From: Davidlohr Bueso <dave@stgolabs.net>
To: akpm@linux-foundation.org
Cc: mhocko@kernel.org, hannes@cmpxchg.org, roman.gushchin@linux.dev,
shakeel.butt@linux.dev, yosryahmed@google.com,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
dave@stgolabs.net
Subject: [PATCH 2/4] mm/memcg: make memory.reclaim interface generic
Date: Mon, 23 Jun 2025 11:58:49 -0700 [thread overview]
Message-ID: <20250623185851.830632-3-dave@stgolabs.net> (raw)
In-Reply-To: <20250623185851.830632-1-dave@stgolabs.net>
This adds a general call for both parsing as well as the
common reclaim semantics. memcg is still the only user and
no change in semantics.
Signed-off-by: Davidlohr Bueso <dave@stgolabs.net>
---
mm/internal.h | 2 +
mm/memcontrol.c | 77 ++------------------------------------
mm/vmscan.c | 98 +++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 104 insertions(+), 73 deletions(-)
diff --git a/mm/internal.h b/mm/internal.h
index 3823fb356d3b..fc4262262b31 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -517,6 +517,8 @@ extern unsigned long highest_memmap_pfn;
bool folio_isolate_lru(struct folio *folio);
void folio_putback_lru(struct folio *folio);
extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason);
+int user_proactive_reclaim(char *buf,
+ struct mem_cgroup *memcg, pg_data_t *pgdat);
/*
* in mm/rmap.c:
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 902da8a9c643..015e406eadfa 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -51,7 +51,6 @@
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
-#include <linux/parser.h>
#include <linux/vmpressure.h>
#include <linux/memremap.h>
#include <linux/mm_inline.h>
@@ -4566,83 +4565,15 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of,
return nbytes;
}
-enum {
- MEMORY_RECLAIM_SWAPPINESS = 0,
- MEMORY_RECLAIM_SWAPPINESS_MAX,
- MEMORY_RECLAIM_NULL,
-};
-
-static const match_table_t tokens = {
- { MEMORY_RECLAIM_SWAPPINESS, "swappiness=%d"},
- { MEMORY_RECLAIM_SWAPPINESS_MAX, "swappiness=max"},
- { MEMORY_RECLAIM_NULL, NULL },
-};
-
static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
- unsigned int nr_retries = MAX_RECLAIM_RETRIES;
- unsigned long nr_to_reclaim, nr_reclaimed = 0;
- int swappiness = -1;
- unsigned int reclaim_options;
- char *old_buf, *start;
- substring_t args[MAX_OPT_ARGS];
-
- buf = strstrip(buf);
-
- old_buf = buf;
- nr_to_reclaim = memparse(buf, &buf) / PAGE_SIZE;
- if (buf == old_buf)
- return -EINVAL;
-
- buf = strstrip(buf);
-
- while ((start = strsep(&buf, " ")) != NULL) {
- if (!strlen(start))
- continue;
- switch (match_token(start, tokens, args)) {
- case MEMORY_RECLAIM_SWAPPINESS:
- if (match_int(&args[0], &swappiness))
- return -EINVAL;
- if (swappiness < MIN_SWAPPINESS || swappiness > MAX_SWAPPINESS)
- return -EINVAL;
- break;
- case MEMORY_RECLAIM_SWAPPINESS_MAX:
- swappiness = SWAPPINESS_ANON_ONLY;
- break;
- default:
- return -EINVAL;
- }
- }
-
- reclaim_options = MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE;
- 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;
- unsigned long reclaimed;
-
- if (signal_pending(current))
- return -EINTR;
-
- /*
- * This is the final attempt, drain percpu lru caches in the
- * hope of introducing more evictable pages for
- * try_to_free_mem_cgroup_pages().
