From cf23422b9d76215316855253da491d4c9f294372 Mon Sep 17 00:00:00 2001 From: minskey guo Date: Mon, 24 May 2010 14:32:41 -0700 Subject: cpu/mem hotplug: enable CPUs online before local memory online Enable users to online CPUs even if the CPUs belongs to a numa node which doesn't have onlined local memory. The zonlists(pg_data_t.node_zonelists[]) of a numa node are created either in system boot/init period, or at the time of local memory online. For a numa node without onlined local memory, its zonelists are not initialized at present. As a result, any memory allocation operations executed by CPUs within this node will fail. In fact, an out-of-memory error is triggered when attempt to online CPUs before memory comes to online. This patch tries to create zonelists for such numa nodes, so that the memory allocation for this node can be fallback'ed to other nodes. [akpm@linux-foundation.org: remove unneeded export] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: minskey guo Cc: Minchan Kim Cc: Yasunori Goto Cc: Andi Kleen Cc: Christoph Lameter Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/memory_hotplug.h') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 35b07b773e6c..864035fb8f8a 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -202,6 +202,7 @@ static inline int is_mem_section_removable(unsigned long pfn, } #endif /* CONFIG_MEMORY_HOTREMOVE */ +extern int mem_online_node(int nid); extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); extern int remove_memory(u64 start, u64 size); -- cgit v1.2.3 From 49ac825587f33afec8841b7fab2eb4db775014e6 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 26 Oct 2010 14:21:30 -0700 Subject: memory hotplug: unify is_removable and offline detection code Now, sysfs interface of memory hotplug shows whether the section is removable or not. But it checks only migrateype of pages and doesn't check details of cluster of pages. Next, memory hotplug's set_migratetype_isolate() has the same kind of check, too. This patch adds the function __count_unmovable_pages() and makes above 2 checks to use the same logic. Then, is_removable and hotremove code uses the same logic. No changes in the hotremove logic itself. TODO: need to find a way to check RECLAMABLE. But, considering bit, calling shrink_slab() against a range before starting memory hotremove sounds better. If so, this patch's logic doesn't need to be changed. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: KAMEZAWA Hiroyuki Reported-by: Michal Hocko Cc: Wu Fengguang Cc: Mel Gorman Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 4 ++ mm/memory_hotplug.c | 17 +-------- mm/page_alloc.c | 87 ++++++++++++++++++++++++++++++++---------- 3 files changed, 72 insertions(+), 36 deletions(-) (limited to 'include/linux/memory_hotplug.h') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 864035fb8f8a..4307231bd22f 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -70,6 +70,10 @@ extern void online_page(struct page *page); extern int online_pages(unsigned long, unsigned long); extern void __offline_isolated_pages(unsigned long, unsigned long); +#ifdef CONFIG_MEMORY_HOTREMOVE +extern bool is_pageblock_removable_nolock(struct page *page); +#endif /* CONFIG_MEMORY_HOTREMOVE */ + /* reasonably generic interface to expand the physical pages in a zone */ extern int __add_pages(int nid, struct zone *zone, unsigned long start_pfn, unsigned long nr_pages); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 4821338b4e4b..b0dc65452973 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -602,27 +602,14 @@ static struct page *next_active_pageblock(struct page *page) /* Checks if this range of memory is likely to be hot-removable. */ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) { - int type; struct page *page = pfn_to_page(start_pfn); struct page *end_page = page + nr_pages; /* Check the starting page of each pageblock within the range */ for (; page < end_page; page = next_active_pageblock(page)) { - type = get_pageblock_migratetype(page); - - /* - * A pageblock containing MOVABLE or free pages is considered - * removable - */ - if (type != MIGRATE_MOVABLE && !pageblock_free(page)) - return 0; - - /* - * A pageblock starting with a PageReserved page is not - * considered removable. - */ - if (PageReserved(page)) + if (!is_pageblock_removable_nolock(page)) return 0; + cond_resched(); } /* All pageblocks in the memory block are likely