Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1625851

Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was "zram: do not use copy_page with non-page alinged address")

From Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Newsgroups linux.kernel
Subject Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was "zram: do not use copy_page with non-page alinged address")
Date 2017-04-19 08:20 +0200
Message-ID <txR85-8fV-17@gated-at.bofh.it> (permalink)
References (1 earlier) <txgLg-2iD-21@gated-at.bofh.it> <txoSt-7uv-1@gated-at.bofh.it> <txvTY-3om-15@gated-at.bofh.it> <txzbb-5tz-17@gated-at.bofh.it> <txzbb-5tz-15@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

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 DEBUG_SLAB is set? so arch copy_page() (if provided by arch)
> > won't be affected otherwise.
> 
> SLAB is not guaranteed to provide page size aligned object AFAIR.

oh, if there are no guarantees for page_sized allocations regardless
the .config then agree, won't help.

	-ss

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was "zram:  do not use copy_page with non-page alinged address") Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> - 2017-04-17 03:50 +0200
  Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was  "zram: do not use copy_page with non-page alinged address") Christoph Lameter <cl@linux.com> - 2017-04-17 17:30 +0200
    Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was  "zram: do not use copy_page with non-page alinged address") Minchan Kim <minchan@kernel.org> - 2017-04-18 02:10 +0200
      Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was  "zram: do not use copy_page with non-page alinged address") Michal Hocko <mhocko@kernel.org> - 2017-04-18 09:40 +0200
        Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was  "zram: do not use copy_page with non-page alinged address") Michal Hocko <mhocko@kernel.org> - 2017-04-18 13:10 +0200
          Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was  "zram: do not use copy_page with non-page alinged address") Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> - 2017-04-19 08:20 +0200
        Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was  "zram: do not use copy_page with non-page alinged address") Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> - 2017-04-18 13:10 +0200
        Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was  "zram: do not use copy_page with non-page alinged address") Minchan Kim <minchan@kernel.org> - 2017-04-19 08:10 +0200
          Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was  "zram: do not use copy_page with non-page alinged address") Matthew Wilcox <willy@infradead.org> - 2017-04-19 14:00 +0200
            Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was  "zram: do not use copy_page with non-page alinged address") Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> - 2017-04-20 03:50 +0200
              Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was  "zram: do not use copy_page with non-page alinged address") Minchan Kim <minchan@kernel.org> - 2017-04-20 09:00 +0200
    Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was  "zram: do not use copy_page with non-page alinged address") Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> - 2017-04-18 12:50 +0200
      Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was  "zram: do not use copy_page with non-page alinged address") Christoph Lameter <cl@linux.com> - 2017-04-18 15:30 +0200
    Re: copy_page() on a kmalloc-ed page with DEBUG_SLAB enabled (was  "zram: do not use copy_page with non-page alinged address") Matthew Wilcox <willy@infradead.org> - 2017-04-18 15:20 +0200

csiph-web