linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Minchan Kim <minchan@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	jlayton@poochiereds.net, bfields@fieldses.org,
	Vlastimil Babka <vbabka@suse.cz>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	koct9i@gmail.com, aquini@redhat.com,
	virtualization@lists.linux-foundation.org,
	Mel Gorman <mgorman@suse.de>, Hugh Dickins <hughd@google.com>,
	Sergey Senozhatsky <sergey.senozhatsky@gmail.com>,
	rknize@motorola.com, Rik van Riel <riel@redhat.com>,
	Gioh Kim <gurugio@hanmail.net>, Minchan Kim <minchan@kernel.org>
Subject: [PATCH v1 10/19] zsmalloc: squeeze inuse into page->mapping
Date: Fri, 11 Mar 2016 16:30:14 +0900	[thread overview]
Message-ID: <1457681423-26664-11-git-send-email-minchan@kernel.org> (raw)
In-Reply-To: <1457681423-26664-1-git-send-email-minchan@kernel.org>

Currently, we store class:fullness into page->mapping.
The number of class we can support is 255 and fullness is 4 so
(8 + 2 = 10bit) is enough to represent them.
Meanwhile, the bits we need to store in-use objects in zspage
is that 11bit is enough.

For example, If we assume that 64K PAGE_SIZE, class_size 32
which is worst case, class->pages_per_zspage become 1 so
the number of objects in zspage is 2048 so 11bit is enough.
The next class is 32 + 256(i.e., ZS_SIZE_CLASS_DELTA).
With worst case that ZS_MAX_PAGES_PER_ZSPAGE, 64K * 4 /
(32 + 256) = 910 so 11bit is still enough.

So, we could squeeze inuse object count to page->mapping.

Signed-off-by: Minchan Kim <minchan@kernel.org>
---
 mm/zsmalloc.c | 103 ++++++++++++++++++++++++++++++++++++++++------------------
 1 file changed, 71 insertions(+), 32 deletions(-)

diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index ca663c82c1fc..954e8758a78d 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -34,8 +34,7 @@
  *		metadata.
  *	page->lru: links together first pages of various zspages.
  *		Basically forming list of zspages in a fullness group.
- *	page->mapping: class index and fullness group of the zspage
- *	page->inuse: the number of objects that are used in this zspage
+ *	page->mapping: override by struct zs_meta
  *
  * Usage of struct page flags:
  *	PG_private: identifies the first component page
@@ -132,6 +131,13 @@
 /* each chunk includes extra space to keep handle */
 #define ZS_MAX_ALLOC_SIZE	PAGE_SIZE
 
+#define CLASS_BITS	8
+#define CLASS_MASK	((1 << CLASS_BITS) - 1)
+#define FULLNESS_BITS	2
+#define FULLNESS_MASK	((1 << FULLNESS_BITS) - 1)
+#define INUSE_BITS	11
+#define INUSE_MASK	((1 << INUSE_BITS) - 1)
+
 /*
  * On systems with 4K page size, this gives 255 size classes! There is a
  * trader-off here:
@@ -145,7 +151,7 @@
  *  ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN
  *  (reason above)
  */
-#define ZS_SIZE_CLASS_DELTA	(PAGE_SIZE >> 8)
+#define ZS_SIZE_CLASS_DELTA	(PAGE_SIZE >> CLASS_BITS)
 
 /*
  * We do not maintain any list for completely empty or full pages
@@ -155,7 +161,7 @@ enum fullness_group {
 	ZS_ALMOST_EMPTY,
 	_ZS_NR_FULLNESS_GROUPS,
 
-	ZS_EMPTY,
+	ZS_EMPTY = _ZS_NR_FULLNESS_GROUPS,
 	ZS_FULL
 };
 
@@ -263,14 +269,11 @@ struct zs_pool {
 #endif
 };
 
-/*
- * A zspage's class index and fullness group
- * are encoded in its (first)page->mapping
- */
-#define CLASS_IDX_BITS	28
-#define FULLNESS_BITS	4
-#define CLASS_IDX_MASK	((1 << CLASS_IDX_BITS) - 1)
-#define FULLNESS_MASK	((1 << FULLNESS_BITS) - 1)
+struct zs_meta {
+	unsigned long class:CLASS_BITS;
+	unsigned long fullness:FULLNESS_BITS;
+	unsigned long inuse:INUSE_BITS;
+};
 
 struct mapping_area {
 #ifdef CONFIG_PGTABLE_MAPPING
@@ -413,28 +416,61 @@ static int is_last_page(struct page *page)
 	return PagePrivate2(page);
 }
 
+static int get_zspage_inuse(struct page *first_page)
+{
+	struct zs_meta *m;
+
+	VM_BUG_ON_PAGE(!is_first_page(first_page), first_page);
+
+	m = (struct zs_meta *)&first_page->mapping;
+
+	return m->inuse;
+}
+
+static void set_zspage_inuse(struct page *first_page, int val)
+{
+	struct zs_meta *m;
+
+	VM_BUG_ON_PAGE(!is_first_page(first_page), first_page);
+
+	m = (struct zs_meta *)&first_page->mapping;
+	m->inuse = val;
+}
+
+static void mod_zspage_inuse(struct page *first_page, int val)
+{
+	struct zs_meta *m;
+
+	VM_BUG_ON_PAGE(!is_first_page(first_page), first_page);
+
+	m = (struct zs_meta *)&first_page->mapping;
+	m->inuse += val;
+}
+
 static void get_zspage_mapping(struct page *first_page,
 				unsigned int *class_idx,
 				enum fullness_group *fullness)
 {
-	unsigned long m;
+	struct zs_meta *m;
+
 	VM_BUG_ON_PAGE(!is_first_page(first_page), first_page);
 
-	m = (unsigned long)first_page->mapping;
-	*fullness = m & FULLNESS_MASK;
-	*class_idx = (m >> FULLNESS_BITS) & CLASS_IDX_MASK;
+	m = (struct zs_meta *)&first_page->mapping;
+	*fullness = m->fullness;
+	*class_idx = m->class;
 }
 
 static void set_zspage_mapping(struct page *first_page,
 				unsigned int class_idx,
 				enum fullness_group fullness)
 {
-	unsigned long m;
+	struct zs_meta *m;
+
 	VM_BUG_ON_PAGE(!is_first_page(first_page), first_page);
 
-	m = ((class_idx & CLASS_IDX_MASK) << FULLNESS_BITS) |
-			(fullness & FULLNESS_MASK);
-	first_page->mapping = (struct address_space *)m;
+	m = (struct zs_meta *)&first_page->mapping;
+	m->fullness = fullness;
+	m->class = class_idx;
 }
 
 /*
@@ -627,9 +663,7 @@ static enum fullness_group get_fullness_group(struct size_class *class,
 	int inuse, objs_per_zspage;
 	enum fullness_group fg;
 
-	VM_BUG_ON_PAGE(!is_first_page(first_page), first_page);
-
-	inuse = first_page->inuse;
+	inuse = get_zspage_inuse(first_page);
 	objs_per_zspage = class->objs_per_zspage;
 
 	if (inuse == 0)
@@ -672,10 +706,10 @@ static void insert_zspage(struct size_class *class,
 
 	/*
 	 * We want to see more ZS_FULL pages and less almost
-	 * empty/full. Put pages with higher ->inuse first.
+	 * empty/full. Put pages with higher inuse first.
 	 */
 	list_add_tail(&first_page->lru, &(*head)->lru);
-	if (first_page->inuse >= (*head)->inuse)
+	if (get_zspage_inuse(first_page) >= get_zspage_inuse(*head))
 		*head = first_page;
 }
 
@@ -891,7 +925,7 @@ static void free_zspage(struct page *first_page)
 	struct page *nextp, *tmp, *head_extra;
 
 	VM_BUG_ON_PAGE(!is_first_page(first_page), first_page);
-	VM_BUG_ON_PAGE(first_page->inuse, first_page);
+	VM_BUG_ON_PAGE(get_zspage_inuse(first_page), first_page);
 
 	head_extra = (struct page *)page_private(first_page);
 
@@ -987,7 +1021,7 @@ static struct page *alloc_zspage(struct size_class *class, gfp_t flags)
 			SetPagePrivate(page);
 			set_page_private(page, 0);
 			first_page = page;
-			first_page->inuse = 0;
+			set_zspage_inuse(page, 0);
 		}
 		if (i == 1)
 			set_page_private(first_page, (unsigned long)page);
@@ -1234,9 +1268,7 @@ static bool can_merge(struct size_class *prev, int size, int pages_per_zspage)
 
 static bool zspage_full(struct size_class *class, struct page *first_page)
 {
-	VM_BUG_ON_PAGE(!is_first_page(first_page), first_page);
-
-	return first_page->inuse == class->objs_per_zspage;
+	return get_zspage_inuse(first_page) == class->objs_per_zspage;
 }
 
 unsigned long zs_get_total_pages(struct zs_pool *pool)
@@ -1369,7 +1401,7 @@ static unsigned long obj_malloc(struct size_class *class,
 		/* record handle in first_page->private */
 		set_page_private(first_page, handle);
 	kunmap_atomic(vaddr);
-	first_page->inuse++;
+	mod_zspage_inuse(first_page, 1);
 	zs_stat_inc(class, OBJ_USED, 1);
 
 	return obj;
@@ -1454,7 +1486,7 @@ static void obj_free(struct size_class *class, unsigned long obj)
 		set_page_private(first_page, 0);
 	kunmap_atomic(vaddr);
 	first_page->freelist = (void *)obj;
-	first_page->inuse--;
+	mod_zspage_inuse(first_page, -1);
 	zs_stat_dec(class, OBJ_USED, 1);
 }
 
