mm: count swap usage

A frequent questions from users about memory management is what numbers of
swap ents are user for processes.  And this information will give some
hints to oom-killer.

Besides we can count the number of swapents per a process by scanning
/proc/<pid>/smaps, this is very slow and not good for usual process
information handler which works like 'ps' or 'top'.  (ps or top is now
enough slow..)

This patch adds a counter of swapents to mm_counter and update is at each
swap events.  Information is exported via /proc/<pid>/status file as

[kamezawa@bluextal memory]$ cat /proc/self/status
Name:   cat
State:  R (running)
Tgid:   2910
Pid:    2910
PPid:   2823
TracerPid:      0
Uid:    500     500     500     500
Gid:    500     500     500     500
FDSize: 256
Groups: 500
VmPeak:    82696 kB
VmSize:    82696 kB
VmLck:         0 kB
VmHWM:       432 kB
VmRSS:       432 kB
VmData:      172 kB
VmStk:        84 kB
VmExe:        48 kB
VmLib:      1568 kB
VmPTE:        40 kB
VmSwap:        0 kB <=============== this.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 14 insertions, 4 deletions

diff --git a/mm/memory.c b/mm/memory.c
index a459761..77d9f84 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -679,7 +679,9 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 						 &src_mm->mmlist);
 				spin_unlock(&mmlist_lock);
 			}
-			if (is_write_migration_entry(entry) &&
+			if (likely(!non_swap_entry(entry)))
+				rss[MM_SWAPENTS]++;
+			else if (is_write_migration_entry(entry) &&
 					is_cow_mapping(vm_flags)) {
 				/*
 				 * COW mappings require pages in both parent
@@ -974,9 +976,14 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 		if (pte_file(ptent)) {
 			if (unlikely(!(vma->vm_flags & VM_NONLINEAR)))
 				print_bad_pte(vma, addr, ptent, NULL);
-		} else if
-		  (unlikely(!free_swap_and_cache(pte_to_swp_entry(ptent))))
-			print_bad_pte(vma, addr, ptent, NULL);
+		} else {
+			swp_entry_t entry = pte_to_swp_entry(ptent);
+
+			if (!non_swap_entry(entry))
+				rss[MM_SWAPENTS]--;
+			if (unlikely(!free_swap_and_cache(entry)))
+				print_bad_pte(vma, addr, ptent, NULL);
+		}
 		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
 	} while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0));
 
@@ -2692,6 +2699,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 
 	inc_mm_counter_fast(mm, MM_ANONPAGES);
+	dec_mm_counter_fast(mm, MM_SWAPENTS);
 	pte = mk_pte(page, vma->vm_page_prot);
 	if ((flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) {
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
diff --git a/mm/rmap.c b/mm/rmap.c
index 73d0472..5cb4711 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -840,6 +840,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 				spin_unlock(&mmlist_lock);
 			}
 			dec_mm_counter(mm, MM_ANONPAGES);
+			inc_mm_counter(mm, MM_SWAPENTS);
 		} else if (PAGE_MIGRATION) {
 			/*
 			 * Store the pfn of the page in a special migration
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 8939849..187a21f 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -840,6 +840,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		goto out;
 	}
 
+	dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
 	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
 	get_page(page);
 	set_pte_at(vma->vm_mm, addr, pte,