The patch titled
Subject: mm: split page_type out from _mapcount
has been added to the -mm tree. Its filename is
mm-split-page_type-out-from-_mapcount.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-split-page_type-out-from-_mapcount.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-split-page_type-out-from-_mapcount.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Matthew Wilcox <mawilcox@xxxxxxxxxxxxx>
Subject: 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: http://lkml.kernel.org/r/20180518194519.3820-3-willy@xxxxxxxxxxxxx
Signed-off-by: Matthew Wilcox <mawilcox@xxxxxxxxxxxxx>
Acked-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Acked-by: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Jérôme Glisse <jglisse@xxxxxxxxxx>
Cc: Lai Jiangshan <jiangshanlai@xxxxxxxxx>
Cc: Martin Schwidefsky <schwidefsky@xxxxxxxxxx>
Cc: Pekka Enberg <penberg@xxxxxxxxxx>
Cc: Randy Dunlap <rdunlap@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mm_types.h | 13 ++++++----
include/linux/page-flags.h | 45 ++++++++++++++++++++---------------
kernel/crash_core.c | 1
mm/page_alloc.c | 13 +++-------
scripts/tags.sh | 6 ++--
5 files changed, 43 insertions(+), 35 deletions(-)
diff -puN include/linux/mm_types.h~mm-split-page_type-out-from-_mapcount include/linux/mm_types.h
--- a/include/linux/mm_types.h~mm-split-page_type-out-from-_mapcount
+++ a/include/linux/mm_types.h
@@ -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;
diff -puN include/linux/page-flags.h~mm-split-page_type-out-from-_mapcount include/linux/page-flags.h
--- a/include/linux/page-flags.h~mm-split-page_type-out-from-_mapcount
+++ a/include/linux/page-flags.h
@@ -642,49 +642,56 @@ PAGEFLAG_FALSE(DoubleMap)
#endif
/*
- * 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) == \
- PAGE_##lname##_MAPCOUNT_VALUE; \
+ 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).
*/
-#define PAGE_BUDDY_MAPCOUNT_VALUE (-128)
-PAGE_MAPCOUNT_OPS(Buddy, BUDDY)
+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).
*/
-#define PAGE_BALLOON_MAPCOUNT_VALUE (-256)
-PAGE_MAPCOUNT_OPS(Balloon, BALLOON)
+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.
*/
-#define PAGE_KMEMCG_MAPCOUNT_VALUE (-512)
-PAGE_MAPCOUNT_OPS(Kmemcg, KMEMCG)
+PAGE_TYPE_OPS(Kmemcg, kmemcg)
extern bool is_free_buddy_page(struct page *page);
diff -puN kernel/crash_core.c~mm-split-page_type-out-from-_mapcount kernel/crash_core.c
--- a/kernel/crash_core.c~mm-split-page_type-out-from-_mapcount
+++ a/kernel/crash_core.c
@@ -460,6 +460,7 @@ static int __init crash_save_vmcoreinfo_
VMCOREINFO_NUMBER(PG_hwpoison);
#endif
VMCOREINFO_NUMBER(PG_head_mask);
+#define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy)
VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE);
#ifdef CONFIG_HUGETLB_PAGE
VMCOREINFO_NUMBER(HUGETLB_PAGE_DTOR);
diff -puN mm/page_alloc.c~mm-split-page_type-out-from-_mapcount mm/page_alloc.c
--- a/mm/page_alloc.c~mm-split-page_type-out-from-_mapcount
+++ a/mm/page_alloc.c
@@ -705,16 +705,14 @@ static inline void rmv_page_order(struct
/*
* 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
- * PAGE_BUDDY_MAPCOUNT_VALUE.
- * 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 p
* 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.
diff -puN scripts/tags.sh~mm-split-page_type-out-from-_mapcount scripts/tags.sh
--- a/scripts/tags.sh~mm-split-page_type-out-from-_mapcount
+++ a/scripts/tags.sh
@@ -185,9 +185,9 @@ regex_c=(
'/\<CLEARPAGEFLAG_NOOP(\([[:alnum:]_]*\).*/ClearPage\1/'
'/\<__CLEARPAGEFLAG_NOOP(\([[:alnum:]_]*\).*/__ClearPage\1/'
'/\<TESTCLEARFLAG_FALSE(\([[:alnum:]_]*\).*/TestClearPage\1/'
- '/^PAGE_MAPCOUNT_OPS(\([[:alnum:]_]*\).*/Page\1/'
- '/^PAGE_MAPCOUNT_OPS(\([[:alnum:]_]*\).*/__SetPage\1/'
- '/^PAGE_MAPCOUNT_OPS(\([[:alnum:]_]*\).*/__ClearPage\1/'
+ '/^PAGE_TYPE_OPS(\([[:alnum:]_]*\).*/Page\1/'
+ '/^PAGE_TYPE_OPS(\([[:alnum:]_]*\).*/__SetPage\1/'
+ '/^PAGE_TYPE_OPS(\([[:alnum:]_]*\).*/__ClearPage\1/'
'/^TASK_PFA_TEST([^,]*, *\([[:alnum:]_]*\))/task_\1/'
'/^TASK_PFA_SET([^,]*, *\([[:alnum:]_]*\))/task_set_\1/'
'/^TASK_PFA_CLEAR([^,]*, *\([[:alnum:]_]*\))/task_clear_\1/'
_
Patches currently in -mm which might be from mawilcox@xxxxxxxxxxxxx are
lib-test_bitmapc-fix-bitmap-optimisation-tests-to-report-errors-correctly.patch
slab-__gfp_zero-is-incompatible-with-a-constructor.patch
s390-use-_refcount-for-pgtables.patch
mm-split-page_type-out-from-_mapcount.patch
mm-mark-pages-in-use-for-page-tables.patch
mm-switch-s_mem-and-slab_cache-in-struct-page.patch
mm-move-private-union-within-struct-page.patch
mm-move-_refcount-out-of-struct-page-union.patch
mm-combine-first-three-unions-in-struct-page.patch
mm-use-page-deferred_list.patch
mm-move-lru-union-within-struct-page.patch
mm-combine-lru-and-main-union-in-struct-page.patch
mm-improve-struct-page-documentation.patch
mm-add-pt_mm-to-struct-page.patch
mm-add-hmm_data-to-struct-page.patch
slabslub-remove-rcu_head-size-checks.patch
slub-remove-kmem_cache-reserved.patch
slub-remove-reserved-file-from-sysfs.patch
mm-distinguish-vmalloc-pages.patch
ida-remove-simple_ida_lock.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
