From: Jiaqi Yan <jiaqiyan@google.com>
To: Hugh Dickins <hughd@google.com>
Cc: Yang Shi <shy828301@gmail.com>,
kirill.shutemov@linux.intel.com, kirill@shutemov.name,
tongtiangen@huawei.com, tony.luck@intel.com,
akpm@linux-foundation.org, naoya.horiguchi@nec.com,
linmiaohe@huawei.com, linux-mm@kvack.org, osalvador@suse.de,
wangkefeng.wang@huawei.com
Subject: Re: [PATCH v10 3/3] mm/khugepaged: recover from poisoned file-backed memory
Date: Mon, 27 Mar 2023 14:15:29 -0700 [thread overview]
Message-ID: <CACw3F51hgNOcewv4GP_dn+kM1fTUwG50Qbi4ZdJ12uQwsH7zSg@mail.gmail.com> (raw)
In-Reply-To: <3731c8e-961c-7497-f7c9-5edf8c6ea793@google.com>
On Fri, Mar 24, 2023 at 5:39 PM Hugh Dickins <hughd@google.com> wrote:
>
> On Fri, 24 Mar 2023, Jiaqi Yan wrote:
> > On Fri, Mar 24, 2023 at 2:15 PM Yang Shi <shy828301@gmail.com> wrote:
> > > On Sat, Mar 4, 2023 at 10:51 PM Jiaqi Yan <jiaqiyan@google.com> wrote:
> > > >
> > > > Make collapse_file roll back when copying pages failed. More concretely:
> > > > - extract copying operations into a separate loop
> > > > - postpone the updates for nr_none until both scanning and copying
> > > > succeeded
> > > > - postpone joining small xarray entries until both scanning and copying
> > > > succeeded
> > > > - postpone the update operations to NR_XXX_THPS until both scanning and
> > > > copying succeeded
> > > > - for non-SHMEM file, roll back filemap_nr_thps_inc if scan succeeded but
> > > > copying failed
> > > >
> > > > Tested manually:
> > > > 0. Enable khugepaged on system under test. Mount tmpfs at /mnt/ramdisk.
> > > > 1. Start a two-thread application. Each thread allocates a chunk of
> > > > non-huge memory buffer from /mnt/ramdisk.
> > > > 2. Pick 4 random buffer address (2 in each thread) and inject
> > > > uncorrectable memory errors at physical addresses.
> > > > 3. Signal both threads to make their memory buffer collapsible, i.e.
> > > > calling madvise(MADV_HUGEPAGE).
> > > > 4. Wait and then check kernel log: khugepaged is able to recover from
> > > > poisoned pages by skipping them.
> > > > 5. Signal both threads to inspect their buffer contents and make sure no
> > > > data corruption.
> > > >
> > > > Signed-off-by: Jiaqi Yan <jiaqiyan@google.com>
> > >
> > > Reviewed-by: Yang Shi <shy828301@gmail.com>
> > >
> > > Just a nit below:
>
> Acked-by: Hugh Dickins <hughd@google.com>
>
> with a little nit from me below, if you are respinning:
>
> > >
> > > > ---
> > > > mm/khugepaged.c | 78 ++++++++++++++++++++++++++++++-------------------
> > > > 1 file changed, 48 insertions(+), 30 deletions(-)
> > > >
> > > > diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> > > > index c3c217f6ebc6e..3ea2aa55c2c52 100644
> > > > --- a/mm/khugepaged.c
> > > > +++ b/mm/khugepaged.c
> > > > @@ -1890,6 +1890,9 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
> > > > {
> > > > struct address_space *mapping = file->f_mapping;
> > > > struct page *hpage;
> > > > + struct page *page;
> > > > + struct page *tmp;
> > > > + struct folio *folio;
> > > > pgoff_t index = 0, end = start + HPAGE_PMD_NR;
> > > > LIST_HEAD(pagelist);
> > > > XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER);
> > > > @@ -1934,8 +1937,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
> > > >
> > > > xas_set(&xas, start);
> > > > for (index = start; index < end; index++) {
> > > > - struct page *page = xas_next(&xas);
> > > > - struct folio *folio;
> > > > + page = xas_next(&xas);
> > > >
> > > > VM_BUG_ON(index != xas.xa_index);
> > > > if (is_shmem) {
> > > > @@ -2117,10 +2119,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
> > > > }
> > > > nr = thp_nr_pages(hpage);
> > > >
> > > > - if (is_shmem)
> > > > - __mod_lruvec_page_state(hpage, NR_SHMEM_THPS, nr);
> > > > - else {
> > > > - __mod_lruvec_page_state(hpage, NR_FILE_THPS, nr);
> > > > + if (!is_shmem) {
> > > > filemap_nr_thps_inc(mapping);
> > > > /*
> > > > * Paired with smp_mb() in do_dentry_open() to ensure
>
> That "nr = thp_nr_pages(hpage);" above becomes stranded a long way away
> from where "nr" is actually used for updating those statistics: please
> move it down with them. (I see "nr" is also reported in the tracepoint
> at the end, FWIW, so maybe that will show "0" in more failure cases than
> it used to, but that's okay - it has been decently initialized.)
>
Thanks Hugh! I will make sure V11 moves "nr" closer to the place it is used.
> Thanks,
> Hugh
prev parent reply other threads:[~2023-03-27 21:15 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-05 6:51 [PATCH v10 0/3] Memory poison recovery in khugepaged collapsing Jiaqi Yan
2023-03-05 6:51 ` [PATCH v10 1/3] mm/khugepaged: recover from poisoned anonymous memory Jiaqi Yan
2023-03-20 14:42 ` Jiaqi Yan
2023-03-21 0:12 ` Yang Shi
2023-03-23 21:37 ` Yang Shi
2023-03-24 15:34 ` Jiaqi Yan
2023-03-24 20:11 ` Yang Shi
2023-03-24 22:31 ` Jiaqi Yan
2023-03-27 20:46 ` Jiaqi Yan
2023-03-05 6:51 ` [PATCH v10 2/3] mm/hwpoison: introduce copy_mc_highpage Jiaqi Yan
2023-03-05 6:56 ` Jiaqi Yan
2023-03-24 20:24 ` Yang Shi
2023-03-05 6:51 ` [PATCH v10 3/3] mm/khugepaged: recover from poisoned file-backed memory Jiaqi Yan
2023-03-24 21:15 ` Yang Shi
2023-03-24 22:54 ` Jiaqi Yan
2023-03-25 0:39 ` Hugh Dickins
2023-03-27 21:15 ` Jiaqi Yan [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CACw3F51hgNOcewv4GP_dn+kM1fTUwG50Qbi4ZdJ12uQwsH7zSg@mail.gmail.com \
--to=jiaqiyan@google.com \
--cc=akpm@linux-foundation.org \
--cc=hughd@google.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=kirill@shutemov.name \
--cc=linmiaohe@huawei.com \
--cc=linux-mm@kvack.org \
--cc=naoya.horiguchi@nec.com \
--cc=osalvador@suse.de \
--cc=shy828301@gmail.com \
--cc=tongtiangen@huawei.com \
--cc=tony.luck@intel.com \
--cc=wangkefeng.wang@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).