linux-stable/include/linux/migrate.h
Oscar Salvador 734c15700c mm: only re-generate demotion targets when a numa node changes its N_CPU state
Abhishek reported that after patch [1], hotplug operations are taking
roughly double the expected time.  [2]

The reason behind is that the CPU callbacks that
migrate_on_reclaim_init() sets always call set_migration_target_nodes()
whenever a CPU is brought up/down.

But we only care about numa nodes going from having cpus to become
cpuless, and vice versa, as that influences the demotion_target order.

We do already have two CPU callbacks (vmstat_cpu_online() and
vmstat_cpu_dead()) that check exactly that, so get rid of the CPU
callbacks in migrate_on_reclaim_init() and only call
set_migration_target_nodes() from vmstat_cpu_{dead,online}() whenever a
numa node change its N_CPU state.

[1] https://lore.kernel.org/linux-mm/20210721063926.3024591-2-ying.huang@intel.com/
[2] https://lore.kernel.org/linux-mm/eb438ddd-2919-73d4-bd9f-b7eecdd9577a@linux.vnet.ibm.com/

[osalvador@suse.de: add feedback from Huang Ying]
  Link: https://lkml.kernel.org/r/20220314150945.12694-1-osalvador@suse.de

Link: https://lkml.kernel.org/r/20220310120749.23077-1-osalvador@suse.de
Fixes: 884a6e5d1f ("mm/migrate: update node demotion order on hotplug events")
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Tested-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reported-by: Abhishek Goel <huntbag@linux.vnet.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Abhishek Goel <huntbag@linux.vnet.ibm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-22 15:57:11 -07:00

186 lines
5.7 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_MIGRATE_H
#define _LINUX_MIGRATE_H
#include <linux/mm.h>
#include <linux/mempolicy.h>
#include <linux/migrate_mode.h>
#include <linux/hugetlb.h>
typedef struct page *new_page_t(struct page *page, unsigned long private);
typedef void free_page_t(struct page *page, unsigned long private);
struct migration_target_control;
/*
* Return values from addresss_space_operations.migratepage():
* - negative errno on page migration failure;
* - zero on page migration success;
*/
#define MIGRATEPAGE_SUCCESS 0
/* Defined in mm/debug.c: */
extern const char *migrate_reason_names[MR_TYPES];
#ifdef CONFIG_MIGRATION
extern void putback_movable_pages(struct list_head *l);
extern int migrate_page(struct address_space *mapping,
struct page *newpage, struct page *page,
enum migrate_mode mode);
extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
unsigned long private, enum migrate_mode mode, int reason,
unsigned int *ret_succeeded);
extern struct page *alloc_migration_target(struct page *page, unsigned long private);
extern int isolate_movable_page(struct page *page, isolate_mode_t mode);
extern void migrate_page_states(struct page *newpage, struct page *page);
extern void migrate_page_copy(struct page *newpage, struct page *page);
extern int migrate_huge_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page);
extern int migrate_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page, int extra_count);
void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep,
spinlock_t *ptl);
void folio_migrate_flags(struct folio *newfolio, struct folio *folio);
void folio_migrate_copy(struct folio *newfolio, struct folio *folio);
int folio_migrate_mapping(struct address_space *mapping,
struct folio *newfolio, struct folio *folio, int extra_count);
extern bool numa_demotion_enabled;
extern void migrate_on_reclaim_init(void);
#ifdef CONFIG_HOTPLUG_CPU
extern void set_migration_target_nodes(void);
#else
static inline void set_migration_target_nodes(void) {}
#endif
#else
static inline void set_migration_target_nodes(void) {}
static inline void putback_movable_pages(struct list_head *l) {}
static inline int migrate_pages(struct list_head *l, new_page_t new,
free_page_t free, unsigned long private, enum migrate_mode mode,
int reason, unsigned int *ret_succeeded)
{ return -ENOSYS; }
static inline struct page *alloc_migration_target(struct page *page,
unsigned long private)
{ return NULL; }
static inline int isolate_movable_page(struct page *page, isolate_mode_t mode)
{ return -EBUSY; }
static inline void migrate_page_states(struct page *newpage, struct page *page)
{
}
static inline void migrate_page_copy(struct page *newpage,
struct page *page) {}
static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page)
{
return -ENOSYS;
}
#define numa_demotion_enabled false
#endif /* CONFIG_MIGRATION */
#ifdef CONFIG_COMPACTION
extern int PageMovable(struct page *page);
extern void __SetPageMovable(struct page *page, struct address_space *mapping);
extern void __ClearPageMovable(struct page *page);
#else
static inline int PageMovable(struct page *page) { return 0; }
static inline void __SetPageMovable(struct page *page,
struct address_space *mapping)
{
}
static inline void __ClearPageMovable(struct page *page)
{
}
#endif
#ifdef CONFIG_NUMA_BALANCING
extern int migrate_misplaced_page(struct page *page,
struct vm_area_struct *vma, int node);
#else
static inline int migrate_misplaced_page(struct page *page,
struct vm_area_struct *vma, int node)
{
return -EAGAIN; /* can't migrate now */
}
#endif /* CONFIG_NUMA_BALANCING */
#ifdef CONFIG_MIGRATION
/*
* Watch out for PAE architecture, which has an unsigned long, and might not
* have enough bits to store all physical address and flags. So far we have
* enough room for all our flags.
*/
#define MIGRATE_PFN_VALID (1UL << 0)
#define MIGRATE_PFN_MIGRATE (1UL << 1)
#define MIGRATE_PFN_WRITE (1UL << 3)
#define MIGRATE_PFN_SHIFT 6
static inline struct page *migrate_pfn_to_page(unsigned long mpfn)
{
if (!(mpfn & MIGRATE_PFN_VALID))
return NULL;
return pfn_to_page(mpfn >> MIGRATE_PFN_SHIFT);
}
static inline unsigned long migrate_pfn(unsigned long pfn)
{
return (pfn << MIGRATE_PFN_SHIFT) | MIGRATE_PFN_VALID;
}
enum migrate_vma_direction {
MIGRATE_VMA_SELECT_SYSTEM = 1 << 0,
MIGRATE_VMA_SELECT_DEVICE_PRIVATE = 1 << 1,
};
struct migrate_vma {
struct vm_area_struct *vma;
/*
* Both src and dst array must be big enough for
* (end - start) >> PAGE_SHIFT entries.
*
* The src array must not be modified by the caller after
* migrate_vma_setup(), and must not change the dst array after
* migrate_vma_pages() returns.
*/
unsigned long *dst;
unsigned long *src;
unsigned long cpages;
unsigned long npages;
unsigned long start;
unsigned long end;
/*
* Set to the owner value also stored in page->pgmap->owner for
* migrating out of device private memory. The flags also need to
* be set to MIGRATE_VMA_SELECT_DEVICE_PRIVATE.
* The caller should always set this field when using mmu notifier
* callbacks to avoid device MMU invalidations for device private
* pages that are not being migrated.
*/
void *pgmap_owner;
unsigned long flags;
};
int migrate_vma_setup(struct migrate_vma *args);
void migrate_vma_pages(struct migrate_vma *migrate);
void migrate_vma_finalize(struct migrate_vma *migrate);
int next_demotion_node(int node);
#else /* CONFIG_MIGRATION disabled: */
static inline int next_demotion_node(int node)
{
return NUMA_NO_NODE;
}
#endif /* CONFIG_MIGRATION */
#endif /* _LINUX_MIGRATE_H */