From: Yang Shi <shy828301@gmail.com>
To: Peter Xu <peterx@redhat.com>
Cc: "HORIGUCHI NAOYA(堀口 直也)" <naoya.horiguchi@nec.com>,
"Hugh Dickins" <hughd@google.com>,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
"Matthew Wilcox" <willy@infradead.org>,
"Oscar Salvador" <osalvador@suse.de>,
"Andrew Morton" <akpm@linux-foundation.org>,
"Linux MM" <linux-mm@kvack.org>,
"Linux FS-devel Mailing List" <linux-fsdevel@vger.kernel.org>,
"Linux Kernel Mailing List" <linux-kernel@vger.kernel.org>
Subject: Re: [v3 PATCH 3/5] mm: hwpoison: refactor refcount check handling
Date: Wed, 6 Oct 2021 19:47:20 -0700 [thread overview]
Message-ID: <CAHbLzkqtaF2iFwg0TmMm_1q+o+-O=CXAAPY2izxL6N=8umX_Cg@mail.gmail.com> (raw)
In-Reply-To: <YV4c1dOfctEMnH2s@t490s>
On Wed, Oct 6, 2021 at 3:02 PM Peter Xu <peterx@redhat.com> wrote:
>
> On Thu, Sep 30, 2021 at 02:53:09PM -0700, Yang Shi wrote:
> > +/*
> > + * Return true if page is still referenced by others, otherwise return
> > + * false.
> > + *
> > + * The dec is true when one extra refcount is expected.
> > + */
> > +static bool has_extra_refcount(struct page_state *ps, struct page *p,
> > + bool dec)
>
> Nit: would it be nicer to keep using things like "extra_pins", so we pass in 1
> for swapcache dirty case and 0 for the rest? Then it'll also match with most
> of the similar cases in e.g. huge_memory.c (please try grep "extra_pins" there).
Thanks for the suggestion. Yes, it makes some sense to me. And the
code comments in patch 4/5 does says (the suggested version by Naoya):
/*
* The shmem page is kept in page cache instead of truncating
* so is expected to have an extra refcount after error-handling.
*/
Will rename it in the new version.
>
> > +{
> > + int count = page_count(p) - 1;
> > +
> > + if (dec)
> > + count -= 1;
> > +
> > + if (count > 0) {
> > + pr_err("Memory failure: %#lx: %s still referenced by %d users\n",
> > + page_to_pfn(p), action_page_types[ps->type], count);
> > + return true;
> > + }
> > +
> > + return false;
> > +}
> > +
> > /*
> > * Error hit kernel page.
> > * Do nothing, try to be lucky and not touch this instead. For a few cases we
> > * could be more sophisticated.
> > */
> > -static int me_kernel(struct page *p, unsigned long pfn)
> > +static int me_kernel(struct page_state *ps, struct page *p)
>
> Not sure whether it's intended, but some of the action() hooks do not call the
> refcount check now while in the past they'll all do. Just to double check
> they're expected, like this one and me_unknown().
Yeah, it is intentional. Before this change all me_* handlers did
check refcount even though it was not necessary, for example,
me_kernel() and me_unknown().
>
> > {
> > unlock_page(p);
> > return MF_IGNORED;
> > @@ -820,9 +852,9 @@ static int me_kernel(struct page *p, unsigned long pfn)
> > /*
> > * Page in unknown state. Do nothing.
