOKUP programs to invoke on socket lookup.
+ *
+ * Allowed return values for a BPF SK_LOOKUP program are SK_PASS and
+ * SK_DROP. Their meaning is as follows:
+ *
+ *  SK_PASS && ctx.selected_sk != NULL: use selected_sk as lookup result
+ *  SK_PASS && ctx.selected_sk == NULL: continue to htable-based socket lookup
+ *  SK_DROP                           : terminate lookup with -ECONNREFUSED
+ *
+ * This macro aggregates return values and selected sockets from
+ * multiple BPF programs according to following rules in order:
+ *
+ *  1. If any program returned SK_PASS and a non-NULL ctx.selected_sk,
+ *     macro result is SK_PASS and last ctx.selected_sk is used.
+ *  2. If any program returned SK_DROP return value,
+ *     macro result is SK_DROP.
+ *  3. Otherwise result is SK_PASS and ctx.selected_sk is NULL.
+ *
+ * Caller must ensure that the prog array is non-NULL, and that the
+ * array as well as the programs it contains remain valid.
+ */
+#define BPF_PROG_SK_LOOKUP_RUN_ARRAY(array, ctx, func)			\
+	({								\
+		struct bpf_sk_lookup_kern *_ctx = &(ctx);		\
+		struct bpf_prog_array_item *_item;			\
+		struct sock *_selected_sk = NULL;			\
+		bool _no_reuseport = false;				\
+		struct bpf_prog *_prog;					\
+		bool _all_pass = true;					\
+		u32 _ret;						\
+									\
+		migrate_disable();					\
+		_item = &(array)->items[0];				\
+		while ((_prog = READ_ONCE(_item->prog))) {		\
+			/* restore most recent selection */		\
+			_ctx->selected_sk = _selected_sk;		\
+			_ctx->no_reuseport = _no_reuseport;		\
+									\
+			_ret = func(_prog, _ctx);			\
+			if (_ret == SK_PASS && _ctx->selected_sk) {	\
+				/* remember last non-NULL socket */	\
+				_selected_sk = _ctx->selected_sk;	\
+				_no_reuseport = _ctx->no_reuseport;	\
+			} else if (_ret == SK_DROP && _all_pass) {	\
+				_all_pass = false;			\
+			}						\
+			_item++;					\
+		}							\
+		_ctx->selected_sk = _selected_sk;			\
+		_ctx->no_reuseport = _no_reuseport;			\
+		migrate_enable();					\
+		_all_pass || _selected_sk ? SK_PASS : SK_DROP;		\
+	 })
+
+static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol,
+					const __be32 saddr, const __be16 sport,
+					const __be32 daddr, const u16 dport,
+					struct sock **psk)
+{
+	struct bpf_prog_array *run_array;
+	struct sock *selected_sk = NULL;
+	bool no_reuseport = false;
+
+	rcu_read_lock();
+	run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]);
+	if (run_array) {
+		struct bpf_sk_lookup_kern ctx = {
+			.family		= AF_INET,
+			.protocol	= protocol,
+			.v4.saddr	= saddr,
+			.v4.daddr	= daddr,
+			.sport		= sport,
+			.dport		= dport,
+		};
+		u32 act;
+
+		act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN);
+		if (act == SK_PASS) {
+			selected_sk = ctx.selected_sk;
+			no_reuseport = ctx.no_reuseport;
+		} else {
+			selected_sk = ERR_PTR(-ECONNREFUSED);
+		}
+	}
+	rcu_read_unlock();
+	*psk = selected_sk;
+	return no_reuseport;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol,
+					const struct in6_addr *saddr,
+					const __be16 sport,
+					const struct in6_addr *daddr,
+					const u16 dport,
+					struct sock **psk)
+{
+	struct bpf_prog_array *run_array;
+	struct sock *selected_sk = NULL;
+	bool no_reuseport = false;
+
+	rcu_read_lock();
+	run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]);
+	if (run_array) {
+		struct bpf_sk_lookup_kern ctx = {
+			.family		= AF_INET6,
+			.protocol	= protocol,
+			.v6.saddr	= saddr,
+			.v6.daddr	= daddr,
+			.sport		= sport,
+			.dport		= dport,
+		};
+		u32 act;
+
+		act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, BPF_PROG_RUN);
+		if (act == SK_PASS) {
+			selected_sk = ctx.selected_sk;
+			no_reuseport = ctx.no_reuseport;
+		} else {
+			selected_sk = ERR_PTR(-ECONNREFUSED);
+		}
+	}
+	rcu_read_unlock();
+	*psk = selected_sk;
+	return no_reuseport;
+}
+#endif /* IS_ENABLED(CONFIG_IPV6) */
+
 #endif /* __LINUX_FILTER_H__ */
diff --git a/include/net/xdp.h b/include/net/xdp.h
index d3005bef812f..dbe9c60797e1 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -104,6 +104,7 @@ struct xdp_frame {
 	struct net_device *dev_rx; /* used by cpumap */
 };
 
