bpf, arm64: Fix incorrect runtime stats

When __bpf_prog_enter() returns zero, the arm64 register x20 that stores
prog start time is not assigned to zero, causing incorrect runtime stats.

To fix it, assign the return value of bpf_prog_enter() to x20 register
immediately upon its return.

Fixes: efc9909 ("bpf, arm64: Add bpf trampoline for arm64")
Reported-by: Ivan Babrou <[email protected]>
Signed-off-by: Xu Kuohai <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Tested-by: Ivan Babrou <[email protected]>
Acked-by: Daniel Borkmann <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]

Author: Xu Kuohai

arch/arm64/net/bpf_jit_comp.c

@@ -1844,15 +1844,15 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
 
 	emit_call(enter_prog, ctx);
 
+	/* save return value to callee saved register x20 */
+	emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx);
+
 	/* if (__bpf_prog_enter(prog) == 0)
 	 *         goto skip_exec_of_prog;
 	 */
 	branch = ctx->image + ctx->idx;
 	emit(A64_NOP, ctx);
 
-	/* save return value to callee saved register x20 */
-	emit(A64_MOV(1, A64_R(20), A64_R(0)), ctx);
-
 	emit(A64_ADD_I(1, A64_R(0), A64_SP, args_off), ctx);
 	if (!p->jited)
 		emit_addr_mov_i64(A64_R(1), (const u64)p->insnsi, ctx);