X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=mm%2Fpage_alloc.c;h=a139339e9d75fde7f33dc7a30f978a91e72d9f75;hb=97bf2856c6014879bd04983a3e9dfcdac1e7fe85;hp=b747cbf8ba1b94003ee96fc9301190af66e6582c;hpb=43bc926fffd92024b46cafaf7350d669ba9ca884;p=linux-2.6.git diff --git a/mm/page_alloc.c b/mm/page_alloc.c index b747cbf8b..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 @@ -37,6 +36,12 @@ #include #include #include +#include +#include +#include +#include +#include +#include #include #include @@ -52,7 +57,6 @@ 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 totalhigh_pages __read_mostly; unsigned long totalreserve_pages __read_mostly; long nr_swap_pages; int percpu_pagelist_fraction; @@ -70,22 +74,65 @@ static void __free_pages_ok(struct page *page, unsigned int order); * TBD: should special case ZONE_DMA32 machines here - in those we normally * don't need any ZONE_NORMAL reservation */ -int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { 256, 256, 32 }; +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); -/* - * Used by page_zone() to look up the address of the struct zone whose - * id is encoded in the upper bits of page->flags - */ -struct zone *zone_table[1 << ZONETABLE_SHIFT] __read_mostly; -EXPORT_SYMBOL(zone_table); +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", "DMA32", "Normal", "HighMem" }; int min_free_kbytes = 1024; -unsigned long __initdata nr_kernel_pages; -unsigned long __initdata nr_all_pages; +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) @@ -128,7 +175,6 @@ static int bad_range(struct zone *zone, struct page *page) return 0; } - #else static inline int bad_range(struct zone *zone, struct page *page) { @@ -187,7 +233,7 @@ static void prep_compound_page(struct page *page, unsigned long order) int i; int nr_pages = 1 << order; - page[1].lru.next = (void *)free_compound_page; /* set dtor */ + 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; @@ -219,12 +265,12 @@ static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags) { int i; - BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM); + 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. */ - BUG_ON((gfp_flags & __GFP_HIGHMEM) && in_interrupt()); + VM_BUG_ON((gfp_flags & __GFP_HIGHMEM) && in_interrupt()); for (i = 0; i < (1 << order); i++) clear_highpage(page + i); } @@ -266,7 +312,7 @@ static inline void rmv_page_order(struct page *page) * satisfies the following equation: * P = B & ~(1 << O) * - * Assumption: *_mem_map is contigious at least up to MAX_ORDER + * 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) @@ -287,22 +333,27 @@ __find_combined_index(unsigned long page_idx, unsigned int order) * 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. + * (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, int order) +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(page))) + if (!pfn_valid(page_to_pfn(buddy))) return 0; #endif - if (PageBuddy(page) && page_order(page) == order) { - BUG_ON(page_count(page) != 0); + 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; @@ -343,8 +394,8 @@ static inline void __free_one_page(struct page *page, page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); - BUG_ON(page_idx & (order_size - 1)); - BUG_ON(bad_range(zone, page)); + 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) { @@ -353,7 +404,7 @@ static inline void __free_one_page(struct page *page, struct page *buddy; buddy = __page_find_buddy(page, page_idx, order); - if (!page_is_buddy(buddy, order)) + if (!page_is_buddy(page, buddy, order)) break; /* Move the buddy up one level. */ list_del(&buddy->lru); @@ -417,7 +468,7 @@ static void free_pages_bulk(struct zone *zone, int count, while (count--) { struct page *page; - BUG_ON(list_empty(list)); + VM_BUG_ON(list_empty(list)); page = list_entry(list->prev, struct page, lru); /* have to delete it as __free_one_page list manipulates */ list_del(&page->lru); @@ -428,9 +479,11 @@ static void free_pages_bulk(struct zone *zone, int count, static void free_one_page(struct zone *zone, struct page *page, int order) { - LIST_HEAD(list); - list_add(&page->lru, &list); - free_pages_bulk(zone, 1, &list, order); + spin_lock(&zone->lock); + zone->all_unreclaimable = 0; + zone->pages_scanned = 0; + __free_one_page(page, zone, order); + spin_unlock(&zone->lock); } static void __free_pages_ok(struct page *page, unsigned int order) @@ -439,19 +492,19 @@ static void __free_pages_ok(struct page *page, unsigned int order) int i; int reserved = 0; - arch_free_page(page, order); - if (!PageHighMem(page)) - mutex_debug_check_no_locks_freed(page_address(page), - PAGE_SIZE<>= 1; - BUG_ON(bad_range(zone, &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); @@ -549,6 +602,8 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) 1 << PG_checked | 1 << PG_mappedtodisk); 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) @@ -611,28 +666,38 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, #ifdef CONFIG_NUMA /* * Called from the slab reaper to drain pagesets on a particular node that - * belong to the currently executing processor. + * 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, z; + 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); - free_pages_bulk(zone, pcp->count, &pcp->list, 0); - pcp->count = 0; + 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); } } @@ -640,7 +705,6 @@ void drain_node_pages(int nodeid) } #endif -#if defined(CONFIG_PM) || defined(CONFIG_HOTPLUG_CPU) static void __drain_pages(unsigned int cpu) { unsigned long flags; @@ -650,6 +714,9 @@ static void __drain_pages(unsigned int cpu) for_each_zone(zone) { struct per_cpu_pageset *pset; + if (!populated_zone(zone)) + continue; + pset = zone_pcp(zone, cpu); for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) { struct per_cpu_pages *pcp; @@ -662,13 +729,13 @@ static void __drain_pages(unsigned int cpu) } } } -#endif /* CONFIG_PM || CONFIG_HOTPLUG_CPU */ #ifdef CONFIG_PM void mark_free_pages(struct zone *zone) { - unsigned long zone_pfn, flags; + unsigned long pfn, max_zone_pfn; + unsigned long flags; int order; struct list_head *curr; @@ -676,18 +743,25 @@ void mark_free_pages(struct zone *zone) return; spin_lock_irqsave(&zone->lock, flags); - for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn) - ClearPageNosaveFree(pfn_to_page(zone_pfn + zone->zone_start_pfn)); + + 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) { - unsigned long start_pfn, i; + unsigned long i; - start_pfn = page_to_pfn(list_entry(curr, struct page, lru)); + pfn = page_to_pfn(list_entry(curr, struct page, lru)); + for (i = 0; i < (1UL << order); i++) + SetPageNosaveFree(pfn_to_page(pfn + i)); + } - for (i=0; i < (1<lock, flags); } @@ -704,27 +778,6 @@ void drain_local_pages(void) } #endif /* CONFIG_PM */ -static void zone_statistics(struct zonelist *zonelist, struct zone *z, int cpu) -{ -#ifdef CONFIG_NUMA - pg_data_t *pg = z->zone_pgdat; - pg_data_t *orig = zonelist->zones[0]->zone_pgdat; - struct per_cpu_pageset *p; - - p = zone_pcp(z, cpu); - if (pg == orig) { - p->numa_hit++; - } else { - p->numa_miss++; - zone_pcp(zonelist->zones[0], cpu)->numa_foreign++; - } - if (pg == NODE_DATA(numa_node_id())) - p->local_node++; - else - p->other_node++; -#endif -} - /* * Free a 0-order page */ @@ -734,28 +787,27 @@ static void fastcall free_hot_cold_page(struct page *page, int cold) struct per_cpu_pages *pcp; unsigned long flags; - arch_free_page(page, 0); + 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); pcp = &zone_pcp(zone, get_cpu())->pcp[cold]; local_irq_save(flags); - __inc_page_state(pgfree); + __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; - } else if (zone->all_unreclaimable) { - spin_lock(&zone->lock); - zone->all_unreclaimable = 0; - zone->pages_scanned = 0; - spin_unlock(&zone->lock); } local_irq_restore(flags); put_cpu(); @@ -783,8 +835,8 @@ void split_page(struct page *page, unsigned int order) { int i; - BUG_ON(PageCompound(page)); - BUG_ON(!page_count(page)); + VM_BUG_ON(PageCompound(page)); + VM_BUG_ON(!page_count(page)); for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); } @@ -810,7 +862,7 @@ again: pcp = &zone_pcp(zone, cpu)->pcp[cold]; local_irq_save(flags); if (!pcp->count) { - pcp->count += rmqueue_bulk(zone, 0, + pcp->count = rmqueue_bulk(zone, 0, pcp->batch, &pcp->list); if (unlikely(!pcp->count)) goto failed; @@ -826,12 +878,12 @@ again: goto failed; } - __mod_page_state_zone(zone, pgalloc, 1 << order); - zone_statistics(zonelist, zone, cpu); + __count_zone_vm_events(PGALLOC, zone, 1 << order); + zone_statistics(zonelist, zone); local_irq_restore(flags); put_cpu(); - BUG_ON(bad_range(zone, page)); + VM_BUG_ON(bad_range(zone, page)); if (prep_new_page(page, order, gfp_flags)) goto again; return page; @@ -850,6 +902,91 @@ failed: #define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ +#ifdef CONFIG_FAIL_PAGE_ALLOC + +static struct fail_page_alloc_attr { + struct fault_attr attr; + + u32 ignore_gfp_highmem; + u32 ignore_gfp_wait; + +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + + struct dentry *ignore_gfp_highmem_file; + struct dentry *ignore_gfp_wait_file; + +#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ + +} fail_page_alloc = { + .attr = FAULT_ATTR_INITIALIZER, + .ignore_gfp_wait = 1, + .ignore_gfp_highmem = 1, +}; + +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); + +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; + + return should_fail(&fail_page_alloc.attr, 1 << order); +} + +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + +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. @@ -881,47 +1018,197 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark, 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_freeliest goes through the zonelist trying to allocate + * 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 = zonelist->zones; + struct zone **z; struct page *page = NULL; - int classzone_idx = zone_idx(*z); + 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: /* - * Go through the zonelist once, looking for a zone with enough free. + * 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(*z, gfp_mask)) - continue; + !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 = (*z)->pages_min; + mark = zone->pages_min; else if (alloc_flags & ALLOC_WMARK_LOW) - mark = (*z)->pages_low; + mark = zone->pages_low; else - mark = (*z)->pages_high; - if (!zone_watermark_ok(*z, order, mark, - classzone_idx, alloc_flags)) + mark = zone->pages_high; + if (!zone_watermark_ok(zone, order, mark, + classzone_idx, alloc_flags)) { if (!zone_reclaim_mode || - !zone_reclaim(*z, gfp_mask, order)) - continue; + !zone_reclaim(zone, gfp_mask, order)) + goto this_zone_full; + } } - page = buffered_rmqueue(zonelist, *z, order, gfp_mask); - if (page) { + 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; } @@ -943,6 +1230,9 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order, 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 */ @@ -956,10 +1246,19 @@ restart: if (page) goto got_pg; - do { - if (cpuset_zone_allowed(*z, gfp_mask|__GFP_HARDWALL)) - wakeup_kswapd(*z, order); - } while (*(++z)); + /* + * 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; + + for (z = zonelist->zones; *z; z++) + wakeup_kswapd(*z, order); /* * OK, we're below the kswapd watermark and have kicked background @@ -993,6 +1292,7 @@ restart: /* 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)) { @@ -1003,7 +1303,7 @@ nofail_alloc: if (page) goto got_pg; if (gfp_mask & __GFP_NOFAIL) { - blk_congestion_wait(WRITE, HZ/50); + congestion_wait(WRITE, HZ/50); goto nofail_alloc; } } @@ -1014,7 +1314,6 @@ nofail_alloc: if (!wait) goto nopage; -rebalance: cond_resched(); /* We now go into synchronous reclaim */ @@ -1066,7 +1365,7 @@ rebalance: do_retry = 1; } if (do_retry) { - blk_congestion_wait(WRITE, HZ/50); + congestion_wait(WRITE, HZ/50); goto rebalance; } @@ -1106,7 +1405,7 @@ fastcall unsigned long get_zeroed_page(gfp_t gfp_mask) * get_zeroed_page() returns a 32-bit address, which cannot represent * a highmem page */ - BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0); + VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0); page = alloc_pages(gfp_mask | __GFP_ZERO, 0); if (page) @@ -1139,7 +1438,7 @@ EXPORT_SYMBOL(__free_pages); fastcall void free_pages(unsigned long addr, unsigned int order) { if (addr != 0) { - BUG_ON(!virt_addr_valid((void *)addr)); + VM_BUG_ON(!virt_addr_valid((void *)addr)); __free_pages(virt_to_page((void *)addr), order); } } @@ -1165,7 +1464,8 @@ EXPORT_SYMBOL(nr_free_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; @@ -1210,161 +1510,10 @@ unsigned int nr_free_pagecache_pages(void) return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER)); } -#ifdef CONFIG_HIGHMEM -unsigned int nr_free_highpages (void) -{ - pg_data_t *pgdat; - unsigned int pages = 0; - - for_each_online_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. - */ -static DEFINE_PER_CPU(struct page_state, page_states) = {0}; - -atomic_t nr_pagecache = ATOMIC_INIT(0); -EXPORT_SYMBOL(nr_pagecache); -#ifdef CONFIG_SMP -DEFINE_PER_CPU(long, nr_pagecache_local) = 0; -#endif - -static void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask) -{ - unsigned cpu; - - memset(ret, 0, nr * sizeof(unsigned long)); - cpus_and(*cpumask, *cpumask, cpu_online_map); - - for_each_cpu_mask(cpu, *cpumask) { - unsigned long *in; - unsigned long *out; - unsigned off; - unsigned next_cpu; - - in = (unsigned long *)&per_cpu(page_states, cpu); - - next_cpu = next_cpu(cpu, *cpumask); - if (likely(next_cpu < NR_CPUS)) - prefetch(&per_cpu(page_states, next_cpu)); - - out = (unsigned long *)ret; - for (off = 0; off < nr; off++) - *out++ += *in++; - } -} - -void get_page_state_node(struct page_state *ret, int node) -{ - int nr; - cpumask_t mask = node_to_cpumask(node); - - nr = offsetof(struct page_state, GET_PAGE_STATE_LAST); - nr /= sizeof(unsigned long); - - __get_page_state(ret, nr+1, &mask); -} - -void get_page_state(struct page_state *ret) -{ - int nr; - cpumask_t mask = CPU_MASK_ALL; - - nr = offsetof(struct page_state, GET_PAGE_STATE_LAST); - nr /= sizeof(unsigned long); - - __get_page_state(ret, nr + 1, &mask); -} - -void get_full_page_state(struct page_state *ret) -{ - cpumask_t mask = CPU_MASK_ALL; - - __get_page_state(ret, sizeof(*ret) / sizeof(unsigned long), &mask); -} - -unsigned long read_page_state_offset(unsigned long offset) -{ - unsigned long ret = 0; - int cpu; - - for_each_online_cpu(cpu) { - unsigned long in; - - in = (unsigned long)&per_cpu(page_states, cpu) + offset; - ret += *((unsigned long *)in); - } - return ret; -} - -void __mod_page_state_offset(unsigned long offset, unsigned long delta) -{ - void *ptr; - - ptr = &__get_cpu_var(page_states); - *(unsigned long *)(ptr + offset) += delta; -} -EXPORT_SYMBOL(__mod_page_state_offset); - -void mod_page_state_offset(unsigned long offset, unsigned long delta) -{ - unsigned long flags; - void *ptr; - - local_irq_save(flags); - ptr = &__get_cpu_var(page_states); - *(unsigned long *)(ptr + offset) += delta; - local_irq_restore(flags); -} -EXPORT_SYMBOL(mod_page_state_offset); - -void __get_zone_counts(unsigned long *active, unsigned long *inactive, - unsigned long *free, struct pglist_data *pgdat) -{ - struct zone *zones = pgdat->node_zones; - int i; - - *active = 0; - *inactive = 0; - *free = 0; - for (i = 0; i < MAX_NR_ZONES; i++) { - *active += zones[i].nr_active; - *inactive += zones[i].nr_inactive; - *free += zones[i].free_pages; - } -} - -void get_zone_counts(unsigned long *active, - unsigned long *inactive, unsigned long *free) +static inline void show_node(struct zone *zone) { - struct pglist_data *pgdat; - - *active = 0; - *inactive = 0; - *free = 0; - for_each_online_pgdat(pgdat) { - unsigned long l, m, n; - __get_zone_counts(&l, &m, &n, pgdat); - *active += l; - *inactive += m; - *free += n; - } + if (NUMA_BUILD) + printk("Node %d ", zone_to_nid(zone)); } void si_meminfo(struct sysinfo *val) @@ -1373,14 +1522,10 @@ 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); } @@ -1394,9 +1539,15 @@ 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); } @@ -1411,60 +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 (!populated_zone(zone)) { - printk(" empty\n"); + if (!populated_zone(zone)) continue; - } else - printk("\n"); + + show_node(zone); + printk("%s per-cpu:\n", zone->name); for_each_online_cpu(cpu) { struct per_cpu_pageset *pageset; pageset = zone_pcp(zone, cpu); - for (temperature = 0; temperature < 2; temperature++) - printk("cpu %d %s: high %d, batch %d used:%d\n", - cpu, - temperature ? "cold" : "hot", - pageset->pcp[temperature].high, - pageset->pcp[temperature].batch, - pageset->pcp[temperature].count); + 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("Free 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" @@ -1495,22 +1640,22 @@ void show_free_areas(void) } for_each_zone(zone) { - 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 (!populated_zone(zone)) { - printk("empty\n"); - continue; - } spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { - nr = zone->free_area[order].nr_free; - 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)); } @@ -1522,43 +1667,29 @@ void show_free_areas(void) * * Add all populated zones of a node to the zonelist. */ -static int __init build_zonelists_node(pg_data_t *pgdat, - struct zonelist *zonelist, int nr_zones, int zone_type) +static int __meminit build_zonelists_node(pg_data_t *pgdat, + struct zonelist *zonelist, int nr_zones, enum zone_type zone_type) { struct zone *zone; - BUG_ON(zone_type > ZONE_HIGHMEM); + BUG_ON(zone_type >= MAX_NR_ZONES); + zone_type++; do { + zone_type--; zone = pgdat->node_zones + zone_type; if (populated_zone(zone)) { -#ifndef CONFIG_HIGHMEM - BUG_ON(zone_type > ZONE_NORMAL); -#endif zonelist->zones[nr_zones++] = zone; check_highest_zone(zone_type); } - zone_type--; - } while (zone_type >= 0); + } while (zone_type); return nr_zones; } -static inline int highest_zone(int zone_bits) -{ - int res = ZONE_NORMAL; - if (zone_bits & (__force int)__GFP_HIGHMEM) - res = ZONE_HIGHMEM; - if (zone_bits & (__force int)__GFP_DMA32) - res = ZONE_DMA32; - if (zone_bits & (__force int)__GFP_DMA) - res = ZONE_DMA; - return res; -} - #ifdef CONFIG_NUMA #define MAX_NODE_LOAD (num_online_nodes()) -static int __initdata node_load[MAX_NUMNODES]; +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 * @node: node whose fallback list we're appending @@ -1573,7 +1704,7 @@ 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, nodemask_t *used_node_mask) +static int __meminit find_next_best_node(int node, nodemask_t *used_node_mask) { int n, val; int min_val = INT_MAX; @@ -1619,15 +1750,16 @@ static int __init find_next_best_node(int node, nodemask_t *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; nodemask_t used_mask; /* initialize zonelists */ - for (i = 0; i < GFP_ZONETYPES; i++) { + for (i = 0; i < MAX_NR_ZONES; i++) { zonelist = pgdat->node_zonelists + i; zonelist->zones[0] = NULL; } @@ -1657,33 +1789,48 @@ static void __init build_zonelists(pg_data_t *pgdat) node_load[node] += load; prev_node = node; load--; - for (i = 0; i < GFP_ZONETYPES; i++) { + for (i = 0; i < MAX_NR_ZONES; i++) { zonelist = pgdat->node_zonelists + i; for (j = 0; zonelist->zones[j] != NULL; j++); - k = highest_zone(i); - - 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 < GFP_ZONETYPES; i++) { + for (i = 0; i < MAX_NR_ZONES; i++) { struct zonelist *zonelist; zonelist = pgdat->node_zonelists + i; - j = 0; - k = highest_zone(i); - 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. @@ -1695,28 +1842,55 @@ static void __init build_zonelists(pg_data_t *pgdat) for (node = local_node + 1; node < MAX_NUMNODES; node++) { if (!node_online(node)) continue; - j = build_zonelists_node(NODE_DATA(node), zonelist, j, k); + 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, k); + 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_each_online_node(i) - build_zonelists(NODE_DATA(i)); - printk("Built %i zonelists\n", num_online_nodes()); - cpuset_init_current_mems_allowed(); + 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); } /* @@ -1732,7 +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; @@ -1750,6 +1925,29 @@ 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 @@ -1763,40 +1961,30 @@ static inline unsigned long wait_table_bits(unsigned long size) #define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1)) -static void __init calculate_zone_totalpages(struct pglist_data *pgdat, - unsigned long *zones_size, unsigned long *zholes_size) -{ - unsigned long realtotalpages, totalpages = 0; - int i; - - for (i = 0; i < MAX_NR_ZONES; i++) - totalpages += zones_size[i]; - pgdat->node_spanned_pages = totalpages; - - realtotalpages = totalpages; - if (zholes_size) - for (i = 0; i < MAX_NR_ZONES; i++) - realtotalpages -= zholes_size[i]; - pgdat->node_present_pages = realtotalpages; - printk(KERN_DEBUG "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 __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, - unsigned long start_pfn) + 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++) { - if (!early_pfn_valid(pfn)) - continue; + /* + * 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); @@ -1821,23 +2009,9 @@ void zone_init_free_lists(struct pglist_data *pgdat, struct zone *zone, } } -#define ZONETABLE_INDEX(x, zone_nr) ((x << ZONES_SHIFT) | zone_nr) -void zonetable_add(struct zone *zone, int nid, int zid, unsigned long pfn, - unsigned long size) -{ - unsigned long snum = pfn_to_section_nr(pfn); - unsigned long end = pfn_to_section_nr(pfn + size); - - if (FLAGS_HAS_NODE) - zone_table[ZONETABLE_INDEX(nid, zid)] = zone; - else - for (; snum <= end; snum++) - zone_table[ZONETABLE_INDEX(snum, zid)] = zone; -} - #ifndef __HAVE_ARCH_MEMMAP_INIT #define memmap_init(size, nid, zone, start_pfn) \ - memmap_init_zone((size), (nid), (zone), (start_pfn)) + memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY) #endif static int __cpuinit zone_batchsize(struct zone *zone) @@ -1939,6 +2113,9 @@ static int __cpuinit process_zones(int cpu) 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)) @@ -1969,12 +2146,14 @@ static inline void free_zone_pagesets(int cpu) 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; - kfree(pset); } } -static int pageset_cpuup_callback(struct notifier_block *nfb, +static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -1982,21 +2161,21 @@ static int pageset_cpuup_callback(struct notifier_block *nfb, 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; + 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 pageset_notifier = +static struct notifier_block __cpuinitdata