+
 static inline struct skb_shared_info *
 xdp_get_shared_info_from_frame(struct xdp_frame *frame)
 {
@@ -113,6 +114,12 @@ xdp_get_shared_info_from_frame(struct xdp_frame *frame)
 				SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
 }
 
+struct xdp_cpumap_stats {
+	unsigned int redirect;
+	unsigned int pass;
+	unsigned int drop;
+};
+
 /* Clear kernel pointers in xdp_frame */
 static inline void xdp_scrub_frame(struct xdp_frame *frame)
 {
@@ -136,39 +143,48 @@ void xdp_convert_frame_to_buff(struct xdp_frame *frame, struct xdp_buff *xdp)
 	xdp->frame_sz = frame->frame_sz;
 }
 
-/* Convert xdp_buff to xdp_frame */
 static inline
-struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp)
+int xdp_update_frame_from_buff(struct xdp_buff *xdp,
+			       struct xdp_frame *xdp_frame)
 {
-	struct xdp_frame *xdp_frame;
-	int metasize;
-	int headroom;
-
-	if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL)
-		return xdp_convert_zc_to_xdp_frame(xdp);
+	int metasize, headroom;
 
 	/* Assure headroom is available for storing info */
 	headroom = xdp->data - xdp->data_hard_start;
 	metasize = xdp->data - xdp->data_meta;
 	metasize = metasize > 0 ? metasize : 0;
 	if (unlikely((headroom - metasize) < sizeof(*xdp_frame)))
-		return NULL;
+		return -ENOSPC;
 
 	/* Catch if driver didn't reserve tailroom for skb_shared_info */
 	if (unlikely(xdp->data_end > xdp_data_hard_end(xdp))) {
 		XDP_WARN("Driver BUG: missing reserved tailroom");
-		return NULL;
+		return -ENOSPC;
 	}
 
-	/* Store info in top of packet */
-	xdp_frame = xdp->data_hard_start;
-
 	xdp_frame->data = xdp->data;
 	xdp_frame->len  = xdp->data_end - xdp->data;
 	xdp_frame->headroom = headroom - sizeof(*xdp_frame);
 	xdp_frame->metasize = metasize;
 	xdp_frame->frame_sz = xdp->frame_sz;
 
+	return 0;
+}
+
+/* Convert xdp_buff to xdp_frame */
+static inline
+struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp)
+{
+	struct xdp_frame *xdp_frame;
+
+	if (xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL)
+		return xdp_convert_zc_to_xdp_frame(xdp);
+
+	/* Store info in top of packet */
+	xdp_frame = xdp->data_hard_start;
+	if (unlikely(xdp_update_frame_from_buff(xdp, xdp_frame) < 0))
+		return NULL;
+
 	/* rxq only valid until napi_schedule ends, convert to xdp_mem_info */
 	xdp_frame->mem = xdp->rxq->mem;
 
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index b73d3e141323..cd24e8a59529 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -177,9 +177,9 @@ DEFINE_EVENT(xdp_redirect_template, xdp_redirect_map_err,
 TRACE_EVENT(xdp_cpumap_kthread,
 
 	TP_PROTO(int map_id, unsigned int processed,  unsigned int drops,
-		 int sched),
+		 int sched, struct xdp_cpumap_stats *xdp_stats),
 
-	TP_ARGS(map_id, processed, drops, sched),
+	TP_ARGS(map_id, processed, drops, sched, xdp_stats),
 
