[RFC PATCH V3 02/17] mm: Maintain mm_struct list in the system

Raghavendra K T posted 17 patches 1 month, 3 weeks ago
There is a newer version of this series
[RFC PATCH V3 02/17] mm: Maintain mm_struct list in the system
Posted by Raghavendra K T 1 month, 3 weeks ago
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
Re: [RFC PATCH V3 02/17] mm: Maintain mm_struct list in the system
Posted by Jonathan Cameron 2 days, 2 hours ago
On Thu, 14 Aug 2025 15:32:52 +0000
Raghavendra K T <raghavendra.kt@amd.com> wrote:

> 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

This is part of the tags block.  Some tools moan if you have blank lines
in that.  Alternatively push it below the --- and it won't end up in
the git commit but tooling will still add the +CC.

> 
> Suggested-by: Bharata B Rao <bharata@amd.com>
> Signed-off-by: Raghavendra K T <raghavendra.kt@amd.com>

A few minor comments on formatting.

> diff --git a/mm/kscand.c b/mm/kscand.c
> index f7bbbc70c86a..d5b0d3041b0f 100644
> --- a/mm/kscand.c
> +++ b/mm/kscand.c

> +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);
> +
Similar to below. I'd keep call and error check more closely coupled
visually by dropping this blank line.

> +	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);

Looks familiar.

wakeup = kscand_has_work()

Or maybe just get rid of that helper and check it explicitly like this.


> +	list_add_tail(&slot->mm_node, &kscand_scan.mm_head);
> +	spin_unlock(&kscand_mm_lock);
> +
> +	mmgrab(mm);
> +	if (wakeup)
> +		wake_up_interruptible(&kscand_wait);
> +}

> +
>  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);
> +

I'd drop this blank line. Keep the call and the error check tightly coupled
in one block of code.

> +	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;
>  }