The patch titled
Subject: hugetlbfs: remove call to huge_pte_alloc without i_mmap_rwsem
has been added to the -mm tree. Its filename is
hugetlbfs-remove-call-to-huge_pte_alloc-without-i_mmap_rwsem.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/hugetlbfs-remove-call-to-huge_pte_…
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/hugetlbfs-remove-call-to-huge_pte_…
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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Mike Kravetz <mike.kravetz(a)oracle.com>
Subject: hugetlbfs: remove call to huge_pte_alloc without i_mmap_rwsem
Commit c0d0381ade79 ("hugetlbfs: use i_mmap_rwsem for more pmd sharing
synchronization") requires callers of huge_pte_alloc to hold i_mmap_rwsem
in at least read mode. This is because the explicit locking in
huge_pmd_share (called by huge_pte_alloc) was removed. When restructuring
the code, the call to huge_pte_alloc in the else block at the beginning of
hugetlb_fault was missed.
Unfortunately, that else clause is exercised when there is no page table
entry. This will likely lead to a call to huge_pmd_share. If
huge_pmd_share thinks pmd sharing is possible, it will traverse the
mapping tree (i_mmap) without holding i_mmap_rwsem. If someone else is
modifying the tree, bad things such as addressing exceptions or worse
could happen.
Simply remove the else clause. It should have been removed previously.
The code following the else will call huge_pte_alloc with the appropriate
locking.
To prevent this type of issue in the future, add routines to assert that
i_mmap_rwsem is held, and call these routines in huge pmd sharing
routines.
Link: http://lkml.kernel.org/r/e670f327-5cf9-1959-96e4-6dc7cc30d3d5@oracle.com
Fixes: c0d0381ade79 ("hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization")
Signed-off-by: Mike Kravetz <mike.kravetz(a)oracle.com>
Suggested-by: Matthew Wilcox <willy(a)infradead.org>
Cc: Michal Hocko <mhocko(a)kernel.org>
Cc: Hugh Dickins <hughd(a)google.com>
Cc: Naoya Horiguchi <n-horiguchi(a)ah.jp.nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar(a)linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange(a)redhat.com>
Cc: "Kirill A.Shutemov" <kirill.shutemov(a)linux.intel.com>
Cc: Davidlohr Bueso <dave(a)stgolabs.net>
Cc: Prakash Sangappa <prakash.sangappa(a)oracle.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
include/linux/fs.h | 10 ++++++++++
include/linux/hugetlb.h | 8 +++++---
mm/hugetlb.c | 15 +++++++--------
mm/rmap.c | 2 +-
4 files changed, 23 insertions(+), 12 deletions(-)
--- a/include/linux/fs.h~hugetlbfs-remove-call-to-huge_pte_alloc-without-i_mmap_rwsem
+++ a/include/linux/fs.h
@@ -518,6 +518,16 @@ static inline void i_mmap_unlock_read(st
up_read(&mapping->i_mmap_rwsem);
}
+static inline void i_mmap_assert_locked(struct address_space *mapping)
+{
+ lockdep_assert_held(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_assert_write_locked(struct address_space *mapping)
+{
+ lockdep_assert_held_write(&mapping->i_mmap_rwsem);
+}
+
/*
* Might pages of this file be mapped into userspace?
*/
--- a/include/linux/hugetlb.h~hugetlbfs-remove-call-to-huge_pte_alloc-without-i_mmap_rwsem
+++ a/include/linux/hugetlb.h
@@ -164,7 +164,8 @@ pte_t *huge_pte_alloc(struct mm_struct *
unsigned long addr, unsigned long sz);
pte_t *huge_pte_offset(struct mm_struct *mm,
unsigned long addr, unsigned long sz);
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
+int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long *addr, pte_t *ptep);
void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
unsigned long *start, unsigned long *end);
struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
@@ -203,8 +204,9 @@ static inline struct address_space *huge
return NULL;
}
-static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr,
- pte_t *ptep)
+static inline int huge_pmd_unshare(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long *addr, pte_t *ptep)
{
return 0;
}
--- a/mm/hugetlb.c~hugetlbfs-remove-call-to-huge_pte_alloc-without-i_mmap_rwsem
+++ a/mm/hugetlb.c
@@ -3953,7 +3953,7 @@ void __unmap_hugepage_range(struct mmu_g
continue;
ptl = huge_pte_lock(h, mm, ptep);
- if (huge_pmd_unshare(mm, &address, ptep)) {
+ if (huge_pmd_unshare(mm, vma, &address, ptep)) {
spin_unlock(ptl);
/*
* We just unmapped a page of PMDs by clearing a PUD.