pageset_notifier = { &pageset_cpuup_callback, NULL, 0 }; void __init setup_per_cpu_pageset(void) @@ -2015,23 +2194,46 @@ void __init setup_per_cpu_pageset(void) #endif static __meminit -void zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) +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_size = wait_table_size(zone_size_pages); - 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)); + 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_size; ++i) + 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) @@ -2053,12 +2255,16 @@ static __meminit void zone_pcp_init(struct zone *zone) zone->name, zone->present_pages, batch); } -static __meminit void init_currently_empty_zone(struct zone *zone, - unsigned long zone_start_pfn, unsigned long size) +__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; - - zone_wait_table_init(zone, size); + 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; @@ -2066,6 +2272,351 @@ static __meminit void init_currently_empty_zone(struct zone *zone, 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]; +} + +static inline unsigned long zone_absent_pages_in_node(int nid, + unsigned long zone_type, + unsigned long *zholes_size) +{ + if (!zholes_size) + return 0; + + return zholes_size[zone_type]; +} + +#endif + +static void __init calculate_node_totalpages(struct pglist_data *pgdat, + unsigned long *zones_size, unsigned long *zholes_size) +{ + unsigned long realtotalpages, totalpages = 0; + enum zone_type i; + + for (i = 0; i < MAX_NR_ZONES; i++) + totalpages += zone_spanned_pages_in_node(pgdat->node_id, i, + zones_size); + pgdat->node_spanned_pages = totalpages; + + realtotalpages = totalpages; + 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(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, + realtotalpages); } /* @@ -2074,12 +2625,13 @@ static __meminit void init_currently_empty_zone(struct zone *zone, * - 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 j; + 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; @@ -2088,18 +2640,47 @@ static void __init free_area_init_core(struct pglist_data *pgdat, for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; - unsigned long size, realsize; + 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); - realsize = size = zones_size[j]; - if (zholes_size) - realsize -= zholes_size[j]; + /* + * 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); + } - if (j < ZONE_HIGHMEM) + 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); @@ -2107,7 +2688,7 @@ static void __init free_area_init_core(struct pglist_data *pgdat, zone->zone_pgdat = pgdat; zone->free_pages = 0; - zone->temp_priority = zone->prev_priority = DEF_PRIORITY; + zone->prev_priority = DEF_PRIORITY; zone_pcp_init(zone); INIT_LIST_HEAD(&zone->active_list); @@ -2116,12 +2697,14 @@ static void __init free_area_init_core(struct pglist_data *pgdat, 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; - zonetable_add(zone, nid, j, zone_start_pfn, size); - init_currently_empty_zone(zone, zone_start_pfn, size); + ret = init_currently_empty_zone(zone, zone_start_pfn, + size, MEMMAP_EARLY); + BUG_ON(ret); zone_start_pfn += size; } } @@ -2156,343 +2739,298 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat) /* * With no DISCONTIG, the global mem_map is just set as node 0's */ - if (pgdat == NODE_DATA(0)) + 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, +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) { pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; - calculate_zone_totalpages(pgdat, zones_size, zholes_size); + calculate_node_totalpages(pgdat, zones_size, zholes_size); alloc_node_mem_map(pgdat); free_area_init_core(pgdat, zones_size, zholes_size); } -#ifndef CONFIG_NEED_MULTIPLE_NODES -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); -#endif + 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, NODE_DATA(0), zones_size, - __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL); -} + /* 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; - for (pgdat = first_online_pgdat(); - pgdat && node; - pgdat = next_online_pgdat(pgdat)) - --node; + /* 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; + } + } - return pgdat; + /* 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; + } + + 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 next_online_pgdat(pgdat); + /* 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 free areas for each zone. - */ -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 (!populated_zone(zone)) - 