> On Jul 15, 2026, at 14:11, Li Zhe <[email protected]> wrote:
>
> On 7/14/26 4:38 PM, Muchun Song wrote:
>>
>>
>> On 2026/7/9 19:25, Li Zhe wrote:
>>> memmap_init_zone_device() repeats nearly identical head-page
>>> initialization for each PFN. Prepare one reusable ZONE_DEVICE head-page
>>> template through the existing slow path, refresh the PFN-dependent
>>> fields in that template before each copy, and memcpy it into each
>>> destination page.
>>>
>>> The optimized path assigns _refcount through the copied template, so
>>> keep it disabled when the page_ref_set tracepoint is enabled.
>>>
>>> This patch accelerates head-page initialization. The pfns_per_compound
>>> == 1 case gets the full benefit here, compound tails are handled in the
>>> next patch.
>>>
>>> Tested in a VM with a 100 GB fsdax namespace device configured with
>>> map=dev on Intel Ice Lake server. This test exercises the nd_pmem rebind
>>> path (pfns_per_compound == 1).
>>>
>>> Test procedure:
>>> Rebind the nd_pmem driver 30 times and collect the memmap initialization
>>> time from the pr_debug() output of memmap_init_zone_device().
>>>
>>> Base(v7.2-rc1):
>>> First binding: 1456 ms
>>> Average of subsequent rebinds: 244.28 ms
>>>
>>> With this patch and its prerequisites applied:
>>> First binding: 1440 ms
>>> Average of subsequent rebinds: 217.19 ms
>>>
>>> This reduces the average rebind time from 244.28 ms to 217.19 ms, or
>>> about 11%.
>>>
>>> Signed-off-by: Li Zhe <[email protected]>
>>> ---
>>> mm/mm_init.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++++-
>>> 1 file changed, 58 insertions(+), 1 deletion(-)
>>>
>>> diff --git a/mm/mm_init.c b/mm/mm_init.c
>>> index 5fccfbacf855..170021e182e0 100644
>>> --- a/mm/mm_init.c
>>> +++ b/mm/mm_init.c
>>> @@ -1065,6 +1065,44 @@ static void __ref
>>> zone_device_page_init_slow(struct page *page,
>>> set_page_count(page, 0);
>>> }
>>> +static inline bool zone_device_page_init_optimization_enabled(void)
>>> +{
>>> + /*
>>> + * The template fast path copies a preinitialized struct page
>>> image.
>>> + * Skip it when the page_ref_set tracepoint is enabled.
>>> + */
>>> + return !page_ref_tracepoint_active(page_ref_set);
>>
>> I'm not sure why we need to make this. I think we can go ahead and
>> perform this optimization unconditionally.
>>
>> If we look at why the tracepoint was added in the first place, it's
>> clear that its primary purpose is for debugging, particularly regarding
>> why CMA memory pages cannot be allocated (see commit 95813b8faa0). But
>> at this stage, the struct page hasn't even been initialized yet; we
>> are currently in the middle of initialization. From the perspective of
>> the page being initialized, the user doesn't need to care at all about
>> how the reference count is changing. Therefore, I don't think we need to
>> include these checks. It would only increase the complexity of the code.
>>
>> I suggest deleting this section of code to keep things simple.
>>
>> Thanks.
>
> I would prefer to keep this check.
>
> When page_ref_set debugging is enabled, preserving the existing per-page
> set_page_count() behavior is still useful, including during
> initialization, because it keeps the debug trace complete and unchanged.
When you say 'useful,' what aspects are you referring to?
>
> In the normal case, page_ref_set is off by default, so this only affects
> an explicit debugging configuration and leaves the production fast path
> unchanged. The extra logic here is also fairly small and stays local to
> this optimization path.
I know there's no real overhead here. The point I'm actually trying to make
is that since deleting the code has no impact, why not go with the simpler
approach?
Thanks.
>
> Thanks,
> Zhe
>
>>> +}
>>> +
>>> +/*
>>> + * 'template' is a reusable page prototype rather than a strictly
>>> immutable
>>> + * object. Most ZONE_DEVICE fields stay constant across the pages
>>> covered by
>>> + * the current template, but section bits and page->virtual may
>>> still depend
>>> + * on the PFN. Refresh those PFN-dependent fields in the template
>>> before
>>> + * copying it into @page.
>>> + */
>>> +static inline void zone_device_page_update_template(struct page
>>> *template,
>>> + unsigned long pfn)
>>> +{
>>> + set_page_section_from_pfn(template, pfn);
>>> +#ifdef WANT_PAGE_VIRTUAL
>>> + if (!is_highmem_idx(ZONE_DEVICE))
>>> + set_page_address(template, __va(pfn << PAGE_SHIFT));
>>> +#endif
>>> +}
>>> +
>>> +static void zone_device_page_init_from_template(struct page *page,
>>> + unsigned long pfn, struct page *template)
>>> +{
>>> + /*
>>> + * 'template' carries the invariant portion of a ZONE_DEVICE struct
>>> + * page. Update the PFN-dependent fields in place before copying it
>>> + * to the destination page.
>>> + */
>>> + zone_device_page_update_template(template, pfn);
>>> + memcpy(page, template, sizeof(*page));
>>> +}
>>> +
>>> /*
>>> * With compound page geometry and when struct pages are stored in
>>> ram most
>>> * tail pages are reused. Consequently, the amount of unique struct
>>> pages to
>>> @@ -1120,6 +1158,7 @@ void __ref memmap_init_zone_device(struct zone
>>> *zone,
>>> unsigned long nr_pages,
>>> struct dev_pagemap *pgmap)
>>> {
>>> + bool use_template = zone_device_page_init_optimization_enabled();
>>> unsigned long pfn, end_pfn = start_pfn + nr_pages;
>>> struct pglist_data *pgdat = zone->zone_pgdat;
>>> struct vmem_altmap *altmap = pgmap_altmap(pgmap);
>>> @@ -1127,6 +1166,7 @@ void __ref memmap_init_zone_device(struct zone
>>> *zone,
>>> unsigned long zone_idx = zone_idx(zone);
>>> unsigned long start = jiffies;
>>> int nid = pgdat->node_id;
>>> + struct page template;
>>>
>>> if (WARN_ON_ONCE(!pgmap || zone_idx != ZONE_DEVICE))
>>> return;
>>> @@ -1144,7 +1184,24 @@ void __ref memmap_init_zone_device(struct zone
>>> *zone,
>>> for (pfn = start_pfn; pfn < end_pfn; pfn += pfns_per_compound) {
>>> struct page *page = pfn_to_page(pfn);
>>>
>>> - zone_device_page_init_slow(page, pfn, zone_idx, nid, pgmap);
>>> + if (!use_template) {
>>> + zone_device_page_init_slow(page, pfn, zone_idx,
>>> + nid, pgmap);
>>> + } else if (pfn == start_pfn) {
>>> + /*
>>> + * Seed the reusable head-page template from the
>>> + * first real struct page, because the existing
>>> + * page-init and pageblock helpers expect a real
>>> + * memmap entry rather than a stack object.
>>> + */
>>> + zone_device_page_init_slow(page, pfn, zone_idx,
>>> + nid, pgmap);
>>> + /* init template page */
>>> + memcpy(&template, page, sizeof(*page));
>>> + } else {
>>> + zone_device_page_init_from_template(page, pfn,
>>> + &template);
>>> + }
>>>
>>> if (IS_ALIGNED(pfn, PAGES_PER_SECTION))
>>> cond_resched();
>>> --
>>> 2.20.1
