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 <[email protected]> --- mm/mm_init.c | 40 +++++++++++++++++++++++++++++++++++----- 1 file changed, 35 insertions(+), 5 deletions(-) diff --git a/mm/mm_init.c b/mm/mm_init.c index 170021e182e0..fb855bb0437a 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1074,6 +1074,16 @@ static inline bool zone_device_page_init_optimization_enabled(void) return !page_ref_tracepoint_active(page_ref_set); } +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 @@ -1131,10 +1141,12 @@ 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. @@ -1143,12 +1155,29 @@ 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++) { 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); + if (!use_template) { + zone_device_tail_page_init(page, pfn, zone_idx, nid, + pgmap, head, order); + } else if (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. + */ + zone_device_tail_page_init(page, pfn, zone_idx, nid, + pgmap, head, order); + /* init template page */ + memcpy(&template, page, sizeof(*page)); + } else { + zone_device_page_init_from_template(page, pfn, + &template); + } } prep_compound_head(head, order); } @@ -1210,7 +1239,8 @@ 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