 	TP_STRUCT__entry(
 		__field(int, map_id)
@@ -188,6 +188,9 @@ TRACE_EVENT(xdp_cpumap_kthread,
 		__field(unsigned int, drops)
 		__field(unsigned int, processed)
 		__field(int, sched)
+		__field(unsigned int, xdp_pass)
+		__field(unsigned int, xdp_drop)
+		__field(unsigned int, xdp_redirect)
 	),
 
 	TP_fast_assign(
@@ -197,16 +200,21 @@ TRACE_EVENT(xdp_cpumap_kthread,
 		__entry->drops		= drops;
 		__entry->processed	= processed;
 		__entry->sched	= sched;
+		__entry->xdp_pass	= xdp_stats->pass;
+		__entry->xdp_drop	= xdp_stats->drop;
+		__entry->xdp_redirect	= xdp_stats->redirect;
 	),
 
 	TP_printk("kthread"
 		  " cpu=%d map_id=%d action=%s"
 		  " processed=%u drops=%u"
-		  " sched=%d",
+		  " sched=%d"
+		  " xdp_pass=%u xdp_drop=%u xdp_redirect=%u",
 		  __entry->cpu, __entry->map_id,
 		  __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
 		  __entry->processed, __entry->drops,
-		  __entry->sched)
+		  __entry->sched,
+		  __entry->xdp_pass, __entry->xdp_drop, __entry->xdp_redirect)
 );
 
 TRACE_EVENT(xdp_cpumap_enqueue,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 5e386389913a..54d0c886e3ba 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -189,6 +189,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_STRUCT_OPS,
 	BPF_PROG_TYPE_EXT,
 	BPF_PROG_TYPE_LSM,
+	BPF_PROG_TYPE_SK_LOOKUP,
 };
 
 enum bpf_attach_type {
@@ -227,6 +228,8 @@ enum bpf_attach_type {
 	BPF_CGROUP_INET6_GETSOCKNAME,
 	BPF_XDP_DEVMAP,
 	BPF_CGROUP_INET_SOCK_RELEASE,
+	BPF_XDP_CPUMAP,
+	BPF_SK_LOOKUP,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -2419,7 +2422,7 @@ union bpf_attr {
  *			Look for an IPv6 socket.
  *
  *		If the *netns* is a negative signed 32-bit integer, then the
- *		socket lookup table in the netns associated with the *ctx* will
+ *		socket lookup table in the netns associated with the *ctx*
  *		will be used. For the TC hooks, this is the netns of the device
  *		in the skb. For socket hooks, this is the netns of the socket.
  *		If *netns* is any other signed 32-bit value greater than or
@@ -2456,7 +2459,7 @@ union bpf_attr {
  *			Look for an IPv6 socket.
  *
  *		If the *netns* is a negative signed 32-bit integer, then the
- *		socket lookup table in the netns associated with the *ctx* will
+ *		socket lookup table in the netns associated with the *ctx*
  *		will be used. For the TC hooks, this is the netns of the device
  *		in the skb. For socket hooks, this is the netns of the socket.
  *		If *netns* is any other signed 32-bit value greater than or
@@ -3068,6 +3071,10 @@ union bpf_attr {
  *
  * long bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
  *	Description
+ *		Helper is overloaded depending on BPF program type. This
+ *		description applies to **BPF_PROG_TYPE_SCHED_CLS** and
+ *		**BPF_PROG_TYPE_SCHED_ACT** programs.
+ *
  *		Assign the *sk* to the *skb*. When combined with appropriate
  *		routing configuration to receive the packet towards the socket,
  *		will cause *skb* to be delivered to the specified socket.
@@ -3093,6 +3100,56 @@ union bpf_attr {
  *		**-ESOCKTNOSUPPORT** if the socket type is not supported
  *		(reuseport).
  *
+ * long bpf_sk_assign(struct bpf_sk_lookup *ctx, struct bpf_sock *sk, u64 flags)
+ *	Description
+ *		Helper is overloaded depending on BPF program type. This
+ *		description applies to **BPF_PROG_TYPE_SK_LOOKUP** programs.
+ *
+ *		Select the *sk* as a result of a socket lookup.
+ *
+ *		For the operation to succeed passed socket must be compatible
+ *		with the packet description provided by the *ctx* object.
+ *
+ *		L4 protocol (**IPPROTO_TCP** or **IPPROTO_UDP**) must
+ *		be an exact match. While IP family (**AF_INET** or
+ *		**AF_INET6**) must be compatible, that is IPv6 sockets
+ *		that are not v6-only can be selected for IPv4 packets.
+ *
+ *		Only TCP listeners and UDP unconnected sockets can be
+ *		selected. *sk* can also be NULL to reset any previous
+ *		selection.
+ *
+ *		*flags* argument can combination of following values:
+ *
+ *		* **BPF_SK_LOOKUP_F_REPLACE** to override the previous
+ *		  socket selection, potentially done by a BPF program
+ *		  that ran before us.
+ *
+ *		* **BPF_SK_LOOKUP_F_NO_REUSEPORT** to skip
+ *		  load-balancing within reuseport group for the socket
+ *		  being selected.
+ *
+ *		On success *ctx->sk* will point to the selected socket.
+ *
+ *	Return
+ *		0 on success, or a negative errno in case of failure.
+ *
+ *		* **-EAFNOSUPPORT** if socket family (*sk->family*) is
+ *		  not compatible with packet family (*ctx->family*).
+ *
+ *		* **-EEXIST** if socket has been already selected,
+ *		  potentially by another program, and
+ *		  **BPF_SK_LOOKUP_F_REPLACE** flag was not specified.
+ *
+ *		* **-EINVAL** if unsupported flags were specified.
+ *
+ *		* **-EPROTOTYPE** if socket L4 protocol
+ *		  (*sk->protocol*) doesn't match packet protocol
+ *		  (*ctx->protocol*).
+ *
+ *		* **-ESOCKTNOSUPPORT** if socket is not in allowed
+ *		  state (TCP listening or UDP unconnected).
+ *
  * u64 bpf_ktime_get_boot_ns(void)
  * 	Description
  * 		Return the time elapsed since system boot, in nanoseconds.
@@ -3606,6 +3663,12 @@ enum {
 	BPF_RINGBUF_HDR_SZ		= 8,
 };
 