@@ -4540,10 +4540,6 @@ vm_fault_t hugetlb_fault(struct mm_struc
} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
return VM_FAULT_HWPOISON_LARGE |
VM_FAULT_SET_HINDEX(hstate_index(h));
- } else {
- ptep = huge_pte_alloc(mm, haddr, huge_page_size(h));
- if (!ptep)
- return VM_FAULT_OOM;
}
/*
@@ -5020,7 +5016,7 @@ unsigned long hugetlb_change_protection(
if (!ptep)
continue;
ptl = huge_pte_lock(h, mm, ptep);
- if (huge_pmd_unshare(mm, &address, ptep)) {
+ if (huge_pmd_unshare(mm, vma, &address, ptep)) {
pages++;
spin_unlock(ptl);
shared_pmd = true;
@@ -5401,12 +5397,14 @@ out:
* returns: 1 successfully unmapped a shared pte page
* 0 the underlying pte page is not shared, or it is the last user
*/
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long *addr, pte_t *ptep)
{
pgd_t *pgd = pgd_offset(mm, *addr);
p4d_t *p4d = p4d_offset(pgd, *addr);
pud_t *pud = pud_offset(p4d, *addr);
+ i_mmap_assert_write_locked(vma->vm_file->f_mapping);
BUG_ON(page_count(virt_to_page(ptep)) == 0);
if (page_count(virt_to_page(ptep)) == 1)
return 0;
@@ -5424,7 +5422,8 @@ pte_t *huge_pmd_share(struct mm_struct *
return NULL;
}
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long *addr, pte_t *ptep)
{
return 0;
}
--- a/mm/rmap.c~hugetlbfs-remove-call-to-huge_pte_alloc-without-i_mmap_rwsem
+++ a/mm/rmap.c
@@ -1469,7 +1469,7 @@ static bool try_to_unmap_one(struct page
* do this outside rmap routines.
*/
VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
- if (huge_pmd_unshare(mm, &address, pvmw.pte)) {
+ if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) {
/*
* huge_pmd_unshare unmapped an entire PMD
* page. There is no way of knowing exactly
_
Patches currently in -mm which might be from mike.kravetz(a)oracle.com are
hugetlbfs-prevent-filesystem-stacking-of-hugetlbfs.patch
hugetlbfs-remove-call-to-huge_pte_alloc-without-i_mmap_rwsem.patch
cma-dont-quit-at-first-error-when-activating-reserved-areas.patch
Commit c0d0381ade79 ("hugetlbfs: use i_mmap_rwsem for more pmd sharing
synchronization") requires callers of huge_pte_alloc to hold i_mmap_rwsem
in at least read mode. This is because the explicit locking in
huge_pmd_share (called by huge_pte_alloc) was removed. When restructuring
the code, the call to huge_pte_alloc in the else block at the beginning
of hugetlb_fault was missed.
Unfortunately, that else clause is exercised when there is no page table
entry. This will likely lead to a call to huge_pmd_share. If
huge_pmd_share thinks pmd sharing is possible, it will traverse the mapping
tree (i_mmap) without holding i_mmap_rwsem. If someone else is modifying
the tree, bad things such as addressing exceptions or worse could happen.
Simply remove the else clause. It should have been removed previously.
The code following the else will call huge_pte_alloc with the appropriate
locking.
Fixes: c0d0381ade79 ("hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization")
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Mike Kravetz <mike.kravetz(a)oracle.com>
---
mm/hugetlb.c | 4 ----
1 file changed, 4 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 590111ea6975..0f6716422a53 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4539,10 +4539,6 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
return VM_FAULT_HWPOISON_LARGE |
VM_FAULT_SET_HINDEX(hstate_index(h));
- } else {
- ptep = huge_pte_alloc(mm, haddr, huge_page_size(h));
- if (!ptep)
- return VM_FAULT_OOM;
}
/*
--
2.25.4
The patch titled
Subject: khugepaged: khugepaged_test_exit() check mmget_still_valid()
has been added to the -mm tree. Its filename is
khugepaged-khugepaged_test_exit-check-mmget_still_valid.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/khugepaged-khugepaged_test_exit-ch…
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/khugepaged-khugepaged_test_exit-ch…
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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Hugh Dickins <hughd(a)google.com>
Subject: khugepaged: khugepaged_test_exit() check mmget_still_valid()
Move collapse_huge_page()'s mmget_still_valid() check into
khugepaged_test_exit() itself. collapse_huge_page() is used for anon THP
only, and earned its mmget_still_valid() check because it inserts a huge
pmd entry in place of the page table's pmd entry; whereas
collapse_file()'s retract_page_tables() or collapse_pte_mapped_thp()
merely clears the page table's pmd entry. But core dumping without mmap
lock must have been as open to mistaking a racily cleared pmd entry for a
page table at physical page 0, as exit_mmap() was. And we certainly have
no interest in mapping as a THP once dumping core.
