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>

6 files changed, 23 insertions, 7 deletions

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index e418f3d8f427..b5c5fc657a88 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -164,6 +164,7 @@ read the file /proc/PID/status:
   VmExe:        68 kB
   VmLib:      1412 kB
   VmPTE:        20 kb
+  VmSwap:        0 kB
   Threads:        1
   SigQ:   0/28578
   SigPnd: 0000000000000000
@@ -219,6 +220,7 @@ Table 1-2: Contents of the statm files (as of 2.6.30-rc7)
  VmExe                       size of text segment
  VmLib                       size of shared library code
  VmPTE                       size of page table entries
+ VmSwap                      size of swap usage (the number of referred swapents)
  Threads                     number of threads
  SigQ                        number of signals queued/max. number for queue
  SigPnd                      bitmap of pending signals for the thread
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 375581276011..183f8ff5f400 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -16,7 +16,7 @@
 
 void task_mem(struct seq_file *m, struct mm_struct *mm)
 {
-        unsigned long data, text, lib;
+        unsigned long data, text, lib, swap;
         unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
 
         /*
@@ -36,6 +36,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
         data = mm->total_vm - mm->shared_vm - mm->stack_vm;
         text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
         lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
+        swap = get_mm_counter(mm, MM_SWAPENTS);
         seq_printf(m,
                 "VmPeak:\t%8lu kB\n"
                 "VmSize:\t%8lu kB\n"
@@ -46,7 +47,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
                 "VmStk:\t%8lu kB\n"
                 "VmExe:\t%8lu kB\n"
                 "VmLib:\t%8lu kB\n"
-                "VmPTE:\t%8lu kB\n",
+                "VmPTE:\t%8lu kB\n"
+                "VmSwap:\t%8lu kB\n",
                 hiwater_vm << (PAGE_SHIFT-10),
                 (total_vm - mm->reserved_vm) << (PAGE_SHIFT-10),
                 mm->locked_vm << (PAGE_SHIFT-10),
@@ -54,7 +56,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
                 total_rss << (PAGE_SHIFT-10),
                 data << (PAGE_SHIFT-10),
                 mm->stack_vm << (PAGE_SHIFT-10), text, lib,
-                (PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10);
+                (PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10,
+                swap << (PAGE_SHIFT-10));
 }
 
 unsigned long task_vsize(struct mm_struct *mm)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 21861239ab0c..19549d7275ab 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -198,6 +198,7 @@ struct core_state {
 enum {
         MM_FILEPAGES,
         MM_ANONPAGES,
+        MM_SWAPENTS,
         NR_MM_COUNTERS
 };
 
diff --git a/mm/memory.c b/mm/memory.c
index a4597614f18d..77d9f840936b 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 73d0472884c2..5cb47111f79e 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 893984946a2c..187a21f8b7bd 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,