From: Alistair Popple <apopple@nvidia.com>
To: Li Zhe <lizhe.67@bytedance.com>
Cc: akpm@linux-foundation.org, arnd@arndb.de, bp@alien8.de,
dave.hansen@linux.intel.com, david@kernel.org, kees@kernel.org,
mingo@redhat.com, rppt@kernel.org, tglx@kernel.org,
linux-arch@vger.kernel.org, linux-hardening@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org, x86@kernel.org
Subject: Re: [PATCH v5 5/8] mm: extend the template fast path to zone-device compound tails
Date: Tue, 7 Jul 2026 13:09:01 +1000 [thread overview]
Message-ID: <akxtWBdz5XjoAAzF@nvdebian.thelocal> (raw)
In-Reply-To: <20260701090553.62691-6-lizhe.67@bytedance.com>
On 2026-07-01 at 19:05 +1000, Li Zhe <lizhe.67@bytedance.com> wrote...
> The template fast path from the previous patch only accelerates head
> pages. Compound tails in memmap_init_compound() still go through the
> slow path one by one.
>
> Build separate head and tail templates and reuse one prepared tail
> template across the tail pages in a compound range. Head pages preserve
> the existing refcount policy, while compound tails always start with a
> refcount of 0 after prep_compound_tail().
>
> This extends the template-copy fast path to pfns_per_compound > 1
> without changing the existing slow path. Tail-page PFN-dependent fields
> are refreshed in the reusable tail template before each copy.
>
> Tested in a VM with a 100 GB devdax namespace (align=2097152) on Intel
> Ice Lake server. This test exercises the dax_pmem rebind path and
> measures memmap initialization latency.
>
> Test procedure:
> Unbind and rebind the dax_pmem driver 30 times, collect memmap
> initialization time from the pr_debug() output of memmap_init_zone_device().
>
> Base(v7.2-rc1):
> First binding: 1462 ms
> Average of subsequent rebinds: 273.31 ms
>
> With this patch and its prerequisites applied:
> First binding: 1403 ms
> Average of subsequent rebinds: 244.37 ms
>
> This reduces the average rebind time from 273.31 ms to 244.37 ms, or
> about 10.6%.
>
> Signed-off-by: Li Zhe <lizhe.67@bytedance.com>
> ---
> mm/mm_init.c | 47 ++++++++++++++++++++++++++++++++++++++++-------
> 1 file changed, 40 insertions(+), 7 deletions(-)
>
> diff --git a/mm/mm_init.c b/mm/mm_init.c
> index cc8417951467..60794050bc07 100644
> --- a/mm/mm_init.c
> +++ b/mm/mm_init.c
> @@ -1081,6 +1081,16 @@ static inline void zone_device_template_page_init(struct page *template,
> memcpy(template, src, sizeof(*template));
> }
>
> +static inline void zone_device_tail_page_init(struct page *page,
> + unsigned long pfn, unsigned long zone_idx, int nid,
> + struct dev_pagemap *pgmap, const struct page *head,
> + unsigned int order)
> +{
> + zone_device_page_init_slow(page, pfn, zone_idx, nid, pgmap);
> + prep_compound_tail(page, head, order);
> + set_page_count(page, 0);
> +}
> +
> /*
> * 'template' is a reusable page prototype rather than a strictly immutable
> * object. Most ZONE_DEVICE fields stay constant across the pages covered by
> @@ -1138,10 +1148,12 @@ static void __ref memmap_init_compound(struct page *head,
> unsigned long head_pfn,
> unsigned long zone_idx, int nid,
> struct dev_pagemap *pgmap,
> - unsigned long nr_pages)
> + unsigned long nr_pages,
> + bool use_template)
> {
> unsigned long pfn, end_pfn = head_pfn + nr_pages;
> unsigned int order = pgmap->vmemmap_shift;
> + struct page template;
>
> /*
> * We have to initialize the pages, including setting up page links.
> @@ -1150,12 +1162,31 @@ static void __ref memmap_init_compound(struct page *head,
> * the pages in the same go.
> */
> __SetPageHead(head);
> - for (pfn = head_pfn + 1; pfn < end_pfn; pfn++) {
> +
> + pfn = head_pfn + 1;
> + /*
> + * All tails of the same compound page share the state established by
> + * prep_compound_tail(). Reuse one tail template for the whole range and
> + * refresh only the PFN-dependent fields in that template before each copy.
