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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-10-21

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

The main changes are:

1) Implement two new kind of BPF maps, that is, queue and stack
   map along with new peek, push and pop operations, from Mauricio.

2) Add support for MSG_PEEK flag when redirecting into an ingress
   psock sk_msg queue, and add a new helper bpf_msg_push_data() for
   insert data into the message, from John.

3) Allow for BPF programs of type BPF_PROG_TYPE_CGROUP_SKB to use
   direct packet access for __skb_buff, from Song.

4) Use more lightweight barriers for walking perf ring buffer for
   libbpf and perf tool as well. Also, various fixes and improvements
   from verifier side, from Daniel.

5) Add per-symbol visibility for DSO in libbpf and hide by default
   global symbols such as netlink related functions, from Andrey.

6) Two improvements to nfp's BPF offload to check vNIC capabilities
   in case prog is shared with multiple vNICs and to protect against
   mis-initializing atomic counters, from Jakub.

7) Fix for bpftool to use 4 context mode for the nfp disassembler,
   also from Jakub.

8) Fix a return value comparison in test_libbpf.sh and add several
   bpftool improvements in bash completion, documentation of bpf fs
   restrictions and batch mode summary print, from Quentin.

9) Fix a file resource leak in BPF selftest's load_kallsyms()
   helper, from Peng.

10) Fix an unused variable warning in map_lookup_and_delete_elem(),
    from Alexei.

11) Fix bpf_skb_adjust_room() signature in BPF UAPI helper doc,
    from Nicolas.

12) Add missing executables to .gitignore in BPF selftests, from Anders.
====================

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

6 files changed, 113 insertions, 20 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e60fff48288b..33014ae73103 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -39,6 +39,9 @@ struct bpf_map_ops {
 	void *(*map_lookup_elem)(struct bpf_map *map, void *key);
 	int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags);
 	int (*map_delete_elem)(struct bpf_map *map, void *key);
+	int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags);
+	int (*map_pop_elem)(struct bpf_map *map, void *value);
+	int (*map_peek_elem)(struct bpf_map *map, void *value);
 
 	/* funcs called by prog_array and perf_event_array map */
 	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
@@ -138,6 +141,7 @@ enum bpf_arg_type {
 	ARG_CONST_MAP_PTR,	/* const argument used as pointer to bpf_map */
 	ARG_PTR_TO_MAP_KEY,	/* pointer to stack used as map key */
 	ARG_PTR_TO_MAP_VALUE,	/* pointer to stack used as map value */
+	ARG_PTR_TO_UNINIT_MAP_VALUE,	/* pointer to valid memory used to store a map value */
 
 	/* the following constraints used to prototype bpf_memcmp() and other
 	 * functions that access data on eBPF program stack
@@ -810,6 +814,9 @@ static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map,
 extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
 extern const struct bpf_func_proto bpf_map_update_elem_proto;
 extern const struct bpf_func_proto bpf_map_delete_elem_proto;
+extern const struct bpf_func_proto bpf_map_push_elem_proto;
+extern const struct bpf_func_proto bpf_map_pop_elem_proto;
+extern const struct bpf_func_proto bpf_map_peek_elem_proto;
 
 extern const struct bpf_func_proto bpf_get_prandom_u32_proto;
 extern const struct bpf_func_proto bpf_get_smp_processor_id_proto;
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index fa48343a5ea1..44d9ab4809bd 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -51,7 +51,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_HASH, htab_lru_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_PERCPU_HASH, htab_lru_percpu_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_LPM_TRIE, trie_map_ops)
 #ifdef CONFIG_PERF_EVENTS
-BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_trace_map_ops)
 #endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
@@ -69,3 +69,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops)
 #endif
 #endif
+BPF_MAP_TYPE(BPF_MAP_TYPE_QUEUE, queue_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 5771874bc01e..91b4c934f02e 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -548,6 +548,27 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb)
 	cb->data_end  = skb->data + skb_headlen(skb);
 }
 
+/* Similar to bpf_compute_data_pointers(), except that save orginal
+ * data in cb->data and cb->meta_data for restore.
+ */
+static inline void bpf_compute_and_save_data_end(
+	struct sk_buff *skb, void **saved_data_end)
+{
+	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
+
+	*saved_data_end = cb->data_end;
+	cb->data_end  = skb->data + skb_headlen(skb);
+}
+
+/* Restore data saved by bpf_compute_data_pointers(). */
+static inline void bpf_restore_data_end(
+	struct sk_buff *skb, void *saved_data_end)
+{
+	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
+
+	cb->data_end = saved_data_end;
+}
+
 static inline u8 *bpf_skb_cb(struct sk_buff *skb)
 {
 	/* eBPF programs may read/write skb->cb[] area to transfer meta
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 0b919f0bc6d6..2a11e9d91dfa 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -176,6 +176,7 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src,
 {
 	dst->sg.data[which] = src->sg.data[which];
 	dst->sg.data[which].length  = size;
+	dst->sg.size		   += size;
 	src->sg.data[which].length -= size;
 	src->sg.data[which].offset += size;
 }
@@ -186,21 +187,29 @@ static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src)
 	sk_msg_init(src);
 }
 
+static inline bool sk_msg_full(const struct sk_msg *msg)
+{
+	return (msg->sg.end == msg->sg.start) && msg->sg.size;
+}
+
 static inline u32 sk_msg_elem_used(const struct sk_msg *msg)
 {
+	if (sk_msg_full(msg))
+		return MAX_MSG_FRAGS;
+
 	return msg->sg.end >= msg->sg.start ?
 		msg->sg.end - msg->sg.start :
 		msg->sg.end + (MAX_MSG_FRAGS - msg->sg.start);
 }
 
