Re: [PATCH v2 3/6] mm/zsmalloc: use a proper page type

[Matthew Wilcox]

On Thu, May 30, 2024 at 02:01:23PM +0900, Sergey Senozhatsky wrote:
> On (24/05/29 13:19), David Hildenbrand wrote:
> > We won't be able to support 256 KiB base pages, which is acceptable.
> [..]
> > +config HAVE_ZSMALLOC
> > +	def_bool y
> > +	depends on MMU
> > +	depends on PAGE_SIZE_LESS_THAN_256KB # we want <= 64 KiB
> 
> Can't really say that I'm happy with this, but if mm-folks are
> fine then okay.

I have an idea ...

We use 6 of the bits in the top byte of the page_type to enumerate
a type (ie value 0x80-0xbf) and then the remaining 24 bits are
available.  It's actually more efficient:

$ ./scripts/bloat-o-meter prev.o .build-debian/mm/filemap.o 
add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-40 (-40)
Function                                     old     new   delta
__filemap_add_folio                         1102    1098      -4
filemap_unaccount_folio                      455     446      -9
replace_page_cache_folio                     474     447     -27
Total: Before=41258, After=41218, chg -0.10%

(that's all from PG_hugetlb)

before:
    1406:       8b 46 30                mov    0x30(%rsi),%eax
                mapcount = atomic_read(&folio->_mapcount) + 1;
    1409:       83 c0 01                add    $0x1,%eax
                if (mapcount < PAGE_MAPCOUNT_RESERVE + 1)
    140c:       83 f8 81                cmp    $0xffffff81,%eax
    140f:       7d 6c                   jge    147d <filemap_unaccount_folio+0x8d>
    1411:       8b 43 30                mov    0x30(%rbx),%eax
    1414:       25 00 08 00 f0          and    $0xf0000800,%eax
    1419:       3d 00 00 00 f0          cmp    $0xf0000000,%eax
    141e:       74 4e                   je     146e <filemap_unaccount_folio+0x7e>

after:
    1406:       8b 46 30                mov    0x30(%rsi),%eax
                mapcount = atomic_read(&folio->_mapcount) + 1;
    1409:       83 c0 01                add    $0x1,%eax
                if (mapcount < PAGE_MAPCOUNT_RESERVE + 1)
    140c:       83 f8 81                cmp    $0xffffff81,%eax
    140f:       7d 63                   jge    1474 <filemap_unaccount_folio+0x8
4>
        if (folio_test_hugetlb(folio))
    1411:       80 7b 33 84             cmpb   $0x84,0x33(%rbx)
    1415:       74 4e                   je     1465 <filemap_unaccount_folio+0x75>

so we go from "mov, and, cmp, je" to just "cmpb, je", which must surely
be faster to execute as well as being more compact in the I$ (6 bytes vs 15).

Anyway, not tested but this is the patch I used to generate the above.
More for comment than application.

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 5265b3434b9e..4129d04ac812 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -942,24 +942,24 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned)
  * mistaken for a page type value.
  */
 
-#define PAGE_TYPE_BASE	0xf0000000
-/* Reserve		0x0000007f to catch underflows of _mapcount */
-#define PAGE_MAPCOUNT_RESERVE	-128
-#define PG_buddy	0x00000080
-#define PG_offline	0x00000100
-#define PG_table	0x00000200
-#define PG_guard	0x00000400
-#define PG_hugetlb	0x00000800
-#define PG_slab		0x00001000
-
-#define PageType(page, flag)						\
-	((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)
-#define folio_test_type(folio, flag)					\
-	((folio->page.page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)
+/* Reserve             0x0000007f to catch underflows of _mapcount */
+#define PAGE_MAPCOUNT_RESERVE  -128
+
+#define PG_buddy	0x80
+#define PG_offline	0x81
+#define PG_table	0x82
+#define PG_guard	0x83
+#define PG_hugetlb	0x84
+#define PG_slab		0x85
+
+#define PageType(page, type)						\
+	(((page)->page_type >> 24) == type)
+#define folio_test_type(folio, type)					\
+	(((folio)->page.page_type >> 24) == type)
 
 static inline int page_type_has_type(unsigned int page_type)
 {
-	return (int)page_type < PAGE_MAPCOUNT_RESERVE;
+	return ((int)page_type < 0) && (page_type < 0xc0000000);
 }
 
 static inline int page_has_type(const struct page *page)
@@ -975,12 +975,12 @@ static __always_inline bool folio_test_##fname(const struct folio *folio)\
 static __always_inline void __folio_set_##fname(struct folio *folio)	\
 {									\
 	VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio);		\
-	folio->page.page_type &= ~PG_##lname;				\
+	folio->page.page_type = PG_##lname << 24;			\
 }									\
 static __always_inline void __folio_clear_##fname(struct folio *folio)	\
 {									\
 	VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio);		\
-	folio->page.page_type |= PG_##lname;				\
+	folio->page.page_type = 0xffffffff;				\
 }
 
 #define PAGE_TYPE_OPS(uname, lname, fname)				\
@@ -992,12 +992,12 @@ static __always_inline int Page##uname(const struct page *page)		\
 static __always_inline void __SetPage##uname(struct page *page)		\
 {									\
 	VM_BUG_ON_PAGE(!PageType(page, 0), page);			\
-	page->page_type &= ~PG_##lname;					\
+	page->page_type = PG_##lname << 24;				\
 }									\
 static __always_inline void __ClearPage##uname(struct page *page)	\
 {									\
 	VM_BUG_ON_PAGE(!Page##uname(page), page);			\
-	page->page_type |= PG_##lname;					\
+	page->page_type = 0xffffffff;					\
 }
 
 /*