X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=mm%2Fpage_alloc.c;h=a139339e9d75fde7f33dc7a30f978a91e72d9f75;hb=97bf2856c6014879bd04983a3e9dfcdac1e7fe85;hp=8d3f6f46105e828d235fe082d96fe35f21dbaac9;hpb=5273a3df6485dc2ad6aa7ddd441b9a21970f003b;p=linux-2.6.git diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8d3f6f461..a139339e9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -14,7 +14,6 @@ * (lots of bits borrowed from Ingo Molnar & Andrew Morton) */ -#include #include #include #include @@ -22,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -31,71 +31,183 @@ #include #include #include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include #include +#include +#include "internal.h" -DECLARE_BITMAP(node_online_map, MAX_NUMNODES); -struct pglist_data *pgdat_list; -unsigned long totalram_pages; -unsigned long totalhigh_pages; -int nr_swap_pages; -int numnodes = 1; -int sysctl_lower_zone_protection = 0; +/* + * MCD - HACK: Find somewhere to initialize this EARLY, or make this + * initializer cleaner + */ +nodemask_t node_online_map __read_mostly = { { [0] = 1UL } }; +EXPORT_SYMBOL(node_online_map); +nodemask_t node_possible_map __read_mostly = NODE_MASK_ALL; +EXPORT_SYMBOL(node_possible_map); +unsigned long totalram_pages __read_mostly; +unsigned long totalreserve_pages __read_mostly; +long nr_swap_pages; +int percpu_pagelist_fraction; -EXPORT_SYMBOL(totalram_pages); -EXPORT_SYMBOL(nr_swap_pages); +static void __free_pages_ok(struct page *page, unsigned int order); /* - * Used by page_zone() to look up the address of the struct zone whose - * id is encoded in the upper bits of page->flags + * results with 256, 32 in the lowmem_reserve sysctl: + * 1G machine -> (16M dma, 800M-16M normal, 1G-800M high) + * 1G machine -> (16M dma, 784M normal, 224M high) + * NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA + * HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL + * HIGHMEM allocation will (224M+784M)/256 of ram reserved in ZONE_DMA + * + * TBD: should special case ZONE_DMA32 machines here - in those we normally + * don't need any ZONE_NORMAL reservation */ -struct zone *zone_table[1 << (ZONES_SHIFT + NODES_SHIFT)]; -EXPORT_SYMBOL(zone_table); +int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { + 256, +#ifdef CONFIG_ZONE_DMA32 + 256, +#endif +#ifdef CONFIG_HIGHMEM + 32 +#endif +}; + +EXPORT_SYMBOL(totalram_pages); + +static char * const zone_names[MAX_NR_ZONES] = { + "DMA", +#ifdef CONFIG_ZONE_DMA32 + "DMA32", +#endif + "Normal", +#ifdef CONFIG_HIGHMEM + "HighMem" +#endif +}; -static char *zone_names[MAX_NR_ZONES] = { "DMA", "Normal", "HighMem" }; int min_free_kbytes = 1024; +unsigned long __meminitdata nr_kernel_pages; +unsigned long __meminitdata nr_all_pages; +static unsigned long __initdata dma_reserve; + +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP + /* + * MAX_ACTIVE_REGIONS determines the maxmimum number of distinct + * ranges of memory (RAM) that may be registered with add_active_range(). + * Ranges passed to add_active_range() will be merged if possible + * so the number of times add_active_range() can be called is + * related to the number of nodes and the number of holes + */ + #ifdef CONFIG_MAX_ACTIVE_REGIONS + /* Allow an architecture to set MAX_ACTIVE_REGIONS to save memory */ + #define MAX_ACTIVE_REGIONS CONFIG_MAX_ACTIVE_REGIONS + #else + #if MAX_NUMNODES >= 32 + /* If there can be many nodes, allow up to 50 holes per node */ + #define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50) + #else + /* By default, allow up to 256 distinct regions */ + #define MAX_ACTIVE_REGIONS 256 + #endif + #endif + + struct node_active_region __initdata early_node_map[MAX_ACTIVE_REGIONS]; + int __initdata nr_nodemap_entries; + unsigned long __initdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES]; + unsigned long __initdata arch_zone_highest_possible_pfn[MAX_NR_ZONES]; +#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE + unsigned long __initdata node_boundary_start_pfn[MAX_NUMNODES]; + unsigned long __initdata node_boundary_end_pfn[MAX_NUMNODES]; +#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */ +#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ + +#ifdef CONFIG_DEBUG_VM +static int page_outside_zone_boundaries(struct zone *zone, struct page *page) +{ + int ret = 0; + unsigned seq; + unsigned long pfn = page_to_pfn(page); + + do { + seq = zone_span_seqbegin(zone); + if (pfn >= zone->zone_start_pfn + zone->spanned_pages) + ret = 1; + else if (pfn < zone->zone_start_pfn) + ret = 1; + } while (zone_span_seqretry(zone, seq)); + + return ret; +} + +static int page_is_consistent(struct zone *zone, struct page *page) +{ +#ifdef CONFIG_HOLES_IN_ZONE + if (!pfn_valid(page_to_pfn(page))) + return 0; +#endif + if (zone != page_zone(page)) + return 0; + + return 1; +} /* * Temporary debugging check for pages not lying within a given zone. */ static int bad_range(struct zone *zone, struct page *page) { - if (page_to_pfn(page) >= zone->zone_start_pfn + zone->spanned_pages) - return 1; - if (page_to_pfn(page) < zone->zone_start_pfn) + if (page_outside_zone_boundaries(zone, page)) return 1; - if (zone != page_zone(page)) + if (!page_is_consistent(zone, page)) return 1; + return 0; } +#else +static inline int bad_range(struct zone *zone, struct page *page) +{ + return 0; +} +#endif -static void bad_page(const char *function, struct page *page) +static void bad_page(struct page *page) { - printk(KERN_EMERG "Bad page state at %s (in process '%s', page %p)\n", - function, current->comm, page); - printk(KERN_EMERG "flags:0x%08lx mapping:%p mapped:%d count:%d\n", + printk(KERN_EMERG "Bad page state in process '%s'\n" + KERN_EMERG "page:%p flags:0x%0*lx mapping:%p mapcount:%d count:%d (%s)\n" + KERN_EMERG "Trying to fix it up, but a reboot is needed\n" + KERN_EMERG "Backtrace:\n", + current->comm, page, (int)(2*sizeof(unsigned long)), (unsigned long)page->flags, page->mapping, - page_mapped(page), page_count(page)); - printk(KERN_EMERG "Backtrace:\n"); + page_mapcount(page), page_count(page), print_tainted()); dump_stack(); - printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n"); - page->flags &= ~(1 << PG_private | + page->flags &= ~(1 << PG_lru | + 1 << PG_private | 1 << PG_locked | - 1 << PG_lru | 1 << PG_active | 1 << PG_dirty | - 1 << PG_maplock | - 1 << PG_anon | + 1 << PG_reclaim | + 1 << PG_slab | 1 << PG_swapcache | - 1 << PG_writeback); + 1 << PG_writeback | + 1 << PG_buddy ); set_page_count(page, 0); + reset_page_mapcount(page); page->mapping = NULL; + add_taint(TAINT_BAD_PAGE); } -#ifndef CONFIG_HUGETLB_PAGE -#define prep_compound_page(page, order) do { } while (0) -#define destroy_compound_page(page, order) do { } while (0) -#else /* * Higher-order pages are called "compound pages". They are structured thusly: * @@ -106,25 +218,28 @@ static void bad_page(const char *function, struct page *page) * All pages have PG_compound set. All pages have their ->private pointing at * the head page (even the head page has this). * - * The first tail page's ->mapping, if non-zero, holds the address of the - * compound page's put_page() function. - * - * The order of the allocation is stored in the first tail page's ->index - * This is only for debug at present. This usage means that zero-order pages - * may not be compound. + * The first tail page's ->lru.next holds the address of the compound page's + * put_page() function. Its ->lru.prev holds the order of allocation. + * This usage means that zero-order pages may not be compound. */ + +static void free_compound_page(struct page *page) +{ + __free_pages_ok(page, (unsigned long)page[1].lru.prev); +} + static void prep_compound_page(struct page *page, unsigned long order) { int i; int nr_pages = 1 << order; - page[1].mapping = 0; - page[1].index = order; + set_compound_page_dtor(page, free_compound_page); + page[1].lru.prev = (void *)order; for (i = 0; i < nr_pages; i++) { struct page *p = page + i; - SetPageCompound(p); - p->private = (unsigned long)page; + __SetPageCompound(p); + set_page_private(p, (unsigned long)page); } } @@ -133,23 +248,116 @@ static void destroy_compound_page(struct page *page, unsigned long order) int i; int nr_pages = 1 << order; - if (!PageCompound(page)) - return; - - if (page[1].index != order) - bad_page(__FUNCTION__, page); + if (unlikely((unsigned long)page[1].lru.prev != order)) + bad_page(page); for (i = 0; i < nr_pages; i++) { struct page *p = page + i; - if (!PageCompound(p)) - bad_page(__FUNCTION__, page); - if (p->private != (unsigned long)page) - bad_page(__FUNCTION__, page); - ClearPageCompound(p); + if (unlikely(!PageCompound(p) | + (page_private(p) != (unsigned long)page))) + bad_page(page); + __ClearPageCompound(p); + } +} + +static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags) +{ + int i; + + VM_BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM); + /* + * clear_highpage() will use KM_USER0, so it's a bug to use __GFP_ZERO + * and __GFP_HIGHMEM from hard or soft interrupt context. + */ + VM_BUG_ON((gfp_flags & __GFP_HIGHMEM) && in_interrupt()); + for (i = 0; i < (1 << order); i++) + clear_highpage(page + i); +} + +/* + * function for dealing with page's order in buddy system. + * zone->lock is already acquired when we use these. + * So, we don't need atomic page->flags operations here. + */ +static inline unsigned long page_order(struct page *page) +{ + return page_private(page); +} + +static inline void set_page_order(struct page *page, int order) +{ + set_page_private(page, order); + __SetPageBuddy(page); +} + +static inline void rmv_page_order(struct page *page) +{ + __ClearPageBuddy(page); + set_page_private(page, 0); +} + +/* + * Locate the struct page for both the matching buddy in our + * pair (buddy1) and the combined O(n+1) page they form (page). + * + * 1) Any buddy B1 will have an order O twin B2 which satisfies + * the following equation: + * B2 = B1 ^ (1 << O) + * For example, if the starting buddy (buddy2) is #8 its order + * 1 buddy is #10: + * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 + * + * 2) Any buddy B will have an order O+1 parent P which + * satisfies the following equation: + * P = B & ~(1 << O) + * + * Assumption: *_mem_map is contiguous at least up to MAX_ORDER + */ +static inline struct page * +__page_find_buddy(struct page *page, unsigned long page_idx, unsigned int order) +{ + unsigned long buddy_idx = page_idx ^ (1 << order); + + return page + (buddy_idx - page_idx); +} + +static inline unsigned long +__find_combined_index(unsigned long page_idx, unsigned int order) +{ + return (page_idx & ~(1 << order)); +} + +/* + * This function checks whether a page is free && is the buddy + * we can do coalesce a page and its buddy if + * (a) the buddy is not in a hole && + * (b) the buddy is in the buddy system && + * (c) a page and its buddy have the same order && + * (d) a page and its buddy are in the same zone. + * + * For recording whether a page is in the buddy system, we use PG_buddy. + * Setting, clearing, and testing PG_buddy is serialized by zone->lock. + * + * For recording page's order, we use page_private(page). + */ +static inline int page_is_buddy(struct page *page, struct page *buddy, + int order) +{ +#ifdef CONFIG_HOLES_IN_ZONE + if (!pfn_valid(page_to_pfn(buddy))) + return 0; +#endif + + if (page_zone_id(page) != page_zone_id(buddy)) + return 0; + + if (PageBuddy(buddy) && page_order(buddy) == order) { + BUG_ON(page_count(buddy) != 0); + return 1; } + return 0; } -#endif /* CONFIG_HUGETLB_PAGE */ /* * Freeing function for a buddy system allocator. @@ -163,9 +371,10 @@ static void destroy_compound_page(struct page *page, unsigned long order) * at the bottom level available, and propagating the changes upward * as necessary, plus some accounting needed to play nicely with other * parts of the VM system. - * At each level, we keep one bit for each pair of blocks, which - * is set to 1 iff only one of the pair is allocated. So when we - * are allocating or freeing one, we can derive the state of the + * At each level, we keep a list of pages, which are heads of continuous + * free pages of length of (1 << order) and marked with PG_buddy. Page's + * order is recorded in page_private(page) field. + * So when we are allocating or freeing one, we can derive the state of the * other. That is, if we allocate a small block, and both were * free, the remainder of the region must be split into blocks. * If a block is freed, and its buddy is also free, then this @@ -174,52 +383,49 @@ static void destroy_compound_page(struct page *page, unsigned long order) * -- wli */ -static inline void __free_pages_bulk (struct page *page, struct page *base, - struct zone *zone, struct free_area *area, unsigned long mask, - unsigned int order) +static inline void __free_one_page(struct page *page, + struct zone *zone, unsigned int order) { - unsigned long page_idx, index; + unsigned long page_idx; + int order_size = 1 << order; - if (order) + if (unlikely(PageCompound(page))) destroy_compound_page(page, order); - page_idx = page - base; - if (page_idx & ~mask) - BUG(); - index = page_idx >> (1 + order); - zone->free_pages -= mask; - while (mask + (1 << (MAX_ORDER-1))) { - struct page *buddy1, *buddy2; - - BUG_ON(area >= zone->free_area + MAX_ORDER); - if (!