From: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Subject: 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@xxxxxxxxxxxxx>
Reviewed-by: Rik van Riel <riel@xxxxxxxxxx>
Reviewed-by: Wanpeng Li <liwanp@xxxxxxxxxxxxxxxxxx>
Reviewed-by: Michal Hocko <mhocko@xxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Andi Kleen <andi@xxxxxxxxxxxxxx>
Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> [2.6.35+]
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/swapops.h | 3 +++
mm/hugetlb.c | 2 +-
mm/migrate.c | 23 ++++++++++++++++++-----
3 files changed, 22 insertions(+), 6 deletions(-)
diff -puN include/linux/swapops.h~mm-migration-add-migrate_entry_wait_huge include/linux/swapops.h
--- a/include/linux/swapops.h~mm-migration-add-migrate_entry_wait_huge
+++ a/include/linux/swapops.h
@@ -137,6 +137,7 @@ static inline void make_migration_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
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 -puN mm/hugetlb.c~mm-migration-add-migrate_entry_wait_huge mm/hugetlb.c
--- a/mm/hugetlb.c~mm-migration-add-migrate_entry_wait_huge
+++ a/mm/hugetlb.c
@@ -2839,7 +2839,7 @@ int hugetlb_fault(struct mm_struct *mm,
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 -puN mm/migrate.c~mm-migration-add-migrate_entry_wait_huge mm/migrate.c
--- a/mm/migrate.c~mm-migration-add-migrate_entry_wait_huge
+++ a/mm/migrate.c
@@ -200,15 +200,14 @@ static void remove_migration_ptes(struct
* 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,
_
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html