* [PATCH v4 1/5] mm/zswap: Extend shrink_memcg() writeback capability
2026-06-18 4:48 [PATCH v4 0/5] mm/zswap: Implement per-cgroup proactive writeback Hao Jia
@ 2026-06-18 4:48 ` Hao Jia
2026-06-18 4:48 ` [PATCH v4 2/5] mm/zswap: Factor writeback loop out of shrink_worker() Hao Jia
` (3 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Hao Jia @ 2026-06-18 4:48 UTC (permalink / raw)
To: akpm, tj, hannes, shakeel.butt, mhocko, yosry, mkoutny, nphamcs,
chengming.zhou, muchun.song, roman.gushchin
Cc: linux-mm, linux-kernel, linux-doc, Hao Jia
From: Hao Jia <jiahao1@lixiang.com>
Currently, shrink_memcg() writes back at most one entry per-node
during its traversal. This makes shrink_worker() inefficient, as
it must repeatedly re-enter shrink_memcg() to make any substantial
progress.
To address this, extend shrink_memcg() and rewrite its LRU iteration
logic to support batch writeback. Introduce the nr_to_writeback
parameter to support a writeback budget based on compressed size.
This enables batch writeback in the shrink_worker() path, while
maintaining a low writeback budget in the zswap_store() path.
Additionally, to prepare for future proactive writeback, update
the return value semantics of shrink_memcg(): a positive value now
represents the actual number of compressed bytes written back, 0
indicates that candidates existed but no writeback succeeded, and
a negative value represents an error code.
Suggested-by: Yosry Ahmed <yosry@kernel.org>
Signed-off-by: Hao Jia <jiahao1@lixiang.com>
---
mm/zswap.c | 116 ++++++++++++++++++++++++++++++++++++++++++++---------
1 file changed, 97 insertions(+), 19 deletions(-)
diff --git a/mm/zswap.c b/mm/zswap.c
index 761cd699e0a3..d7d031dee4cd 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -160,6 +160,11 @@ struct zswap_pool {
char tfm_name[CRYPTO_MAX_ALG_NAME];
};
+struct zswap_shrink_walk_arg {
+ unsigned long bytes_written;
+ bool encountered_page_in_swapcache;
+};
+
/* Global LRU lists shared by all zswap pools. */
static struct list_lru zswap_list_lru;
@@ -1089,8 +1094,9 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
void *arg)
{
struct zswap_entry *entry = container_of(item, struct zswap_entry, lru);
- bool *encountered_page_in_swapcache = (bool *)arg;
+ struct zswap_shrink_walk_arg *walk_arg = arg;
swp_entry_t swpentry;
+ unsigned int length;
enum lru_status ret = LRU_REMOVED_RETRY;
int writeback_result;
@@ -1135,8 +1141,13 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
* Once the lru lock is dropped, the entry might get freed. The
* swpentry is copied to the stack, and entry isn't deref'd again
* until the entry is verified to still be alive in the tree.
+ *
+ * entry->length is also copied while the lock is held, because
+ * zswap_writeback_entry() frees the entry on success and we still
+ * need its compressed size to account for writeback.
*/
swpentry = entry->swpentry;
+ length = entry->length;
/*
* It's safe to drop the lock here because we return either
@@ -1155,12 +1166,13 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
* into the warmer region. We should terminate shrinking (if we're in the dynamic
* shrinker context).
*/
- if (writeback_result == -EEXIST && encountered_page_in_swapcache) {
+ if (writeback_result == -EEXIST) {
ret = LRU_STOP;
- *encountered_page_in_swapcache = true;
+ walk_arg->encountered_page_in_swapcache = true;
}
} else {
zswap_written_back_pages++;
+ walk_arg->bytes_written += length;
}
return ret;
@@ -1169,8 +1181,11 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
static unsigned long zswap_shrinker_scan(struct shrinker *shrinker,
struct shrink_control *sc)
{
+ struct zswap_shrink_walk_arg walk_arg = {
+ .bytes_written = 0,
+ .encountered_page_in_swapcache = false,
+ };
unsigned long shrink_ret;
- bool encountered_page_in_swapcache = false;
if (!zswap_shrinker_enabled ||
!mem_cgroup_zswap_writeback_enabled(sc->memcg)) {
@@ -1179,9 +1194,9 @@ static unsigned long zswap_shrinker_scan(struct shrinker *shrinker,
}
shrink_ret = list_lru_shrink_walk(&zswap_list_lru, sc, &shrink_memcg_cb,
- &encountered_page_in_swapcache);
+ &walk_arg);
- if (encountered_page_in_swapcache)
+ if (walk_arg.encountered_page_in_swapcache)
return SHRINK_STOP;
return shrink_ret ? shrink_ret : SHRINK_STOP;
@@ -1275,10 +1290,32 @@ static struct shrinker *zswap_alloc_shrinker(void)
return shrinker;
}
-static int shrink_memcg(struct mem_cgroup *memcg)
-{
- int nid, shrunk = 0, scanned = 0;
+/*
+ * The maximum acceptable scan cost factor for writing back
+ * PAGE_SIZE bytes of compressed data.
+ */
+#define ZSWAP_WB_SCAN_FACTOR 16UL
+#define NR_ZSWAP_WB_BATCH 64UL
+/*
+ * Iterate over the per-node zswap LRUs of @memcg in batches, writing back
+ * up to @nr_to_writeback * PAGE_SIZE bytes of compressed data.
+ *
+ * Return: The number of bytes written back, or -ENOENT if @memcg has
+ * writeback disabled, is a zombie cgroup, or has empty zswap LRUs.
