diff options
| author | Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> | 2013-06-12 14:05:04 -0700 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2013-06-20 11:28:20 -0700 |
| commit | 79848ba66d91e0c171ff203363e0c96629279c15 (patch) | |
| tree | 6573331e1bfb895058433d0faa8a6bee4d70e552 | |
| parent | 78ef884ebb6c02d45abefc95350f428be7390a26 (diff) | |
mm: migration: add migrate_entry_wait_huge()
commit 30dad30922ccc733cfdbfe232090cf674dc374dc upstream.
When we have a page fault for the address which is backed by a hugepage
under migration, the kernel can't wait correctly and do busy looping on
hugepage fault until the migration finishes. As a result, users who try
to kick hugepage migration (via soft offlining, for example) occasionally
experience long delay or soft lockup.
This is because pte_offset_map_lock() can't get a correct migration entry
or a correct page table lock for hugepage. This patch introduces
migration_entry_wait_huge() to solve this.
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
| -rw-r--r-- | include/linux/swapops.h | 3 | ||||
| -rw-r--r-- | mm/hugetlb.c | 2 | ||||
| -rw-r--r-- | mm/migrate.c | 23 |
3 files changed, 22 insertions, 6 deletions
diff --git a/include/linux/swapops.h b/include/linux/swapops.h index cd42e30b7c6..96c7110986c 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -113,6 +113,7 @@ static inline void make_migration_entry_read(swp_entry_t *entry) extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); +extern void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte); #else #define make_migration_entry(page, write) swp_entry(0, 0) @@ -124,6 +125,8 @@ static inline int is_migration_entry(swp_entry_t swp) static inline void make_migration_entry_read(swp_entry_t *entryp) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } +static inline void migration_entry_wait_huge(struct mm_struct *mm, + pte_t *pte) { } static inline int is_write_migration_entry(swp_entry_t entry) { return 0; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 14420ddbc14..a3498eb134b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2662,7 +2662,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (ptep) { entry = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_migration(entry))) { - migration_entry_wait(mm, (pmd_t *)ptep, address); + migration_entry_wait_huge(mm, ptep); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | diff --git a/mm/migrate.c b/mm/migrate.c index d41b945d53f..3e315a7e4c8 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -184,15 +184,14 @@ static void remove_migration_ptes(struct page *old, struct page *new) * * This function is called from do_swap_page(). */ -void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, - unsigned long address) +static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, + spinlock_t *ptl) { - pte_t *ptep, pte; - spinlock_t *ptl; + pte_t pte; swp_entry_t entry; struct page *page; - ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + spin_lock(ptl); pte = *ptep; if (!is_swap_pte(pte)) goto out; @@ -220,6 +219,20 @@ out: pte_unmap_unlock(ptep, ptl); } +void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, + unsigned long address) +{ + spinlock_t *ptl = pte_lockptr(mm, pmd); + pte_t *ptep = pte_offset_map(pmd, address); + __migration_entry_wait(mm, ptep, ptl); +} + +void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte) +{ + spinlock_t *ptl = &(mm)->page_table_lock; + __migration_entry_wait(mm, pte, ptl); +} + #ifdef CONFIG_BLOCK /* Returns true if all buffers are successfully locked */ static bool buffer_migrate_lock_buffers(struct buffer_head *head, |