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) - seq_printf(m, "%6lu ", zone->free_area[order].nr_free); - 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, -}; - -/* - * Output information about zones in @pgdat. - */ -static int zoneinfo_show(struct seq_file *m, void *arg) +/* sort the node_map by start_pfn */ +static void __init sort_node_map(void) { - pg_data_t *pgdat = arg; - struct zone *zone; - struct zone *node_zones = pgdat->node_zones; - unsigned long flags; + sort(early_node_map, (size_t)nr_nodemap_entries, + sizeof(struct node_active_region), + cmp_node_active_region, NULL); +} - for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; zone++) { - int i; +/* 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) +{ + int i; - if (!populated_zone(zone)) - continue; + /* Regions in the early_node_map can be in any order */ + sort_node_map(); - spin_lock_irqsave(&zone->lock, flags); - seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name); - seq_printf(m, - "\n pages free %lu" - "\n min %lu" - "\n low %lu" - "\n high %lu" - "\n active %lu" - "\n inactive %lu" - "\n scanned %lu (a: %lu i: %lu)" - "\n spanned %lu" - "\n present %lu", - zone->free_pages, - zone->pages_min, - zone->pages_low, - zone->pages_high, - zone->nr_active, - zone->nr_inactive, - zone->pages_scanned, - zone->nr_scan_active, zone->nr_scan_inactive, - zone->spanned_pages, - zone->present_pages); - seq_printf(m, - "\n protection: (%lu", - zone->lowmem_reserve[0]); - for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++) - seq_printf(m, ", %lu", zone->lowmem_reserve[i]); - seq_printf(m, - ")" - "\n pagesets"); - for_each_online_cpu(i) { - struct per_cpu_pageset *pageset; - int j; + /* 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; - pageset = zone_pcp(zone, i); - for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) { - if (pageset->pcp[j].count) - break; - } - if (j == ARRAY_SIZE(pageset->pcp)) - continue; - for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) { - seq_printf(m, - "\n cpu: %i pcp: %i" - "\n count: %i" - "\n high: %i" - "\n batch: %i", - i, j, - pageset->pcp[j].count, - pageset->pcp[j].high, - pageset->pcp[j].batch); - } -#ifdef CONFIG_NUMA - seq_printf(m, - "\n numa_hit: %lu" - "\n numa_miss: %lu" - "\n numa_foreign: %lu" - "\n interleave_hit: %lu" - "\n local_node: %lu" - "\n other_node: %lu", - pageset->numa_hit, - pageset->numa_miss, - pageset->numa_foreign, - pageset->interleave_hit, - pageset->local_node, - pageset->other_node); -#endif - } - seq_printf(m, - "\n all_unreclaimable: %u" - "\n prev_priority: %i" - "\n temp_priority: %i" - "\n start_pfn: %lu", - zone->all_unreclaimable, - zone->prev_priority, - zone->temp_priority, - zone->zone_start_pfn); - spin_unlock_irqrestore(&zone->lock, flags); - seq_putc(m, '\n'); - } + printk(KERN_WARNING "Could not find start_pfn for node %lu\n", nid); return 0; } -struct seq_operations zoneinfo_op = { - .start = frag_start, /* iterate over all zones. The same as in - * fragmentation. */ - .next = frag_next, - .stop = frag_stop, - .show = zoneinfo_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_dma32", - "pgalloc_dma", - - "pgfree", - "pgactivate", - "pgdeactivate", - - "pgfault", - "pgmajfault", - - "pgrefill_high", - "pgrefill_normal", - "pgrefill_dma32", - "pgrefill_dma", - - "pgsteal_high", - "pgsteal_normal", - "pgsteal_dma32", - "pgsteal_dma", - - "pgscan_kswapd_high", - "pgscan_kswapd_normal", - "pgscan_kswapd_dma32", - "pgscan_kswapd_dma", - - "pgscan_direct_high", - "pgscan_direct_normal", - "pgscan_direct_dma32", - "pgscan_direct_dma", - - "pginodesteal", - "slabs_scanned", - "kswapd_steal", - "kswapd_inodesteal", - "pageoutrun", - "allocstall", - - "pgrotated", - "nr_bounce", -}; - -static void *vmstat_start(struct seq_file *m, 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) { - struct page_state *ps; - - if (*pos >= ARRAY_SIZE(vmstat_text)) - return NULL; - - 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; + return find_min_pfn_for_node(MAX_NUMNODES); } -static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos) +/** + * 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) { - (*pos)++; - if (*pos >= ARRAY_SIZE(vmstat_text)) - return NULL; - return (unsigned long *)m->private + *pos; + int i; + unsigned long max_pfn = 0; + + for (i = 0; i < nr_nodemap_entries; i++) + max_pfn = max(max_pfn, early_node_map[i].end_pfn); + + return max_pfn; } -static int vmstat_show(struct seq_file *m, void *arg) -{ - unsigned long *l = arg; - unsigned long off = l - (unsigned