+ */
+static long shrink_memcg(struct mem_cgroup *memcg,
+ unsigned long nr_to_writeback)
+{
+ struct zswap_shrink_walk_arg walk_arg = {
+ .bytes_written = 0,
+ .encountered_page_in_swapcache = false,
+ };
+ u64 bytes_to_writeback = nr_to_writeback << PAGE_SHIFT;
+ bool memcg_list_is_empty = true;
+ int nid;
+
+ /* Memcg with zswap writeback disabled are not candidates. */
if (!mem_cgroup_zswap_writeback_enabled(memcg))
return -ENOENT;
@@ -1290,24 +1327,65 @@ static int shrink_memcg(struct mem_cgroup *memcg)
return -ENOENT;
for_each_node_state(nid, N_NORMAL_MEMORY) {
- unsigned long nr_to_walk = 1;
+ unsigned long nr_to_scan, nr_scanned = 0;
+ unsigned long remain;
+ walk_arg.encountered_page_in_swapcache = false;
+ /*
+ * Cap by LRU length: bounds rewalks when referenced
+ * entries keep rotating to the tail.
+ */
+ nr_to_scan = list_lru_count_one(&zswap_list_lru, nid, memcg);
+ if (!nr_to_scan)
+ continue;
+ memcg_list_is_empty = false;
+
+ /*
+ * Cap by SCAN_FACTOR * remain budget: bounds scan cost
+ * to the remaining writeback budget.
+ */
+ remain = DIV_ROUND_UP(bytes_to_writeback - walk_arg.bytes_written, PAGE_SIZE);
+ nr_to_scan = min(nr_to_scan,
+ remain * ZSWAP_WB_SCAN_FACTOR);
- shrunk += list_lru_walk_one(&zswap_list_lru, nid, memcg,
- &shrink_memcg_cb, NULL, &nr_to_walk);
- scanned += 1 - nr_to_walk;
+ while (nr_scanned < nr_to_scan) {
+ unsigned long nr_to_walk = min(NR_ZSWAP_WB_BATCH,
+ nr_to_scan - nr_scanned);
+
+ /*
+ * Account for the committed budget rather than the walker's
+ * actual delta. If the list is emptied concurrently, the
+ * walker visits nothing and nr_scanned would never advance.
+ */
+ nr_scanned += nr_to_walk;
+
+ list_lru_walk_one(&zswap_list_lru, nid, memcg,
+ &shrink_memcg_cb,
+ &walk_arg,
+ &nr_to_walk);
+
+ if (walk_arg.bytes_written >= bytes_to_writeback)
+ return walk_arg.bytes_written;
+
+ if (walk_arg.encountered_page_in_swapcache)
+ break;
+
+ cond_resched();
+ }
}
- if (!scanned)
+ /* Return -ENOENT if all zswap LRU lists are empty. */
+ if (memcg_list_is_empty)
return -ENOENT;
- return shrunk ? 0 : -EAGAIN;
+ return walk_arg.bytes_written;
}
static void shrink_worker(struct work_struct *w)
{
struct mem_cgroup *memcg;
- int ret, failures = 0, attempts = 0;
+ int failures = 0, attempts = 0;
unsigned long thr;
+ long ret;
/* Reclaim down to the accept threshold */
thr = zswap_accept_thr_pages();
@@ -1368,7 +1446,7 @@ static void shrink_worker(struct work_struct *w)
goto resched;
}
- ret = shrink_memcg(memcg);
+ ret = shrink_memcg(memcg, NR_ZSWAP_WB_BATCH);
/* drop the extra reference */
mem_cgroup_put(memcg);
@@ -1382,7 +1460,7 @@ static void shrink_worker(struct work_struct *w)
continue;
++attempts;
- if (ret && ++failures == MAX_RECLAIM_RETRIES)
+ if (ret <= 0 && ++failures == MAX_RECLAIM_RETRIES)
break;
resched:
cond_resched();
@@ -1492,7 +1570,7 @@ bool zswap_store(struct folio *folio)
objcg = get_obj_cgroup_from_folio(folio);
if (objcg && !obj_cgroup_may_zswap(objcg)) {
memcg = get_mem_cgroup_from_objcg(objcg);
- if (shrink_memcg(memcg)) {
+ if (shrink_memcg(memcg, 1) <= 0) {
mem_cgroup_put(memcg);
goto put_objcg;
}
--
2.34.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v4 2/5] mm/zswap: Factor writeback loop out of shrink_worker()
2026-06-18 4:48 [PATCH v4 0/5] mm/zswap: Implement per-cgroup proactive writeback Hao Jia
2026-06-18 4:48 ` [PATCH v4 1/5] mm/zswap: Extend shrink_memcg() writeback capability Hao Jia
@ 2026-06-18 4:48 ` Hao Jia
2026-06-18 4:48 ` [PATCH v4 3/5] mm/zswap: Implement proactive writeback Hao Jia
` (2 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Hao Jia @ 2026-06-18 4:48 UTC (permalink / raw)
To: akpm, tj, hannes, shakeel.butt, mhocko, yosry, mkoutny, nphamcs,
chengming.zhou, muchun.song, roman.gushchin
Cc: linux-mm, linux-kernel, linux-doc, Hao Jia
From: Hao Jia <jiahao1@lixiang.com>
In preparation for sharing the writeback loop with proactive
writeback, move the memcg iteration into zswap_iter_global() and the
loop into zswap_try_to_writeback(lower, upper). shrink_worker() is
reduced to computing the accept threshold and invoking the helper.
Suggested-by: Yosry Ahmed <yosry@kernel.org>
Signed-off-by: Hao Jia <jiahao1@lixiang.com>
---
mm/zswap.c | 136 +++++++++++++++++++++++++++++++----------------------
1 file changed, 81 insertions(+), 55 deletions(-)
diff --git a/mm/zswap.c b/mm/zswap.c
index d7d031dee4cd..e29f8a61412d 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1380,61 +1380,75 @@ static long shrink_memcg(struct mem_cgroup *memcg,
return walk_arg.bytes_written;
}
-static void shrink_worker(struct work_struct *w)
+/*
+ * Global iteration uses a global cursor to select from all online
+ * memcgs in a round-robin fashion.
+ *
+ * We save iteration cursor memcg into zswap_next_shrink,
+ * which can be modified by the offline memcg cleaner
+ * zswap_memcg_offline_cleanup().
+ *
+ * Since the offline cleaner is called only once, we cannot leave an
+ * offline memcg reference in zswap_next_shrink.
