linux_dsm_epyc7002/include/linux/memory_hotplug.h
Wang Nan 6326440077 memory-hotplug: add zone_for_memory() for selecting zone for new memory
This series of patches fixes a problem when adding memory in bad manner.
For example: for a x86_64 machine booted with "mem=400M" and with 2GiB
memory installed, following commands cause problem:

  # echo 0x40000000 > /sys/devices/system/memory/probe
 [   28.613895] init_memory_mapping: [mem 0x40000000-0x47ffffff]
  # echo 0x48000000 > /sys/devices/system/memory/probe
 [   28.693675] init_memory_mapping: [mem 0x48000000-0x4fffffff]
  # echo online_movable > /sys/devices/system/memory/memory9/state
  # echo 0x50000000 > /sys/devices/system/memory/probe
 [   29.084090] init_memory_mapping: [mem 0x50000000-0x57ffffff]
  # echo 0x58000000 > /sys/devices/system/memory/probe
 [   29.151880] init_memory_mapping: [mem 0x58000000-0x5fffffff]
  # echo online_movable > /sys/devices/system/memory/memory11/state
  # echo online> /sys/devices/system/memory/memory8/state
  # echo online> /sys/devices/system/memory/memory10/state
  # echo offline> /sys/devices/system/memory/memory9/state
 [   30.558819] Offlined Pages 32768
  # free
              total       used       free     shared    buffers     cached
 Mem:        780588 18014398509432020     830552          0          0      51180
 -/+ buffers/cache: 18014398509380840     881732
 Swap:            0          0          0

This is because the above commands probe higher memory after online a
section with online_movable, which causes ZONE_HIGHMEM (or ZONE_NORMAL
for systems without ZONE_HIGHMEM) overlaps ZONE_MOVABLE.

After the second online_movable, the problem can be observed from
zoneinfo:

  # cat /proc/zoneinfo
  ...
  Node 0, zone  Movable
    pages free     65491
          min      250
          low      312
          high     375
          scanned  0
          spanned  18446744073709518848
          present  65536
          managed  65536
  ...

This series of patches solve the problem by checking ZONE_MOVABLE when
choosing zone for new memory.  If new memory is inside or higher than
ZONE_MOVABLE, makes it go there instead.

After applying this series of patches, following are free and zoneinfo
result (after offlining memory9):

  bash-4.2# free
                total       used       free     shared    buffers     cached
   Mem:        780956      80112     700844          0          0      51180
   -/+ buffers/cache:      28932     752024
   Swap:            0          0          0

  bash-4.2# cat /proc/zoneinfo

  Node 0, zone      DMA
    pages free     3389
          min      14
          low      17
          high     21
          scanned  0
          spanned  4095
          present  3998
          managed  3977
      nr_free_pages 3389
  ...
    start_pfn:         1
    inactive_ratio:    1
  Node 0, zone    DMA32
    pages free     73724
          min      341
          low      426
          high     511
          scanned  0
          spanned  98304
          present  98304
          managed  92958
      nr_free_pages 73724
    ...
    start_pfn:         4096
    inactive_ratio:    1
  Node 0, zone   Normal
    pages free     32630
          min      120
          low      150
          high     180
          scanned  0
          spanned  32768
          present  32768
          managed  32768
      nr_free_pages 32630
  ...
    start_pfn:         262144
    inactive_ratio:    1
  Node 0, zone  Movable
    pages free     65476
          min      241
          low      301
          high     361
          scanned  0
          spanned  98304
          present  65536
          managed  65536
      nr_free_pages 65476
  ...
    start_pfn:         294912
    inactive_ratio:    1

This patch (of 7):

Introduce zone_for_memory() in arch independent code for
arch_add_memory() use.

Many arch_add_memory() function simply selects ZONE_HIGHMEM or
ZONE_NORMAL and add new memory into it.  However, with the existance of
ZONE_MOVABLE, the selection method should be carefully considered: if
new, higher memory is added after ZONE_MOVABLE is setup, the default
zone and ZONE_MOVABLE may overlap each other.

should_add_memory_movable() checks the status of ZONE_MOVABLE.  If it
has already contain memory, compare the address of new memory and
movable memory.  If new memory is higher than movable, it should be
added into ZONE_MOVABLE instead of default zone.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: "Mel Gorman" <mgorman@suse.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-06 18:01:21 -07:00

273 lines
8.0 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 and offlined memory */
enum {
MMOP_OFFLINE = -1,
MMOP_ONLINE_KEEP,
MMOP_ONLINE_KERNEL,
MMOP_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);
extern int try_online_node(int nid);
#ifdef CONFIG_MEMORY_HOTREMOVE
extern bool is_pageblock_removable_nolock(struct page *page);
extern int arch_remove_memory(u64 start, u64 size);
extern int __remove_pages(struct zone *zone, unsigned long start_pfn,
unsigned long nr_pages);
#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);
#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_HAVE_BOOTMEM_INFO_NODE
extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
#else
static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
{
}
#endif
extern void put_page_bootmem(struct page *page);
extern void get_page_bootmem(unsigned long ingo, struct page *page,
unsigned long type);
void get_online_mems(void);
void put_online_mems(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 int try_online_node(int nid)
{
return 0;
}
static inline void get_online_mems(void) {}
static inline void put_online_mems(void) {}
#endif /* ! CONFIG_MEMORY_HOTPLUG */
#ifdef CONFIG_MEMORY_HOTREMOVE
extern int is_mem_section_removable(unsigned long pfn, unsigned long nr_pages);
extern void try_offline_node(int nid);
extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
extern void remove_memory(int nid, u64 start, u64 size);
#else
static inline int is_mem_section_removable(unsigned long pfn,
unsigned long nr_pages)
{
return 0;
}
static inline void try_offline_node(int nid) {}
static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
{
return -EINVAL;
}
static inline void remove_memory(int nid, u64 start, u64 size) {}
#endif /* CONFIG_MEMORY_HOTREMOVE */
extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
void *arg, int (*func)(struct memory_block *, void *));
extern int add_memory(int nid, u64 start, u64 size);
extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default);
extern int arch_add_memory(int nid, u64 start, u64 size);
extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
extern bool is_memblock_offlined(struct memory_block *mem);
extern void remove_memory(int nid, u64 start, u64 size);
extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn);
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 */