Merge branch 'bpf-type-format'

Martin KaFai Lau says:

====================
This patch introduces BPF Type Format (BTF).

BTF (BPF Type Format) is the meta data format which describes
the data types of BPF program/map.  Hence, it basically focus
on the C programming language which the modern BPF is primary
using.  The first use case is to provide a generic pretty print
capability for a BPF map.

A modified pahole that can convert dwarf to BTF is here:

  https://github.com/iamkafai/pahole/tree/btf

Please see individual patch for details.

v5:
- Remove BTF_KIND_FLOAT and BTF_KIND_FUNC which are not
  currently used.  They can be added in the future.
  Some bpf_df_xxx() are removed together.
- Add comment in patch 7 to clarify that the new bpffs_map_fops
  should not be extended further.

v4:
- Fix warning (remove unneeded semicolon)
- Remove a redundant variable (nr_bytes) from btf_int_check_meta() in
  patch 1.  Caught by W=1.

v3:
- Rebase to bpf-next
- Fix sparse warning (by adding static)
- Add BTF header logging: btf_verifier_log_hdr()
- Fix the alignment test on btf->type_off
- Add tests for the BTF header
- Lower the max BTF size to 16MB.  It should be enough
  for some time.  We could raise it later if it would
  be needed.

v2:
- Use kvfree where needed in patch 1 and 2
- Also consider BTF_INT_OFFSET() in the btf_int_check_meta()
  in patch 1
- Fix an incorrect goto target in map_create() during
  the btf-error-path in patch 7
- re-org some local vars to keep the rev xmas tree in btf.c
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

include/linux/bpf.h

@@ -22,6 +22,8 @@ struct perf_event;
 struct bpf_prog;
 struct bpf_map;
 struct sock;
+struct seq_file;
+struct btf;
 
 /* map is generic key/value storage optionally accesible by eBPF programs */
 struct bpf_map_ops {
@@ -43,10 +45,14 @@ struct bpf_map_ops {
 	void (*map_fd_put_ptr)(void *ptr);
 	u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
 	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);
 };
 
 struct bpf_map {
-	/* 1st cacheline with read-mostly members of which some
+	/* The first two cachelines with read-mostly members of which some
 	 * are also accessed in fast-path (e.g. ops, max_entries).
 	 */
 	const struct bpf_map_ops *ops ____cacheline_aligned;
@@ -62,10 +68,13 @@ struct bpf_map {
 	u32 pages;
 	u32 id;
 	int numa_node;
+	u32 btf_key_id;
+	u32 btf_value_id;
+	struct btf *btf;
 	bool unpriv_array;
-	/* 7 bytes hole */
+	/* 55 bytes hole */
 
-	/* 2nd cacheline with misc members to avoid false sharing
+	/* The 3rd and 4th cacheline with misc members to avoid false sharing
 	 * particularly with refcounting.
 	 */
 	struct user_struct *user ____cacheline_aligned;
@@ -100,6 +109,11 @@ static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map)
 	return container_of(map, struct bpf_offloaded_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;
+}
+
 extern const struct bpf_map_ops bpf_map_offload_ops;
 
 /* function argument constraints */

include/linux/btf.h

@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Facebook */
+
+#ifndef _LINUX_BTF_H
+#define _LINUX_BTF_H 1
+
+#include <linux/types.h>
+
+struct btf;
+struct btf_type;
+union bpf_attr;
+
+extern const struct file_operations btf_fops;
+
+void btf_put(struct btf *btf);
+int btf_new_fd(const union bpf_attr *attr);
+struct btf *btf_get_by_fd(int fd);
+int btf_get_info_by_fd(const struct btf *btf,
+		       const union bpf_attr *attr,
+		       union bpf_attr __user *uattr);
+/* Figure out the size of a type_id.  If type_id is a modifier
+ * (e.g. const), it will be resolved to find out the type with size.
+ *
+ * For example:
+ * In describing "const void *",  type_id is "const" and "const"
+ * refers to "void *".  The return type will be "void *".
+ *
+ * If type_id is a simple "int", then return type will be "int".
+ *
+ * @btf: struct btf object
+ * @type_id: Find out the size of type_id. The type_id of the return
+ *           type is set to *type_id.
+ * @ret_size: It can be NULL.  If not NULL, the size of the return
+ *            type is set to *ret_size.
+ * Return: The btf_type (resolved to another type with size info if needed).
+ *         NULL is returned if type_id itself does not have size info
+ *         (e.g. void) or it cannot be resolved to another type that
+ *         has size info.
+ *         *type_id and *ret_size will not be changed in the
+ *         NULL return case.
+ */
+const struct btf_type *btf_type_id_size(const struct btf *btf,
+					u32 *type_id,
+					u32 *ret_size);
+void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,
+		       struct seq_file *m);
+
+#endif