__test_and_change_bit(index, area->map)) - /* - * the buddy page is still allocated. - */ - break; - /* - * Move the buddy up one level. - * This code is taking advantage of the identity: - * -mask = 1+~mask - */ - buddy1 = base + (page_idx ^ -mask); - buddy2 = base + page_idx; - BUG_ON(bad_range(zone, buddy1)); - BUG_ON(bad_range(zone, buddy2)); - list_del(&buddy1->lru); - mask <<= 1; - area++; - index >>= 1; - page_idx &= mask; + page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); + + VM_BUG_ON(page_idx & (order_size - 1)); + VM_BUG_ON(bad_range(zone, page)); + + zone->free_pages += order_size; + while (order < MAX_ORDER-1) { + unsigned long combined_idx; + struct free_area *area; + struct page *buddy; + + buddy = __page_find_buddy(page, page_idx, order); + if (!page_is_buddy(page, buddy, order)) + break; /* Move the buddy up one level. */ + + list_del(&buddy->lru); + area = zone->free_area + order; + area->nr_free--; + rmv_page_order(buddy); + combined_idx = __find_combined_index(page_idx, order); + page = page + (combined_idx - page_idx); + page_idx = combined_idx; + order++; } - list_add(&(base + page_idx)->lru, &area->free_list); + set_page_order(page, order); + list_add(&page->lru, &zone->free_area[order].free_list); + zone->free_area[order].nr_free++; } -static inline void free_pages_check(const char *function, struct page *page) +static inline int free_pages_check(struct page *page) { - if ( page_mapped(page) || - page->mapping != NULL || - page_count(page) != 0 || + if (unlikely(page_mapcount(page) | + (page->mapping != NULL) | + (page_count(page) != 0) | (page->flags & ( 1 << PG_lru | 1 << PG_private | @@ -227,19 +433,25 @@ static inline void free_pages_check(const char *function, struct page *page) 1 << PG_active | 1 << PG_reclaim | 1 << PG_slab | - 1 << PG_maplock | - 1 << PG_anon | 1 << PG_swapcache | - 1 << PG_writeback ))) - bad_page(function, page); + 1 << PG_writeback | + 1 << PG_reserved | + 1 << PG_buddy )))) + bad_page(page); if (PageDirty(page)) - ClearPageDirty(page); + __ClearPageDirty(page); + /* + * For now, we report if PG_reserved was found set, but do not + * clear it, and do not free the page. But we shall soon need + * to do more, for when the ZERO_PAGE count wraps negative. + */ + return PageReserved(page); } /* * Frees a list of pages. * Assumes all pages on list are in same zone, and of same order. - * count is the number of pages to free, or 0 for all on the list. + * count is the number of pages to free. * * If the zone was previously in an "all pages pinned" state then look to * see if this freeing clears that state. @@ -247,107 +459,160 @@ static inline void free_pages_check(const char *function, struct page *page) * And clear the zone's pages_scanned counter, to hold off the "all pages are * pinned" detection logic. */ -static int -free_pages_bulk(struct zone *zone, int count, - struct list_head *list, unsigned int order) +static void free_pages_bulk(struct zone *zone, int count, + struct list_head *list, int order) { - unsigned long mask, flags; - struct free_area *area; - struct page *base, *page = NULL; - int ret = 0; - - mask = (~0UL) << order; - base = zone->zone_mem_map; - area = zone->free_area + order; - spin_lock_irqsave(&zone->lock, flags); + spin_lock(&zone->lock); zone->all_unreclaimable = 0; zone->pages_scanned = 0; - while (!list_empty(list) && count--) { + while (count--) { + struct page *page; + + VM_BUG_ON(list_empty(list)); page = list_entry(list->prev, struct page, lru); - /* have to delete it as __free_pages_bulk list manipulates */ + /* have to delete it as __free_one_page list manipulates */ list_del(&page->lru); - __free_pages_bulk(page, base, zone, area, mask, order); - ret++; + __free_one_page(page, zone, order); } - spin_unlock_irqrestore(&zone->lock, flags); - return ret; + spin_unlock(&zone->lock); +} + +static void free_one_page(struct zone *zone, struct page *page, int order) +{ + spin_lock(&zone->lock); + zone->all_unreclaimable = 0; + zone->pages_scanned = 0; + __free_one_page(page, zone, order); + spin_unlock(&zone->lock); } -void __free_pages_ok(struct page *page, unsigned int order) +static void __free_pages_ok(struct page *page, unsigned int order) { - LIST_HEAD(list); + unsigned long flags; int i; + int reserved = 0; - mod_page_state(pgfree, 1 << order); + if (arch_free_page(page, order)) + return; for (i = 0 ; i < (1 << order) ; ++i) - free_pages_check(__FUNCTION__, page + i); - list_add(&page->lru, &list); - kernel_map_pages(page, 1<> (1+(order)), (area)->map) +/* + * permit the bootmem allocator to evade page validation on high-order frees + */ +void fastcall __init __free_pages_bootmem(struct page *page, unsigned int order) +{ + if (order == 0) { + __ClearPageReserved(page); + set_page_count(page, 0); + set_page_refcounted(page); + __free_page(page); + } else { + int loop; + + prefetchw(page); + for (loop = 0; loop < BITS_PER_LONG; loop++) { + struct page *p = &page[loop]; + + if (loop + 1 < BITS_PER_LONG) + prefetchw(p + 1); + __ClearPageReserved(p); + set_page_count(p, 0); + } -static inline struct page * -expand(struct zone *zone, struct page *page, - unsigned long index, int low, int high, struct free_area *area) + set_page_refcounted(page); + __free_pages(page, order); + } +} + + +/* + * The order of subdivision here is critical for the IO subsystem. + * Please do not alter this order without good reasons and regression + * testing. Specifically, as large blocks of memory are subdivided, + * the order in which smaller blocks are delivered depends on the order + * they're subdivided in this function. This is the primary factor + * influencing the order in which pages are delivered to the IO + * subsystem according to empirical testing, and this is also justified + * by considering the behavior of a buddy system containing a single + * large block of memory acted on by a series of small allocations. + * This behavior is a critical factor in sglist merging's success. + * + * -- wli + */ +static inline void expand(struct zone *zone, struct page *page, + int low, int high, struct free_area *area) { unsigned long size = 1 << high; while (high > low) { - BUG_ON(bad_range(zone, page)); area--; high--; size >>= 1; - list_add(&page->lru, &area->free_list); - MARK_USED(index, high, area); - index += size; - page += size; + VM_BUG_ON(bad_range(zone, &page[size])); + list_add(&page[size].lru, &area->free_list); + area->nr_free++; + set_page_order(&page[size], high); } - return page; -} - -static inline void set_page_refs(struct page *page, int order) -{ -#ifdef CONFIG_MMU - set_page_count(page, 1); -#else - int i; - - /* - * We need to reference all the pages for this order, otherwise if - * anyone accesses one of the pages with (get/put) it will be freed. - */ - for (i = 0; i < (1 << order); i++) - set_page_count(page+i, 1); -#endif /* CONFIG_MMU */ } /* * This page is about to be returned from the page allocator */ -static void prep_new_page(struct page *page, int order) +static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) { - if (page->mapping || page_mapped(page) || - (page->flags & ( + if (unlikely(page_mapcount(page) | + (page->mapping != NULL) | + (page_count(page) != 0) | + (page->flags & ( + 1 << PG_lru | 1 << PG_private | 1 << PG_locked | - 1 << PG_lru | 1 << PG_active | 1 << PG_dirty | 1 << PG_reclaim | - 1 << PG_maplock | - 1 << PG_anon | + 1 << PG_slab | 1 << PG_swapcache | - 1 << PG_writeback ))) - bad_page(__FUNCTION__, page); + 1 << PG_writeback | + 1 << PG_reserved | + 1 << PG_buddy )))) + bad_page(page); + + /* + * For now, we report if PG_reserved was found set, but do not + * clear it, and do not allocate the page: as a safety net. + */ + if (PageReserved(page)) + return 1; page->flags &= ~(1 << PG_uptodate | 1 << PG_error | 1 << PG_referenced | 1 << PG_arch_1 | 1 << PG_checked | 1 << PG_mappedtodisk); - page->private = 0; - set_page_refs(page, order); + set_page_private(page, 0); + set_page_refcounted(page); + + arch_alloc_page(page, order); + kernel_map_pages(page, 1 << order, 1); + + if (gfp_flags & __GFP_ZERO) + prep_zero_page(page, order, gfp_flags); + + if (order && (gfp_flags & __GFP_COMP)) + prep_compound_page(page, order); + + return 0; } /* @@ -359,7 +624,6 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order) struct free_area * area; unsigned int current_order; struct page *page; - unsigned int index; for (current_order = order; current_order < MAX_ORDER; ++current_order) { area = zone->free_area + current_order; @@ -368,11 +632,11 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order) page = list_entry(area->free_list.next, struct page, lru); list_del(&page->lru); - index = page - zone->zone_mem_map; - if (current_order != MAX_ORDER-1) - MARK_USED(index, current_order, area); + rmv_page_order(page); + area->nr_free--; zone->free_pages -= 1UL << order; - return expand(zone, page, index, order, current_order, area); + expand(zone, page, order, current_order, area); + return page; } return NULL; @@ -386,65 +650,119 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order) static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list) { - unsigned long flags; int i; - int allocated = 0; - struct page *page; - spin_lock_irqsave(&zone->lock, flags); + spin_lock(&zone->lock); for (i = 0; i < count; ++i) { - page = __rmqueue(zone, order); - if (page == NULL) + struct page *page = __rmqueue(zone, order); + if (unlikely(page == NULL)) break; - allocated++; list_add_tail(&page->lru, list); } - spin_unlock_irqrestore(&zone->lock, flags); - return allocated; + spin_unlock(&zone->lock); + return i; +} + +#ifdef CONFIG_NUMA +/* + * Called from the slab reaper to drain pagesets on a particular node that + * belongs to the currently executing processor. + * Note that this function must be called with the thread pinned to + * a single processor. + */ +void drain_node_pages(int nodeid) +{ + int i; + enum zone_type z; + unsigned long flags; + + for (z = 0; z < MAX_NR_ZONES; z++) { + struct zone *zone = NODE_DATA(nodeid)->node_zones + z; + struct per_cpu_pageset *pset; + + if (!populated_zone(zone)) + continue; + + pset = zone_pcp(zone, smp_processor_id()); + for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) { + struct per_cpu_pages *pcp; + + pcp = &pset->pcp[i]; + if (pcp->count) { + int to_drain; + + local_irq_save(flags); + if (pcp->count >= pcp->batch) + to_drain = pcp->batch; + else + to_drain = pcp->count; + free_pages_bulk(zone, to_drain, &pcp->list, 0); + pcp->count -= to_drain; + local_irq_restore(flags); + } + } + } } +#endif -#if defined(CONFIG_PM) || defined(CONFIG_HOTPLUG_CPU) static void __drain_pages(unsigned int cpu) { + unsigned long flags; struct zone *zone; int i; for_each_zone(zone) { struct per_cpu_pageset *pset; - pset = &zone->pageset[cpu]; + if (!populated_zone(zone)) + continue; + + pset = zone_pcp(zone, cpu); for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) { struct per_cpu_pages *pcp; pcp = &pset->pcp[i]; - pcp->count -= free_pages_bulk(zone, pcp->count, - &pcp->list, 0); + local_irq_save(flags); + free_pages_bulk(zone, pcp->count, &pcp->list, 0); + pcp->count = 0; + local_irq_restore(flags); } } } -#endif /* CONFIG_PM || CONFIG_HOTPLUG_CPU */ #ifdef CONFIG_PM -int is_head_of_free_region(struct page *page) + +void mark_free_pages(struct zone *zone) { - struct zone *zone = page_zone(page); - unsigned long flags; + unsigned long pfn, max_zone_pfn; + unsigned long flags; int order; struct list_head *curr; - /* - * Should not matter as we need quiescent system for - * suspend anyway, but... - */ + if (!zone->spanned_pages) + return; + spin_lock_irqsave(&zone->lock, flags); + + max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages; + for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) + if (pfn_valid(pfn)) { + struct page *page = pfn_to_page(pfn); + + if (!PageNosave(page)) + ClearPageNosaveFree(page); + } + for (order = MAX_ORDER - 1; order >= 0; --order) - list_for_each(curr, &zone->free_area[order].free_list) - if (page == list_entry(curr, struct page, lru)) { - spin_unlock_irqrestore(&zone->lock, flags); - return 1 << order; - } + list_for_each(curr, &zone->free_area[order].free_list) { + unsigned long i; + + pfn = page_to_pfn(list_entry(curr, struct page, lru)); + for (i = 0; i < (1UL << order); i++) + SetPageNosaveFree(pfn_to_page(pfn + i)); + } + spin_unlock_irqrestore(&zone->lock, flags); - return 0; } /* @@ -463,22 +781,34 @@ void drain_local_pages(void) /* * Free a 0-order page */ -static void FASTCALL(free_hot_cold_page(struct page *page, int cold)); static void fastcall free_hot_cold_page(struct page *page, int cold) { struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; unsigned long flags; + if (arch_free_page(page, 0)) + return; + + if (PageAnon(page)) + page->mapping = NULL; + if (free_pages_check(page)) + return; + + if (!PageHighMem(page)) + debug_check_no_locks_freed(page_address(page), PAGE_SIZE); + arch_free_page(page, 0); kernel_map_pages(page, 1, 0); - inc_page_state(pgfree); - free_pages_check(__FUNCTION__, page); - pcp = &zone->pageset[get_cpu()].pcp[cold]; + + pcp = &zone_pcp(zone, get_cpu())->pcp[cold]; local_irq_save(flags); - if (pcp->count >= pcp->high) - pcp->count -= free_pages_bulk(zone, pcp->batch, &pcp->list, 0); + __count_vm_event(PGFREE); list_add(&page->lru, &pcp->list); pcp->count++; + if (pcp->count >= pcp->high) { + free_pages_bulk(zone, pcp->batch, &pcp->list, 0); + pcp->count -= pcp->batch; + } local_irq_restore(flags); put_cpu(); } @@ -493,145 +823,489 @@ void fastcall free_cold_page(struct page *page) free_hot_cold_page(page, 1); } +/* + * split_page takes a non-compound higher-order page, and splits it into + * n (1< 0 path. Saves a branch * or two. */ - -static struct page * -buffered_rmqueue(struct zone *zone, int order, int gfp_flags) +static struct page *buffered_rmqueue(struct zonelist *zonelist, + struct zone *zone, int order, gfp_t gfp_flags) { unsigned long flags; - struct page *page = NULL; + struct page *page; int cold = !!