diff options
Diffstat (limited to 'kernel/bpf/core.c')
| -rw-r--r-- | kernel/bpf/core.c | 276 |
1 files changed, 207 insertions, 69 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 3ece2da55625..8b018ff48875 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -18,7 +18,6 @@ */ #include <uapi/linux/btf.h> -#include <crypto/sha1.h> #include <linux/filter.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> @@ -1422,6 +1421,27 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); *to++ = BPF_STX_MEM(from->code, from->dst_reg, BPF_REG_AX, from->off); break; + + case BPF_ST | BPF_PROBE_MEM32 | BPF_DW: + case BPF_ST | BPF_PROBE_MEM32 | BPF_W: + case BPF_ST | BPF_PROBE_MEM32 | BPF_H: + case BPF_ST | BPF_PROBE_MEM32 | BPF_B: + *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ + from->imm); + *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); + /* + * Cannot use BPF_STX_MEM() macro here as it + * hardcodes BPF_MEM mode, losing PROBE_MEM32 + * and breaking arena addressing in the JIT. + */ + *to++ = (struct bpf_insn) { + .code = BPF_STX | BPF_PROBE_MEM32 | + BPF_SIZE(from->code), + .dst_reg = from->dst_reg, + .src_reg = BPF_REG_AX, + .off = from->off, + }; + break; } out: return to - to_buff; @@ -1466,27 +1486,16 @@ void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other) * know whether fp here is the clone or the original. */ fp->aux->prog = fp; + if (fp->aux->offload) + fp->aux->offload->prog = fp; bpf_prog_clone_free(fp_other); } -static void adjust_insn_arrays(struct bpf_prog *prog, u32 off, u32 len) -{ -#ifdef CONFIG_BPF_SYSCALL - struct bpf_map *map; - int i; - - if (len <= 1) - return; - - for (i = 0; i < prog->aux->used_map_cnt; i++) { - map = prog->aux->used_maps[i]; - if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY) - bpf_insn_array_adjust(map, off, len); - } -#endif -} - -struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) +/* + * Now this function is used only to blind the main prog and must be invoked only when + * bpf_prog_need_blind() returns true. + */ +struct bpf_prog *bpf_jit_blind_constants(struct bpf_verifier_env *env, struct bpf_prog *prog) { struct bpf_insn insn_buff[16], aux[2]; struct bpf_prog *clone, *tmp; @@ -1494,13 +1503,17 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) struct bpf_insn *insn; int i, rewritten; - if (!prog->blinding_requested || prog->blinded) - return prog; + if (WARN_ON_ONCE(env && env->prog != prog)) + return ERR_PTR(-EINVAL); clone = bpf_prog_clone_create(prog, GFP_USER); if (!clone) return ERR_PTR(-ENOMEM); + /* make sure bpf_patch_insn_data() patches the correct prog */ + if (env) + env->prog = clone; + insn_cnt = clone->len; insn = clone->insnsi; @@ -1528,21 +1541,28 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) if (!rewritten) continue; - tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten); - if (IS_ERR(tmp)) { + if (env) + tmp = bpf_patch_insn_data(env, i, insn_buff, rewritten); + else + tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten); + + if (IS_ERR_OR_NULL(tmp)) { + if (env) + /* restore the original prog */ + env->prog = prog; /* Patching may have repointed aux->prog during * realloc from the original one, so we need to * fix it up here on error. */ bpf_jit_prog_release_other(prog, clone); - return tmp; + return IS_ERR(tmp) ? tmp : ERR_PTR(-ENOMEM); } clone = tmp; insn_delta = rewritten - 1; - /* Instructions arrays must be updated using absolute xlated offsets */ - adjust_insn_arrays(clone, prog->aux->subprog_start + i, rewritten); + if (env) + env->prog = clone; /* Walk new program and skip insns we just inserted. */ insn = clone->insnsi + i + insn_delta; @@ -1553,6 +1573,15 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) clone->blinded = 1; return clone; } + +bool bpf_insn_is_indirect_target(const struct bpf_verifier_env *env, const struct bpf_prog *prog, + int insn_idx) +{ + if (!env) + return false; + insn_idx += prog->aux->subprog_start; + return env->insn_aux_data[insn_idx].indirect_target; +} #endif /* CONFIG_BPF_JIT */ /* Base function for offset calculation. Needs to go into .text section, @@ -1736,6 +1765,12 @@ bool bpf_opcode_in_insntable(u8 code) } #ifndef CONFIG_BPF_JIT_ALWAYS_ON +/* Absolute value of s32 without undefined behavior for S32_MIN */ +static u32 