From: Matthew Wilcox <willy@infradead.org>
To: Christoph Hellwig <hch@infradead.org>
Cc: linux-mm@kvack.org, John Hubbard <jhubbard@nvidia.com>,
William Kucharski <william.kucharski@oracle.com>,
linux-kernel@vger.kernel.org, Jason Gunthorpe <jgg@ziepe.ca>,
Mike Kravetz <mike.kravetz@oracle.com>
Subject: Re: [PATCH v2 06/28] gup: Fix some contiguous memmap assumptions
Date: Mon, 10 Jan 2022 13:37:13 +0000 [thread overview]
Message-ID: <Ydw2iQR8fT+qGkz6@casper.infradead.org> (raw)
In-Reply-To: <YdvuhjweiC1SjVF4@infradead.org>
On Mon, Jan 10, 2022 at 12:29:58AM -0800, Christoph Hellwig wrote:
> On Mon, Jan 10, 2022 at 04:23:44AM +0000, Matthew Wilcox (Oracle) wrote:
> > Several functions in gup.c assume that a compound page has virtually
> > contiguous page structs. This isn't true for SPARSEMEM configs unless
> > SPARSEMEM_VMEMMAP is also set. Fix them by using nth_page() instead of
> > plain pointer arithmetic.
>
> So is this an actualy bug that need a Fixes tag, or do all architectures
> that support THP and sparsemem use SPARSEMEM_VMEMMAP?
As far as I can tell (and I am by no means an expert in this area),
this problem only affects pages of order MAX_ORDER or higher. That is,
somebody using regular 2MB hugepages on x86 won't see a problem, whether
they're using VMEMMAP or not. It only starts to become a problem for
1GB hugepages.
Since THPs are (currently) only allocated from the page allocator, it's
never a problem for THPs, only hugetlbfs. Correcting the places which
can't see a 1GB page is just defense against copy-and-paste programming.
So I'll defer to Mike -- does this ever affect real systems and thus
warrant a backport? I know this doesn't affect UEK because we enable
SPARSEMEM_VMEMMAP.
> > + page = nth_page(head, (addr & (sz-1)) >> PAGE_SHIFT);
>
> Would be nice to fix the indeation for sz - 1 while you're at it.
Done.
next prev parent reply other threads:[~2022-01-10 13:37 UTC|newest]
Thread overview: 96+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-01-10 4:23 [PATCH v2 00/28] Convert GUP to folios Matthew Wilcox (Oracle)
2022-01-10 4:23 ` [PATCH v2 01/28] gup: Remove for_each_compound_range() Matthew Wilcox (Oracle)
2022-01-10 8:22 ` Christoph Hellwig
2022-01-11 1:07 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 02/28] gup: Remove for_each_compound_head() Matthew Wilcox (Oracle)
2022-01-10 8:23 ` Christoph Hellwig
2022-01-11 1:11 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 03/28] gup: Change the calling convention for compound_range_next() Matthew Wilcox (Oracle)
2022-01-10 8:25 ` Christoph Hellwig
2022-01-11 1:14 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 04/28] gup: Optimise compound_range_next() Matthew Wilcox (Oracle)
2022-01-10 8:26 ` Christoph Hellwig
2022-01-11 1:16 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 05/28] gup: Change the calling convention for compound_next() Matthew Wilcox (Oracle)
2022-01-10 8:27 ` Christoph Hellwig
2022-01-10 13:28 ` Matthew Wilcox
2022-01-11 1:18 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 06/28] gup: Fix some contiguous memmap assumptions Matthew Wilcox (Oracle)
2022-01-10 8:29 ` Christoph Hellwig
2022-01-10 13:37 ` Matthew Wilcox [this message]
2022-01-10 19:05 ` [External] : " Mike Kravetz
2022-01-11 1:47 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 07/28] gup: Remove an assumption of a contiguous memmap Matthew Wilcox (Oracle)
2022-01-10 8:30 ` Christoph Hellwig
2022-01-11 3:27 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 08/28] gup: Handle page split race more efficiently Matthew Wilcox (Oracle)
2022-01-10 8:31 ` Christoph Hellwig
2022-01-11 3:30 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 09/28] gup: Turn hpage_pincount_add() into page_pincount_add() Matthew Wilcox (Oracle)
2022-01-10 8:31 ` Christoph Hellwig
2022-01-11 3:35 ` John Hubbard
2022-01-11 4:32 ` John Hubbard
2022-01-11 13:46 ` Matthew Wilcox