+ * We can rely on the cleaner only if we get online memcg under lock.
+ *
+ * If we get an offline memcg, we cannot determine if the cleaner has
+ * already been called or will be called later. We must put back the
+ * reference before returning from this function. Otherwise, the
+ * offline memcg left in zswap_next_shrink will hold the reference
+ * until the next run of shrink_worker().
+ */
+static struct mem_cgroup *zswap_iter_global(void)
{
struct mem_cgroup *memcg;
- int failures = 0, attempts = 0;
- unsigned long thr;
- long ret;
-
- /* Reclaim down to the accept threshold */
- thr = zswap_accept_thr_pages();
/*
- * Global reclaim will select cgroup in a round-robin fashion from all
- * online memcgs, but memcgs that have no pages in zswap and
- * writeback-disabled memcgs (memory.zswap.writeback=0) are not
- * candidates for shrinking.
+ * Start from the next memcg after zswap_next_shrink.
+ * When the offline cleaner has already advanced the cursor,
+ * advancing the cursor here overlooks one memcg, but this
+ * should be negligibly rare.
*
- * Shrinking will be aborted if we encounter the following
- * MAX_RECLAIM_RETRIES times:
- * - No writeback-candidate memcgs found in a memcg tree walk.
- * - Shrinking a writeback-candidate memcg failed.
- *
- * We save iteration cursor memcg into zswap_next_shrink,
- * which can be modified by the offline memcg cleaner
- * zswap_memcg_offline_cleanup().
- *
- * Since the offline cleaner is called only once, we cannot leave an
- * offline memcg reference in zswap_next_shrink.
- * We can rely on the cleaner only if we get online memcg under lock.
- *
- * If we get an offline memcg, we cannot determine if the cleaner has
- * already been called or will be called later. We must put back the
- * reference before returning from this function. Otherwise, the
- * offline memcg left in zswap_next_shrink will hold the reference
- * until the next run of shrink_worker().
+ * If we get an online memcg, keep the extra reference in case
+ * the original one obtained by mem_cgroup_iter() is dropped by
+ * zswap_memcg_offline_cleanup() while we are shrinking the
+ * memcg.
*/
+ spin_lock(&zswap_shrink_lock);
do {
- /*
- * Start shrinking from the next memcg after zswap_next_shrink.
- * When the offline cleaner has already advanced the cursor,
- * advancing the cursor here overlooks one memcg, but this
- * should be negligibly rare.
- *
- * If we get an online memcg, keep the extra reference in case
- * the original one obtained by mem_cgroup_iter() is dropped by
- * zswap_memcg_offline_cleanup() while we are shrinking the
- * memcg.
- */
- spin_lock(&zswap_shrink_lock);
- do {
- memcg = mem_cgroup_iter(NULL, zswap_next_shrink, NULL);
- zswap_next_shrink = memcg;
- } while (memcg && !mem_cgroup_tryget_online(memcg));
- spin_unlock(&zswap_shrink_lock);
+ memcg = mem_cgroup_iter(NULL, zswap_next_shrink, NULL);
+ zswap_next_shrink = memcg;
+ } while (memcg && !mem_cgroup_tryget_online(memcg));
+ spin_unlock(&zswap_shrink_lock);
+
+ return memcg;
+}
+
+/*
+ * Walk the memcg tree and write back zswap pages until the
+ * (lower_pages, upper_pages) window closes, or abort encounter
+ * MAX_RECLAIM_RETRIES times of the following conditions:
+ * - No writeback-candidate memcgs found in a memcg tree walk.
+ * - Shrinking a writeback-candidate memcg failed.
+ *
+ * For shrink_worker(), it passes lower=thr and upper=zswap_total_pages().
+ * The @upper limit is refreshed in each iteration by re-evaluating
+ * zswap_total_pages(), and the window closes once the total falls
+ * below the threshold.
+ */
+static void zswap_try_to_writeback(unsigned long lower_pages,
+ unsigned long upper_pages)
+{
+ int failures = 0, attempts = 0;
+ struct mem_cgroup *iter_memcg;
+
+ while (lower_pages < upper_pages) {
+ unsigned long batch_size;
+ long shrunk;
- if (!memcg) {
+ cond_resched();
+
+ iter_memcg = zswap_iter_global();
+ if (!iter_memcg) {
/*
* Continue shrinking without incrementing failures if
* we found candidate memcgs in the last tree walk.
@@ -1443,12 +1457,16 @@ static void shrink_worker(struct work_struct *w)
break;
attempts = 0;
- goto resched;
+ continue;
}
- ret = shrink_memcg(memcg, NR_ZSWAP_WB_BATCH);
+ batch_size = min(upper_pages - lower_pages, NR_ZSWAP_WB_BATCH);
+ shrunk = shrink_memcg(iter_memcg, batch_size);
/* drop the extra reference */
- mem_cgroup_put(memcg);
+ mem_cgroup_put(iter_memcg);
+
+ /* zswap total pages might have changed, refresh it. */
+ upper_pages = zswap_total_pages();
/*
* There are no writeback-candidate pages in the memcg.
@@ -1456,15 +1474,23 @@ static void shrink_worker(struct work_struct *w)
* with pages in zswap. Skip this without incrementing attempts
* and failures.
