Introduce an array of struct obj_cgroup pointers to zspage to keep track
of compressed objects' memcg ownership, if the zs_pool has been made to
be memcg-aware at creation time.
Move the error path for alloc_zspage to a jump label to simplify the
growing error handling path for a failed zpdesc allocation.
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Suggested-by: Harry Yoo <harry.yoo@oracle.com>
Signed-off-by: Joshua Hahn <joshua.hahnjy@gmail.com>
---
mm/zsmalloc.c | 34 ++++++++++++++++++++++++++--------
1 file changed, 26 insertions(+), 8 deletions(-)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 3f0f42b78314..dcf99516227c 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -39,6 +39,7 @@
#include <linux/zsmalloc.h>
#include <linux/fs.h>
#include <linux/workqueue.h>
+#include <linux/memcontrol.h>
#include "zpdesc.h"
#define ZSPAGE_MAGIC 0x58
@@ -273,6 +274,7 @@ struct zspage {
struct zpdesc *first_zpdesc;
struct list_head list; /* fullness list */
struct zs_pool *pool;
+ struct obj_cgroup **objcgs;
struct zspage_lock zsl;
};
@@ -825,6 +827,8 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class,
zpdesc = next;
} while (zpdesc != NULL);
+ if (pool->memcg_aware)
+ kfree(zspage->objcgs);
cache_free_zspage(zspage);
class_stat_sub(class, ZS_OBJS_ALLOCATED, class->objs_per_zspage);
@@ -946,6 +950,16 @@ static struct zspage *alloc_zspage(struct zs_pool *pool,
if (!IS_ENABLED(CONFIG_COMPACTION))
gfp &= ~__GFP_MOVABLE;
+ if (pool->memcg_aware) {
+ zspage->objcgs = kcalloc(class->objs_per_zspage,
+ sizeof(struct obj_cgroup *),
+ gfp & ~__GFP_HIGHMEM);
+ if (!zspage->objcgs) {
+ cache_free_zspage(zspage);
+ return NULL;
+ }
+ }
+
zspage->magic = ZSPAGE_MAGIC;
zspage->pool = pool;
zspage->class = class->index;
@@ -955,14 +969,8 @@ static struct zspage *alloc_zspage(struct zs_pool *pool,
struct zpdesc *zpdesc;
zpdesc = alloc_zpdesc(gfp, nid);
- if (!zpdesc) {
- while (--i >= 0) {
- zpdesc_dec_zone_page_state(zpdescs[i]);
- free_zpdesc(zpdescs[i]);
- }
- cache_free_zspage(zspage);
- return NULL;
- }
+ if (!zpdesc)
+ goto err;
__zpdesc_set_zsmalloc(zpdesc);
zpdesc_inc_zone_page_state(zpdesc);
@@ -973,6 +981,16 @@ static struct zspage *alloc_zspage(struct zs_pool *pool,
init_zspage(class, zspage);
return zspage;
+
+err:
+ while (--i >= 0) {
+ zpdesc_dec_zone_page_state(zpdescs[i]);
+ free_zpdesc(zpdescs[i]);
+ }
+ if (pool->memcg_aware)
+ kfree(zspage->objcgs);
+ cache_free_zspage(zspage);
+ return NULL;
}
static struct zspage *find_get_zspage(struct size_class *class)
--
2.52.0On Wed, Mar 11, 2026 at 12:52 PM Joshua Hahn <joshua.hahnjy@gmail.com> wrote:
>
> Introduce an array of struct obj_cgroup pointers to zspage to keep track
> of compressed objects' memcg ownership, if the zs_pool has been made to
> be memcg-aware at creation time.
>
> Move the error path for alloc_zspage to a jump label to simplify the
> growing error handling path for a failed zpdesc allocation.
>
> Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
> Suggested-by: Harry Yoo <harry.yoo@oracle.com>
> Signed-off-by: Joshua Hahn <joshua.hahnjy@gmail.com>
> ---
> mm/zsmalloc.c | 34 ++++++++++++++++++++++++++--------
> 1 file changed, 26 insertions(+), 8 deletions(-)
>
> diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
> index 3f0f42b78314..dcf99516227c 100644
> --- a/mm/zsmalloc.c
> +++ b/mm/zsmalloc.c
> @@ -39,6 +39,7 @@
> #include <linux/zsmalloc.h>
> #include <linux/fs.h>
> #include <linux/workqueue.h>
> +#include <linux/memcontrol.h>
> #include "zpdesc.h"
>
> #define ZSPAGE_MAGIC 0x58
> @@ -273,6 +274,7 @@ struct zspage {
> struct zpdesc *first_zpdesc;
> struct list_head list; /* fullness list */
> struct zs_pool *pool;
> + struct obj_cgroup **objcgs;
> struct zspage_lock zsl;
> };
>
> @@ -825,6 +827,8 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class,
> zpdesc = next;
> } while (zpdesc != NULL);
>
> + if (pool->memcg_aware)
> + kfree(zspage->objcgs);
> cache_free_zspage(zspage);
>
> class_stat_sub(class, ZS_OBJS_ALLOCATED, class->objs_per_zspage);
> @@ -946,6 +950,16 @@ static struct zspage *alloc_zspage(struct zs_pool *pool,
> if (!IS_ENABLED(CONFIG_COMPACTION))
> gfp &= ~__GFP_MOVABLE;
>
> + if (pool->memcg_aware) {
> + zspage->objcgs = kcalloc(class->objs_per_zspage,
> + sizeof(struct obj_cgroup *),
> + gfp & ~__GFP_HIGHMEM);
I remembered asking this, so my apologies if I missed/forgot your
response - but would vmalloc work here? i.e kvcalloc to fallback to
vmalloc etc.?
> + if (!zspage->objcgs) {
> + cache_free_zspage(zspage);
> + return NULL;
> + }
> + }
> +
> zspage->magic = ZSPAGE_MAGIC;
> zspage->pool = pool;
> zspage->class = class->index;
> @@ -955,14 +969,8 @@ static struct zspage *alloc_zspage(struct zs_pool *pool,
> struct zpdesc *zpdesc;
>
> zpdesc = alloc_zpdesc(gfp, nid);
> - if (!zpdesc) {
> - while (--i >= 0) {
> - zpdesc_dec_zone_page_state(zpdescs[i]);
> - free_zpdesc(zpdescs[i]);
> - }
> - cache_free_zspage(zspage);
> - return NULL;
> - }
> + if (!zpdesc)
> + goto err;
> __zpdesc_set_zsmalloc(zpdesc);
>
> zpdesc_inc_zone_page_state(zpdesc);
> @@ -973,6 +981,16 @@ static struct zspage *alloc_zspage(struct zs_pool *pool,
> init_zspage(class, zspage);
>
> return zspage;
> +
> +err:
> + while (--i >= 0) {
> + zpdesc_dec_zone_page_state(zpdescs[i]);
> + free_zpdesc(zpdescs[i]);
> + }
> + if (pool->memcg_aware)
> + kfree(zspage->objcgs);
> + cache_free_zspage(zspage);
> + return NULL;
> }
>
> static struct zspage *find_get_zspage(struct size_class *class)
> --
> 2.52.0
>
On Wed, 11 Mar 2026 13:17:22 -0700 Nhat Pham <nphamcs@gmail.com> wrote:
> On Wed, Mar 11, 2026 at 12:52 PM Joshua Hahn <joshua.hahnjy@gmail.com> wrote:
> >
> > Introduce an array of struct obj_cgroup pointers to zspage to keep track
> > of compressed objects' memcg ownership, if the zs_pool has been made to
> > be memcg-aware at creation time.
> >
> > Move the error path for alloc_zspage to a jump label to simplify the
> > growing error handling path for a failed zpdesc allocation.
> >
> > Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
> > Suggested-by: Harry Yoo <harry.yoo@oracle.com>
> > Signed-off-by: Joshua Hahn <joshua.hahnjy@gmail.com>
> > ---
> > mm/zsmalloc.c | 34 ++++++++++++++++++++++++++--------
> > 1 file changed, 26 insertions(+), 8 deletions(-)
> >
> > diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
> > index 3f0f42b78314..dcf99516227c 100644
> > --- a/mm/zsmalloc.c
> > +++ b/mm/zsmalloc.c
> > @@ -39,6 +39,7 @@
> > #include <linux/zsmalloc.h>
> > #include <linux/fs.h>
> > #include <linux/workqueue.h>
> > +#include <linux/memcontrol.h>
> > #include "zpdesc.h"
> >
> > #define ZSPAGE_MAGIC 0x58
> > @@ -273,6 +274,7 @@ struct zspage {
> > struct zpdesc *first_zpdesc;
> > struct list_head list; /* fullness list */
> > struct zs_pool *pool;
> > + struct obj_cgroup **objcgs;
> > struct zspage_lock zsl;
> > };
> >
> > @@ -825,6 +827,8 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class,
> > zpdesc = next;
> > } while (zpdesc != NULL);
> >
> > + if (pool->memcg_aware)
> > + kfree(zspage->objcgs);
> > cache_free_zspage(zspage);
> >
> > class_stat_sub(class, ZS_OBJS_ALLOCATED, class->objs_per_zspage);
> > @@ -946,6 +950,16 @@ static struct zspage *alloc_zspage(struct zs_pool *pool,
> > if (!IS_ENABLED(CONFIG_COMPACTION))
> > gfp &= ~__GFP_MOVABLE;
> >
> > + if (pool->memcg_aware) {
> > + zspage->objcgs = kcalloc(class->objs_per_zspage,
> > + sizeof(struct obj_cgroup *),
> > + gfp & ~__GFP_HIGHMEM);
>
> I remembered asking this, so my apologies if I missed/forgot your
> response - but would vmalloc work here? i.e kvcalloc to fallback to
> vmalloc etc.?
Hello Nhat : -)
Thank you for reviewing, and for your acks on the other parts!
You're right, I missed changing that on my end after v1. No reason
vmalloc shouldn't work here, let me make that change in v3.
Thanks, I hope you have a great day!
Joshua
© 2016 - 2026 Red Hat, Inc.