mm: per-cgroup memory reclaim stats

Track the following reclaim counters for every memory cgroup: PGREFILL,
PGSCAN, PGSTEAL, PGACTIVATE, PGDEACTIVATE, PGLAZYFREE and PGLAZYFREED.

These values are exposed using the memory.stats interface of cgroup v2.

The meaning of each value is the same as for global counters, available
using /proc/vmstat.

Also, for consistency, rename mem_cgroup_count_vm_event() to
count_memcg_event_mm().

Link: http://lkml.kernel.org/r/1494530183-30808-1-git-send-email-guro@fb.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Documentation/cgroup-v2.txt

@@ -956,6 +956,34 @@ PAGE_SIZE multiple when read back.
 
 		Number of times a shadow node has been reclaimed
 
+	  pgrefill
+
+		Amount of scanned pages (in an active LRU list)
+
+	  pgscan
+
+		Amount of scanned pages (in an inactive LRU list)
+
+	  pgsteal
+
+		Amount of reclaimed pages
+
+	  pgactivate
+
+		Amount of pages moved to the active LRU list
+
+	  pgdeactivate
+
+		Amount of pages moved to the inactive LRU lis
+
+	  pglazyfree
+
+		Amount of pages postponed to be freed under memory pressure
+
+	  pglazyfreed
+
+		Amount of reclaimed lazyfree pages
+
   memory.swap.current
 
 	A read-only single value file which exists on non-root

fs/dax.c

@@ -1213,7 +1213,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
 	case IOMAP_MAPPED:
 		if (iomap.flags & IOMAP_F_NEW) {
 			count_vm_event(PGMAJFAULT);
-			mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT);
+			count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
 			major = VM_FAULT_MAJOR;
 		}
 		error = dax_insert_mapping(mapping, iomap.bdev, iomap.dax_dev,

fs/ncpfs/mmap.c

@@ -89,7 +89,7 @@ static int ncp_file_mmap_fault(struct vm_fault *vmf)
 	 * -- nyc
 	 */
 	count_vm_event(PGMAJFAULT);
-	mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT);
+	count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
 	return VM_FAULT_MAJOR;
 }
 

include/linux/memcontrol.h

@@ -357,6 +357,17 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
 }
 struct mem_cgroup *mem_cgroup_from_id(unsigned short id);
 
+static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
+{
+	struct mem_cgroup_per_node *mz;
+
+	if (mem_cgroup_disabled())
+		return NULL;
+
+	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+	return mz->memcg;
+}
+
 /**
  * parent_mem_cgroup - find the accounting parent of a memcg
  * @memcg: memcg whose parent to find
@@ -546,8 +557,23 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
 
-static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
-					     enum vm_event_item idx)
+static inline void count_memcg_events(struct mem_cgroup *memcg,
+				      enum vm_event_item idx,
+				      unsigned long count)
+{
+	if (!mem_cgroup_disabled())
+		this_cpu_add(memcg->stat->events[idx], count);
+}
+
+static inline void count_memcg_page_event(struct page *page,
+					  enum memcg_stat_item idx)
+{
+	if (page->mem_cgroup)
+		count_memcg_events(page->mem_cgroup, idx, 1);
+}
+
+static inline void count_memcg_event_mm(struct mm_struct *mm,
+					enum vm_event_item idx)
 {
 	struct mem_cgroup *memcg;
 
@@ -675,6 +701,11 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
 	return NULL;
 }
 
+static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
+{
+	return NULL;
+}
+
 static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
 {
 	return true;
@@ -789,8 +820,19 @@ static inline void mem_cgroup_split_huge_fixup(struct page *head)
 {
 }
 
+static inline void count_memcg_events(struct mem_cgroup *memcg,
+				      enum vm_event_item idx,
+				      unsigned long count)
+{
+}
+
+static inline void count_memcg_page_event(struct page *page,
+					  enum memcg_stat_item idx)
+{
+}
+
 static inline
-void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
+void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 {
 }
 #endif /* CONFIG_MEMCG */

mm/filemap.c

@@ -2265,7 +2265,7 @@ int filemap_fault(struct vm_fault *vmf)
 		/* No page in the page cache at all */
 		do_sync_mmap_readahead(vmf->vma, ra, file, offset);
 		count_vm_event(PGMAJFAULT);
-		mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT);
+		count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
 		ret = VM_FAULT_MAJOR;
 retry_find:
 		page = find_get_page(mapping, offset);

mm/memcontrol.c

@@ -5230,6 +5230,16 @@ static int memory_stat_show(struct seq_file *m, void *v)
 	seq_printf(m, "pgfault %lu\n", events[PGFAULT]);
 	seq_printf(m, "pgmajfault %lu\n", events[PGMAJFAULT]);
 
