diff options
author | Daniel Borkmann <daniel@iogearbox.net> | 2017-12-20 13:42:57 +0100 |
---|---|---|
committer | Alexei Starovoitov <ast@kernel.org> | 2017-12-20 18:09:40 -0800 |
commit | 7105e828c087de970fcb5a9509db51bfe6bd7894 (patch) | |
tree | 47cca432779b910dab12ee5cc81b792f6e432a76 /tools/bpf | |
parent | 4f74d80971bce93d9e608c40324d662c70eb4664 (diff) | |
download | linux-stable-7105e828c087de970fcb5a9509db51bfe6bd7894.tar.gz linux-stable-7105e828c087de970fcb5a9509db51bfe6bd7894.tar.bz2 linux-stable-7105e828c087de970fcb5a9509db51bfe6bd7894.zip |
bpf: allow for correlation of maps and helpers in dump
Currently a dump of an xlated prog (post verifier stage) doesn't
correlate used helpers as well as maps. The prog info lists
involved map ids, however there's no correlation of where in the
program they are used as of today. Likewise, bpftool does not
correlate helper calls with the target functions.
The latter can be done w/o any kernel changes through kallsyms,
and also has the advantage that this works with inlined helpers
and BPF calls.
Example, via interpreter:
# tc filter show dev foo ingress
filter protocol all pref 49152 bpf chain 0
filter protocol all pref 49152 bpf chain 0 handle 0x1 foo.o:[ingress] \
direct-action not_in_hw id 1 tag c74773051b364165 <-- prog id:1
* Output before patch (calls/maps remain unclear):
# bpftool prog dump xlated id 1 <-- dump prog id:1
0: (b7) r1 = 2
1: (63) *(u32 *)(r10 -4) = r1
2: (bf) r2 = r10
3: (07) r2 += -4
4: (18) r1 = 0xffff95c47a8d4800
6: (85) call unknown#73040
7: (15) if r0 == 0x0 goto pc+18
8: (bf) r2 = r10
9: (07) r2 += -4
10: (bf) r1 = r0
11: (85) call unknown#73040
12: (15) if r0 == 0x0 goto pc+23
[...]
* Output after patch:
# bpftool prog dump xlated id 1
0: (b7) r1 = 2
1: (63) *(u32 *)(r10 -4) = r1
2: (bf) r2 = r10
3: (07) r2 += -4
4: (18) r1 = map[id:2] <-- map id:2
6: (85) call bpf_map_lookup_elem#73424 <-- helper call
7: (15) if r0 == 0x0 goto pc+18
8: (bf) r2 = r10
9: (07) r2 += -4
10: (bf) r1 = r0
11: (85) call bpf_map_lookup_elem#73424
12: (15) if r0 == 0x0 goto pc+23
[...]
# bpftool map show id 2 <-- show/dump/etc map id:2
2: hash_of_maps flags 0x0
key 4B value 4B max_entries 3 memlock 4096B
Example, JITed, same prog:
# tc filter show dev foo ingress
filter protocol all pref 49152 bpf chain 0
filter protocol all pref 49152 bpf chain 0 handle 0x1 foo.o:[ingress] \
direct-action not_in_hw id 3 tag c74773051b364165 jited
# bpftool prog show id 3
3: sched_cls tag c74773051b364165
loaded_at Dec 19/13:48 uid 0
xlated 384B jited 257B memlock 4096B map_ids 2
# bpftool prog dump xlated id 3
0: (b7) r1 = 2
1: (63) *(u32 *)(r10 -4) = r1
2: (bf) r2 = r10
3: (07) r2 += -4
4: (18) r1 = map[id:2] <-- map id:2
6: (85) call __htab_map_lookup_elem#77408 <-+ inlined rewrite
7: (15) if r0 == 0x0 goto pc+2 |
8: (07) r0 += 56 |
9: (79) r0 = *(u64 *)(r0 +0) <-+
10: (15) if r0 == 0x0 goto pc+24
11: (bf) r2 = r10
12: (07) r2 += -4
[...]
Example, same prog, but kallsyms disabled (in that case we are
also not allowed to pass any relative offsets, etc, so prog
becomes pointer sanitized on dump):
# sysctl kernel.kptr_restrict=2
kernel.kptr_restrict = 2
# bpftool prog dump xlated id 3
0: (b7) r1 = 2
1: (63) *(u32 *)(r10 -4) = r1
2: (bf) r2 = r10
3: (07) r2 += -4
4: (18) r1 = map[id:2]
6: (85) call bpf_unspec#0
7: (15) if r0 == 0x0 goto pc+2
[...]
