From: Bharata B Rao <bharata@amd.com>
To: <linux-kernel@vger.kernel.org>, <linux-mm@kvack.org>
Cc: <Jonathan.Cameron@huawei.com>, <dave.hansen@intel.com>,
<gourry@gourry.net>, <hannes@cmpxchg.org>,
<mgorman@techsingularity.net>, <mingo@redhat.com>,
<peterz@infradead.org>, <raghavendra.kt@amd.com>,
<riel@surriel.com>, <rientjes@google.com>, <sj@kernel.org>,
<weixugc@google.com>, <willy@infradead.org>,
<ying.huang@linux.alibaba.com>, <ziy@nvidia.com>,
<dave@stgolabs.net>, <nifan.cxl@gmail.com>,
<xuezhengchu@huawei.com>, <yiannis@zptcorp.com>,
<akpm@linux-foundation.org>, <david@redhat.com>,
<byungchul@sk.com>, <kinseyho@google.com>,
<joshua.hahnjy@gmail.com>, <yuanchu@google.com>,
<balbirs@nvidia.com>, Bharata B Rao <bharata@amd.com>
Subject: [RFC PATCH v1 7/7] mm: klruscand: use mglru scanning for page promotion
Date: Thu, 14 Aug 2025 19:18:26 +0530 [thread overview]
Message-ID: <20250814134826.154003-8-bharata@amd.com> (raw)
In-Reply-To: <20250814134826.154003-1-bharata@amd.com>
From: Kinsey Ho <kinseyho@google.com>
Introduce a new kernel daemon, klruscand, that periodically invokes the
MGLRU page table walk. It leverages the new callbacks to gather access
information and forwards it to the pghot hot page tracking sub-system
for promotion decisions.
This benefits from reusing the existing MGLRU page table walk
infrastructure, which is optimized with features such as hierarchical
scanning and bloom filters to reduce CPU overhead.
As an additional optimization to be added in the future, we can tune
the scan intervals for each memcg.
Signed-off-by: Kinsey Ho <kinseyho@google.com>
Signed-off-by: Yuanchu Xie <yuanchu@google.com>
Signed-off-by: Bharata B Rao <bharata@amd.com>
[Reduced the scan interval to 100ms, pfn_t to unsigned long]
---
mm/Kconfig | 8 ++++
mm/Makefile | 1 +
mm/klruscand.c | 118 +++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 127 insertions(+)
create mode 100644 mm/klruscand.c
diff --git a/mm/Kconfig b/mm/Kconfig
index 8b236eb874cf..6d53c1208729 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1393,6 +1393,14 @@ config PGHOT
by various sources. Asynchronous promotion is done by per-node
kernel threads.
+config KLRUSCAND
+ bool "Kernel lower tier access scan daemon"
+ default y
+ depends on PGHOT && LRU_GEN_WALKS_MMU
+ help
+ Scan for accesses from lower tiers by invoking MGLRU to perform
+ page table walks.
+
source "mm/damon/Kconfig"
endmenu
diff --git a/mm/Makefile b/mm/Makefile
index 8799bd0c68ed..1d39ef55f3e5 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -148,3 +148,4 @@ obj-$(CONFIG_EXECMEM) += execmem.o
obj-$(CONFIG_TMPFS_QUOTA) += shmem_quota.o
obj-$(CONFIG_PT_RECLAIM) += pt_reclaim.o
obj-$(CONFIG_PGHOT) += kpromoted.o
+obj-$(CONFIG_KLRUSCAND) += klruscand.o
diff --git a/mm/klruscand.c b/mm/klruscand.c
new file mode 100644
index 000000000000..1a51aab29bd9
--- /dev/null
+++ b/mm/klruscand.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/memcontrol.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/random.h>
+#include <linux/migrate.h>
+#include <linux/mm_inline.h>
+#include <linux/slab.h>
+#include <linux/sched/clock.h>
+#include <linux/memory-tiers.h>
+#include <linux/sched/mm.h>
+#include <linux/sched.h>
+#include <linux/pghot.h>
+
+#include "internal.h"
+
+#define KLRUSCAND_INTERVAL_MS 100
+#define BATCH_SIZE (2 << 16)
+
+static struct task_struct *scan_thread;
+static unsigned long pfn_batch[BATCH_SIZE];
+static int batch_index;
+
+static void flush_cb(void)
+{
+ int i = 0;
+
+ for (; i < batch_index; i++) {
+ u64 pfn = pfn_batch[i];
+
+ pghot_record_access((unsigned long)pfn, NUMA_NO_NODE,
+ PGHOT_PGTABLE_SCAN, jiffies);
+
+ if (i % 16 == 0)
+ cond_resched();
+ }
+ batch_index = 0;
+}
+
+static int accessed_cb(unsigned long pfn)
+{
+ if (batch_index >= BATCH_SIZE)
+ return -EAGAIN;
+