abs_s32(s32 x) +{ + return x >= 0 ? (u32)x : -(u32)x; +} + /** * ___bpf_prog_run - run eBPF program on a given context * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers @@ -1900,8 +1935,8 @@ select_insn: DST = do_div(AX, (u32) SRC); break; case 1: - AX = abs((s32)DST); - AX = do_div(AX, abs((s32)SRC)); + AX = abs_s32((s32)DST); + AX = do_div(AX, abs_s32((s32)SRC)); if ((s32)DST < 0) DST = (u32)-AX; else @@ -1928,8 +1963,8 @@ select_insn: DST = do_div(AX, (u32) IMM); break; case 1: - AX = abs((s32)DST); - AX = do_div(AX, abs((s32)IMM)); + AX = abs_s32((s32)DST); + AX = do_div(AX, abs_s32((s32)IMM)); if ((s32)DST < 0) DST = (u32)-AX; else @@ -1955,8 +1990,8 @@ select_insn: DST = (u32) AX; break; case 1: - AX = abs((s32)DST); - do_div(AX, abs((s32)SRC)); + AX = abs_s32((s32)DST); + do_div(AX, abs_s32((s32)SRC)); if (((s32)DST < 0) == ((s32)SRC < 0)) DST = (u32)AX; else @@ -1982,8 +2017,8 @@ select_insn: DST = (u32) AX; break; case 1: - AX = abs((s32)DST); - do_div(AX, abs((s32)IMM)); + AX = abs_s32((s32)DST); + do_div(AX, abs_s32((s32)IMM)); if (((s32)DST < 0) == ((s32)IMM < 0)) DST = (u32)AX; else @@ -2060,12 +2095,12 @@ select_insn: if (unlikely(tail_call_cnt >= MAX_TAIL_CALL_CNT)) goto out; - tail_call_cnt++; - prog = READ_ONCE(array->ptrs[index]); if (!prog) goto out; + tail_call_cnt++; + /* ARG1 at this point is guaranteed to point to CTX from * the verifier side due to the fact that the tail call is * handled like a helper, that is, bpf_tail_call_proto, @@ -2505,18 +2540,55 @@ static bool bpf_prog_select_interpreter(struct bpf_prog *fp) return select_interpreter; } -/** - * bpf_prog_select_runtime - select exec runtime for BPF program - * @fp: bpf_prog populated with BPF program - * @err: pointer to error variable - * - * Try to JIT eBPF program, if JIT is not available, use interpreter. - * The BPF program will be executed via bpf_prog_run() function. - * - * Return: the &fp argument along with &err set to 0 for success or - * a negative errno code on failure - */ -struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) +static struct bpf_prog *bpf_prog_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog) +{ +#ifdef CONFIG_BPF_JIT + struct bpf_prog *orig_prog; + struct bpf_insn_aux_data *orig_insn_aux; + + if (!bpf_prog_need_blind(prog)) + return bpf_int_jit_compile(env, prog); + + if (env) { + /* + * If env is not NULL, we are called from the end of bpf_check(), at this + * point, only insn_aux_data is used after failure, so it should be restored + * on failure. + */ + orig_insn_aux = bpf_dup_insn_aux_data(env); + if (!orig_insn_aux) + return prog; + } + + orig_prog = prog; + prog = bpf_jit_blind_constants(env, prog); + /* + * If blinding was requested and we failed during blinding, we must fall + * back to the interpreter. + */ + if (IS_ERR(prog)) + goto out_restore; + + prog = bpf_int_jit_compile(env, prog); + if (prog->jited) { + bpf_jit_prog_release_other(prog, orig_prog); + if (env) + vfree(orig_insn_aux); + return prog; + } + + bpf_jit_prog_release_other(orig_prog, prog); + +out_restore: + prog = orig_prog; + if (env) + bpf_restore_insn_aux_data(env, orig_insn_aux); +#endif + return prog; +} + +struct bpf_prog *__bpf_prog_select_runtime(struct bpf_verifier_env *env, struct bpf_prog *fp, + int *err) { /* In case of BPF to BPF calls, verifier did all the prep * work with regards to JITing, etc. @@ -2544,7 +2616,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) if (*err) return fp; - fp = bpf_int_jit_compile(fp); + fp = bpf_prog_jit_compile(env, fp); bpf_prog_jit_attempt_done(fp); if (!fp->jited && jit_needed) { *err = -ENOTSUPP; @@ -2570,6 +2642,22 @@ finalize: return fp; } + +/** + * bpf_prog_select_runtime - select exec runtime for BPF program + * @fp: bpf_prog populated with BPF program + * @err: pointer to error variable + * + * Try to JIT eBPF program, if JIT is not available, use interpreter. + * The BPF program will be executed via bpf_prog_run() function. + * + * Return: the &fp argument along with &err set to 0 for success or + * a negative errno code on failure + */ +struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) +{ + return __bpf_prog_select_runtime(NULL, fp, err); +} EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); static unsigned int __bpf_prog_ret1(const