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 <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 31c237a..24376fe 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -13,12 +13,16 @@
#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 2ec5138..7ab7d2b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -397,6 +397,27 @@
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 4ca1241..0db8037 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 @@
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 @@
* 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 @@
#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)