to be hot-removable */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 099790052bfe..6a683f819439 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5297,12 +5297,65 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags, * page allocater never alloc memory from ISOLATE block. */ +static int +__count_immobile_pages(struct zone *zone, struct page *page, int count) +{ + unsigned long pfn, iter, found; + /* + * For avoiding noise data, lru_add_drain_all() should be called + * If ZONE_MOVABLE, the zone never contains immobile pages + */ + if (zone_idx(zone) == ZONE_MOVABLE) + return true; + + if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE) + return true; + + pfn = page_to_pfn(page); + for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) { + unsigned long check = pfn + iter; + + if (!pfn_valid_within(check)) { + iter++; + continue; + } + page = pfn_to_page(check); + if (!page_count(page)) { + if (PageBuddy(page)) + iter += (1 << page_order(page)) - 1; + continue; + } + if (!PageLRU(page)) + found++; + /* + * If there are RECLAIMABLE pages, we need to check it. + * But now, memory offline itself doesn't call shrink_slab() + * and it still to be fixed. + */ + /* + * If the page is not RAM, page_count()should be 0. + * we don't need more check. This is an _used_ not-movable page. + * + * The problematic thing here is PG_reserved pages. PG_reserved + * is set to both of a memory hole page and a _used_ kernel + * page at boot. + */ + if (found > count) + return false; + } + return true; +} + +bool is_pageblock_removable_nolock(struct page *page) +{ + struct zone *zone = page_zone(page); + return __count_immobile_pages(zone, page, 0); +} + int set_migratetype_isolate(struct page *page) { struct zone *zone; - struct page *curr_page; - unsigned long flags, pfn, iter; - unsigned long immobile = 0; + unsigned long flags, pfn; struct memory_isolate_notify arg; int notifier_ret; int ret = -EBUSY; @@ -5312,11 +5365,6 @@ int set_migratetype_isolate(struct page *page) zone_idx = zone_idx(zone); spin_lock_irqsave(&zone->lock, flags); - if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE || - zone_idx == ZONE_MOVABLE) { - ret = 0; - goto out; - } pfn = page_to_pfn(page); arg.start_pfn = pfn; @@ -5338,21 +5386,18 @@ int set_migratetype_isolate(struct page *page) notifier_ret = notifier_to_errno(notifier_ret); if (notifier_ret) goto out; - - for (iter = pfn; iter < (pfn + pageblock_nr_pages); iter++) { - if (!pfn_valid_within(pfn)) - continue; - - curr_page = pfn_to_page(iter); - if (!page_count(curr_page) || PageLRU(curr_page)) - continue; - - immobile++; - } - - if (arg.pages_found == immobile) + /* + * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself. + * We just check MOVABLE pages. + */ + if (__count_immobile_pages(zone, page, arg.pages_found)) ret = 0; + /* + * immobile means "not-on-lru" paes. If immobile is larger than + * removable-by-driver pages reported by notifier, we'll fail. + */ + out: if (!ret) { set_pageblock_migratetype(page, MIGRATE_ISOLATE); -- cgit v1.2.3 From 20d6c96b5f1cad5c5da4641945ec17a1d9a1afc8 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Thu, 2 Dec 2010 14:31:19 -0800 Subject: mem-hotplug: introduce {un}lock_memory_hotplug() Presently hwpoison is using lock_system_sleep() to prevent a race with memory hotplug. However lock_system_sleep() is a no-op if CONFIG_HIBERNATION=n. Therefore we need a new lock. Signed-off-by: KOSAKI Motohiro Cc: Andi Kleen Cc: Kamezawa Hiroyuki Suggested-by: Hugh Dickins Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 6 ++++++ mm/memory-failure.c | 8 ++++---- mm/memory_hotplug.c | 31 ++++++++++++++++++++++++------- 3 files changed, 34 insertions(+), 11 deletions(-) (limited to 'include/linux/memory_hotplug.h') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 4307231bd22f..31c237a00c48 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -161,6 +161,9 @@ extern void register_page_bootmem_info_node(struct pglist_data *pgdat); extern void put_page_bootmem(struct page *page); #endif +void lock_memory_hotplug(void); +void unlock_memory_hotplug(void); + #else /* ! CONFIG_MEMORY_HOTPLUG */ /* * Stub functions for when hotplug is off @@ -192,6 +195,9 @@ static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) { } +static inline void lock_memory_hotplug(void) {} +static inline void unlock_memory_hotplug(void) {} + #endif /* ! CONFIG_MEMORY_HOTPLUG */ #ifdef