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


Groups > linux.kernel > #1311359

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

From Vlastimil Babka <vbabka@suse.cz>
Newsgroups linux.kernel
Subject Re: [PATCH v3] zsmalloc: fix migrate_zspage-zs_free race condition
Date 2016-01-18 09:00 +0100
Message-ID <qScTf-5Ya-1@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> <qSczT-5RA-5@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On 18.1.2016 8:39, Sergey Senozhatsky wrote:
> 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
>> 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()...

Ah, release semantic, good point indeed. OK then we need the v2 approach again,
with WRITE_ONCE() in record_obj(). Or some kind of record_obj_release() with
release semantic, which would be a bit more effective, but I guess migration is
not that critical path to be worth introducing it.

Thanks,
Vlastimil

> 
> 	-ss
> 

Back to linux.kernel | Previous | NextPrevious 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