linux_dsm_epyc7002/include/linux/memory_hotplug.h
Oscar Salvador 03e85f9d5f mm/page_alloc: Introduce free_area_init_core_hotplug
Currently, whenever a new node is created/re-used from the memhotplug
path, we call free_area_init_node()->free_area_init_core().  But there is
some code that we do not really need to run when we are coming from such
path.

free_area_init_core() performs the following actions:

1) Initializes pgdat internals, such as spinlock, waitqueues and more.
2) Account # nr_all_pages and # nr_kernel_pages. These values are used later on
   when creating hash tables.
3) Account number of managed_pages per zone, substracting dma_reserved and
   memmap pages.
4) Initializes some fields of the zone structure data
5) Calls init_currently_empty_zone to initialize all the freelists
6) Calls memmap_init to initialize all pages belonging to certain zone

When called from memhotplug path, free_area_init_core() only performs
actions #1 and #4.

Action #2 is pointless as the zones do not have any pages since either the
node was freed, or we are re-using it, eitherway all zones belonging to
this node should have 0 pages.  For the same reason, action #3 results
always in manages_pages being 0.

Action #5 and #6 are performed later on when onlining the pages:
 online_pages()->move_pfn_range_to_zone()->init_currently_empty_zone()
 online_pages()->move_pfn_range_to_zone()->memmap_init_zone()

This patch does two things:

First, moves the node/zone initializtion to their own function, so it
allows us to create a small version of free_area_init_core, where we only
perform:

1) Initialization of pgdat internals, such as spinlock, waitqueues and more
4) Initialization of some fields of the zone structure data

These two functions are: pgdat_init_internals() and zone_init_internals().

The second thing this patch does, is to introduce
free_area_init_core_hotplug(), the memhotplug version of
free_area_init_core():

Currently, we call free_area_init_node() from the memhotplug path.  In
there, we set some pgdat's fields, and call calculate_node_totalpages().
calculate_node_totalpages() calculates the # of pages the node has.

Since the node is either new, or we are re-using it, the zones belonging
to this node should not have any pages, so there is no point to calculate
this now.

Actually, we re-set these values to 0 later on with the calls to:

reset_node_managed_pages()
reset_node_present_pages()

The # of pages per node and the # of pages per zone will be calculated when
onlining the pages:

online_pages()->move_pfn_range()->move_pfn_range_to_zone()->resize_zone_range()
online_pages()->move_pfn_range()->move_pfn_range_to_zone()->resize_pgdat_range()

Also, since free_area_init_core/free_area_init_node will now only get called during early init, let us replace
__paginginit with __init, so their code gets freed up.

[osalvador@techadventures.net: fix section usage]
  Link: http://lkml.kernel.org/r/20180731101752.GA473@techadventures.net
[osalvador@suse.de: v6]
  Link: http://lkml.kernel.org/r/20180801122348.21588-6-osalvador@techadventures.net
Link: http://lkml.kernel.org/r/20180730101757.28058-5-osalvador@techadventures.net
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Pasha Tatashin <Pavel.Tatashin@microsoft.com>
Cc: Aaron Lu <aaron.lu@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-22 10:52:45 -07:00

345 lines
10 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#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;
struct resource;
struct vmem_altmap;
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Return page for the valid pfn only if the page is online. All pfn
* walkers which rely on the fully initialized page->flags and others
* should use this rather than pfn_valid && pfn_to_page
*/
#define pfn_to_online_page(pfn) \
({ \
struct page *___page = NULL; \
unsigned long ___nr = pfn_to_section_nr(pfn); \
\
if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\
___page = pfn_to_page(pfn); \
___page; \
})
/*
* 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,
};
/*
* 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 int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
unsigned long *valid_start, unsigned long *valid_end);
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);
extern bool memhp_auto_online;
/* If movable_node boot option specified */
extern bool movable_node_enabled;
static inline bool movable_node_is_enabled(void)
{
return movable_node_enabled;
}
#ifdef CONFIG_MEMORY_HOTREMOVE
extern int arch_remove_memory(u64 start, u64 size,
struct vmem_altmap *altmap);
extern int __remove_pages(struct zone *zone, unsigned long start_pfn,
unsigned long nr_pages, struct vmem_altmap *altmap);
#endif /* CONFIG_MEMORY_HOTREMOVE */
/* reasonably generic interface to expand the physical pages */
extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
struct vmem_altmap *altmap, bool want_memblock);
#ifndef CONFIG_ARCH_HAS_ADD_PAGES
static inline int add_pages(int nid, unsigned long start_pfn,
unsigned long nr_pages, struct vmem_altmap *altmap,
bool want_memblock)
{
return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock);
}
#else /* ARCH_HAS_ADD_PAGES */
int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
struct vmem_altmap *altmap, bool want_memblock);
#endif /* ARCH_HAS_ADD_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 __init 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);
void mem_hotplug_begin(void);
void mem_hotplug_done(void);
extern void set_zone_contiguous(struct zone *zone);
extern void clear_zone_contiguous(struct zone *zone);
#else /* ! CONFIG_MEMORY_HOTPLUG */
#define pfn_to_online_page(pfn) \
({ \
struct page *___page = NULL; \
if (pfn_valid(pfn)) \
___page = pfn_to_page(pfn); \
___page; \
})
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) {}
static inline void mem_hotplug_begin(void) {}
static inline void mem_hotplug_done(void) {}
static inline bool movable_node_is_enabled(void)
{
return false;
}
#endif /* ! CONFIG_MEMORY_HOTPLUG */
#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
/*
* 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);
}
#else /* !(CONFIG_MEMORY_HOTPLUG || CONFIG_DEFERRED_STRUCT_PAGE_INIT) */
/*
* 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) {}
#endif /* !(CONFIG_MEMORY_HOTPLUG || CONFIG_DEFERRED_STRUCT_PAGE_INIT) */
#ifdef CONFIG_MEMORY_HOTREMOVE
extern bool 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 bool is_mem_section_removable(unsigned long pfn,
unsigned long nr_pages)
{
return false;
}
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 void __ref free_area_init_core_hotplug(int nid);
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 add_memory_resource(int nid, struct resource *resource, bool online);
extern int arch_add_memory(int nid, u64 start, u64 size,
struct vmem_altmap *altmap, bool want_memblock);
extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
unsigned long nr_pages, struct vmem_altmap *altmap);
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 pglist_data *pgdat,
unsigned long start_pfn, struct vmem_altmap *altmap);
extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms,
unsigned long map_offset, struct vmem_altmap *altmap);
extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
unsigned long pnum);
extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
int online_type);
extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
unsigned long nr_pages);
#endif /* __LINUX_MEMORY_HOTPLUG_H */