mm/ksm: fix ksm_zero_pages accounting

commit c2dc78b86e0821ecf9a9d0c35dba2618279a5bb6 upstream.

We normally ksm_zero_pages++ in ksmd when page is merged with zero page,
but ksm_zero_pages-- is done from page tables side, where there is no any
accessing protection of ksm_zero_pages.

So we can read very exceptional value of ksm_zero_pages in rare cases,
such as -1, which is very confusing to users.

Fix it by changing to use atomic_long_t, and the same case with the
mm->ksm_zero_pages.

Link: https://lkml.kernel.org/r/20240528-b4-ksm-counters-v3-2-34bb358fdc13@linux.dev
Fixes: e2942062e01d ("ksm: count all zero pages placed by KSM")
Fixes: 6080d19f0704 ("ksm: add ksm zero pages for each process")
Signed-off-by: Chengming Zhou <chengming.zhou@linux.dev>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ran Xiaokai <ran.xiaokai@zte.com.cn>
Cc: Stefan Roesch <shr@devkernel.io>
Cc: xu xin <xu.xin16@zte.com.cn>
Cc: Yang Yang <yang.yang29@zte.com.cn>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

4 files changed, 21 insertions, 11 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index ffd54617c354..6e61d93ffa55 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3207,7 +3207,7 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
 	mm = get_task_mm(task);
 	if (mm) {
 		seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items);
-		seq_printf(m, "ksm_zero_pages %lu\n", mm->ksm_zero_pages);
+		seq_printf(m, "ksm_zero_pages %ld\n", mm_ksm_zero_pages(mm));
 		seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages);
 		seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm));
 		mmput(mm);
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index c2dd786a30e1..b9cdeba03668 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -33,16 +33,27 @@ void __ksm_exit(struct mm_struct *mm);
  */
 #define is_ksm_zero_pte(pte)	(is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte))
 
-extern unsigned long ksm_zero_pages;
+extern atomic_long_t ksm_zero_pages;
+
+static inline void ksm_map_zero_page(struct mm_struct *mm)
+{
+	atomic_long_inc(&ksm_zero_pages);
+	atomic_long_inc(&mm->ksm_zero_pages);
+}
 
 static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte)
 {
 	if (is_ksm_zero_pte(pte)) {
-		ksm_zero_pages--;
-		mm->ksm_zero_pages--;
+		atomic_long_dec(&ksm_zero_pages);
+		atomic_long_dec(&mm->ksm_zero_pages);
 	}
 }
 
+static inline long mm_ksm_zero_pages(struct mm_struct *mm)
+{
+	return atomic_long_read(&mm->ksm_zero_pages);
+}
+
 static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
 	int ret;
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 36c5b43999e6..ba25777ec0a7 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -899,7 +899,7 @@ struct mm_struct {
 		 * Represent how many empty pages are merged with kernel zero
 		 * pages when enabling KSM use_zero_pages.
 		 */
-		unsigned long ksm_zero_pages;
+		atomic_long_t ksm_zero_pages;
 #endif /* CONFIG_KSM */
 #ifdef CONFIG_LRU_GEN
 		struct {
diff --git a/mm/ksm.c b/mm/ksm.c
index 83831ab1ffd8..2e4cd681622d 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -282,7 +282,7 @@ static unsigned int zero_checksum __read_mostly;
 static bool ksm_use_zero_pages __read_mostly;
 
 /* The number of zero pages which is placed by KSM */
-unsigned long ksm_zero_pages;
+atomic_long_t ksm_zero_pages = ATOMIC_LONG_INIT(0);
 
 #ifdef CONFIG_NUMA
 /* Zeroed when merging across nodes is not allowed */
@@ -1242,8 +1242,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 		 * the dirty bit in zero page's PTE is set.
 		 */
 		newpte = pte_mkdirty(pte_mkspecial(pfn_pte(page_to_pfn(kpage), vma->vm_page_prot)));
-		ksm_zero_pages++;
-		mm->ksm_zero_pages++;
+		ksm_map_zero_page(mm);
 		/*
 		 * We're replacing an anonymous page with a zero page, which is
 		 * not anonymous. We need to do proper accounting otherwise we
@@ -3105,7 +3104,7 @@ static void wait_while_offlining(void)
 #ifdef CONFIG_PROC_FS
 long ksm_process_profit(struct mm_struct *mm)
 {
-	return (long)(mm->ksm_merging_pages + mm->ksm_zero_pages) * PAGE_SIZE -
+	return (long)(mm->ksm_merging_pages + mm_ksm_zero_pages(mm)) * PAGE_SIZE -
 		mm->ksm_rmap_items * sizeof(struct ksm_rmap_item);
 }
 #endif /* CONFIG_PROC_FS */
@@ -3384,7 +3383,7 @@ KSM_ATTR_RO(pages_volatile);
 static ssize_t ksm_zero_pages_show(struct kobject *kobj,
 				struct kobj_attribute *attr, char *buf)
 {
-	return sysfs_emit(buf, "%ld\n", ksm_zero_pages);
+	return sysfs_emit(buf, "%ld\n", atomic_long_read(&ksm_zero_pages));
 }
 KSM_ATTR_RO(ksm_zero_pages);
 
@@ -3393,7 +3392,7 @@ static ssize_t general_profit_show(struct kobject *kobj,
 {
 	long general_profit;
 
-	general_profit = (ksm_pages_sharing + ksm_zero_pages) * PAGE_SIZE -
+	general_profit = (ksm_pages_sharing + atomic_long_read(&ksm_zero_pages)) * PAGE_SIZE -
 				ksm_rmap_items * sizeof(struct ksm_rmap_item);
 
 	return sysfs_emit(buf, "%ld\n", general_profit);