summary refs log tree commit diff
path: root/arch
diff options
context:
space:
mode:
authorLuke Nelson <lukenels@cs.washington.edu>2020-05-05 17:03:18 -0700
committerDaniel Borkmann <daniel@iogearbox.net>2020-05-06 09:48:15 +0200
commit21a099abb765c3754689e1f7ca4536fa560112d0 (patch)
treec6d2bc71c49617d48dd2d01a93821de4d6162349 /arch
parent0224b2acea0f9e3908d33e27b2dcb4e04686e997 (diff)
downloadlinux-21a099abb765c3754689e1f7ca4536fa560112d0.tar.gz
bpf, riscv: Optimize FROM_LE using verifier_zext on RV64
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@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/20200506000320.28965-3-luke.r.nels@gmail.com
Diffstat (limited to 'arch')
-rw-r--r--arch/riscv/net/bpf_jit_comp64.c20
1 files 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);