![Lai Jiangshan](/assets/img/avatar_default.png)
Add online_movable and online_kernel for logic memory hotplug. This is the dynamic version of "movablecore" & "kernelcore". We have the same reason to introduce it as to introduce "movablecore" & "kernelcore". It has the same motive as "movablecore" & "kernelcore", but it is dynamic/running-time: o We can configure memory as kernelcore or movablecore after boot. Userspace workload is increased, we need more hugepage, we can't use "online_movable" to add memory and allow the system use more THP(transparent-huge-page), vice-verse when kernel workload is increase. Also help for virtualization to dynamic configure host/guest's memory, to save/(reduce waste) memory. Memory capacity on Demand o When a new node is physically online after boot, we need to use "online_movable" or "online_kernel" to configure/portion it as we expected when we logic-online it. This configuration also helps for physically-memory-migrate. o all benefit as the same as existed "movablecore" & "kernelcore". o Preparing for movable-node, which is very important for power-saving, hardware partitioning and high-available-system(hardware fault management). (Note, we don't introduce movable-node here.) Action behavior: When a memoryblock/memorysection is onlined by "online_movable", the kernel will not have directly reference to the page of the memoryblock, thus we can remove that memory any time when needed. When it is online by "online_kernel", the kernel can use it. When it is online by "online", the zone type doesn't changed. Current constraints: Only the memoryblock which is adjacent to the ZONE_MOVABLE can be online from ZONE_NORMAL to ZONE_MOVABLE. [akpm@linux-foundation.org: use min_t, cleanups] Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Greg KH <greg@kroah.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
258 lines
7.4 KiB
C
258 lines
7.4 KiB
C
#ifndef __LINUX_MEMORY_HOTPLUG_H
|
|
#define __LINUX_MEMORY_HOTPLUG_H
|
|
|
|
#include <linux/mmzone.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/bug.h>
|
|
|
|
struct page;
|
|
struct zone;
|
|
struct pglist_data;
|
|
struct mem_section;
|
|
struct memory_block;
|
|
|
|
#ifdef CONFIG_MEMORY_HOTPLUG
|
|
|
|
/*
|
|
* Types for free bootmem stored in page->lru.next. These have to be in
|
|
* some random range in unsigned long space for debugging purposes.
|
|
*/
|
|
enum {
|
|
MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12,
|
|
SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE,
|
|
MIX_SECTION_INFO,
|
|
NODE_INFO,
|
|
MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
|
|
};
|
|
|
|
/* Types for control the zone type of onlined memory */
|
|
enum {
|
|
ONLINE_KEEP,
|
|
ONLINE_KERNEL,
|
|
ONLINE_MOVABLE,
|
|
};
|
|
|
|
/*
|
|
* pgdat resizing functions
|
|
*/
|
|
static inline
|
|
void pgdat_resize_lock(struct pglist_data *pgdat, unsigned long *flags)
|
|
{
|
|
spin_lock_irqsave(&pgdat->node_size_lock, *flags);
|
|
}
|
|
static inline
|
|
void pgdat_resize_unlock(struct pglist_data *pgdat, unsigned long *flags)
|
|
{
|
|
spin_unlock_irqrestore(&pgdat->node_size_lock, *flags);
|
|
}
|
|
static inline
|
|
void pgdat_resize_init(struct pglist_data *pgdat)
|
|
{
|
|
spin_lock_init(&pgdat->node_size_lock);
|
|
}
|
|
/*
|
|
* Zone resizing functions
|
|
*
|
|
* Note: any attempt to resize a zone should has pgdat_resize_lock()
|
|
* zone_span_writelock() both held. This ensure the size of a zone
|
|
* can't be changed while pgdat_resize_lock() held.
