Unverified Commit 6cea0048 authored by openeuler-ci-bot's avatar openeuler-ci-bot Committed by Gitee
Browse files

!2793 handle uninitialized numa nodes gracefully. 

Merge Pull Request from: @ci-robot 
 
PR sync from: Wupeng Ma <mawupeng1@huawei.com>
https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/QP5QADEIWBBOYYMYKJ6GV2S7USQE5Q6Z/ 
From: Ma Wupeng <mawupeng1@huawei.com>

handle uninitialized numa nodes gracefully.

Michal Hocko (2):
  mm, memory_hotplug: make arch_alloc_nodedata independent on
    CONFIG_MEMORY_HOTPLUG
  mm: handle uninitialized numa nodes gracefully

Oscar Salvador (1):
  arch/x86/mm/numa: Do not initialize nodes twice


-- 
2.25.1
 
https://gitee.com/openeuler/kernel/issues/I8EPOJ 
 
Link:https://gitee.com/openeuler/kernel/pulls/2793

 

Reviewed-by: default avatarKefeng Wang <wangkefeng.wang@huawei.com>
Reviewed-by: default avatarLiu YongQiang <liuyongqiang13@huawei.com>
Signed-off-by: default avatarZhang Changzhong <zhangchangzhong@huawei.com>
parents e102a105 cbce63a0

arch/ia64/mm/discontig.c

+2 −4
Original line number Diff line number Diff line
@@ -631,12 +631,11 @@ void __init paging_init(void) 
	zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));

}



#ifdef CONFIG_MEMORY_HOTPLUG

pg_data_t *arch_alloc_nodedata(int nid)

pg_data_t * __init arch_alloc_nodedata(int nid)

{

	unsigned long size = compute_pernodesize(nid);



	return kzalloc(size, GFP_KERNEL);

	return _va(memblock_alloc(size, SMP_CACHE_BYTES));

}



void arch_free_nodedata(pg_data_t *pgdat)
@@ -649,7 +648,6 @@ void arch_refresh_nodedata(int update_node, pg_data_t *update_pgdat) 
	pgdat_list[update_node] = update_pgdat;

	scatter_node_data();

}

#endif



#ifdef CONFIG_SPARSEMEM_VMEMMAP

int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,

arch/x86/mm/numa.c

+10 −16
Original line number Diff line number Diff line
@@ -722,21 +722,6 @@ void __init x86_numa_init(void) 
	numa_init(dummy_numa_init);

}



static void __init init_memory_less_node(int nid)

{

	unsigned long zones_size[MAX_NR_ZONES] = {0};

	unsigned long zholes_size[MAX_NR_ZONES] = {0};



	/* Allocate and initialize node data. Memory-less node is now online.*/

	alloc_node_data(nid);

	free_area_init_node(nid, zones_size, 0, zholes_size);



	/*

	 * All zonelists will be built later in start_kernel() after per cpu

	 * areas are initialized.

	 */

}



/*

 * Setup early cpu_to_node.

 *
@@ -764,8 +749,17 @@ void __init init_cpu_to_node(void) 
		if (node == NUMA_NO_NODE)

			continue;



		/*

		 * Exclude this node from

		 * bringup_nonboot_cpus

		 *  cpu_up

		 *   __try_online_node

		 *    register_one_node

		 * because node_subsys is not initialized yet.

		 * TODO remove dependency on node_online

		 */

		if (!node_online(node))

			init_memory_less_node(node);

			node_set_online(node);



		numa_set_node(cpu, node);

	}

include/linux/memory_hotplug.h

+60 −60
Original line number Diff line number Diff line
@@ -15,6 +15,66 @@ struct memory_block; 
struct resource;

struct vmem_altmap;



#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION

/*

 * For supporting node-hotadd, we have to allocate a new pgdat.

 *

 * If an arch has generic style NODE_DATA(),

 * node_data[nid] = kzalloc() works well. But it depends on the architecture.

 *

 * In general, generic_alloc_nodedata() is used.

 * Now, arch_free_nodedata() is just defined for error path of node_hot_add.

 *

 */

extern pg_data_t *arch_alloc_nodedata(int nid);

extern void arch_free_nodedata(pg_data_t *pgdat);

extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat);



#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */



#define arch_alloc_nodedata(nid)	generic_alloc_nodedata(nid)

#define arch_free_nodedata(pgdat)	generic_free_nodedata(pgdat)



#ifdef CONFIG_NUMA

/*

 * XXX: node aware allocation can't work well to get new node's memory at this time.

 *	Because, pgdat for the new node is not allocated/initialized yet itself.

 *	To use new node's memory, more consideration will be necessary.

 */

#define generic_alloc_nodedata(nid)				\

({								\

	__va(memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES));	\

})

/*

 * This definition is just for error path in node hotadd.

 * For node hotremove, we have to replace this.

