[PATCH 1/1] mm/ksm: add ksm_pages_sharing for each process to calculate profit more accurately

[Longlong Xia <xialonglong@kylinos.cn>]

The general_profit_show() function only considers ksm_pages_sharing,
while ksm_process_profit() includes both ksm_pages_sharing and
ksm_pages_shared for each process. This leads to a mismatch between
the total profits from ksm_process_profit() and general_profit_show().

Based on my tests, the sum of ksm_process_profit() for all processes
can be up to 20% higher than general_profit_show(), depending on
the size of page_shared. For individual processes, the ratio of
ksm_pages_sharing to ksm_merging_pages is usually not equal to 1.

To resolve this, we suggest introducing ksm_pages_sharing for each
process to accurately calculate its pages_sharing, ensuring
ksm_process_profit() reflects shared memory benefits more accurately.

Add a new proc file named as ksm_pages_sharing both under /proc/<pid>/
and /proc/self/ksm_stat/ to indicate the saved pages of this process.
(not including ksm_zero_pages)

Suggested-by: Xu Xin <xu.xin16@zte.com.cn>
Signed-off-by: Longlong Xia <xialonglong@kylinos.cn>
---
 Documentation/admin-guide/mm/ksm.rst |  5 +++--
 Documentation/filesystems/proc.rst   |  8 ++++++++
 fs/proc/base.c                       | 18 ++++++++++++++++++
 include/linux/mm_types.h             |  5 +++++
 mm/ksm.c                             | 12 ++++++++----
 5 files changed, 42 insertions(+), 6 deletions(-)

diff --git a/Documentation/admin-guide/mm/ksm.rst b/Documentation/admin-guide/mm/ksm.rst
index ad8e7a41f3b5..0b33ef98930f 100644
--- a/Documentation/admin-guide/mm/ksm.rst
+++ b/Documentation/admin-guide/mm/ksm.rst
@@ -256,9 +256,10 @@ several times, which are unprofitable memory consumed.
 	process_profit =~ ksm_saved_pages * sizeof(page) -
 			  ksm_rmap_items * sizeof(rmap_item).
 
-   where ksm_saved_pages equals to the sum of ``ksm_merging_pages`` and
+   where ksm_saved_pages equals to the sum of ``ksm_pages_sharing`` and
    ``ksm_zero_pages``, both of which are shown under the directory
-   ``/proc/<pid>/ksm_stat``, and ksm_rmap_items is also shown in
+   ``/proc/<pid>/ksm_stat``, ksm_merging_pages and ksm_rmap_items are
+   also shown in
    ``/proc/<pid>/ksm_stat``. The process profit is also shown in
    ``/proc/<pid>/ksm_stat`` as ksm_process_profit.
 
diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index 2a17865dfe39..e14ea8389500 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -2290,6 +2290,7 @@ Example
     / # cat /proc/self/ksm_stat
     ksm_rmap_items 0
     ksm_zero_pages 0
+    ksm_pages_sharing 0
     ksm_merging_pages 0
     ksm_process_profit 0
     ksm_merge_any: no
@@ -2312,6 +2313,13 @@ ksm_zero_pages
 When /sys/kernel/mm/ksm/use_zero_pages is enabled, it represent how many
 empty pages are merged with kernel zero pages by KSM.
 
+ksm_pages_sharing
+^^^^^^^^^^^^^^^^^
+
+It represents how many pages saved of this process.
+(not including ksm_zero_pages). It is the same with what
+/proc/<pid>/ksm_pages_sharing shows.
+
 ksm_merging_pages
 ^^^^^^^^^^^^^^^^^
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index c667702dc69b..327bf82acf54 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3262,6 +3262,21 @@ static int proc_pid_ksm_merging_pages(struct seq_file *m, struct pid_namespace *
 
