[PATCH bpf-next v2 10/22] bpf: Batch the patches of bpf_opt_subreg_zext_lo32_rnd_hi32()

[Qiliang Yuan]

bpf_opt_subreg_zext_lo32_rnd_hi32() inserts a zero extension, or with
BPF_F_TEST_RND_HI32 a randomization of the upper half, after every
instruction that needs it, one bpf_patch_insn_data() at a time.

Each of them costs O(prog->len). Loading pyperf180 with
BPF_F_TEST_RND_HI32 does 4610 of them, which takes more than twice as
long as loading it without.

Queue them with bpf_patch_list_add() and commit them at the end of the
pass.

perf stat -r10 of loading with BPF_F_TEST_RND_HI32, average of two
runs, x86_64 VM with 32 vCPUs, before and after this patch:

              before     after
  pyperf180   1.507 s    0.359 s
  pyperf600   4.533 s    0.899 s

Signed-off-by: Qiliang Yuan <odys.yuan@xxxxxxxxx>
---
 kernel/bpf/fixups.c | 22 ++++++++--------------
 1 file changed, 8 insertions(+), 14 deletions(-)

diff --git a/kernel/bpf/fixups.c b/kernel/bpf/fixups.c
index 7c7c38eb9f0c2..6c2dce8f3b6eb 100644
--- a/kernel/bpf/fixups.c
+++ b/kernel/bpf/fixups.c
@@ -922,9 +922,8 @@ int bpf_opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env,
 	struct bpf_insn *zext_patch = env->insn_buf;
 	struct bpf_insn *rnd_hi32_patch = &env->insn_buf[2];
 	struct bpf_insn_aux_data *aux = env->insn_aux_data;
-	int i, patch_len, delta = 0, len = env->prog->len;
+	int i, patch_len, len = env->prog->len;
 	struct bpf_insn *insns = env->prog->insnsi;
-	struct bpf_prog *new_prog;
 	bool rnd_hi32;
 
 	rnd_hi32 = attr->prog_flags & BPF_F_TEST_RND_HI32;
@@ -933,13 +932,12 @@ int bpf_opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env,
 	rnd_hi32_patch[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32);
 	rnd_hi32_patch[3] = BPF_ALU64_REG(BPF_OR, 0, BPF_REG_AX);
 	for (i = 0; i < len; i++) {
-		int adj_idx = i + delta;
 		struct bpf_insn insn;
 		int load_reg;
 
-		insn = insns[adj_idx];
+		insn = insns[i];
 		load_reg = insn_def_regno(&insn);
-		if (!aux[adj_idx].zext_dst) {
+		if (!aux[i].zext_dst) {
 			u8 code, class;
 			u32 imm_rnd;
 
@@ -960,7 +958,7 @@ int bpf_opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env,
 
 			/* ctx load could be transformed into wider load. */
 			if (class == BPF_LDX &&
-			    aux[adj_idx].ptr_type == PTR_TO_CTX)
+			    aux[i].ptr_type == PTR_TO_CTX)
 				continue;
 
 			imm_rnd = get_random_u32();
@@ -999,16 +997,12 @@ int bpf_opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env,
 		patch = zext_patch;
 		patch_len = 2;
 apply_patch_buffer:
-		new_prog = bpf_patch_insn_data(env, adj_idx, patch, patch_len);
-		if (!new_prog)
-			return -ENOMEM;
-		env->prog = new_prog;
-		insns = new_prog->insnsi;
-		aux = env->insn_aux_data;
-		delta += patch_len - 1;
+		patch = bpf_patch_list_add(env, i, patch, patch_len);
+		if (IS_ERR(patch))
+			return PTR_ERR(patch);
 	}
 
-	return 0;
+	return bpf_patch_list_commit(env);
 }
 
 /*

-- 
2.43.0