Re: [PATCH v6 4/8] mm: add a template-based fast path for zone-device page init

On 7/9/26 9:25 PM, 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);
> +}
> +
> +/*
> + * '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));

I wonder why the code updates the pfn in the template and then memcpy's page as
opposed to have a read-only template, copy that to the page and update the pfn
in the 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();

Balbir