bpf, riscv: Optimize BPF_JSET BPF_K using andi on RV64

This patch optimizes BPF_JSET BPF_K by using a RISC-V andi instruction
when the BPF immediate fits in 12 bits, instead of first loading the
immediate to a temporary register.

Examples of generated code with and without this optimization:

BPF_JMP_IMM(BPF_JSET, R1, 2, 1) without optimization:

  20: li    t1,2
  24: and   t1,a0,t1
  28: bnez  t1,0x30

BPF_JMP_IMM(BPF_JSET, R1, 2, 1) with optimization:

  20: andi  t1,a0,2
  24: bnez  t1,0x2c

BPF_JMP32_IMM(BPF_JSET, R1, 2, 1) without optimization:

  20: li    t1,2
  24: mv    t2,a0
  28: slli  t2,t2,0x20
  2c: srli  t2,t2,0x20
  30: slli  t1,t1,0x20
  34: srli  t1,t1,0x20
  38: and   t1,t2,t1
  3c: bnez  t1,0x44

BPF_JMP32_IMM(BPF_JSET, R1, 2, 1) with optimization:

  20: andi  t1,a0,2
  24: bnez  t1,0x2c

In these examples, because the upper 32 bits of the sign-extended
immediate are 0, BPF_JMP BPF_JSET and BPF_JMP32 BPF_JSET are equivalent
and therefore the JIT produces identical code for them.
Co-developed-by: Xi Wang <xi.wang@gmail.com>
Signed-off-by: Xi Wang <xi.wang@gmail.com>
Signed-off-by: Luke Nelson <luke.r.nels@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Björn Töpel <bjorn.topel@gmail.com>
Acked-by: Björn Töpel <bjorn.topel@gmail.com>
Link: https://lore.kernel.org/bpf/20200506000320.28965-5-luke.r.nels@gmail.com

arch/riscv/net/bpf_jit_comp64.c

@@ -792,8 +792,6 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 	case BPF_JMP32 | BPF_JSGE | BPF_K:
 	case BPF_JMP | BPF_JSLE | BPF_K:
 	case BPF_JMP32 | BPF_JSLE | BPF_K:
-	case BPF_JMP | BPF_JSET | BPF_K:
-	case BPF_JMP32 | BPF_JSET | BPF_K:
 		rvoff = rv_offset(i, off, ctx);
 		s = ctx->ninsns;
 		if (imm) {
@@ -813,15 +811,28 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
 
 		/* Adjust for extra insns */
 		rvoff -= (e - s) << 2;
+		emit_branch(BPF_OP(code), rd, rs, rvoff, ctx);
+		break;
 
-		if (BPF_OP(code) == BPF_JSET) {
-			/* Adjust for and */
-			rvoff -= 4;
-			emit(rv_and(rs, rd, rs), ctx);
-			emit_branch(BPF_JNE, rs, RV_REG_ZERO, rvoff, ctx);
+	case BPF_JMP | BPF_JSET | BPF_K:
+	case BPF_JMP32 | BPF_JSET | BPF_K:
+		rvoff = rv_offset(i, off, ctx);
+		s = ctx->ninsns;
+		if (is_12b_int(imm)) {
+			emit(rv_andi(RV_REG_T1, rd, imm), ctx);
 		} else {
-			emit_branch(BPF_OP(code), rd, rs, rvoff, ctx);
+			emit_imm(RV_REG_T1, imm, ctx);
+			emit(rv_and(RV_REG_T1, rd, RV_REG_T1), ctx);
 		}
+		/* For jset32, we should clear the upper 32 bits of t1, but
+		 * sign-extension is sufficient here and saves one instruction,
+		 * as t1 is used only in comparison against zero.
+		 */
+		if (!is64 && imm < 0)
+			emit(rv_addiw(RV_REG_T1, RV_REG_T1, 0), ctx);
+		e = ctx->ninsns;
+		rvoff -= (e - s) << 2;
+		emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff, ctx);
 		break;
 
 	/* function call */