LoongArch/smp: Call rcutree_report_cpu_starting() at tlb_init()

Machines which have more than 8 nodes fail to boot SMP after commit
a2ccf463 ("LoongArch/smp: Call rcutree_report_cpu_starting()
earlier"). Because such machines use tlb-based per-cpu base address
rather than dmw-based per-cpu base address, resulting per-cpu variables
can only be accessed after tlb_init(). But rcutree_report_cpu_starting()
is now called before tlb_init() and accesses per-cpu variables indeed.

Since the original patch want to avoid the lockdep warning caused by
page allocation in tlb_init(), we can move rcutree_report_cpu_starting()
to tlb_init() where after tlb exception configuration but before page
allocation.

Fixes: a2ccf463 ("LoongArch/smp: Call rcutree_report_cpu_starting() earlier")
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

arch/loongarch/kernel/smp.c

@@ -509,7 +509,6 @@ asmlinkage void start_secondary(void)
 	sync_counter();
 	cpu = raw_smp_processor_id();
 	set_my_cpu_offset(per_cpu_offset(cpu));
-	rcutree_report_cpu_starting(cpu);
 
 	cpu_probe();
 	constant_clockevent_init();

arch/loongarch/mm/tlb.c

@@ -284,12 +284,16 @@ static void setup_tlb_handler(int cpu)
 		set_handler(EXCCODE_TLBNR * VECSIZE, handle_tlb_protect, VECSIZE);
 		set_handler(EXCCODE_TLBNX * VECSIZE, handle_tlb_protect, VECSIZE);
 		set_handler(EXCCODE_TLBPE * VECSIZE, handle_tlb_protect, VECSIZE);
-	}
+	} else {
+		int vec_sz __maybe_unused;
+		void *addr __maybe_unused;
+		struct page *page __maybe_unused;
+
+		/* Avoid lockdep warning */
+		rcutree_report_cpu_starting(cpu);
+
 #ifdef CONFIG_NUMA
-	else {
-		void *addr;
-		struct page *page;
-		const int vec_sz = sizeof(exception_handlers);
+		vec_sz = sizeof(exception_handlers);
 
 		if (pcpu_handlers[cpu])
 			return;
@@ -305,8 +309,8 @@ static void setup_tlb_handler(int cpu)
 		csr_write64(pcpu_handlers[cpu], LOONGARCH_CSR_EENTRY);
 		csr_write64(pcpu_handlers[cpu], LOONGARCH_CSR_MERRENTRY);
 		csr_write64(pcpu_handlers[cpu] + 80*VECSIZE, LOONGARCH_CSR_TLBRENTRY);
-	}
 #endif
+	}
 }
 
 void tlb_init(int cpu)