mm: zswap: fix global shrinker error handling logic

This patch fixes the zswap global shrinker, which did not shrink the zpool
as expected.

The issue addressed is that shrink_worker() did not distinguish between
unexpected errors and expected errors, such as failed writeback from an
empty memcg.  The shrinker would stop shrinking after iterating through
the memcg tree 16 times, even if there was only one empty memcg.

With this patch, the shrinker no longer considers encountering an empty
memcg, encountering a memcg with writeback disabled, or reaching the end
of a memcg tree walk as a failure, as long as there are memcgs that are
candidates for writeback.  Systems with one or more empty memcgs will now
observe significantly higher zswap writeback activity after the zswap pool
limit is hit.

To avoid an infinite loop when there are no writeback candidates, this
patch tracks writeback attempts during memcg tree walks and limits reties
if no writeback candidates are found.

To handle the empty memcg case, the helper function shrink_memcg() is
modified to check if the memcg is empty and then return -ENOENT.

Link: https://lkml.kernel.org/r/20240731004918.33182-3-flintglass@gmail.com
Fixes: a65b0e7607cc ("zswap: make shrinking memcg-aware")
Signed-off-by: Takero Funaki <flintglass@gmail.com>
Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/zswap.c b/mm/zswap.c
index bd97f9824d8afc541766a77c21edeca0175d717b..71b75ff1f3fb7c770573a76831c9c7e9b21e1ffb 100644 (file)
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1287,10 +1287,10 @@ static struct shrinker *zswap_alloc_shrinker(void)
 
 static int shrink_memcg(struct mem_cgroup *memcg)
 {
-       int nid, shrunk = 0;
+       int nid, shrunk = 0, scanned = 0;
 
        if (!mem_cgroup_zswap_writeback_enabled(memcg))
-               return -EINVAL;
+               return -ENOENT;
 
        /*
         * Skip zombies because their LRUs are reparented and we would be
@@ -1304,21 +1304,34 @@ static int shrink_memcg(struct mem_cgroup *memcg)
 
                shrunk += list_lru_walk_one(&zswap_list_lru, nid, memcg,
                                            &shrink_memcg_cb, NULL, &nr_to_walk);
+               scanned += 1 - nr_to_walk;
        }
+
+       if (!scanned)
+               return -ENOENT;
+
        return shrunk ? 0 : -EAGAIN;
 }
 
 static void shrink_worker(struct work_struct *w)
 {
        struct mem_cgroup *memcg;
-       int ret, failures = 0;
+       int ret, failures = 0, attempts = 0;
        unsigned long thr;
 
        /* Reclaim down to the accept threshold */
        thr = zswap_accept_thr_pages();
 
        /*
-        * Global reclaim will select cgroup in a round-robin fashion.
+        * 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.
+        *
+        * 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
@@ -1354,9 +1367,14 @@ static void shrink_worker(struct work_struct *w)
                spin_unlock(&zswap_shrink_lock);
 
                if (!memcg) {
-                       if (++failures == MAX_RECLAIM_RETRIES)
+                       /*
+                        * Continue shrinking without incrementing failures if
+                        * we found candidate memcgs in the last tree walk.
+                        */
+                       if (!attempts && ++failures == MAX_RECLAIM_RETRIES)
                                break;
 
+                       attempts = 0;
                        goto resched;
                }
 
@@ -1364,8 +1382,16 @@ static void shrink_worker(struct work_struct *w)
                /* drop the extra reference */
                mem_cgroup_put(memcg);
 
-               if (ret == -EINVAL)
-                       break;
+               /*
+                * There are no writeback-candidate pages in the memcg.
+                * This is not an issue as long as we can find another memcg
+                * with pages in zswap. Skip this without incrementing attempts
+                * and failures.
+                */
+               if (ret == -ENOENT)
+                       continue;
+               ++attempts;
+
                if (ret && ++failures == MAX_RECLAIM_RETRIES)
                        break;
 resched: