riscv, bpf: try RVC for reg move within BPF_CMPXCHG JIT

[PATCH] riscv, bpf: try RVC for reg move within BPF_CMPXCHG JIT

Posted by Xiao Wang 1 year, 8 months ago

We could try to emit compressed insn for reg move operation during CMPXCHG
JIT, the instruction compression has no impact on the jump offsets of
following forward and backward jump instructions.

Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
---
 arch/riscv/net/bpf_jit_comp64.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index aac190085472..c134aaec4295 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -531,8 +531,10 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
 	/* r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg); */
 	case BPF_CMPXCHG:
 		r0 = bpf_to_rv_reg(BPF_REG_0, ctx);
-		emit(is64 ? rv_addi(RV_REG_T2, r0, 0) :
-		     rv_addiw(RV_REG_T2, r0, 0), ctx);
+		if (is64)
+			emit_mv(RV_REG_T2, r0, ctx);
+		else
+			emit_addiw(RV_REG_T2, r0, 0, ctx);
 		emit(is64 ? rv_lr_d(r0, 0, rd, 0, 0) :
 		     rv_lr_w(r0, 0, rd, 0, 0), ctx);
 		jmp_offset = ninsns_rvoff(8);
-- 
2.25.1

Re: [PATCH] riscv, bpf: try RVC for reg move within BPF_CMPXCHG JIT

Posted by Björn Töpel 1 year, 8 months ago

Xiao Wang <xiao.w.wang@intel.com> writes:

> We could try to emit compressed insn for reg move operation during CMPXCHG
> JIT, the instruction compression has no impact on the jump offsets of
> following forward and backward jump instructions.

...and at some point we should start supporting Zacas and friends,
instead of lr/sc.

> Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>

Acked-by: Björn Töpel <bjorn@kernel.org>