bpf: mini eBPF library, test stubs and verifier testsuite

1.
the library includes a trivial set of BPF syscall wrappers:
int bpf_create_map(int key_size, int value_size, int max_entries);
int bpf_update_elem(int fd, void *key, void *value);
int bpf_lookup_elem(int fd, void *key, void *value);
int bpf_delete_elem(int fd, void *key);
int bpf_get_next_key(int fd, void *key, void *next_key);
int bpf_prog_load(enum bpf_prog_type prog_type,
		  const struct sock_filter_int *insns, int insn_len,
		  const char *license);
bpf_prog_load() stores verifier log into global bpf_log_buf[] array

and BPF_*() macros to build instructions

2.
test stubs configure eBPF infra with 'unspec' map and program types.
These are fake types used by user space testsuite only.

3.
verifier tests valid and invalid programs and expects predefined
error log messages from kernel.
40 tests so far.

$ sudo ./test_verifier
 #0 add+sub+mul OK
 #1 unreachable OK
 #2 unreachable2 OK
 #3 out of range jump OK
 #4 out of range jump2 OK
 #5 test1 ld_imm64 OK
 ...
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

kernel/bpf/Makefile

 obj-y := core.o syscall.o verifier.o
+
+ifdef CONFIG_TEST_BPF
+obj-y += test_stub.o
+endif

kernel/bpf/test_stub.c

+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/bpf.h>
+
+/* test stubs for BPF_MAP_TYPE_UNSPEC and for BPF_PROG_TYPE_UNSPEC
+ * to be used by user space verifier testsuite
+ */
+struct bpf_context {
+	u64 arg1;
+	u64 arg2;
+};
+
+static u64 test_func(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	return 0;
+}
+
+static struct bpf_func_proto test_funcs[] = {
+	[BPF_FUNC_unspec] = {
+		.func = test_func,
+		.gpl_only = true,
+		.ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
+		.arg1_type = ARG_CONST_MAP_PTR,
+		.arg2_type = ARG_PTR_TO_MAP_KEY,
+	},
+};
+
+static const struct bpf_func_proto *test_func_proto(enum bpf_func_id func_id)
+{
+	if (func_id < 0 || func_id >= ARRAY_SIZE(test_funcs))
+		return NULL;
+	return &test_funcs[func_id];
+}
+
+static const struct bpf_context_access {
+	int size;
+	enum bpf_access_type type;
+} test_ctx_access[] = {
+	[offsetof(struct bpf_context, arg1)] = {
+		FIELD_SIZEOF(struct bpf_context, arg1),
+		BPF_READ
+	},
+	[offsetof(struct bpf_context, arg2)] = {
+		FIELD_SIZEOF(struct bpf_context, arg2),
+		BPF_READ
+	},
+};
+
+static bool test_is_valid_access(int off, int size, enum bpf_access_type type)
+{
+	const struct bpf_context_access *access;
+
+	if (off < 0 || off >= ARRAY_SIZE(test_ctx_access))
+		return false;
+
+	access = &test_ctx_access[off];
+	if (access->size == size && (access->type & type))
+		return true;
+
+	return false;
+}
+
+static struct bpf_verifier_ops test_ops = {
+	.get_func_proto = test_func_proto,
+	.is_valid_access = test_is_valid_access,
+};
+
+static struct bpf_prog_type_list tl_prog = {
+	.ops = &test_ops,
+	.type = BPF_PROG_TYPE_UNSPEC,
+};
+
+static struct bpf_map *test_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_map *map;
+
+	map = kzalloc(sizeof(*map), GFP_USER);
+	if (!map)
+		return ERR_PTR(-ENOMEM);
+
+	map->key_size = attr->key_size;
+	map->value_size = attr->value_size;
+	map->max_entries = attr->max_entries;
+	return map;
+}
+
+static void test_map_free(struct bpf_map *map)
+{
+	kfree(map);
+}
+
+static struct bpf_map_ops test_map_ops = {
+	.map_alloc = test_map_alloc,
+	.map_free = test_map_free,
+};
+
+static struct bpf_map_type_list tl_map = {
+	.ops = &test_map_ops,
+	.type = BPF_MAP_TYPE_UNSPEC,
+};
+
+static int __init register_test_ops(void)
+{
+	bpf_register_map_type(&tl_map);
+	bpf_register_prog_type(&tl_prog);
+	return 0;
+}
+late_initcall(register_test_ops);

lib/Kconfig.debug

@@ -1672,7 +1672,8 @@ config TEST_BPF
 	  against the BPF interpreter or BPF JIT compiler depending on the
 	  current setting. This is in particular useful for BPF JIT compiler
 	  development, but also to run regression tests against changes in
-	  the interpreter code.
+	  the interpreter code. It also enables test stubs for eBPF maps and
+	  verifier used by user space verifier testsuite.
 