*/
- if (ret == -ENOENT)
+ if (shrunk == -ENOENT)
continue;
++attempts;
- if (ret <= 0 && ++failures == MAX_RECLAIM_RETRIES)
+ if (shrunk <= 0 && ++failures == MAX_RECLAIM_RETRIES)
break;
-resched:
- cond_resched();
- } while (zswap_total_pages() > thr);
+ }
+}
+
+static void shrink_worker(struct work_struct *w)
+{
+ unsigned long thr;
+
+ /* Reclaim down to the accept threshold */
+ thr = zswap_accept_thr_pages();
+
+ zswap_try_to_writeback(thr, zswap_total_pages());
}
/*********************************
--
2.34.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v4 3/5] mm/zswap: Implement proactive writeback
2026-06-18 4:48 [PATCH v4 0/5] mm/zswap: Implement per-cgroup proactive writeback Hao Jia
2026-06-18 4:48 ` [PATCH v4 1/5] mm/zswap: Extend shrink_memcg() writeback capability Hao Jia
2026-06-18 4:48 ` [PATCH v4 2/5] mm/zswap: Factor writeback loop out of shrink_worker() Hao Jia
@ 2026-06-18 4:48 ` Hao Jia
2026-06-18 4:48 ` [PATCH v4 4/5] mm/zswap: Add per-memcg stat for " Hao Jia
2026-06-18 4:48 ` [PATCH v4 5/5] selftests/cgroup: Add tests for zswap " Hao Jia
4 siblings, 0 replies; 6+ messages in thread
From: Hao Jia @ 2026-06-18 4:48 UTC (permalink / raw)
To: akpm, tj, hannes, shakeel.butt, mhocko, yosry, mkoutny, nphamcs,
chengming.zhou, muchun.song, roman.gushchin
Cc: linux-mm, linux-kernel, linux-doc, Hao Jia
From: Hao Jia <jiahao1@lixiang.com>
Zswap currently writes back pages to backing swap reactively, triggered
either by the shrinker or when the pool reaches its size limit. There is
no mechanism to control the amount of writeback for a specific memory
cgroup. However, users may want to proactively write back zswap pages,
e.g., to free up memory for other applications or to prepare for
memory-intensive workloads.
Introduce a "zswap_writeback_only" key to the memory.reclaim cgroup
interface. When specified, this key bypasses standard memory reclaim
and exclusively performs proactive zswap writeback up to the requested
budget. If omitted, the default reclaim behavior remains unchanged.
Example usage:
# Write back 10MB of compressed data from zswap to the backing swap
echo "10M zswap_writeback_only" > memory.reclaim
Note that the actual amount of compressed data written back may be less
than requested due to the zswap second-chance algorithm: referenced
entries are rotated on the LRU on the first encounter and only written
back on a second pass. If fewer bytes are written back than requested,
-EAGAIN is returned, matching the existing memory.reclaim semantics.
Internally, extend user_proactive_reclaim() to parse the new
"zswap_writeback_only" token and invoke the dedicated handler
zswap_proactive_writeback(). This handler reuses
zswap_try_to_writeback() to walk the target memcg subtree, draining
per-node zswap LRUs through list_lru_walk_one() with the
shrink_memcg_cb() callback.
Suggested-by: Yosry Ahmed <yosry@kernel.org>
Suggested-by: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Hao Jia <jiahao1@lixiang.com>
---
Documentation/admin-guide/cgroup-v2.rst | 18 ++++-
Documentation/admin-guide/mm/zswap.rst | 11 +++-
include/linux/zswap.h | 7 ++
mm/vmscan.c | 14 ++++
mm/zswap.c | 87 +++++++++++++++++++++----
5 files changed, 120 insertions(+), 17 deletions(-)
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 6efd0095ed99..e52d97e8e9c6 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1425,9 +1425,10 @@ PAGE_SIZE multiple when read back.
The following nested keys are defined.
- ========== ================================
+ ==================== ==================================================
swappiness Swappiness value to reclaim with
- ========== ================================
+ zswap_writeback_only Only perform proactive zswap writeback
+ ==================== ==================================================
Specifying a swappiness value instructs the kernel to perform
the reclaim with that swappiness value. Note that this has the
@@ -1437,6 +1438,19 @@ The following nested keys are defined.
The valid range for swappiness is [0-200, max], setting
swappiness=max exclusively reclaims anonymous memory.
+ The zswap_writeback_only key skips ordinary memory reclaim and
+ writes back pages from zswap to the backing swap device until
+ the requested amount has been written or no further candidates
+ are found. This is useful to proactively offload cold compressed
+ data from the zswap pool to the swap device. It is only available
+ if zswap writeback is enabled. zswap_writeback_only cannot be
+ combined with swappiness; specifying both returns -EINVAL.
+
+ Example::
+
+ # Writeback up to 10MB of compressed data from zswap to the backing swap
+ echo "10M zswap_writeback_only" > memory.reclaim
+
memory.peak
A read-write single value file which exists on non-root cgroups.
diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst
index 2464425c783d..fdeb197d1683 100644
--- a/Documentation/admin-guide/mm/zswap.rst
+++ b/Documentation/admin-guide/mm/zswap.rst
@@ -131,7 +131,16 @@ User can enable it as follows::
echo Y > /sys/module/zswap/parameters/shrinker_enabled
This can be enabled at the boot time if ``CONFIG_ZSWAP_SHRINKER_DEFAULT_ON`` is
-selected.
+selected. Once enabled, the shrinker automatically writes back zswap pages to
+backing swap during memory reclaim.
+
+If users want to explicitly trigger proactive zswap writeback for a specific
+memory cgroup without invoking standard page reclaim, it can be done as follows::
+
+ echo "10M zswap_writeback_only" > /sys/fs/cgroup/<cgroup-name>/memory.reclaim
+
+Both of the methods mentioned above are subject to the ``memory.zswap.writeback``
+control. This means that ``memory.zswap.writeback`` can prevent all zswap writeback.