CONFIG_MEMORY_HOTREMOVE diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 124324134ff6..46ab2c044b0e 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -51,6 +51,7 @@ #include #include #include +#include #include "internal.h" int sysctl_memory_failure_early_kill __read_mostly = 0; @@ -1230,11 +1231,10 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags) return 1; /* - * The lock_system_sleep prevents a race with memory hotplug, - * because the isolation assumes there's only a single user. + * The lock_memory_hotplug prevents a race with memory hotplug. * This is a big hammer, a better would be nicer. */ - lock_system_sleep(); + lock_memory_hotplug(); /* * Isolate the page, so that it doesn't get reallocated if it @@ -1264,7 +1264,7 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags) ret = 1; } unset_migratetype_isolate(p); - unlock_system_sleep(); + unlock_memory_hotplug(); return ret; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9260314a221e..2c6523af5473 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -34,6 +34,23 @@ #include "internal.h" +DEFINE_MUTEX(mem_hotplug_mutex); + +void lock_memory_hotplug(void) +{ + mutex_lock(&mem_hotplug_mutex); + + /* for exclusive hibernation if CONFIG_HIBERNATION=y */ + lock_system_sleep(); +} + +void unlock_memory_hotplug(void) +{ + unlock_system_sleep(); + mutex_unlock(&mem_hotplug_mutex); +} + + /* add this memory to iomem resource */ static struct resource *register_memory_resource(u64 start, u64 size) { @@ -493,7 +510,7 @@ int mem_online_node(int nid) pg_data_t *pgdat; int ret; - lock_system_sleep(); + lock_memory_hotplug(); pgdat = hotadd_new_pgdat(nid, 0); if (pgdat) { ret = -ENOMEM; @@ -504,7 +521,7 @@ int mem_online_node(int nid) BUG_ON(ret); out: - unlock_system_sleep(); + unlock_memory_hotplug(); return ret; } @@ -516,7 +533,7 @@ int __ref add_memory(int nid, u64 start, u64 size) struct resource *res; int ret; - lock_system_sleep(); + lock_memory_hotplug(); res = register_memory_resource(start, size); ret = -EEXIST; @@ -563,7 +580,7 @@ error: release_memory_resource(res); out: - unlock_system_sleep(); + unlock_memory_hotplug(); return ret; } EXPORT_SYMBOL_GPL(add_memory); @@ -791,7 +808,7 @@ static int offline_pages(unsigned long start_pfn, if (!test_pages_in_a_zone(start_pfn, end_pfn)) return -EINVAL; - lock_system_sleep(); + lock_memory_hotplug(); zone = page_zone(pfn_to_page(start_pfn)); node = zone_to_nid(zone); @@ -880,7 +897,7 @@ repeat: writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &arg); - unlock_system_sleep(); + unlock_memory_hotplug(); return 0; failed_removal: @@ -891,7 +908,7 @@ failed_removal: undo_isolate_page_range(start_pfn, end_pfn); out: - unlock_system_sleep(); + unlock_memory_hotplug(); return ret; } -- cgit v1.2.3 From 925268a06dc2b1ff7bfcc37419a6827a0e739639 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 11 Jan 2011 16:44:01 +0900 Subject: memory hotplug: one more lock on memory hotplug Now, memory_hotplug_(un)lock() is used for add/remove/offline pages for avoiding races with hibernation. But this should be held in online_pages(), too. It seems asymmetric. There are cases where one has to avoid a race with memory hotplug notifier and his own local code, and hotplug v.s. hotplug. This will add a generic solution for avoiding races. In other view, having lock here has no big impacts. online pages is tend to be done by udev script at el against each memory section one by one. Then, it's better to have lock here, too. Cc: # 2.6.37 Reviewed-by: Christoph Lameter Acked-by: David Rientjes Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Pekka Enberg --- include/linux/memory_hotplug.h | 6 ++++++ mm/memory_hotplug.c | 4 ++++ 2 files changed, 10 insertions(+) (limited to 'include/linux/memory_hotplug.h') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 31c237a00c48..12b9eb5a36c3 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -161,6 +161,12 @@ extern void register_page_bootmem_info_node(struct pglist_data *pgdat); extern void put_page_bootmem(struct page *page); #endif +/* + * Lock for memory hotplug guarantees 1) all callbacks for memory hotplug + * notifier will be called under this. 2) offline/online/add/remove memory + * will not run simultaneously. + */ + void lock_memory_hotplug(void); void unlock_memory_hotplug(void); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 2c6523af5473..83163c096a75 