(gfp_flags & __GFP_COLD); + int cpu; - if (order == 0) { +again: + cpu = get_cpu(); + if (likely(order == 0)) { struct per_cpu_pages *pcp; - pcp = &zone->pageset[get_cpu()].pcp[cold]; + pcp = &zone_pcp(zone, cpu)->pcp[cold]; local_irq_save(flags); - if (pcp->count <= pcp->low) - pcp->count += rmqueue_bulk(zone, 0, + if (!pcp->count) { + pcp->count = rmqueue_bulk(zone, 0, pcp->batch, &pcp->list); - if (pcp->count) { - page = list_entry(pcp->list.next, struct page, lru); - list_del(&page->lru); - pcp->count--; + if (unlikely(!pcp->count)) + goto failed; } - local_irq_restore(flags); - put_cpu(); - } - - if (page == NULL) { + page = list_entry(pcp->list.next, struct page, lru); + list_del(&page->lru); + pcp->count--; + } else { spin_lock_irqsave(&zone->lock, flags); page = __rmqueue(zone, order); - spin_unlock_irqrestore(&zone->lock, flags); + spin_unlock(&zone->lock); + if (!page) + goto failed; } - if (page != NULL) { - BUG_ON(bad_range(zone, page)); - mod_page_state_zone(zone, pgalloc, 1 << order); - prep_new_page(page, order); - if (order && (gfp_flags & __GFP_COMP)) - prep_compound_page(page, order); - } + __count_zone_vm_events(PGALLOC, zone, 1 << order); + zone_statistics(zonelist, zone); + local_irq_restore(flags); + put_cpu(); + + VM_BUG_ON(bad_range(zone, page)); + if (prep_new_page(page, order, gfp_flags)) + goto again; return page; + +failed: + local_irq_restore(flags); + put_cpu(); + return NULL; } -/* - * This is the 'heart' of the zoned buddy allocator. - * - * Herein lies the mysterious "incremental min". That's the - * - * local_low = z->pages_low; - * min += local_low; - * - * thing. The intent here is to provide additional protection to low zones for - * allocation requests which _could_ use higher zones. So a GFP_HIGHMEM - * request is not allowed to dip as deeply into the normal zone as a GFP_KERNEL - * request. This preserves additional space in those lower zones for requests - * which really do need memory from those zones. It means that on a decent - * sized machine, GFP_HIGHMEM and GFP_KERNEL requests basically leave the DMA - * zone untouched. - */ -struct page * fastcall -__alloc_pages(unsigned int gfp_mask, unsigned int order, - struct zonelist *zonelist) -{ - const int wait = gfp_mask & __GFP_WAIT; - unsigned long min; - struct zone **zones; - struct page *page; - struct reclaim_state reclaim_state; - struct task_struct *p = current; - int i; - int alloc_type; - int do_retry; +#define ALLOC_NO_WATERMARKS 0x01 /* don't check watermarks at all */ +#define ALLOC_WMARK_MIN 0x02 /* use pages_min watermark */ +#define ALLOC_WMARK_LOW 0x04 /* use pages_low watermark */ +#define ALLOC_WMARK_HIGH 0x08 /* use pages_high watermark */ +#define ALLOC_HARDER 0x10 /* try to alloc harder */ +#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ +#define ALLOC_CPUSET 0x40 /* check for correct cpuset */ - might_sleep_if(wait); +#ifdef CONFIG_FAIL_PAGE_ALLOC - zones = zonelist->zones; /* the list of zones suitable for gfp_mask */ - if (zones[0] == NULL) /* no zones in the zonelist */ - return NULL; +static struct fail_page_alloc_attr { + struct fault_attr attr; - alloc_type = zone_idx(zones[0]); + u32 ignore_gfp_highmem; + u32 ignore_gfp_wait; - /* Go through the zonelist once, looking for a zone with enough free */ - for (i = 0; zones[i] != NULL; i++) { - struct zone *z = zones[i]; +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS - min = (1<protection[alloc_type]; + struct dentry *ignore_gfp_highmem_file; + struct dentry *ignore_gfp_wait_file; - /* - * We let real-time tasks dip their real-time paws a little - * deeper into reserves. - */ - if (rt_task(p)) - min -= z->pages_low >> 1; +#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ - if (z->free_pages >= min || - (!wait && z->free_pages >= z->pages_high)) { - page = buffered_rmqueue(z, order, gfp_mask); - if (page) - goto got_pg; - } - } +} fail_page_alloc = { + .attr = FAULT_ATTR_INITIALIZER, + .ignore_gfp_wait = 1, + .ignore_gfp_highmem = 1, +}; - /* we're somewhat low on memory, failed to find what we needed */ - for (i = 0; zones[i] != NULL; i++) - wakeup_kswapd(zones[i]); +static int __init setup_fail_page_alloc(char *str) +{ + return setup_fault_attr(&fail_page_alloc.attr, str); +} +__setup("fail_page_alloc=", setup_fail_page_alloc); - /* Go through the zonelist again, taking __GFP_HIGH into account */ - for (i = 0; zones[i] != NULL; i++) { - struct zone *z = zones[i]; +static int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +{ + if (gfp_mask & __GFP_NOFAIL) + return 0; + if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) + return 0; + if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT)) + return 0; - min = (1<protection[alloc_type]; + return should_fail(&fail_page_alloc.attr, 1 << order); +} - if (gfp_mask & __GFP_HIGH) - min -= z->pages_low >> 2; - if (rt_task(p)) - min -= z->pages_low >> 1; +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS - if (z->free_pages >= min || - (!wait && z->free_pages >= z->pages_high)) { - page = buffered_rmqueue(z, order, gfp_mask); - if (page) - goto got_pg; +static int __init fail_page_alloc_debugfs(void) +{ + mode_t mode = S_IFREG | S_IRUSR | S_IWUSR; + struct dentry *dir; + int err; + + err = init_fault_attr_dentries(&fail_page_alloc.attr, + "fail_page_alloc"); + if (err) + return err; + dir = fail_page_alloc.attr.dentries.dir; + + fail_page_alloc.ignore_gfp_wait_file = + debugfs_create_bool("ignore-gfp-wait", mode, dir, + &fail_page_alloc.ignore_gfp_wait); + + fail_page_alloc.ignore_gfp_highmem_file = + debugfs_create_bool("ignore-gfp-highmem", mode, dir, + &fail_page_alloc.ignore_gfp_highmem); + + if (!fail_page_alloc.ignore_gfp_wait_file || + !fail_page_alloc.ignore_gfp_highmem_file) { + err = -ENOMEM; + debugfs_remove(fail_page_alloc.ignore_gfp_wait_file); + debugfs_remove(fail_page_alloc.ignore_gfp_highmem_file); + cleanup_fault_attr_dentries(&fail_page_alloc.attr); + } + + return err; +} + +late_initcall(fail_page_alloc_debugfs); + +#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ + +#else /* CONFIG_FAIL_PAGE_ALLOC */ + +static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +{ + return 0; +} + +#endif /* CONFIG_FAIL_PAGE_ALLOC */ + +/* + * Return 1 if free pages are above 'mark'. This takes into account the order + * of the allocation. + */ +int zone_watermark_ok(struct zone *z, int order, unsigned long mark, + int classzone_idx, int alloc_flags) +{ + /* free_pages my go negative - that's OK */ + long min = mark, free_pages = z->free_pages - (1 << order) + 1; + int o; + + if (alloc_flags & ALLOC_HIGH) + min -= min / 2; + if (alloc_flags & ALLOC_HARDER) + min -= min / 4; + + if (free_pages <= min + z->lowmem_reserve[classzone_idx]) + return 0; + for (o = 0; o < order; o++) { + /* At the next order, this order's pages become unavailable */ + free_pages -= z->free_area[o].nr_free << o; + + /* Require fewer higher order pages to be free */ + min >>= 1; + + if (free_pages <= min) + return 0; + } + return 1; +} + +#ifdef CONFIG_NUMA +/* + * zlc_setup - Setup for "zonelist cache". Uses cached zone data to + * skip over zones that are not allowed by the cpuset, or that have + * been recently (in last second) found to be nearly full. See further + * comments in mmzone.h. Reduces cache footprint of zonelist scans + * that have to skip over alot of full or unallowed zones. + * + * If the zonelist cache is present in the passed in zonelist, then + * returns a pointer to the allowed node mask (either the current + * tasks mems_allowed, or node_online_map.) + * + * If the zonelist cache is not available for this zonelist, does + * nothing and returns NULL. + * + * If the fullzones BITMAP in the zonelist cache is stale (more than + * a second since last zap'd) then we zap it out (clear its bits.) + * + * We hold off even calling zlc_setup, until after we've checked the + * first zone in the zonelist, on the theory that most allocations will + * be satisfied from that first zone, so best to examine that zone as + * quickly as we can. + */ +static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags) +{ + struct zonelist_cache *zlc; /* cached zonelist speedup info */ + nodemask_t *allowednodes; /* zonelist_cache approximation */ + + zlc = zonelist->zlcache_ptr; + if (!zlc) + return NULL; + + if (jiffies - zlc->last_full_zap > 1 * HZ) { + bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST); + zlc->last_full_zap = jiffies; + } + + allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ? + &cpuset_current_mems_allowed : + &node_online_map; + return allowednodes; +} + +/* + * Given 'z' scanning a zonelist, run a couple of quick checks to see + * if it is worth looking at further for free memory: + * 1) Check that the zone isn't thought to be full (doesn't have its + * bit set in the zonelist_cache fullzones BITMAP). + * 2) Check that the zones node (obtained from the zonelist_cache + * z_to_n[] mapping) is allowed in the passed in allowednodes mask. + * Return true (non-zero) if zone is worth looking at further, or + * else return false (zero) if it is not. + * + * This check -ignores- the distinction between various watermarks, + * such as GFP_HIGH, GFP_ATOMIC, PF_MEMALLOC, ... If a zone is + * found to be full for any variation of these watermarks, it will + * be considered full for up to one second by all requests, unless + * we are so low on memory on all allowed nodes that we are forced + * into the second scan of the zonelist. + * + * In the second scan we ignore this zonelist cache and exactly + * apply the watermarks to all zones, even it is slower to do so. + * We are low on memory in the second scan, and should leave no stone + * unturned looking for a free page. + */ +static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z, + nodemask_t *allowednodes) +{ + struct zonelist_cache *zlc; /* cached zonelist speedup info */ + int i; /* index of *z in zonelist zones */ + int n; /* node that zone *z is on */ + + zlc = zonelist->zlcache_ptr; + if (!zlc) + return 1; + + i = z - zonelist->zones; + n = zlc->z_to_n[i]; + + /* This zone is worth trying if it is allowed but not full */ + return node_isset(n, *allowednodes) && !test_bit(i, zlc->fullzones); +} + +/* + * Given 'z' scanning a zonelist, set the corresponding bit in + * zlc->fullzones, so that subsequent attempts to allocate a page + * from that zone don't waste time re-examining it. + */ +static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z) +{ + struct zonelist_cache *zlc; /* cached zonelist speedup info */ + int i; /* index of *z in zonelist zones */ + + zlc = zonelist->zlcache_ptr; + if (!zlc) + return; + + i = z - zonelist->zones; + + set_bit(i, zlc->fullzones); +} + +#else /* CONFIG_NUMA */ + +static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags) +{ + return NULL; +} + +static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z, + nodemask_t *allowednodes) +{ + return 1; +} + +static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z) +{ +} +#endif /* CONFIG_NUMA */ + +/* + * get_page_from_freelist goes through the zonelist trying to allocate + * a page. + */ +static struct page * +get_page_from_freelist(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, int alloc_flags) +{ + struct zone **z; + struct page *page = NULL; + int classzone_idx = zone_idx(zonelist->zones[0]); + struct zone *zone; + nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */ + int zlc_active = 0; /* set if using zonelist_cache */ + int did_zlc_setup = 0; /* just call zlc_setup() one time */ + +zonelist_scan: + /* + * Scan zonelist, looking for a zone with enough free. + * See also cpuset_zone_allowed() comment in kernel/cpuset.c. + */ + z = zonelist->zones; + + do { + if (NUMA_BUILD && zlc_active && + !zlc_zone_worth_trying(zonelist, z, allowednodes)) + continue; + zone = *z; + if (unlikely(NUMA_BUILD && (gfp_mask & __GFP_THISNODE) && + zone->zone_pgdat != zonelist->zones[0]->zone_pgdat)) + break; + if ((alloc_flags & ALLOC_CPUSET) && + !cpuset_zone_allowed_softwall(zone, gfp_mask)) + goto try_next_zone; + + if (!(alloc_flags & ALLOC_NO_WATERMARKS)) { + unsigned long mark; + if (alloc_flags & ALLOC_WMARK_MIN) + mark = zone->pages_min; + else if (alloc_flags & ALLOC_WMARK_LOW) + mark = zone->pages_low; + else + mark = zone->pages_high; + if (!zone_watermark_ok(zone, order, mark, + classzone_idx, alloc_flags)) { + if (!zone_reclaim_mode || + !zone_reclaim(zone, gfp_mask, order)) + goto this_zone_full; + } + } + + page = buffered_rmqueue(zonelist, zone, order, gfp_mask); + if (page) + break; +this_zone_full: + if (NUMA_BUILD) + zlc_mark_zone_full(zonelist, z); +try_next_zone: + if (NUMA_BUILD && !did_zlc_setup) { + /* we do zlc_setup after the first zone is tried */ + allowednodes = zlc_setup(zonelist, alloc_flags); + zlc_active = 1; + did_zlc_setup = 1; } + } while (*(++z) != NULL); + + if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) { + /* Disable zlc cache for second zonelist scan */ + zlc_active = 0; + goto zonelist_scan; + } + return page; +} + +/* + * This is the 'heart' of the zoned buddy allocator. + */ +struct page * fastcall +__alloc_pages(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist) +{ + const gfp_t wait = gfp_mask & __GFP_WAIT; + struct zone **z; + struct page *page; + struct reclaim_state reclaim_state; + struct task_struct *p = current; + int do_retry; + int alloc_flags; + int did_some_progress; + + might_sleep_if(wait); + + if (should_fail_alloc_page(gfp_mask, order)) + return NULL; + +restart: + z = zonelist->zones; /* the list of zones suitable for gfp_mask */ + + if (unlikely(*z == NULL)) { + /* Should this ever happen?? */ + return NULL; } - /* here we're in the low on memory slow path */ + page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order, + zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET); + if (page) + goto got_pg; -rebalance: - if ((p->flags & (PF_MEMALLOC | PF_MEMDIE)) && !in_interrupt()) { - /* go through the zonelist yet again, ignoring mins */ - for (i = 0; zones[i] != NULL; i++) { - struct zone *z = zones[i]; + /* + * GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and + * __GFP_NOWARN set) should not cause reclaim since the subsystem + * (f.e. slab) using GFP_THISNODE may choose to trigger reclaim + * using a larger set of nodes after it has established that the + * allowed per node queues are empty and that nodes are + * over allocated. + */ + if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE) + goto nopage; - page = buffered_rmqueue(z, order, gfp_mask); + for (z = zonelist->zones; *z; z++) + wakeup_kswapd(*z, order); + + /* + * OK, we're below the kswapd watermark and have kicked background + * reclaim. Now things get more complex, so set up alloc_flags according + * to how we want to proceed. + * + * The caller may dip into page reserves a bit more if the caller + * cannot run direct reclaim, or if the caller has realtime scheduling + * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will + * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH). + */ + alloc_flags = ALLOC_WMARK_MIN; + if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait) + alloc_flags |= ALLOC_HARDER; + if (gfp_mask & __GFP_HIGH) + alloc_flags |= ALLOC_HIGH; + if (wait) + alloc_flags |= ALLOC_CPUSET; + + /* + * Go through the zonelist again. Let __GFP_HIGH and allocations + * coming from realtime tasks go deeper into reserves. + * + * This is the last chance, in general, before the goto nopage. + * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. + * See also cpuset_zone_allowed() comment in kernel/cpuset.c. + */ + page = get_page_from_freelist(gfp_mask, order, zonelist, alloc_flags); + if (page) + goto got_pg; + + /* This allocation should allow future memory freeing. */ + +rebalance: + if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE))) + && !in_interrupt()) { + if (!(gfp_mask & __GFP_NOMEMALLOC)) { +nofail_alloc: + /* go through the zonelist yet again, ignoring mins */ + page = get_page_from_freelist(gfp_mask, order, + zonelist, ALLOC_NO_WATERMARKS); if (page) goto got_pg; + if (gfp_mask & __GFP_NOFAIL) { + congestion_wait(WRITE, HZ/50); + goto nofail_alloc; + } } goto nopage; } @@ -640,35 +1314,48 @@ rebalance: if (!wait) goto nopage; + cond_resched(); + + /* We now go into synchronous reclaim */ + cpuset_memory_pressure_bump(); p->flags |= PF_MEMALLOC; reclaim_state.reclaimed_slab = 0; p->reclaim_state = &reclaim_state; - try_to_free_pages(zones, gfp_mask, order); + did_some_progress = try_to_free_pages(zonelist->zones, gfp_mask); p->reclaim_state = NULL; p->flags &= ~PF_MEMALLOC; - /* go through the zonelist yet one more time */ - for (i = 0; zones[i] != NULL; i++) { - struct zone *z = zones[i]; + cond_resched(); - min = (1UL << order) + z->protection[alloc_type]; + if (likely(did_some_progress)) { + page = get_page_from_freelist(gfp_mask, order, + zonelist, alloc_flags); + if (page) + goto got_pg; + } else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) { + /* + * Go through the zonelist yet one more time, keep + * very high watermark here, this is only to catch + * a parallel oom killing, we must fail if we're still + * under heavy pressure. + */ + page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order, + zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET); + if (page) + goto got_pg; - if (z->free_pages >= min || - (!wait && z->free_pages >= z->pages_high)) { - page = buffered_rmqueue(z, order, gfp_mask); - if (page) - goto got_pg; - } + out_of_memory(zonelist, gfp_mask, order); + goto restart; } /* * Don't let big-order allocations loop unless the caller explicitly * requests that. Wait for some write requests to complete then retry. * - * In this implementation, __GFP_REPEAT means __GFP_NOFAIL, but that - * may not be true in other implementations. + * In this implementation, __GFP_REPEAT means __GFP_NOFAIL for order + * <= 3, but that may not be true in other implementations. */ do_retry = 0; if (!