Re: [PATCH v1] mm, pagemap: expose hwpoison entry

[Naoya Horiguchi]

On Mon, Oct 04, 2021 at 01:55:30PM +0200, David Hildenbrand wrote:
> On 04.10.21 13:50, Naoya Horiguchi wrote:
> > From: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
> > 
> > A hwpoison entry is a non-present page table entry to report
> > memory error events to userspace. If we have an easy way to know
> > which processes have hwpoison entries, that might be useful for
> > user processes to take proper actions. But we don't have it now.
> > So make pagemap interface expose hwpoison entries to userspace.
> 
> Noting that this is only a way to inspect hwpoison set for private anonymous
> memory. You cannot really identify anything related to shared memory.
> 
> Do you also handle private hugetlb pages?

I think yes.  As long as hugepages are mmap()ed, we should be able to
identify them with hwpoison entry (even if used via private/shared mapping).

> 
> > 
> > Hwpoison entry for hugepage is also exposed by this patch. The below
> > example shows how pagemap is visible in the case where a memory error
> > hit a hugepage mapped to a process.
> > 
> >      $ ./page-types --no-summary --pid $PID --raw --list --addr 0x700000000+0x400
> >      voffset offset  len     flags
> >      700000000       12fa00  1       ___U_______Ma__H_G_________________f_______1
> >      700000001       12fa01  1ff     ___________Ma___TG_________________f_______1
> >      700000200       12f800  1       __________B________X_______________f______w_
> >      700000201       12f801  1       ___________________X_______________f______w_   // memory failure hit this page
> >      700000202       12f802  1fe     __________B________X_______________f______w_
> > 
> > The entries with both of "X" flag (hwpoison flag) and "w" flag (swap
> > flag) are considered as hwpoison entries.  So all pages in 2MB range
> > are inaccessible from the process.  We can get actual error location
> > by page-types in physical address mode.
> > 
> >      $ ./page-types --no-summary --addr 0x12f800+0x200 --raw --list
> >      offset  len     flags
> >      12f800  1       __________B_________________________________
> >      12f801  1       ___________________X________________________
> >      12f802  1fe     __________B_________________________________
> > 
> > Signed-off-by: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
> > ---
> >   fs/proc/task_mmu.c      | 41 ++++++++++++++++++++++++++++++++---------
> >   include/linux/swapops.h | 13 +++++++++++++
> >   tools/vm/page-types.c   |  7 ++++++-
> >   3 files changed, 51 insertions(+), 10 deletions(-)
> 
> 
> Please also update the documentation located at
> 
> Documentation/admin-guide/mm/pagemap.rst

I will do this in the next post.

Thanks,
Naoya Horigcuhi