 	  If unsure, say N.
 

samples/bpf/Makefile

+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+# List of programs to build
+hostprogs-y := test_verifier
+
+test_verifier-objs := test_verifier.o libbpf.o
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+
+HOSTCFLAGS += -I$(objtree)/usr/include

samples/bpf/libbpf.c

+/* eBPF mini library */
+#include <stdlib.h>
+#include <stdio.h>
+#include <linux/unistd.h>
+#include <unistd.h>
+#include <string.h>
+#include <linux/netlink.h>
+#include <linux/bpf.h>
+#include <errno.h>
+#include "libbpf.h"
+
+static __u64 ptr_to_u64(void *ptr)
+{
+	return (__u64) (unsigned long) ptr;
+}
+
+int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
+		   int max_entries)
+{
+	union bpf_attr attr = {
+		.map_type = map_type,
+		.key_size = key_size,
+		.value_size = value_size,
+		.max_entries = max_entries
+	};
+
+	return syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr));
+}
+
+int bpf_update_elem(int fd, void *key, void *value)
+{
+	union bpf_attr attr = {
+		.map_fd = fd,
+		.key = ptr_to_u64(key),
+		.value = ptr_to_u64(value),
+	};
+
+	return syscall(__NR_bpf, BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
+}
+
+int bpf_lookup_elem(int fd, void *key, void *value)
+{
+	union bpf_attr attr = {
+		.map_fd = fd,
+		.key = ptr_to_u64(key),
+		.value = ptr_to_u64(value),
+	};
+
+	return syscall(__NR_bpf, BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr));
+}
+
+int bpf_delete_elem(int fd, void *key)
+{
+	union bpf_attr attr = {
+		.map_fd = fd,
+		.key = ptr_to_u64(key),
+	};
+
+	return syscall(__NR_bpf, BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
+}
+
+int bpf_get_next_key(int fd, void *key, void *next_key)
+{
+	union bpf_attr attr = {
+		.map_fd = fd,
+		.key = ptr_to_u64(key),
+		.next_key = ptr_to_u64(next_key),
+	};
+
+	return syscall(__NR_bpf, BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
+}
+
+#define ROUND_UP(x, n) (((x) + (n) - 1u) & ~((n) - 1u))
+
+char bpf_log_buf[LOG_BUF_SIZE];
+
+int bpf_prog_load(enum bpf_prog_type prog_type,
+		  const struct bpf_insn *insns, int prog_len,
+		  const char *license)
+{
+	union bpf_attr attr = {
+		.prog_type = prog_type,
+		.insns = ptr_to_u64((void *) insns),
+		.insn_cnt = prog_len / sizeof(struct bpf_insn),
+		.license = ptr_to_u64((void *) license),
+		.log_buf = ptr_to_u64(bpf_log_buf),
+		.log_size = LOG_BUF_SIZE,
+		.log_level = 1,
+	};
+
+	bpf_log_buf[0] = 0;
+
+	return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
+}

samples/bpf/libbpf.h

+/* eBPF mini library */
+#ifndef __LIBBPF_H
+#define __LIBBPF_H
+
+struct bpf_insn;
+
+int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
+		   int max_entries);
+int bpf_update_elem(int fd, void *key, void *value);
+int bpf_lookup_elem(int fd, void *key, void *value);
+int bpf_delete_elem(int fd, void *key);
+int bpf_get_next_key(int fd, void *key, void *next_key);
+
+int bpf_prog_load(enum bpf_prog_type prog_type,
+		  const struct bpf_insn *insns, int insn_len,
+		  const char *license);
+
+#define LOG_BUF_SIZE 8192
+extern char bpf_log_buf[LOG_BUF_SIZE];
+
+/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
+
+#define BPF_ALU64_REG(OP, DST, SRC)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_X,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+#define BPF_ALU32_REG(OP, DST, SRC)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU | BPF_OP(OP) | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */
+
+#define BPF_ALU64_IMM(OP, DST, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_K,	\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+#define BPF_ALU32_IMM(OP, DST, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU | BPF_OP(OP) | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+/* Short form of mov, dst_reg = src_reg */
+
+#define BPF_MOV64_REG(DST, SRC)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+/* Short form of mov, dst_reg = imm32 */
+
+#define BPF_MOV64_IMM(DST, IMM)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
+/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */
+#define BPF_LD_IMM64(DST, IMM)					\
+	BPF_LD_IMM64_RAW(DST, 0, IMM)
+
+#define BPF_LD_IMM64_RAW(DST, SRC, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_LD | BPF_DW | BPF_IMM,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = 0,					\
+		.imm   = (__u32) (IMM) }),			\
+	((struct bpf_insn) {					\
+		.code  = 0, /* zero is reserved opcode */	\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = ((__u64) (IMM)) >> 32 })
+
+#define BPF_PSEUDO_MAP_FD	1
+
+/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */
+#define BPF_LD_MAP_FD(DST, MAP_FD)				\
+	BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD)
+
+
+/* Memory load, dst_reg = *(uint *) (src_reg + off16) */
+
+#define BPF_LDX_MEM(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+/* Memory store, *(uint *) (dst_reg + off16) = src_reg */
+
+#define BPF_STX_MEM(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+/* Memory store, *(uint *) (dst_reg + off16) = imm32 */
+
+#define BPF_ST_MEM(SIZE, DST, OFF, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM,	\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = OFF,					\
+		.imm   = IMM })
+
+/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */
+
+#define BPF_JMP_REG(OP, DST, SRC, OFF)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP | BPF_OP(OP) | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */
+
+#define BPF_JMP_IMM(OP, DST, IMM, OFF)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP | BPF_OP(OP) | BPF_K,		\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = OFF,					\
+		.imm   = IMM })
+
+/* Raw code statement block */
+
+#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM)			\
+	((struct bpf_insn) {					\
+		.code  = CODE,					\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = IMM })
+
+/* Program exit */
+
+#define BPF_EXIT_INSN()						\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP | BPF_EXIT,			\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = 0 })
+
+#endif