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 ++++ 1 file changed, 4 insertions(+) (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); -- cgit v1.2.2 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 ++++++ 1 file changed, 6 insertions(+) (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 -- cgit v1.2.2 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 ++++++ 1 file changed, 6 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); -- cgit v1.2.2 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 --- include/linux/memory_hotplug.h | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux/memory_hotplug.h') 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 -- cgit v1.2.2