Re: [RESEND v2 PATCH 0/2] Bug fix in aio ring page migration

2014-05-13 Thread Gu Zheng
Hi Greg, Thanks for your attention on this thread. On 05/14/2014 07:58 AM, Greg Kroah-Hartman wrote: > On Thu, Mar 13, 2014 at 05:45:42PM +0800, Gu Zheng wrote: >> This patchset has been applied to linux-next, and these problems also exist >> in 3.12.y and 3.13.y stable tree. >> So please merge th

Re: [RESEND v2 PATCH 0/2] Bug fix in aio ring page migration

2014-05-13 Thread Greg Kroah-Hartman
On Thu, Mar 13, 2014 at 05:45:42PM +0800, Gu Zheng wrote: > This patchset has been applied to linux-next, and these problems also exist > in 3.12.y and 3.13.y stable tree. > So please merge this patchset to 3.12.y and 3.13.y stable tree. > > commit 692c9b8c5ee8d263bb8348171f0bebd3d84eb2c1 > Author

Re: [RESEND v2 PATCH 0/2] Bug fix in aio ring page migration

2014-03-16 Thread Ben Hutchings
On Thu, 2014-03-13 at 17:45 +0800, Gu Zheng wrote: > This patchset has been applied to linux-next, and these problems also exist > in 3.12.y and 3.13.y stable tree. > So please merge this patchset to 3.12.y and 3.13.y stable tree. They must be in Linus's tree before they are acceptable for stable.

Re: [RESEND v2 PATCH 0/2] Bug fix in aio ring page migration

2014-03-13 Thread Gu Zheng
This patchset has been applied to linux-next, and these problems also exist in 3.12.y and 3.13.y stable tree. So please merge this patchset to 3.12.y and 3.13.y stable tree. commit 692c9b8c5ee8d263bb8348171f0bebd3d84eb2c1 Author: Tang Chen Date: Mon Mar 10 16:15:33 2014 +0800 aio, memory-h

[RESEND v2 PATCH 0/2] Bug fix in aio ring page migration

2014-03-10 Thread Tang Chen
This patch-set fixes the following two problems: 1. Need to use ctx->completion_lock to protect ring pages from being mis-written while migration. 2. Need memory barrier to ensure memory copy is done before ctx->ring_pages[] is updated. NOTE: AIO ring page migration was implemented since L

[V2 PATCH 0/2] Bug fix in aio ring page migration

2014-03-09 Thread Tang Chen
This patch-set fixes the following two problems: 1. Need to use ctx->completion_lock to protect ring pages from being mis-written while migration. 2. Need memory barrier to ensure memory copy is done before ctx->ring_pages[] is updated. NOTE: AIO ring page migration was implemented since