From: Raghavendra K T <raghavendra.kt@amd.com>
To: <raghavendra.kt@amd.com>
Cc: <AneeshKumar.KizhakeVeetil@arm.com>, <Michael.Day@amd.com>,
<akpm@linux-foundation.org>, <bharata@amd.com>,
<dave.hansen@intel.com>, <david@redhat.com>,
<dongjoo.linux.dev@gmail.com>, <feng.tang@intel.com>,
<gourry@gourry.net>, <hannes@cmpxchg.org>, <honggyu.kim@sk.com>,
<hughd@google.com>, <jhubbard@nvidia.com>, <jon.grimm@amd.com>,
<k.shutemov@gmail.com>, <kbusch@meta.com>,
<kmanaouil.dev@gmail.com>, <leesuyeon0506@gmail.com>,
<leillc@google.com>, <liam.howlett@oracle.com>,
<linux-kernel@vger.kernel.org>, <linux-mm@kvack.org>,
<mgorman@techsingularity.net>, <mingo@redhat.com>,
<nadav.amit@gmail.com>, <nphamcs@gmail.com>,
<peterz@infradead.org>, <riel@surriel.com>, <rientjes@google.com>,
<rppt@kernel.org>, <santosh.shukla@amd.com>, <shivankg@amd.com>,
<shy828301@gmail.com>, <sj@kernel.org>, <vbabka@suse.cz>,
<weixugc@google.com>, <willy@infradead.org>,
<ying.huang@linux.alibaba.com>, <ziy@nvidia.com>,
<Jonathan.Cameron@huawei.com>, <dave@stgolabs.net>,
<yuanchu@google.com>, <kinseyho@google.com>, <hdanton@sina.com>,
<harry.yoo@oracle.com>
Subject: [RFC PATCH V3 02/17] mm: Maintain mm_struct list in the system
Date: Thu, 14 Aug 2025 15:32:52 +0000 [thread overview]
Message-ID: <20250814153307.1553061-3-raghavendra.kt@amd.com> (raw)
In-Reply-To: <20250814153307.1553061-1-raghavendra.kt@amd.com>
The list is used to iterate over all the mm and do PTE A bit scanning.
mm_slot infrastructure is reused to aid insert and lookup of mm_struct.
CC: linux-fsdevel@vger.kernel.org
Suggested-by: Bharata B Rao <bharata@amd.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@amd.com>
---
include/linux/kscand.h | 30 +++++++++++++++
kernel/fork.c | 2 +
mm/internal.h | 1 +
mm/kscand.c | 86 ++++++++++++++++++++++++++++++++++++++++++
mm/mmap.c | 2 +
mm/vma_exec.c | 3 ++
6 files changed, 124 insertions(+)
create mode 100644 include/linux/kscand.h
diff --git a/include/linux/kscand.h b/include/linux/kscand.h
new file mode 100644
index 000000000000..ef9947a33ee5
--- /dev/null
+++ b/include/linux/kscand.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_KSCAND_H_
+#define _LINUX_KSCAND_H_
+
+#ifdef CONFIG_KSCAND
+extern void __kscand_enter(struct mm_struct *mm);
+extern void __kscand_exit(struct mm_struct *mm);
+
+static inline void kscand_execve(struct mm_struct *mm)
+{
+ __kscand_enter(mm);
+}
+
+static inline void kscand_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+ __kscand_enter(mm);
+}
+
+static inline void kscand_exit(struct mm_struct *mm)
+{
+ __kscand_exit(mm);
+}
+#else /* !CONFIG_KSCAND */
+static inline void __kscand_enter(struct mm_struct *mm) {}
+static inline void __kscand_exit(struct mm_struct *mm) {}
+static inline void kscand_execve(struct mm_struct *mm) {}
+static inline void kscand_fork(struct mm_struct *mm, struct mm_struct *oldmm) {}
