From: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
To: David Hildenbrand <david@redhat.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
Linux MM <linux-mm@kvack.org>,
linux-hyperv@vger.kernel.org, xen-devel@lists.xenproject.org,
linux-acpi@vger.kernel.org,
Andrew Morton <akpm@linux-foundation.org>,
Alexander Duyck <alexander.h.duyck@linux.intel.com>,
Oscar Salvador <osalvador@suse.de>,
Mel Gorman <mgorman@techsingularity.net>,
Michal Hocko <mhocko@kernel.org>,
Dave Hansen <dave.hansen@intel.com>,
Vlastimil Babka <vbabka@suse.cz>,
Wei Yang <richard.weiyang@linux.alibaba.com>,
Mike Rapoport <rppt@kernel.org>,
Scott Cheloha <cheloha@linux.ibm.com>,
Michael Ellerman <mpe@ellerman.id.au>
Subject: Re: [PATCH v1 2/5] mm/page_alloc: place pages to tail in __putback_isolated_page()
Date: Mon, 28 Sep 2020 22:38:35 +0200 [thread overview]
Message-ID: <CAM9Jb+iitZzZeF5b8eCWoR7fD=D3t76YDRaYsBC1o8nx-2jEYA@mail.gmail.com> (raw)
In-Reply-To: <20200928182110.7050-3-david@redhat.com>
> __putback_isolated_page() already documents that pages will be placed to
> the tail of the freelist - this is, however, not the case for
> "order >= MAX_ORDER - 2" (see buddy_merge_likely()) - which should be
> the case for all existing users.
>
> This change affects two users:
> - free page reporting
> - page isolation, when undoing the isolation (including memory onlining).
>
> This behavior is desireable for pages that haven't really been touched
> lately, so exactly the two users that don't actually read/write page
> content, but rather move untouched pages.
>
> The new behavior is especially desirable for memory onlining, where we
> allow allocation of newly onlined pages via undo_isolate_page_range()
> in online_pages(). Right now, we always place them to the head of the
> free list, resulting in undesireable behavior: Assume we add
> individual memory chunks via add_memory() and online them right away to
> the NORMAL zone. We create a dependency chain of unmovable allocations
> e.g., via the memmap. The memmap of the next chunk will be placed onto
> previous chunks - if the last block cannot get offlined+removed, all
> dependent ones cannot get offlined+removed. While this can already be
> observed with individual DIMMs, it's more of an issue for virtio-mem
> (and I suspect also ppc DLPAR).
>
> Document that this should only be used for optimizations, and no code
> should realy on this for correction (if the order of freepage lists
> ever changes).
>
> We won't care about page shuffling: memory onlining already properly
> shuffles after onlining. free page reporting doesn't care about
> physically contiguous ranges, and there are already cases where page
> isolation will simply move (physically close) free pages to (currently)
> the head of the freelists via move_freepages_block() instead of
> shuffling. If this becomes ever relevant, we should shuffle the whole
> zone when undoing isolation of larger ranges, and after
> free_contig_range().
>
> Reviewed-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
> Reviewed-by: Oscar Salvador <osalvador@suse.de>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
> Cc: Mel Gorman <mgorman@techsingularity.net>
> Cc: Michal Hocko <mhocko@kernel.org>
> Cc: Dave Hansen <dave.hansen@intel.com>
> Cc: Vlastimil Babka <vbabka@suse.cz>
> Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
> Cc: Oscar Salvador <osalvador@suse.de>
> Cc: Mike Rapoport <rppt@kernel.org>
> Cc: Scott Cheloha <cheloha@linux.ibm.com>
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Signed-off-by: David Hildenbrand <david@redhat.com>
> ---
> mm/page_alloc.c | 18 ++++++++++++++++--
> 1 file changed, 16 insertions(+), 2 deletions(-)
>
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index daab90e960fe..9e3ed4a6f69a 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -89,6 +89,18 @@ typedef int __bitwise fop_t;
> */
> #define FOP_SKIP_REPORT_NOTIFY ((__force fop_t)BIT(0))
>
> +/*
> + * Place the (possibly merged) page to the tail of the freelist. Will ignore
> + * page shuffling (relevant code - e.g., memory onlining - is expected to
> + * shuffle the whole zone).
> + *
> + * Note: No code should rely onto this flag for correctness - it's purely
> + * to allow for optimizations when handing back either fresh pages
> + * (memory onlining) or untouched pages (page isolation, free page
> + * reporting).
