From 7fef431be9c9ac255838a9578331567b9dba4477 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 15 Oct 2020 20:09:35 -0700 Subject: [PATCH] mm/page_alloc: place pages to tail in __free_pages_core() __free_pages_core() is used when exposing fresh memory to the buddy during system boot and when onlining memory in generic_online_page(). generic_online_page() is used in two cases: 1. Direct memory onlining in online_pages(). 2. Deferred memory onlining in memory-ballooning-like mechanisms (HyperV balloon and virtio-mem), when parts of a section are kept fake-offline to be fake-onlined later on. In 1, we already place pages to the tail of the freelist. Pages will be freed to MIGRATE_ISOLATE lists first and moved to the tail of the freelists via undo_isolate_page_range(). In 2, we currently don't implement a proper rule. In case of virtio-mem, where we currently always online MAX_ORDER - 1 pages, the pages will be placed to the HEAD of the freelist - undesireable. While the hyper-v balloon calls generic_online_page() with single pages, usually it will call it on successive single pages in a larger block. The pages are fresh, so place them to the tail of the freelist and avoid the PCP. In __free_pages_core(), remove the now superflouos call to set_page_refcounted() and add a comment regarding page initialization and the refcount. Note: In 2. we currently don't shuffle. If ever relevant (page shuffling is usually of limited use in virtualized environments), we might want to shuffle after a sequence of generic_online_page() calls in the relevant callers. Signed-off-by: David Hildenbrand Signed-off-by: Andrew Morton Reviewed-by: Vlastimil Babka Reviewed-by: Oscar Salvador Reviewed-by: Wei Yang Acked-by: Pankaj Gupta Acked-by: Michal Hocko Cc: Alexander Duyck Cc: Mel Gorman Cc: Dave Hansen Cc: Mike Rapoport Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Wei Liu Cc: Matthew Wilcox Cc: Michael Ellerman Cc: Michal Hocko Cc: Scott Cheloha Link: https://lkml.kernel.org/r/20201005121534.15649-5-david@redhat.com Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ea7b697bcf6c..3b032dac62e6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -275,7 +275,8 @@ bool pm_suspended_storage(void) unsigned int pageblock_order __read_mostly; #endif -static void __free_pages_ok(struct page *page, unsigned int order); +static void __free_pages_ok(struct page *page, unsigned int order, + fpi_t fpi_flags); /* * results with 256, 32 in the lowmem_reserve sysctl: @@ -687,7 +688,7 @@ out: void free_compound_page(struct page *page) { mem_cgroup_uncharge(page); - __free_pages_ok(page, compound_order(page)); + __free_pages_ok(page, compound_order(page), FPI_NONE); } void prep_compound_page(struct page *page, unsigned int order) @@ -1423,14 +1424,14 @@ static void free_pcppages_bulk(struct zone *zone, int count, static void free_one_page(struct zone *zone, struct page *page, unsigned long pfn, unsigned int order, - int migratetype) + int migratetype, fpi_t fpi_flags) { spin_lock(&zone->lock); if (unlikely(has_isolate_pageblock(zone) || is_migrate_isolate(migratetype))) { migratetype = get_pfnblock_migratetype(page, pfn); } - __free_one_page(page, pfn, zone, order, migratetype, FPI_NONE); + __free_one_page(page, pfn, zone, order, migratetype, fpi_flags); spin_unlock(&zone->lock); } @@ -1508,7 +1509,8 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end) } } -static void __free_pages_ok(struct page *page, unsigned int order) +static void __free_pages_ok(struct page *page, unsigned int order, + fpi_t fpi_flags) { unsigned long flags; int migratetype; @@ -1520,7 +1522,8 @@ static void __free_pages_ok(struct page *page, unsigned int order) migratetype = get_pfnblock_migratetype(page, pfn); local_irq_save(flags); __count_vm_events(PGFREE, 1 << order); - free_one_page(page_zone(page), page, pfn, order, migratetype); + free_one_page(page_zone(page), page, pfn, order, migratetype, + fpi_flags); local_irq_restore(flags); } @@ -1530,6 +1533,11 @@ void __free_pages_core(struct page *page, unsigned int order) struct page *p = page; unsigned int loop; + /* + * When initializing the memmap, __init_single_page() sets the refcount + * of all pages to 1 ("allocated"/"not free"). We have to set the + * refcount of all involved pages to 0. + */ prefetchw(p); for (loop = 0; loop < (nr_pages - 1); loop++, p++) { prefetchw(p + 1); @@ -1540,8 +1548,12 @@ void __free_pages_core(struct page *page, unsigned int order) set_page_count(p, 0); atomic_long_add(nr_pages, &page_zone(page)->managed_pages); - set_page_refcounted(page); - __free_pages(page, order); + + /* + * Bypass PCP and place fresh pages right to the tail, primarily + * relevant for memory onlining. + */ + __free_pages_ok(page, order, FPI_TO_TAIL); } #ifdef CONFIG_NEED_MULTIPLE_NODES @@ -3168,7 +3180,8 @@ static void free_unref_page_commit(struct page *page, unsigned long pfn) */ if (migratetype >= MIGRATE_PCPTYPES) { if (unlikely(is_migrate_isolate(migratetype))) { - free_one_page(zone, page, pfn, 0, migratetype); + free_one_page(zone, page, pfn, 0, migratetype, + FPI_NONE); return; } migratetype = MIGRATE_MOVABLE; @@ -4991,7 +5004,7 @@ static inline void free_the_page(struct page *page, unsigned int order) if (order == 0) /* Via pcp? */ free_unref_page(page); else - __free_pages_ok(page, order); + __free_pages_ok(page, order, FPI_NONE); } void __free_pages(struct page *page, unsigned int order)