+	seq_printf(m, "pgrefill %lu\n", events[PGREFILL]);
+	seq_printf(m, "pgscan %lu\n", events[PGSCAN_KSWAPD] +
+		   events[PGSCAN_DIRECT]);
+	seq_printf(m, "pgsteal %lu\n", events[PGSTEAL_KSWAPD] +
+		   events[PGSTEAL_DIRECT]);
+	seq_printf(m, "pgactivate %lu\n", events[PGACTIVATE]);
+	seq_printf(m, "pgdeactivate %lu\n", events[PGDEACTIVATE]);
+	seq_printf(m, "pglazyfree %lu\n", events[PGLAZYFREE]);
+	seq_printf(m, "pglazyfreed %lu\n", events[PGLAZYFREED]);
+
 	seq_printf(m, "workingset_refault %lu\n",
 		   stat[WORKINGSET_REFAULT]);
 	seq_printf(m, "workingset_activate %lu\n",

mm/memory.c

@@ -2719,7 +2719,7 @@ int do_swap_page(struct vm_fault *vmf)
 		/* Had to read the page from swap area: Major fault */
 		ret = VM_FAULT_MAJOR;
 		count_vm_event(PGMAJFAULT);
-		mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+		count_memcg_event_mm(vma->vm_mm, PGMAJFAULT);
 	} else if (PageHWPoison(page)) {
 		/*
 		 * hwpoisoned dirty swapcache pages are kept for killing
@@ -3837,7 +3837,7 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	__set_current_state(TASK_RUNNING);
 
 	count_vm_event(PGFAULT);
-	mem_cgroup_count_vm_event(vma->vm_mm, PGFAULT);
+	count_memcg_event_mm(vma->vm_mm, PGFAULT);
 
 	/* do counter updates before entering really critical section. */
 	check_sync_rss_stat(current);

mm/shmem.c

@@ -1646,8 +1646,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 			if (fault_type) {
 				*fault_type |= VM_FAULT_MAJOR;
 				count_vm_event(PGMAJFAULT);
-				mem_cgroup_count_vm_event(charge_mm,
-							  PGMAJFAULT);
+				count_memcg_event_mm(charge_mm, PGMAJFAULT);
 			}
 			/* Here we actually start the io */
 			page = shmem_swapin(swap, gfp, info, index);

mm/swap.c

@@ -591,6 +591,7 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec,
 		add_page_to_lru_list(page, lruvec, LRU_INACTIVE_FILE);
 
 		__count_vm_events(PGLAZYFREE, hpage_nr_pages(page));
+		count_memcg_page_event(page, PGLAZYFREE);
 		update_page_reclaim_stat(lruvec, 1, 0);
 	}
 }

mm/vmscan.c

@@ -1294,6 +1294,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			}
 
 			count_vm_event(PGLAZYFREED);
+			count_memcg_page_event(page, PGLAZYFREED);
 		} else if (!mapping || !__remove_mapping(mapping, page, true))
 			goto keep_locked;
 		/*
@@ -1323,6 +1324,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		if (!PageMlocked(page)) {
 			SetPageActive(page);
 			pgactivate++;
+			count_memcg_page_event(page, PGACTIVATE);
 		}
 keep_locked:
 		unlock_page(page);
@@ -1762,11 +1764,16 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
 	reclaim_stat->recent_scanned[file] += nr_taken;
 
-	if (global_reclaim(sc)) {
-		if (current_is_kswapd())
+	if (current_is_kswapd()) {
+		if (global_reclaim(sc))
 			__count_vm_events(PGSCAN_KSWAPD, nr_scanned);
-		else
+		count_memcg_events(lruvec_memcg(lruvec), PGSCAN_KSWAPD,
+				   nr_scanned);
+	} else {
+		if (global_reclaim(sc))
 			__count_vm_events(PGSCAN_DIRECT, nr_scanned);
+		count_memcg_events(lruvec_memcg(lruvec), PGSCAN_DIRECT,
+				   nr_scanned);
 	}
 	spin_unlock_irq(&pgdat->lru_lock);
 
@@ -1778,11 +1785,16 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 	spin_lock_irq(&pgdat->lru_lock);
 
-	if (global_reclaim(sc)) {
-		if (current_is_kswapd())
+	if (current_is_kswapd()) {
+		if (global_reclaim(sc))
 			__count_vm_events(PGSTEAL_KSWAPD, nr_reclaimed);
-		else
+		count_memcg_events(lruvec_memcg(lruvec), PGSTEAL_KSWAPD,
+				   nr_reclaimed);
+	} else {
+		if (global_reclaim(sc))
 			__count_vm_events(PGSTEAL_DIRECT, nr_reclaimed);
+		count_memcg_events(lruvec_memcg(lruvec), PGSTEAL_DIRECT,
+				   nr_reclaimed);
 	}
 
 	putback_inactive_pages(lruvec, &page_list);
@@ -1927,8 +1939,11 @@ static unsigned move_active_pages_to_lru(struct lruvec *lruvec,
 		}
 	}
 
-	if (!is_active_lru(lru))
+	if (!is_active_lru(lru)) {
 		__count_vm_events(PGDEACTIVATE, nr_moved);
+		count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE,
+				   nr_moved);
+	}
 
 	return nr_moved;
 }
@@ -1966,6 +1981,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	reclaim_stat->recent_scanned[file] += nr_taken;
 
 	__count_vm_events(PGREFILL, nr_scanned);
+	count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);
 
 	spin_unlock_irq(&pgdat->lru_lock);