ksm: add ksm zero pages for each process

As the number of ksm zero pages is not included in ksm_merging_pages per
process when enabling use_zero_pages, it's unclear of how many actual
pages are merged by KSM. To let users accurately estimate their memory
demands when unsharing KSM zero-pages, it's necessary to show KSM zero-
pages per process. In addition, it help users to know the actual KSM
profit because KSM-placed zero pages are also benefit from KSM.

since unsharing zero pages placed by KSM accurately is achieved, then
tracking empty pages merging and unmerging is not a difficult thing any
longer.

Since we already have /proc/<pid>/ksm_stat, just add the information of
'ksm_zero_pages' in it.

Link: https://lkml.kernel.org/r/20230613030938.185993-1-yang.yang29@zte.com.cn
Signed-off-by: xu xin <xu.xin16@zte.com.cn>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Xiaokai Ran <ran.xiaokai@zte.com.cn>
Reviewed-by: Yang Yang <yang.yang29@zte.com.cn>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: Xuexin Jiang <jiang.xuexin@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

6 files changed, 17 insertions, 8 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 05452c3b9872..eb2e498e3b8d 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3207,6 +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_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 e80aa49009b2..c2dd786a30e1 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -35,10 +35,12 @@ void __ksm_exit(struct mm_struct *mm);
 
 extern unsigned long ksm_zero_pages;
 
-static inline void ksm_might_unmap_zero_page(pte_t pte)
+static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte)
 {
-	if (is_ksm_zero_pte(pte))
+	if (is_ksm_zero_pte(pte)) {
 		ksm_zero_pages--;
+		mm->ksm_zero_pages--;
+	}
 }
 
 static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
@@ -109,7 +111,7 @@ static inline void ksm_exit(struct mm_struct *mm)
 {
 }
 
-static inline void ksm_might_unmap_zero_page(pte_t pte)
+static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte)
 {
 }
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 5e74ce4a28cd..51d04c1847c1 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -812,7 +812,7 @@ struct mm_struct {
 #ifdef CONFIG_KSM
 		/*
 		 * Represent how many pages of this process are involved in KSM
-		 * merging.
+		 * merging (not including ksm_zero_pages).
 		 */
 		unsigned long ksm_merging_pages;
 		/*
@@ -820,7 +820,12 @@ struct mm_struct {
 		 * including merged and not merged.
 		 */
 		unsigned long ksm_rmap_items;
-#endif
+		/*
+		 * Represent how many empty pages are merged with kernel zero
+		 * pages when enabling KSM use_zero_pages.
+		 */
+		unsigned long ksm_zero_pages;
+#endif /* CONFIG_KSM */
 #ifdef CONFIG_LRU_GEN
 		struct {
 			/* this mm_struct is on lru_gen_mm_list */
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 419981dcc889..4b8b8673d5d9 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -710,7 +710,7 @@ static void __collapse_huge_page_copy_succeeded(pte_t *pte,
 				spin_lock(ptl);
 				ptep_clear(vma->vm_mm, address, _pte);
 				spin_unlock(ptl);
-				ksm_might_unmap_zero_page(pteval);
+				ksm_might_unmap_zero_page(vma->vm_mm, pteval);
 			}
 		} else {
 			src_page = pte_page(pteval);
diff --git a/mm/ksm.c b/mm/ksm.c
index e037d9aad691..e1772081e8cb 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1233,6 +1233,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 		 */
 		newpte = pte_mkdirty(pte_mkspecial(pfn_pte(page_to_pfn(kpage), vma->vm_page_prot)));
 		ksm_zero_pages++;
+		mm->ksm_zero_pages++;
 		/*
 		 * We're replacing an anonymous page with a zero page, which is
 		 * not anonymous. We need to do proper accounting otherwise we
diff --git a/mm/memory.c b/mm/memory.c
index c256da05bb5e..5f863b1a0edc 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1434,7 +1434,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			zap_install_uffd_wp_if_needed(vma, addr, pte, details,
 						      ptent);
 			if (unlikely(!page)) {
-				ksm_might_unmap_zero_page(ptent);
+				ksm_might_unmap_zero_page(mm, ptent);
 				continue;
 			}
 
@@ -3130,7 +3130,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 				inc_mm_counter(mm, MM_ANONPAGES);
 			}
 		} else {
-			ksm_might_unmap_zero_page(vmf->orig_pte);
+			ksm_might_unmap_zero_page(mm, vmf->orig_pte);
 			inc_mm_counter(mm, MM_ANONPAGES);
 		}
 		flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));