android_kernel_msm-6.1_noth.../include/linux/migrate.h
Mina Almasry 8cc5fcbb5b mm, hugetlb: fix racy resv_huge_pages underflow on UFFDIO_COPY
On UFFDIO_COPY, if we fail to copy the page contents while holding the
hugetlb_fault_mutex, we will drop the mutex and return to the caller after
allocating a page that consumed a reservation.  In this case there may be
a fault that double consumes the reservation.  To handle this, we free the
allocated page, fix the reservations, and allocate a temporary hugetlb
page and return that to the caller.  When the caller does the copy outside
of the lock, we again check the cache, and allocate a page consuming the
reservation, and copy over the contents.

Test:
Hacked the code locally such that resv_huge_pages underflows produce
a warning and the copy_huge_page_from_user() always fails, then:

./tools/testing/selftests/vm/userfaultfd hugetlb_shared 10
        2 /tmp/kokonut_test/huge/userfaultfd_test && echo test success
./tools/testing/selftests/vm/userfaultfd hugetlb 10
	2 /tmp/kokonut_test/huge/userfaultfd_test && echo test success

Both tests succeed and produce no warnings. After the
test runs number of free/resv hugepages is correct.

[yuehaibing@huawei.com: remove set but not used variable 'vm_alloc_shared']
  Link: https://lkml.kernel.org/r/20210601141610.28332-1-yuehaibing@huawei.com
[almasrymina@google.com: fix allocation error check and copy func name]
  Link: https://lkml.kernel.org/r/20210605010626.1459873-1-almasrymina@google.com

Link: https://lkml.kernel.org/r/20210528005029.88088-1-almasrymina@google.com
Signed-off-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-06-30 20:47:26 -07:00

200 lines
5.9 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 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*/
#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 */