![Aaron Lu](/assets/img/avatar_default.png)
Prior to 3.15, there was a race between zap_pte_range() and page_mkclean() where writes to a page could be lost. Dave Hansen discovered by inspection that there is a similar race between move_ptes() and page_mkclean(). We've been able to reproduce the issue by enlarging the race window with a msleep(), but have not been able to hit it without modifying the code. So, we think it's a real issue, but is difficult or impossible to hit in practice. The zap_pte_range() issue is fixed by commit 1cf35d47712d("mm: split 'tlb_flush_mmu()' into tlb flushing and memory freeing parts"). And this patch is to fix the race between page_mkclean() and mremap(). Here is one possible way to hit the race: suppose a process mmapped a file with READ | WRITE and SHARED, it has two threads and they are bound to 2 different CPUs, e.g. CPU1 and CPU2. mmap returned X, then thread 1 did a write to addr X so that CPU1 now has a writable TLB for addr X on it. Thread 2 starts mremaping from addr X to Y while thread 1 cleaned the page and then did another write to the old addr X again. The 2nd write from thread 1 could succeed but the value will get lost. thread 1 thread 2 (bound to CPU1) (bound to CPU2) 1: write 1 to addr X to get a writeable TLB on this CPU 2: mremap starts 3: move_ptes emptied PTE for addr X and setup new PTE for addr Y and then dropped PTL for X and Y 4: page laundering for N by doing fadvise FADV_DONTNEED. When done, pageframe N is deemed clean. 5: *write 2 to addr X 6: tlb flush for addr X 7: munmap (Y, pagesize) to make the page unmapped 8: fadvise with FADV_DONTNEED again to kick the page off the pagecache 9: pread the page from file to verify the value. If 1 is there, it means we have lost the written 2. *the write may or may not cause segmentation fault, it depends on if the TLB is still on the CPU. Please note that this is only one specific way of how the race could occur, it didn't mean that the race could only occur in exact the above config, e.g. more than 2 threads could be involved and fadvise() could be done in another thread, etc. For anonymous pages, they could race between mremap() and page reclaim: THP: a huge PMD is moved by mremap to a new huge PMD, then the new huge PMD gets unmapped/splitted/pagedout before the flush tlb happened for the old huge PMD in move_page_tables() and we could still write data to it. The normal anonymous page has similar situation. To fix this, check for any dirty PTE in move_ptes()/move_huge_pmd() and if any, did the flush before dropping the PTL. If we did the flush for every move_ptes()/move_huge_pmd() call then we do not need to do the flush in move_pages_tables() for the whole range. But if we didn't, we still need to do the whole range flush. Alternatively, we can track which part of the range is flushed in move_ptes()/move_huge_pmd() and which didn't to avoid flushing the whole range in move_page_tables(). But that would require multiple tlb flushes for the different sub-ranges and should be less efficient than the single whole range flush. KBuild test on my Sandybridge desktop doesn't show any noticeable change. v4.9-rc4: real 5m14.048s user 32m19.800s sys 4m50.320s With this commit: real 5m13.888s user 32m19.330s sys 4m51.200s Reported-by: Dave Hansen <dave.hansen@intel.com> Signed-off-by: Aaron Lu <aaron.lu@intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
236 lines
7.1 KiB
C
236 lines
7.1 KiB
C
#ifndef _LINUX_HUGE_MM_H
|
|
#define _LINUX_HUGE_MM_H
|
|
|
|
extern int do_huge_pmd_anonymous_page(struct fault_env *fe);
|
|
extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
|
|
pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
|
|
struct vm_area_struct *vma);
|
|
extern void huge_pmd_set_accessed(struct fault_env *fe, pmd_t orig_pmd);
|
|
extern int do_huge_pmd_wp_page(struct fault_env *fe, pmd_t orig_pmd);
|
|
extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
|
|
unsigned long addr,
|
|
pmd_t *pmd,
|
|
unsigned int flags);
|
|
extern bool madvise_free_huge_pmd(struct mmu_gather *tlb,
|
|
struct vm_area_struct *vma,
|
|
pmd_t *pmd, unsigned long addr, unsigned long next);
|
|
extern int zap_huge_pmd(struct mmu_gather *tlb,
|
|
struct vm_area_struct *vma,
|
|
pmd_t *pmd, unsigned long addr);
|
|
extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
|
|
unsigned long addr, unsigned long end,
|
|
unsigned char *vec);
|
|
extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
|
|
unsigned long new_addr, unsigned long old_end,
|
|
pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush);
|
|
extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
|
|
unsigned long addr, pgprot_t newprot,
|
|
int prot_numa);
|
|
int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *,
|
|
pfn_t pfn, bool write);
|
|
enum transparent_hugepage_flag {
|
|
TRANSPARENT_HUGEPAGE_FLAG,
|
|
TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG,
|
|
TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG,
|
|
#ifdef CONFIG_DEBUG_VM
|
|
TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG,
|
|
#endif
|
|
};
|
|
|
|
struct kobject;
|
|
struct kobj_attribute;
|
|
|
|
extern ssize_t single_hugepage_flag_store(struct kobject *kobj,
|
|
struct kobj_attribute *attr,
|
|
const char *buf, size_t count,
|
|
enum transparent_hugepage_flag flag);
|
|
extern ssize_t single_hugepage_flag_show(struct kobject *kobj,
|
|
struct kobj_attribute *attr, char *buf,
|
|
enum transparent_hugepage_flag flag);
|
|
extern struct kobj_attribute shmem_enabled_attr;