|
|
*/
|
|
static inline unsigned zone_span_seqbegin(struct zone *zone)
|
|
{
|
|
return read_seqbegin(&zone->span_seqlock);
|
|
}
|
|
static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
|
|
{
|
|
return read_seqretry(&zone->span_seqlock, iv);
|
|
}
|
|
static inline void zone_span_writelock(struct zone *zone)
|
|
{
|
|
write_seqlock(&zone->span_seqlock);
|
|
}
|
|
static inline void zone_span_writeunlock(struct zone *zone)
|
|
{
|
|
write_sequnlock(&zone->span_seqlock);
|
|
}
|
|
static inline void zone_seqlock_init(struct zone *zone)
|
|
{
|
|
seqlock_init(&zone->span_seqlock);
|
|
}
|
|
extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
|
|
extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
|
|
extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
|
|
/* VM interface that may be used by firmware interface */
|
|
extern int online_pages(unsigned long, unsigned long, int);
|
|
extern void __offline_isolated_pages(unsigned long, unsigned long);
|
|
|
|
typedef void (*online_page_callback_t)(struct page *page);
|
|
|
|
extern int set_online_page_callback(online_page_callback_t callback);
|
|
extern int restore_online_page_callback(online_page_callback_t callback);
|
|
|
|
extern void __online_page_set_limits(struct page *page);
|
|
extern void __online_page_increment_counters(struct page *page);
|
|
extern void __online_page_free(struct page *page);
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
extern bool is_pageblock_removable_nolock(struct page *page);
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
|
|
/* reasonably generic interface to expand the physical pages in a zone */
|
|
extern int __add_pages(int nid, struct zone *zone, unsigned long start_pfn,
|
|
unsigned long nr_pages);
|
|
extern int __remove_pages(struct zone *zone, unsigned long start_pfn,
|
|
unsigned long nr_pages);
|
|
|
|
#ifdef CONFIG_NUMA
|
|
extern int memory_add_physaddr_to_nid(u64 start);
|
|
#else
|
|
static inline int memory_add_physaddr_to_nid(u64 start)
|
|
{
|
|
return 0;
|
|
}
|
|
#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_SPARSEMEM_VMEMMAP
|
|
static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
|
|
{
|
|
}
|
|
static inline void put_page_bootmem(struct page *page)
|
|
{
|
|
}
|
|
#else
|
|
extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
|
|
extern void put_page_bootmem(struct page *page);
|
|
#endif
|
|
|
|
/*
|
|
* Lock for memory hotplug guarantees 1) all callbacks for memory hotplug
|
|
* notifier will be called under this. 2) offline/online/add/remove memory
|
|
* will not run simultaneously.
|
|
*/
|
|
|
|
void lock_memory_hotplug(void);
|
|
void unlock_memory_hotplug(void);
|
|
|
|
#else /* ! CONFIG_MEMORY_HOTPLUG */
|
|
/*
|
|
* Stub functions for when hotplug is off
|
|
*/
|
|
static inline void pgdat_resize_lock(struct pglist_data *p, unsigned long *f) {}
|
|
static inline void pgdat_resize_unlock(struct pglist_data *p, unsigned long *f) {}
|
|
static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
|
|
|
|
static inline unsigned zone_span_seqbegin(struct zone *zone)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void zone_span_writelock(struct zone *zone) {}
|
|
static inline void zone_span_writeunlock(struct zone *zone) {}
|
|
static inline void zone_seqlock_init(struct zone *zone) {}
|
|
|
|
static inline int mhp_notimplemented(const char *func)
|
|
{
|
|
printk(KERN_WARNING "%s() called, with CONFIG_MEMORY_HOTPLUG disabled\n", func);
|
|
dump_stack();
|
|
return -ENOSYS;
|
|
}
|
|
|
|
static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
|
|
{
|
|
}
|
|
|
|
static inline void lock_memory_hotplug(void) {}
|
|
static inline void unlock_memory_hotplug(void) {}
|
|
|
|
#endif /* ! CONFIG_MEMORY_HOTPLUG */
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
|
|
extern int is_mem_section_removable(unsigned long pfn, unsigned long nr_pages);
|
|
|
|
#else
|
|
static inline int is_mem_section_removable(unsigned long pfn,
|
|
unsigned long nr_pages)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif /* CONFIG_MEMORY_HOTREMOVE */
|
|
|
|
extern int mem_online_node(int nid);
|
|
extern int add_memory(int nid, u64 start, u64 size);
|
|
extern int arch_add_memory(int nid, u64 start, u64 size);
|
|
extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
|
|
extern int offline_memory_block(struct memory_block *mem);
|
|
extern int remove_memory(u64 start, u64 size);
|
|
extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
|
|
int nr_pages);
|
|
extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms);
|
|
extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
|
|
unsigned long pnum);
|
|
|
|
#endif /* __LINUX_MEMORY_HOTPLUG_H */
|