memcg: add the pagefault count into memcg stats

Two new stats in per-memcg memory.stat which tracks the number of page
faults and number of major page faults.

  "pgfault"
  "pgmajfault"

They are different from "pgpgin"/"pgpgout" stat which count number of
pages charged/discharged to the cgroup and have no meaning of reading/
writing page to disk.

It is valuable to track the two stats for both measuring application's
performance as well as the efficiency of the kernel page reclaim path.
Counting pagefaults per process is useful, but we also need the aggregated
value since processes are monitored and controlled in cgroup basis in
memcg.

Functional test: check the total number of pgfault/pgmajfault of all
memcgs and compare with global vmstat value:

  $ cat /proc/vmstat | grep fault
  pgfault 1070751
  pgmajfault 553

  $ cat /dev/cgroup/memory.stat | grep fault
  pgfault 1071138
  pgmajfault 553
  total_pgfault 1071142
  total_pgmajfault 553

  $ cat /dev/cgroup/A/memory.stat | grep fault
  pgfault 199
  pgmajfault 0
  total_pgfault 199
  total_pgmajfault 0

Performance test: run page fault test(pft) wit 16 thread on faulting in
15G anon pages in 16G container.  There is no regression noticed on the
"flt/cpu/s"

Sample output from pft:

  TAG pft:anon-sys-default:
    Gb  Thr CLine   User     System     Wall    flt/cpu/s fault/wsec
    15   16   1     0.67s   233.41s    14.76s   16798.546 266356.260

  +-------------------------------------------------------------------------+
      N           Min           Max        Median           Avg        Stddev
  x  10     16682.962     17344.027     16913.524     16928.812      166.5362
  +  10     16695.568     16923.896     16820.604     16824.652     84.816568
  No difference proven at 95.0% confidence

[akpm@linux-foundation.org: fix build]
[hughd@google.com: shmem fix]
Signed-off-by: Ying Han <yinghan@google.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 56 insertions, 5 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 7455ccd..bcdc393 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1661,6 +1661,7 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		/* No page in the page cache at all */
 		do_sync_mmap_readahead(vma, ra, file, offset);
 		count_vm_event(PGMAJFAULT);
+		mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
 		ret = VM_FAULT_MAJOR;
 retry_find:
 		page = find_get_page(mapping, offset);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4021fcd..bd9052a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -94,6 +94,8 @@ enum mem_cgroup_events_index {
 	MEM_CGROUP_EVENTS_PGPGIN,	/* # of pages paged in */
 	MEM_CGROUP_EVENTS_PGPGOUT,	/* # of pages paged out */
 	MEM_CGROUP_EVENTS_COUNT,	/* # of pages paged in/out */
+	MEM_CGROUP_EVENTS_PGFAULT,	/* # of page-faults */
+	MEM_CGROUP_EVENTS_PGMAJFAULT,	/* # of major page-faults */
 	MEM_CGROUP_EVENTS_NSTATS,
 };
 /*
@@ -590,6 +592,16 @@ static void mem_cgroup_swap_statistics(struct mem_cgroup *mem,
 	this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_SWAPOUT], val);
 }
 
+void mem_cgroup_pgfault(struct mem_cgroup *mem, int val)
+{
+	this_cpu_add(mem->stat->events[MEM_CGROUP_EVENTS_PGFAULT], val);
+}
+
+void mem_cgroup_pgmajfault(struct mem_cgroup *mem, int val)
+{
+	this_cpu_add(mem->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT], val);
+}
+
 static unsigned long mem_cgroup_read_events(struct mem_cgroup *mem,
 					    enum mem_cgroup_events_index idx)
 {
@@ -827,6 +839,33 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *mem)
 	return (mem == root_mem_cgroup);
 }
 
+void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
+{
+	struct mem_cgroup *mem;
+
+	if (!mm)
+		return;
+
+	rcu_read_lock();
+	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	if (unlikely(!mem))
+		goto out;
+
+	switch (idx) {
+	case PGMAJFAULT:
+		mem_cgroup_pgmajfault(mem, 1);
+		break;
+	case PGFAULT:
+		mem_cgroup_pgfault(mem, 1);
+		break;
+	default:
+		BUG();
+	}
+out:
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(mem_cgroup_count_vm_event);
+
 /*
  * Following LRU functions are allowed to be used without PCG_LOCK.
  * Operations are called by routine of global LRU independently from memcg.
@@ -3958,6 +3997,8 @@ enum {
 	MCS_PGPGIN,
 	MCS_PGPGOUT,
 	MCS_SWAP,
+	MCS_PGFAULT,
+	MCS_PGMAJFAULT,
 	MCS_INACTIVE_ANON,
 	MCS_ACTIVE_ANON,
 	MCS_INACTIVE_FILE,
@@ -3980,6 +4021,8 @@ struct {
 	{"pgpgin", "total_pgpgin"},
 	{"pgpgout", "total_pgpgout"},
 	{"swap", "total_swap"},
+	{"pgfault", "total_pgfault"},
+	{"pgmajfault", "total_pgmajfault"},
 	{"inactive_anon", "total_inactive_anon"},
 	{"active_anon", "total_active_anon"},
 	{"inactive_file", "total_inactive_file"},
@@ -4008,6 +4051,10 @@ mem_cgroup_get_local_stat(struct mem_cgroup *mem, struct mcs_total_stat *s)
 		val = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_SWAPOUT);
 		s->stat[MCS_SWAP] += val * PAGE_SIZE;
 	}
+	val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGFAULT);
+	s->stat[MCS_PGFAULT] += val;
+	val = mem_cgroup_read_events(mem, MEM_CGROUP_EVENTS_PGMAJFAULT);
+	s->stat[MCS_PGMAJFAULT] += val;
 
 	/* per zone stat */
 	val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_ANON);
diff --git a/mm/memory.c b/mm/memory.c
index fc24f7d..6953d39 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2874,6 +2874,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		/* Had to read the page from swap area: Major fault */
 		ret = VM_FAULT_MAJOR;
 		count_vm_event(PGMAJFAULT);
+		mem_cgroup_count_vm_event(mm, PGMAJFAULT);
 	} else if (PageHWPoison(page)) {
 		/*
 		 * hwpoisoned dirty swapcache pages are kept for killing
@@ -3413,6 +3414,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	__set_current_state(TASK_RUNNING);
 
 	count_vm_event(PGFAULT);
+	mem_cgroup_count_vm_event(mm, PGFAULT);
 
 	/* do counter updates before entering really critical section. */
 	check_sync_rss_stat(current);
diff --git a/mm/shmem.c b/mm/shmem.c
index 69edb45..1acfb26 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1305,12 +1305,10 @@ repeat:
 		swappage = lookup_swap_cache(swap);
 		if (!swappage) {
 			shmem_swp_unmap(entry);
+			spin_unlock(&info->lock);
 			/* here we actually do the io */
-			if (type && !(*type & VM_FAULT_MAJOR)) {
-				__count_vm_event(PGMAJFAULT);
+			if (type)
 				*type |= VM_FAULT_MAJOR;
-			}
-			spin_unlock(&info->lock);
 			swappage = shmem_swapin(swap, gfp, info, idx);
 			if (!swappage) {
 				spin_lock(&info->lock);
@@ -1549,7 +1547,10 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
 	if (error)
 		return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
-
+	if (ret & VM_FAULT_MAJOR) {
+		count_vm_event(PGMAJFAULT);
+		mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+	}
 	return ret | VM_FAULT_LOCKED;
 }