include/uapi/linux/bpf.h

@@ -95,6 +95,7 @@ enum bpf_cmd {
 	BPF_OBJ_GET_INFO_BY_FD,
 	BPF_PROG_QUERY,
 	BPF_RAW_TRACEPOINT_OPEN,
+	BPF_BTF_LOAD,
 };
 
 enum bpf_map_type {
@@ -279,6 +280,9 @@ union bpf_attr {
 					 */
 		char	map_name[BPF_OBJ_NAME_LEN];
 		__u32	map_ifindex;	/* ifindex of netdev to create on */
+		__u32	btf_fd;		/* fd pointing to a BTF type data */
+		__u32	btf_key_id;	/* BTF type_id of the key */
+		__u32	btf_value_id;	/* BTF type_id of the value */
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -363,6 +367,14 @@ union bpf_attr {
 		__u64 name;
 		__u32 prog_fd;
 	} raw_tracepoint;
+
+	struct { /* anonymous struct for BPF_BTF_LOAD */
+		__aligned_u64	btf;
+		__aligned_u64	btf_log_buf;
+		__u32		btf_size;
+		__u32		btf_log_size;
+		__u32		btf_log_level;
+	};
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:

include/uapi/linux/btf.h

@@ -0,0 +1,130 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Copyright (c) 2018 Facebook */
+#ifndef _UAPI__LINUX_BTF_H__
+#define _UAPI__LINUX_BTF_H__
+
+#include <linux/types.h>
+
+#define BTF_MAGIC	0xeB9F
+#define BTF_MAGIC_SWAP	0x9FeB
+#define BTF_VERSION	1
+#define BTF_FLAGS_COMPR	0x01
+
+struct btf_header {
+	__u16	magic;
+	__u8	version;
+	__u8	flags;
+
+	__u32	parent_label;
+	__u32	parent_name;
+
+	/* All offsets are in bytes relative to the end of this header */
+	__u32	label_off;	/* offset of label section	*/
+	__u32	object_off;	/* offset of data object section*/
+	__u32	func_off;	/* offset of function section	*/
+	__u32	type_off;	/* offset of type section	*/
+	__u32	str_off;	/* offset of string section	*/
+	__u32	str_len;	/* length of string section	*/
+};
+
+/* Max # of type identifier */
+#define BTF_MAX_TYPE	0x7fffffff
+/* Max offset into the string section */
+#define BTF_MAX_NAME_OFFSET	0x7fffffff
+/* Max # of struct/union/enum members or func args */
+#define BTF_MAX_VLEN	0xffff
+
+/* The type id is referring to a parent BTF */
+#define BTF_TYPE_PARENT(id)	(((id) >> 31) & 0x1)
+#define BTF_TYPE_ID(id)		((id) & BTF_MAX_TYPE)
+
+/* String is in the ELF string section */
+#define BTF_STR_TBL_ELF_ID(ref)	(((ref) >> 31) & 0x1)
+#define BTF_STR_OFFSET(ref)	((ref) & BTF_MAX_NAME_OFFSET)
+
+struct btf_type {
+	__u32 name;
+	/* "info" bits arrangement
+	 * bits  0-15: vlen (e.g. # of struct's members)
+	 * bits 16-23: unused
+	 * bits 24-28: kind (e.g. int, ptr, array...etc)
+	 * bits 29-30: unused
+	 * bits    31: root
+	 */
+	__u32 info;
+	/* "size" is used by INT, ENUM, STRUCT and UNION.
+	 * "size" tells the size of the type it is describing.
+	 *
+	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT.
+	 * "type" is a type_id referring to another type.
+	 */
+	union {
+		__u32 size;
+		__u32 type;
+	};
+};
+
+#define BTF_INFO_KIND(info)	(((info) >> 24) & 0x1f)
+#define BTF_INFO_ISROOT(info)	(!!(((info) >> 24) & 0x80))
+#define BTF_INFO_VLEN(info)	((info) & 0xffff)
+
+#define BTF_KIND_UNKN		0	/* Unknown	*/
+#define BTF_KIND_INT		1	/* Integer	*/
+#define BTF_KIND_PTR		2	/* Pointer	*/
+#define BTF_KIND_ARRAY		3	/* Array	*/
+#define BTF_KIND_STRUCT		4	/* Struct	*/
+#define BTF_KIND_UNION		5	/* Union	*/
+#define BTF_KIND_ENUM		6	/* Enumeration	*/
+#define BTF_KIND_FWD		7	/* Forward	*/
+#define BTF_KIND_TYPEDEF	8	/* Typedef	*/
+#define BTF_KIND_VOLATILE	9	/* Volatile	*/
+#define BTF_KIND_CONST		10	/* Const	*/
+#define BTF_KIND_RESTRICT	11	/* Restrict	*/
+#define BTF_KIND_MAX		11
+#define NR_BTF_KINDS		12
+
+/* For some specific BTF_KIND, "struct btf_type" is immediately
+ * followed by extra data.
+ */
+
+/* BTF_KIND_INT is followed by a u32 and the following
+ * is the 32 bits arrangement:
+ */
+#define BTF_INT_ENCODING(VAL)	(((VAL) & 0xff000000) >> 24)
+#define BTF_INT_OFFSET(VAL)	(((VAL  & 0x00ff0000)) >> 16)
+#define BTF_INT_BITS(VAL)	((VAL)  & 0x0000ffff)
+
+/* Attributes stored in the BTF_INT_ENCODING */
+#define BTF_INT_SIGNED	0x1
+#define BTF_INT_CHAR	0x2
+#define BTF_INT_BOOL	0x4
+#define BTF_INT_VARARGS	0x8
+
+/* BTF_KIND_ENUM is followed by multiple "struct btf_enum".
+ * The exact number of btf_enum is stored in the vlen (of the
+ * info in "struct btf_type").
+ */
+struct btf_enum {
+	__u32	name;
+	__s32	val;
+};
+
+/* BTF_KIND_ARRAY is followed by one "struct btf_array" */
+struct btf_array {
+	__u32	type;
+	__u32	index_type;
+	__u32	nelems;
+};
+
+/* BTF_KIND_STRUCT and BTF_KIND_UNION are followed
+ * by multiple "struct btf_member".  The exact number
+ * of btf_member is stored in the vlen (of the info in
+ * "struct btf_type").
+ */
+struct btf_member {
+	__u32	name;
+	__u32	type;
+	__u32	offset;	/* offset in bits */
+};
+
+#endif /* _UAPI__LINUX_BTF_H__ */

