summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorSergey Senozhatsky <sergey.senozhatsky.work@gmail.com>2018-04-05 16:24:43 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-04-05 21:36:26 -0700
commit010b495e2fa32353d0ef6aa70a8169e5ef617a15 (patch)
tree4816a3f43c5ccbbfa8f0a95d4024b338c2400ae7
parentcb9f753a3731f7fe16447bea45cb6f8e8bb432fb (diff)
zsmalloc: introduce zs_huge_class_size()
Patch series "zsmalloc/zram: drop zram's max_zpage_size", v3. ZRAM's max_zpage_size is a bad thing. It forces zsmalloc to store normal objects as huge ones, which results in bigger zsmalloc memory usage. Drop it and use actual zsmalloc huge-class value when decide if the object is huge or not. This patch (of 2): Not every object can be share its zspage with other objects, e.g. when the object is as big as zspage or nearly as big a zspage. For such objects zsmalloc has a so called huge class - every object which belongs to huge class consumes the entire zspage (which consists of a physical page). On x86_64, PAGE_SHIFT 12 box, the first non-huge class size is 3264, so starting down from size 3264, objects can share page(-s) and thus minimize memory wastage. ZRAM, however, has its own statically defined watermark for huge objects, namely "3 * PAGE_SIZE / 4 = 3072", and forcibly stores every object larger than this watermark (3072) as a PAGE_SIZE object, in other words, to a huge class, while zsmalloc can keep some of those objects in non-huge classes. This results in increased memory consumption. zsmalloc knows better if the object is huge or not. Introduce zs_huge_class_size() function which tells if the given object can be stored in one of non-huge classes or not. This will let us to drop ZRAM's huge object watermark and fully rely on zsmalloc when we decide if the object is huge. [sergey.senozhatsky.work@gmail.com: add pool param to zs_huge_class_size()] Link: http://lkml.kernel.org/r/20180314081833.1096-2-sergey.senozhatsky@gmail.com Link: http://lkml.kernel.org/r/20180306070639.7389-2-sergey.senozhatsky@gmail.com Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Acked-by: Minchan Kim <minchan@kernel.org> Cc: Mike Rapoport <rppt@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--include/linux/zsmalloc.h2
-rw-r--r--mm/zsmalloc.c41
2 files changed, 43 insertions, 0 deletions
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index 57a8e98f2708..2219cce81ca4 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -47,6 +47,8 @@ void zs_destroy_pool(struct zs_pool *pool);
unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t flags);
void zs_free(struct zs_pool *pool, unsigned long obj);
+size_t zs_huge_class_size(struct zs_pool *pool);
+
void *zs_map_object(struct zs_pool *pool, unsigned long handle,
enum zs_mapmode mm);
void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index a583ab111a43..5a532ebedc44 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -193,6 +193,7 @@ static struct vfsmount *zsmalloc_mnt;
* (see: fix_fullness_group())
*/
static const int fullness_threshold_frac = 4;
+static size_t huge_class_size;
struct size_class {
spinlock_t lock;
@@ -1407,6 +1408,25 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
}
EXPORT_SYMBOL_GPL(zs_unmap_object);
+/**
+ * zs_huge_class_size() - Returns the size (in bytes) of the first huge
+ * zsmalloc &size_class.
+ * @pool: zsmalloc pool to use
+ *
+ * The function returns the size of the first huge class - any object of equal
+ * or bigger size will be stored in zspage consisting of a single physical
+ * page.
+ *
+ * Context: Any context.
+ *
+ * Return: the size (in bytes) of the first huge zsmalloc &size_class.
+ */
+size_t zs_huge_class_size(struct zs_pool *pool)
+{
+ return huge_class_size;
+}
+EXPORT_SYMBOL_GPL(zs_huge_class_size);
+
static unsigned long obj_malloc(struct size_class *class,
struct zspage *zspage, unsigned long handle)
{
@@ -2364,6 +2384,27 @@ struct zs_pool *zs_create_pool(const char *name)
objs_per_zspage = pages_per_zspage * PAGE_SIZE / size;
/*
+ * We iterate from biggest down to smallest classes,
+ * so huge_class_size holds the size of the first huge
+ * class. Any object bigger than or equal to that will
+ * endup in the huge class.
+ */
+ if (pages_per_zspage != 1 && objs_per_zspage != 1 &&
+ !huge_class_size) {
+ huge_class_size = size;
+ /*
+ * The object uses ZS_HANDLE_SIZE bytes to store the
+ * handle. We need to subtract it, because zs_malloc()
+ * unconditionally adds handle size before it performs
+ * size class search - so object may be smaller than
+ * huge class size, yet it still can end up in the huge
+ * class because it grows by ZS_HANDLE_SIZE extra bytes
+ * right before class lookup.
+ */
+ huge_class_size -= (ZS_HANDLE_SIZE - 1);
+ }
+
+ /*
* size_class is used for normal zsmalloc operation such
* as alloc/free for that size. Although it is natural that we
* have one size_class for each size, there is a chance that we