[PATCH bpf-next] bpf: avoid retpoline for bpf_for_each_map_elem

[Andrey Ignatov <rdna@fb.com>]

Similarly to 09772d92cd5a ("bpf: avoid retpoline for
lookup/update/delete calls on maps") and 84430d4232c3 ("bpf, verifier:
avoid retpoline for map push/pop/peek operation") avoid indirect call
while calling bpf_for_each_map_elem.

Before (a program fragment):

  ; if (rules_map) {
   142: (15) if r4 == 0x0 goto pc+8
   143: (bf) r3 = r10
  ; bpf_for_each_map_elem(rules_map, process_each_rule, &ctx, 0);
   144: (07) r3 += -24
   145: (bf) r1 = r4
   146: (18) r2 = subprog[+5]
   148: (b7) r4 = 0
   149: (85) call bpf_for_each_map_elem#143680  <-- indirect call via
                                                    helper

After (same program fragment):

   ; if (rules_map) {
    142: (15) if r4 == 0x0 goto pc+8
    143: (bf) r3 = r10
   ; bpf_for_each_map_elem(rules_map, process_each_rule, &ctx, 0);
    144: (07) r3 += -24
    145: (bf) r1 = r4
    146: (18) r2 = subprog[+5]
    148: (b7) r4 = 0
    149: (85) call bpf_for_each_array_elem#170336  <-- direct call

On a benchmark that calls bpf_for_each_map_elem() once and does many
other things (mostly checking fields in skb) with CONFIG_RETPOLINE=y it
makes program faster.

Before:

  ============================================================================
  Benchmark.cpp                                              time/iter iters/s
  ============================================================================
  IngressMatchByRemoteEndpoint                                80.78ns 12.38M
  IngressMatchByRemoteIP                                      80.66ns 12.40M
  IngressMatchByRemotePort                                    80.87ns 12.37M

After:

  ============================================================================
  Benchmark.cpp                                              time/iter iters/s
  ============================================================================
  IngressMatchByRemoteEndpoint                                73.49ns 13.61M
  IngressMatchByRemoteIP                                      71.48ns 13.99M
  IngressMatchByRemotePort                                    70.39ns 14.21M

Signed-off-by: Andrey Ignatov <rdna@fb.com>
---
 kernel/bpf/verifier.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1433752db740..68948f1ed443 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -12946,7 +12946,8 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 		     insn->imm == BPF_FUNC_map_push_elem   ||
 		     insn->imm == BPF_FUNC_map_pop_elem    ||
 		     insn->imm == BPF_FUNC_map_peek_elem   ||
-		     insn->imm == BPF_FUNC_redirect_map)) {
+		     insn->imm == BPF_FUNC_redirect_map    ||
+		     insn->imm == BPF_FUNC_for_each_map_elem)) {
 			aux = &env->insn_aux_data[i + delta];
 			if (bpf_map_ptr_poisoned(aux))
 				goto patch_call_imm;
@@ -12990,6 +12991,11 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 				     (int (*)(struct bpf_map *map, void *value))NULL));
 			BUILD_BUG_ON(!__same_type(ops->map_redirect,
 				     (int (*)(struct bpf_map *map, u32 ifindex, u64 flags))NULL));
+			BUILD_BUG_ON(!__same_type(ops->map_for_each_callback,
+				     (int (*)(struct bpf_map *map,
+					      bpf_callback_t callback_fn,
+					      void *callback_ctx,
+					      u64 flags))NULL));
 
 patch_map_ops_generic:
 			switch (insn->imm) {
@@ -13014,6 +13020,9 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 			case BPF_FUNC_redirect_map:
 				insn->imm = BPF_CALL_IMM(ops->map_redirect);
 				continue;
+			case BPF_FUNC_for_each_map_elem:
+				insn->imm = BPF_CALL_IMM(ops->map_for_each_callback);
+				continue;
 			}
 
 			goto patch_call_imm;
-- 
2.30.2