From 99c55f7d47c0dc6fc64729f37bf435abf43f4c60 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 26 Sep 2014 00:16:57 -0700 Subject: bpf: introduce BPF syscall and maps BPF syscall is a multiplexor for a range of different operations on eBPF. This patch introduces syscall with single command to create a map. Next patch adds commands to access maps. 'maps' is a generic storage of different types for sharing data between kernel and userspace. Userspace example: /* this syscall wrapper creates a map with given type and attributes * and returns map_fd on success. * use close(map_fd) to delete the map */ 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 bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); } 'union bpf_attr' is backwards compatible with future extensions. More details in Documentation/networking/filter.txt and in manpage Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 479ed0b6be16..f58a10f9670c 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -62,4 +62,27 @@ struct bpf_insn { __s32 imm; /* signed immediate constant */ }; +/* BPF syscall commands */ +enum bpf_cmd { + /* create a map with given type and attributes + * fd = bpf(BPF_MAP_CREATE, union bpf_attr *, u32 size) + * returns fd or negative error + * map is deleted when fd is closed + */ + BPF_MAP_CREATE, +}; + +enum bpf_map_type { + BPF_MAP_TYPE_UNSPEC, +}; + +union bpf_attr { + struct { /* anonymous struct used by BPF_MAP_CREATE command */ + __u32 map_type; /* one of enum bpf_map_type */ + __u32 key_size; /* size of key in bytes */ + __u32 value_size; /* size of value in bytes */ + __u32 max_entries; /* max number of entries in a map */ + }; +} __attribute__((aligned(8))); + #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3 From db20fd2b01087bdfbe30bce314a198eefedcc42e Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 26 Sep 2014 00:16:59 -0700 Subject: bpf: add lookup/update/delete/iterate methods to BPF maps 'maps' is a generic storage of different types for sharing data between kernel and userspace. The maps are accessed from user space via BPF syscall, which has commands: - create a map with given type and attributes fd = bpf(BPF_MAP_CREATE, union bpf_attr *attr, u32 size) returns fd or negative error - lookup key in a given map referenced by fd err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero and stores found elem into value or negative error - create or update key/value pair in a given map err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->value returns zero or negative error - find and delete element by key in a given map err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key - iterate map elements (based on input key return next_key) err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size) using attr->map_fd, attr->key, attr->next_key - close(fd) deletes the map Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f58a10f9670c..395cabd2ca0a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -70,6 +70,35 @@ enum bpf_cmd { * map is deleted when fd is closed */ BPF_MAP_CREATE, + + /* lookup key in a given map + * err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size) + * Using attr->map_fd, attr->key, attr->value + * returns zero and stores found elem into value + * or negative error + */ + BPF_MAP_LOOKUP_ELEM, + + /* create or update key/value pair in a given map + * err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size) + * Using attr->map_fd, attr->key, attr->value + * returns zero or negative error + */ + BPF_MAP_UPDATE_ELEM, + + /* find and delete elem by key in a given map + * err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size) + * Using attr->map_fd, attr->key + * returns zero or negative error + */ + BPF_MAP_DELETE_ELEM, + + /* lookup key in a given map and return next key + * err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size) + * Using attr->map_fd, attr->key, attr->next_key + * returns zero and stores next key or negative error + */ + BPF_MAP_GET_NEXT_KEY, }; enum bpf_map_type { @@ -83,6 +112,15 @@ union bpf_attr { __u32 value_size; /* size of value in bytes */ __u32 max_entries; /* max number of entries in a map */ }; + + struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ + __u32 map_fd; + __aligned_u64 key; + union { + __aligned_u64 value; + __aligned_u64 next_key; + }; + }; } __attribute__((aligned(8))); #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3 From 09756af46893c18839062976c3252e93a1beeba7 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 26 Sep 2014 00:17:00 -0700 Subject: bpf: expand BPF syscall with program load/unload eBPF programs are similar to kernel modules. They are loaded by the user process and automatically unloaded when process exits. Each eBPF program is a safe run-to-completion set of instructions. eBPF verifier statically determines that the program terminates and is safe to execute. The following syscall wrapper can be used to load the program: int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, int insn_cnt, const char *license) { union bpf_attr attr = { .prog_type = prog_type, .insns = ptr_to_u64(insns), .insn_cnt = insn_cnt, .license = ptr_to_u64(license), }; return bpf(BPF_PROG_LOAD, &attr, sizeof(attr)); } where 'insns' is an array of eBPF instructions and 'license' is a string that must be GPL compatible to call helper functions marked gpl_only Upon succesful load the syscall returns prog_fd. Use close(prog_fd) to unload the program. User space tests and examples follow in the later patches Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 395cabd2ca0a..424f442016e7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -99,12 +99,23 @@ enum bpf_cmd { * returns zero and stores next key or negative error */ BPF_MAP_GET_NEXT_KEY, + + /* verify and load eBPF program + * prog_fd = bpf(BPF_PROG_LOAD, union bpf_attr *attr, u32 size) + * Using attr->prog_type, attr->insns, attr->license + * returns fd or negative error + */ + BPF_PROG_LOAD, }; enum bpf_map_type { BPF_MAP_TYPE_UNSPEC, }; +enum bpf_prog_type { + BPF_PROG_TYPE_UNSPEC, +}; + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -121,6 +132,21 @@ union bpf_attr { __aligned_u64 next_key; }; }; + + struct { /* anonymous struct used by BPF_PROG_LOAD command */ + __u32 prog_type; /* one of enum bpf_prog_type */ + __u32 insn_cnt; + __aligned_u64 insns; + __aligned_u64 license; + }; } __attribute__((aligned(8))); +/* integer value in 'imm' field of BPF_CALL instruction selects which helper + * function eBPF program intends to call + */ +enum bpf_func_id { + BPF_FUNC_unspec, + __BPF_FUNC_MAX_ID, +}; + #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3 From cbd357008604925355ae7b54a09137dabb81b580 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 26 Sep 2014 00:17:03 -0700 Subject: bpf: verifier (add ability to receive verification log) add optional attributes for BPF_PROG_LOAD syscall: union bpf_attr { struct { ... __u32 log_level; /* verbosity level of eBPF verifier */ __u32 log_size; /* size of user buffer */ __aligned_u64 log_buf; /* user supplied 'char *buffer' */ }; }; when log_level > 0 the verifier will return its verification log in the user supplied buffer 'log_buf' which can be used by program author to analyze why verifier rejected given program. 'Understanding eBPF verifier messages' section of Documentation/networking/filter.txt provides several examples of these messages, like the program: BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), BPF_LD_MAP_FD(BPF_REG_1, 0), BPF_CALL_FUNC(BPF_FUNC_map_lookup_elem), BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1), BPF_ST_MEM(BPF_DW, BPF_REG_0, 4, 0), BPF_EXIT_INSN(), will be rejected with the following multi-line message in log_buf: 0: (7a) *(u64 *)(r10 -8) = 0 1: (bf) r2 = r10 2: (07) r2 += -8 3: (b7) r1 = 0 4: (85) call 1 5: (15) if r0 == 0x0 goto pc+1 R0=map_ptr R10=fp 6: (7a) *(u64 *)(r0 +4) = 0 misaligned access off 4 size 8 The format of the output can change at any time as verifier evolves. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 424f442016e7..31b0ac208a52 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -138,6 +138,9 @@ union bpf_attr { __u32 insn_cnt; __aligned_u64 insns; __aligned_u64 license; + __u32 log_level; /* verbosity level of verifier */ + __u32 log_size; /* size of user buffer */ + __aligned_u64 log_buf; /* user supplied buffer */ }; } __attribute__((aligned(8))); -- cgit v1.2.3