mirror of
https://git.proxmox.com/git/mirror_ubuntu-kernels.git
synced 2025-11-14 18:13:07 +00:00
When the THP NUMA fault support was added THP migration was not supported yet. So the ad hoc THP migration was implemented in NUMA fault handling. Since v4.14 THP migration has been supported so it doesn't make too much sense to still keep another THP migration implementation rather than using the generic migration code. This patch reworks the NUMA fault handling to use generic migration implementation to migrate misplaced page. There is no functional change. After the refactor the flow of NUMA fault handling looks just like its PTE counterpart: Acquire ptl Prepare for migration (elevate page refcount) Release ptl Isolate page from lru and elevate page refcount Migrate the misplaced THP If migration fails just restore the old normal PMD. In the old code anon_vma lock was needed to serialize THP migration against THP split, but since then the THP code has been reworked a lot, it seems anon_vma lock is not required anymore to avoid the race. The page refcount elevation when holding ptl should prevent from THP split. Use migrate_misplaced_page() for both base page and THP NUMA hinting fault and remove all the dead and duplicate code. [dan.carpenter@oracle.com: fix a double unlock bug] Link: https://lkml.kernel.org/r/YLX8uYN01JmfLnlK@mwanda Link: https://lkml.kernel.org/r/20210518200801.7413-4-shy828301@gmail.com Signed-off-by: Yang Shi <shy828301@gmail.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Acked-by: Mel Gorman <mgorman@suse.de> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
178 lines
5.3 KiB
C
178 lines
5.3 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
|
|
|
|
enum migrate_reason {
|
|
MR_COMPACTION,
|
|
MR_MEMORY_FAILURE,
|
|
MR_MEMORY_HOTPLUG,
|
|
MR_SYSCALL, /* also applies to cpusets */
|
|
MR_MEMPOLICY_MBIND,
|
|
MR_NUMA_MISPLACED,
|
|
MR_CONTIG_RANGE,
|
|
MR_LONGTERM_PIN,
|
|
MR_TYPES
|
|
};
|
|
|
|
/* In mm/debug.c; also keep sync with include/trace/events/migrate.h */
|
|
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);
|
|
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);
|
|
extern void copy_huge_page(struct page *dst, struct page *src);
|
|
#else
|
|
|
|
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)
|
|
{ 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;
|
|
}
|
|
|
|
static inline void copy_huge_page(struct page *dst, struct page *src)
|
|
{
|
|
}
|
|
#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_LOCKED (1UL << 2)
|
|
#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);
|
|
|
|
#endif /* CONFIG_MIGRATION */
|
|
|
|
#endif /* _LINUX_MIGRATE_H */
|