On Thu, Apr 20, 2017 at 10:45:42AM +0900, Sergey Senozhatsky wrote:
> On (04/19/17 04:51), Matthew Wilcox wrote:
> [..]
> > > > > Another approach is the API does normal thing for non-aligned prefix
> > > > > and
> > > > > tail space and fast thing for aligned space.
> > > > > Otherwise, it would
On Thu, Apr 20, 2017 at 10:45:42AM +0900, Sergey Senozhatsky wrote:
> On (04/19/17 04:51), Matthew Wilcox wrote:
> [..]
> > > > > Another approach is the API does normal thing for non-aligned prefix
> > > > > and
> > > > > tail space and fast thing for aligned space.
> > > > > Otherwise, it would
On (04/19/17 04:51), Matthew Wilcox wrote:
[..]
> > > > Another approach is the API does normal thing for non-aligned prefix and
> > > > tail space and fast thing for aligned space.
> > > > Otherwise, it would be happy if the API has WARN_ON non-page SIZE
> > > > aligned
> > > > address.
>
> Why
On (04/19/17 04:51), Matthew Wilcox wrote:
[..]
> > > > Another approach is the API does normal thing for non-aligned prefix and
> > > > tail space and fast thing for aligned space.
> > > > Otherwise, it would be happy if the API has WARN_ON non-page SIZE
> > > > aligned
> > > > address.
>
> Why
On Wed, Apr 19, 2017 at 03:02:37PM +0900, Minchan Kim wrote:
> On Tue, Apr 18, 2017 at 09:33:07AM +0200, Michal Hocko wrote:
> > I do not follow. Why would you need kmap for something that is already
> > in the kernel space?
>
> Because it can work with highmem pages.
That's
On Wed, Apr 19, 2017 at 03:02:37PM +0900, Minchan Kim wrote:
> On Tue, Apr 18, 2017 at 09:33:07AM +0200, Michal Hocko wrote:
> > I do not follow. Why would you need kmap for something that is already
> > in the kernel space?
>
> Because it can work with highmem pages.
That's
On (04/18/17 13:06), Michal Hocko wrote:
[..]
> > > copy_page is a performance sensitive function and I believe that we do
> > > those tricks exactly for this purpose.
> >
> > a wild thought,
> >
> > use
> > #define copy_page(to,from) memcpy((to), (from), PAGE_SIZE)
> >
> > when
On (04/18/17 13:06), Michal Hocko wrote:
[..]
> > > copy_page is a performance sensitive function and I believe that we do
> > > those tricks exactly for this purpose.
> >
> > a wild thought,
> >
> > use
> > #define copy_page(to,from) memcpy((to), (from), PAGE_SIZE)
> >
> > when
Hello Michal,
On Tue, Apr 18, 2017 at 09:33:07AM +0200, Michal Hocko wrote:
> On Tue 18-04-17 09:03:19, Minchan Kim wrote:
> > On Mon, Apr 17, 2017 at 10:20:42AM -0500, Christoph Lameter wrote:
> > > On Mon, 17 Apr 2017, Sergey Senozhatsky wrote:
> > >
> > > > Minchan reported that doing
Hello Michal,
On Tue, Apr 18, 2017 at 09:33:07AM +0200, Michal Hocko wrote:
> On Tue 18-04-17 09:03:19, Minchan Kim wrote:
> > On Mon, Apr 17, 2017 at 10:20:42AM -0500, Christoph Lameter wrote:
> > > On Mon, 17 Apr 2017, Sergey Senozhatsky wrote:
> > >
> > > > Minchan reported that doing
On Tue, 18 Apr 2017, Sergey Senozhatsky wrote:
> > Simple solution is to not allocate pages via the slab allocator but use
> > the page allocator for this. The page allocator provides proper alignment.
>
> sure, but at the same time it's not completely uncommon and unseen thing
>
> ~/_next$ git
On Tue, 18 Apr 2017, Sergey Senozhatsky wrote:
> > Simple solution is to not allocate pages via the slab allocator but use
> > the page allocator for this. The page allocator provides proper alignment.
>
> sure, but at the same time it's not completely uncommon and unseen thing
>
> ~/_next$ git
On Mon, Apr 17, 2017 at 10:20:42AM -0500, Christoph Lameter wrote:
> Simple solution is to not allocate pages via the slab allocator but use
> the page allocator for this. The page allocator provides proper alignment.
>
> There is a reason it is called the page allocator because if you want a
>
On Mon, Apr 17, 2017 at 10:20:42AM -0500, Christoph Lameter wrote:
> Simple solution is to not allocate pages via the slab allocator but use
> the page allocator for this. The page allocator provides proper alignment.
>
> There is a reason it is called the page allocator because if you want a
>
On Tue 18-04-17 19:56:41, Sergey Senozhatsky wrote:
> On (04/18/17 09:33), Michal Hocko wrote:
> [..]