> > */
> > -static int me_unknown(struct page *p, unsigned long pfn)
> > +static int me_unknown(struct page_state *ps, struct page *p)
> > {
> > - pr_err("Memory failure: %#lx: Unknown page state\n", pfn);
> > + pr_err("Memory failure: %#lx: Unknown page state\n", page_to_pfn(p));
> > unlock_page(p);
> > return MF_FAILED;
> > }
>
> Thanks,
>
> --
> Peter Xu
>
next prev parent reply other threads:[~2021-10-07 2:47 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-30 21:53 [RFC v3 PATCH 0/5] Solve silent data loss caused by poisoned page cache (shmem/tmpfs) Yang Shi
2021-09-30 21:53 ` [v3 PATCH 1/5] mm: hwpoison: remove the unnecessary THP check Yang Shi
2021-10-06 2:35 ` Yang Shi
2021-10-06 4:00 ` Naoya Horiguchi
2021-10-06 17:56 ` Yang Shi
2021-09-30 21:53 ` [v3 PATCH 2/5] mm: filemap: check if THP has hwpoisoned subpage for PMD page fault Yang Shi
2021-10-01 7:23 ` Naoya Horiguchi
2021-10-01 21:07 ` Yang Shi
2021-10-04 14:06 ` Kirill A. Shutemov
2021-10-04 18:17 ` Yang Shi
2021-10-04 19:41 ` Kirill A. Shutemov
2021-10-04 20:13 ` Yang Shi
2021-10-06 19:54 ` Peter Xu
2021-10-06 23:41 ` Yang Shi
2021-10-07 16:14 ` Peter Xu
2021-10-07 18:28 ` Yang Shi
2021-10-08 9:35 ` Kirill A. Shutemov
2021-10-11 22:57 ` Peter Xu
2021-10-06 20:15 ` Peter Xu
2021-10-06 23:57 ` Yang Shi
2021-10-07 16:06 ` Peter Xu
2021-10-07 18:19 ` Yang Shi
2021-10-07 20:27 ` Yang Shi
2021-10-07 21:28 ` Yang Shi
2021-10-12 0:55 ` Peter Xu
2021-10-12 1:44 ` Peter Xu
2021-10-12 18:02 ` Yang Shi
2021-10-12 22:10 ` Peter Xu
2021-10-13 2:48 ` Yang Shi
2021-10-13 3:01 ` Peter Xu
2021-10-13 3:27 ` Yang Shi
2021-10-13 3:41 ` Peter Xu
2021-10-13 21:42 ` Yang Shi
2021-10-13 23:13 ` Peter Xu
2021-10-14 6:54 ` Naoya Horiguchi
2021-10-06 20:18 ` Peter Xu
2021-10-07 2:49 ` Yang Shi
2021-11-01 19:05 ` Naresh Kamboju
2021-11-01 19:26 ` Yang Shi
2021-09-30 21:53 ` [v3 PATCH 3/5] mm: hwpoison: refactor refcount check handling Yang Shi
2021-10-06 22:01 ` Peter Xu
2021-10-07 2:47 ` Yang Shi [this message]
2021-10-07 16:18 ` Peter Xu
2021-09-30 21:53 ` [v3 PATCH 4/5] mm: shmem: don't truncate page if memory failure happens Yang Shi
2021-10-01 7:05 ` Naoya Horiguchi
2021-10-01 21:08 ` Yang Shi
2021-10-12 1:57 ` Peter Xu
2021-10-12 19:17 ` Yang Shi
2021-10-12 22:26 ` Peter Xu
2021-10-13 3:00 ` Yang Shi
2021-10-13 3:06 ` Peter Xu
2021-10-13 3:29 ` Yang Shi
2021-09-30 21:53 ` [v3 PATCH 5/5] mm: hwpoison: handle non-anonymous THP correctly Yang Shi
2021-10-01 7:06 ` Naoya Horiguchi
2021-10-01 21:09 ` Yang Shi
2021-10-13 2:40 ` [RFC v3 PATCH 0/5] Solve silent data loss caused by poisoned page cache (shmem/tmpfs) Peter Xu
2021-10-13 3:09 ` Yang Shi
2021-10-13 3:24 ` Peter Xu
2021-10-14 6:54 ` Naoya Horiguchi
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='CAHbLzkqtaF2iFwg0TmMm_1q+o+-O=CXAAPY2izxL6N=8umX_Cg@mail.gmail.com' \
--to=shy828301@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=hughd@google.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=naoya.horiguchi@nec.com \
--cc=osalvador@suse.de \
--cc=peterx@redhat.com \
--cc=willy@infradead.org \
/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).