(gfp_mask & __GFP_NORETRY)) { @@ -678,7 +1365,7 @@ rebalance: do_retry = 1; } if (do_retry) { - blk_congestion_wait(WRITE, HZ/50); + congestion_wait(WRITE, HZ/50); goto rebalance; } @@ -688,62 +1375,20 @@ nopage: " order:%d, mode:0x%x\n", p->comm, order, gfp_mask); dump_stack(); + show_mem(); } - return NULL; got_pg: - kernel_map_pages(page, 1 << order, 1); return page; } EXPORT_SYMBOL(__alloc_pages); -#ifdef CONFIG_NUMA -/* Early boot: Everything is done by one cpu, but the data structures will be - * used by all cpus - spread them on all nodes. - */ -static __init unsigned long get_boot_pages(unsigned int gfp_mask, unsigned int order) -{ -static int nodenr; - int i = nodenr; - struct page *page; - - for (;;) { - if (i > nodenr + numnodes) - return 0; - if (node_present_pages(i%numnodes)) { - struct zone **z; - /* The node contains memory. Check that there is - * memory in the intended zonelist. - */ - z = NODE_DATA(i%numnodes)->node_zonelists[gfp_mask & GFP_ZONEMASK].zones; - while (*z) { - if ( (*z)->free_pages > (1UL<nr_active + zone->nr_inactive; - - return pages; -} - #ifdef CONFIG_NUMA unsigned int nr_free_pages_pgdat(pg_data_t *pgdat) { - unsigned int i, sum = 0; + unsigned int sum = 0; + enum zone_type i; for (i = 0; i < MAX_NR_ZONES; i++) sum += pgdat->node_zones[i].free_pages; @@ -844,20 +1476,19 @@ unsigned int nr_free_pages_pgdat(pg_data_t *pgdat) static unsigned int nr_free_zone_pages(int offset) { - pg_data_t *pgdat; + /* Just pick one node, since fallback list is circular */ + pg_data_t *pgdat = NODE_DATA(numa_node_id()); unsigned int sum = 0; - for_each_pgdat(pgdat) { - struct zonelist *zonelist = pgdat->node_zonelists + offset; - struct zone **zonep = zonelist->zones; - struct zone *zone; + struct zonelist *zonelist = pgdat->node_zonelists + offset; + struct zone **zonep = zonelist->zones; + struct zone *zone; - for (zone = *zonep++; zone; zone = *zonep++) { - unsigned long size = zone->present_pages; - unsigned long high = zone->pages_high; - if (size > high) - sum += size - high; - } + for (zone = *zonep++; zone; zone = *zonep++) { + unsigned long size = zone->present_pages; + unsigned long high = zone->pages_high; + if (size > high) + sum += size - high; } return sum; @@ -868,7 +1499,7 @@ static unsigned int nr_free_zone_pages(int offset) */ unsigned int nr_free_buffer_pages(void) { - return nr_free_zone_pages(GFP_USER & GFP_ZONEMASK); + return nr_free_zone_pages(gfp_zone(GFP_USER)); } /* @@ -876,96 +1507,13 @@ unsigned int nr_free_buffer_pages(void) */ unsigned int nr_free_pagecache_pages(void) { - return nr_free_zone_pages(GFP_HIGHUSER & GFP_ZONEMASK); -} - -#ifdef CONFIG_HIGHMEM -unsigned int nr_free_highpages (void) -{ - pg_data_t *pgdat; - unsigned int pages = 0; - - for_each_pgdat(pgdat) - pages += pgdat->node_zones[ZONE_HIGHMEM].free_pages; - - return pages; -} -#endif - -#ifdef CONFIG_NUMA -static void show_node(struct zone *zone) -{ - printk("Node %d ", zone->zone_pgdat->node_id); -} -#else -#define show_node(zone) do { } while (0) -#endif - -/* - * Accumulate the page_state information across all CPUs. - * The result is unavoidably approximate - it can change - * during and after execution of this function. - */ -DEFINE_PER_CPU(struct page_state, page_states) = {0}; -EXPORT_PER_CPU_SYMBOL(page_states); - -atomic_t nr_pagecache = ATOMIC_INIT(0); -EXPORT_SYMBOL(nr_pagecache); -#ifdef CONFIG_SMP -DEFINE_PER_CPU(long, nr_pagecache_local) = 0; -#endif - -void __get_page_state(struct page_state *ret, int nr) -{ - int cpu = 0; - - memset(ret, 0, sizeof(*ret)); - while (cpu < NR_CPUS) { - unsigned long *in, *out, off; - - if (!cpu_possible(cpu)) { - cpu++; - continue; - } - - in = (unsigned long *)&per_cpu(page_states, cpu); - cpu++; - if (cpu < NR_CPUS && cpu_possible(cpu)) - prefetch(&per_cpu(page_states, cpu)); - out = (unsigned long *)ret; - for (off = 0; off < nr; off++) - *out++ += *in++; - } -} - -void get_page_state(struct page_state *ret) -{ - int nr; - - nr = offsetof(struct page_state, GET_PAGE_STATE_LAST); - nr /= sizeof(unsigned long); - - __get_page_state(ret, nr + 1); -} - -void get_full_page_state(struct page_state *ret) -{ - __get_page_state(ret, sizeof(*ret) / sizeof(unsigned long)); + return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER)); } -void get_zone_counts(unsigned long *active, - unsigned long *inactive, unsigned long *free) +static inline void show_node(struct zone *zone) { - struct zone *zone; - - *active = 0; - *inactive = 0; - *free = 0; - for_each_zone(zone) { - *active += zone->nr_active; - *inactive += zone->nr_inactive; - *free += zone->free_pages; - } + if (NUMA_BUILD) + printk("Node %d ", zone_to_nid(zone)); } void si_meminfo(struct sysinfo *val) @@ -974,14 +1522,12 @@ void si_meminfo(struct sysinfo *val) val->sharedram = 0; val->freeram = nr_free_pages(); val->bufferram = nr_blockdev_pages(); -#ifdef CONFIG_HIGHMEM val->totalhigh = totalhigh_pages; val->freehigh = nr_free_highpages(); -#else - val->totalhigh = 0; - val->freehigh = 0; -#endif val->mem_unit = PAGE_SIZE; + + if (vx_flags(VXF_VIRT_MEM, 0)) + vx_vsi_meminfo(val); } EXPORT_SYMBOL(si_meminfo); @@ -993,9 +1539,17 @@ void si_meminfo_node(struct sysinfo *val, int nid) val->totalram = pgdat->node_present_pages; val->freeram = nr_free_pages_pgdat(pgdat); +#ifdef CONFIG_HIGHMEM val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages; val->freehigh = pgdat->node_zones[ZONE_HIGHMEM].free_pages; +#else + val->totalhigh = 0; + val->freehigh = 0; +#endif val->mem_unit = PAGE_SIZE; + + if (vx_flags(VXF_VIRT_MEM, 0)) + vx_vsi_meminfo(val); } #endif @@ -1008,63 +1562,54 @@ void si_meminfo_node(struct sysinfo *val, int nid) */ void show_free_areas(void) { - struct page_state ps; - int cpu, temperature; + int cpu; unsigned long active; unsigned long inactive; unsigned long free; struct zone *zone; for_each_zone(zone) { - show_node(zone); - printk("%s per-cpu:", zone->name); - - if (!zone->present_pages) { - printk(" empty\n"); + if (!populated_zone(zone)) continue; - } else - printk("\n"); - for (cpu = 0; cpu < NR_CPUS; ++cpu) { - struct per_cpu_pageset *pageset; + show_node(zone); + printk("%s per-cpu:\n", zone->name); - if (!cpu_possible(cpu)) - continue; + for_each_online_cpu(cpu) { + struct per_cpu_pageset *pageset; - pageset = zone->pageset + cpu; + pageset = zone_pcp(zone, cpu); - for (temperature = 0; temperature < 2; temperature++) - printk("cpu %d %s: low %d, high %d, batch %d\n", - cpu, - temperature ? "cold" : "hot", - pageset->pcp[temperature].low, - pageset->pcp[temperature].high, - pageset->pcp[temperature].batch); + printk("CPU %4d: Hot: hi:%5d, btch:%4d usd:%4d " + "Cold: hi:%5d, btch:%4d usd:%4d\n", + cpu, pageset->pcp[0].high, + pageset->pcp[0].batch, pageset->pcp[0].count, + pageset->pcp[1].high, pageset->pcp[1].batch, + pageset->pcp[1].count); } } - get_page_state(&ps); get_zone_counts(&active, &inactive, &free); - printk("\nFree pages: %11ukB (%ukB HighMem)\n", - K(nr_free_pages()), - K(nr_free_highpages())); - printk("Active:%lu inactive:%lu dirty:%lu writeback:%lu " "unstable:%lu free:%u slab:%lu mapped:%lu pagetables:%lu\n", active, inactive, - ps.nr_dirty, - ps.nr_writeback, - ps.nr_unstable, + global_page_state(NR_FILE_DIRTY), + global_page_state(NR_WRITEBACK), + global_page_state(NR_UNSTABLE_NFS), nr_free_pages(), - ps.nr_slab, - ps.nr_mapped, - ps.nr_page_table_pages); + global_page_state(NR_SLAB_RECLAIMABLE) + + global_page_state(NR_SLAB_UNRECLAIMABLE), + global_page_state(NR_FILE_MAPPED), + global_page_state(NR_PAGETABLE)); for_each_zone(zone) { int i; + if (!populated_zone(zone)) + continue; + show_node(zone); printk("%s" " free:%lukB" @@ -1074,6 +1619,8 @@ void show_free_areas(void) " active:%lukB" " inactive:%lukB" " present:%lukB" + " pages_scanned:%lu" + " all_unreclaimable? %s" "\n", zone->name, K(zone->free_pages), @@ -1082,34 +1629,33 @@ void show_free_areas(void) K(zone->pages_high), K(zone->nr_active), K(zone->nr_inactive), - K(zone->present_pages) + K(zone->present_pages), + zone->pages_scanned, + (zone->all_unreclaimable ? "yes" : "no") ); - printk("protections[]:"); + printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) - printk(" %lu", zone->protection[i]); + printk(" %lu", zone->lowmem_reserve[i]); printk("\n"); } for_each_zone(zone) { - struct list_head *elem; - unsigned long nr, flags, order, total = 0; + unsigned long nr[MAX_ORDER], flags, order, total = 0; + + if (!populated_zone(zone)) + continue; show_node(zone); printk("%s: ", zone->name); - if (!zone->present_pages) { - printk("empty\n"); - continue; - } spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { - nr = 0; - list_for_each(elem, &zone->free_area[order].free_list) - ++nr; - total += nr << order; - printk("%lu*%lukB ", nr, K(1UL) << order); + nr[order] = zone->free_area[order].nr_free; + total += nr[order] << order; } spin_unlock_irqrestore(&zone->lock, flags); + for (order = 0; order < MAX_ORDER; order++) + printk("%lu*%lukB ", nr[order], K(1UL) << order); printk("= %lukB\n", K(total)); } @@ -1118,42 +1664,36 @@ void show_free_areas(void) /* * Builds allocation fallback zone lists. + * + * Add all populated zones of a node to the zonelist. */ -static int __init build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, int j, int k) +static int __meminit build_zonelists_node(pg_data_t *pgdat, + struct zonelist *zonelist, int nr_zones, enum zone_type zone_type) { - switch (k) { - struct zone *zone; - default: - BUG(); - case ZONE_HIGHMEM: - zone = pgdat->node_zones + ZONE_HIGHMEM; - if (zone->present_pages) { -#ifndef CONFIG_HIGHMEM - BUG(); -#endif - zonelist->zones[j++] = zone; + struct zone *zone; + + BUG_ON(zone_type >= MAX_NR_ZONES); + zone_type++; + + do { + zone_type--; + zone = pgdat->node_zones + zone_type; + if (populated_zone(zone)) { + zonelist->zones[nr_zones++] = zone; + check_highest_zone(zone_type); } - case ZONE_NORMAL: - zone = pgdat->node_zones + ZONE_NORMAL; - if (zone->present_pages) - zonelist->zones[j++] = zone; - case ZONE_DMA: - zone = pgdat->node_zones + ZONE_DMA; - if (zone->present_pages) - zonelist->zones[j++] = zone; - } - return j; + } while (zone_type); + return nr_zones; } #ifdef CONFIG_NUMA -#define MAX_NODE_LOAD (numnodes) -static int __initdata node_load[MAX_NUMNODES]; +#define MAX_NODE_LOAD (num_online_nodes()) +static int __meminitdata node_load[MAX_NUMNODES]; /** - * find_next_best_node - find the next node that should appear in a given - * node's fallback list + * find_next_best_node - find the next node that should appear in a given node's fallback list * @node: node whose fallback list we're appending - * @used_node_mask: pointer to the bitmap of already used nodes + * @used_node_mask: nodemask_t of already used nodes * * We use a number of factors to determine which is the next node that should * appear on a given node's fallback list. The node should not have appeared @@ -1164,25 +1704,31 @@ static int __initdata node_load[MAX_NUMNODES]; * on them otherwise. * It returns -1 if no node is found. */ -static int __init find_next_best_node(int node, void *used_node_mask) +static int __meminit find_next_best_node(int node, nodemask_t *used_node_mask) { - int i, n, val; + int n, val; int min_val = INT_MAX; int best_node = -1; - for (i = 0; i < numnodes; i++) { - cpumask_t tmp; + /* Use the local node if we haven't already */ + if (!node_isset(node, *used_node_mask)) { + node_set(node, *used_node_mask); + return node; + } - /* Start from local node */ - n = (node+i)%numnodes; + for_each_online_node(n) { + cpumask_t tmp; /* Don't want a node to appear more than once */ - if (test_bit(n, used_node_mask)) + if (node_isset(n, *used_node_mask)) continue; /* Use the distance array to find the distance */ val = node_distance(node, n); + /* Penalize nodes under us ("prefer the next node") */ + val += (n < node); + /* Give preference to headless and unused nodes */ tmp = node_to_cpumask(n); if (!cpus_empty(tmp)) @@ -1199,38 +1745,47 @@ static int __init find_next_best_node(int node, void *used_node_mask) } if (best_node >= 0) - set_bit(best_node, used_node_mask); + node_set(best_node, *used_node_mask); return best_node; } -static void __init build_zonelists(pg_data_t *pgdat) +static void __meminit build_zonelists(pg_data_t *pgdat) { - int i, j, k, node, local_node; + int j, node, local_node; + enum zone_type i; int prev_node, load; struct zonelist *zonelist; - DECLARE_BITMAP(used_mask, MAX_NUMNODES); + nodemask_t used_mask; /* initialize zonelists */ for (i = 0; i < MAX_NR_ZONES; i++) { zonelist = pgdat->node_zonelists + i; - memset(zonelist, 0, sizeof(*zonelist)); zonelist->zones[0] = NULL; } /* NUMA-aware ordering of nodes */ local_node = pgdat->node_id; - load = numnodes; + load = num_online_nodes(); prev_node = local_node; - bitmap_zero(used_mask, MAX_NUMNODES); - while ((node = find_next_best_node(local_node, used_mask)) >= 0) { + nodes_clear(used_mask); + while ((node = find_next_best_node(local_node, &used_mask)) >= 0) { + int distance = node_distance(local_node, node); + /* - * We don't want to pressure a particular node. + * If another node is sufficiently far away then it is better + * to reclaim pages in a zone before going off node. + */ + if (distance > RECLAIM_DISTANCE) + zone_reclaim_mode = 1; + + /* + * We don't want to pressure a particular node. * So adding penalty to the first node in same * distance group to make it round-robin. */ - if (node_distance(local_node, node) != - node_distance(local_node, prev_node)) + + if (distance != node_distance(local_node, prev_node)) node_load[node] += load; prev_node = node; load--; @@ -1238,39 +1793,44 @@ static void __init build_zonelists(pg_data_t *pgdat) zonelist = pgdat->node_zonelists + i; for (j = 0; zonelist->zones[j] != NULL; j++); - k = ZONE_NORMAL; - if (i & __GFP_HIGHMEM) - k = ZONE_HIGHMEM; - if (i & __GFP_DMA) - k = ZONE_DMA; - - j = build_zonelists_node(NODE_DATA(node), zonelist, j, k); + j = build_zonelists_node(NODE_DATA(node), zonelist, j, i); zonelist->zones[j] = NULL; } } } +/* Construct the zonelist performance cache - see further mmzone.h */ +static void __meminit build_zonelist_cache(pg_data_t *pgdat) +{ + int i; + + for (i = 0; i < MAX_NR_ZONES; i++) { + struct zonelist *zonelist; + struct zonelist_cache *zlc; + struct zone **z; + + zonelist = pgdat->node_zonelists + i; + zonelist->zlcache_ptr = zlc = &zonelist->zlcache; + bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST); + for (z = zonelist->zones; *z; z++) + zlc->z_to_n[z - zonelist->zones] = zone_to_nid(*z); + } +} + #else /* CONFIG_NUMA */ -static void __init build_zonelists(pg_data_t *pgdat) +static void __meminit build_zonelists(pg_data_t *pgdat) { - int i, j, k, node, local_node; + int node, local_node; + enum zone_type i,j; local_node = pgdat->node_id; for (i = 0; i < MAX_NR_ZONES; i++) { struct zonelist *zonelist; zonelist = pgdat->node_zonelists + i; - memset(zonelist, 0, sizeof(*zonelist)); - - j = 0; - k = ZONE_NORMAL; - if (i & __GFP_HIGHMEM) - k = ZONE_HIGHMEM; - if (i & __GFP_DMA) - k = ZONE_DMA; - j = build_zonelists_node(pgdat, zonelist, j, k); + j = build_zonelists_node(pgdat, zonelist, 0, i); /* * Now we build the zonelist so that it contains the zones * of all the other nodes. @@ -1279,24 +1839,58 @@ static void __init build_zonelists(pg_data_t *pgdat) * zones coming right after the local ones are those from * node N+1 (modulo N) */ - for (node = local_node + 1; node < numnodes; node++) - j = build_zonelists_node(NODE_DATA(node), zonelist, j, k); - for (node = 0; node < local_node; node++) - j = build_zonelists_node(NODE_DATA(node), zonelist, j, k); - - zonelist->zones[j++] = NULL; + for (node = local_node + 1; node < MAX_NUMNODES; node++) { + if (!node_online(node)) + continue; + j = build_zonelists_node(NODE_DATA(node), zonelist, j, i); + } + for (node = 0; node < local_node; node++) { + if (!node_online(node)) + continue; + j = build_zonelists_node(NODE_DATA(node), zonelist, j, i); + } + + zonelist->zones[j] = NULL; } } +/* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */ +static void __meminit build_zonelist_cache(pg_data_t *pgdat) +{ + int i; + + for (i = 0; i < MAX_NR_ZONES; i++) + pgdat->node_zonelists[i].zlcache_ptr = NULL; +} + #endif /* CONFIG_NUMA */ -void __init build_all_zonelists(void) +/* return values int ....just for stop_machine_run() */ +static int __meminit __build_all_zonelists(void *dummy) { - int i; + int nid; - for(i = 0 ; i < numnodes ; i++) - build_zonelists(NODE_DATA(i)); - printk("Built %i zonelists\n", numnodes); + for_each_online_node(nid) { + build_zonelists(NODE_DATA(nid)); + build_zonelist_cache(NODE_DATA(nid)); + } + return 0; +} + +void __meminit build_all_zonelists(void) +{ + if (system_state == SYSTEM_BOOTING) { + __build_all_zonelists(NULL); + cpuset_init_current_mems_allowed(); + } else { + /* we have to stop all cpus to guaranntee there is no user + of zonelist */ + stop_machine_run(__build_all_zonelists, NULL, NR_CPUS); + /* cpuset refresh routine should be here */ + } + vm_total_pages = nr_free_pagecache_pages(); + printk("Built %i zonelists. Total pages: %ld\n", + num_online_nodes(), vm_total_pages); } /* @@ -1312,7 +1906,8 @@ void __init build_all_zonelists(void) */ #define PAGES_PER_WAITQUEUE 256 -static inline unsigned long wait_table_size(unsigned long pages) +#ifndef CONFIG_MEMORY_HOTPLUG +static inline unsigned long wait_table_hash_nr_entries(unsigned long pages) { unsigned long size = 1; @@ -1330,526 +1925,1196 @@ static inline unsigned long wait_table_size(unsigned long pages) return max(size, 4UL); } +#else +/* + * A zone's size might be changed by hot-add, so it is not possible to determine + * a suitable size for its wait_table. So we use the maximum size now. + * + * The max wait table size = 4096 x sizeof(wait_queue_head_t). ie: + * + * i386 (preemption config) : 4096 x 16 = 64Kbyte. + * ia64, x86-64 (no preemption): 4096 x 20 = 80Kbyte. + * ia64, x86-64 (preemption) : 4096 x 24 = 96Kbyte. + * + * The maximum entries are prepared when a zone's memory is (512K + 256) pages + * or more by the traditional way. (See above). It equals: + * + * i386, x86-64, powerpc(4K page size) : = ( 2G + 1M)byte. + * ia64(16K page size) : = ( 8G + 4M)byte. + * powerpc (64K page size) : = (32G +16M)byte. + */ +static inline unsigned long wait_table_hash_nr_entries(unsigned long pages) +{ + return 4096UL; +} +#endif + +/* + * This is an integer logarithm so that shifts can be used later + * to extract the more random high bits from the multiplicative + * hash function before the remainder is taken. + */ +static inline unsigned long wait_table_bits(unsigned long size) +{ + return ffz(~size); +} + +#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1)) + +/* + * Initially all pages are reserved - free ones are freed + * up by free_all_bootmem() once the early boot process is + * done. Non-atomic initialization, single-pass. + */ +void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, + unsigned long start_pfn, enum memmap_context context) +{ + struct page *page; + unsigned long end_pfn = start_pfn + size; + unsigned long pfn; + + for (pfn = start_pfn; pfn < end_pfn; pfn++) { + /* + * There can be holes in boot-time mem_map[]s + * handed to this function. They do not + * exist on hotplugged memory. + */ + if (context == MEMMAP_EARLY) { + if (!early_pfn_valid(pfn)) + continue; + if (!early_pfn_in_nid(pfn, nid)) + continue; + } + page = pfn_to_page(pfn); + set_page_links(page, zone, nid, pfn); + init_page_count(page); + reset_page_mapcount(page); + SetPageReserved(page); + INIT_LIST_HEAD(&page->lru); +#ifdef WANT_PAGE_VIRTUAL + /* The shift won't overflow because ZONE_NORMAL is below 4G. */ + if (!is_highmem_idx(zone)) + set_page_address(page, __va(pfn << PAGE_SHIFT)); +#endif + } +} + +void zone_init_free_lists(struct pglist_data *pgdat, struct zone *zone, + unsigned long size) +{ + int order; + for (order = 0; order < MAX_ORDER ; order++) { + INIT_LIST_HEAD(&zone->free_area[order].free_list); + zone->free_area[order].nr_free = 0; + } +} + +#ifndef __HAVE_ARCH_MEMMAP_INIT +#define memmap_init(size, nid, zone, start_pfn) \ + memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY) +#endif + +static int __cpuinit zone_batchsize(struct zone *zone) +{ + int batch; + + /* + * The per-cpu-pages pools are set to around 1000th of the + * size of the zone. But no more than 1/2 of a meg. + * + * OK, so we don't know how big the cache is. So guess. + */ + batch = zone->present_pages / 1024; + if (batch * PAGE_SIZE > 512 * 1024) + batch = (512 * 1024) / PAGE_SIZE; + batch /= 4; /* We effectively *= 4 below */ + if (batch < 1) + batch = 1; + + /* + * Clamp the batch to a 2^n - 1 value. Having a power + * of 2 value was found to be more likely to have + * suboptimal cache aliasing properties in some cases. + * + * For example if 2 tasks are alternately allocating + * batches of pages, one task can end up with a lot + * of pages of one half of the possible page colors + * and the other with pages of the other colors. + */ + batch = (1 << (fls(batch + batch/2)-1)) - 1; + + return batch; +} + +inline void setup_pageset(struct per_cpu_pageset *p, unsigned long batch) +{ + struct per_cpu_pages *pcp; + + memset(p, 0, sizeof(*p)); + + pcp = &p->pcp[0]; /* hot */ + pcp->count = 0; + pcp->high = 6 * batch; + pcp->batch = max(1UL, 1 * batch); + INIT_LIST_HEAD(&pcp->list); + + pcp = &p->pcp[1]; /* cold*/ + pcp->count = 0; + pcp->high = 2 * batch; + pcp->batch = max(1UL, batch/2); + INIT_LIST_HEAD(&pcp->list); +} + +/* + * setup_pagelist_highmark() sets the high water mark for hot per_cpu_pagelist + * to the value high for the pageset p. + */ + +static void setup_pagelist_highmark(struct per_cpu_pageset *p, + unsigned long high) +{ + struct per_cpu_pages *pcp; + + pcp = &p->pcp[0]; /* hot list */ + pcp->high = high; + pcp->batch = max(1UL, high/4); + if ((high/4) > (PAGE_SHIFT * 8)) + pcp->batch = PAGE_SHIFT * 8; +} + + +#ifdef CONFIG_NUMA +/* + * Boot pageset table. One per cpu which is going to be used for all + * zones and all nodes. The parameters will be set in such a way + * that an item put on a list will immediately be handed over to + * the buddy list. This is safe since pageset manipulation is done + * with interrupts disabled. + * + * Some NUMA counter updates may also be caught by the boot pagesets. + * + * The boot_pagesets must be kept even after bootup is complete for + * unused processors and/or zones. They do play a role for bootstrapping + * hotplugged processors. + * + * zoneinfo_show() and maybe other functions do + * not check if the processor is online before following the pageset pointer. + * Other parts of the kernel may not check if the zone is available. + */ +static struct per_cpu_pageset boot_pageset[NR_CPUS]; + +/* + * Dynamically allocate memory for the + * per cpu pageset array in struct zone. + */ +static int __cpuinit process_zones(int cpu) +{ + struct zone *zone, *dzone; + + for_each_zone(zone) { + + if (!populated_zone(zone)) + continue; + + zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset), + GFP_KERNEL, cpu_to_node(cpu)); + if (!zone_pcp(zone, cpu)) + goto bad; + + setup_pageset(zone_pcp(zone, cpu), zone_batchsize(zone)); + + if (percpu_pagelist_fraction) + setup_pagelist_highmark(zone_pcp(zone, cpu), + (zone->present_pages / percpu_pagelist_fraction)); + } + + return 0; +bad: + for_each_zone(dzone) { + if (dzone == zone) + break; + kfree(zone_pcp(dzone, cpu)); + zone_pcp(dzone, cpu) = NULL; + } + return -ENOMEM; +} + +static inline void free_zone_pagesets(int cpu) +{ + struct zone *zone; + + for_each_zone(zone) { + struct per_cpu_pageset *pset = zone_pcp(zone, cpu); + + /* Free per_cpu_pageset if it is slab allocated */ + if (pset != &boot_pageset[cpu]) + kfree(pset); + zone_pcp(zone, cpu) = NULL; + } +} + +static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + int cpu = (long)hcpu; + int ret = NOTIFY_OK; + + switch (action) { + case CPU_UP_PREPARE: + if (process_zones(cpu)) + ret = NOTIFY_BAD; + break; + case CPU_UP_CANCELED: + case CPU_DEAD: + free_zone_pagesets(cpu); + break; + default: + break; + } + return ret; +} + +static struct notifier_block __cpuinitdata pageset_notifier = + { &pageset_cpuup_callback, NULL, 0 }; + +void __init setup_per_cpu_pageset(void) +{ + int err; + + /* Initialize per_cpu_pageset for cpu 0. + * A cpuup callback will do this for every cpu + * as it comes online + */ + err = process_zones(smp_processor_id()); + BUG_ON(err); + register_cpu_notifier(&pageset_notifier); +} + +#endif + +static __meminit +int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) +{ + int i; + struct pglist_data *pgdat = zone->zone_pgdat; + size_t alloc_size; + + /* + * The per-page waitqueue mechanism uses hashed waitqueues + * per zone. + */ + zone->wait_table_hash_nr_entries = + wait_table_hash_nr_entries(zone_size_pages); + zone->wait_table_bits = + wait_table_bits(zone->wait_table_hash_nr_entries); + alloc_size = zone->wait_table_hash_nr_entries + * sizeof(wait_queue_head_t); + + if (system_state == SYSTEM_BOOTING) { + zone->wait_table = (wait_queue_head_t *) + alloc_bootmem_node(pgdat, alloc_size); + } else { + /* + * This case means that a zone whose size was 0 gets new memory + * via memory hot-add. + * But it may be the case that a new node was hot-added. In + * this case vmalloc() will not be able to use this new node's + * memory - this wait_table must be initialized to use this new + * node itself as well. + * To use this new node's memory, further consideration will be + * necessary. + */ + zone->wait_table = (wait_queue_head_t *)vmalloc(alloc_size); + } + if (!zone->wait_table) + return -ENOMEM; + + for(i = 0; i < zone->wait_table_hash_nr_entries; ++i) + init_waitqueue_head(zone->wait_table + i); + + return 0; +} + +static __meminit void zone_pcp_init(struct zone *zone) +{ + int cpu; + unsigned long batch = zone_batchsize(zone); + + for (cpu = 0; cpu < NR_CPUS; cpu++) { +#ifdef CONFIG_NUMA + /* Early boot. Slab allocator not functional yet */ + zone_pcp(zone, cpu) = &boot_pageset[cpu]; + setup_pageset(&boot_pageset[cpu],0); +#else + setup_pageset(zone_pcp(zone,cpu), batch); +#endif + } + if (zone->present_pages) + printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%lu\n", + zone->name, zone->present_pages, batch); +} + +__meminit int init_currently_empty_zone(struct zone *zone, + unsigned long zone_start_pfn, + unsigned long size, + enum memmap_context context) +{ + struct pglist_data *pgdat = zone->zone_pgdat; + int ret; + ret = zone_wait_table_init(zone, size); + if (ret) + return ret; + pgdat->nr_zones = zone_idx(zone) + 1; + + zone->zone_start_pfn = zone_start_pfn; + + memmap_init(size, pgdat->node_id, zone_idx(zone), zone_start_pfn); + + zone_init_free_lists(pgdat, zone, zone->spanned_pages); + + return 0; +} + +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +/* + * Basic iterator support. Return the first range of PFNs for a node + * Note: nid == MAX_NUMNODES returns first region regardless of node + */ +static int __init first_active_region_index_in_nid(int nid) +{ + int i; + + for (i = 0; i < nr_nodemap_entries; i++) + if (nid == MAX_NUMNODES || early_node_map[i].nid == nid) + return i; + + return -1; +} + +/* + * Basic iterator support. Return the next active range of PFNs for a node + * Note: nid == MAX_NUMNODES returns next region regardles of node + */ +static int __init next_active_region_index_in_nid(int index, int nid) +{ + for (index = index + 1; index < nr_nodemap_entries; index++) + if (nid == MAX_NUMNODES || early_node_map[index].nid == nid) + return index; + + return -1; +} + +#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID +/* + * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. + * Architectures may implement their own version but if add_active_range() + * was used and there are no special requirements, this is a convenient + * alternative + */ +int __init early_pfn_to_nid(unsigned long pfn) +{ + int i; + + for (i = 0; i < nr_nodemap_entries; i++) { + unsigned long start_pfn = early_node_map[i].start_pfn; + unsigned long end_pfn = early_node_map[i].end_pfn; + + if (start_pfn <= pfn && pfn < end_pfn) + return early_node_map[i].nid; + } + + return 0; +} +#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ + +/* Basic iterator support to walk early_node_map[] */ +#define for_each_active_range_index_in_nid(i, nid) \ + for (i = first_active_region_index_in_nid(nid); i != -1; \ + i = next_active_region_index_in_nid(i, nid)) + +/** + * free_bootmem_with_active_regions - Call free_bootmem_node for each active range + * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed. + * @max_low_pfn: The highest PFN that will be passed to free_bootmem_node + * + * If an architecture guarantees that all ranges registered with + * add_active_ranges() contain no holes and may be freed, this + * this function may be used instead of calling free_bootmem() manually. + */ +void __init free_bootmem_with_active_regions(int nid, + unsigned long max_low_pfn) +{ + int i; + + for_each_active_range_index_in_nid(i, nid) { + unsigned long size_pages = 0; + unsigned long end_pfn = early_node_map[i].end_pfn; + + if (early_node_map[i].start_pfn >= max_low_pfn) + continue; + + if (end_pfn > max_low_pfn) + end_pfn = max_low_pfn; + + size_pages = end_pfn - early_node_map[i].start_pfn; + free_bootmem_node(NODE_DATA(early_node_map[i].nid), + PFN_PHYS(early_node_map[i].start_pfn), + size_pages << PAGE_SHIFT); + } +} + +/** + * sparse_memory_present_with_active_regions - Call memory_present for each active range + * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used. + * + * If an architecture guarantees that all ranges registered with + * add_active_ranges() contain no holes and may be freed, this + * function may be used instead of calling memory_present() manually. + */ +void __init sparse_memory_present_with_active_regions(int nid) +{ + int i; + + for_each_active_range_index_in_nid(i, nid) + memory_present(early_node_map[i].nid, + early_node_map[i].start_pfn, + early_node_map[i].end_pfn); +} + +/** + * push_node_boundaries - Push node boundaries to at least the requested boundary + * @nid: The nid of the node to push the boundary for + * @start_pfn: The start pfn of the node + * @end_pfn: The end pfn of the node + * + * In reserve-based hot-add, mem_map is allocated that is unused until hotadd + * time. Specifically, on x86_64, SRAT will report ranges that can potentially + * be hotplugged even though no physical memory exists. This function allows + * an arch to push out the node boundaries so mem_map is allocated that can + * be used later. + */ +#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE +void __init push_node_boundaries(unsigned int nid, + unsigned long start_pfn, unsigned long end_pfn) +{ + printk(KERN_DEBUG "Entering push_node_boundaries(%u, %lu, %lu)\n", + nid, start_pfn, end_pfn); + + /* Initialise the boundary for this node if necessary */ + if (node_boundary_end_pfn[nid] == 0) + node_boundary_start_pfn[nid] = -1UL; + + /* Update the boundaries */ + if (node_boundary_start_pfn[nid] > start_pfn) + node_boundary_start_pfn[nid] = start_pfn; + if (node_boundary_end_pfn[nid] < end_pfn) + node_boundary_end_pfn[nid] = end_pfn; +} + +/* If necessary, push the node boundary out for reserve hotadd */ +static void __init account_node_boundary(unsigned int nid, + unsigned long *start_pfn, unsigned long *end_pfn) +{ + printk(KERN_DEBUG "Entering account_node_boundary(%u, %lu, %lu)\n", + nid, *start_pfn, *end_pfn); + + /* Return if boundary information has not been provided */ + if (node_boundary_end_pfn[nid] == 0) + return; + + /* Check the boundaries and update if necessary */ + if (node_boundary_start_pfn[nid] < *start_pfn) + *start_pfn = node_boundary_start_pfn[nid]; + if (node_boundary_end_pfn[nid] > *end_pfn) + *end_pfn = node_boundary_end_pfn[nid]; +} +#else +void __init push_node_boundaries(unsigned int nid, + unsigned long start_pfn, unsigned long end_pfn) {} + +static void __init account_node_boundary(unsigned int nid, + unsigned long *start_pfn, unsigned long *end_pfn) {} +#endif + + +/** + * get_pfn_range_for_nid - Return the start and end page frames for a node + * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned. + * @start_pfn: Passed by reference. On return, it will have the node start_pfn. + * @end_pfn: Passed by reference. On return, it will have the node end_pfn. + * + * It returns the start and end page frame of a node based on information + * provided by an arch calling add_active_range(). If called for a node + * with no available memory, a warning is printed and the start and end + * PFNs will be 0. + */ +void __init get_pfn_range_for_nid(unsigned int nid, + unsigned long *start_pfn, unsigned long *end_pfn) +{ + int i; + *start_pfn = -1UL; + *end_pfn = 0; + + for_each_active_range_index_in_nid(i, nid) { + *start_pfn = min(*start_pfn, early_node_map[i].start_pfn); + *end_pfn = max(*end_pfn, early_node_map[i].end_pfn); + } + + if (*start_pfn == -1UL) { + printk(KERN_WARNING "Node %u active with no memory\n", nid); + *start_pfn = 0; + } + + /* Push the node boundaries out if requested */ + account_node_boundary(nid, start_pfn, end_pfn); +} + +/* + * Return the number of pages a zone spans in a node, including holes + * present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node() + */ +unsigned long __init zone_spanned_pages_in_node(int nid, + unsigned long zone_type, + unsigned long *ignored) +{ + unsigned long node_start_pfn, node_end_pfn; + unsigned long zone_start_pfn, zone_end_pfn; + + /* Get the start and end of the node and zone */ + get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn); + zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type]; + zone_end_pfn = arch_zone_highest_possible_pfn[zone_type]; + + /* Check that this node has pages within the zone's required range */ + if (zone_end_pfn < node_start_pfn || zone_start_pfn > node_end_pfn) + return 0; + + /* Move the zone boundaries inside the node if necessary */ + zone_end_pfn = min(zone_end_pfn, node_end_pfn); + zone_start_pfn = max(zone_start_pfn, node_start_pfn); + + /* Return the spanned pages */ + return zone_end_pfn - zone_start_pfn; +} + +/* + * Return the number of holes in a range on a node. If nid is MAX_NUMNODES, + * then all holes in the requested range will be accounted for. + */ +unsigned long __init __absent_pages_in_range(int nid, + unsigned long range_start_pfn, + unsigned long range_end_pfn) +{ + int i = 0; + unsigned long prev_end_pfn = 0, hole_pages = 0; + unsigned long start_pfn; + + /* Find the end_pfn of the first active range of pfns in the node */ + i = first_active_region_index_in_nid(nid); + if (i == -1) + return 0; + + /* Account for ranges before physical memory on this node */ + if (early_node_map[i].start_pfn > range_start_pfn) + hole_pages = early_node_map[i].start_pfn - range_start_pfn; + + prev_end_pfn = early_node_map[i].start_pfn; + + /* Find all holes for the zone within the node */ + for (; i != -1; i = next_active_region_index_in_nid(i, nid)) { + + /* No need to continue if prev_end_pfn is outside the zone */ + if (prev_end_pfn >= range_end_pfn) + break; + + /* Make sure the end of the zone is not within the hole */ + start_pfn = min(early_node_map[i].start_pfn, range_end_pfn); + prev_end_pfn = max(prev_end_pfn, range_start_pfn); + + /* Update the hole size cound and move on */ + if (start_pfn > range_start_pfn) { + BUG_ON(prev_end_pfn > start_pfn); + hole_pages += start_pfn - prev_end_pfn; + } + prev_end_pfn = early_node_map[i].end_pfn; + } + + /* Account for ranges past physical memory on this node */ + if (range_end_pfn > prev_end_pfn) + hole_pages += range_end_pfn - + max(range_start_pfn, prev_end_pfn); + + return hole_pages; +} + +/** + * absent_pages_in_range - Return number of page frames in holes within a range + * @start_pfn: The start PFN to start searching for holes + * @end_pfn: The end PFN to stop searching for holes + * + * It returns the number of pages frames in memory holes within a range. + */ +unsigned long __init absent_pages_in_range(unsigned long start_pfn, + unsigned long end_pfn) +{ + return __absent_pages_in_range(MAX_NUMNODES, start_pfn, end_pfn); +} + +/* Return the number of page frames in holes in a zone on a node */ +unsigned long __init zone_absent_pages_in_node(int nid, + unsigned long zone_type, + unsigned long *ignored) +{ + unsigned long node_start_pfn, node_end_pfn; + unsigned long zone_start_pfn, zone_end_pfn; + + get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn); + zone_start_pfn = max(arch_zone_lowest_possible_pfn[zone_type], + node_start_pfn); + zone_end_pfn = min(arch_zone_highest_possible_pfn[zone_type], + node_end_pfn); + + return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn); +} + +#else +static inline unsigned long zone_spanned_pages_in_node(int nid, + unsigned long zone_type, + unsigned long *zones_size) +{ + return zones_size[zone_type]; +} -/* - * This is an integer logarithm so that shifts can be used later - * to extract the more random high bits from the multiplicative - * hash function before the remainder is taken. - */ -static inline unsigned long wait_table_bits(unsigned long size) +static inline unsigned long zone_absent_pages_in_node(int nid, + unsigned long zone_type, + unsigned long *zholes_size) { - return ffz(~size); + if (!zholes_size) + return 0; + + return zholes_size[zone_type]; } -#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1)) +#endif -static void __init calculate_zone_totalpages(struct pglist_data *pgdat, +static void __init calculate_node_totalpages(struct pglist_data *pgdat, unsigned long *zones_size, unsigned long *zholes_size) { unsigned long realtotalpages, totalpages = 0; - int i; + enum zone_type i; for (i = 0; i < MAX_NR_ZONES; i++) - totalpages += zones_size[i]; + totalpages += zone_spanned_pages_in_node(pgdat->node_id, i, + zones_size); pgdat->node_spanned_pages = totalpages; realtotalpages = totalpages; - if (zholes_size) - for (i = 0; i < MAX_NR_ZONES; i++) - realtotalpages -= zholes_size[i]; + for (i = 0; i < MAX_NR_ZONES; i++) + realtotalpages -= + zone_absent_pages_in_node(pgdat->node_id, i, + zholes_size); pgdat->node_present_pages = realtotalpages; - printk("On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages); -} - - -/* - * Initially all pages are reserved - free ones are freed - * up by free_all_bootmem() once the early boot process is - * done. Non-atomic initialization, single-pass. - */ -void __init memmap_init_zone(struct page *start, unsigned long size, int nid, - unsigned long zone, unsigned long start_pfn) -{ - struct page *page; - - for (page = start; page < (start + size); page++) { - set_page_zone(page, NODEZONE(nid, zone)); - set_page_count(page, 0); - SetPageReserved(page); - INIT_LIST_HEAD(&page->lru); -#ifdef WANT_PAGE_VIRTUAL - /* The shift won't overflow because ZONE_NORMAL is below 4G. */ - if (zone != ZONE_HIGHMEM) - set_page_address(page, __va(start_pfn << PAGE_SHIFT)); -#endif - start_pfn++; - } + printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, + realtotalpages); } -#ifndef __HAVE_ARCH_MEMMAP_INIT -#define memmap_init(start, size, nid, zone, start_pfn) \ - memmap_init_zone((start), (size), (nid), (zone), (start_pfn)) -#endif - /* * Set up the zone data structures: * - mark all pages reserved * - mark all memory queues empty * - clear the memory bitmaps */ -static void __init free_area_init_core(struct pglist_data *pgdat, +static void __meminit free_area_init_core(struct pglist_data *pgdat, unsigned long *zones_size, unsigned long *zholes_size) { - unsigned long i, j; - const unsigned long zone_required_alignment = 1UL << (MAX_ORDER-1); - int cpu, nid = pgdat->node_id; - struct page *lmem_map = pgdat->node_mem_map; + enum zone_type j; + int nid = pgdat->node_id; unsigned long zone_start_pfn = pgdat->node_start_pfn; + int ret; + pgdat_resize_init(pgdat); pgdat->nr_zones = 0; init_waitqueue_head(&pgdat->kswapd_wait); + pgdat->kswapd_max_order = 0; for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; - unsigned long size, realsize; - unsigned long batch; + unsigned long size, realsize, memmap_pages; + + size = zone_spanned_pages_in_node(nid, j, zones_size); + realsize = size - zone_absent_pages_in_node(nid, j, + zholes_size); + + /* + * Adjust realsize so that it accounts for how much memory + * is used by this zone for memmap. This affects the watermark + * and per-cpu initialisations + */ + memmap_pages = (size * sizeof(struct page)) >> PAGE_SHIFT; + if (realsize >= memmap_pages) { + realsize -= memmap_pages; + printk(KERN_DEBUG + " %s zone: %lu pages used for memmap\n", + zone_names[j], memmap_pages); + } else + printk(KERN_WARNING + " %s zone: %lu pages exceeds realsize %lu\n", + zone_names[j], memmap_pages, realsize); + + /* Account for reserved DMA pages */ + if (j == ZONE_DMA && realsize > dma_reserve) { + realsize -= dma_reserve; + printk(KERN_DEBUG " DMA zone: %lu pages reserved\n", + dma_reserve); + } - zone_table[NODEZONE(nid, j)] = zone; - realsize = size = zones_size[j]; - if (zholes_size) - realsize -= zholes_size[j]; + if (!is_highmem_idx(j)) + nr_kernel_pages += realsize; + nr_all_pages += realsize; zone->spanned_pages = size; zone->present_pages = realsize; +#ifdef CONFIG_NUMA + zone->node = nid; + zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio) + / 100; + zone->min_slab_pages = (realsize * sysctl_min_slab_ratio) / 100; +#endif zone->name = zone_names[j]; spin_lock_init(&zone->lock); spin_lock_init(&zone->lru_lock); + zone_seqlock_init(zone); zone->zone_pgdat = pgdat; zone->free_pages = 0; - zone->temp_priority = zone->prev_priority = DEF_PRIORITY; - - /* - * The per-cpu-pages pools are set to around 1000th of the - * size of the zone. But no more than 1/4 of a meg - there's - * no point in going beyond the size of L2 cache. - * - * OK, so we don't know how big the cache is. So guess. - */ - batch = zone->present_pages / 1024; - if (batch * PAGE_SIZE > 256 * 1024) - batch = (256 * 1024) / PAGE_SIZE; - batch /= 4; /* We effectively *= 4 below */ - if (batch < 1) - batch = 1; - - for (cpu = 0; cpu < NR_CPUS; cpu++) { - struct per_cpu_pages *pcp; - - pcp = &zone->pageset[cpu].pcp[0]; /* hot */ - pcp->count = 0; - pcp->low = 2 * batch; - pcp->high = 6 * batch; - pcp->batch = 1 * batch; - INIT_LIST_HEAD(&pcp->list); + zone->prev_priority = DEF_PRIORITY; - pcp = &zone->pageset[cpu].pcp[1]; /* cold */ - pcp->count = 0; - pcp->low = 0; - pcp->high = 2 * batch; - pcp->batch = 1 * batch; - INIT_LIST_HEAD(&pcp->list); - } - printk(" %s zone: %lu pages, LIFO batch:%lu\n", - zone_names[j], realsize, batch); + zone_pcp_init(zone); INIT_LIST_HEAD(&zone->active_list); INIT_LIST_HEAD(&zone->inactive_list); - atomic_set(&zone->nr_scan_active, 0); - atomic_set(&zone->nr_scan_inactive, 0); + zone->nr_scan_active = 0; + zone->nr_scan_inactive = 0; zone->nr_active = 0; zone->nr_inactive = 0; + zap_zone_vm_stats(zone); + atomic_set(&zone->reclaim_in_progress, 0); if (!size) continue; - /* - * The per-page waitqueue mechanism uses hashed waitqueues - * per zone. - */ - zone->wait_table_size = wait_table_size(size); - zone->wait_table_bits = - wait_table_bits(zone->wait_table_size); - zone->wait_table = (wait_queue_head_t *) - alloc_bootmem_node(pgdat, zone->wait_table_size - * sizeof(wait_queue_head_t)); - - for(i = 0; i < zone->wait_table_size; ++i) - init_waitqueue_head(zone->wait_table + i); - - pgdat->nr_zones = j+1; - - zone->zone_mem_map = lmem_map; - zone->zone_start_pfn = zone_start_pfn; - - if ((zone_start_pfn) & (zone_required_alignment-1)) - printk("BUG: wrong zone alignment, it will crash\n"); - - memmap_init(lmem_map, size, nid, j, zone_start_pfn); - + ret = init_currently_empty_zone(zone, zone_start_pfn, + size, MEMMAP_EARLY); + BUG_ON(ret); zone_start_pfn += size; - lmem_map += size; + } +} - for (i = 0; ; i++) { - unsigned long bitmap_size; +static void __init alloc_node_mem_map(struct pglist_data *pgdat) +{ + /* Skip empty nodes */ + if (!pgdat->node_spanned_pages) + return; - INIT_LIST_HEAD(&zone->free_area[i].free_list); - if (i == MAX_ORDER-1) { - zone->free_area[i].map = NULL; - break; - } +#ifdef CONFIG_FLAT_NODE_MEM_MAP + /* ia64 gets its own node_mem_map, before this, without bootmem */ + if (!pgdat->node_mem_map) { + unsigned long size, start, end; + struct page *map; - /* - * Page buddy system uses "index >> (i+1)", - * where "index" is at most "size-1". - * - * The extra "+3" is to round down to byte - * size (8 bits per byte assumption). Thus - * we get "(size-1) >> (i+4)" as the last byte - * we can access. - * - * The "+1" is because we want to round the - * byte allocation up rather than down. So - * we should have had a "+7" before we shifted - * down by three. Also, we have to add one as - * we actually _use_ the last bit (it's [0,n] - * inclusive, not [0,n[). - * - * So we actually had +7+1 before we shift - * down by 3. But (n+8) >> 3 == (n >> 3) + 1 - * (modulo overflows, which we do not have). - * - * Finally, we LONG_ALIGN because all bitmap - * operations are on longs. - */ - bitmap_size = (size-1) >> (i+4); - bitmap_size = LONG_ALIGN(bitmap_size+1); - zone->free_area[i].map = - (unsigned long *) alloc_bootmem_node(pgdat, bitmap_size); - } + /* + * The zone's endpoints aren't required to be MAX_ORDER + * aligned but the node_mem_map endpoints must be in order + * for the buddy allocator to function correctly. + */ + start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1); + end = pgdat->node_start_pfn + pgdat->node_spanned_pages; + end = ALIGN(end, MAX_ORDER_NR_PAGES); + size = (end - start) * sizeof(struct page); + map = alloc_remap(pgdat->node_id, size); + if (!map) + map = alloc_bootmem_node(pgdat, size); + pgdat->node_mem_map = map + (pgdat->node_start_pfn - start); + } +#ifdef CONFIG_FLATMEM + /* + * With no DISCONTIG, the global mem_map is just set as node 0's + */ + if (pgdat == NODE_DATA(0)) { + mem_map = NODE_DATA(0)->node_mem_map; +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP + if (page_to_pfn(mem_map) != pgdat->node_start_pfn) + mem_map -= pgdat->node_start_pfn; +#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ } +#endif +#endif /* CONFIG_FLAT_NODE_MEM_MAP */ } -void __init free_area_init_node(int nid, struct pglist_data *pgdat, - struct page *node_mem_map, unsigned long *zones_size, - unsigned long node_start_pfn, unsigned long *zholes_size) +void __meminit free_area_init_node(int nid, struct pglist_data *pgdat, + unsigned long *zones_size, unsigned long node_start_pfn, + unsigned long *zholes_size) { - unsigned long size; - pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; - calculate_zone_totalpages(pgdat, zones_size, zholes_size); - if (!node_mem_map) { - size = (pgdat->node_spanned_pages + 1) * sizeof(struct page); - node_mem_map = alloc_bootmem_node(pgdat, size); - } - pgdat->node_mem_map = node_mem_map; + calculate_node_totalpages(pgdat, zones_size, zholes_size); + + alloc_node_mem_map(pgdat); free_area_init_core(pgdat, zones_size, zholes_size); } -#ifndef CONFIG_DISCONTIGMEM -static bootmem_data_t contig_bootmem_data; -struct pglist_data contig_page_data = { .bdata = &contig_bootmem_data }; +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +/** + * add_active_range - Register a range of PFNs backed by physical memory + * @nid: The node ID the range resides on + * @start_pfn: The start PFN of the available physical memory + * @end_pfn: The end PFN of the available physical memory + * + * These ranges are stored in an early_node_map[] and later used by + * free_area_init_nodes() to calculate zone sizes and holes. If the + * range spans a memory hole, it is up to the architecture to ensure + * the memory is not freed by the bootmem allocator. If possible + * the range being registered will be merged with existing ranges. + */ +void __init add_active_range(unsigned int nid, unsigned long start_pfn, + unsigned long end_pfn) +{ + int i; -EXPORT_SYMBOL(contig_page_data); + printk(KERN_DEBUG "Entering add_active_range(%d, %lu, %lu) " + "%d entries of %d used\n", + nid, start_pfn, end_pfn, + nr_nodemap_entries, MAX_ACTIVE_REGIONS); -void __init free_area_init(unsigned long *zones_size) -{ - free_area_init_node(0, &contig_page_data, NULL, zones_size, - __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL); - mem_map = contig_page_data.node_mem_map; -} -#endif + /* Merge with existing active regions if possible */ + for (i = 0; i < nr_nodemap_entries; i++) { + if (early_node_map[i].nid != nid) + continue; -#ifdef CONFIG_PROC_FS + /* Skip if an existing region covers this new one */ + if (start_pfn >= early_node_map[i].start_pfn && + end_pfn <= early_node_map[i].end_pfn) + return; -#include + /* Merge forward if suitable */ + if (start_pfn <= early_node_map[i].end_pfn && + end_pfn > early_node_map[i].end_pfn) { + early_node_map[i].end_pfn = end_pfn; + return; + } -static void *frag_start(struct seq_file *m, loff_t *pos) -{ - pg_data_t *pgdat; - loff_t node = *pos; + /* Merge backward if suitable */ + if (start_pfn < early_node_map[i].end_pfn && + end_pfn >= early_node_map[i].start_pfn) { + early_node_map[i].start_pfn = start_pfn; + return; + } + } - for (pgdat = pgdat_list; pgdat && node; pgdat = pgdat->pgdat_next) - --node; + /* Check that early_node_map is large enough */ + if (i >= MAX_ACTIVE_REGIONS) { + printk(KERN_CRIT "More than %d memory regions, truncating\n", + MAX_ACTIVE_REGIONS); + return; + } - return pgdat; + early_node_map[i].nid = nid; + early_node_map[i].start_pfn = start_pfn; + early_node_map[i].end_pfn = end_pfn; + nr_nodemap_entries = i + 1; } -static void *frag_next(struct seq_file *m, void *arg, loff_t *pos) +/** + * shrink_active_range - Shrink an existing registered range of PFNs + * @nid: The node id the range is on that should be shrunk + * @old_end_pfn: The old end PFN of the range + * @new_end_pfn: The new PFN of the range + * + * i386 with NUMA use alloc_remap() to store a node_mem_map on a local node. + * The map is kept at the end physical page range that has already been + * registered with add_active_range(). This function allows an arch to shrink + * an existing registered range. + */ +void __init shrink_active_range(unsigned int nid, unsigned long old_end_pfn, + unsigned long new_end_pfn) { - pg_data_t *pgdat = (pg_data_t *)arg; + int i; - (*pos)++; - return pgdat->pgdat_next; + /* Find the old active region end and shrink */ + for_each_active_range_index_in_nid(i, nid) + if (early_node_map[i].end_pfn == old_end_pfn) { + early_node_map[i].end_pfn = new_end_pfn; + break; + } } -static void frag_stop(struct seq_file *m, void *arg) +/** + * remove_all_active_ranges - Remove all currently registered regions + * + * During discovery, it may be found that a table like SRAT is invalid + * and an alternative discovery method must be used. This function removes + * all currently registered regions. + */ +void __init remove_all_active_ranges(void) { + memset(early_node_map, 0, sizeof(early_node_map)); + nr_nodemap_entries = 0; +#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE + memset(node_boundary_start_pfn, 0, sizeof(node_boundary_start_pfn)); + memset(node_boundary_end_pfn, 0, sizeof(node_boundary_end_pfn)); +#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */ } -/* - * This walks the freelist for each zone. Whilst this is slow, I'd rather - * be slow here than slow down the fast path by keeping stats - mjbligh - */ -static int frag_show(struct seq_file *m, void *arg) +/* Compare two active node_active_regions */ +static int __init cmp_node_active_region(const void *a, const void *b) { - pg_data_t *pgdat = (pg_data_t *)arg; - struct zone *zone; - struct zone *node_zones = pgdat->node_zones; - unsigned long flags; - int order; + struct node_active_region *arange = (struct node_active_region *)a; + struct node_active_region *brange = (struct node_active_region *)b; - for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { - if (!zone->present_pages) - continue; + /* Done this way to avoid overflows */ + if (arange->start_pfn > brange->start_pfn) + return 1; + if (arange->start_pfn < brange->start_pfn) + return -1; - spin_lock_irqsave(&zone->lock, flags); - seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name); - for (order = 0; order < MAX_ORDER; ++order) { - unsigned long nr_bufs = 0; - struct list_head *elem; - - list_for_each(elem, &(zone->free_area[order].free_list)) - ++nr_bufs; - seq_printf(m, "%6lu ", nr_bufs); - } - spin_unlock_irqrestore(&zone->lock, flags); - seq_putc(m, '\n'); - } return 0; } -struct seq_operations fragmentation_op = { - .start = frag_start, - .next = frag_next, - .stop = frag_stop, - .show = frag_show, -}; - -static char *vmstat_text[] = { - "nr_dirty", - "nr_writeback", - "nr_unstable", - "nr_page_table_pages", - "nr_mapped", - "nr_slab", - - "pgpgin", - "pgpgout", - "pswpin", - "pswpout", - "pgalloc_high", - - "pgalloc_normal", - "pgalloc_dma", - "pgfree", - "pgactivate", - "pgdeactivate", - - "pgfault", - "pgmajfault", - "pgrefill_high", - "pgrefill_normal", - "pgrefill_dma", - - "pgsteal_high", - "pgsteal_normal", - "pgsteal_dma", - "pgscan_kswapd_high", - "pgscan_kswapd_normal", - - "pgscan_kswapd_dma", - "pgscan_direct_high", - "pgscan_direct_normal", - "pgscan_direct_dma", - "pginodesteal", - - "slabs_scanned", - "kswapd_steal", - "kswapd_inodesteal", - "pageoutrun", - "allocstall", - - "pgrotated", -}; +/* sort the node_map by start_pfn */ +static void __init sort_node_map(void) +{ + sort(early_node_map, (size_t)nr_nodemap_entries, + sizeof(struct node_active_region), + cmp_node_active_region, NULL); +} -static void *vmstat_start(struct seq_file *m, loff_t *pos) +/* Find the lowest pfn for a node. This depends on a sorted early_node_map */ +unsigned long __init find_min_pfn_for_node(unsigned long nid) { - struct page_state *ps; + int i; - if (*pos >= ARRAY_SIZE(vmstat_text)) - return NULL; + /* Regions in the early_node_map can be in any order */ + sort_node_map(); + + /* Assuming a sorted map, the first range found has the starting pfn */ + for_each_active_range_index_in_nid(i, nid) + return early_node_map[i].start_pfn; - ps = kmalloc(sizeof(*ps), GFP_KERNEL); - m->private = ps; - if (!ps) - return ERR_PTR(-ENOMEM); - get_full_page_state(ps); - ps->pgpgin /= 2; /* sectors -> kbytes */ - ps->pgpgout /= 2; - return (unsigned long *)ps + *pos; + printk(KERN_WARNING "Could not find start_pfn for node %lu\n", nid); + return 0; } -static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos) +/** + * find_min_pfn_with_active_regions - Find the minimum PFN registered + * + * It returns the minimum PFN based on information provided via + * add_active_range(). + */ +unsigned long __init find_min_pfn_with_active_regions(void) { - (*pos)++; - if (*pos >= ARRAY_SIZE(vmstat_text)) - return NULL; - return (unsigned long *)m->private + *pos; + return find_min_pfn_for_node(MAX_NUMNODES); } -static int vmstat_show(struct seq_file *m, void *arg) +/** + * find_max_pfn_with_active_regions - Find the maximum PFN registered + * + * It returns the maximum PFN based on information provided via + * add_active_range(). + */ +unsigned long __init find_max_pfn_with_active_regions(void) { - unsigned long *l = arg; - unsigned long off = l - (unsigned long *)m->private; + int i; + unsigned long max_pfn = 0; - seq_printf(m, "%s %lu\n", vmstat_text[off], *l); - return 0; + for (i = 0; i < nr_nodemap_entries; i++) + max_pfn = max(max_pfn, early_node_map[i].end_pfn); + + return max_pfn; +} + +/** + * free_area_init_nodes - Initialise all pg_data_t and zone data + * @max_zone_pfn: an array of max PFNs for each zone + * + * This will call free_area_init_node() for each active node in the system. + * Using the page ranges provided by add_active_range(), the size of each + * zone in each node and their holes is calculated. If the maximum PFN + * between two adjacent zones match, it is assumed that the zone is empty. + * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed + * that arch_max_dma32_pfn has no pages. It is also assumed that a zone + * starts where the previous one ended. For example, ZONE_DMA32 starts + * at arch_max_dma_pfn. + */ +void __init free_area_init_nodes(unsigned long *max_zone_pfn) +{ + unsigned long nid; + enum zone_type i; + + /* Record where the zone boundaries are */ + memset(arch_zone_lowest_possible_pfn, 0, + sizeof(arch_zone_lowest_possible_pfn)); + memset(arch_zone_highest_possible_pfn, 0, + sizeof(arch_zone_highest_possible_pfn)); + arch_zone_lowest_possible_pfn[0] = find_min_pfn_with_active_regions(); + arch_zone_highest_possible_pfn[0] = max_zone_pfn[0]; + for (i = 1; i < MAX_NR_ZONES; i++) { + arch_zone_lowest_possible_pfn[i] = + arch_zone_highest_possible_pfn[i-1]; + arch_zone_highest_possible_pfn[i] = + max(max_zone_pfn[i], arch_zone_lowest_possible_pfn[i]); + } + + /* Print out the zone ranges */ + printk("Zone PFN ranges:\n"); + for (i = 0; i < MAX_NR_ZONES; i++) + printk(" %-8s %8lu -> %8lu\n", + zone_names[i], + arch_zone_lowest_possible_pfn[i], + arch_zone_highest_possible_pfn[i]); + + /* Print out the early_node_map[] */ + printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries); + for (i = 0; i < nr_nodemap_entries; i++) + printk(" %3d: %8lu -> %8lu\n", early_node_map[i].nid, + early_node_map[i].start_pfn, + early_node_map[i].end_pfn); + + /* Initialise every node */ + for_each_online_node(nid) { + pg_data_t *pgdat = NODE_DATA(nid); + free_area_init_node(nid, pgdat, NULL, + find_min_pfn_for_node(nid), NULL); + } } +#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ -static void vmstat_stop(struct seq_file *m, void *arg) +/** + * set_dma_reserve - set the specified number of pages reserved in the first zone + * @new_dma_reserve: The number of pages to mark reserved + * + * The per-cpu batchsize and zone watermarks are determined by present_pages. + * In the DMA zone, a significant percentage may be consumed by kernel image + * and other unfreeable allocations which can skew the watermarks badly. This + * function may optionally be used to account for unfreeable pages in the + * first zone (e.g., ZONE_DMA). The effect will be lower watermarks and + * smaller per-cpu batchsize. + */ +void __init set_dma_reserve(unsigned long new_dma_reserve) { - kfree(m->private); - m->private = NULL; + dma_reserve = new_dma_reserve; } -struct seq_operations vmstat_op = { - .start = vmstat_start, - .next = vmstat_next, - .stop = vmstat_stop, - .show = vmstat_show, -}; +#ifndef CONFIG_NEED_MULTIPLE_NODES +static bootmem_data_t contig_bootmem_data; +struct pglist_data contig_page_data = { .bdata = &contig_bootmem_data }; -#endif /* CONFIG_PROC_FS */ +EXPORT_SYMBOL(contig_page_data); +#endif + +void __init free_area_init(unsigned long *zones_size) +{ + free_area_init_node(0, NODE_DATA(0), zones_size, + __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL); +} -#ifdef CONFIG_HOTPLUG_CPU static int page_alloc_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { int cpu = (unsigned long)hcpu; - long *count; if (action == CPU_DEAD) { - /* Drain local pagecache count. */ - count = &per_cpu(nr_pagecache_local, cpu); - atomic_add(*count, &nr_pagecache); - *count = 0; local_irq_disable(); __drain_pages(cpu); + vm_events_fold_cpu(cpu); local_irq_enable(); + refresh_cpu_vm_stats(cpu); } return NOTIFY_OK; } -#endif /* CONFIG_HOTPLUG_CPU */ void __init page_alloc_init(void) { hotcpu_notifier(page_alloc_cpu_notify, 0); } -static unsigned long higherzone_val(struct zone *z, int max_zone, - int alloc_type) +/* + * calculate_totalreserve_pages - called when sysctl_lower_zone_reserve_ratio + * or min_free_kbytes changes. + */ +static void calculate_totalreserve_pages(void) { - int z_idx = zone_idx(z); - struct zone *higherzone; - unsigned long pages; - - /* there is no higher zone to get a contribution from */ - if (z_idx == MAX_NR_ZONES-1) - return 0; + struct pglist_data *pgdat; + unsigned long reserve_pages = 0; + enum zone_type i, j; - higherzone = &z->zone_pgdat->node_zones[z_idx+1]; + for_each_online_pgdat(pgdat) { + for (i = 0; i < MAX_NR_ZONES; i++) { + struct zone *zone = pgdat->node_zones + i; + unsigned long max = 0; - /* We always start with the higher zone's protection value */ - pages = higherzone->protection[alloc_type]; + /* Find valid and maximum lowmem_reserve in the zone */ + for (j = i; j < MAX_NR_ZONES; j++) { + if (zone->lowmem_reserve[j] > max) + max = zone->lowmem_reserve[j]; + } - /* - * We get a lower-zone-protection contribution only if there are - * pages in the higher zone and if we're not the highest zone - * in the current zonelist. e.g., never happens for GFP_DMA. Happens - * only for ZONE_DMA in a GFP_KERNEL allocation and happens for ZONE_DMA - * and ZONE_NORMAL for a GFP_HIGHMEM allocation. - */ - if (higherzone->present_pages && z_idx < alloc_type) - pages += higherzone->pages_low * sysctl_lower_zone_protection; + /* we treat pages_high as reserved pages. */ + max += zone->pages_high; - return pages; + if (max > zone->present_pages) + max = zone->present_pages; + reserve_pages += max; + } + } + totalreserve_pages = reserve_pages; } /* - * setup_per_zone_protection - called whenver min_free_kbytes or - * sysctl_lower_zone_protection changes. Ensures that each zone - * has a correct pages_protected value, so an adequate number of + * setup_per_zone_lowmem_reserve - called whenever + * sysctl_lower_zone_reserve_ratio changes. Ensures that each zone + * has a correct pages reserved value, so an adequate number of * pages are left in the zone after a successful __alloc_pages(). - * - * This algorithm is way confusing. I tries to keep the same behavior - * as we had with the incremental min iterative algorithm. */ -static void setup_per_zone_protection(void) +static void setup_per_zone_lowmem_reserve(void) { struct pglist_data *pgdat; - struct zone *zones, *zone; - int max_zone; - int i, j; + enum zone_type j, idx; - for_each_pgdat(pgdat) { - zones = pgdat->node_zones; + for_each_online_pgdat(pgdat) { + for (j = 0; j < MAX_NR_ZONES; j++) { + struct zone *zone = pgdat->node_zones + j; + unsigned long present_pages = zone->present_pages; - for (i = 0, max_zone = 0; i < MAX_NR_ZONES; i++) - if (zones[i].present_pages) - max_zone = i; + zone->lowmem_reserve[j] = 0; - /* - * For each of the different allocation types: - * GFP_DMA -> GFP_KERNEL -> GFP_HIGHMEM - */ - for (i = 0; i < MAX_NR_ZONES; i++) { - /* - * For each of the zones: - * ZONE_HIGHMEM -> ZONE_NORMAL -> ZONE_DMA - */ - for (j = MAX_NR_ZONES-1; j >= 0; j--) { - zone = &zones[j]; - - /* - * We never protect zones that don't have memory - * in them (j>max_zone) or zones that aren't in - * the zonelists for a certain type of - * allocation (j>i). We have to assign these to - * zero because the lower zones take - * contributions from the higher zones. - */ - if (j > max_zone || j > i) { - zone->protection[i] = 0; - continue; - } - /* - * The contribution of the next higher zone - */ - zone->protection[i] = higherzone_val(zone, - max_zone, i); - zone->protection[i] += zone->pages_low; + idx = j; + while (idx) { + struct zone *lower_zone; + + idx--; + + if (sysctl_lowmem_reserve_ratio[idx] < 1) + sysctl_lowmem_reserve_ratio[idx] = 1; + + lower_zone = pgdat->node_zones + idx; + lower_zone->lowmem_reserve[j] = present_pages / + sysctl_lowmem_reserve_ratio[idx]; + present_pages += lower_zone->present_pages; } } } + + /* update totalreserve_pages */ + calculate_totalreserve_pages(); } -/* - * setup_per_zone_pages_min - called when min_free_kbytes changes. Ensures - * that the pages_{min,low,high} values for each zone are set correctly - * with respect to min_free_kbytes. +/** + * setup_per_zone_pages_min - called when min_free_kbytes changes. + * + * Ensures that the pages_{min,low,high} values for each zone are set correctly + * with respect to min_free_kbytes. */ -static void setup_per_zone_pages_min(void) +void setup_per_zone_pages_min(void) { unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10); unsigned long lowmem_pages = 0; @@ -1863,13 +3128,20 @@ static void setup_per_zone_pages_min(void) } for_each_zone(zone) { + u64 tmp; + spin_lock_irqsave(&zone->lru_lock, flags); + tmp = (u64)pages_min * zone->present_pages; + do_div(tmp, lowmem_pages); if (is_highmem(zone)) { /* - * Often, highmem doesn't need to reserve any pages. - * But the pages_min/low/high values are also used for - * batching up page reclaim activity so we need a - * decent value here. + * __GFP_HIGH and PF_MEMALLOC allocations usually don't + * need highmem pages, so cap pages_min to a small + * value here. + * + * The (pages_high-pages_low) and (pages_low-pages_min) + * deltas controls asynch page reclaim, and so should + * not be capped for highmem. */ int min_pages; @@ -1880,41 +3152,45 @@ static void setup_per_zone_pages_min(void) min_pages = 128; zone->pages_min = min_pages; } else { - /* if it's a lowmem zone, reserve a number of pages + /* + * If it's a lowmem zone, reserve a number of pages * proportionate to the zone's size. */ - zone->pages_min = (pages_min * zone->present_pages) / - lowmem_pages; + zone->pages_min = tmp; } - zone->pages_low = zone->pages_min * 2; - zone->pages_high = zone->pages_min * 3; + zone->pages_low = zone->pages_min + (tmp >> 2); + zone->pages_high = zone->pages_min + (tmp >> 1); spin_unlock_irqrestore(&zone->lru_lock, flags); } + + /* update totalreserve_pages */ + calculate_totalreserve_pages(); } /* * Initialise min_free_kbytes. * * For small machines we want it small (128k min). For large machines - * we want it large (16MB max). But it is not linear, because network + * we want it large (64MB max). But it is not linear, because network * bandwidth does not increase linearly with machine size. We use * - * min_free_kbytes = sqrt(lowmem_kbytes) + * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy: + * min_free_kbytes = sqrt(lowmem_kbytes * 16) * * which yields * - * 16MB: 128k - * 32MB: 181k - * 64MB: 256k - * 128MB: 362k - * 256MB: 512k - * 512MB: 724k - * 1024MB: 1024k - * 2048MB: 1448k - * 4096MB: 2048k - * 8192MB: 2896k - * 16384MB: 4096k + * 16MB: 512k + * 32MB: 724k + * 64MB: 1024k + * 128MB: 1448k + * 256MB: 2048k + * 512MB: 2896k + * 1024MB: 4096k + * 2048MB: 5792k + * 4096MB: 8192k + * 8192MB: 11584k + * 16384MB: 16384k */ static int __init init_per_zone_pages_min(void) { @@ -1922,13 +3198,13 @@ static int __init init_per_zone_pages_min(void) lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10); - min_free_kbytes = int_sqrt(lowmem_kbytes); + min_free_kbytes = int_sqrt(lowmem_kbytes * 16); if (min_free_kbytes < 128) min_free_kbytes = 128; - if (min_free_kbytes > 16384) - min_free_kbytes = 16384; + if (min_free_kbytes > 65536) + min_free_kbytes = 65536; setup_per_zone_pages_min(); - setup_per_zone_protection(); + setup_per_zone_lowmem_reserve(); return 0; } module_init(init_per_zone_pages_min) @@ -1939,23 +3215,209 @@ module_init(init_per_zone_pages_min) * changes. */ int min_free_kbytes_sysctl_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length) + struct file *file, void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec(table, write, file, buffer, length); + proc_dointvec(table, write, file, buffer, length, ppos); setup_per_zone_pages_min(); - setup_per_zone_protection(); + return 0; +} + +#ifdef CONFIG_NUMA +int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write, + struct file *file, void __user *buffer, size_t *length, loff_t *ppos) +{ + struct zone *zone; + int rc; + + rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos); + if (rc) + return rc; + + for_each_zone(zone) + zone->min_unmapped_pages = (zone->present_pages * + sysctl_min_unmapped_ratio) / 100; + return 0; +} + +int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, + struct file *file, void __user *buffer, size_t *length, loff_t *ppos) +{ + struct zone *zone; + int rc; + + rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos); + if (rc) + return rc; + + for_each_zone(zone) + zone->min_slab_pages = (zone->present_pages * + sysctl_min_slab_ratio) / 100; + return 0; +} +#endif + +/* + * lowmem_reserve_ratio_sysctl_handler - just a wrapper around + * proc_dointvec() so that we can call setup_per_zone_lowmem_reserve() + * whenever sysctl_lowmem_reserve_ratio changes. + * + * The reserve ratio obviously has absolutely no relation with the + * pages_min watermarks. The lowmem reserve ratio can only make sense + * if in function of the boot time zone sizes. + */ +int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, + struct file *file, void __user *buffer, size_t *length, loff_t *ppos) +{ + proc_dointvec_minmax(table, write, file, buffer, length, ppos); + setup_per_zone_lowmem_reserve(); return 0; } /* - * lower_zone_protection_sysctl_handler - just a wrapper around - * proc_dointvec() so that we can call setup_per_zone_protection() - * whenever sysctl_lower_zone_protection changes. + * percpu_pagelist_fraction - changes the pcp->high for each zone on each + * cpu. It is the fraction of total pages in each zone that a hot per cpu pagelist + * can have before it gets flushed back to buddy allocator. */ -int lower_zone_protection_sysctl_handler(ctl_table *table, int write, - struct file *file, void __user *buffer, size_t *length) + +int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write, + struct file *file, void __user *buffer, size_t *length, loff_t *ppos) { - proc_dointvec_minmax(table, write, file, buffer, length); - setup_per_zone_protection(); + struct zone *zone; + unsigned int cpu; + int ret; + + ret = proc_dointvec_minmax(table, write, file, buffer, length, ppos); + if (!write || (ret == -EINVAL)) + return ret; + for_each_zone(zone) { + for_each_online_cpu(cpu) { + unsigned long high; + high = zone->present_pages / percpu_pagelist_fraction; + setup_pagelist_highmark(zone_pcp(zone, cpu), high); + } + } return 0; } + +int hashdist = HASHDIST_DEFAULT; + +#ifdef CONFIG_NUMA +static int __init set_hashdist(char *str) +{ + if (!str) + return 0; + hashdist = simple_strtoul(str, &str, 0); + return 1; +} +__setup("hashdist=", set_hashdist); +#endif + +/* + * allocate a large system hash table from bootmem + * - it is assumed that the hash table must contain an exact power-of-2 + * quantity of entries + * - limit is the number of hash buckets, not the total allocation size + */ +void *__init alloc_large_system_hash(const char *tablename, + unsigned long bucketsize, + unsigned long numentries, + int scale, + int flags, + unsigned int *_hash_shift, + unsigned int *_hash_mask, + unsigned long limit) +{ + unsigned long long max = limit; + unsigned long log2qty, size; + void *table = NULL; + + /* allow the kernel cmdline to have a say */ + if (!numentries) { + /* round applicable memory size up to nearest megabyte */ + numentries = nr_kernel_pages; + numentries += (1UL << (20 - PAGE_SHIFT)) - 1; + numentries >>= 20 - PAGE_SHIFT; + numentries <<= 20 - PAGE_SHIFT; + + /* limit to 1 bucket per 2^scale bytes of low memory */ + if (scale > PAGE_SHIFT) + numentries >>= (scale - PAGE_SHIFT); + else + numentries <<= (PAGE_SHIFT - scale); + + /* Make sure we've got at least a 0-order allocation.. */ + if (unlikely((numentries * bucketsize) < PAGE_SIZE)) + numentries = PAGE_SIZE / bucketsize; + } + numentries = roundup_pow_of_two(numentries); + + /* limit allocation size to 1/16 total memory by default */ + if (max == 0) { + max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4; + do_div(max, bucketsize); + } + + if (numentries > max) + numentries = max; + + log2qty = ilog2(numentries); + + do { + size = bucketsize << log2qty; + if (flags & HASH_EARLY) + table = alloc_bootmem(size); + else if (hashdist) + table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL); + else { + unsigned long order; + for (order = 0; ((1UL << order) << PAGE_SHIFT) < size; order++) + ; + table = (void*) __get_free_pages(GFP_ATOMIC, order); + } + } while (!table && size > PAGE_SIZE && --log2qty); + + if (!table) + panic("Failed to allocate %s hash table\n", tablename); + + printk("%s hash table entries: %d (order: %d, %lu bytes)\n", + tablename, + (1U << log2qty), + ilog2(size) - PAGE_SHIFT, + size); + + if (_hash_shift) + *_hash_shift = log2qty; + if (_hash_mask) + *_hash_mask = (1 << log2qty) - 1; + + return table; +} + +#ifdef CONFIG_OUT_OF_LINE_PFN_TO_PAGE +struct page *pfn_to_page(unsigned long pfn) +{ + return __pfn_to_page(pfn); +} +unsigned long page_to_pfn(struct page *page) +{ + return __page_to_pfn(page); +} +EXPORT_SYMBOL(pfn_to_page); +EXPORT_SYMBOL(page_to_pfn); +#endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */ + +#if MAX_NUMNODES > 1 +/* + * Find the highest possible node id. + */ +int highest_possible_node_id(void) +{ + unsigned int node; + unsigned int highest = 0; + + for_each_node_mask(node, node_possible_map) + highest = node; + return highest; +} +EXPORT_SYMBOL(highest_possible_node_id); +#endif