+static inline void kscand_exit(struct mm_struct *mm) {}
+#endif
+#endif /* _LINUX_KSCAND_H_ */
diff --git a/kernel/fork.c b/kernel/fork.c
index 1ee8eb11f38b..a13043de91b0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -85,6 +85,7 @@
#include <linux/user-return-notifier.h>
#include <linux/oom.h>
#include <linux/khugepaged.h>
+#include <linux/kscand.h>
#include <linux/signalfd.h>
#include <linux/uprobes.h>
#include <linux/aio.h>
@@ -1116,6 +1117,7 @@ static inline void __mmput(struct mm_struct *mm)
uprobe_clear_state(mm);
exit_aio(mm);
+ kscand_exit(mm);
ksm_exit(mm);
khugepaged_exit(mm); /* must run before exit_mmap */
exit_mmap(mm);
diff --git a/mm/internal.h b/mm/internal.h
index 6b8ed2017743..dd86efc54885 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -8,6 +8,7 @@
#define __MM_INTERNAL_H
#include <linux/fs.h>
+#include <linux/kscand.h>
#include <linux/khugepaged.h>
#include <linux/mm.h>
#include <linux/mm_inline.h>
diff --git a/mm/kscand.c b/mm/kscand.c
index f7bbbc70c86a..d5b0d3041b0f 100644
--- a/mm/kscand.c
+++ b/mm/kscand.c
@@ -7,12 +7,14 @@
#include <linux/swap.h>
#include <linux/mm_inline.h>
#include <linux/kthread.h>
+#include <linux/kscand.h>
#include <linux/string.h>
#include <linux/delay.h>
#include <linux/cleanup.h>
#include <asm/pgalloc.h>
#include "internal.h"
+#include "mm_slot.h"
static struct task_struct *kscand_thread __read_mostly;
static DEFINE_MUTEX(kscand_mutex);
@@ -29,11 +31,23 @@ static bool need_wakeup;
static unsigned long kscand_sleep_expire;
+static DEFINE_SPINLOCK(kscand_mm_lock);
static DECLARE_WAIT_QUEUE_HEAD(kscand_wait);
+#define KSCAND_SLOT_HASH_BITS 10
+static DEFINE_READ_MOSTLY_HASHTABLE(kscand_slots_hash, KSCAND_SLOT_HASH_BITS);
+
+static struct kmem_cache *kscand_slot_cache __read_mostly;
+
+/* Per mm information collected to control VMA scanning */
+struct kscand_mm_slot {
+ struct mm_slot slot;
+};
+
/* Data structure to keep track of current mm under scan */
struct kscand_scan {
struct list_head mm_head;
+ struct kscand_mm_slot *mm_slot;
};
struct kscand_scan kscand_scan = {
@@ -69,6 +83,12 @@ static void kscand_wait_work(void)
wait_event_timeout(kscand_wait, kscand_should_wakeup(),
scan_sleep_jiffies);
}
+
+static inline int kscand_test_exit(struct mm_struct *mm)
+{
+ return atomic_read(&mm->mm_users) == 0;
+}
+
static void kscand_do_scan(void)
{
unsigned long iter = 0, mms_to_scan;
@@ -109,6 +129,65 @@ static int kscand(void *none)
return 0;
}
+static inline void kscand_destroy(void)
+{
+ kmem_cache_destroy(kscand_slot_cache);
+}
+
+void __kscand_enter(struct mm_struct *mm)
+{
+ struct kscand_mm_slot *kscand_slot;
+ struct mm_slot *slot;
+ int wakeup;
+
+ /* __kscand_exit() must not run from under us */
+ VM_BUG_ON_MM(kscand_test_exit(mm), mm);
+
+ kscand_slot = mm_slot_alloc(kscand_slot_cache);
+
+ if (!kscand_slot)
+ return;
+
+ slot = &kscand_slot->slot;
+
