powerpc/bpf/32: perform three operands ALU operations

When an ALU instruction is preceded by a MOV instruction
that just moves a source register into the destination register of
the ALU, replace that MOV+ALU instructions by an ALU operation
taking the source of the MOV as second source instead of using its
destination.

Before the change, code could look like the following, with
superfluous separate register move (mr) instructions.

  70:	7f c6 f3 78 	mr      r6,r30
  74:	7f a5 eb 78 	mr      r5,r29
  78:	30 c6 ff f4 	addic   r6,r6,-12
  7c:	7c a5 01 d4 	addme   r5,r5

With this commit, addition instructions take r30 and r29 directly.

  70:	30 de ff f4 	addic   r6,r30,-12
  74:	7c bd 01 d4 	addme   r5,r29
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/b6719beaf01f9dcbcdbb787ef67c4a2f8e3a4cb6.1675245773.git.christophe.leroy@csgroup.eu

arch/powerpc/net/bpf_jit_comp32.c

@@ -290,6 +290,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 
 	for (i = 0; i < flen; i++) {
 		u32 code = insn[i].code;
+		u32 prevcode = i ? insn[i - 1].code : 0;
 		u32 dst_reg = bpf_to_ppc(insn[i].dst_reg);
 		u32 dst_reg_h = dst_reg - 1;
 		u32 src_reg = bpf_to_ppc(insn[i].src_reg);
@@ -308,6 +309,15 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
 		u32 tmp_idx;
 		int j;
 
+		if (i && (BPF_CLASS(code) == BPF_ALU64 || BPF_CLASS(code) == BPF_ALU) &&
+		    (BPF_CLASS(prevcode) == BPF_ALU64 || BPF_CLASS(prevcode) == BPF_ALU) &&
+		    BPF_OP(prevcode) == BPF_MOV && BPF_SRC(prevcode) == BPF_X &&
+		    insn[i - 1].dst_reg == insn[i].dst_reg && insn[i - 1].imm != 1) {
+			src2_reg = bpf_to_ppc(insn[i - 1].src_reg);
+			src2_reg_h = src2_reg - 1;
+			ctx->idx = addrs[i - 1] / 4;
+		}
+
 		/*
 		 * addrs[] maps a BPF bytecode address into a real offset from
 		 * the start of the body code.