> + */
> + if (use_template) {
> struct page *page = pfn_to_page(pfn);
>
> - zone_device_page_init_slow(page, pfn, zone_idx, nid, pgmap);
> - prep_compound_tail(page, head, order);
> - set_page_count(page, 0);
> + zone_device_tail_page_init(page, pfn, zone_idx, nid,
> + pgmap, head, order);
> + zone_device_template_page_init(&template, page);
> + pfn++;
Similar comment as the previous patch - I think it's clearer to just init the
template page here as a separate step and not unroll the loop.
- Alistair
> + }
> +
> + for (; pfn < end_pfn; pfn++) {
> + struct page *page = pfn_to_page(pfn);
> +
> + if (use_template)
> + zone_device_page_init_from_template(page, pfn,
> + &template);
> + else
> + zone_device_tail_page_init(page, pfn, zone_idx, nid,
> + pgmap, head, order);
> }
> prep_compound_head(head, order);
> }
> @@ -1205,7 +1236,8 @@ void __ref memmap_init_zone_device(struct zone *zone,
> zone_device_template_page_init(&template, page);
> if (pfns_per_compound != 1)
> memmap_init_compound(page, pfn, zone_idx, nid, pgmap,
> - compound_nr_pages(start_pfn, altmap, pgmap));
> + compound_nr_pages(start_pfn, altmap, pgmap),
> + use_template);
> pfn += pfns_per_compound;
> }
>
> @@ -1226,7 +1258,8 @@ void __ref memmap_init_zone_device(struct zone *zone,
> continue;
>
> memmap_init_compound(page, pfn, zone_idx, nid, pgmap,
> - compound_nr_pages(pfn, altmap, pgmap));
> + compound_nr_pages(pfn, altmap, pgmap),
> + use_template);
> }
>
> pageblock_migratetype_init_range(start_pfn, nr_pages, MIGRATE_MOVABLE);
> --
> 2.20.1
>
next prev parent reply other threads:[~2026-07-07 3:09 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-01 9:05 [PATCH v5 0/8] mm: optimize zone-device memmap initialization Li Zhe
2026-07-01 9:05 ` [PATCH v5 1/8] mm: fix stale ZONE_DEVICE refcount comment Li Zhe
2026-07-06 9:11 ` David Hildenbrand (Arm)
2026-07-07 2:28 ` Alistair Popple
2026-07-01 9:05 ` [PATCH v5 2/8] mm: factor zone-device page init helpers out of __init_zone_device_page Li Zhe
2026-07-06 9:13 ` David Hildenbrand (Arm)
2026-07-06 11:50 ` Li Zhe
2026-07-06 13:47 ` David Hildenbrand (Arm)
2026-07-07 3:25 ` Li Zhe
2026-07-01 9:05 ` [PATCH v5 3/8] mm: add a set_page_section_from_pfn() helper Li Zhe
2026-07-06 9:15 ` David Hildenbrand (Arm)
2026-07-06 11:52 ` Li Zhe
2026-07-06 13:48 ` David Hildenbrand (Arm)
2026-07-07 3:26 ` Li Zhe
2026-07-01 9:05 ` [PATCH v5 4/8] mm: add a template-based fast path for zone-device page init Li Zhe
2026-07-03 14:06 ` Mike Rapoport
2026-07-06 7:45 ` Li Zhe
2026-07-07 3:06 ` Alistair Popple
2026-07-07 3:02 ` Alistair Popple
2026-07-01 9:05 ` [PATCH v5 5/8] mm: extend the template fast path to zone-device compound tails Li Zhe
2026-07-07 3:09 ` Alistair Popple [this message]
2026-07-01 9:05 ` [PATCH v5 6/8] string: introduce memcpy_nt() helpers Li Zhe
2026-07-06 9:18 ` David Hildenbrand (Arm)
2026-07-06 11:53 ` Li Zhe
2026-07-06 13:49 ` David Hildenbrand (Arm)
2026-07-07 3:28 ` Li Zhe
2026-07-01 9:05 ` [PATCH v5 7/8] x86/string: extend memcpy_flushcache() fixed-size fastpaths Li Zhe
2026-07-01 9:05 ` [PATCH v5 8/8] mm: use memcpy_nt() in zone-device template copies Li Zhe
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=akxtWBdz5XjoAAzF@nvdebian.thelocal \
--to=apopple@nvidia.com \
--cc=akpm@linux-foundation.org \
--cc=arnd@arndb.de \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=david@kernel.org \
--cc=kees@kernel.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-hardening@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lizhe.67@bytedance.com \
--cc=mingo@redhat.com \
--cc=rppt@kernel.org \
--cc=tglx@kernel.org \
--cc=x86@kernel.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