Example, BPF calls via interpreter:
# bpftool prog dump xlated id 1
0: (85) call pc+2#__bpf_prog_run_args32
1: (b7) r0 = 1
2: (95) exit
3: (b7) r0 = 2
4: (95) exit
Example, BPF calls via JIT:
# sysctl net.core.bpf_jit_enable=1
net.core.bpf_jit_enable = 1
# sysctl net.core.bpf_jit_kallsyms=1
net.core.bpf_jit_kallsyms = 1
# bpftool prog dump xlated id 1
0: (85) call pc+2#bpf_prog_3b185187f1855c4c_F
1: (b7) r0 = 1
2: (95) exit
3: (b7) r0 = 2
4: (95) exit
And finally, an example for tail calls that is now working
as well wrt correlation:
# bpftool prog dump xlated id 2
[...]
10: (b7) r2 = 8
11: (85) call bpf_trace_printk#-41312
12: (bf) r1 = r6
13: (18) r2 = map[id:1]
15: (b7) r3 = 0
16: (85) call bpf_tail_call#12
17: (b7) r1 = 42
18: (6b) *(u16 *)(r6 +46) = r1
19: (b7) r0 = 0
20: (95) exit
# bpftool map show id 1
1: prog_array flags 0x0
key 4B value 4B max_entries 1 memlock 4096B
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'tools/bpf')
-rw-r--r-- | tools/bpf/bpftool/prog.c | 181 |
1 files changed, 172 insertions, 9 deletions
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 037484ceaeaf..42ee8892549c 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -401,6 +401,88 @@ static int do_show(int argc, char **argv) return err; } +#define SYM_MAX_NAME 256 + +struct kernel_sym { + unsigned long address; + char name[SYM_MAX_NAME]; +}; + +struct dump_data { + unsigned long address_call_base; + struct kernel_sym *sym_mapping; + __u32 sym_count; + char scratch_buff[SYM_MAX_NAME]; +}; + +static int kernel_syms_cmp(const void *sym_a, const void *sym_b) +{ + return ((struct kernel_sym *)sym_a)->address - + ((struct kernel_sym *)sym_b)->address; +} + +static void kernel_syms_load(struct dump_data *dd) +{ + struct kernel_sym *sym; + char buff[256]; + void *tmp, *address; + FILE *fp; + + fp = fopen("/proc/kallsyms", "r"); + if (!fp) + return; + + while (!feof(fp)) { + if (!fgets(buff, sizeof(buff), fp)) + break; + tmp = realloc(dd->sym_mapping, + (dd->sym_count + 1) * + sizeof(*dd->sym_mapping)); + if (!tmp) { +out: + free(dd->sym_mapping); + dd->sym_mapping = NULL; + fclose(fp); + return; + } + dd->sym_mapping = tmp; + sym = &dd->sym_mapping[dd->sym_count]; + if (sscanf(buff, "%p %*c %s", &address, sym->name) != 2) + continue; + sym->address = (unsigned long)address; + if (!strcmp(sym->name, "__bpf_call_base")) { + dd->address_call_base = sym->address; + /* sysctl kernel.kptr_restrict was set */ + if (!sym->address) + goto out; + } + if (sym->address) + dd->sym_count++; + } + + fclose(fp); + + qsort(dd->sym_mapping, dd->sym_count, + sizeof(*dd->sym_mapping), kernel_syms_cmp); +} + +static void kernel_syms_destroy(struct dump_data *dd) +{ + free(dd->sym_mapping); +} + +static struct kernel_sym *kernel_syms_search(struct dump_data *dd, + unsigned long key) +{ + struct kernel_sym sym = { + .address = key, + }; + + return dd->sym_mapping ? + bsearch(&sym, dd->sym_mapping, dd->sym_count, + sizeof(*dd->sym_mapping), kernel_syms_cmp) : NULL; +} + static void print_insn(struct bpf_verifier_env *env, const char *fmt, ...) { va_list args; @@ -410,8 +492,71 @@ static void print_insn(struct bpf_verifier_env *env, const char *fmt, ...) va_end(args); } -static void dump_xlated_plain(void *buf, unsigned int len, bool opcodes) +static const char *print_call_pcrel(struct dump_data *dd, + struct kernel_sym *sym, + unsigned long address, + const struct bpf_insn *insn) { + if (sym) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%+d#%s", insn->off, sym->name); + else + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%+d#0x%lx", insn->off, address); + return dd->scratch_buff; +} + +static const char *print_call_helper(struct dump_data *dd, + struct