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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-08-07

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

The main changes are:

1) Add cgroup local storage for BPF programs, which provides a fast
   accessible memory for storing various per-cgroup data like number
   of transmitted packets, etc, from Roman.

2) Support bpf_get_socket_cookie() BPF helper in several more program
   types that have a full socket available, from Andrey.

3) Significantly improve the performance of perf events which are
   reported from BPF offload. Also convert a couple of BPF AF_XDP
   samples overto use libbpf, both from Jakub.

4) seg6local LWT provides the End.DT6 action, which allows to
   decapsulate an outer IPv6 header containing a Segment Routing Header.
   Adds this action now to the seg6local BPF interface, from Mathieu.

5) Do not mark dst register as unbounded in MOV64 instruction when
   both src and dst register are the same, from Arthur.

6) Define u_smp_rmb() and u_smp_wmb() to their respective barrier
   instructions on arm64 for the AF_XDP sample code, from Brian.

7) Convert the tcp_client.py and tcp_server.py BPF selftest scripts
   over from Python 2 to Python 3, from Jeremy.

8) Enable BTF build flags to the BPF sample code Makefile, from Taeung.

9) Remove an unnecessary rcu_read_lock() in run_lwt_bpf(), from Taehee.

10) Several improvements to the README.rst from the BPF documentation
    to make it more consistent with RST format, from Tobin.

11) Replace all occurrences of strerror() by calls to strerror_r()
    in libbpf and fix a FORTIFY_SOURCE build error along with it,
    from Thomas.

12) Fix a bug in bpftool's get_btf() function to correctly propagate
    an error via PTR_ERR(), from Yue.
====================

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

5 files changed, 119 insertions, 8 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index d50c2f0a655a..f91b0f8ff3a9 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -4,22 +4,46 @@
 
 #include <linux/errno.h>
 #include <linux/jump_label.h>
+#include <linux/percpu.h>
+#include <linux/rbtree.h>
 #include <uapi/linux/bpf.h>
 
 struct sock;
 struct sockaddr;
 struct cgroup;
 struct sk_buff;
+struct bpf_map;
+struct bpf_prog;
 struct bpf_sock_ops_kern;
+struct bpf_cgroup_storage;
 
 #ifdef CONFIG_CGROUP_BPF
 
 extern struct static_key_false cgroup_bpf_enabled_key;
 #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key)
 
+DECLARE_PER_CPU(void*, bpf_cgroup_storage);
+
+struct bpf_cgroup_storage_map;
+
+struct bpf_storage_buffer {
+	struct rcu_head rcu;
+	char data[0];
+};
+
+struct bpf_cgroup_storage {
+	struct bpf_storage_buffer *buf;
+	struct bpf_cgroup_storage_map *map;
+	struct bpf_cgroup_storage_key key;
+	struct list_head list;
+	struct rb_node node;
+	struct rcu_head rcu;
+};
+
 struct bpf_prog_list {
 	struct list_head node;
 	struct bpf_prog *prog;
+	struct bpf_cgroup_storage *storage;
 };
 
 struct bpf_prog_array;
@@ -77,6 +101,26 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 				      short access, enum bpf_attach_type type);
 
+static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage)
+{
+	struct bpf_storage_buffer *buf;
+
+	if (!storage)
+		return;
+
+	buf = READ_ONCE(storage->buf);
+	this_cpu_write(bpf_cgroup_storage, &buf->data[0]);
+}
+
+struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog);
+void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage);
+void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
+			     struct cgroup *cgroup,
+			     enum bpf_attach_type type);
+void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage);
+int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map);
+void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map);
+
 /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb)			      \
 ({									      \
@@ -221,6 +265,16 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
 	return -EINVAL;
 }
 
+static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage) {}
+static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog,
+					    struct bpf_map *map) { return 0; }
+static inline void bpf_cgroup_storage_release(struct bpf_prog *prog,
+					      struct bpf_map *map) {}
+static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(
+	struct bpf_prog *prog) { return 0; }
+static inline void bpf_cgroup_storage_free(
+	struct bpf_cgroup_storage *storage) {}
+
 #define cgroup_bpf_enabled (0)
 #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5b5ad95cf339..cd8790d2c6ed 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -155,6 +155,7 @@ enum bpf_arg_type {
 enum bpf_return_type {
 	RET_INTEGER,			/* function returns integer */
 	RET_VOID,			/* function doesn't return anything */
+	RET_PTR_TO_MAP_VALUE,		/* returns a pointer to map elem value */
 	RET_PTR_TO_MAP_VALUE_OR_NULL,	/* returns a pointer to map elem value or NULL */
 };
 
@@ -282,6 +283,7 @@ struct bpf_prog_aux {
 	struct bpf_prog *prog;
 	struct user_struct *user;
 	u64 load_time; /* ns since boottime */
+	struct bpf_map *cgroup_storage;
 	char name[BPF_OBJ_NAME_LEN];
 #ifdef CONFIG_SECURITY
 	void *security;
@@ -348,9 +350,14 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
  * The 'struct bpf_prog_array *' should only be replaced with xchg()
  * since other cpus are walking the array of pointers in parallel.
  */
+struct bpf_prog_array_item {
+	struct bpf_prog *prog;
+	struct bpf_cgroup_storage *cgroup_storage;
+};
+
 struct bpf_prog_array {
 	struct rcu_head rcu;
-	struct bpf_prog *progs[0];
+	struct bpf_prog_array_item items[0];
 };
 
 struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
@@ -371,7 +378,8 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 
 #define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null)	\
 	({						\
-		struct bpf_prog **_prog, *__prog;	\
+		struct bpf_prog_array_item *_item;	\
+		struct bpf_prog *_prog;			\
 		struct bpf_prog_array *_array;		\
 		u32 _ret = 1;				\
 		preempt_disable();			\
@@ -379,10 +387,11 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 		_array = rcu_dereference(array);	\
 		if (unlikely(check_non_null && !_array))\
 			goto _out;			\
-		_prog = _array->progs;			\
-		while ((__prog = READ_ONCE(*_prog))) {	\
-			_ret &= func(__prog, ctx);	\
-			_prog++;			\
+		_item = &_array->items[0];		\
+		while ((_prog = READ_ONCE(_item->prog))) {		\
+			bpf_cgroup_storage_set(_item->cgroup_storage);	\
+			_ret &= func(_prog, ctx);	\
+			_item++;			\
 		}					\
 _out:							\
 		rcu_read_unlock();			\
@@ -435,6 +444,8 @@ struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 int bpf_map_precharge_memlock(u32 pages);
+int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
+void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages);
 void *bpf_map_area_alloc(size_t size, int numa_node);
 void bpf_map_area_free(void *base);
 void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
@@ -777,6 +788,8 @@ extern const struct bpf_func_proto bpf_sock_map_update_proto;
 extern const struct bpf_func_proto bpf_sock_hash_update_proto;
 extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
 
+extern const struct bpf_func_proto bpf_get_local_storage_proto;
+
 /* Shared helpers among cBPF and eBPF. */
 void bpf_user_rnd_init_once(void);
 u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index c5700c2d5549..add08be53b6f 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -37,6 +37,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, perf_event_array_map_ops)
 #ifdef CONFIG_CGROUPS
 BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops)
 #endif
+#ifdef CONFIG_CGROUP_BPF
+BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, cgroup_storage_map_ops)
+#endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_HASH, htab_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_HASH, htab_percpu_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_HASH, htab_lru_map_ops)
diff --git a/include/net/seg6_local.h b/include/net/seg6_local.h
index 661fd5b4d3e0..08359e2d8b35 100644
--- a/include/net/seg6_local.h
+++ b/include/net/seg6_local.h
@@ -21,10 +21,12 @@
 
 extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
 			       u32 tbl_id);
+extern bool seg6_bpf_has_valid_srh(struct sk_buff *skb);
 
 struct seg6_bpf_srh_state {
-	bool valid;
+	struct ipv6_sr_hdr *srh;
 	u16 hdrlen;
+	bool valid;
 };
 
 DECLARE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 870113916cac..dd5758dc35d3 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -75,6 +75,11 @@ struct bpf_lpm_trie_key {
 	__u8	data[0];	/* Arbitrary size */
 };
 
+struct bpf_cgroup_storage_key {
+	__u64	cgroup_inode_id;	/* cgroup inode id */
+	__u32	attach_type;		/* program attach type */
+};
+
 /* BPF syscall commands, see bpf(2) man-page for details. */
 enum bpf_cmd {
 	BPF_MAP_CREATE,
@@ -120,6 +125,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_CPUMAP,
 	BPF_MAP_TYPE_XSKMAP,
 	BPF_MAP_TYPE_SOCKHASH,
+	BPF_MAP_TYPE_CGROUP_STORAGE,
 };
 
 enum bpf_prog_type {
@@ -1371,6 +1377,20 @@ union bpf_attr {
  * 		A 8-byte long non-decreasing number on success, or 0 if the
  * 		socket field is missing inside *skb*.
  *
+ * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
+ * 	Description
+ * 		Equivalent to bpf_get_socket_cookie() helper that accepts
+ * 		*skb*, but gets socket from **struct bpf_sock_addr** contex.
+ * 	Return
+ * 		A 8-byte long non-decreasing number.
+ *
+ * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
+ * 	Description
+ * 		Equivalent to bpf_get_socket_cookie() helper that accepts
+ * 		*skb*, but gets socket from **struct bpf_sock_ops** contex.
+ * 	Return
+ * 		A 8-byte long non-decreasing number.
+ *
  * u32 bpf_get_socket_uid(struct sk_buff *skb)
  * 	Return
  * 		The owner UID of the socket associated to *skb*. If the socket
@@ -2075,6 +2095,24 @@ union bpf_attr {
  * 	Return
  * 		A 64-bit integer containing the current cgroup id based
  * 		on the cgroup within which the current task is running.
+ *
+ * void* get_local_storage(void *map, u64 flags)
+ *	Description
+ *		Get the pointer to the local storage area.
+ *		The type and the size of the local storage is defined
+ *		by the *map* argument.
+ *		The *flags* meaning is specific for each map type,
+ *		and has to be 0 for cgroup local storage.
+ *
+ *		Depending on the bpf program type, a local storage area
+ *		can be shared between multiple instances of the bpf program,
+ *		running simultaneously.
+ *
+ *		A user should care about the synchronization by himself.
+ *		For example, by using the BPF_STX_XADD instruction to alter
+ *		the shared data.
+ *	Return
+ *		Pointer to the local storage area.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2157,7 +2195,8 @@ union bpf_attr {
 	FN(rc_repeat),			\
 	FN(rc_keydown),			\
 	FN(skb_cgroup_id),		\
-	FN(get_current_cgroup_id),
+	FN(get_current_cgroup_id),	\
+	FN(get_local_storage),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call