Commit 6e292b9b authored by Matthew Wilcox's avatar Matthew Wilcox Committed by Linus Torvalds

mm: split page_type out from _mapcount

We're already using a union of many fields here, so stop abusing the
_mapcount and make page_type its own field.  That implies renaming some of
the machinery that creates PageBuddy, PageBalloon and PageKmemcg; bring
back the PG_buddy, PG_balloon and PG_kmemcg names.

As suggested by Kirill, make page_type a bitmask.  Because it starts out
life as -1 (thanks to sharing the storage with _mapcount), setting a page
flag means clearing the appropriate bit.  This gives us space for probably
twenty or so extra bits (depending how paranoid we want to be about
_mapcount underflow).

Link: default avatarMatthew Wilcox <>
Acked-by: default avatarKirill A. Shutemov <>
Acked-by: default avatarVlastimil Babka <>
Cc: Christoph Lameter <>
Cc: Dave Hansen <>
Cc: Jérôme Glisse <>
Cc: Lai Jiangshan <>
Cc: Martin Schwidefsky <>
Cc: Pekka Enberg <>
Cc: Randy Dunlap <>
Cc: Andrey Ryabinin <>
Signed-off-by: default avatarAndrew Morton <>
Signed-off-by: default avatarLinus Torvalds <>
parent 620b4e90
......@@ -96,6 +96,14 @@ struct page {
union {
* If the page is neither PageSlab nor mappable to userspace,
* the value stored here may help determine what this page
* is used for. See page-flags.h for a list of page types
* which are currently stored here.
unsigned int page_type;
_slub_counter_t counters;
unsigned int active; /* SLAB */
struct { /* SLUB */
......@@ -109,11 +117,6 @@ struct page {
* Count of ptes mapped in mms, to show when
* page is mapped & limit reverse map searches.
* Extra information about page type may be
* stored here for pages that are never mapped,
* in which case the value MUST BE <= -2.
* See page-flags.h for more details.
atomic_t _mapcount;
......@@ -642,49 +642,56 @@ PAGEFLAG_FALSE(DoubleMap)
* For pages that are never mapped to userspace, page->mapcount may be
* used for storing extra information about page type. Any value used
* for this purpose must be <= -2, but it's better start not too close
* to -2 so that an underflow of the page_mapcount() won't be mistaken
* for a special page.
* For pages that are never mapped to userspace (and aren't PageSlab),
* page_type may be used. Because it is initialised to -1, we invert the
* sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and
* __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and
* low bits so that an underflow or overflow of page_mapcount() won't be
* mistaken for a page type value.
#define PAGE_MAPCOUNT_OPS(uname, lname) \
#define PAGE_TYPE_BASE 0xf0000000
/* Reserve 0x0000007f to catch underflows of page_mapcount */
#define PG_buddy 0x00000080
#define PG_balloon 0x00000100
#define PG_kmemcg 0x00000200
#define PageType(page, flag) \
((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)
#define PAGE_TYPE_OPS(uname, lname) \
static __always_inline int Page##uname(struct page *page) \
{ \
return atomic_read(&page->_mapcount) == \
return PageType(page, PG_##lname); \
} \
static __always_inline void __SetPage##uname(struct page *page) \
{ \
VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page); \
atomic_set(&page->_mapcount, PAGE_##lname##_MAPCOUNT_VALUE); \
VM_BUG_ON_PAGE(!PageType(page, 0), page); \
page->page_type &= ~PG_##lname; \
} \
static __always_inline void __ClearPage##uname(struct page *page) \
{ \
VM_BUG_ON_PAGE(!Page##uname(page), page); \
atomic_set(&page->_mapcount, -1); \
page->page_type |= PG_##lname; \
* PageBuddy() indicate that the page is free and in the buddy system
* PageBuddy() indicates that the page is free and in the buddy system
* (see mm/page_alloc.c).
PAGE_TYPE_OPS(Buddy, buddy)
* PageBalloon() is set on pages that are on the balloon page list
* PageBalloon() is true for pages that are on the balloon page list
* (see mm/balloon_compaction.c).
PAGE_TYPE_OPS(Balloon, balloon)
* If kmemcg is enabled, the buddy allocator will set PageKmemcg() on
* pages allocated with __GFP_ACCOUNT. It gets cleared on page free.
PAGE_TYPE_OPS(Kmemcg, kmemcg)
extern bool is_free_buddy_page(struct page *page);
......@@ -460,6 +460,7 @@ static int __init crash_save_vmcoreinfo_init(void)
......@@ -705,16 +705,14 @@ static inline void rmv_page_order(struct page *page)
* This function checks whether a page is free && is the buddy
* we can do coalesce a page and its buddy if
* we can coalesce a page and its buddy if
* (a) the buddy is not in a hole (check before calling!) &&
* (b) the buddy is in the buddy system &&
* (c) a page and its buddy have the same order &&
* (d) a page and its buddy are in the same zone.
* For recording whether a page is in the buddy system, we set ->_mapcount
* Setting, clearing, and testing _mapcount PAGE_BUDDY_MAPCOUNT_VALUE is
* serialized by zone->lock.
* For recording whether a page is in the buddy system, we set PageBuddy.
* Setting, clearing, and testing PageBuddy is serialized by zone->lock.
* For recording page's order, we use page_private(page).
......@@ -759,9 +757,8 @@ 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 _mapcount
* PAGE_BUDDY_MAPCOUNT_VALUE. Page's order is recorded in page_private(page)
* field.
* free pages of length of (1 << order) and marked with PageBuddy.
* Page's order is recorded in page_private(page) field.
* So when we are allocating or freeing one, we can derive the state of the
* other. That is, if we allocate a small block, and both were
* free, the remainder of the region must be split into blocks.
......@@ -179,9 +179,9 @@ regex_c=(
'/^TASK_PFA_TEST([^,]*, *\([[:alnum:]_]*\))/task_\1/'
'/^TASK_PFA_SET([^,]*, *\([[:alnum:]_]*\))/task_set_\1/'
'/^TASK_PFA_CLEAR([^,]*, *\([[:alnum:]_]*\))/task_clear_\1/'
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment