The patch titled
Subject: zsmalloc: migrate tail pages in zspage
has been added to the -mm tree. Its filename is
zsmalloc-migrate-tail-pages-in-zspage.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/zsmalloc-migrate-tail-pages-in-zspage.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/zsmalloc-migrate-tail-pages-in-zspage.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/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Minchan Kim <minchan@xxxxxxxxxx>
Subject: zsmalloc: migrate tail pages in zspage
This patch enables tail page migration of zspage.
In this point, I tested zsmalloc regression with micro-benchmark which
does zs_malloc/map/unmap/zs_free for all size class in every CPU(my system
is 12) during 20 sec.
It shows 1% regression which is really small when we consider the benefit
of this feature and realworkload overhead(i.e., most overhead comes from
compression).
Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx>Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: Konstantin Khlebnikov <koct9i@xxxxxxxxx>
Cc: Rafael Aquini <aquini@xxxxxxxxxx>
Cc: Russ Knize <rknize@xxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Sergey Senozhatsky <sergey.senozhatsky@xxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Gioh Kim <gi-oh.kim@xxxxxxxxxxxxxxxx>
Cc: Sangseok Lee <sangseok.lee@xxxxxxx>
Cc: Chan Gyun Jeong <chan.jeong@xxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: YiPing Xu <xuyiping@xxxxxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/zsmalloc.c | 129 ++++++++++++++++++++++++++++++++++++++++++------
1 file changed, 114 insertions(+), 15 deletions(-)
diff -puN mm/zsmalloc.c~zsmalloc-migrate-tail-pages-in-zspage mm/zsmalloc.c
--- a/mm/zsmalloc.c~zsmalloc-migrate-tail-pages-in-zspage
+++ a/mm/zsmalloc.c
@@ -551,6 +551,19 @@ static void set_zspage_mapping(struct pa
m->class = class_idx;
}
+static bool check_isolated_page(struct page *first_page)
+{
+ struct page *cursor;
+
+ for (cursor = first_page; cursor != NULL; cursor =
+ get_next_page(cursor)) {
+ if (PageIsolated(cursor))
+ return true;
+ }
+
+ return false;
+}
+
/*
* zsmalloc divides the pool into various size classes where each
* class maintains a list of zspages where each zspage is divided
@@ -1052,6 +1065,44 @@ void lock_zspage(struct page *first_page
} while ((cursor = get_next_page(cursor)) != NULL);
}
+int trylock_zspage(struct page *first_page, struct page *locked_page)
+{
+ struct page *cursor, *fail;
+
+ VM_BUG_ON_PAGE(!is_first_page(first_page), first_page);
+
+ for (cursor = first_page; cursor != NULL; cursor =
+ get_next_page(cursor)) {
+ if (cursor != locked_page) {
+ if (!trylock_page(cursor)) {
+ fail = cursor;
+ goto unlock;
+ }
+ }
+ }
+
+ return 1;
+unlock:
+ for (cursor = first_page; cursor != fail; cursor =
+ get_next_page(cursor)) {
+ if (cursor != locked_page)
+ unlock_page(cursor);
+ }
+
+ return 0;
+}
+
+void unlock_zspage(struct page *first_page, struct page *locked_page)
+{
+ struct page *cursor = first_page;
+
+ for (; cursor != NULL; cursor = get_next_page(cursor)) {
+ VM_BUG_ON_PAGE(!PageLocked(cursor), cursor);
+ if (cursor != locked_page)
+ unlock_page(cursor);
+ }
+}
+
static void free_zspage(struct zs_pool *pool, struct page *first_page)
{
struct page *nextp, *tmp;
@@ -1090,15 +1141,16 @@ static void init_zspage(struct size_clas
first_page->freelist = NULL;
INIT_LIST_HEAD(&first_page->lru);
set_zspage_inuse(first_page, 0);
- BUG_ON(!trylock_page(first_page));
- __SetPageMovable(first_page, mapping);
- unlock_page(first_page);
while (page) {
struct page *next_page;
struct link_free *link;
void *vaddr;
+ BUG_ON(!trylock_page(page));
+ __SetPageMovable(page, mapping);
+ unlock_page(page);
+
vaddr = kmap_atomic(page);