+ spin_lock(&kscand_mm_lock);
+ mm_slot_insert(kscand_slots_hash, mm, slot);
+
+ wakeup = list_empty(&kscand_scan.mm_head);
+ list_add_tail(&slot->mm_node, &kscand_scan.mm_head);
+ spin_unlock(&kscand_mm_lock);
+
+ mmgrab(mm);
+ if (wakeup)
+ wake_up_interruptible(&kscand_wait);
+}
+
+void __kscand_exit(struct mm_struct *mm)
+{
+ struct kscand_mm_slot *mm_slot;
+ struct mm_slot *slot;
+ int free = 0;
+
+ spin_lock(&kscand_mm_lock);
+ slot = mm_slot_lookup(kscand_slots_hash, mm);
+ mm_slot = mm_slot_entry(slot, struct kscand_mm_slot, slot);
+ if (mm_slot && kscand_scan.mm_slot != mm_slot) {
+ hash_del(&slot->hash);
+ list_del(&slot->mm_node);
+ free = 1;
+ }
+
+ spin_unlock(&kscand_mm_lock);
+
+ if (free) {
+ mm_slot_free(kscand_slot_cache, mm_slot);
+ mmdrop(mm);
+ } else if (mm_slot) {
+ mmap_write_lock(mm);
+ mmap_write_unlock(mm);
+ }
+}
+
static int start_kscand(void)
{
struct task_struct *kthread;
@@ -149,6 +228,12 @@ static int __init kscand_init(void)
{
int err;
+ kscand_slot_cache = KMEM_CACHE(kscand_mm_slot, 0);
+
+ if (!kscand_slot_cache) {
+ pr_err("kscand: kmem_cache error");
+ return -ENOMEM;
+ }
err = start_kscand();
if (err)
goto err_kscand;
@@ -157,6 +242,7 @@ static int __init kscand_init(void)
err_kscand:
stop_kscand();
+ kscand_destroy();
return err;
}
diff --git a/mm/mmap.c b/mm/mmap.c
index 09c563c95112..c9ffe65866de 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -37,6 +37,7 @@
#include <linux/perf_event.h>
#include <linux/audit.h>
#include <linux/khugepaged.h>
+#include <linux/kscand.h>
#include <linux/uprobes.h>
#include <linux/notifier.h>
#include <linux/memory.h>
@@ -1849,6 +1850,7 @@ __latent_entropy int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
if (!retval) {
mt_set_in_rcu(vmi.mas.tree);
ksm_fork(mm, oldmm);
+ kscand_fork(mm, oldmm);
khugepaged_fork(mm, oldmm);
} else {
diff --git a/mm/vma_exec.c b/mm/vma_exec.c
index 2dffb02ed6a2..8576b377f7ad 100644
--- a/mm/vma_exec.c
+++ b/mm/vma_exec.c
@@ -128,6 +128,8 @@ int create_init_stack_vma(struct mm_struct *mm, struct vm_area_struct **vmap,
if (err)
goto err_ksm;
+ kscand_execve(mm);
+
/*
* Place the stack at the largest stack address the architecture
* supports. Later, we'll move this to an appropriate place. We don't
@@ -151,6 +153,7 @@ int create_init_stack_vma(struct mm_struct *mm, struct vm_area_struct **vmap,
return 0;
err:
+ kscand_exit(mm);
ksm_exit(mm);
err_ksm:
mmap_write_unlock(mm);
--
2.34.1
next prev parent reply other threads:[~2025-08-14 15:34 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-14 15:32 [RFC PATCH V3 00/17] mm: slowtier page promotion based on PTE A bit Raghavendra K T
2025-08-14 15:32 ` [RFC PATCH V3 01/17] mm: Add kscand kthread for PTE A bit scan Raghavendra K T
2025-08-14 15:32 ` Raghavendra K T [this message]
2025-08-14 15:32 ` [RFC PATCH V3 03/17] mm: Scan the mm and create a migration list Raghavendra K T