kernel_sym *sym, + unsigned long address) +{ + if (sym) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "%s", sym->name); + else + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "0x%lx", address); + return dd->scratch_buff; +} + +static const char *print_call(void *private_data, + const struct bpf_insn *insn) +{ + struct dump_data *dd = private_data; + unsigned long address = dd->address_call_base + insn->imm; + struct kernel_sym *sym; + + sym = kernel_syms_search(dd, address); + if (insn->src_reg == BPF_PSEUDO_CALL) + return print_call_pcrel(dd, sym, address, insn); + else + return print_call_helper(dd, sym, address); +} + +static const char *print_imm(void *private_data, + const struct bpf_insn *insn, + __u64 full_imm) +{ + struct dump_data *dd = private_data; + + if (insn->src_reg == BPF_PSEUDO_MAP_FD) + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "map[id:%u]", insn->imm); + else + snprintf(dd->scratch_buff, sizeof(dd->scratch_buff), + "0x%llx", (unsigned long long)full_imm); + return dd->scratch_buff; +} + +static void dump_xlated_plain(struct dump_data *dd, void *buf, + unsigned int len, bool opcodes) +{ + const struct bpf_insn_cbs cbs = { + .cb_print = print_insn, + .cb_call = print_call, + .cb_imm = print_imm, + .private_data = dd, + }; struct bpf_insn *insn = buf; bool double_insn = false; unsigned int i; @@ -425,7 +570,7 @@ static void dump_xlated_plain(void *buf, unsigned int len, bool opcodes) double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW); printf("% 4d: ", i); - print_bpf_insn(print_insn, NULL, insn + i, true); + print_bpf_insn(&cbs, NULL, insn + i, true); if (opcodes) { printf(" "); @@ -454,8 +599,15 @@ static void print_insn_json(struct bpf_verifier_env *env, const char *fmt, ...) va_end(args); } -static void dump_xlated_json(void *buf, unsigned int len, bool opcodes) +static void dump_xlated_json(struct dump_data *dd, void *buf, + unsigned int len, bool opcodes) { + const struct bpf_insn_cbs cbs = { + .cb_print = print_insn_json, + .cb_call = print_call, + .cb_imm = print_imm, + .private_data = dd, + }; struct bpf_insn *insn = buf; bool double_insn = false; unsigned int i; @@ -470,7 +622,7 @@ static void dump_xlated_json(void *buf, unsigned int len, bool opcodes) jsonw_start_object(json_wtr); jsonw_name(json_wtr, "disasm"); - print_bpf_insn(print_insn_json, NULL, insn + i, true); + print_bpf_insn(&cbs, NULL, insn + i, true); if (opcodes) { jsonw_name(json_wtr, "opcodes"); @@ -505,6 +657,7 @@ static void dump_xlated_json(void *buf, unsigned int len, bool opcodes) static int do_dump(int argc, char **argv) { struct bpf_prog_info info = {}; + struct dump_data dd = {}; __u32 len = sizeof(info); unsigned int buf_size; char *filepath = NULL; @@ -592,6 +745,14 @@ static int do_dump(int argc, char **argv) goto err_free; } + if ((member_len == &info.jited_prog_len && + info.jited_prog_insns == 0) || + (member_len == &info.xlated_prog_len && + info.xlated_prog_insns == 0)) { + p_err("error retrieving insn dump: kernel.kptr_restrict set?"); + goto err_free; + } + if (filepath) { fd = open(filepath, O_WRONLY | O_CREAT | O_TRUNC, 0600); if (fd < 0) { @@ -608,17 +769,19 @@ static int do_dump(int argc, char **argv) goto err_free; } } else { - if (member_len == &info.jited_prog_len) + if (member_len == &info.jited_prog_len) { disasm_print_insn(buf, *member_len, opcodes); - else + } else { + kernel_syms_load(&dd); if (json_output) - dump_xlated_json(buf, *member_len, opcodes); + dump_xlated_json(&dd, buf, *member_len, opcodes); else - dump_xlated_plain(buf, *member_len, opcodes); + dump_xlated_plain(&dd, buf, *member_len, opcodes); + kernel_syms_destroy(&dd); + } } free(buf); - return 0; err_free: |