+/* BPF_FUNC_sk_assign flags in bpf_sk_lookup context. */
+enum {
+	BPF_SK_LOOKUP_F_REPLACE		= (1ULL << 0),
+	BPF_SK_LOOKUP_F_NO_REUSEPORT	= (1ULL << 1),
+};
+
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
 	BPF_ADJ_ROOM_NET,
@@ -3849,6 +3912,19 @@ struct bpf_devmap_val {
 	} bpf_prog;
 };
 
+/* CPUMAP map-value layout
+ *
+ * The struct data-layout of map-value is a configuration interface.
+ * New members can only be added to the end of this structure.
+ */
+struct bpf_cpumap_val {
+	__u32 qsize;	/* queue size to remote target CPU */
+	union {
+		int   fd;	/* prog fd on map write */
+		__u32 id;	/* prog id on map read */
+	} bpf_prog;
+};
+
 enum sk_action {
 	SK_DROP = 0,
 	SK_PASS,
@@ -3986,7 +4062,7 @@ struct bpf_link_info {
 
 /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
  * by user and intended to be used by socket (e.g. to bind to, depends on
- * attach attach type).
+ * attach type).
  */
 struct bpf_sock_addr {
 	__u32 user_family;	/* Allows 4-byte read, but no write. */
@@ -4335,4 +4411,19 @@ struct bpf_pidns_info {
 	__u32 pid;
 	__u32 tgid;
 };
+
+/* User accessible data for SK_LOOKUP programs. Add new fields at the end. */
+struct bpf_sk_lookup {
+	__bpf_md_ptr(struct bpf_sock *, sk); /* Selected socket */
+
+	__u32 family;		/* Protocol family (AF_INET, AF_INET6) */
+	__u32 protocol;		/* IP protocol (IPPROTO_TCP, IPPROTO_UDP) */
+	__u32 remote_ip4;	/* Network byte order */
+	__u32 remote_ip6[4];	/* Network byte order */
+	__u32 remote_port;	/* Network byte order */
+	__u32 local_ip4;	/* Network byte order */
+	__u32 local_ip6[4];	/* Network byte order */
+	__u32 local_port;	/* Host byte order */
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */