linux-kernel - [PATCH RFC 3/6] mm/zsmalloc: use a proper page type

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20240522210341.1030552-4-david@redhat.com>
Date: Wed, 22 May 2024 23:03:38 +0200
From: David Hildenbrand <david@...hat.com>
To: linux-kernel@...r.kernel.org
Cc: linux-mm@...ck.org,
	David Hildenbrand <david@...hat.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	"Matthew Wilcox (Oracle)" <willy@...radead.org>,
	Mike Rapoport <rppt@...nel.org>,
	Minchan Kim <minchan@...nel.org>,
	Sergey Senozhatsky <senozhatsky@...omium.org>,
	Hyeonggon Yoo <42.hyeyoo@...il.com>
Subject: [PATCH RFC 3/6] mm/zsmalloc: use a proper page type

Let's clean it up: use a proper page type and store our data (offset
into a page) in the lower 16 bit as documented.

We'll have to restrict ourselves to <= 64KB base page size (so the offset
fits into 16 bit), which sounds reasonable. Unfortunately, we don't have
any space to store it elsewhere for now.

Based on this, we should do a proper "struct zsdesc" conversion, as
proposed in [1].

This removes the last _mapcount/page_type offender.

[1] https://lore.kernel.org/all/20231130101242.2590384-1-42.hyeyoo@gmail.com/

Cc: Hyeonggon Yoo <42.hyeyoo@...il.com>
Signed-off-by: David Hildenbrand <david@...hat.com>
---
 include/linux/page-flags.h |  3 +++
 mm/Kconfig                 |  1 +
 mm/zsmalloc.c              | 23 +++++++++++++++++++----
 3 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index ed9ac4b5233d..ccaf16656de9 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -959,6 +959,7 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned)
 #define PG_guard	0x00080000
 #define PG_hugetlb	0x00100800
 #define PG_slab		0x00200000
+#define PG_zsmalloc	0x00400000
 
 #define PageType(page, flag)						\
 	((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)
@@ -1073,6 +1074,8 @@ FOLIO_TYPE_OPS(hugetlb, hugetlb)
 FOLIO_TEST_FLAG_FALSE(hugetlb)
 #endif
 
+PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc)
+
 /**
  * PageHuge - Determine if the page belongs to hugetlbfs
  * @page: The page to test.
diff --git a/mm/Kconfig b/mm/Kconfig
index b4cb45255a54..0371d79b1b75 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -190,6 +190,7 @@ config ZSMALLOC
 	tristate
 	prompt "N:1 compression allocator (zsmalloc)" if ZSWAP
 	depends on MMU
+	depends on PAGE_SIZE_LESS_THAN_256KB # we want <= 64KB
 	help
 	  zsmalloc is a slab-based memory allocator designed to store
 	  pages of various compression levels efficiently. It achieves
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index b42d3545ca85..6f0032e06242 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -20,7 +20,8 @@
  *	page->index: links together all component pages of a zspage
  *		For the huge page, this is always 0, so we use this field
  *		to store handle.
- *	page->page_type: first object offset in a subpage of zspage
+ *	page->page_type: PG_zsmalloc, lower 16 bit locate the first object
+ *		offset in a subpage of a zspage
  *
  * Usage of struct page flags:
  *	PG_private: identifies the first component page
@@ -450,14 +451,22 @@ static inline struct page *get_first_page(struct zspage *zspage)
 	return first_page;
 }
 
+static inline void reset_first_obj_offset(struct page *page)
+{
+	page->page_type |= 0xffff;
+}
+
 static inline unsigned int get_first_obj_offset(struct page *page)
 {
-	return page->page_type;
+	return page->page_type & 0xffff;
 }
 
 static inline void set_first_obj_offset(struct page *page, unsigned int offset)
 {
-	page->page_type = offset;
+	BUILD_BUG_ON(PAGE_SIZE & ~0xffff);
+	VM_WARN_ON_ONCE(offset & ~0xffff);
+	page->page_type &= ~0xffff;
+	page->page_type |= offset & 0xffff;
 }
 
 static inline unsigned int get_freeobj(struct zspage *zspage)
@@ -791,8 +800,9 @@ static void reset_page(struct page *page)
 	__ClearPageMovable(page);
 	ClearPagePrivate(page);
 	set_page_private(page, 0);
-	page_mapcount_reset(page);
 	page->index = 0;
+	reset_first_obj_offset(page);
+	__ClearPageZsmalloc(page);
 }
 
 static int trylock_zspage(struct zspage *zspage)
@@ -965,11 +975,13 @@ static struct zspage *alloc_zspage(struct zs_pool *pool,
 		if (!page) {
 			while (--i >= 0) {
 				dec_zone_page_state(pages[i], NR_ZSPAGES);
+				__ClearPageZsmalloc(pages[i]);
 				__free_page(pages[i]);
 			}
 			cache_free_zspage(pool, zspage);
 			return NULL;
 		}
+		__SetPageZsmalloc(page);
 
 		inc_zone_page_state(page, NR_ZSPAGES);
 		pages[i] = page;
@@ -1762,6 +1774,9 @@ static int zs_page_migrate(struct page *newpage, struct page *page,
 
 	VM_BUG_ON_PAGE(!PageIsolated(page), page);
 
+	/* We're committed, tell the world that this is a Zsmalloc page. */
+	__SetPageZsmalloc(newpage);
+
 	/* The page is locked, so this pointer must remain valid */
 	zspage = get_zspage(page);
 	pool = zspage->pool;
-- 
2.45.0