Re: [PATCH v5 4/8] mm: add a template-based fast path for zone-device page init

[Alistair Popple <apopple@nvidia.com>]

On 2026-07-01 at 19:05 +1000, Li Zhe <lizhe.67@bytedance.com> 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 <lizhe.67@bytedance.com>
> ---
>  mm/mm_init.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 74 insertions(+), 2 deletions(-)
> 
> diff --git a/mm/mm_init.c b/mm/mm_init.c
> index 4c7fad440c2a..cc8417951467 100644
> --- a/mm/mm_init.c
> +++ b/mm/mm_init.c
> @@ -1066,6 +1066,50 @@ 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);
> +}
> +
> +static inline void zone_device_template_page_init(struct page *template,
> +						  struct page *src)
> +{
> +	memcpy(template, src, sizeof(*template));

I'd drop this function and just open-code the memcpy as I think that ends up
being clearer and removes a naming confusion - I kept mixing up the purpose of
`zone_device_template_page_init` and `zone_device_page_init_from_template`

> +}
> +
> +/*
> + * '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
> @@ -1121,6 +1165,7 @@ 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);
> @@ -1128,6 +1173,7 @@ 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;
> @@ -1142,10 +1188,36 @@ void __ref memmap_init_zone_device(struct zone *zone,
>  		nr_pages = end_pfn - start_pfn;
>  	}
>  
> -	for (pfn = start_pfn; pfn < end_pfn; pfn += pfns_per_compound) {
> -		struct page *page = pfn_to_page(pfn);
> +
> +	if (!nr_pages)
> +		return;
> +
> +	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.
> +	 */
> +	if (use_template) {
> +		struct page *page = pfn_to_page(start_pfn);
>  
>  		zone_device_page_init_slow(page, pfn, zone_idx, nid, pgmap);
> +		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));
> +		pfn += pfns_per_compound;

I think it would be clearer and less error prone to not unroll the loop here.
Instead just initialise the template page and leave the for loop starting at
pfn = start_pfn and let it handle the rest of the steps. I can't imagine the
extra call to zone_deivce_page_init_from_template() would cause a noticable
perf impact.

It also avoids the obvious danger of someone updating the loop but missing the
unrolled version above.

 - Alistair

> +	}
> +
> +	for (; pfn < end_pfn; pfn += pfns_per_compound) {
> +		struct page *page = pfn_to_page(pfn);
> +
> +		if (use_template)
> +			zone_device_page_init_from_template(page, pfn,
> +							    &template);
> +		else
> +			zone_device_page_init_slow(page, pfn, zone_idx,
> +						   nid, pgmap);
>  
>  		if (IS_ALIGNED(pfn, PAGES_PER_SECTION))
>  			cond_resched();
> -- 
> 2.20.1