A debugfs interface is provided for various statistic about pool size, number
of pages stored, same-value filled pages and various counters for the reasons
diff --git a/include/linux/zswap.h b/include/linux/zswap.h
index 30c193a1207e..7bf38318dab1 100644
--- a/include/linux/zswap.h
+++ b/include/linux/zswap.h
@@ -35,6 +35,7 @@ void zswap_lruvec_state_init(struct lruvec *lruvec);
void zswap_folio_swapin(struct folio *folio);
bool zswap_is_enabled(void);
bool zswap_never_enabled(void);
+int zswap_proactive_writeback(struct mem_cgroup *memcg, unsigned long nr_to_writeback);
#else
struct zswap_lruvec_state {};
@@ -69,6 +70,12 @@ static inline bool zswap_never_enabled(void)
return true;
}
+static inline int zswap_proactive_writeback(struct mem_cgroup *memcg,
+ unsigned long nr_to_writeback)
+{
+ return -EOPNOTSUPP;
+}
+
#endif
#endif /* _LINUX_ZSWAP_H */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 299b5d9e8836..2e6c14569fc2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -64,6 +64,7 @@
#include <linux/swapops.h>
#include <linux/sched/sysctl.h>
+#include <linux/zswap.h>
#include "internal.h"
#include "swap.h"
@@ -7855,11 +7856,13 @@ static unsigned long __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask,
enum {
MEMORY_RECLAIM_SWAPPINESS = 0,
MEMORY_RECLAIM_SWAPPINESS_MAX,
+ MEMORY_RECLAIM_ZSWAP_WRITEBACK_ONLY,
MEMORY_RECLAIM_NULL,
};
static const match_table_t tokens = {
{ MEMORY_RECLAIM_SWAPPINESS, "swappiness=%d"},
{ MEMORY_RECLAIM_SWAPPINESS_MAX, "swappiness=max"},
+ { MEMORY_RECLAIM_ZSWAP_WRITEBACK_ONLY, "zswap_writeback_only"},
{ MEMORY_RECLAIM_NULL, NULL },
};
@@ -7869,6 +7872,7 @@ int user_proactive_reclaim(char *buf,
unsigned int nr_retries = MAX_RECLAIM_RETRIES;
unsigned long nr_to_reclaim, nr_reclaimed = 0;
int swappiness = -1;
+ bool zswap_writeback_only = false;
char *old_buf, *start;
substring_t args[MAX_OPT_ARGS];
gfp_t gfp_mask = GFP_KERNEL;
@@ -7899,11 +7903,21 @@ int user_proactive_reclaim(char *buf,
case MEMORY_RECLAIM_SWAPPINESS_MAX:
swappiness = SWAPPINESS_ANON_ONLY;
break;
+ case MEMORY_RECLAIM_ZSWAP_WRITEBACK_ONLY:
+ zswap_writeback_only = true;
+ break;
default:
return -EINVAL;
}
}
+ if (zswap_writeback_only) {
+ /* zswap_writeback_only and swappiness are mutually exclusive. */
+ if (swappiness != -1)
+ return -EINVAL;
+ return zswap_proactive_writeback(memcg, nr_to_reclaim);
+ }
+
while (nr_reclaimed < nr_to_reclaim) {
/* Will converge on zero, but reclaim enforces a minimum */
unsigned long batch_size = (nr_to_reclaim - nr_reclaimed) / 4;
diff --git a/mm/zswap.c b/mm/zswap.c
index e29f8a61412d..28200552dde3 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1423,6 +1423,27 @@ static struct mem_cgroup *zswap_iter_global(void)
return memcg;
}
+/*
+ * Local iteration uses a local cursor to select from online memcgs
+ * under @root in a round-robin fashion.
+ *
+ * Pass the previous return value as @prev to advance the round-robin
+ * iteration, or pass NULL to start a new walk. If exiting early before
+ * the iteration completes, the caller must call mem_cgroup_iter_break()
+ * to release the cursor reference.
+ */
+static struct mem_cgroup *zswap_iter_local(struct mem_cgroup *root,
+ struct mem_cgroup *prev)
+{
+ struct mem_cgroup *memcg;
+
+ do {
+ memcg = mem_cgroup_iter(root, prev, NULL);
+ prev = memcg;
+ } while (memcg && !mem_cgroup_tryget_online(memcg));
+ return memcg;
+}
+
/*
* Walk the memcg tree and write back zswap pages until the
* (lower_pages, upper_pages) window closes, or abort encounter
@@ -1430,16 +1451,23 @@ static struct mem_cgroup *zswap_iter_global(void)
* - No writeback-candidate memcgs found in a memcg tree walk.
* - Shrinking a writeback-candidate memcg failed.
*
- * For shrink_worker(), it passes lower=thr and upper=zswap_total_pages().
- * The @upper limit is refreshed in each iteration by re-evaluating
- * zswap_total_pages(), and the window closes once the total falls
- * below the threshold.
+ * For shrink_worker() (proactive=false), it passes lower=thr and
+ * upper=zswap_total_pages(). The @upper limit is refreshed in each
+ * iteration by re-evaluating zswap_total_pages(), and the window
+ * closes once the total falls below the threshold.
+ *
+ * For zswap_proactive_writeback() (proactive=true), it passes lower=0
+ * and upper=nr_to_writeback. The @lower limit is advanced by the
+ * compressed bytes written back via shrink_memcg(). The window closes
+ * once @nr_to_writeback pages of compressed data have been written back.
*/
-static void zswap_try_to_writeback(unsigned long lower_pages,
- unsigned long upper_pages)
+static int zswap_try_to_writeback(struct mem_cgroup *memcg,
+ unsigned long lower_pages,
+ unsigned long upper_pages, bool proactive)
{
- int failures = 0, attempts = 0;
- struct mem_cgroup *iter_memcg;
+ int ret = 0, failures = 0, attempts = 0;
+ struct mem_cgroup *iter_memcg = NULL;
+ u64 bytes_written = 0;
while (lower_pages < upper_pages) {
unsigned long batch_size;
@@ -1447,14 +1475,17 @@ static void zswap_try_to_writeback(unsigned long lower_pages,
cond_resched();
- iter_memcg = zswap_iter_global();
+ iter_memcg = proactive ? zswap_iter_local(memcg, iter_memcg)
+ : zswap_iter_global();
if (!iter_memcg) {
/*
* Continue shrinking without incrementing failures if
* we found candidate memcgs in the last tree walk.
*/
- if (!attempts && ++failures == MAX_RECLAIM_RETRIES)
+ if (!attempts && ++failures == MAX_RECLAIM_RETRIES) {
+ ret = -EAGAIN;
break;
+ }
attempts = 0;
continue;
@@ -1465,8 +1496,17 @@ static void zswap_try_to_writeback(unsigned long lower_pages,
/* drop the extra reference */
mem_cgroup_put(iter_memcg);
- /* zswap total pages might have changed, refresh it. */
- upper_pages = zswap_total_pages();
+ /*
+ * Advance the window endpoint owned by this caller:
+ * - !proactive: zswap total pages might have changed, refresh.