- */
- if (!nr_retries)
- lru_add_drain_all();
-
- reclaimed = try_to_free_mem_cgroup_pages(memcg,
- batch_size, GFP_KERNEL,
- reclaim_options,
- swappiness == -1 ? NULL : &swappiness);
-
- if (!reclaimed && !nr_retries--)
- return -EAGAIN;
+ int ret;
- nr_reclaimed += reclaimed;
- }
+ ret = user_proactive_reclaim(buf, memcg, NULL);
+ if (ret)
+ return ret;
return nbytes;
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c13c01eb0b42..63ddec550c3b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -57,6 +57,7 @@
#include <linux/rculist_nulls.h>
#include <linux/random.h>
#include <linux/mmu_notifier.h>
+#include <linux/parser.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
@@ -6714,6 +6715,15 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
return nr_reclaimed;
}
+#else
+unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
+ unsigned long nr_pages,
+ gfp_t gfp_mask,
+ unsigned int reclaim_options,
+ int *swappiness)
+{
+ return 0;
+}
#endif
static void kswapd_age_node(struct pglist_data *pgdat, struct scan_control *sc)
@@ -7708,6 +7718,94 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
return ret;
}
+
+enum {
+ MEMORY_RECLAIM_SWAPPINESS = 0,
+ MEMORY_RECLAIM_SWAPPINESS_MAX,
+ MEMORY_RECLAIM_NULL,
+};
+static const match_table_t tokens = {
+ { MEMORY_RECLAIM_SWAPPINESS, "swappiness=%d"},
+ { MEMORY_RECLAIM_SWAPPINESS_MAX, "swappiness=max"},
+ { MEMORY_RECLAIM_NULL, NULL },
+};
+
+int user_proactive_reclaim(char *buf, struct mem_cgroup *memcg, pg_data_t *pgdat)
+{
+ unsigned int nr_retries = MAX_RECLAIM_RETRIES;
+ unsigned long nr_to_reclaim, nr_reclaimed = 0;
+ int swappiness = -1;
+ char *old_buf, *start;
+ substring_t args[MAX_OPT_ARGS];
+
+ if (!buf || (!memcg && !pgdat))
+ return -EINVAL;
+
+ buf = strstrip(buf);
+
+ old_buf = buf;
+ nr_to_reclaim = memparse(buf, &buf) / PAGE_SIZE;
+ if (buf == old_buf)
+ return -EINVAL;
+
+ buf = strstrip(buf);
+
+ while ((start = strsep(&buf, " ")) != NULL) {
+ if (!strlen(start))
+ continue;
+ switch (match_token(start, tokens, args)) {
+ case MEMORY_RECLAIM_SWAPPINESS:
+ if (match_int(&args[0], &swappiness))
+ return -EINVAL;
+ if (swappiness < MIN_SWAPPINESS ||
+ swappiness > MAX_SWAPPINESS)
+ return -EINVAL;
+ break;
+ case MEMORY_RECLAIM_SWAPPINESS_MAX:
+ swappiness = SWAPPINESS_ANON_ONLY;
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+
+ 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;
+ unsigned long reclaimed;
+
+ if (signal_pending(current))
+ return -EINTR;
+
+ /*
+ * This is the final attempt, drain percpu lru caches in the
+ * hope of introducing more evictable pages.
+ */
+ if (!nr_retries)
+ lru_add_drain_all();
+
+ if (memcg) {
+ unsigned int reclaim_options;
+
+ reclaim_options = MEMCG_RECLAIM_MAY_SWAP |
+ MEMCG_RECLAIM_PROACTIVE;
+ reclaimed = try_to_free_mem_cgroup_pages(memcg,
+ batch_size, GFP_KERNEL,
+ reclaim_options,
+ swappiness == -1 ? NULL : &swappiness);
+ } else {
+ return -EINVAL;
+ }
+
+ if (!reclaimed && !nr_retries--)
+ return -EAGAIN;
+
+ nr_reclaimed += reclaimed;
+ }
+
+ return 0;
+}
+
#endif
/**
--
2.39.5
next prev parent reply other threads:[~2025-06-23 18:59 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-23 18:58 [PATCH -next v2 0/4] mm: per-node proactive reclaim Davidlohr Bueso
2025-06-23 18:58 ` [PATCH 1/4] mm/vmscan: respect psi_memstall region in node reclaim Davidlohr Bueso
2025-06-25 17:08 ` Shakeel Butt
2025-07-17 1:44 ` Roman Gushchin
2025-06-23 18:58 ` Davidlohr Bueso [this message]
2025-06-23 21:45 ` [PATCH 2/4] mm/memcg: make memory.reclaim interface generic Andrew Morton
2025-06-23 23:36 ` Davidlohr Bueso
2025-06-24 18:26 ` Klara Modin
2025-07-17 1:58 ` Roman Gushchin
2025-07-17 16:35 ` Davidlohr Bueso
2025-07-17 22:17 ` Shakeel Butt
2025-07-17 22:52 ` Andrew Morton
2025-07-17 23:56 ` Davidlohr Bueso
2025-07-18 0:17 ` Shakeel Butt
2025-06-23 18:58 ` [PATCH 3/4] mm/vmscan: make __node_reclaim() more generic Davidlohr Bueso
2025-07-17 2:03 ` Roman Gushchin
2025-07-17 22:25 ` Shakeel Butt
2025-06-23 18:58 ` [PATCH 4/4] mm: introduce per-node proactive reclaim interface Davidlohr Bueso
2025-06-25 23:10 ` Shakeel Butt
2025-06-27 19:07 ` SeongJae Park
2025-07-17 2:46 ` Roman Gushchin
2025-07-17 16:26 ` Davidlohr Bueso
2025-07-17 22:46 ` Andrew Morton
[not found] ` <20250717064925.2304-1-hdanton@sina.com>
2025-07-17 7:39 ` Michal Hocko
2025-07-17 22:28 ` Shakeel Butt
2025-06-23 21:50 ` [PATCH -next v2 0/4] mm: per-node proactive reclaim Andrew Morton
2025-07-16 0:24 ` Andrew Morton
2025-07-16 15:15 ` Shakeel Butt
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250623185851.830632-3-dave@stgolabs.net \
--to=dave@stgolabs.net \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
--cc=roman.gushchin@linux.dev \
--cc=shakeel.butt@linux.dev \
--cc=yosryahmed@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).