@@ -2000,6 +2032,13 @@ static int __init zs_init(void)
 	if (ret)
 		goto notifier_fail;
 
+	/*
+	 * A zspage's class index, fullness group, inuse object count are
+	 * encoded in its (first)page->mapping so sizeof(struct zs_meta)
+	 * should be less than sizeof(page->mapping(i.e., unsigned long)).
+	 */
+	BUILD_BUG_ON(sizeof(struct zs_meta) > sizeof(unsigned long));
+
 	init_zs_size_classes();
 
 #ifdef CONFIG_ZPOOL
-- 
1.9.1

  parent reply	other threads:[~2016-03-11  7:32 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-11  7:30 [PATCH v1 00/19] Support non-lru page migration Minchan Kim
2016-03-11  7:30 ` [PATCH v1 01/19] mm: use put_page to free page instead of putback_lru_page Minchan Kim
2016-03-14  8:48   ` Vlastimil Babka
2016-03-15  1:16     ` Minchan Kim
2016-03-15 19:06       ` Vlastimil Babka
2016-03-11  7:30 ` [PATCH v1 02/19] mm/compaction: support non-lru movable page migration Minchan Kim
2016-03-11  8:11   ` kbuild test robot
2016-03-11  8:35     ` Minchan Kim
2016-03-11  7:30 ` [PATCH v1 03/19] fs/anon_inodes: new interface to create new inode Minchan Kim
2016-03-11  8:05   ` Al Viro
2016-03-11 14:24     ` Gioh Kim
2016-03-11  7:30 ` [PATCH v1 04/19] mm/balloon: use general movable page feature into balloon Minchan Kim
2016-03-11  7:30 ` [PATCH v1 05/19] zsmalloc: use first_page rather than page Minchan Kim
2016-03-15  6:19   ` Sergey Senozhatsky
2016-03-11  7:30 ` [PATCH v1 06/19] zsmalloc: clean up many BUG_ON Minchan Kim
2016-03-15  6:19   ` Sergey Senozhatsky
2016-03-11  7:30 ` [PATCH v1 07/19] zsmalloc: reordering function parameter Minchan Kim
2016-03-15  6:20   ` Sergey Senozhatsky
2016-03-11  7:30 ` [PATCH v1 08/19] zsmalloc: remove unused pool param in obj_free Minchan Kim
2016-03-15  6:21   ` Sergey Senozhatsky
2016-03-11  7:30 ` [PATCH v1 09/19] zsmalloc: keep max_object in size_class Minchan Kim
2016-03-12  1:44   ` xuyiping
2016-03-14  4:55     ` Minchan Kim
2016-03-15  6:28   ` Sergey Senozhatsky
2016-03-15  6:41     ` Minchan Kim
2016-03-11  7:30 ` Minchan Kim [this message]
2016-03-11  7:30 ` [PATCH v1 11/19] zsmalloc: squeeze freelist into page->mapping Minchan Kim
2016-03-15  6:40   ` Sergey Senozhatsky
2016-03-15  6:51     ` Minchan Kim
2016-03-17 12:09       ` YiPing Xu
2016-03-17 22:17         ` Minchan Kim
2016-03-11  7:30 ` [PATCH v1 12/19] zsmalloc: move struct zs_meta from mapping to freelist Minchan Kim
2016-03-11  7:30 ` [PATCH v1 13/19] zsmalloc: factor page chain functionality out Minchan Kim
2016-03-12  3:09   ` xuyiping
2016-03-14  4:58     ` Minchan Kim
2016-03-11  7:30 ` [PATCH v1 14/19] zsmalloc: separate free_zspage from putback_zspage Minchan Kim
2016-03-11  7:30 ` [PATCH v1 15/19] zsmalloc: zs_compact refactoring Minchan Kim
2016-03-11  7:30 ` [PATCH v1 16/19] zsmalloc: migrate head page of zspage Minchan Kim
2016-03-11  7:30 ` [PATCH v1 17/19] zsmalloc: use single linked list for page chain Minchan Kim
2016-03-11  7:30 ` [PATCH v1 18/19] zsmalloc: migrate tail pages in zspage Minchan Kim
2016-03-11  7:30 ` [PATCH v1 19/19] zram: use __GFP_MOVABLE for memory allocation Minchan Kim
2016-03-15  6:56   ` Sergey Senozhatsky

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1457681423-26664-11-git-send-email-minchan@kernel.org \
    --to=minchan@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=aquini@redhat.com \
    --cc=bfields@fieldses.org \
    --cc=gurugio@hanmail.net \
    --cc=hughd@google.com \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=jlayton@poochiereds.net \
    --cc=koct9i@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@suse.de \
    --cc=riel@redhat.com \
    --cc=rknize@motorola.com \
    --cc=sergey.senozhatsky@gmail.com \
    --cc=vbabka@suse.cz \
    --cc=virtualization@lists.linux-foundation.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).