Link: http://lkml.kernel.org/r/alpine.LSU.2.11.2008021217020.27773@eggly.anvils
Fixes: 59ea6d06cfa9 ("coredump: fix race condition between collapse_huge_page() and core dumping")
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Cc: Andrea Arcangeli <aarcange(a)redhat.com>
Cc: Song Liu <songliubraving(a)fb.com>
Cc: Mike Kravetz <mike.kravetz(a)oracle.com>
Cc: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Cc: <stable(a)vger.kernel.org> [4.8+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/khugepaged.c | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
--- a/mm/khugepaged.c~khugepaged-khugepaged_test_exit-check-mmget_still_valid
+++ a/mm/khugepaged.c
@@ -431,7 +431,7 @@ static void insert_to_mm_slots_hash(stru
static inline int khugepaged_test_exit(struct mm_struct *mm)
{
- return atomic_read(&mm->mm_users) == 0;
+ return atomic_read(&mm->mm_users) == 0 || !mmget_still_valid(mm);
}
static bool hugepage_vma_check(struct vm_area_struct *vma,
@@ -1100,9 +1100,6 @@ static void collapse_huge_page(struct mm
* handled by the anon_vma lock + PG_lock.
*/
mmap_write_lock(mm);
- result = SCAN_ANY_PROCESS;
- if (!mmget_still_valid(mm))
- goto out;
result = hugepage_vma_revalidate(mm, address, &vma);
if (result)
goto out;
_
Patches currently in -mm which might be from hughd(a)google.com are
mm-memcontrol-decouple-reference-counting-from-page-accounting-fix.patch
khugepaged-collapse_pte_mapped_thp-flush-the-right-range.patch
khugepaged-collapse_pte_mapped_thp-protect-the-pmd-lock.patch
khugepaged-retract_page_tables-remember-to-test-exit.patch
khugepaged-khugepaged_test_exit-check-mmget_still_valid.patch
The patch titled
Subject: khugepaged: retract_page_tables() remember to test exit
has been added to the -mm tree. Its filename is
khugepaged-retract_page_tables-remember-to-test-exit.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/khugepaged-retract_page_tables-rem…
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/khugepaged-retract_page_tables-rem…
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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Hugh Dickins <hughd(a)google.com>
Subject: khugepaged: retract_page_tables() remember to test exit
Only once have I seen this scenario (and forgot even to notice what forced
the eventual crash): a sequence of "BUG: Bad page map" alerts from
vm_normal_page(), from zap_pte_range() servicing exit_mmap();
pmd:00000000, pte values corresponding to data in physical page 0.
The pte mappings being zapped in this case were supposed to be from a huge
page of ext4 text (but could as well have been shmem): my belief is that
it was racing with collapse_file()'s retract_page_tables(), found *pmd
pointing to a page table, locked it, but *pmd had become 0 by the time
start_pte was decided.
In most cases, that possibility is excluded by holding mmap lock; but
exit_mmap() proceeds without mmap lock. Most of what's run by khugepaged
checks khugepaged_test_exit() after acquiring mmap lock:
khugepaged_collapse_pte_mapped_thps() and hugepage_vma_revalidate() do so,
for example. But retract_page_tables() did not: fix that.
The fix is for retract_page_tables() to check khugepaged_test_exit(),
after acquiring mmap lock, before doing anything to the page table.
Getting the mmap lock serializes with __mmput(), which briefly takes and
drops it in __khugepaged_exit(); then the khugepaged_test_exit() check on
mm_users makes sure we don't touch the page table once exit_mmap() might
reach it, since exit_mmap() will be proceeding without mmap lock, not
expecting anyone to be racing with it.