+ * - proactive: accumulate bytes freed and fold to pages.
+ */
+ if (!proactive) {
+ upper_pages = zswap_total_pages();
+ } else if (shrunk > 0) {
+ bytes_written += shrunk;
+ lower_pages = DIV_ROUND_UP(bytes_written, PAGE_SIZE);
+ }
/*
* There are no writeback-candidate pages in the memcg.
@@ -1478,9 +1518,15 @@ static void zswap_try_to_writeback(unsigned long lower_pages,
continue;
++attempts;
- if (shrunk <= 0 && ++failures == MAX_RECLAIM_RETRIES)
+ if (shrunk <= 0 && ++failures == MAX_RECLAIM_RETRIES) {
+ ret = -EAGAIN;
break;
+ }
}
+
+ if (proactive)
+ mem_cgroup_iter_break(memcg, iter_memcg);
+ return ret;
}
static void shrink_worker(struct work_struct *w)
@@ -1490,7 +1536,7 @@ static void shrink_worker(struct work_struct *w)
/* Reclaim down to the accept threshold */
thr = zswap_accept_thr_pages();
- zswap_try_to_writeback(thr, zswap_total_pages());
+ zswap_try_to_writeback(NULL, thr, zswap_total_pages(), false);
}
/*********************************
@@ -1736,6 +1782,19 @@ int zswap_load(struct folio *folio)
return 0;
}
+int zswap_proactive_writeback(struct mem_cgroup *memcg,
+ unsigned long nr_to_writeback)
+{
+ if (!memcg)
+ return -EINVAL;
+ if (!mem_cgroup_zswap_writeback_enabled(memcg))
+ return -EINVAL;
+ if (!nr_to_writeback)
+ return 0;
+
+ return zswap_try_to_writeback(memcg, 0, nr_to_writeback, true);
+}
+
void zswap_invalidate(swp_entry_t swp)
{
pgoff_t offset = swp_offset(swp);
--
2.34.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v4 4/5] mm/zswap: Add per-memcg stat for proactive writeback
2026-06-18 4:48 [PATCH v4 0/5] mm/zswap: Implement per-cgroup proactive writeback Hao Jia
` (2 preceding siblings ...)
2026-06-18 4:48 ` [PATCH v4 3/5] mm/zswap: Implement proactive writeback Hao Jia
@ 2026-06-18 4:48 ` Hao Jia
2026-06-18 4:48 ` [PATCH v4 5/5] selftests/cgroup: Add tests for zswap " Hao Jia
4 siblings, 0 replies; 6+ messages in thread
From: Hao Jia @ 2026-06-18 4:48 UTC (permalink / raw)
To: akpm, tj, hannes, shakeel.butt, mhocko, yosry, mkoutny, nphamcs,
chengming.zhou, muchun.song, roman.gushchin
Cc: linux-mm, linux-kernel, linux-doc, Hao Jia
From: Hao Jia <jiahao1@lixiang.com>
Add a new stat zswpwb_proactive_b to memory.stat. This counter is
incremented by entry->length during proactive writebacks triggered
via the zswap_writeback_only key in memory.reclaim. It tracks the
compressed size (in bytes) of pages proactively written back from
zswap to swap, allowing users to better monitor and tune the
proactive writeback mechanism.
Signed-off-by: Hao Jia <jiahao1@lixiang.com>
---
Documentation/admin-guide/cgroup-v2.rst | 4 ++++
include/linux/memcontrol.h | 1 +
mm/memcontrol.c | 3 +++
mm/zswap.c | 23 ++++++++++++++++++-----
4 files changed, 26 insertions(+), 5 deletions(-)
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index e52d97e8e9c6..c164bb415002 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1748,6 +1748,10 @@ The following nested keys are defined.
zswpwb
Number of pages written from zswap to swap.
+ zswpwb_proactive_b
+ Bytes of compressed data proactively written back from
+ zswap to swap via memory.reclaim zswap_writeback_only key.
+
zswap_incomp
Number of incompressible pages currently stored in zswap
without compression. These pages could not be compressed to
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e1f46a0016fc..56580b264dc4 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -40,6 +40,7 @@ enum memcg_stat_item {
MEMCG_ZSWAP_B,
MEMCG_ZSWAPPED,
MEMCG_ZSWAP_INCOMP,
+ MEMCG_ZSWPWB_PROACTIVE_B,
MEMCG_NR_STAT,
};
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 56cd4af08232..5ffb5095f0ee 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -433,6 +433,7 @@ static const unsigned int memcg_stat_items[] = {
MEMCG_ZSWAP_B,
MEMCG_ZSWAPPED,
MEMCG_ZSWAP_INCOMP,
+ MEMCG_ZSWPWB_PROACTIVE_B,
};
#define NR_MEMCG_NODE_STAT_ITEMS ARRAY_SIZE(memcg_node_stat_items)
@@ -1558,6 +1559,7 @@ static const struct memory_stat memory_stats[] = {
{ "zswap", MEMCG_ZSWAP_B },
{ "zswapped", MEMCG_ZSWAPPED },
{ "zswap_incomp", MEMCG_ZSWAP_INCOMP },
+ { "zswpwb_proactive_b", MEMCG_ZSWPWB_PROACTIVE_B },
#endif
{ "file_mapped", NR_FILE_MAPPED },
{ "file_dirty", NR_FILE_DIRTY },
@@ -1614,6 +1616,7 @@ static int memcg_page_state_unit(int item)
switch (item) {
case MEMCG_PERCPU_B:
case MEMCG_ZSWAP_B:
+ case MEMCG_ZSWPWB_PROACTIVE_B:
case NR_SLAB_RECLAIMABLE_B:
case NR_SLAB_UNRECLAIMABLE_B:
return 1;
diff --git a/mm/zswap.c b/mm/zswap.c
index 28200552dde3..d78bacf80209 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -163,6 +163,7 @@ struct zswap_pool {
struct zswap_shrink_walk_arg {
unsigned long bytes_written;
bool encountered_page_in_swapcache;
+ bool proactive;
};
/* Global LRU lists shared by all zswap pools. */
@@ -990,7 +991,8 @@ static bool zswap_decompress(struct zswap_entry *entry, struct folio *folio)
* freed.
