bpf, arm64: save 4 bytes in prologue when ebpf insns came from cbpf

We can trivially save 4 bytes in prologue for cBPF since tail calls
can never be used from there. The register push/pop is pairwise,
here, x25 (fp) and x26 (tcc), so no point in changing that, only
reset to zero is not needed.

Signed-off-by: Daniel Borkmann <[e-mail]>
Signed-off-by: Alexei Starovoitov <[e-mail]>

arch/arm64/net/bpf_jit_comp.c

···
 /* Tail call offset to jump into */
 #define PROLOGUE_OFFSET 7
 
-static int build_prologue(struct jit_ctx *ctx)
+static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
 {
 	const struct bpf_prog *prog = ctx->prog;
 	const u8 r6 = bpf2a64[BPF_REG_6];
···
 	/* Set up BPF prog stack base register */
 	emit(A64_MOV(1, fp, A64_SP), ctx);
 
-	/* Initialize tail_call_cnt */
-	emit(A64_MOVZ(1, tcc, 0, 0), ctx);
+	if (!ebpf_from_cbpf) {
+		/* Initialize tail_call_cnt */
+		emit(A64_MOVZ(1, tcc, 0, 0), ctx);
 
-	cur_offset = ctx->idx - idx0;
-	if (cur_offset != PROLOGUE_OFFSET) {
-		pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
-			    cur_offset, PROLOGUE_OFFSET);
-		return -1;
+		cur_offset = ctx->idx - idx0;
+		if (cur_offset != PROLOGUE_OFFSET) {
+			pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
+				    cur_offset, PROLOGUE_OFFSET);
+			return -1;
+		}
 	}
 
 	ctx->stack_size = STACK_ALIGN(prog->aux->stack_depth);
···
 	struct bpf_prog *tmp, *orig_prog = prog;
 	struct bpf_binary_header *header;
 	struct arm64_jit_data *jit_data;
+	bool was_classic = bpf_prog_was_classic(prog);
 	bool tmp_blinded = false;
 	bool extra_pass = false;
 	struct jit_ctx ctx;
···
 		goto out_off;
 	}
 
-	if (build_prologue(&ctx)) {
+	if (build_prologue(&ctx, was_classic)) {
 		prog = orig_prog;
 		goto out_off;
 	}
···
 skip_init_ctx:
 	ctx.idx = 0;
 
-	build_prologue(&ctx);
+	build_prologue(&ctx, was_classic);
 
 	if (build_body(&ctx)) {
 		bpf_jit_binary_free(header);