Preserved pages are represented in the memblock reserved list, but page structs for pages in the reserved list are initialized early while boot is single threaded which means that a large number of preserved pages can impact boot time. To mitigate, defer initialization of preserved pages by skipping them when other reserved pages are initialized and initializing them later with a separate kernel thread.
Signed-off-by: Anthony Yznaga <[email protected]> --- arch/x86/mm/init_64.c | 1 - include/linux/mm.h | 2 +- mm/memblock.c | 10 ++++++++-- mm/page_alloc.c | 52 +++++++++++++++++++++++++++++++++++++++++++-------- 4 files changed, 53 insertions(+), 12 deletions(-) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 72662615977b..ae569ef6bd7d 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1245,7 +1245,6 @@ void __init mem_init(void) after_bootmem = 1; x86_init.hyper.init_after_bootmem(); - pkram_free_pgt(); totalram_pages_add(pkram_reserved_pages); /* * Must be done after boot memory is put on freelist, because here we diff --git a/include/linux/mm.h b/include/linux/mm.h index 5a323422d783..69b9cd08c721 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2297,7 +2297,7 @@ extern void free_highmem_page(struct page *page); extern void adjust_managed_page_count(struct page *page, long count); extern void mem_init_print_info(const char *str); -extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end); +extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid); /* Free the reserved page into the buddy system, so it gets managed. */ static inline void __free_reserved_page(struct page *page) diff --git a/mm/memblock.c b/mm/memblock.c index 33597f352dc0..5524edbaf691 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -2042,11 +2042,17 @@ static unsigned long __init free_low_memory_core_early(void) unsigned long count = 0; phys_addr_t start, end; u64 i; + enum memblock_flags exclude; memblock_clear_hotplug(0, -1); - for_each_reserved_mem_region(i, &start, &end) - reserve_bootmem_region(start, end); + if (IS_ENABLED(CONFIG_DEFERRED_STRUCT_PAGE_INIT)) + exclude = MEMBLOCK_PRESERVED; + else + exclude = MEMBLOCK_NONE; + + for_each_reserved_mem_range(i, 0, exclude, &start, &end, NULL) + reserve_bootmem_region(start, end, -1); /* * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 69827d4fa052..afd97b31725e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -68,6 +68,7 @@ #include <linux/lockdep.h> #include <linux/nmi.h> #include <linux/psi.h> +#include <linux/pkram.h> #include <asm/sections.h> #include <asm/tlbflush.h> @@ -1408,15 +1409,18 @@ static void __meminit __init_single_page(struct page *page, unsigned long pfn, } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT -static void __meminit init_reserved_page(unsigned long pfn) +static void __meminit init_reserved_page(unsigned long pfn, int nid) { pg_data_t *pgdat; - int nid, zid; + int zid; - if (!early_page_uninitialised(pfn)) - return; + if (nid == -1) { + if (!early_page_uninitialised(pfn)) + return; + + nid = early_pfn_to_nid(pfn); + } - nid = early_pfn_to_nid(pfn); pgdat = NODE_DATA(nid); for (zid = 0; zid < MAX_NR_ZONES; zid++) { @@ -1428,7 +1432,7 @@ static void __meminit init_reserved_page(unsigned long pfn) __init_single_page(pfn_to_page(pfn), pfn, zid, nid); } #else -static inline void init_reserved_page(unsigned long pfn) +static inline void init_reserved_page(unsigned long pfn, int nid) { } #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ @@ -1439,7 +1443,7 @@ static inline void init_reserved_page(unsigned long pfn) * marks the pages PageReserved. The remaining valid pages are later * sent to the buddy page allocator. */ -void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end) +void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid) { unsigned long start_pfn = PFN_DOWN(start); unsigned long end_pfn = PFN_UP(end); @@ -1448,7 +1452,7 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end) if (pfn_valid(start_pfn)) { struct page *page = pfn_to_page(start_pfn); - init_reserved_page(start_pfn); + init_reserved_page(start_pfn, nid); /* Avoid false-positive PageTail() */ INIT_LIST_HEAD(&page->lru); @@ -1876,6 +1880,34 @@ static int __init deferred_init_memmap(void *data) return 0; } +#ifdef CONFIG_PKRAM +static int __init deferred_init_preserved(void *dummy) +{ + unsigned long start = jiffies; + unsigned long nr_pages = 0; + phys_addr_t spa, epa; + int nid; + u64 i; + + for_each_reserved_mem_range(i, MEMBLOCK_PRESERVED, 0, &spa, &epa, &nid) { + reserve_bootmem_region(spa, epa, nid); + nr_pages += ((epa - spa) >> PAGE_SHIFT); + } + + pr_info("initialised %lu preserved pages in %ums\n", nr_pages, + jiffies_to_msecs(jiffies - start)); + + /* + * Free the preserved pages pagetable now that page structs are + * initialized. + */ + pkram_free_pgt(); + + pgdat_init_report_one_done(); + return 0; +} +#endif /* CONFIG_PKRAM */ + /* * If this zone has deferred pages, try to grow it by initializing enough * deferred pages to satisfy the allocation specified by order, rounded up to @@ -1985,6 +2017,10 @@ void __init page_alloc_init_late(void) /* There will be num_node_state(N_MEMORY) threads */ atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY)); +#ifdef CONFIG_PKRAM + atomic_inc(&pgdat_init_n_undone); + kthread_run(deferred_init_preserved, NULL, "pgdatainit_preserved"); +#endif for_each_node_state(nid, N_MEMORY) { kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid); } -- 2.13.3
