Subject: + mm-thp-move-ptl-taking-inside-page_check_address_pmd.patch added to -mm tree
To: kirill.shutemov@xxxxxxxxxxxxxxx,aarcange@xxxxxxxxxx,ak@xxxxxxxxxxxxxxx,athorlton@xxxxxxx,dave.hansen@xxxxxxxxx,davej@xxxxxxxxxx,dhowells@xxxxxxxxxx,ebiederm@xxxxxxxxxxxx,fweisbec@xxxxxxxxx,hannes@xxxxxxxxxxx,hughd@xxxxxxxxxx,keescook@xxxxxxxxxxxx,mgorman@xxxxxxx,mingo@xxxxxxxxxx,mtk.manpages@xxxxxxxxx,n-horiguchi@xxxxxxxxxxxxx,oleg@xxxxxxxxxx,paulmck@xxxxxxxxxxxxxxxxxx,peterz@xxxxxxxxxxxxx,riel@xxxxxxxxxx,robinmholt@xxxxxxxxx,sedat.dilek@xxxxxxxxx,srikar@xxxxxxxxxxxxxxxxxx,tglx@xxxxxxxxxxxxx,viro@xxxxxxxxxxxxxxxxxx
From: akpm@xxxxxxxxxxxxxxxxxxxx
Date: Mon, 07 Oct 2013 16:10:13 -0700
The patch titled
Subject: mm, thp: move ptl taking inside page_check_address_pmd()
has been added to the -mm tree. Its filename is
mm-thp-move-ptl-taking-inside-page_check_address_pmd.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-thp-move-ptl-taking-inside-page_check_address_pmd.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-thp-move-ptl-taking-inside-page_check_address_pmd.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Subject: mm, thp: move ptl taking inside page_check_address_pmd()
With split page table lock we can't know which lock we need to take before
we find the relevant pmd.
Let's move lock taking inside the function.
Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Tested-by: Alex Thorlton <athorlton@xxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "Eric W . Biederman" <ebiederm@xxxxxxxxxxxx>
Cc: "Paul E . McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Dave Jones <davej@xxxxxxxxxx>
Cc: David Howells <dhowells@xxxxxxxxxx>
Cc: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Michael Kerrisk <mtk.manpages@xxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Robin Holt <robinmholt@xxxxxxxxx>
Cc: Sedat Dilek <sedat.dilek@xxxxxxxxx>
Cc: Srikar Dronamraju <srikar@xxxxxxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/huge_mm.h | 3 +-
mm/huge_memory.c | 43 +++++++++++++++++++++++---------------
mm/rmap.c | 13 ++++-------
3 files changed, 34 insertions(+), 25 deletions(-)
diff -puN include/linux/huge_mm.h~mm-thp-move-ptl-taking-inside-page_check_address_pmd include/linux/huge_mm.h
--- a/include/linux/huge_mm.h~mm-thp-move-ptl-taking-inside-page_check_address_pmd
+++ a/include/linux/huge_mm.h
@@ -54,7 +54,8 @@ enum page_check_address_pmd_flag {
extern pmd_t *page_check_address_pmd(struct page *page,
struct mm_struct *mm,
unsigned long address,
- enum page_check_address_pmd_flag flag);
+ enum page_check_address_pmd_flag flag,
+ spinlock_t **ptl);
#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
diff -puN mm/huge_memory.c~mm-thp-move-ptl-taking-inside-page_check_address_pmd mm/huge_memory.c
--- a/mm/huge_memory.c~mm-thp-move-ptl-taking-inside-page_check_address_pmd
+++ a/mm/huge_memory.c
@@ -1493,23 +1493,33 @@ int __pmd_trans_huge_lock(pmd_t *pmd, st
return 0;
}
+/*
+ * This function returns whether a given @page is mapped onto the @address
+ * in the virtual space of @mm.
+ *
+ * When it's true, this function returns *pmd with holding the page table lock
+ * and passing it back to the caller via @ptl.
+ * If it's false, returns NULL without holding the page table lock.