-static inline bool sk_msg_full(const struct sk_msg *msg)
+static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which)
 {
-	return (msg->sg.end == msg->sg.start) && msg->sg.size;
+	return &msg->sg.data[which];
 }
 
-static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which)
+static inline struct scatterlist sk_msg_elem_cpy(struct sk_msg *msg, int which)
 {
-	return &msg->sg.data[which];
+	return msg->sg.data[which];
 }
 
 static inline struct page *sk_msg_page(struct sk_msg *msg, int which)
@@ -266,11 +275,6 @@ static inline struct sk_psock *sk_psock(const struct sock *sk)
 	return rcu_dereference_sk_user_data(sk);
 }
 
-static inline bool sk_has_psock(struct sock *sk)
-{
-	return sk_psock(sk) != NULL && sk->sk_prot->recvmsg == tcp_bpf_recvmsg;
-}
-
 static inline void sk_psock_queue_msg(struct sk_psock *psock,
 				      struct sk_msg *msg)
 {
@@ -370,6 +374,26 @@ static inline bool sk_psock_test_state(const struct sk_psock *psock,
 	return test_bit(bit, &psock->state);
 }
 
+static inline struct sk_psock *sk_psock_get_checked(struct sock *sk)
+{
+	struct sk_psock *psock;
+
+	rcu_read_lock();
+	psock = sk_psock(sk);
+	if (psock) {
+		if (sk->sk_prot->recvmsg != tcp_bpf_recvmsg) {
+			psock = ERR_PTR(-EBUSY);
+			goto out;
+		}
+
+		if (!refcount_inc_not_zero(&psock->refcnt))
+			psock = ERR_PTR(-EBUSY);
+	}
+out:
+	rcu_read_unlock();
+	return psock;
+}
+
 static inline struct sk_psock *sk_psock_get(struct sock *sk)
 {
 	struct sk_psock *psock;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3600ae0f25c3..8a61c3e8c15d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2051,11 +2051,6 @@ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer);
 #define TCP_ULP_MAX		128
 #define TCP_ULP_BUF_MAX		(TCP_ULP_NAME_MAX*TCP_ULP_MAX)
 
-enum {
-	TCP_ULP_TLS,
-	TCP_ULP_BPF,
-};
-
 struct tcp_ulp_ops {
 	struct list_head	list;
 
@@ -2064,9 +2059,7 @@ struct tcp_ulp_ops {
 	/* cleanup ulp */
 	void (*release)(struct sock *sk);
 
-	int		uid;
 	char		name[TCP_ULP_NAME_MAX];
-	bool		user_visible;
 	struct module	*owner;
 };
 int tcp_register_ulp(struct tcp_ulp_ops *type);
@@ -2089,7 +2082,7 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, u32 bytes,
 int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		    int nonblock, int flags, int *addr_len);
 int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
-		      struct msghdr *msg, int len);
+		      struct msghdr *msg, int len, int flags);
 
 /* Call BPF_SOCK_OPS program that returns an int. If the return value
  * is < 0, then the BPF op failed (for example if the loaded BPF
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f9187b41dff6..852dc17ab47a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -103,6 +103,7 @@ enum bpf_cmd {
 	BPF_BTF_LOAD,
 	BPF_BTF_GET_FD_BY_ID,
 	BPF_TASK_FD_QUERY,
+	BPF_MAP_LOOKUP_AND_DELETE_ELEM,
 };
 
 enum bpf_map_type {
@@ -128,6 +129,8 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_CGROUP_STORAGE,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+	BPF_MAP_TYPE_QUEUE,
+	BPF_MAP_TYPE_STACK,
 };
 
 enum bpf_prog_type {
@@ -462,6 +465,28 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
+ * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * 	Description
+ * 		Push an element *value* in *map*. *flags* is one of:
+ *
+ * 		**BPF_EXIST**
+ * 		If the queue/stack is full, the oldest element is removed to
+ * 		make room for this.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_pop_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Pop an element from *map*.
+ * Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_peek_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Get an element from *map* without removing it.
+ * Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  * int bpf_probe_read(void *dst, u32 size, const void *src)
  * 	Description
  * 		For tracing programs, safely attempt to read *size* bytes from
@@ -1433,7 +1458,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags)
+ * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags)
  * 	Description
  * 		Grow or shrink the room for data in the packet associated to
  * 		*skb* by *len_diff*, and according to the selected *mode*.
@@ -2215,6 +2240,23 @@ union bpf_attr {
  *		pointer that was returned from bpf_sk_lookup_xxx\ ().
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_msg_push_data(struct sk_buff *skb, u32 start, u32 len, u64 flags)
+ *	Description
+ *		For socket policies, insert *len* bytes into msg at offset
+ *		*start*.
+ *
+ *		If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a
+ *		*msg* it may want to insert metadata or options into the msg.
+ *		This can later be read and used by any of the lower layer BPF
+ *		hooks.
+ *
+ *		This helper may fail if under memory pressure (a malloc
+ *		fails) in these cases BPF programs will get an appropriate
+ *		error and BPF programs will need to handle them.
+ *
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2303,7 +2345,11 @@ union bpf_attr {
 	FN(skb_ancestor_cgroup_id),	\
 	FN(sk_lookup_tcp),		\
 	FN(sk_lookup_udp),		\
-	FN(sk_release),
+	FN(sk_release),			\
+	FN(map_push_elem),		\
+	FN(map_pop_elem),		\
+	FN(map_peek_elem),		\
+	FN(msg_push_data),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call