link = (struct link_free *)vaddr + off / sizeof(*link);
@@ -1848,6 +1900,7 @@ static enum fullness_group putback_zspag
VM_BUG_ON_PAGE(!list_empty(&first_page->lru), first_page);
VM_BUG_ON_PAGE(ZsPageIsolate(first_page), first_page);
+ VM_BUG_ON_PAGE(check_isolated_page(first_page), first_page);
fullness = get_fullness_group(class, first_page);
insert_zspage(class, fullness, first_page);
@@ -1954,6 +2007,12 @@ static struct page *isolate_source_page(
if (!page)
continue;
+ /* To prevent race between object and page migration */
+ if (!trylock_zspage(page, NULL)) {
+ page = NULL;
+ continue;
+ }
+
remove_zspage(class, i, page);
inuse = get_zspage_inuse(page);
@@ -1962,6 +2021,7 @@ static struct page *isolate_source_page(
if (inuse != freezed) {
unfreeze_zspage(class, page, freezed);
putback_zspage(class, page);
+ unlock_zspage(page, NULL);
page = NULL;
continue;
}
@@ -1993,6 +2053,12 @@ static struct page *isolate_target_page(
if (!page)
continue;
+ /* To prevent race between object and page migration */
+ if (!trylock_zspage(page, NULL)) {
+ page = NULL;
+ continue;
+ }
+
remove_zspage(class, i, page);
inuse = get_zspage_inuse(page);
@@ -2001,6 +2067,7 @@ static struct page *isolate_target_page(
if (inuse != freezed) {
unfreeze_zspage(class, page, freezed);
putback_zspage(class, page);
+ unlock_zspage(page, NULL);
page = NULL;
continue;
}
@@ -2074,11 +2141,13 @@ static void __zs_compact(struct zs_pool
putback_zspage(class, dst_page);
unfreeze_zspage(class, dst_page,
class->objs_per_zspage);
+ unlock_zspage(dst_page, NULL);
spin_unlock(&class->lock);
dst_page = NULL;
}
if (zspage_empty(class, src_page)) {
+ unlock_zspage(src_page, NULL);
free_zspage(pool, src_page);
spin_lock(&class->lock);
zs_stat_dec(class, OBJ_ALLOCATED,
@@ -2101,12 +2170,14 @@ static void __zs_compact(struct zs_pool
putback_zspage(class, src_page);
unfreeze_zspage(class, src_page,
class->objs_per_zspage);
+ unlock_zspage(src_page, NULL);
}
if (dst_page) {
putback_zspage(class, dst_page);
unfreeze_zspage(class, dst_page,
class->objs_per_zspage);
+ unlock_zspage(dst_page, NULL);
}
spin_unlock(&class->lock);
@@ -2209,10 +2280,11 @@ bool zs_page_isolate(struct page *page,
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageIsolated(page), page);
/*
- * In this implementation, it allows only first page migration.
+ * first_page will not be destroyed by PG_lock of @page but it could
+ * be migrated out. For prohibiting it, zs_page_migrate calls
+ * trylock_zspage so it closes the race.
*/
- VM_BUG_ON_PAGE(!is_first_page(page), page);
- first_page = page;
+ first_page = get_first_page(page);
/*
* Without class lock, fullness is meaningless while constant
@@ -2226,9 +2298,18 @@ bool zs_page_isolate(struct page *page,
if (!spin_trylock(&class->lock))
return false;
+ if (check_isolated_page(first_page))
+ goto skip_isolate;
+
+ /*
+ * If this is first time isolation for zspage, isolate zspage from
+ * size_class to prevent further allocations from the zspage.
+ */
get_zspage_mapping(first_page, &class_idx, &fullness);
remove_zspage(class, fullness, first_page);
SetZsPageIsolate(first_page);
+
+skip_isolate:
SetPageIsolated(page);
spin_unlock(&class->lock);
@@ -2251,7 +2332,7 @@ int zs_page_migrate(struct address_space
VM_BUG_ON_PAGE(!PageMovable(page), page);
VM_BUG_ON_PAGE(!PageIsolated(page), page);
- first_page = page;
+ first_page = get_first_page(page);
get_zspage_mapping(first_page, &class_idx, &fullness);
pool = page->mapping->private_data;
class = pool->size_class[class_idx];
@@ -2266,6 +2347,13 @@ int zs_page_migrate(struct address_space
if (get_zspage_inuse(first_page) == 0)
goto out_class_unlock;
+ /*
+ * It prevents first_page migration during tail page opeartion for
+ * get_first_page's stability.
