riscv: bpf: eliminate zero extension code-gen

Cc: Björn Töpel <bjorn.topel@gmail.com>
Acked-by: Björn Töpel <bjorn.topel@gmail.com>
Tested-by: Björn Töpel <bjorn.topel@gmail.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

arch/riscv/net/bpf_jit_comp.c

@@ -731,6 +731,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 {
 	bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 ||
 		    BPF_CLASS(insn->code) == BPF_JMP;
+	struct bpf_prog_aux *aux = ctx->prog->aux;
 	int rvoff, i = insn - ctx->prog->insnsi;
 	u8 rd = -1, rs = -1, code = insn->code;
 	s16 off = insn->off;
@@ -742,8 +743,13 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	/* dst = src */
 	case BPF_ALU | BPF_MOV | BPF_X:
 	case BPF_ALU64 | BPF_MOV | BPF_X:
+		if (imm == 1) {
+			/* Special mov32 for zext */
+			emit_zext_32(rd, ctx);
+			break;
+		}
 		emit(is64 ? rv_addi(rd, rs, 0) : rv_addiw(rd, rs, 0), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 
@@ -771,19 +777,19 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU | BPF_MUL | BPF_X:
 	case BPF_ALU64 | BPF_MUL | BPF_X:
 		emit(is64 ? rv_mul(rd, rd, rs) : rv_mulw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_DIV | BPF_X:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
 		emit(is64 ? rv_divu(rd, rd, rs) : rv_divuw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MOD | BPF_X:
 	case BPF_ALU64 | BPF_MOD | BPF_X:
 		emit(is64 ? rv_remu(rd, rd, rs) : rv_remuw(rd, rd, rs), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_LSH | BPF_X:
@@ -867,7 +873,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_ALU | BPF_MOV | BPF_K:
 	case BPF_ALU64 | BPF_MOV | BPF_K:
 		emit_imm(rd, imm, ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 
@@ -882,7 +888,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			emit(is64 ? rv_add(rd, rd, RV_REG_T1) :
 			     rv_addw(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_SUB | BPF_K:
@@ -895,7 +901,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			emit(is64 ? rv_sub(rd, rd, RV_REG_T1) :
 			     rv_subw(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_AND | BPF_K:
@@ -906,7 +912,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			emit_imm(RV_REG_T1, imm, ctx);
 			emit(rv_and(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_OR | BPF_K:
@@ -917,7 +923,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			emit_imm(RV_REG_T1, imm, ctx);
 			emit(rv_or(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_XOR | BPF_K:
@@ -928,7 +934,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 			emit_imm(RV_REG_T1, imm, ctx);
 			emit(rv_xor(rd, rd, RV_REG_T1), ctx);
 		}
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MUL | BPF_K:
@@ -936,7 +942,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		emit_imm(RV_REG_T1, imm, ctx);
 		emit(is64 ? rv_mul(rd, rd, RV_REG_T1) :
 		     rv_mulw(rd, rd, RV_REG_T1), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_DIV | BPF_K:
@@ -944,7 +950,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		emit_imm(RV_REG_T1, imm, ctx);
 		emit(is64 ? rv_divu(rd, rd, RV_REG_T1) :
 		     rv_divuw(rd, rd, RV_REG_T1), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_MOD | BPF_K:
@@ -952,7 +958,7 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		emit_imm(RV_REG_T1, imm, ctx);
 		emit(is64 ? rv_remu(rd, rd, RV_REG_T1) :
 		     rv_remuw(rd, rd, RV_REG_T1), ctx);
-		if (!is64)
+		if (!is64 && !aux->verifier_zext)
 			emit_zext_32(rd, ctx);
 		break;
 	case BPF_ALU | BPF_LSH | BPF_K:
@@ -1239,6 +1245,8 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		emit_imm(RV_REG_T1, off, ctx);
 		emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx);
 		emit(rv_lbu(rd, 0, RV_REG_T1), ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_H:
 		if (is_12b_int(off)) {
@@ -1249,6 +1257,8 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		emit_imm(RV_REG_T1, off, ctx);
 		emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx);
 		emit(rv_lhu(rd, 0, RV_REG_T1), ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_W:
 		if (is_12b_int(off)) {
@@ -1259,6 +1269,8 @@ static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 		emit_imm(RV_REG_T1, off, ctx);
 		emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx);
 		emit(rv_lwu(rd, 0, RV_REG_T1), ctx);
+		if (insn_is_zext(&insn[1]))
+			return 1;
 		break;
 	case BPF_LDX | BPF_MEM | BPF_DW:
 		if (is_12b_int(off)) {
@@ -1503,6 +1515,11 @@ static void bpf_flush_icache(void *start, void *end)
 	flush_icache_range((unsigned long)start, (unsigned long)end);
 }
 
+bool bpf_jit_needs_zext(void)
+{
+	return true;
+}
+
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {
 	bool tmp_blinded = false, extra_pass = false;