arm64: irq: set the correct node for VMAP stack

In current code, init_irq_stacks() will call cpu_to_node().
The cpu_to_node() depends on percpu "numa_node" which is initialized in:
     arch_call_rest_init() --> rest_init() -- kernel_init()
	--> kernel_init_freeable() --> smp_prepare_cpus()

But init_irq_stacks() is called in init_IRQ() which is before
arch_call_rest_init().

So in init_irq_stacks(), the cpu_to_node() does not work, it
always return 0. In NUMA, it makes the node 1 cpu accesses the IRQ stack which
is in the node 0.

This patch fixes it by:
  1.) export the early_cpu_to_node(), and use it in the init_irq_stacks().
  2.) change init_irq_stacks() to __init function.

Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Huang Shijie <shijie@os.amperecomputing.com>
Link: https://lore.kernel.org/r/20231124031513.81548-1-shijie@os.amperecomputing.com
Signed-off-by: Will Deacon <will@kernel.org>

Author: HuangShijie2024

arch/arm64/kernel/irq.c

@@ -22,6 +22,7 @@
 #include <linux/vmalloc.h>
 #include <asm/daifflags.h>
 #include <asm/exception.h>
+#include <asm/numa.h>
 #include <asm/softirq_stack.h>
 #include <asm/stacktrace.h>
 #include <asm/vmap_stack.h>
@@ -51,13 +52,13 @@ static void init_irq_scs(void)
 }
 
 #ifdef CONFIG_VMAP_STACK
-static void init_irq_stacks(void)
+static void __init init_irq_stacks(void)
 {
 	int cpu;
 	unsigned long *p;
 
 	for_each_possible_cpu(cpu) {
-		p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, cpu_to_node(cpu));
+		p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, early_cpu_to_node(cpu));
 		per_cpu(irq_stack_ptr, cpu) = p;
 	}
 }

drivers/base/arch_numa.c

@@ -144,7 +144,7 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid)
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(__per_cpu_offset);
 
-static int __init early_cpu_to_node(int cpu)
+int __init early_cpu_to_node(int cpu)
 {
 	return cpu_to_node_map[cpu];
 }

include/asm-generic/numa.h

@@ -35,6 +35,7 @@ int __init numa_add_memblk(int nodeid, u64 start, u64 end);
 void __init numa_set_distance(int from, int to, int distance);
 void __init numa_free_distance(void);
 void __init early_map_cpu_to_node(unsigned int cpu, int nid);
+int __init early_cpu_to_node(int cpu);
 void numa_store_cpu_info(unsigned int cpu);
 void numa_add_cpu(unsigned int cpu);
 void numa_remove_cpu(unsigned int cpu);
@@ -46,6 +47,7 @@ static inline void numa_add_cpu(unsigned int cpu) { }
 static inline void numa_remove_cpu(unsigned int cpu) { }
 static inline void arch_numa_init(void) { }
 static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { }
+static inline int early_cpu_to_node(int cpu) { return 0; }
 
 #endif	/* CONFIG_NUMA */