long *)m->private; +/** + * 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]); + } - seq_printf(m, "%s %lu\n", vmstat_text[off], *l); - return 0; + /* 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 }; + +EXPORT_SYMBOL(contig_page_data); +#endif -#endif /* CONFIG_PROC_FS */ +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; - unsigned long *src, *dest; if (action == CPU_DEAD) { - int i; - - /* Drain local pagecache count. */ - count = &per_cpu(nr_pagecache_local, cpu); - atomic_add(*count, &nr_pagecache); - *count = 0; local_irq_disable(); __drain_pages(cpu); - - /* Add dead cpu's page_states to our own. */ - dest = (unsigned long *)&__get_cpu_var(page_states); - src = (unsigned long *)&per_cpu(page_states, cpu); - - for (i = 0; i < sizeof(struct page_state)/sizeof(unsigned long); - i++) { - dest[i] += src[i]; - src[i] = 0; - } - + 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) { @@ -2507,7 +3045,7 @@ static void calculate_totalreserve_pages(void) { struct pglist_data *pgdat; unsigned long reserve_pages = 0; - int i, j; + enum zone_type i, j; for_each_online_pgdat(pgdat) { for (i = 0; i < MAX_NR_ZONES; i++) { @@ -2540,7 +3078,7 @@ static void calculate_totalreserve_pages(void) static void setup_per_zone_lowmem_reserve(void) { struct pglist_data *pgdat; - int j, idx; + enum zone_type j, idx; for_each_online_pgdat(pgdat) { for (j = 0; j < MAX_NR_ZONES; j++) { @@ -2549,9 +3087,12 @@ static void setup_per_zone_lowmem_reserve(void) zone->lowmem_reserve[j] = 0; - for (idx = j-1; idx >= 0; idx--) { + idx = j; + while (idx) { struct zone *lower_zone; + idx--; + if (sysctl_lowmem_reserve_ratio[idx] < 1) sysctl_lowmem_reserve_ratio[idx] = 1; @@ -2567,10 +3108,11 @@ static void setup_per_zone_lowmem_reserve(void) 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. */ void setup_per_zone_pages_min(void) { @@ -2680,6 +3222,40 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write, 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() @@ -2723,7 +3299,7 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write, return 0; } -__initdata int hashdist = HASHDIST_DEFAULT; +int hashdist = HASHDIST_DEFAULT; #ifdef CONFIG_NUMA static int __init set_hashdist(char *str) @@ -2758,7 +3334,7 @@ void *__init alloc_large_system_hash(const char *tablename, /* allow the kernel cmdline to have a say */ if (!numentries) { /* round applicable memory size up to nearest megabyte */ - numentries = (flags & HASH_HIGHMEM) ? nr_all_pages : nr_kernel_pages; + numentries = nr_kernel_pages; numentries += (1UL << (20 - PAGE_SHIFT)) - 1; numentries >>= 20 - PAGE_SHIFT; numentries <<= 20 - PAGE_SHIFT; @@ -2768,6 +3344,10 @@ void *__init alloc_large_system_hash(const char *tablename, 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); @@ -2780,7 +3360,7 @@ void *__init alloc_large_system_hash(const char *tablename, if (numentries > max) numentries = max; - log2qty = long_log2(numentries); + log2qty = ilog2(numentries); do { size = bucketsize << log2qty; @@ -2802,7 +3382,7 @@ void *__init alloc_large_system_hash(const char *tablename, printk("%s hash table entries: %d (order: %d, %lu bytes)\n", tablename, (1U << log2qty), - long_log2(size) - PAGE_SHIFT, + ilog2(size) - PAGE_SHIFT, size); if (_hash_shift) @@ -2814,42 +3394,30 @@ void *__init alloc_large_system_hash(const char *tablename, } #ifdef CONFIG_OUT_OF_LINE_PFN_TO_PAGE -/* - * pfn <-> page translation. out-of-line version. - * (see asm-generic/memory_model.h) - */ -#if defined(CONFIG_FLATMEM) -struct page *pfn_to_page(unsigned long pfn) -{ - return mem_map + (pfn - ARCH_PFN_OFFSET); -} -unsigned long page_to_pfn(struct page *page) -{ - return (page - mem_map) + ARCH_PFN_OFFSET; -} -#elif defined(CONFIG_DISCONTIGMEM) -struct page *pfn_to_page(unsigned long pfn) -{ - int nid = arch_pfn_to_nid(pfn); - return NODE_DATA(nid)->node_mem_map + arch_local_page_offset(pfn,nid); -} -unsigned long page_to_pfn(struct page *page) -{ - struct pglist_data *pgdat = NODE_DATA(page_to_nid(page)); - return (page - pgdat->node_mem_map) + pgdat->node_start_pfn; -} -#elif defined(CONFIG_SPARSEMEM) struct page *pfn_to_page(unsigned long pfn) { - return __section_mem_map_addr(__pfn_to_section(pfn)) + pfn; + return __pfn_to_page(pfn); } - unsigned long page_to_pfn(struct page *page) { - long section_id = page_to_section(page); - return page - __section_mem_map_addr(__nr_to_section(section_id)); + return __page_to_pfn(page); } -#endif /* CONFIG_FLATMEM/DISCONTIGMME/SPARSEMEM */ 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