 	return 0;
 }
+
+static int proc_pid_ksm_pages_sharing(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *task)
+{
+	struct mm_struct *mm;
+
+	mm = get_task_mm(task);
+	if (mm) {
+		seq_printf(m, "%lu\n", mm->ksm_pages_sharing);
+		mmput(mm);
+	}
+
+	return 0;
+}
+
 static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *task)
 {
@@ -3272,6 +3287,7 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
 	if (mm) {
 		seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items);
 		seq_printf(m, "ksm_zero_pages %ld\n", mm_ksm_zero_pages(mm));
+		seq_printf(m, "ksm_pages_sharing %lu\n", mm->ksm_pages_sharing);
 		seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages);
 		seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm));
 		seq_printf(m, "ksm_merge_any: %s\n",
@@ -3421,6 +3437,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache),
 #endif
 #ifdef CONFIG_KSM
+	ONE("ksm_pages_sharing",  S_IRUSR, proc_pid_ksm_pages_sharing),
 	ONE("ksm_merging_pages",  S_IRUSR, proc_pid_ksm_merging_pages),
 	ONE("ksm_stat",  S_IRUSR, proc_pid_ksm_stat),
 #endif
@@ -3758,6 +3775,7 @@ static const struct pid_entry tid_base_stuff[] = {
 	ONE("seccomp_cache", S_IRUSR, proc_pid_seccomp_cache),
 #endif
 #ifdef CONFIG_KSM
+	ONE("ksm_pages_sharing",  S_IRUSR, proc_pid_ksm_pages_sharing),
 	ONE("ksm_merging_pages",  S_IRUSR, proc_pid_ksm_merging_pages),
 	ONE("ksm_stat",  S_IRUSR, proc_pid_ksm_stat),
 #endif
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index d6b91e8a66d6..d260cb09c10a 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1176,6 +1176,11 @@ struct mm_struct {
 		 * merging (not including ksm_zero_pages).
 		 */
 		unsigned long ksm_merging_pages;
+		/*
+		 * Represents how many pages saved of this process.
+		 * (not including ksm_zero_pages).
+		 */
+		unsigned long ksm_pages_sharing;
 		/*
 		 * Represent how many pages are checked for ksm merging
 		 * including merged and not merged.
diff --git a/mm/ksm.c b/mm/ksm.c
index 8583fb91ef13..c2d85ea07b1c 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -824,6 +824,7 @@ static void remove_node_from_stable_tree(struct ksm_stable_node *stable_node)
 	hlist_for_each_entry(rmap_item, &stable_node->hlist, hlist) {
 		if (rmap_item->hlist.next) {
 			ksm_pages_sharing--;
+			rmap_item->mm->ksm_pages_sharing--;
 			trace_ksm_remove_rmap_item(stable_node->kpfn, rmap_item, rmap_item->mm);
 		} else {
 			ksm_pages_shared--;
@@ -976,8 +977,10 @@ static void remove_rmap_item_from_tree(struct ksm_rmap_item *rmap_item)
 		folio_unlock(folio);
 		folio_put(folio);
 
-		if (!hlist_empty(&stable_node->hlist))
+		if (!hlist_empty(&stable_node->hlist)) {
 			ksm_pages_sharing--;
+			rmap_item->mm->ksm_pages_sharing--;
+		}
 		else
 			ksm_pages_shared--;
 
@@ -2202,9 +2205,10 @@ static void stable_tree_append(struct ksm_rmap_item *rmap_item,
 	rmap_item->address |= STABLE_FLAG;
 	hlist_add_head(&rmap_item->hlist, &stable_node->hlist);
 
-	if (rmap_item->hlist.next)
+	if (rmap_item->hlist.next) {
 		ksm_pages_sharing++;
-	else
+		rmap_item->mm->ksm_pages_sharing++;
+	} else
 		ksm_pages_shared++;
 
 	rmap_item->mm->ksm_merging_pages++;
@@ -3290,7 +3294,7 @@ bool ksm_process_mergeable(struct mm_struct *mm)
 
 long ksm_process_profit(struct mm_struct *mm)
 {
-	return (long)(mm->ksm_merging_pages + mm_ksm_zero_pages(mm)) * PAGE_SIZE -
+	return (long)(mm->ksm_pages_sharing + mm_ksm_zero_pages(mm)) * PAGE_SIZE -
 		mm->ksm_rmap_items * sizeof(struct ksm_rmap_item);
 }
 #endif /* CONFIG_PROC_FS */
-- 
2.43.0