arm: bpf: eliminate zero extension code-gen

Cc: Shubham Bansal <illusionist.neo@gmail.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

arch/arm/net/bpf_jit_32.c

@@ -736,7 +736,8 @@ static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
 
 		/* ALU operation */
 		emit_alu_r(rd[1], rs, true, false, op, ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 	}
 
 	arm_bpf_put_reg64(dst, rd, ctx);
@@ -758,8 +759,9 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
 				  struct jit_ctx *ctx) {
 	if (!is64) {
 		emit_a32_mov_r(dst_lo, src_lo, ctx);
-		/* Zero out high 4 bytes */
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			/* Zero out high 4 bytes */
+			emit_a32_mov_i(dst_hi, 0, ctx);
 	} else if (__LINUX_ARM_ARCH__ < 6 &&
 		   ctx->cpu_architecture < CPU_ARCH_ARMv5TE) {
 		/* complete 8 byte move */
@@ -1060,17 +1062,20 @@ static inline void emit_ldx_r(const s8 dst[], const s8 src,
 	case BPF_B:
 		/* Load a Byte */
 		emit(ARM_LDRB_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_H:
 		/* Load a HalfWord */
 		emit(ARM_LDRH_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_W:
 		/* Load a Word */
 		emit(ARM_LDR_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(rd[0], 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_DW:
 		/* Load a Double Word */
@@ -1359,6 +1364,11 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_MOV | BPF_X:
 		switch (BPF_SRC(code)) {
 		case BPF_X:
+			if (imm == 1) {
+				/* Special mov32 for zext */
+				emit_a32_mov_i(dst_hi, 0, ctx);
+				break;
+			}
 			emit_a32_mov_r64(is64, dst, src, ctx);
 			break;
 		case BPF_K:
@@ -1438,7 +1448,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		}
 		emit_udivmod(rd_lo, rd_lo, rt, ctx, BPF_OP(code));
 		arm_bpf_put_reg32(dst_lo, rd_lo, ctx);
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	case BPF_ALU64 | BPF_DIV | BPF_K:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
@@ -1453,7 +1464,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			return -EINVAL;
 		if (imm)
 			emit_a32_alu_i(dst_lo, imm, ctx, BPF_OP(code));
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	/* dst = dst << imm */
 	case BPF_ALU64 | BPF_LSH | BPF_K:
@@ -1488,7 +1500,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	/* dst = ~dst */
 	case BPF_ALU | BPF_NEG:
 		emit_a32_alu_i(dst_lo, 0, ctx, BPF_OP(code));
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		if (!ctx->prog->aux->verifier_zext)
+			emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	/* dst = ~dst (64 bit) */
 	case BPF_ALU64 | BPF_NEG:
@@ -1544,11 +1557,13 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 #else /* ARMv6+ */
 			emit(ARM_UXTH(rd[1], rd[1]), ctx);
 #endif
-			emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
+			if (!ctx->prog->aux->verifier_zext)
+				emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
 			break;
 		case 32:
 			/* zero-extend 32 bits into 64 bits */
-			emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
+			if (!ctx->prog->aux->verifier_zext)
+				emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
 			break;
 		case 64:
 			/* nop */
@@ -1838,6 +1853,11 @@ void bpf_jit_compile(struct bpf_prog *prog)
 	/* Nothing to do here. We support Internal BPF. */
 }
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	struct bpf_prog *tmp, *orig_prog = prog;