[ 3.5.y.z extended stable ] Patch "mm: migration: add migrate_entry_wait_huge()" has been added to staging queue

[Luis Henriques]

This is a note to let you know that I have just added a patch titled

    mm: migration: add migrate_entry_wait_huge()

to the linux-3.5.y-queue branch of the 3.5.y.z extended stable tree 
which can be found at:

 http://kernel.ubuntu.com/git?p=ubuntu/linux.git;a=shortlog;h=refs/heads/linux-3.5.y-queue

If you, or anyone else, feels it should not be added to this tree, please 
reply to this email.

For more information about the 3.5.y.z tree, see
https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable

Thanks.
-Luis

------

>From e27c302dc446eeaa11942e83b2e087538e0ee2eb Mon Sep 17 00:00:00 2001
From: Naoya Horiguchi <n-horiguchi at ah.jp.nec.com>
Date: Wed, 12 Jun 2013 14:05:04 -0700
Subject: [PATCH] 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 at ah.jp.nec.com>
Reviewed-by: Rik van Riel <riel at redhat.com>
Reviewed-by: Wanpeng Li <liwanp at linux.vnet.ibm.com>
Reviewed-by: Michal Hocko <mhocko at suse.cz>
Cc: Mel Gorman <mgorman at suse.de>
Cc: Andi Kleen <andi at firstfloor.org>
Cc: KOSAKI Motohiro <kosaki.motohiro at jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques at canonical.com>
---
 include/linux/swapops.h |  3 +++
 mm/hugetlb.c            |  2 +-
 mm/migrate.c            | 23 ++++++++++++++++++-----
 3 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 47ead51..c5fd30d 100644
--- 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 74b8327..c6557ef 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2769,7 +2769,7 @@ 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 65cc229..41e906a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -182,15 +182,14 @@ 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;
@@ -218,6 +217,20 @@ 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,
--
1.8.1.2