+ */
pmd_t *page_check_address_pmd(struct page *page,
struct mm_struct *mm,
unsigned long address,
- enum page_check_address_pmd_flag flag)
+ enum page_check_address_pmd_flag flag,
+ spinlock_t **ptl)
{
- pmd_t *pmd, *ret = NULL;
+ pmd_t *pmd;
if (address & ~HPAGE_PMD_MASK)
- goto out;
+ return NULL;
pmd = mm_find_pmd(mm, address);
if (!pmd)
- goto out;
+ return NULL;
+ *ptl = pmd_lock(mm, pmd);
if (pmd_none(*pmd))
- goto out;
+ goto unlock;
if (pmd_page(*pmd) != page)
- goto out;
+ goto unlock;
/*
* split_vma() may create temporary aliased mappings. There is
* no risk as long as all huge pmd are found and have their
@@ -1519,14 +1529,15 @@ pmd_t *page_check_address_pmd(struct pag
*/
if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG &&
pmd_trans_splitting(*pmd))
- goto out;
+ goto unlock;
if (pmd_trans_huge(*pmd)) {
VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG &&
!pmd_trans_splitting(*pmd));
- ret = pmd;
+ return pmd;
}
-out:
- return ret;
+unlock:
+ spin_unlock(*ptl);
+ return NULL;
}
static int __split_huge_page_splitting(struct page *page,
@@ -1534,6 +1545,7 @@ static int __split_huge_page_splitting(s
unsigned long address)
{
struct mm_struct *mm = vma->vm_mm;
+ spinlock_t *ptl;
pmd_t *pmd;
int ret = 0;
/* For mmu_notifiers */
@@ -1541,9 +1553,8 @@ static int __split_huge_page_splitting(s
const unsigned long mmun_end = address + HPAGE_PMD_SIZE;
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
- spin_lock(&mm->page_table_lock);
pmd = page_check_address_pmd(page, mm, address,
- PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG);
+ PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG, &ptl);
if (pmd) {
/*
* We can't temporarily set the pmd to null in order
@@ -1554,8 +1565,8 @@ static int __split_huge_page_splitting(s
*/
pmdp_splitting_flush(vma, address, pmd);
ret = 1;
+ spin_unlock(ptl);
}
- spin_unlock(&mm->page_table_lock);
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
return ret;
@@ -1686,14 +1697,14 @@ static int __split_huge_page_map(struct
unsigned long address)
{
struct mm_struct *mm = vma->vm_mm;
+ spinlock_t *ptl;
pmd_t *pmd, _pmd;
int ret = 0, i;
pgtable_t pgtable;
unsigned long haddr;
- spin_lock(&mm->page_table_lock);
pmd = page_check_address_pmd(page, mm, address,
- PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG);
+ PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG, &ptl);
if (pmd) {
pgtable = pgtable_trans_huge_withdraw(mm, pmd);
pmd_populate(mm, &_pmd, pgtable);
@@ -1748,8 +1759,8 @@ static int __split_huge_page_map(struct
pmdp_invalidate(vma, address, pmd);
pmd_populate(mm, pmd, pgtable);
ret = 1;
+ spin_unlock(ptl);
}
- spin_unlock(&mm->page_table_lock);
return ret;
}
diff -puN mm/rmap.c~mm-thp-move-ptl-taking-inside-page_check_address_pmd mm/rmap.c
--- a/mm/rmap.c~mm-thp-move-ptl-taking-inside-page_check_address_pmd
+++ a/mm/rmap.c
@@ -665,25 +665,23 @@ int page_referenced_one(struct page *pag
unsigned long *vm_flags)
{
struct mm_struct *mm = vma->vm_mm;
+ spinlock_t *ptl;
int referenced = 0;
if (unlikely(PageTransHuge(page))) {
pmd_t *pmd;
- spin_lock(&mm->page_table_lock);
/*
* rmap might return false positives; we must filter
* these out using page_check_address_pmd().
*/
pmd = page_check_address_pmd(page, mm, address,
- PAGE_CHECK_ADDRESS_PMD_FLAG);
- if (!pmd) {
- spin_unlock(&mm->page_table_lock);
+ PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl);
+ if (!pmd)
goto out;
- }
if (vma->vm_flags & VM_LOCKED) {
- spin_unlock(&mm->page_table_lock);
+ spin_unlock(ptl);
*mapcount = 0; /* break early from loop */
*vm_flags |= VM_LOCKED;
goto out;
@@ -692,10 +690,9 @@ int page_referenced_one(struct page *pag
/* go ahead even if the pmd is pmd_trans_splitting() */
if (pmdp_clear_flush_young_notify(vma, address, pmd))
referenced++;
- spin_unlock(&mm->page_table_lock);
+ spin_unlock(ptl);
} else {
pte_t *pte;
- spinlock_t *ptl;
/*
* rmap might return false positives; we must filter
_
Patches currently in -mm which might be from kirill.shutemov@xxxxxxxxxxxxxxx are
mm-huge_memoryc-fix-stale-comments-of-transparent_hugepage_flags.patch
mm-thp-cleanup-mv-alloc_hugepage-to-better-place.patch
mm-thp-khugepaged-add-policy-for-finding-target-node.patch
mm-thp-khugepaged-add-policy-for-finding-target-node-fix.patch
mm-avoid-increase-sizeofstruct-page-due-to-split-page-table-lock.patch
mm-rename-use_split_ptlocks-to-use_split_pte_ptlocks.patch
mm-convert-mm-nr_ptes-to-atomic_long_t.patch
mm-introduce-api-for-split-page-table-lock-for-pmd-level.patch
mm-thp-change-pmd_trans_huge_lock-to-return-taken-lock.patch
mm-thp-move-ptl-taking-inside-page_check_address_pmd.patch
mm-thp-do-not-access-mm-pmd_huge_pte-directly.patch
mm-hugetlb-convert-hugetlbfs-to-use-split-pmd-lock.patch
mm-convert-the-rest-to-new-page-table-lock-api.patch
mm-implement-split-page-table-lock-for-pmd-level.patch
x86-mm-enable-split-page-table-lock-for-pmd-level.patch
thp-mm-locking-tail-page-is-a-bug.patch
mm-drop-actor-argument-of-do_generic_file_read.patch
mm-drop-actor-argument-of-do_generic_file_read-fix.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
