From: Usama Arif <usama.arif@linux.dev>
To: Andrew Morton <akpm@linux-foundation.org>,
david@kernel.org, ljs@kernel.org, liam@infradead.org,
vbabka@kernel.org, rppt@kernel.org, surenb@google.com,
mhocko@suse.com, kasong@tencent.com, qi.zheng@linux.dev,
shakeel.butt@linux.dev, axelrasmussen@google.com,
yuanchu@google.com, weixugc@google.com, chrisl@kernel.org,
nphamcs@gmail.com, baoquan.he@linux.dev, youngjun.park@lge.com,
hannes@cmpxchg.org, roman.gushchin@linux.dev,
muchun.song@linux.dev, linux-mm@kvack.org,
linux-kernel@vger.kernel.org, cgroups@vger.kernel.org,
rientjes@google.com, kernel-team@meta.com
Cc: Usama Arif <usama.arif@linux.dev>
Subject: [PATCH v2 1/2] mm/vmstat, mm/memcontrol: add _monotonic vmstat readers
Date: Mon, 13 Jul 2026 09:34:16 -0700 [thread overview]
Message-ID: <20260713163443.3562378-2-usama.arif@linux.dev> (raw)
In-Reply-To: <20260713163443.3562378-1-usama.arif@linux.dev>
lruvec_page_state(), node_page_state(), and global_node_page_state()
all clamp negative reads to zero on CONFIG_SMP so that a transient
per-CPU delta skew presents as zero pages rather than
as a garbage unsigned value. This is the right behaviour for
non-monotonic page-count readers.
It is however incorrect for callers that snapshot a monotonically-
incremented event counter and compute a delta from two samples.
Once the underlying signed long wraps past LONG_MAX, the clamped read
drops to zero while the previously-recorded snapshot still holds the
pre-wrap value; the unsigned subtraction then underflows into a
~2^31 spurious delta for 32-bit architecture and corrupts the
caller's accumulator.
Add non-clamping siblings that return the underlying state value
cast to unsigned long:
global_node_page_state_monotonic()
node_page_state_monotonic()
lruvec_page_state_monotonic()
With both samples read via the _monotonic variant, unsigned modular
subtraction stays correct across a signed-long wraparound as long
as the true growth between two samples fits in unsigned long
(< 2^32 on 32-bit, < 2^64 on 64-bit); the 32-bit bound is the
practically-reachable one that motivates this helper.
The variants are only safe for monotonically-incremented counters.
Non-monotonic page-count readers must keep using the existing
clamped helpers so transient negative reads still present as zero.
This is a prerequisite for the following patch which
replaces the producer-side anon_cost/file_cost accumulators with a
read-side accumulator in prepare_scan_control() that samples
monotonic per-LRU vmstat counters (PGROTATE_*, PGRECLAIM_PAGEOUT_*,
WORKINGSET_RESTORE_*) via lruvec_page_state_monotonic() and folds
the unsigned modular delta into a per-lruvec cost_accum[].
Signed-off-by: Usama Arif <usama.arif@linux.dev>
---
include/linux/memcontrol.h | 8 ++++++++
include/linux/vmstat.h | 16 ++++++++++++++++
mm/memcontrol.c | 36 ++++++++++++++++++++++++++++++++++++
mm/vmstat.c | 11 +++++++++++
4 files changed, 71 insertions(+)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e1f46a0016fc..b40bc4f6fe4a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -931,6 +931,8 @@ unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item);
bool memcg_stat_item_valid(int idx);
bool memcg_vm_event_item_valid(enum vm_event_item idx);
unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx);
+unsigned long lruvec_page_state_monotonic(struct lruvec *lruvec,
+ enum node_stat_item idx);
unsigned long lruvec_page_state_local(struct lruvec *lruvec,
enum node_stat_item idx);
@@ -1378,6 +1380,12 @@ static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
return node_page_state(lruvec_pgdat(lruvec), idx);
}
+static inline unsigned long lruvec_page_state_monotonic(struct lruvec *lruvec,
+ enum node_stat_item idx)
+{
+ return node_page_state_monotonic(lruvec_pgdat(lruvec), idx);
+}
+
static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
enum node_stat_item idx)
{
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 3c9c266cf782..fb8c76289e02 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -194,6 +194,19 @@ unsigned long global_node_page_state_pages(enum node_stat_item item)
return x;
}
+/*
+ * Non-clamping variant of global_node_page_state() intended for callers that
+ * snapshot a monotonically-incremented counter and subtract two samples.
+ * Returns the raw wrapping value so that unsigned modular subtraction stays
+ * correct across a signed-long overflow (a real hazard on 32-bit) that the
+ * clamp in global_node_page_state() would otherwise turn into a huge spurious
+ * delta. Do NOT use for non-monotonic page-count reads.