+ pfn_batch[batch_index++] = pfn;
+ return 0;
+}
+
+static int klruscand_run(void *unused)
+{
+ struct lru_gen_mm_walk *walk;
+
+ walk = kzalloc(sizeof(*walk),
+ __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN);
+ if (!walk)
+ return -ENOMEM;
+
+ while (!kthread_should_stop()) {
+ unsigned long next_wake_time;
+ long sleep_time;
+ struct mem_cgroup *memcg;
+ int flags;
+ int nid;
+
+ next_wake_time = jiffies + msecs_to_jiffies(KLRUSCAND_INTERVAL_MS);
+
+ for_each_node_state(nid, N_MEMORY) {
+ pg_data_t *pgdat = NODE_DATA(nid);
+ struct reclaim_state rs = { 0 };
+
+ if (node_is_toptier(nid))
+ continue;
+
+ rs.mm_walk = walk;
+ set_task_reclaim_state(current, &rs);
+ flags = memalloc_noreclaim_save();
+
+ memcg = mem_cgroup_iter(NULL, NULL, NULL);
+ do {
+ struct lruvec *lruvec =
+ mem_cgroup_lruvec(memcg, pgdat);
+ unsigned long max_seq =
+ READ_ONCE((lruvec)->lrugen.max_seq);
+
+ lru_gen_scan_lruvec(lruvec, max_seq,
+ accessed_cb, flush_cb);
+ cond_resched();
+ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
+
+ memalloc_noreclaim_restore(flags);
+ set_task_reclaim_state(current, NULL);
+ memset(walk, 0, sizeof(*walk));
+ }
+
+ sleep_time = next_wake_time - jiffies;
+ if (sleep_time > 0 && sleep_time != MAX_SCHEDULE_TIMEOUT)
+ schedule_timeout_idle(sleep_time);
+ }
+ kfree(walk);
+ return 0;
+}
+
+static int __init klruscand_init(void)
+{
+ struct task_struct *task;
+
+ task = kthread_run(klruscand_run, NULL, "klruscand");
+
+ if (IS_ERR(task)) {
+ pr_err("Failed to create klruscand kthread\n");
+ return PTR_ERR(task);
+ }
+
+ scan_thread = task;
+ return 0;
+}
+module_init(klruscand_init);
--
2.34.1
next prev parent reply other threads:[~2025-08-14 13:52 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-14 13:48 [RFC PATCH v1 0/7] A subsystem for hot page detection and promotion Bharata B Rao
2025-08-14 13:48 ` [RFC PATCH v1 1/7] mm: migrate: Allow misplaced migration without VMA too Bharata B Rao
2025-08-15 1:29 ` Huang, Ying
2025-08-14 13:48 ` [RFC PATCH v1 2/7] migrate: implement migrate_misplaced_folios_batch Bharata B Rao
2025-08-15 1:39 ` Huang, Ying
2025-08-14 13:48 ` [RFC PATCH v1 3/7] mm: Hot page tracking and promotion Bharata B Rao
2025-08-15 1:56 ` Huang, Ying
2025-08-15 14:16 ` Bharata B Rao
[not found] ` <CGME20250821111729epcas5p4b57cdfb4a339e8ac7fc1ea803d6baa34@epcas5p4.samsung.com>
2025-08-21 11:17 ` Alok Rathore
2025-08-21 15:10 ` Bharata B Rao
2025-08-14 13:48 ` [RFC PATCH v1 4/7] x86: ibs: In-kernel IBS driver for memory access profiling Bharata B Rao
2025-08-14 13:48 ` [RFC PATCH v1 5/7] x86: ibs: Enable IBS profiling for memory accesses Bharata B Rao
2025-08-14 13:48 ` [RFC PATCH v1 6/7] mm: mglru: generalize page table walk Bharata B Rao
2025-08-14 13:48 ` Bharata B Rao [this message]
2025-08-15 11:59 ` [RFC PATCH v1 0/7] A subsystem for hot page detection and promotion Balbir Singh
2025-08-15 15:35 ` Bharata B Rao
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=20250814134826.154003-8-bharata@amd.com \
--to=bharata@amd.com \
--cc=Jonathan.Cameron@huawei.com \
--cc=akpm@linux-foundation.org \
--cc=balbirs@nvidia.com \
--cc=byungchul@sk.com \
--cc=dave.hansen@intel.com \
--cc=dave@stgolabs.net \
--cc=david@redhat.com \
--cc=gourry@gourry.net \
--cc=hannes@cmpxchg.org \
--cc=joshua.hahnjy@gmail.com \
--cc=kinseyho@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@techsingularity.net \
--cc=mingo@redhat.com \
--cc=nifan.cxl@gmail.com \
--cc=peterz@infradead.org \
--cc=raghavendra.kt@amd.com \
--cc=riel@surriel.com \
--cc=rientjes@google.com \
--cc=sj@kernel.org \
--cc=weixugc@google.com \
--cc=willy@infradead.org \
--cc=xuezhengchu@huawei.com \
--cc=yiannis@zptcorp.com \
--cc=ying.huang@linux.alibaba.com \
--cc=yuanchu@google.com \
--cc=ziy@nvidia.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