> > > Another approach is the API does normal thing for non-aligned prefix and
> > > tail space and fast thing for aligned space.
> > > Otherwise, it would be happy if the API has WARN_ON non-page
On Tue 18-04-17 19:56:41, Sergey Senozhatsky wrote:
> On (04/18/17 09:33), Michal Hocko wrote:
> [..]
> > > Another approach is the API does normal thing for non-aligned prefix and
> > > tail space and fast thing for aligned space.
> > > Otherwise, it would be happy if the API has WARN_ON non-page
On (04/18/17 09:33), Michal Hocko wrote:
[..]
> > Another approach is the API does normal thing for non-aligned prefix and
> > tail space and fast thing for aligned space.
> > Otherwise, it would be happy if the API has WARN_ON non-page SIZE aligned
> > address.
>
> copy_page is a performance
On (04/18/17 09:33), Michal Hocko wrote:
[..]
> > Another approach is the API does normal thing for non-aligned prefix and
> > tail space and fast thing for aligned space.
> > Otherwise, it would be happy if the API has WARN_ON non-page SIZE aligned
> > address.
>
> copy_page is a performance
On (04/17/17 10:20), Christoph Lameter wrote:
> On Mon, 17 Apr 2017, Sergey Senozhatsky wrote:
> > Minchan reported that doing copy_page() on a kmalloc(PAGE_SIZE) page
> > with DEBUG_SLAB enabled can cause a memory corruption (See below or
> >
On (04/17/17 10:20), Christoph Lameter wrote:
> On Mon, 17 Apr 2017, Sergey Senozhatsky wrote:
> > Minchan reported that doing copy_page() on a kmalloc(PAGE_SIZE) page
> > with DEBUG_SLAB enabled can cause a memory corruption (See below or
> >
On Tue 18-04-17 09:03:19, Minchan Kim wrote:
> On Mon, Apr 17, 2017 at 10:20:42AM -0500, Christoph Lameter wrote:
> > On Mon, 17 Apr 2017, Sergey Senozhatsky wrote:
> >
> > > Minchan reported that doing copy_page() on a kmalloc(PAGE_SIZE) page
> > > with DEBUG_SLAB enabled can cause a memory
On Tue 18-04-17 09:03:19, Minchan Kim wrote:
> On Mon, Apr 17, 2017 at 10:20:42AM -0500, Christoph Lameter wrote:
> > On Mon, 17 Apr 2017, Sergey Senozhatsky wrote:
> >
> > > Minchan reported that doing copy_page() on a kmalloc(PAGE_SIZE) page
> > > with DEBUG_SLAB enabled can cause a memory
On Mon, Apr 17, 2017 at 10:20:42AM -0500, Christoph Lameter wrote:
> On Mon, 17 Apr 2017, Sergey Senozhatsky wrote:
>
> > Minchan reported that doing copy_page() on a kmalloc(PAGE_SIZE) page
> > with DEBUG_SLAB enabled can cause a memory corruption (See below or
> >
On Mon, Apr 17, 2017 at 10:20:42AM -0500, Christoph Lameter wrote:
> On Mon, 17 Apr 2017, Sergey Senozhatsky wrote:
>
> > Minchan reported that doing copy_page() on a kmalloc(PAGE_SIZE) page
> > with DEBUG_SLAB enabled can cause a memory corruption (See below or
> >
On Mon, 17 Apr 2017, Sergey Senozhatsky wrote:
> Minchan reported that doing copy_page() on a kmalloc(PAGE_SIZE) page
> with DEBUG_SLAB enabled can cause a memory corruption (See below or
> lkml.kernel.org/r/1492042622-12074-2-git-send-email-minc...@kernel.org )
Yes the alignment guarantees do
On Mon, 17 Apr 2017, Sergey Senozhatsky wrote:
> Minchan reported that doing copy_page() on a kmalloc(PAGE_SIZE) page
> with DEBUG_SLAB enabled can cause a memory corruption (See below or
> lkml.kernel.org/r/1492042622-12074-2-git-send-email-minc...@kernel.org )
Yes the alignment guarantees do
Hello,
I'll fork it into a separate thread and Cc more MM people.
sorry for top-posting.
Minchan reported that doing copy_page() on a kmalloc(PAGE_SIZE) page
with DEBUG_SLAB enabled can cause a memory corruption (See below or
lkml.kernel.org/r/1492042622-12074-2-git-send-email-minc...@kernel.org
Hello,
I'll fork it into a separate thread and Cc more MM people.
sorry for top-posting.
Minchan reported that doing copy_page() on a kmalloc(PAGE_SIZE) page
with DEBUG_SLAB enabled can cause a memory corruption (See below or
lkml.kernel.org/r/1492042622-12074-2-git-send-email-minc...@kernel.org
28 matches
Mail list logo