*/
static int zswap_writeback_entry(struct zswap_entry *entry,
- swp_entry_t swpentry)
+ swp_entry_t swpentry,
+ bool proactive)
{
struct xarray *tree;
pgoff_t offset = swp_offset(swpentry);
@@ -1045,6 +1047,15 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
if (entry->objcg)
count_objcg_events(entry->objcg, ZSWPWB, 1);
+ if (proactive && entry->objcg) {
+ struct mem_cgroup *memcg;
+
+ rcu_read_lock();
+ memcg = obj_cgroup_memcg(entry->objcg);
+ mod_memcg_state(memcg, MEMCG_ZSWPWB_PROACTIVE_B, entry->length);
+ rcu_read_unlock();
+ }
+
zswap_entry_free(entry);
/* folio is up to date */
@@ -1155,7 +1166,7 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
*/
spin_unlock(&l->lock);
- writeback_result = zswap_writeback_entry(entry, swpentry);
+ writeback_result = zswap_writeback_entry(entry, swpentry, walk_arg->proactive);
if (writeback_result) {
zswap_reject_reclaim_fail++;
@@ -1184,6 +1195,7 @@ static unsigned long zswap_shrinker_scan(struct shrinker *shrinker,
struct zswap_shrink_walk_arg walk_arg = {
.bytes_written = 0,
.encountered_page_in_swapcache = false,
+ .proactive = false,
};
unsigned long shrink_ret;
@@ -1305,11 +1317,12 @@ static struct shrinker *zswap_alloc_shrinker(void)
* writeback disabled, is a zombie cgroup, or has empty zswap LRUs.
*/
static long shrink_memcg(struct mem_cgroup *memcg,
- unsigned long nr_to_writeback)
+ unsigned long nr_to_writeback, bool proactive)
{
struct zswap_shrink_walk_arg walk_arg = {
.bytes_written = 0,
.encountered_page_in_swapcache = false,
+ .proactive = proactive,
};
u64 bytes_to_writeback = nr_to_writeback << PAGE_SHIFT;
bool memcg_list_is_empty = true;
@@ -1492,7 +1505,7 @@ static int zswap_try_to_writeback(struct mem_cgroup *memcg,
}
batch_size = min(upper_pages - lower_pages, NR_ZSWAP_WB_BATCH);
- shrunk = shrink_memcg(iter_memcg, batch_size);
+ shrunk = shrink_memcg(iter_memcg, batch_size, proactive);
/* drop the extra reference */
mem_cgroup_put(iter_memcg);
@@ -1642,7 +1655,7 @@ bool zswap_store(struct folio *folio)
objcg = get_obj_cgroup_from_folio(folio);
if (objcg && !obj_cgroup_may_zswap(objcg)) {
memcg = get_mem_cgroup_from_objcg(objcg);
- if (shrink_memcg(memcg, 1) <= 0) {
+ if (shrink_memcg(memcg, 1, false) <= 0) {
mem_cgroup_put(memcg);
goto put_objcg;
}
--
2.34.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH v4 5/5] selftests/cgroup: Add tests for zswap proactive writeback
2026-06-18 4:48 [PATCH v4 0/5] mm/zswap: Implement per-cgroup proactive writeback Hao Jia
` (3 preceding siblings ...)
2026-06-18 4:48 ` [PATCH v4 4/5] mm/zswap: Add per-memcg stat for " Hao Jia
@ 2026-06-18 4:48 ` Hao Jia
4 siblings, 0 replies; 6+ messages in thread
From: Hao Jia @ 2026-06-18 4:48 UTC (permalink / raw)
To: akpm, tj, hannes, shakeel.butt, mhocko, yosry, mkoutny, nphamcs,
chengming.zhou, muchun.song, roman.gushchin
Cc: linux-mm, linux-kernel, linux-doc, Hao Jia
From: Hao Jia <jiahao1@lixiang.com>
Add test_zswap_proactive_writeback() to cover the new memory.reclaim
"zswap_writeback_only" key. The test populates a memory cgroup zswap
pool, triggers proactive writeback, and verifies the behavior by
observing the change in zswpwb_proactive_b. Invalid input combinations
are also covered.
Extend test_zswap_writeback_one() to assert that the existing
non-proactive writeback path leaves zswpwb_proactive_b at zero.
Signed-off-by: Hao Jia <jiahao1@lixiang.com>
---
tools/testing/selftests/cgroup/test_zswap.c | 153 +++++++++++++++++++-
1 file changed, 152 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c
index 49b36ee79160..9c153fdd3a08 100644
--- a/tools/testing/selftests/cgroup/test_zswap.c
+++ b/tools/testing/selftests/cgroup/test_zswap.c
@@ -60,7 +60,12 @@ static int get_zswap_stored_pages(size_t *value)
static long get_cg_wb_count(const char *cg)
{
- return cg_read_key_long(cg, "memory.stat", "zswpwb");
+ return cg_read_key_long(cg, "memory.stat", "zswpwb ");
+}
+
+static long get_cg_pwb_bytes(const char *cg)
+{
+ return cg_read_key_long(cg, "memory.stat", "zswpwb_proactive_b ");
}
static long get_zswpout(const char *cgroup)
@@ -355,6 +360,7 @@ static int attempt_writeback(const char *cgroup, void *arg)
static int test_zswap_writeback_one(const char *cgroup, bool wb)
{
long zswpwb_before, zswpwb_after;
+ long pwb_bytes;
zswpwb_before = get_cg_wb_count(cgroup);
if (zswpwb_before != 0) {
@@ -362,6 +368,12 @@ static int test_zswap_writeback_one(const char *cgroup, bool wb)
return -1;
}
+ pwb_bytes = get_cg_pwb_bytes(cgroup);
+ if (pwb_bytes != 0) {
+ ksft_print_msg("zswpwb_proactive_b_before = %ld instead of 0\n", pwb_bytes);
+ return -1;
+ }
+
if (cg_run(cgroup, attempt_writeback, (void *) &wb))
return -1;
@@ -379,6 +391,17 @@ static int test_zswap_writeback_one(const char *cgroup, bool wb)
return -1;
}
+ /*
+ * attempt_writeback() does not use the proactive writeback path, so
+ * zswpwb_proactive_b must stay at zero regardless of whether
+ * writeback was enabled.
