This patch adds two optimizations for BPF_ALU BPF_END BPF_FROM_LE in
the RV64 BPF JIT.
First, it enables the verifier zero-extension optimization to avoid zero
extension when imm == 32. Second, it avoids generating code for imm ==
64, since it is equivalent to a no-op.
Co-developed-by: Xi Wang <xi.wang@xxxxxxxxx>
Signed-off-by: Xi Wang <xi.wang@xxxxxxxxx>
Signed-off-by: Luke Nelson <luke.r.nels@xxxxxxxxx>
---
arch/riscv/net/bpf_jit_comp64.c | 20 ++++++++++++++------
1 file changed, 14 insertions(+), 6 deletions(-)
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index e2636902a74e..c3ce9a911b66 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -542,13 +542,21 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
/* dst = BSWAP##imm(dst) */
case BPF_ALU | BPF_END | BPF_FROM_LE:
- {
- int shift = 64 - imm;
-
- emit(rv_slli(rd, rd, shift), ctx);
- emit(rv_srli(rd, rd, shift), ctx);
+ switch (imm) {
+ case 16:
+ emit(rv_slli(rd, rd, 48), ctx);
+ emit(rv_srli(rd, rd, 48), ctx);
+ break;
+ case 32:
+ if (!aux->verifier_zext)
+ emit_zext_32(rd, ctx);
+ break;
+ case 64:
+ /* Do nothing */
+ break;
+ }
break;
- }
+
case BPF_ALU | BPF_END | BPF_FROM_BE:
emit(rv_addi(RV_REG_T2, RV_REG_ZERO, 0), ctx);
--
2.17.1