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -407,6 +407,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) int ret; struct memory_notify arg; + lock_memory_hotplug(); arg.start_pfn = pfn; arg.nr_pages = nr_pages; arg.status_change_nid = -1; @@ -419,6 +420,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) ret = notifier_to_errno(ret); if (ret) { memory_notify(MEM_CANCEL_ONLINE, &arg); + unlock_memory_hotplug(); return ret; } /* @@ -443,6 +445,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) printk(KERN_DEBUG "online_pages %lx at %lx failed\n", nr_pages, pfn); memory_notify(MEM_CANCEL_ONLINE, &arg); + unlock_memory_hotplug(); return ret; } @@ -467,6 +470,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) if (onlined_pages) memory_notify(MEM_ONLINE, &arg); + unlock_memory_hotplug(); return 0; } -- cgit v1.2.3 From 5f24ce5fd34c3ca1b3d10d30da754732da64d5c0 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 13 Jan 2011 15:47:00 -0800 Subject: thp: remove PG_buddy PG_buddy can be converted to _mapcount == -2. So the PG_compound_lock can be added to page->flags without overflowing (because of the sparse section bits increasing) with CONFIG_X86_PAE=y and CONFIG_X86_PAT=y. This also has to move the memory hotplug code from _mapcount to lru.next to avoid any risk of clashes. We can't use lru.next for PG_buddy removal, but memory hotplug can use lru.next even more easily than the mapcount instead. Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/page.c | 14 ++++++++------ include/linux/memory_hotplug.h | 14 +++++++++----- include/linux/mm.h | 21 +++++++++++++++++++++ include/linux/page-flags.h | 7 +------ mm/memory_hotplug.c | 14 ++++++++------ mm/page_alloc.c | 7 +++---- mm/sparse.c | 4 ++-- 7 files changed, 52 insertions(+), 29 deletions(-) (limited to 'include/linux/memory_hotplug.h') diff --git a/fs/proc/page.c b/fs/proc/page.c index b06c674624e6..6d8e6a9e93ab 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -116,15 +116,17 @@ u64 stable_page_flags(struct page *page) if (PageHuge(page)) u |= 1 << KPF_HUGE; - u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked); - /* - * Caveats on high order pages: - * PG_buddy will only be set on the head page; SLUB/SLQB do the same - * for PG_slab; SLOB won't set PG_slab at all on compound pages. + * Caveats on high order pages: page->_count will only be set + * -1 on the head page; SLUB/SLQB do the same for PG_slab; + * SLOB won't set PG_slab at all on compound pages. */ + if (PageBuddy(page)) + u |= 1 << KPF_BUDDY; + + u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked); + u |= kpf_copy_bit(k, KPF_SLAB, PG_slab); - u |= kpf_copy_bit(k, KPF_BUDDY, PG_buddy); u |= kpf_copy_bit(k, KPF_ERROR, PG_error); u |= kpf_copy_bit(k, KPF_DIRTY, PG_dirty); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 31c237a00c48..24376fe7ee68 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -13,12 +13,16 @@ struct mem_section; #ifdef CONFIG_MEMORY_HOTPLUG /* - * Types for free bootmem. - * The normal smallest mapcount is -1. Here is smaller value than it. + * Types for free bootmem stored in page->lru.next. These have to be in + * some random range in unsigned long space for debugging purposes. */ -#define SECTION_INFO (-1 - 1) -#define MIX_SECTION_INFO (-1 - 2) -#define NODE_INFO (-1 - 3) +enum { + MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12, + SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, + MIX_SECTION_INFO, + NODE_INFO, + MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO, +}; /* * pgdat resizing functions diff --git a/include/linux/mm.h b/include/linux/mm.h index 2ec5138badab..7ab7d2b60041 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -397,6 +397,27 @@ static inline void init_page_count(struct page *page) atomic_set(&page->_count, 1); } +/* + * PageBuddy() indicate that the page is free and in the buddy system + * (see mm/page_alloc.c). + */ +static inline int PageBuddy(struct page *page) +{ + return atomic_read(&page->_mapcount) == -2; +} + +static inline void __SetPageBuddy(struct page *page) +{ + VM_BUG_ON(atomic_read(&page->_mapcount) != -1); + atomic_set(&page->_mapcount, -2); +} + +static inline void __ClearPageBuddy(struct page *page) +{ + VM_BUG_ON(!PageBuddy(page)); + atomic_set(&page->_mapcount, -1); +} + void put_page(struct page *page); void put_pages_list(struct list_head *pages); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4ca1241ef94e..0db8037e2725 