lkml.org 
[lkml]   [2013]   [Oct]   [14]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
SubjectRe: [PATCH 1/2] mm: try to detect that page->ptl is in use
From
On Mon, Oct 14, 2013 at 4:45 PM, Kirill A. Shutemov
<kirill.shutemov@linux.intel.com> wrote:
> prep_new_page() initialize page->private (and therefore page->ptl) with
> 0. Make sure nobody took it in use in between allocation of the page and
> page table constructor.
>
> It can happen if arch try to use slab for page table allocation: slab
> code uses page->slab_cache and page->first_page (for tail pages), which
> share storage with page->ptl.
>
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> ---
> Documentation/vm/split_page_table_lock | 4 ++++
> include/linux/mm.h | 9 +++++++++
> 2 files changed, 13 insertions(+)
>
> diff --git a/Documentation/vm/split_page_table_lock b/Documentation/vm/split_page_table_lock
> index e2f617b732..3c54f7dca2 100644
> --- a/Documentation/vm/split_page_table_lock
> +++ b/Documentation/vm/split_page_table_lock
> @@ -53,6 +53,10 @@ There's no need in special enabling of PTE split page table lock:
> everything required is done by pgtable_page_ctor() and pgtable_page_dtor(),
> which must be called on PTE table allocation / freeing.
>
> +Make sure the architecture doesn't use slab allocator for page table
> +allacation: slab uses page->slab_cache and page->first_page for its pages.

Typo: allocation.

> +These fields share storage with page->ptl.
> +
> PMD split lock only makes sense if you have more than two page table
> levels.
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 658e8b317f..9a4a873b2f 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -1262,6 +1262,15 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
>
> static inline bool ptlock_init(struct page *page)
> {
> + /*
> + * prep_new_page() initialize page->private (and therefore page->ptl)
> + * with 0. Make sure nobody took it in use in between.
> + *
> + * It can happen if arch try to use slab for page table allocation:
> + * slab code uses page->slab_cache and page->first_page (for tail
> + * pages), which share storage with page->ptl.
> + */
> + VM_BUG_ON(page->ptl);
> if (!ptlock_alloc(page))
> return false;
> spin_lock_init(ptlock_ptr(page));
> --
> 1.8.4.rc3
>

--
Thanks.
-- Max


\
 
 \ /
  Last update: 2013-10-14 15:21    [W:0.053 / U:2.184 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site