Introduce a new migration mode that allow to offload the copy to a device
DMA engine. This changes the workflow of migration and not all
address_space migratepage callback can support this.
This is intended to be use by migrate_vma() which itself is use for thing
like HMM (see include/linux/hmm.h).
No additional per-filesystem migratepage testing is needed. I disables
MIGRATE_SYNC_NO_COPY in all problematic migratepage() callback and i
added comment in those to explain why (part of this patch). The commit
message is unclear it should say that any callback that wish to support
this new mode need to be aware of the difference in the migration flow
from other mode.
Some of these callbacks do extra locking while copying (aio, zsmalloc,
balloon, ...) and for DMA to be effective you want to copy multiple
pages in one DMA operations. But in the problematic case you can not
easily hold the extra lock accross multiple call to this callback.
Usual flow is:
For each page {
1 - lock page
2 - call migratepage() callback
3 - (extra locking in some migratepage() callback)
4 - migrate page state (freeze refcount, update page cache, buffer
head, ...)
5 - copy page
6 - (unlock any extra lock of migratepage() callback)
7 - return from migratepage() callback
8 - unlock page
}
The new mode MIGRATE_SYNC_NO_COPY:
1 - lock multiple pages
For each page {
2 - call migratepage() callback
3 - abort in all problematic migratepage() callback
4 - migrate page state (freeze refcount, update page cache, buffer
head, ...)
} // finished all calls to migratepage() callback
5 - DMA copy multiple pages
6 - unlock all the pages
To support MIGRATE_SYNC_NO_COPY in the problematic case we would need a
new callback migratepages() (for instance) that deals with multiple
pages in one transaction.
Because the problematic cases are not important for current usage I did
not wanted to complexify this patchset even more for no good reason.
Link: http://lkml.kernel.org/r/20170817000548.32038-14-jglisse@redhat.com
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Nellans <dnellans@nvidia.com>
Cc: Evgeny Baskakov <ebaskakov@nvidia.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mark Hairgrove <mhairgrove@nvidia.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Sherry Cheung <SCheung@nvidia.com>
Cc: Subhash Gutti <sgutti@nvidia.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Bob Liu <liubo95@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
159 lines
4.7 KiB
C
159 lines
4.7 KiB
C
#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,
|
|
int **reason);
|
|
typedef void free_page_t(struct page *page, unsigned long private);
|
|
|
|
/*
|
|
* 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_CMA,
|
|
MR_TYPES
|
|
};
|
|
|
|
/* In mm/debug.c; also keep sync with include/trace/events/migrate.h */
|
|
extern char *migrate_reason_names[MR_TYPES];
|
|
|
|
static inline struct page *new_page_nodemask(struct page *page,
|
|
int preferred_nid, nodemask_t *nodemask)
|
|
{
|
|
gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL;
|
|
unsigned int order = 0;
|
|
struct page *new_page = NULL;
|
|
|
|
if (PageHuge(page))
|
|
return alloc_huge_page_nodemask(page_hstate(compound_head(page)),
|
|
preferred_nid, nodemask);
|
|
|
|
if (thp_migration_supported() && PageTransHuge(page)) {
|
|
order = HPAGE_PMD_ORDER;
|
|
gfp_mask |= GFP_TRANSHUGE;
|
|
}
|
|
|
|
if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
|
|
gfp_mask |= __GFP_HIGHMEM;
|
|
|
|
new_page = __alloc_pages_nodemask(gfp_mask, order,
|
|
preferred_nid, nodemask);
|
|
|
|
if (new_page && PageTransHuge(page))
|
|
prep_transhuge_page(new_page);
|
|
|
|
return new_page;
|
|
}
|
|
|
|
#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 int isolate_movable_page(struct page *page, isolate_mode_t mode);
|
|
extern void putback_movable_page(struct page *page);
|
|
|
|
extern int migrate_prep(void);
|
|
extern int migrate_prep_local(void);
|
|
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,
|
|
struct buffer_head *head, enum migrate_mode mode,
|
|
int extra_count);
|
|
#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 int isolate_movable_page(struct page *page, isolate_mode_t mode)
|
|
{ return -EBUSY; }
|
|
|
|
static inline int migrate_prep(void) { return -ENOSYS; }
|
|
static inline int migrate_prep_local(void) { return -ENOSYS; }
|
|
|
|
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;
|
|
}
|
|
|
|
#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 bool pmd_trans_migrating(pmd_t pmd);
|
|
extern int migrate_misplaced_page(struct page *page,
|
|
struct vm_area_struct *vma, int node);
|
|
#else
|
|
static inline bool pmd_trans_migrating(pmd_t pmd)
|
|
{
|
|
return false;
|
|
}
|
|
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 */
|
|
|
|
#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
|
|
extern int migrate_misplaced_transhuge_page(struct mm_struct *mm,
|
|
struct vm_area_struct *vma,
|
|
pmd_t *pmd, pmd_t entry,
|
|
unsigned long address,
|
|
struct page *page, int node);
|
|
#else
|
|
static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm,
|
|
struct vm_area_struct *vma,
|
|
pmd_t *pmd, pmd_t entry,
|
|
unsigned long address,
|
|
struct page *page, int node)
|
|
{
|
|
return -EAGAIN;
|
|
}
|
|
#endif /* CONFIG_NUMA_BALANCING && CONFIG_TRANSPARENT_HUGEPAGE*/
|
|
|
|
#endif /* _LINUX_MIGRATE_H */
|