diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 3f85254f3cef2c22012e08ed61061795c5f8c99a..5ec7dd753cd15f4d983aa90b256d1b4d5068bbd4 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1679,6 +1679,21 @@ PAGE_SIZE multiple when read back.
limit, it will refuse to take any more stores before existing
entries fault back in or are written out to disk.
+ memory.zswap.writeback
+ A read-write single value file. The default value is "1". The
+ initial value of the root cgroup is 1, and when a new cgroup is
+ created, it inherits the current value of its parent.
+
+ When this is set to 0, all swapping attempts to swapping devices
+ are disabled. This included both zswap writebacks, and swapping due
+ to zswap store failures. If the zswap store failures are recurring
+ (for e.g if the pages are incompressible), users can observe
+ reclaim inefficiency after disabling writeback (because the same
+ pages might be rejected again and again).
+
+ Note that this is subtly different from setting memory.swap.max to
+ 0, as it still allows for pages to be written to the zswap pool.
+
memory.pressure
A read-only nested-keyed file.
diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst
index 62fc244ec70204bfd912d6a2ed3b93c819d7136b..b42132969e31570986f4d60eaf3e550c6365ab2a 100644
--- a/Documentation/admin-guide/mm/zswap.rst
+++ b/Documentation/admin-guide/mm/zswap.rst
@@ -153,6 +153,16 @@ attribute, e. g.::
Setting this parameter to 100 will disable the hysteresis.
+Some users cannot tolerate the swapping that comes with zswap store failures
+and zswap writebacks. Swapping can be disabled entirely (without disabling
+zswap itself) on a cgroup-basis as follows:
+
+ echo 0 > /sys/fs/cgroup/<cgroup-name>/memory.zswap.writeback
+
+Note that if the store failures are recurring (for e.g if the pages are
+incompressible), users can observe reclaim inefficiency after disabling
+writeback (because the same pages might be rejected again and again).
+
When there is a sizable amount of cold memory residing in the zswap pool, it
can be advantageous to proactively write these cold pages to swap and reclaim
the memory for other use cases. By default, the zswap shrinker is disabled.
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 43b77363ab8e74954184ea7dfb9eaee52ad1de2d..5de775e6cdd91754d9b7136ad6737a6fdb8c3a04 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -219,6 +219,12 @@ struct mem_cgroup {
#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
unsigned long zswap_max;
+
+ /*
+ * Prevent pages from this memcg from being written back from zswap to
+ * swap, and from being swapped out on zswap store failures.
+ */
+ bool zswap_writeback;
#endif
unsigned long soft_limit;
@@ -1941,6 +1947,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
bool obj_cgroup_may_zswap(struct obj_cgroup *objcg);
void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size);
void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size);
+bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg);
#else
static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
{
@@ -1954,6 +1961,11 @@ static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg,
size_t size)
{
}
+static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
+{
+ /* if zswap is disabled, do not block pages going to the swapping device */
+ return true;
+}
#endif
#endif /* _LINUX_MEMCONTROL_H */
diff --git a/include/linux/zswap.h b/include/linux/zswap.h
index e88572d4c72028065d45075b9904d08528fcea89..0b709f5bc65fac2477df81ee766305dd2aa33200 100644
--- a/include/linux/zswap.h
+++ b/include/linux/zswap.h
@@ -35,6 +35,7 @@ void zswap_swapoff(int type);
void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg);
void zswap_lruvec_state_init(struct lruvec *lruvec);
void zswap_folio_swapin(struct folio *folio);
+bool is_zswap_enabled(void);
#else
struct zswap_lruvec_state {};
@@ -55,6 +56,12 @@ static inline void zswap_swapoff(int type) {}
static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {}
static inline void zswap_lruvec_state_init(struct lruvec *lruvec) {}
static inline void zswap_folio_swapin(struct folio *folio) {}
+
+static inline bool is_zswap_enabled(void)
+{
+ return false;
+}
+
#endif
