mm: migration: add migrate_entry_wait_huge()

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>
Cc: <stable@vger.kernel.org>	[2.6.35+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 47ead515c81197fc897bc7ef37fead3d9ab4b39f..c5fd30d2a415a48964eb1fb2aaaac0db255656e1 100644 (file)
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -137,6 +137,7 @@ 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)
@@ -148,6 +149,8 @@ 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 f8feeeca6686543713a1dada46759b60b2eae240..e2bfbf73a551d0747fbea1b69200dd773e36754e 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2839,7 +2839,7 @@ 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 b1f57501de9c8f4f0705b30fef748c4c3f145e86..6f0c24438bbaaf6ffdaa4f840ab8da37cf9e236a 100644 (file)
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -200,15 +200,14 @@ static void remove_migration_ptes(struct page *old, struct page *new)
  * get to the page and wait until migration is finished.
  * When we return from this function the fault will be retried.
  */
-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;
@@ -236,6 +235,20 @@ 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,