 */

#define generic_free_nodedata(pgdat)	kfree(pgdat)



extern pg_data_t *node_data[];

static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)

{

	node_data[nid] = pgdat;

}



#else /* !CONFIG_NUMA */



/* never called */

static inline pg_data_t *generic_alloc_nodedata(int nid)

{

	BUG();

	return NULL;

}

static inline void generic_free_nodedata(pg_data_t *pgdat)

{

}

static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)

{

}

#endif /* CONFIG_NUMA */

#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */





#ifdef CONFIG_MEMORY_HOTPLUG

/*

 * Return page for the valid pfn only if the page is online. All pfn
@@ -146,66 +206,6 @@ static inline int memory_add_physaddr_to_nid(u64 start) 
}

#endif



#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION

/*

 * For supporting node-hotadd, we have to allocate a new pgdat.

 *

 * If an arch has generic style NODE_DATA(),

 * node_data[nid] = kzalloc() works well. But it depends on the architecture.

 *

 * In general, generic_alloc_nodedata() is used.

 * Now, arch_free_nodedata() is just defined for error path of node_hot_add.

 *

 */

extern pg_data_t *arch_alloc_nodedata(int nid);

extern void arch_free_nodedata(pg_data_t *pgdat);

extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat);



#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */



#define arch_alloc_nodedata(nid)	generic_alloc_nodedata(nid)

#define arch_free_nodedata(pgdat)	generic_free_nodedata(pgdat)



#ifdef CONFIG_NUMA

/*

 * If ARCH_HAS_NODEDATA_EXTENSION=n, this func is used to allocate pgdat.

 * XXX: kmalloc_node() can't work well to get new node's memory at this time.

 *	Because, pgdat for the new node is not allocated/initialized yet itself.

 *	To use new node's memory, more consideration will be necessary.

 */

#define generic_alloc_nodedata(nid)				\

({								\

	kzalloc(sizeof(pg_data_t), GFP_KERNEL);			\

})

/*

 * This definition is just for error path in node hotadd.

 * For node hotremove, we have to replace this.

 */

#define generic_free_nodedata(pgdat)	kfree(pgdat)



extern pg_data_t *node_data[];

static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)

{

	node_data[nid] = pgdat;

}



#else /* !CONFIG_NUMA */



/* never called */

static inline pg_data_t *generic_alloc_nodedata(int nid)

{

	BUG();

	return NULL;

}

static inline void generic_free_nodedata(pg_data_t *pgdat)

{

}

static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)

{

}

#endif /* CONFIG_NUMA */

#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */



#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE

extern void __init register_page_bootmem_info_node(struct pglist_data *pgdat);

#else

mm/internal.h

+2 −0
Original line number Diff line number Diff line
@@ -614,4 +614,6 @@ extern int is_pagecache_reading_kernel_recovery_enable(void); 
extern int is_get_user_kernel_recovery_enable(void);

#endif



DECLARE_PER_CPU(struct per_cpu_nodestat, boot_nodestats);



#endif	/* __MM_INTERNAL_H */

mm/memory_hotplug.c

+10 −14
Original line number Diff line number Diff line
@@ -920,18 +920,20 @@ static void reset_node_present_pages(pg_data_t *pgdat) 
}



/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */

static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)

static pg_data_t __ref *hotadd_init_pgdat(int nid, u64 start)

{

	struct pglist_data *pgdat;

	unsigned long start_pfn = PFN_DOWN(start);



	pgdat = NODE_DATA(nid);

	if (!pgdat) {

		pgdat = arch_alloc_nodedata(nid);

		if (!pgdat)

			return NULL;



		arch_refresh_nodedata(nid, pgdat);

	/*

	 * NODE_DATA is preallocated (free_area_init) but its internal

	 * state is not allocated completely. Add missing pieces.

	 * Completely offline nodes stay around and they just need

	 * reintialization.

	 */

	if (pgdat->per_cpu_nodestats == &boot_nodestats) {

	} else {

		/*

		 * Reset the nr_zones, order and classzone_idx before reuse.
@@ -943,10 +945,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) 
		pgdat->kswapd_classzone_idx = 0;

	}



	/* we can use NODE_DATA(nid) from here */



	pgdat->node_id = nid;

	pgdat->node_start_pfn = start_pfn;

	pgdat->node_start_pfn = 0;



	/* init node's zones as empty zones, we don't have any present pages.*/

	free_area_init_core_hotplug(nid);
@@ -1000,7 +999,7 @@ static int __try_online_node(int nid, u64 start, bool set_node_online) 
	if (node_online(nid))

		return 0;



	pgdat = hotadd_new_pgdat(nid, start);

	pgdat = hotadd_init_pgdat(nid, start);

	if (!pgdat) {

		pr_err("Cannot online node %d due to NULL pgdat\n", nid);

		ret = -ENOMEM;
@@ -1123,9 +1122,6 @@ int __ref add_memory_resource(int nid, struct resource *res) 


	return ret;

error:

	/* rollback pgdat allocation and others */

	if (new_node)

		rollback_node_hotadd(nid);

	memblock_remove(start, size);

	mem_hotplug_done();

	return ret;