#endif /* _LINUX_ZSWAP_H */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b08b9cd4a3a8fd937cfb53b4d5b517aba7a07749..3ca691fb5b491f080a10ac61ba35f79319b8b8f4 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5538,6 +5538,8 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX);
#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
memcg->zswap_max = PAGE_COUNTER_MAX;
+ WRITE_ONCE(memcg->zswap_writeback,
+ !parent || READ_ONCE(parent->zswap_writeback));
#endif
page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
if (parent) {
@@ -8166,6 +8168,12 @@ void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size)
rcu_read_unlock();
}
+bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
+{
+ /* if zswap is disabled, do not block pages going to the swapping device */
+ return !is_zswap_enabled() || !memcg || READ_ONCE(memcg->zswap_writeback);
+}
+
static u64 zswap_current_read(struct cgroup_subsys_state *css,
struct cftype *cft)
{
@@ -8198,6 +8206,31 @@ static ssize_t zswap_max_write(struct kernfs_open_file *of,
return nbytes;
}
+static int zswap_writeback_show(struct seq_file *m, void *v)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
+
+ seq_printf(m, "%d\n", READ_ONCE(memcg->zswap_writeback));
+ return 0;
+}
+
+static ssize_t zswap_writeback_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+ int zswap_writeback;
+ ssize_t parse_ret = kstrtoint(strstrip(buf), 0, &zswap_writeback);
+
+ if (parse_ret)
+ return parse_ret;
+
+ if (zswap_writeback != 0 && zswap_writeback != 1)
+ return -EINVAL;
+
+ WRITE_ONCE(memcg->zswap_writeback, zswap_writeback);
+ return nbytes;
+}
+
static struct cftype zswap_files[] = {
{
.name = "zswap.current",
@@ -8210,6 +8243,11 @@ static struct cftype zswap_files[] = {
.seq_show = zswap_max_show,
.write = zswap_max_write,
},
+ {
+ .name = "zswap.writeback",
+ .seq_show = zswap_writeback_show,
+ .write = zswap_writeback_write,
+ },
{ } /* terminate */
};
#endif /* CONFIG_MEMCG_KMEM && CONFIG_ZSWAP */
diff --git a/mm/page_io.c b/mm/page_io.c
index 09c6a4f316f3e205c310c83433d8f9ee2bc36fc7..ae2b49055e435713d75bed34cf1c58168925aa45 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -201,6 +201,11 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
folio_end_writeback(folio);
return 0;
}
+ if (!mem_cgroup_zswap_writeback_enabled(folio_memcg(folio))) {
+ folio_mark_dirty(folio);
+ return AOP_WRITEPAGE_ACTIVATE;
+ }
+
__swap_writepage(folio, wbc);
return 0;
}
diff --git a/mm/shmem.c b/mm/shmem.c
index a4d388973021a94271a891134de652eaa648bc48..928aa230493261ef5abfe2ad21217d8b94c6bd12 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1514,8 +1514,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
mutex_unlock(&shmem_swaplist_mutex);
BUG_ON(folio_mapped(folio));
- swap_writepage(&folio->page, wbc);
- return 0;
+ return swap_writepage(&folio->page, wbc);
}
mutex_unlock(&shmem_swaplist_mutex);
diff --git a/mm/zswap.c b/mm/zswap.c
index f760801a3ea87ccef81fb65bd3e954c245200f62..ca25b676048ea6d0b399661e9ebca137585f8dbd 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -153,6 +153,11 @@ static bool zswap_shrinker_enabled = IS_ENABLED(
CONFIG_ZSWAP_SHRINKER_DEFAULT_ON);
module_param_named(shrinker_enabled, zswap_shrinker_enabled, bool, 0644);
+bool is_zswap_enabled(void)
+{
+ return zswap_enabled;
+}
+
/*********************************
* data structures
**********************************/
@@ -596,7 +601,8 @@ static unsigned long zswap_shrinker_scan(struct shrinker *shrinker,
struct zswap_pool *pool = shrinker->private_data;
bool encountered_page_in_swapcache = false;
- if (!zswap_shrinker_enabled) {
+ if (!zswap_shrinker_enabled ||
+ !mem_cgroup_zswap_writeback_enabled(sc->memcg)) {
sc->nr_scanned = 0;
return SHRINK_STOP;
}
@@ -637,7 +643,7 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker,
struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(sc->nid));
unsigned long nr_backing, nr_stored, nr_freeable, nr_protected;
- if (!zswap_shrinker_enabled)
+ if (!zswap_shrinker_enabled || !mem_cgroup_zswap_writeback_enabled(memcg))
return 0;
#ifdef CONFIG_MEMCG_KMEM
@@ -923,6 +929,9 @@ static int shrink_memcg(struct mem_cgroup *memcg)
struct zswap_pool *pool;
int nid, shrunk = 0;
+ if (!mem_cgroup_zswap_writeback_enabled(memcg))
+ return -EINVAL;
+
/*
* Skip zombies because their LRUs are reparented and we would be
* reclaiming from the parent instead of the dead memcg.