From d8eca5bbb2be9bc7546f9e733786fa2f1a594c67 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 9 Apr 2019 23:20:03 +0200 Subject: bpf: implement lookup-free direct value access for maps This generic extension to BPF maps allows for directly loading an address residing inside a BPF map value as a single BPF ldimm64 instruction! The idea is similar to what BPF_PSEUDO_MAP_FD does today, which is a special src_reg flag for ldimm64 instruction that indicates that inside the first part of the double insns's imm field is a file descriptor which the verifier then replaces as a full 64bit address of the map into both imm parts. For the newly added BPF_PSEUDO_MAP_VALUE src_reg flag, the idea is the following: the first part of the double insns's imm field is again a file descriptor corresponding to the map, and the second part of the imm field is an offset into the value. The verifier will then replace both imm parts with an address that points into the BPF map value at the given value offset for maps that support this operation. Currently supported is array map with single entry. It is possible to support more than just single map element by reusing both 16bit off fields of the insns as a map index, so full array map lookup could be expressed that way. It hasn't been implemented here due to lack of concrete use case, but could easily be done so in future in a compatible way, since both off fields right now have to be 0 and would correctly denote a map index 0. The BPF_PSEUDO_MAP_VALUE is a distinct flag as otherwise with BPF_PSEUDO_MAP_FD we could not differ offset 0 between load of map pointer versus load of map's value at offset 0, and changing BPF_PSEUDO_MAP_FD's encoding into off by one to differ between regular map pointer and map value pointer would add unnecessary complexity and increases barrier for debugability thus less suitable. Using the second part of the imm field as an offset into the value does /not/ come with limitations since maximum possible value size is in u32 universe anyway. This optimization allows for efficiently retrieving an address to a map value memory area without having to issue a helper call which needs to prepare registers according to calling convention, etc, without needing the extra NULL test, and without having to add the offset in an additional instruction to the value base pointer. The verifier then treats the destination register as PTR_TO_MAP_VALUE with constant reg->off from the user passed offset from the second imm field, and guarantees that this is within bounds of the map value. Any subsequent operations are normally treated as typical map value handling without anything extra needed from verification side. The two map operations for direct value access have been added to array map for now. In future other types could be supported as well depending on the use case. The main use case for this commit is to allow for BPF loader support for global variables that reside in .data/.rodata/.bss sections such that we can directly load the address of them with minimal additional infrastructure required. Loader support has been added in subsequent commits for libbpf library. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- kernel/bpf/arraymap.c | 32 +++++++++++++++++++ kernel/bpf/core.c | 3 +- kernel/bpf/disasm.c | 5 +-- kernel/bpf/syscall.c | 28 ++++++++++++----- kernel/bpf/verifier.c | 86 +++++++++++++++++++++++++++++++++++++++------------ 5 files changed, 124 insertions(+), 30 deletions(-) (limited to 'kernel/bpf') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index c72e0d8e1e65..1a6e9861d554 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -160,6 +160,36 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key) return array->value + array->elem_size * (index & array->index_mask); } +static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm, + u32 off) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + + if (map->max_entries != 1) + return -ENOTSUPP; + if (off >= map->value_size) + return -EINVAL; + + *imm = (unsigned long)array->value; + return 0; +} + +static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm, + u32 *off) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u64 base = (unsigned long)array->value; + u64 range = array->elem_size; + + if (map->max_entries != 1) + return -ENOTSUPP; + if (imm < base || imm >= base + range) + return -ENOENT; + + *off = imm - base; + return 0; +} + /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { @@ -419,6 +449,8 @@ 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_direct_value_addr = array_map_direct_value_addr, + .map_direct_value_meta = array_map_direct_value_meta, .map_seq_show_elem = array_map_seq_show_elem, .map_check_btf = array_map_check_btf, }; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 2966cb368bf4..ace8c22c8b0e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -292,7 +292,8 @@ int bpf_prog_calc_tag(struct bpf_prog *fp) dst[i] = fp->insnsi[i]; if (!was_ld_map && dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) && - dst[i].src_reg == BPF_PSEUDO_MAP_FD) { + (dst[i].src_reg == BPF_PSEUDO_MAP_FD || + dst[i].src_reg == BPF_PSEUDO_MAP_VALUE)) { was_ld_map = true; dst[i].imm = 0; } else if (was_ld_map && diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index de73f55e42fd..d9ce383c0f9c 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -205,10 +205,11 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, * part of the ldimm64 insn is accessible. */ u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; - bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD; + bool is_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD || + insn->src_reg == BPF_PSEUDO_MAP_VALUE; char tmp[64]; - if (map_ptr && !allow_ptr_leaks) + if (is_ptr && !allow_ptr_leaks) imm = 0; verbose(cbs->private_data, "(%02x) r%d = %s\n", diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 1d65e56594db..828518bb947b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2072,13 +2072,26 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) } static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog, - unsigned long addr) + unsigned long addr, u32 *off, + u32 *type) { + const struct bpf_map *map; int i; - for (i = 0; i < prog->aux->used_map_cnt; i++) - if (prog->aux->used_maps[i] == (void *)addr) - return prog->aux->used_maps[i]; + for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) { + map = prog->aux->used_maps[i]; + if (map == (void *)addr) { + *type = BPF_PSEUDO_MAP_FD; + return map; + } + if (!map->ops->map_direct_value_meta) + continue; + if (!map->ops->map_direct_value_meta(map, addr, off)) { + *type = BPF_PSEUDO_MAP_VALUE; + return map; + } + } + return NULL; } @@ -2086,6 +2099,7 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) { const struct bpf_map *map; struct bpf_insn *insns; + u32 off, type; u64 imm; int i; @@ -2113,11 +2127,11 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) continue; imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm; - map = bpf_map_from_imm(prog, imm); + map = bpf_map_from_imm(prog, imm, &off, &type); if (map) { - insns[i].src_reg = BPF_PSEUDO_MAP_FD; + insns[i].src_reg = type; insns[i].imm = map->id; - insns[i + 1].imm = 0; + insns[i + 1].imm = off; continue; } } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 48718e1da16d..6ab7a23fc924 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5056,18 +5056,12 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return 0; } -/* return the map pointer stored inside BPF_LD_IMM64 instruction */ -static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn) -{ - u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32; - - return (struct bpf_map *) (unsigned long) imm64; -} - /* verify BPF_LD_IMM64 instruction */ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) { + struct bpf_insn_aux_data *aux = cur_aux(env); struct bpf_reg_state *regs = cur_regs(env); + struct bpf_map *map; int err; if (BPF_SIZE(insn->code) != BPF_DW) { @@ -5091,11 +5085,22 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } - /* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */ - BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD); + map = env->used_maps[aux->map_index]; + mark_reg_known_zero(env, regs, insn->dst_reg); + regs[insn->dst_reg].map_ptr = map; + + if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) { + regs[insn->dst_reg].type = PTR_TO_MAP_VALUE; + regs[insn->dst_reg].off = aux->map_off; + if (map_value_has_spin_lock(map)) + regs[insn->dst_reg].id = ++env->id_gen; + } else if (insn->src_reg == BPF_PSEUDO_MAP_FD) { + regs[insn->dst_reg].type = CONST_PTR_TO_MAP; + } else { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } - regs[insn->dst_reg].type = CONST_PTR_TO_MAP; - regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn); return 0; } @@ -6803,8 +6808,10 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) } if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) { + struct bpf_insn_aux_data *aux; struct bpf_map *map; struct fd f; + u64 addr; if (i == insn_cnt - 1 || insn[1].code != 0 || insn[1].dst_reg != 0 || insn[1].src_reg != 0 || @@ -6813,13 +6820,19 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) return -EINVAL; } - if (insn->src_reg == 0) + if (insn[0].src_reg == 0) /* valid generic load 64-bit imm */ goto next_insn; - if (insn[0].src_reg != BPF_PSEUDO_MAP_FD || - insn[1].imm != 0) { - verbose(env, "unrecognized bpf_ld_imm64 insn\n"); + /* In final convert_pseudo_ld_imm64() step, this is + * converted into regular 64-bit imm load insn. + */ + if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD && + insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) || + (insn[0].src_reg == BPF_PSEUDO_MAP_FD && + insn[1].imm != 0)) { + verbose(env, + "unrecognized bpf_ld_imm64 insn\n"); return -EINVAL; } @@ -6837,16 +6850,47 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) return err; } - /* store map pointer inside BPF_LD_IMM64 instruction */ - insn[0].imm = (u32) (unsigned long) map; - insn[1].imm = ((u64) (unsigned long) map) >> 32; + aux = &env->insn_aux_data[i]; + if (insn->src_reg == BPF_PSEUDO_MAP_FD) { + addr = (unsigned long)map; + } else { + u32 off = insn[1].imm; + + if (off >= BPF_MAX_VAR_OFF) { + verbose(env, "direct value offset of %u is not allowed\n", off); + fdput(f); + return -EINVAL; + } + + if (!map->ops->map_direct_value_addr) { + verbose(env, "no direct value access support for this map type\n"); + fdput(f); + return -EINVAL; + } + + err = map->ops->map_direct_value_addr(map, &addr, off); + if (err) { + verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n", + map->value_size, off); + fdput(f); + return err; + } + + aux->map_off = off; + addr += off; + } + + insn[0].imm = (u32)addr; + insn[1].imm = addr >> 32; /* check whether we recorded this map already */ - for (j = 0; j < env->used_map_cnt; j++) + for (j = 0; j < env->used_map_cnt; j++) { if (env->used_maps[j] == map) { + aux->map_index = j; fdput(f); goto next_insn; } + } if (env->used_map_cnt >= MAX_USED_MAPS) { fdput(f); @@ -6863,6 +6907,8 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) fdput(f); return PTR_ERR(map); } + + aux->map_index = env->used_map_cnt; env->used_maps[env->used_map_cnt++] = map; if (bpf_map_is_cgroup_storage(map) && -- cgit v1.2.3