+ */
+ if (!trylock_zspage(first_page, page))
+ goto out_class_unlock;
+
freezed = freeze_zspage(class, first_page);
if (freezed != get_zspage_inuse(first_page))
goto out_unfreeze;
@@ -2304,21 +2392,26 @@ int zs_page_migrate(struct address_space
kunmap_atomic(addr);
replace_sub_page(class, first_page, newpage, page);
- first_page = newpage;
+ first_page = get_first_page(newpage);
get_page(newpage);
VM_BUG_ON_PAGE(get_fullness_group(class, first_page) ==
ZS_EMPTY, first_page);
- ClearZsPageIsolate(first_page);
- putback_zspage(class, first_page);
+ if (!check_isolated_page(first_page)) {
+ INIT_LIST_HEAD(&first_page->lru);
+ ClearZsPageIsolate(first_page);
+ putback_zspage(class, first_page);
+ }
+
/* Migration complete. Free old page */
ClearPageIsolated(page);
reset_page(page);
put_page(page);
ret = MIGRATEPAGE_SUCCESS;
-
+ page = newpage;
out_unfreeze:
unfreeze_zspage(class, first_page, freezed);
+ unlock_zspage(first_page, page);
out_class_unlock:
spin_unlock(&class->lock);
@@ -2336,7 +2429,7 @@ void zs_page_putback(struct page *page)
VM_BUG_ON_PAGE(!PageMovable(page), page);
VM_BUG_ON_PAGE(!PageIsolated(page), page);
- first_page = page;
+ first_page = get_first_page(page);
get_zspage_mapping(first_page, &class_idx, &fullness);
pool = page->mapping->private_data;
class = pool->size_class[class_idx];
@@ -2346,11 +2439,17 @@ void zs_page_putback(struct page *page)
* in zs_free will wait the page lock of @page without
* destroying of zspage.
*/
- INIT_LIST_HEAD(&first_page->lru);
spin_lock(&class->lock);
ClearPageIsolated(page);
- ClearZsPageIsolate(first_page);
- putback_zspage(class, first_page);
+ /*
+ * putback zspage to right list if this is last isolated page
+ * putback in the zspage.
+ */
+ if (!check_isolated_page(first_page)) {
+ INIT_LIST_HEAD(&first_page->lru);
+ ClearZsPageIsolate(first_page);
+ putback_zspage(class, first_page);
+ }
spin_unlock(&class->lock);
}
_
Patches currently in -mm which might be from minchan@xxxxxxxxxx are
zsmalloc-use-first_page-rather-than-page.patch
zsmalloc-clean-up-many-bug_on.patch
zsmalloc-reordering-function-parameter.patch
zsmalloc-remove-unused-pool-param-in-obj_free.patch
mm-use-put_page-to-free-page-instead-of-putback_lru_page.patch
mm-compaction-support-non-lru-movable-page-migration.patch
mm-add-non-lru-movable-page-support-document.patch
mm-balloon-use-general-movable-page-feature-into-balloon.patch
zsmalloc-keep-max_object-in-size_class.patch
zsmalloc-squeeze-inuse-into-page-mapping.patch
zsmalloc-remove-page_mapcount_reset.patch
zsmalloc-squeeze-freelist-into-page-mapping.patch
zsmalloc-move-struct-zs_meta-from-mapping-to-freelist.patch
zsmalloc-factor-page-chain-functionality-out.patch
zsmalloc-separate-free_zspage-from-putback_zspage.patch
zsmalloc-zs_compact-refactoring.patch
zsmalloc-migrate-head-page-of-zspage.patch
zsmalloc-use-single-linked-list-for-page-chain.patch
zsmalloc-migrate-tail-pages-in-zspage.patch
zram-use-__gfp_movable-for-memory-allocation.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
