nfp: bpf: optimize codegen for JSET with a constant

The top word of the constant can only have bits set if sign
extension set it to all-1, therefore we don't really have to
mask the top half of the register.  We can just OR it into
the result as is.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

1 files changed, 10 insertions, 12 deletions

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index f765e76e4924..e23ca90289f7 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -3052,21 +3052,19 @@ static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
 	u64 imm = insn->imm; /* sign extend */
+	u8 dst_gpr = insn->dst_reg * 2;
 	swreg tmp_reg;
 
-	if (imm & ~0U) {
-		tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
-		emit_alu(nfp_prog, reg_none(),
-			 reg_a(insn->dst_reg * 2), ALU_OP_AND, tmp_reg);
-		emit_br(nfp_prog, BR_BNE, insn->off, 0);
-	}
-
-	if (imm >> 32) {
-		tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
+	tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
+	emit_alu(nfp_prog, imm_b(nfp_prog),
+		 reg_a(dst_gpr), ALU_OP_AND, tmp_reg);
+	/* Upper word of the mask can only be 0 or ~0 from sign extension,
+	 * so either ignore it or OR the whole thing in.
+	 */
+	if (imm >> 32)
 		emit_alu(nfp_prog, reg_none(),
-			 reg_a(insn->dst_reg * 2 + 1), ALU_OP_AND, tmp_reg);
-		emit_br(nfp_prog, BR_BNE, insn->off, 0);
-	}
+			 reg_a(dst_gpr + 1), ALU_OP_OR, imm_b(nfp_prog));
+	emit_br(nfp_prog, BR_BNE, insn->off, 0);
 
 	return 0;
 }