Re: kernel BUG at /src/linux-dev/mm/mempolicy.c:1738! on v3.16-rc1

2014-06-20 Thread Hugh Dickins
On Fri, 20 Jun 2014, Naoya Horiguchi wrote: > On Fri, Jun 20, 2014 at 01:03:58PM -0700, Hugh Dickins wrote: > > On Fri, 20 Jun 2014, Naoya Horiguchi wrote: > > > On Fri, Jun 20, 2014 at 09:24:36AM -0500, Christoph Lameter wrote: > > > > On Thu, 19 Jun 2014, Naoya Horiguchi wrote: > > > > > > > > >

Re: kernel BUG at /src/linux-dev/mm/mempolicy.c:1738! on v3.16-rc1

2014-06-20 Thread Naoya Horiguchi
On Fri, Jun 20, 2014 at 01:03:58PM -0700, Hugh Dickins wrote: > On Fri, 20 Jun 2014, Naoya Horiguchi wrote: > > On Fri, Jun 20, 2014 at 09:24:36AM -0500, Christoph Lameter wrote: > > > On Thu, 19 Jun 2014, Naoya Horiguchi wrote: > > > > > > > I'm suspecting that mbind_range() do something wrong aro

Re: kernel BUG at /src/linux-dev/mm/mempolicy.c:1738! on v3.16-rc1

2014-06-20 Thread Christoph Lameter
On Fri, 20 Jun 2014, Hugh Dickins wrote: > [PATCH] mm: fix crashes from mbind() merging vmas > > v2.6.34's 9d8cebd4bcd7 ("mm: fix mbind vma merge problem") introduced > vma merging to mbind(), but it should have also changed the convention > of passing start vma from queue_pages_range() (formerly

Re: kernel BUG at /src/linux-dev/mm/mempolicy.c:1738! on v3.16-rc1

2014-06-20 Thread Hugh Dickins
On Fri, 20 Jun 2014, Naoya Horiguchi wrote: > On Fri, Jun 20, 2014 at 09:24:36AM -0500, Christoph Lameter wrote: > > On Thu, 19 Jun 2014, Naoya Horiguchi wrote: > > > > > I'm suspecting that mbind_range() do something wrong around vma handling, > > > but I don't have enough luck yet. Anyone has an

Re: kernel BUG at /src/linux-dev/mm/mempolicy.c:1738! on v3.16-rc1

2014-06-20 Thread Naoya Horiguchi
On Fri, Jun 20, 2014 at 09:24:36AM -0500, Christoph Lameter wrote: > On Thu, 19 Jun 2014, Naoya Horiguchi wrote: > > > I'm suspecting that mbind_range() do something wrong around vma handling, > > but I don't have enough luck yet. Anyone has an idea? > > Well memory policy data corrupted. This look

Re: kernel BUG at /src/linux-dev/mm/mempolicy.c:1738! on v3.16-rc1

2014-06-20 Thread Naoya Horiguchi
On Thu, Jun 19, 2014 at 09:35:48PM -0700, Hugh Dickins wrote: > On Thu, 19 Jun 2014, Naoya Horiguchi wrote: > > Hi, > > > > I triggered the following bug on v3.16-rc1 when I did mbind() testing > > where multiple processes repeat calling mbind() for a shared mapped file > > (causing pingpong of pa

Re: kernel BUG at /src/linux-dev/mm/mempolicy.c:1738! on v3.16-rc1

2014-06-20 Thread Christoph Lameter
On Thu, 19 Jun 2014, Naoya Horiguchi wrote: > I'm suspecting that mbind_range() do something wrong around vma handling, > but I don't have enough luck yet. Anyone has an idea? Well memory policy data corrupted. This looks like you were trying to do page migration via mbind()? Could we get some mo

Re: kernel BUG at /src/linux-dev/mm/mempolicy.c:1738! on v3.16-rc1

2014-06-19 Thread Hugh Dickins
On Thu, 19 Jun 2014, Naoya Horiguchi wrote: > Hi, > > I triggered the following bug on v3.16-rc1 when I did mbind() testing > where multiple processes repeat calling mbind() for a shared mapped file > (causing pingpong of page migration.) The shared mapped file on shmem/tmpfs? So involving share

kernel BUG at /src/linux-dev/mm/mempolicy.c:1738! on v3.16-rc1

2014-06-19 Thread Naoya Horiguchi
Hi, I triggered the following bug on v3.16-rc1 when I did mbind() testing where multiple processes repeat calling mbind() for a shared mapped file (causing pingpong of page migration.) In my investigation, it seems that some vma accidentally has vma->vm_start = 0, which makes new_vma_page() choos