|
|
|
|
#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
|
|
#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
|
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
|
|
pmd_t *pmd, int flags);
|
|
|
|
#define HPAGE_PMD_SHIFT PMD_SHIFT
|
|
#define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT)
|
|
#define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1))
|
|
|
|
extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
|
|
|
|
#define transparent_hugepage_enabled(__vma) \
|
|
((transparent_hugepage_flags & \
|
|
(1<<TRANSPARENT_HUGEPAGE_FLAG) || \
|
|
(transparent_hugepage_flags & \
|
|
(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG) && \
|
|
((__vma)->vm_flags & VM_HUGEPAGE))) && \
|
|
!((__vma)->vm_flags & VM_NOHUGEPAGE) && \
|
|
!is_vma_temporary_stack(__vma))
|
|
#define transparent_hugepage_use_zero_page() \
|
|
(transparent_hugepage_flags & \
|
|
(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG))
|
|
#ifdef CONFIG_DEBUG_VM
|
|
#define transparent_hugepage_debug_cow() \
|
|
(transparent_hugepage_flags & \
|
|
(1<<TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG))
|
|
#else /* CONFIG_DEBUG_VM */
|
|
#define transparent_hugepage_debug_cow() 0
|
|
#endif /* CONFIG_DEBUG_VM */
|
|
|
|
extern unsigned long transparent_hugepage_flags;
|
|
|
|
extern unsigned long thp_get_unmapped_area(struct file *filp,
|
|
unsigned long addr, unsigned long len, unsigned long pgoff,
|
|
unsigned long flags);
|
|
|
|
extern void prep_transhuge_page(struct page *page);
|
|
extern void free_transhuge_page(struct page *page);
|
|
|
|
int split_huge_page_to_list(struct page *page, struct list_head *list);
|
|
static inline int split_huge_page(struct page *page)
|
|
{
|
|
return split_huge_page_to_list(page, NULL);
|
|
}
|
|
void deferred_split_huge_page(struct page *page);
|
|
|
|
void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
|
|
unsigned long address, bool freeze, struct page *page);
|
|
|
|
#define split_huge_pmd(__vma, __pmd, __address) \
|
|
do { \
|
|
pmd_t *____pmd = (__pmd); \
|
|
if (pmd_trans_huge(*____pmd) \
|
|
|| pmd_devmap(*____pmd)) \
|
|
__split_huge_pmd(__vma, __pmd, __address, \
|
|
false, NULL); \
|
|
} while (0)
|
|
|
|
|
|
void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
|
|
bool freeze, struct page *page);
|
|
|
|
extern int hugepage_madvise(struct vm_area_struct *vma,
|
|
unsigned long *vm_flags, int advice);
|
|
extern void vma_adjust_trans_huge(struct vm_area_struct *vma,
|
|
unsigned long start,
|
|
unsigned long end,
|
|
long adjust_next);
|
|
extern spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd,
|
|
struct vm_area_struct *vma);
|
|
/* mmap_sem must be held on entry */
|
|
static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
|
|
if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd))
|
|
return __pmd_trans_huge_lock(pmd, vma);
|
|
else
|
|
return NULL;
|
|
}
|
|
static inline int hpage_nr_pages(struct page *page)
|
|
{
|
|
if (unlikely(PageTransHuge(page)))
|
|
return HPAGE_PMD_NR;
|
|
return 1;
|
|
}
|
|
|
|
extern int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t orig_pmd);
|
|
|
|
extern struct page *huge_zero_page;
|
|
|
|
static inline bool is_huge_zero_page(struct page *page)
|
|
{
|
|
return ACCESS_ONCE(huge_zero_page) == page;
|
|
}
|
|
|
|
static inline bool is_huge_zero_pmd(pmd_t pmd)
|
|
{
|
|
return is_huge_zero_page(pmd_page(pmd));
|
|
}
|
|
|
|
struct page *mm_get_huge_zero_page(struct mm_struct *mm);
|
|
void mm_put_huge_zero_page(struct mm_struct *mm);
|
|
|
|
#define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot))
|
|
|
|
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
|
|
#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
|
|
#define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
|
|
#define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; })
|
|
|
|
#define hpage_nr_pages(x) 1
|
|
|
|
#define transparent_hugepage_enabled(__vma) 0
|
|
|
|
static inline void prep_transhuge_page(struct page *page) {}
|
|
|
|
#define transparent_hugepage_flags 0UL
|
|
|
|
#define thp_get_unmapped_area NULL
|
|
|
|
static inline int
|
|
split_huge_page_to_list(struct page *page, struct list_head *list)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int split_huge_page(struct page *page)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void deferred_split_huge_page(struct page *page) {}
|
|
#define split_huge_pmd(__vma, __pmd, __address) \
|
|
do { } while (0)
|
|
|
|
static inline void split_huge_pmd_address(struct vm_area_struct *vma,
|
|
unsigned long address, bool freeze, struct page *page) {}
|
|
|
|
static inline int hugepage_madvise(struct vm_area_struct *vma,
|
|
unsigned long *vm_flags, int advice)
|
|
{
|
|
BUG();
|
|
return 0;
|
|
}
|
|
static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
|
|
unsigned long start,
|
|
unsigned long end,
|
|
long adjust_next)
|
|
{
|
|
}
|
|
static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline int do_huge_pmd_numa_page(struct fault_env *fe, pmd_t orig_pmd)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline bool is_huge_zero_page(struct page *page)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline void mm_put_huge_zero_page(struct mm_struct *mm)
|
|
{
|
|
return;
|
|
}
|
|
|
|
static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma,
|
|
unsigned long addr, pmd_t *pmd, int flags)
|
|
{
|
|
return NULL;
|
|
}
|
|
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
|
|
|
|
#endif /* _LINUX_HUGE_MM_H */
|