Link: http://lkml.kernel.org/r/alpine.LSU.2.11.2008021215400.27773@eggly.anvils
Fixes: f3f0e1d2150b ("khugepaged: add support of collapse for tmpfs/shmem pages")
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Cc: Andrea Arcangeli <aarcange(a)redhat.com>
Cc: Mike Kravetz <mike.kravetz(a)oracle.com>
Cc: Song Liu <songliubraving(a)fb.com>
Cc: <stable(a)vger.kernel.org> [4.8+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/khugepaged.c | 24 ++++++++++++++----------
1 file changed, 14 insertions(+), 10 deletions(-)
--- a/mm/khugepaged.c~khugepaged-retract_page_tables-remember-to-test-exit
+++ a/mm/khugepaged.c
@@ -1532,6 +1532,7 @@ out:
static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff)
{
struct vm_area_struct *vma;
+ struct mm_struct *mm;
unsigned long addr;
pmd_t *pmd, _pmd;
@@ -1560,7 +1561,8 @@ static void retract_page_tables(struct a
continue;
if (vma->vm_end < addr + HPAGE_PMD_SIZE)
continue;
- pmd = mm_find_pmd(vma->vm_mm, addr);
+ mm = vma->vm_mm;
+ pmd = mm_find_pmd(mm, addr);
if (!pmd)
continue;
/*
@@ -1570,17 +1572,19 @@ static void retract_page_tables(struct a
* mmap_lock while holding page lock. Fault path does it in
* reverse order. Trylock is a way to avoid deadlock.
*/
- if (mmap_write_trylock(vma->vm_mm)) {
- spinlock_t *ptl = pmd_lock(vma->vm_mm, pmd);
- /* assume page table is clear */
- _pmd = pmdp_collapse_flush(vma, addr, pmd);
- spin_unlock(ptl);
- mmap_write_unlock(vma->vm_mm);
- mm_dec_nr_ptes(vma->vm_mm);
- pte_free(vma->vm_mm, pmd_pgtable(_pmd));
+ if (mmap_write_trylock(mm)) {
+ if (!khugepaged_test_exit(mm)) {
+ spinlock_t *ptl = pmd_lock(mm, pmd);
+ /* assume page table is clear */
+ _pmd = pmdp_collapse_flush(vma, addr, pmd);
+ spin_unlock(ptl);
+ mm_dec_nr_ptes(mm);
+ pte_free(mm, pmd_pgtable(_pmd));
+ }
+ mmap_write_unlock(mm);
} else {
/* Try again later */
- khugepaged_add_pte_mapped_thp(vma->vm_mm, addr);
+ khugepaged_add_pte_mapped_thp(mm, addr);
}
}
i_mmap_unlock_write(mapping);
_
Patches currently in -mm which might be from hughd(a)google.com are
mm-memcontrol-decouple-reference-counting-from-page-accounting-fix.patch
khugepaged-collapse_pte_mapped_thp-flush-the-right-range.patch
khugepaged-collapse_pte_mapped_thp-protect-the-pmd-lock.patch
khugepaged-retract_page_tables-remember-to-test-exit.patch
khugepaged-khugepaged_test_exit-check-mmget_still_valid.patch
The patch titled
Subject: khugepaged: collapse_pte_mapped_thp() protect the pmd lock
has been added to the -mm tree. Its filename is
khugepaged-collapse_pte_mapped_thp-protect-the-pmd-lock.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/khugepaged-collapse_pte_mapped_thp…
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/khugepaged-collapse_pte_mapped_thp…
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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Hugh Dickins <hughd(a)google.com>
Subject: khugepaged: collapse_pte_mapped_thp() protect the pmd lock
When retract_page_tables() removes a page table to make way for a huge
pmd, it holds huge page lock, i_mmap_lock_write, mmap_write_trylock and
pmd lock; but when collapse_pte_mapped_thp() does the same (to handle the
case when the original mmap_write_trylock had failed), only
mmap_write_trylock and pmd lock are held.
That's not enough. One machine has twice crashed under load, with "BUG:
spinlock bad magic" and GPF on 6b6b6b6b6b6b6b6b. Examining the second
crash, page_vma_mapped_walk_done()'s spin_unlock of pvmw->ptl (serving
page_referenced() on a file THP, that had found a page table at *pmd)
discovers that the page table page and its lock have already been freed by
the time it comes to unlock.
