zswap: memcontrol: implement zswap writeback disabling

During our experiment with zswap, we sometimes observe swap IOs due to
occasional zswap store failures and writebacks-to-swap.  These swapping
IOs prevent many users who cannot tolerate swapping from adopting zswap to
save memory and improve performance where possible.

This patch adds the option to disable this behavior entirely: do not
writeback to backing swapping device when a zswap store attempt fail, and
do not write pages in the zswap pool back to the backing swap device (both
when the pool is full, and when the new zswap shrinker is called).

This new behavior can be opted-in/out on a per-cgroup basis via a new
cgroup file.  By default, writebacks to swap device is enabled, which is
the previous behavior.  Initially, writeback is enabled for the root
cgroup, and a newly created cgroup will inherit the current setting of its
parent.

Note that this is subtly different from setting memory.swap.max to 0, as
it still allows for pages to be stored in the zswap pool (which itself
consumes swap space in its current form).

This patch should be applied on top of the zswap shrinker series:

https://lore.kernel.org/linux-mm/20231130194023.4102148-1-nphamcs@gmail.com/

as it also disables the zswap shrinker, a major source of zswap
writebacks.

For the most part, this feature is motivated by internal parties who
have already established their opinions regarding swapping - the
workloads that are highly sensitive to IO, and especially those who are
using servers with really slow disk performance (for instance, massive
but slow HDDs).  For these folks, it's impossible to convince them to
even entertain zswap if swapping also comes as a packaged deal. 
Writeback disabling is quite a useful feature in these situations - on
a mixed workloads deployment, they can disable writeback for the more
IO-sensitive workloads, and enable writeback for other background
workloads.

For instance, on a server with HDD, I allocate memories and populate
them with random values (so that zswap store will always fail), and
specify memory.high low enough to trigger reclaim.  The time it takes
to allocate the memories and just read through it a couple of times
(doing silly things like computing the values' average etc.):

zswap.writeback disabled:
real 0m30.537s
user 0m23.687s
sys 0m6.637s
0 pages swapped in
0 pages swapped out

zswap.writeback enabled:
real 0m45.061s
user 0m24.310s
sys 0m8.892s
712686 pages swapped in
461093 pages swapped out

(the last two lines are from vmstat -s).

[nphamcs@gmail.com: add a comment about recurring zswap store failures leading to reclaim inefficiency]
  Link: https://lkml.kernel.org/r/20231221005725.3446672-1-nphamcs@gmail.com
Link: https://lkml.kernel.org/r/20231207192406.3809579-1-nphamcs@gmail.com
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Chris Li <chrisl@kernel.org>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: David Heidelberg <david@ixit.cz>
Cc: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Cc: Zefan Li <lizefan.x@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

4 files changed, 55 insertions, 4 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b08b9cd4a3a8..3ca691fb5b49 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 09c6a4f316f3..ae2b49055e43 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 a4d388973021..928aa2304932 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 f760801a3ea8..ca25b676048e 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.