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

Groups > linux.kernel > #1311354

Re: [PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition

From Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Newsgroups linux.kernel
Subject Re: [PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition
Date 2016-01-18 08:40 +0100
Message-ID <qSczT-5RA-5@gated-at.bofh.it> (permalink)
References <qSaRs-4GI-5@gated-at.bofh.it> <qSbDQ-5ho-5@gated-at.bofh.it> <qSbXc-5nZ-3@gated-at.bofh.it> <qSc6R-5GF-7@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

On (01/18/16 16:11), Minchan Kim wrote:
[..]
> > so, even if clear_bit_unlock/test_and_set_bit_lock do smp_mb or
> > barrier(), there is no corresponding barrier from record_obj()->WRITE_ONCE().
> > so I don't think WRITE_ONCE() will help the compiler, or am I missing
> > something?
> 
> We need two things

thanks.

> 1. compiler barrier

um... probably gcc can reorder that sequence to something like this

	*handle = obj_malloc()   /* unpin the object */
	zs_object_copy(*handle, used_obj, class) /* now use it*/

ok.


> 2. memory barrier.
> 
> As compiler barrier, WRITE_ONCE works to prevent store tearing here
> by compiler.
> However, if we omit unpin_tag here, we lose memory barrier(e,g, smp_mb)
> so another CPU could see stale data caused CPU memory reordering.

oh... good find! lost release semantic of unpin_tag()...

	-ss

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

Thread

[PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition Junil Lee <junil0814.lee@lge.com> - 2016-01-18 06:50 +0100
  Re: [PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> - 2016-01-18 07:20 +0100
  Re: [PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition Minchan Kim <minchan@kernel.org> - 2016-01-18 07:40 +0100
    Re: [PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> - 2016-01-18 08:00 +0100
      Re: [PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition Minchan Kim <minchan@kernel.org> - 2016-01-18 08:10 +0100
        Re: [PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> - 2016-01-18 08:40 +0100
          Re: [PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition Vlastimil Babka <vbabka@suse.cz> - 2016-01-18 09:00 +0100
            Re: [PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition Minchan Kim <minchan@kernel.org> - 2016-01-18 09:20 +0100
              Re: [PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> - 2016-01-18 12:10 +0100
              Re: [PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition Vlastimil Babka <vbabka@suse.cz> - 2016-01-18 13:20 +0100
                Re: [PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition Minchan Kim <minchan@kernel.org> - 2016-01-18 15:10 +0100
                Re: [PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition Vlastimil Babka <vbabka@suse.cz> - 2016-01-18 15:20 +0100

csiph-web