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -48,9 +48,6 @@ * struct page (these bits with information) are always mapped into kernel * address space... * - * PG_buddy is set to indicate that the page is free and in the buddy system - * (see mm/page_alloc.c). - * * PG_hwpoison indicates that a page got corrupted in hardware and contains * data with incorrect ECC bits that triggered a machine check. Accessing is * not safe since it may cause another machine check. Don't touch! @@ -96,7 +93,6 @@ enum pageflags { PG_swapcache, /* Swap page: swp_entry_t in private */ PG_mappedtodisk, /* Has blocks allocated on-disk */ PG_reclaim, /* To be reclaimed asap */ - PG_buddy, /* Page is free, on buddy lists */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ #ifdef CONFIG_MMU @@ -233,7 +229,6 @@ PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1) * risky: they bypass page accounting. */ TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback) -__PAGEFLAG(Buddy, buddy) PAGEFLAG(MappedToDisk, mappedtodisk) /* PG_readahead is only used for file reads; PG_reclaim is only for writes */ @@ -461,7 +456,7 @@ static inline int PageTransCompound(struct page *page) #define PAGE_FLAGS_CHECK_AT_FREE \ (1 << PG_lru | 1 << PG_locked | \ 1 << PG_private | 1 << PG_private_2 | \ - 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \ + 1 << PG_writeback | 1 << PG_reserved | \ 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \ __PG_COMPOUND_LOCK) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a2832c092509..e92f04749fcb 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -82,9 +82,10 @@ static void release_memory_resource(struct resource *res) #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE #ifndef CONFIG_SPARSEMEM_VMEMMAP -static void get_page_bootmem(unsigned long info, struct page *page, int type) +static void get_page_bootmem(unsigned long info, struct page *page, + unsigned long type) { - atomic_set(&page->_mapcount, type); + page->lru.next = (struct list_head *) type; SetPagePrivate(page); set_page_private(page, info); atomic_inc(&page->_count); @@ -94,15 +95,16 @@ static void get_page_bootmem(unsigned long info, struct page *page, int type) * so use __ref to tell modpost not to generate a warning */ void __ref put_page_bootmem(struct page *page) { - int type; + unsigned long type; - type = atomic_read(&page->_mapcount); - BUG_ON(type >= -1); + type = (unsigned long) page->lru.next; + BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || + type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE); if (atomic_dec_return(&page->_count) == 1) { ClearPagePrivate(page); set_page_private(page, 0); - reset_page_mapcount(page); + INIT_LIST_HEAD(&page->lru); __free_pages_bootmem(page, 0); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e7664b9f706c..9dfe49bceff4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -449,8 +449,8 @@ __find_combined_index(unsigned long page_idx, unsigned int 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 whether a page is in the buddy system, we set ->_mapcount -2. + * Setting, clearing, and testing _mapcount -2 is serialized by zone->lock. * * For recording page's order, we use page_private(page). */ @@ -483,7 +483,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, * as necessary, plus some accounting needed to play nicely with other * parts of the VM system. * 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 + * free pages of length of (1 << order) and marked with _mapcount -2. 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 @@ -5574,7 +5574,6 @@ static struct trace_print_flags pageflag_names[] = { {1UL << PG_swapcache, "swapcache" }, {1UL << PG_mappedtodisk, "mappedtodisk" }, {1UL << PG_reclaim, "reclaim" }, - {1UL << PG_buddy, "buddy" }, {1UL << PG_swapbacked, "swapbacked" }, {1UL << PG_unevictable, "unevictable" }, #ifdef CONFIG_MMU diff --git a/mm/sparse.c b/mm/sparse.c index 95ac219af379..93250207c5cf 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -671,10 +671,10 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) static void free_map_bootmem(struct page *page, unsigned long nr_pages) { unsigned long maps_section_nr, removing_section_nr, i; - int magic; + unsigned long magic; for (i = 0; i < nr_pages; i++, page++) { - magic = atomic_read(&page->_mapcount); + magic = (unsigned long) page->lru.next; BUG_ON(magic == NODE_INFO); -- cgit v1.2.3