kernel/bpf/Makefile

@@ -4,6 +4,7 @@ obj-y := core.o
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
+obj-$(CONFIG_BPF_SYSCALL) += btf.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
 obj-$(CONFIG_BPF_SYSCALL) += cpumap.o

kernel/bpf/arraymap.c

@@ -11,11 +11,13 @@
  * General Public License for more details.
  */
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/filter.h>
 #include <linux/perf_event.h>
+#include <uapi/linux/btf.h>
 
 #include "map_in_map.h"
 
@@ -336,6 +338,52 @@ static void array_map_free(struct bpf_map *map)
 	bpf_map_area_free(array);
 }
 
+static void array_map_seq_show_elem(struct bpf_map *map, void *key,
+				    struct seq_file *m)
+{
+	void *value;
+
+	rcu_read_lock();
+
+	value = array_map_lookup_elem(map, key);
+	if (!value) {
+		rcu_read_unlock();
+		return;
+	}
+
+	seq_printf(m, "%u: ", *(u32 *)key);
+	btf_type_seq_show(map->btf, map->btf_value_id, value, m);
+	seq_puts(m, "\n");
+
+	rcu_read_unlock();
+}
+
+static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf,
+			       u32 btf_key_id, u32 btf_value_id)
+{
+	const struct btf_type *key_type, *value_type;
+	u32 key_size, value_size;
+	u32 int_data;
+
+	key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
+	if (!key_type || BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
+		return -EINVAL;
+
+	int_data = *(u32 *)(key_type + 1);
+	/* bpf array can only take a u32 key.  This check makes
+	 * sure that the btf matches the attr used during map_create.
+	 */
+	if (BTF_INT_BITS(int_data) != 32 || key_size != 4 ||
+	    BTF_INT_OFFSET(int_data))
+		return -EINVAL;
+
+	value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
+	if (!value_type || value_size > map->value_size)
+		return -EINVAL;
+
+	return 0;
+}
+
 const struct bpf_map_ops array_map_ops = {
 	.map_alloc_check = array_map_alloc_check,
 	.map_alloc = array_map_alloc,
@@ -345,6 +393,8 @@ const struct bpf_map_ops array_map_ops = {
 	.map_update_elem = array_map_update_elem,
 	.map_delete_elem = array_map_delete_elem,
 	.map_gen_lookup = array_map_gen_lookup,
+	.map_seq_show_elem = array_map_seq_show_elem,
+	.map_check_btf = array_map_check_btf,
 };
 
 const struct bpf_map_ops percpu_array_map_ops = {