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>

1 files changed, 54 insertions, 11 deletions

diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index 883f88fa5bfc..8740406df2cd 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -21,10 +21,39 @@ static const char * const func_id_str[] = {
 };
 #undef __BPF_FUNC_STR_FN
 
-const char *func_id_name(int id)
+static const char *__func_get_name(const struct bpf_insn_cbs *cbs,
+                                   const struct bpf_insn *insn,
+                                   char *buff, size_t len)
 {
         BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID);
 
+        if (insn->src_reg != BPF_PSEUDO_CALL &&
+            insn->imm >= 0 && insn->imm < __BPF_FUNC_MAX_ID &&
+            func_id_str[insn->imm])
+                return func_id_str[insn->imm];
+
+        if (cbs && cbs->cb_call)
+                return cbs->cb_call(cbs->private_data, insn);
+
+        if (insn->src_reg == BPF_PSEUDO_CALL)
+                snprintf(buff, len, "%+d", insn->imm);
+
+        return buff;
+}
+
+static const char *__func_imm_name(const struct bpf_insn_cbs *cbs,
+                                   const struct bpf_insn *insn,
+                                   u64 full_imm, char *buff, size_t len)
+{
+        if (cbs && cbs->cb_imm)
+                return cbs->cb_imm(cbs->private_data, insn, full_imm);
+
+        snprintf(buff, len, "0x%llx", (unsigned long long)full_imm);
+        return buff;
+}
+
+const char *func_id_name(int id)
+{
         if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id])
                 return func_id_str[id];
         else
@@ -83,7 +112,7 @@ static const char *const bpf_jmp_string[16] = {
         [BPF_EXIT >> 4] = "exit",
 };
 
-static void print_bpf_end_insn(bpf_insn_print_cb verbose,
+static void print_bpf_end_insn(bpf_insn_print_t verbose,
                                struct bpf_verifier_env *env,
                                const struct bpf_insn *insn)
 {
@@ -92,9 +121,12 @@ static void print_bpf_end_insn(bpf_insn_print_cb verbose,
                 insn->imm, insn->dst_reg);
 }
 
-void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env,
-                    const struct bpf_insn *insn, bool allow_ptr_leaks)
+void print_bpf_insn(const struct bpf_insn_cbs *cbs,
+                    struct bpf_verifier_env *env,
+                    const struct bpf_insn *insn,
+                    bool allow_ptr_leaks)
 {
+        const bpf_insn_print_t verbose = cbs->cb_print;
         u8 class = BPF_CLASS(insn->code);
 
         if (class == BPF_ALU || class == BPF_ALU64) {
@@ -175,12 +207,15 @@ void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env,
                          */
                         u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
                         bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+                        char tmp[64];
 
                         if (map_ptr && !allow_ptr_leaks)
                                 imm = 0;
 
-                        verbose(env, "(%02x) r%d = 0x%llx\n", insn->code,
-                                insn->dst_reg, (unsigned long long)imm);
+                        verbose(env, "(%02x) r%d = %s\n",
+                                insn->code, insn->dst_reg,
+                                __func_imm_name(cbs, insn, imm,
+                                                tmp, sizeof(tmp)));
                 } else {
                         verbose(env, "BUG_ld_%02x\n", insn->code);
                         return;
@@ -189,12 +224,20 @@ void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env,
                 u8 opcode = BPF_OP(insn->code);
 
                 if (opcode == BPF_CALL) {
-                        if (insn->src_reg == BPF_PSEUDO_CALL)
-                                verbose(env, "(%02x) call pc%+d\n", insn->code,
-                                        insn->imm);
-                        else
+                        char tmp[64];
+
+                        if (insn->src_reg == BPF_PSEUDO_CALL) {
+                                verbose(env, "(%02x) call pc%s\n",
+                                        insn->code,
+                                        __func_get_name(cbs, insn,
+                                                        tmp, sizeof(tmp)));
+                        } else {
+                                strcpy(tmp, "unknown");
                                 verbose(env, "(%02x) call %s#%d\n", insn->code,
-                                        func_id_name(insn->imm), insn->imm);
+                                        __func_get_name(cbs, insn,
+                                                        tmp, sizeof(tmp)),
+                                        insn->imm);
+                        }
                 } else if (insn->code == (BPF_JMP | BPF_JA)) {
                         verbose(env, "(%02x) goto pc%+d\n",
                                 insn->code, insn->off);