2022-01-10 4:23 ` [PATCH v2 10/28] gup: Turn hpage_pincount_sub() into page_pincount_sub() Matthew Wilcox (Oracle)
2022-01-10 8:32 ` Christoph Hellwig
2022-01-11 6:40 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 11/28] mm: Make compound_pincount always available Matthew Wilcox (Oracle)
2022-01-11 4:06 ` John Hubbard
2022-01-11 4:38 ` Matthew Wilcox
2022-01-11 5:10 ` John Hubbard
2022-01-20 9:15 ` Christoph Hellwig
2022-01-10 4:23 ` [PATCH v2 12/28] mm: Add folio_put_refs() Matthew Wilcox (Oracle)
2022-01-10 8:32 ` Christoph Hellwig
2022-01-11 4:14 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 13/28] mm: Add folio_pincount_ptr() Matthew Wilcox (Oracle)
2022-01-10 8:33 ` Christoph Hellwig
2022-01-11 4:22 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 14/28] mm: Convert page_maybe_dma_pinned() to use a folio Matthew Wilcox (Oracle)
2022-01-10 8:33 ` Christoph Hellwig
2022-01-11 4:27 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 15/28] gup: Add try_get_folio() and try_grab_folio() Matthew Wilcox (Oracle)
2022-01-10 8:34 ` Christoph Hellwig
2022-01-11 5:00 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 16/28] mm: Remove page_cache_add_speculative() and page_cache_get_speculative() Matthew Wilcox (Oracle)
2022-01-10 8:35 ` Christoph Hellwig
2022-01-11 5:14 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 17/28] gup: Add gup_put_folio() Matthew Wilcox (Oracle)
2022-01-10 8:35 ` Christoph Hellwig
2022-01-11 6:44 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 18/28] hugetlb: Use try_grab_folio() instead of try_grab_compound_head() Matthew Wilcox (Oracle)
2022-01-10 8:36 ` Christoph Hellwig
2022-01-11 6:47 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 19/28] gup: Convert try_grab_page() to call try_grab_folio() Matthew Wilcox (Oracle)
2022-01-10 8:36 ` Christoph Hellwig
2022-01-11 7:01 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 20/28] gup: Convert gup_pte_range() to use a folio Matthew Wilcox (Oracle)
2022-01-10 8:37 ` Christoph Hellwig
2022-01-11 7:06 ` John Hubbard
2022-01-10 4:23 ` [PATCH v2 21/28] gup: Convert gup_hugepte() " Matthew Wilcox (Oracle)
2022-01-10 8:37 ` Christoph Hellwig
2022-01-11 7:33 ` John Hubbard
2022-01-10 4:24 ` [PATCH v2 22/28] gup: Convert gup_huge_pmd() " Matthew Wilcox (Oracle)
2022-01-10 8:37 ` Christoph Hellwig
2022-01-11 7:36 ` John Hubbard
2022-01-10 4:24 ` [PATCH v2 23/28] gup: Convert gup_huge_pud() " Matthew Wilcox (Oracle)
2022-01-10 8:38 ` Christoph Hellwig
2022-01-11 7:38 ` John Hubbard
2022-01-10 4:24 ` [PATCH v2 24/28] gup: Convert gup_huge_pgd() " Matthew Wilcox (Oracle)
2022-01-10 8:38 ` Christoph Hellwig
2022-01-11 7:38 ` John Hubbard
2022-01-10 4:24 ` [PATCH v2 25/28] gup: Convert compound_next() to gup_folio_next() Matthew Wilcox (Oracle)
2022-01-10 8:39 ` Christoph Hellwig
2022-01-11 7:41 ` John Hubbard
2022-01-10 4:24 ` [PATCH v2 26/28] gup: Convert compound_range_next() to gup_folio_range_next() Matthew Wilcox (Oracle)
2022-01-10 8:41 ` Christoph Hellwig
2022-01-10 13:41 ` Matthew Wilcox
2022-01-11 7:44 ` John Hubbard
2022-01-10 4:24 ` [PATCH v2 27/28] mm: Add isolate_lru_folio() Matthew Wilcox (Oracle)
2022-01-10 8:42 ` Christoph Hellwig
2022-01-11 7:49 ` John Hubbard
2022-01-10 4:24 ` [PATCH v2 28/28] gup: Convert check_and_migrate_movable_pages() to use a folio Matthew Wilcox (Oracle)
2022-01-10 8:42 ` Christoph Hellwig
2022-01-11 7:52 ` John Hubbard
2022-01-10 15:31 ` [PATCH v2 00/28] Convert GUP to folios Jason Gunthorpe
2022-01-10 16:09 ` Matthew Wilcox
2022-01-10 17:26 ` William Kucharski
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=Ydw2iQR8fT+qGkz6@casper.infradead.org \
--to=willy@infradead.org \
--cc=hch@infradead.org \
--cc=jgg@ziepe.ca \
--cc=jhubbard@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mike.kravetz@oracle.com \
--cc=william.kucharski@oracle.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.