+ */
+ pwb_bytes = get_cg_pwb_bytes(cgroup);
+ if (pwb_bytes != 0) {
+ ksft_print_msg("zswpwb_proactive_b_after is %ld, expected 0\n", pwb_bytes);
+ return -1;
+ }
+
return 0;
}
@@ -770,6 +793,133 @@ static int test_zswap_incompressible(const char *root)
return ret;
}
+/*
+ * Trigger proactive zswap writeback with the following steps:
+ * 1. Allocate memory.
+ * 2. Push allocated memory into zswap.
+ * 3. Proactively write back zswap pages to swap
+ * using "zswap_writeback_only".
+ */
+static int proactive_writeback_workload(const char *cgroup, void *arg)
+{
+ long pagesize = sysconf(_SC_PAGESIZE);
+ size_t memsize = pagesize * 1024;
+ char reclaim_cmd[64];
+ char buf[pagesize];
+ long zswap_usage;
+ int ret = -1;
+ int rc;
+ char *mem;
+
+ mem = (char *)malloc(memsize);
+ if (!mem)
+ return ret;
+
+ for (int i = 0; i < pagesize; i++)
+ buf[i] = i < pagesize / 2 ? (char)i : 0;
+ for (int i = 0; i < memsize; i += pagesize)
+ memcpy(&mem[i], buf, pagesize);
+
+ /* Evict allocated memory into zswap. */
+ if (cg_write_numeric(cgroup, "memory.reclaim", memsize)) {
+ ksft_print_msg("Failed to push pages into zswap\n");
+ goto out;
+ }
+
+ zswap_usage = cg_read_long(cgroup, "memory.zswap.current");
+ if (zswap_usage <= 0) {
+ ksft_print_msg("no zswap pool to write back\n");
+ goto out;
+ }
+
+ /* Trigger proactive zswap writeback. */
+ snprintf(reclaim_cmd, sizeof(reclaim_cmd), "%zu zswap_writeback_only", zswap_usage);
+ rc = cg_write(cgroup, "memory.reclaim", reclaim_cmd);
+ if (rc && rc != -EAGAIN) {
+ ksft_print_msg("proactive zswap writeback failed: %d\n", rc);
+ goto out;
+ }
+
+ ret = 0;
+out:
+ free(mem);
+ return ret;
+}
+
+static int check_writeback_invalid_inputs(const char *cgroup)
+{
+ static char * const bad_inputs[] = {
+ "zswap_writeback_only",
+ "1M zswap_writeback_only swappiness=60",
+ "1M swappiness=60 zswap_writeback_only",
+ "1M zswap_writeback_only swappiness=max",
+ "1M swappiness=max zswap_writeback_only",
+ };
+ int i, rc;
+
+ for (i = 0; i < ARRAY_SIZE(bad_inputs); i++) {
+ rc = cg_write(cgroup, "memory.reclaim", bad_inputs[i]);
+ if (rc != -EINVAL) {
+ ksft_print_msg("memory.reclaim '%s': returned %d, expected %d\n",
+ bad_inputs[i], rc, -EINVAL);
+ return -1;
+ }
+ }
+ return 0;
+}
+
+static int test_zswap_proactive_writeback(const char *root)
+{
+ long wb_before, wb_after;
+ long pwb_b_before, pwb_b_after;
+ long wb_delta, pwb_b_delta;
+ int ret = KSFT_FAIL;
+ char *test_group;
+
+ if (cg_read_strcmp(root, "memory.zswap.writeback", "1"))
+ return KSFT_SKIP;
+
+ test_group = cg_name(root, "zswap_proactive_test");
+ if (!test_group)
+ return KSFT_FAIL;
+ if (cg_create(test_group))
+ goto out;
+ if (check_writeback_invalid_inputs(test_group))
+ goto out;
+
+ pwb_b_before = get_cg_pwb_bytes(test_group);
+ wb_before = get_cg_wb_count(test_group);
+ if (pwb_b_before < 0 || wb_before < 0)
+ goto out;
+
+ if (cg_run(test_group, proactive_writeback_workload, NULL))
+ goto out;
+
+ pwb_b_after = get_cg_pwb_bytes(test_group);
+ wb_after = get_cg_wb_count(test_group);
+ if (pwb_b_after < 0 || wb_after < 0)
+ goto out;
+
+ pwb_b_delta = pwb_b_after - pwb_b_before;
+ wb_delta = wb_after - wb_before;
+
+ if (pwb_b_delta <= 0) {
+ ksft_print_msg("zswpwb_proactive_b did not increase: delta=%ld\n",
+ pwb_b_delta);
+ goto out;
+ }
+ if (wb_delta <= 0) {
+ ksft_print_msg("zswpwb did not increase: delta=%ld\n", wb_delta);
+ goto out;
+ }
+
+ ret = KSFT_PASS;
+out:
+ cg_destroy(test_group);
+ free(test_group);
+ return ret;
+}
+
#define T(x) { x, #x }
struct zswap_test {
int (*fn)(const char *root);
@@ -783,6 +933,7 @@ struct zswap_test {
T(test_no_kmem_bypass),
T(test_no_invasive_cgroup_shrink),
T(test_zswap_incompressible),
+ T(test_zswap_proactive_writeback),
};
#undef T
--
2.34.1
^ permalink raw reply related [flat|nested] 6+ messages in thread