void *ctx, @@ -2586,8 +2674,10 @@ static struct bpf_prog_dummy { }, }; -struct bpf_empty_prog_array bpf_empty_prog_array = { - .null_prog = NULL, +struct bpf_prog_array bpf_empty_prog_array = { + .items = { + { .prog = NULL }, + }, }; EXPORT_SYMBOL(bpf_empty_prog_array); @@ -2598,14 +2688,14 @@ struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) if (prog_cnt) p = kzalloc_flex(*p, items, prog_cnt + 1, flags); else - p = &bpf_empty_prog_array.hdr; + p = &bpf_empty_prog_array; return p; } void bpf_prog_array_free(struct bpf_prog_array *progs) { - if (!progs || progs == &bpf_empty_prog_array.hdr) + if (!progs || progs == &bpf_empty_prog_array) return; kfree_rcu(progs, rcu); } @@ -2614,19 +2704,17 @@ static void __bpf_prog_array_free_sleepable_cb(struct rcu_head *rcu) { struct bpf_prog_array *progs; - /* If RCU Tasks Trace grace period implies RCU grace period, there is - * no need to call kfree_rcu(), just call kfree() directly. + /* + * RCU Tasks Trace grace period implies RCU grace period, there is no + * need to call kfree_rcu(), just call kfree() directly. */ progs = container_of(rcu, struct bpf_prog_array, rcu); - if (rcu_trace_implies_rcu_gp()) - kfree(progs); - else - kfree_rcu(progs, rcu); + kfree(progs); } void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs) { - if (!progs || progs == &bpf_empty_prog_array.hdr) + if (!progs || progs == &bpf_empty_prog_array) return; call_rcu_tasks_trace(&progs->rcu, __bpf_prog_array_free_sleepable_cb); } @@ -3057,7 +3145,7 @@ const struct bpf_func_proto bpf_tail_call_proto = { * It is encouraged to implement bpf_int_jit_compile() instead, so that * eBPF and implicitly also cBPF can get JITed! */ -struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_prog *prog) +struct bpf_prog * __weak bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog) { return prog; } @@ -3287,6 +3375,63 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_bulk_tx); #ifdef CONFIG_BPF_SYSCALL +void bpf_get_linfo_file_line(struct btf *btf, const struct bpf_line_info *linfo, + const char **filep, const char **linep, int *nump) +{ + /* Get base component of the file path. */ + if (filep) { + *filep = btf_name_by_offset(btf, linfo->file_name_off); + *filep = kbasename(*filep); + } + + /* Obtain the source line, and strip whitespace in prefix. */ + if (linep) { + *linep = btf_name_by_offset(btf, linfo->line_off); + while (isspace(**linep)) + *linep += 1; + } + + if (nump) + *nump = BPF_LINE_INFO_LINE_NUM(linfo->line_col); +} + +const struct bpf_line_info *bpf_find_linfo(const struct bpf_prog *prog, u32 insn_off) +{ + const struct bpf_line_info *linfo; + u32 nr_linfo; + int l, r, m; + + nr_linfo = prog->aux->nr_linfo; + if (!nr_linfo || insn_off >= prog->len) + return NULL; + + linfo = prog->aux->linfo; + /* Loop invariant: linfo[l].insn_off <= insns_off. + * linfo[0].insn_off == 0 which always satisfies above condition. + * Binary search is searching for rightmost linfo entry that satisfies + * the above invariant, giving us the desired record that covers given + * instruction offset. + */ + l = 0; + r = nr_linfo - 1; + while (l < r) { + /* (r - l + 1) / 2 means we break a tie to the right, so if: + * l=1, r=2, linfo[l].insn_off <= insn_off, linfo[r].insn_off > insn_off, + * then m=2, we see that linfo[m].insn_off > insn_off, and so + * r becomes 1 and we exit the loop with correct l==1. + * If the tie was broken to the left, m=1 would end us up in + * an endless loop where l and m stay at 1 and r stays at 2. + */ + m = l + (r - l + 1) / 2; + if (linfo[m].insn_off <= insn_off) + l = m; + else + r = m - 1; + } + + return &linfo[l]; +} + int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char **filep, const char **linep, int *nump) { @@ -3321,14 +3466,7 @@ int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char * if (idx == -1) return -ENOENT; - /* Get base component of the file path. */ - *filep = btf_name_by_offset(btf, linfo[idx].file_name_off); - *filep = kbasename(*filep); - /* Obtain the source line, and strip whitespace in prefix. */ - *linep = btf_name_by_offset(btf, linfo[idx].line_off); - while (isspace(**linep)) - *linep += 1; - *nump = BPF_LINE_INFO_LINE_NUM(linfo[idx].line_col); + bpf_get_linfo_file_line(btf, &linfo[idx], filep, linep, nump); return 0; } |