Follow the example of retract_page_tables(), but we only need one of huge
page lock or i_mmap_lock_write to secure against this: because it's the
narrower lock, and because it simplifies collapse_pte_mapped_thp() to know
the hpage earlier, choose to rely on huge page lock here.
Link: http://lkml.kernel.org/r/alpine.LSU.2.11.2008021213070.27773@eggly.anvils
Fixes: 27e1f8273113 ("khugepaged: enable collapse pmd for pte-mapped THP")
Signed-off-by: Hugh Dickins <hughd(a)google.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com>
Cc: Andrea Arcangeli <aarcange(a)redhat.com>
Cc: Mike Kravetz <mike.kravetz(a)oracle.com>
Cc: Song Liu <songliubraving(a)fb.com>
Cc: <stable(a)vger.kernel.org> [5.4+]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/khugepaged.c | 44 +++++++++++++++++++-------------------------
1 file changed, 19 insertions(+), 25 deletions(-)
--- a/mm/khugepaged.c~khugepaged-collapse_pte_mapped_thp-protect-the-pmd-lock
+++ a/mm/khugepaged.c
@@ -1412,7 +1412,7 @@ void collapse_pte_mapped_thp(struct mm_s
{
unsigned long haddr = addr & HPAGE_PMD_MASK;
struct vm_area_struct *vma = find_vma(mm, haddr);
- struct page *hpage = NULL;
+ struct page *hpage;
pte_t *start_pte, *pte;
pmd_t *pmd, _pmd;
spinlock_t *ptl;
@@ -1432,9 +1432,17 @@ void collapse_pte_mapped_thp(struct mm_s
if (!hugepage_vma_check(vma, vma->vm_flags | VM_HUGEPAGE))
return;
+ hpage = find_lock_page(vma->vm_file->f_mapping,
+ linear_page_index(vma, haddr));
+ if (!hpage)
+ return;
+
+ if (!PageHead(hpage))
+ goto drop_hpage;
+
pmd = mm_find_pmd(mm, haddr);
if (!pmd)
- return;
+ goto drop_hpage;
start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl);
@@ -1453,30 +1461,11 @@ void collapse_pte_mapped_thp(struct mm_s
page = vm_normal_page(vma, addr, *pte);
- if (!page || !PageCompound(page))
- goto abort;
-
- if (!hpage) {
- hpage = compound_head(page);
- /*
- * The mapping of the THP should not change.
- *
- * Note that uprobe, debugger, or MAP_PRIVATE may
- * change the page table, but the new page will
- * not pass PageCompound() check.
- */
- if (WARN_ON(hpage->mapping != vma->vm_file->f_mapping))
- goto abort;
- }
-
/*
- * Confirm the page maps to the correct subpage.
- *
- * Note that uprobe, debugger, or MAP_PRIVATE may change
- * the page table, but the new page will not pass
- * PageCompound() check.
+ * Note that uprobe, debugger, or MAP_PRIVATE may change the
+ * page table, but the new page will not be a subpage of hpage.
*/
- if (WARN_ON(hpage + i != page))
+ if (hpage + i != page)
goto abort;
count++;
}
@@ -1495,7 +1484,7 @@ void collapse_pte_mapped_thp(struct mm_s
pte_unmap_unlock(start_pte, ptl);
/* step 3: set proper refcount and mm_counters. */
- if (hpage) {
+ if (count) {
page_ref_sub(hpage, count);
add_mm_counter(vma->vm_mm, mm_counter_file(hpage), -count);
}
@@ -1506,10 +1495,15 @@ void collapse_pte_mapped_thp(struct mm_s
spin_unlock(ptl);
mm_dec_nr_ptes(mm);
pte_free(mm, pmd_pgtable(_pmd));
+
+drop_hpage:
+ unlock_page(hpage);
+ put_page(hpage);
return;
abort:
pte_unmap_unlock(start_pte, ptl);
+ goto drop_hpage;
}
static int khugepaged_collapse_pte_mapped_thps(struct mm_slot *mm_slot)
_
Patches currently in -mm which might be from hughd(a)google.com are
mm-memcontrol-decouple-reference-counting-from-page-accounting-fix.patch
khugepaged-collapse_pte_mapped_thp-flush-the-right-range.patch
khugepaged-collapse_pte_mapped_thp-protect-the-pmd-lock.patch
khugepaged-retract_page_tables-remember-to-test-exit.patch
khugepaged-khugepaged_test_exit-check-mmget_still_valid.patch