2025-08-14 15:32 ` [RFC PATCH V3 04/17] mm/kscand: Add only hot pages to " Raghavendra K T
2025-08-14 15:32 ` [RFC PATCH V3 05/17] mm: Create a separate kthread for migration Raghavendra K T
2025-08-14 15:32 ` [RFC PATCH V3 06/17] mm/migration: migrate accessed folios to toptier node Raghavendra K T
2025-08-14 15:32 ` [RFC PATCH V3 07/17] mm: Add throttling of mm scanning using scan_period Raghavendra K T
2025-08-14 15:32 ` [RFC PATCH V3 08/17] mm: Add throttling of mm scanning using scan_size Raghavendra K T
2025-08-14 15:32 ` [RFC PATCH V3 09/17] mm: Add initial scan delay Raghavendra K T
2025-08-14 15:33 ` [RFC PATCH V3 10/17] mm: Add a heuristic to calculate target node Raghavendra K T
2025-08-14 15:33 ` [RFC PATCH V3 11/17] mm/kscand: Implement migration failure feedback Raghavendra K T
2025-08-14 15:33 ` [RFC PATCH V3 12/17] sysfs: Add sysfs support to tune scanning Raghavendra K T
2025-08-14 15:33 ` [RFC PATCH V3 13/17] mm/vmstat: Add vmstat counters Raghavendra K T
2025-08-14 15:33 ` [RFC PATCH V3 14/17] trace/kscand: Add tracing of scanning and migration Raghavendra K T
2025-08-14 15:33 ` [RFC PATCH V3 15/17] prctl: Introduce new prctl to control scanning Raghavendra K T
2025-08-14 15:33 ` [RFC PATCH V3 16/17] prctl: Fine tune scan_period with prctl scale param Raghavendra K T
2025-08-14 15:33 ` [RFC PATCH V3 17/17] mm: Create a list of fallback target nodes Raghavendra K T
2025-08-21 15:24 ` [RFC PATCH V3 00/17] mm: slowtier page promotion based on PTE A bit Raghavendra K T
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=20250814153307.1553061-3-raghavendra.kt@amd.com \
--to=raghavendra.kt@amd.com \
--cc=AneeshKumar.KizhakeVeetil@arm.com \
--cc=Jonathan.Cameron@huawei.com \
--cc=Michael.Day@amd.com \
--cc=akpm@linux-foundation.org \
--cc=bharata@amd.com \
--cc=dave.hansen@intel.com \
--cc=dave@stgolabs.net \
--cc=david@redhat.com \
--cc=dongjoo.linux.dev@gmail.com \
--cc=feng.tang@intel.com \
--cc=gourry@gourry.net \
--cc=hannes@cmpxchg.org \
--cc=harry.yoo@oracle.com \
--cc=hdanton@sina.com \
--cc=honggyu.kim@sk.com \
--cc=hughd@google.com \
--cc=jhubbard@nvidia.com \
--cc=jon.grimm@amd.com \
--cc=k.shutemov@gmail.com \
--cc=kbusch@meta.com \
--cc=kinseyho@google.com \
--cc=kmanaouil.dev@gmail.com \
--cc=leesuyeon0506@gmail.com \
--cc=leillc@google.com \
--cc=liam.howlett@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@techsingularity.net \
--cc=mingo@redhat.com \
--cc=nadav.amit@gmail.com \
--cc=nphamcs@gmail.com \
--cc=peterz@infradead.org \
--cc=riel@surriel.com \
--cc=rientjes@google.com \
--cc=rppt@kernel.org \
--cc=santosh.shukla@amd.com \
--cc=shivankg@amd.com \
--cc=shy828301@gmail.com \
--cc=sj@kernel.org \
--cc=vbabka@suse.cz \
--cc=weixugc@google.com \
--cc=willy@infradead.org \
--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;
as well as URLs for NNTP newsgroup(s).