+ */
+static inline unsigned long global_node_page_state_monotonic(enum node_stat_item item)
+{
+ return (unsigned long)atomic_long_read(&vm_node_stat[item]);
+}
+
static inline unsigned long global_node_page_state(enum node_stat_item item)
{
VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
@@ -259,11 +272,14 @@ extern unsigned long node_page_state(struct pglist_data *pgdat,
enum node_stat_item item);
extern unsigned long node_page_state_pages(struct pglist_data *pgdat,
enum node_stat_item item);
+extern unsigned long node_page_state_monotonic(struct pglist_data *pgdat,
+ enum node_stat_item item);
extern void fold_vm_numa_events(void);
#else
#define sum_zone_node_page_state(node, item) global_zone_page_state(item)
#define node_page_state(node, item) global_node_page_state(item)
#define node_page_state_pages(node, item) global_node_page_state_pages(item)
+#define node_page_state_monotonic(node, item) global_node_page_state_monotonic(item)
static inline void fold_vm_numa_events(void)
{
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 56cd4af08232..b4a357c5f7e0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -502,6 +502,42 @@ unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx)
return x;
}
+/**
+ * lruvec_page_state_monotonic - non-clamping lruvec stat read for delta sampling
+ * @lruvec: the LRU vector to read from
+ * @idx: the node_stat_item to read
+ *
+ * Returns the raw state[idx] value cast to unsigned long, skipping the
+ * clamp-negative-to-zero step in lruvec_page_state(). Intended for callers
+ * that snapshot a monotonically-incremented counter and subtract two
+ * samples: unsigned modular arithmetic then yields the correct delta across
+ * a signed-long wraparound (a real hazard on 32-bit) that the clamp would
+ * otherwise turn into a huge spurious delta.
+ *
+ * Do NOT use for non-monotonic page-count reads where a transient negative
+ * reading from per-CPU delta skew must present as zero.
+ *
+ * XXX: This helper (and its node/global peers) exists because we place
+ * monotonically-incremented event counters (PGROTATE_*, PGRECLAIM_PAGEOUT_*)
+ * into enum node_stat_item.
+ */
+unsigned long lruvec_page_state_monotonic(struct lruvec *lruvec,
+ enum node_stat_item idx)
+{
+ struct mem_cgroup_per_node *pn;
+ int i;
+
+ if (mem_cgroup_disabled())
+ return node_page_state_monotonic(lruvec_pgdat(lruvec), idx);
+
+ i = memcg_stats_index(idx);
+ if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx))
+ return 0;
+
+ pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+ return (unsigned long)READ_ONCE(pn->lruvec_stats->state[i]);
+}
+
unsigned long lruvec_page_state_local(struct lruvec *lruvec,
enum node_stat_item idx)
{
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f534972f517d..c4364f0eb08a 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1024,6 +1024,17 @@ unsigned long node_page_state(struct pglist_data *pgdat,
return node_page_state_pages(pgdat, item);
}
+
+/*
+ * Non-clamping variant of node_page_state() intended for callers that
+ * snapshot a monotonically-incremented counter and subtract two samples.
+ * See global_node_page_state_monotonic() for the rationale.
+ */
+unsigned long node_page_state_monotonic(struct pglist_data *pgdat,
+ enum node_stat_item item)
+{
+ return (unsigned long)atomic_long_read(&pgdat->vm_stat[item]);
+}
#endif
/*
--
2.53.0-Meta
next prev parent reply other threads:[~2026-07-13 16:34 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-07-13 16:34 [PATCH v2 0/2] mm/vmscan: reduce lru_lock contention via vmstat-derived scan-balance cost Usama Arif
2026-07-13 16:34 ` Usama Arif [this message]
2026-07-13 16:34 ` [PATCH v2 2/2] " Usama Arif
2026-07-14 12:44 ` Usama Arif
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=20260713163443.3562378-2-usama.arif@linux.dev \
--to=usama.arif@linux.dev \
--cc=akpm@linux-foundation.org \
--cc=axelrasmussen@google.com \
--cc=baoquan.he@linux.dev \
--cc=cgroups@vger.kernel.org \
--cc=chrisl@kernel.org \
--cc=david@kernel.org \
--cc=hannes@cmpxchg.org \
--cc=kasong@tencent.com \
--cc=kernel-team@meta.com \
--cc=liam@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ljs@kernel.org \
--cc=mhocko@suse.com \
--cc=muchun.song@linux.dev \
--cc=nphamcs@gmail.com \
--cc=qi.zheng@linux.dev \
--cc=rientjes@google.com \
--cc=roman.gushchin@linux.dev \
--cc=rppt@kernel.org \
--cc=shakeel.butt@linux.dev \
--cc=surenb@google.com \
--cc=vbabka@kernel.org \
--cc=weixugc@google.com \
--cc=youngjun.park@lge.com \
--cc=yuanchu@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