> + */
> +#define FOP_TO_TAIL ((__force fop_t)BIT(1))
> +
> /* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
> static DEFINE_MUTEX(pcp_batch_high_lock);
> #define MIN_PERCPU_PAGELIST_FRACTION (8)
> @@ -1038,7 +1050,9 @@ static inline void __free_one_page(struct page *page, unsigned long pfn,
> done_merging:
> set_page_order(page, order);
>
> - if (is_shuffle_order(order))
> + if (fop_flags & FOP_TO_TAIL)
> + to_tail = true;
> + else if (is_shuffle_order(order))
> to_tail = shuffle_pick_tail();
> else
> to_tail = buddy_merge_likely(pfn, buddy_pfn, page, order);
> @@ -3300,7 +3314,7 @@ void __putback_isolated_page(struct page *page, unsigned int order, int mt)
>
> /* Return isolated page to tail of freelist. */
> __free_one_page(page, page_to_pfn(page), zone, order, mt,
> - FOP_SKIP_REPORT_NOTIFY);
> + FOP_SKIP_REPORT_NOTIFY | FOP_TO_TAIL);
> }
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
next prev parent reply other threads:[~2020-09-28 20:38 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-28 18:21 [PATCH v1 0/5] mm: place pages to the freelist tail when onling and undoing isolation David Hildenbrand
2020-09-28 18:21 ` [PATCH v1 1/5] mm/page_alloc: convert "report" flag of __free_one_page() to a proper flag David Hildenbrand
2020-09-28 20:11 ` Pankaj Gupta
2020-09-29 8:58 ` Wei Yang
2020-10-02 13:17 ` Michal Hocko
2020-10-02 13:41 ` Matthew Wilcox
2020-10-02 14:48 ` David Hildenbrand
2020-10-02 14:57 ` David Hildenbrand
2020-09-28 18:21 ` [PATCH v1 2/5] mm/page_alloc: place pages to tail in __putback_isolated_page() David Hildenbrand
2020-09-28 20:38 ` Pankaj Gupta [this message]
2020-09-29 9:10 ` Wei Yang
2020-10-02 13:19 ` Michal Hocko
2020-09-28 18:21 ` [PATCH v1 3/5] mm/page_alloc: always move pages to the tail of the freelist in unset_migratetype_isolate() David Hildenbrand
2020-09-28 20:55 ` Pankaj Gupta
2020-09-29 9:18 ` Wei Yang
2020-09-29 10:12 ` David Hildenbrand
2020-09-30 7:48 ` Wei Yang
2020-10-02 13:24 ` Michal Hocko
2020-10-02 15:20 ` David Hildenbrand
2020-10-05 6:56 ` Michal Hocko
2020-10-05 8:20 ` Mel Gorman
2020-10-05 9:11 ` David Hildenbrand
2020-09-28 18:21 ` [PATCH v1 4/5] mm/page_alloc: place pages to tail in __free_pages_core() David Hildenbrand
2020-09-28 20:33 ` Pankaj Gupta
2020-09-29 9:36 ` Wei Yang
2020-09-29 10:14 ` David Hildenbrand
2020-10-02 13:41 ` Michal Hocko
2020-10-02 15:10 ` David Hildenbrand
2020-09-28 18:21 ` [PATCH v1 5/5] mm/memory_hotplug: update comment regarding zone shuffling David Hildenbrand
2020-09-29 9:40 ` Wei Yang
2020-10-02 13:41 ` Michal Hocko
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='CAM9Jb+iitZzZeF5b8eCWoR7fD=D3t76YDRaYsBC1o8nx-2jEYA@mail.gmail.com' \
--to=pankaj.gupta.linux@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=alexander.h.duyck@linux.intel.com \
--cc=cheloha@linux.ibm.com \
--cc=dave.hansen@intel.com \
--cc=david@redhat.com \
--cc=linux-acpi@vger.kernel.org \
--cc=linux-hyperv@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@techsingularity.net \
--cc=mhocko@kernel.org \
--cc=mpe@ellerman.id.au \
--cc=osalvador@suse.de \
--cc=richard.weiyang@linux.alibaba.com \
--cc=rppt@kernel.org \
--cc=vbabka@suse.cz \
--cc=xen-devel@lists.xenproject.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).