mm: /proc/pid/smaps:: show proportional swap share of the mapping

We want to know per-process workingset size for smart memory management
on userland and we use swap(ex, zram) heavily to maximize memory
efficiency so workingset includes swap as well as RSS.

On such system, if there are lots of shared anonymous pages, it's really
hard to figure out exactly how many each process consumes memory(ie, rss
+ wap) if the system has lots of shared anonymous memory(e.g, android).

This patch introduces SwapPss field on /proc/<pid>/smaps so we can get
more exact workingset size per process.

Bongkyu tested it. Result is below.

1. 50M used swap
SwapTotal: 461976 kB
SwapFree: 411192 kB

$ adb shell cat /proc/*/smaps | grep "SwapPss:" | awk '{sum += $2} END {print sum}';
48236
$ adb shell cat /proc/*/smaps | grep "Swap:" | awk '{sum += $2} END {print sum}';
141184

2. 240M used swap
SwapTotal: 461976 kB
SwapFree: 216808 kB

$ adb shell cat /proc/*/smaps | grep "SwapPss:" | awk '{sum += $2} END {print sum}';
230315
$ adb shell cat /proc/*/smaps | grep "Swap:" | awk '{sum += $2} END {print sum}';
1387744

[akpm@linux-foundation.org: simplify kunmap_atomic() call]
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reported-by: Bongkyu Kim <bongkyu.kim@lge.com>
Tested-by: Bongkyu Kim <bongkyu.kim@lge.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Jerome Marchand <jmarchan@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Documentation/filesystems/proc.txt

@@ -424,6 +424,7 @@ Private_Dirty:         0 kB
 Referenced:          892 kB
 Anonymous:             0 kB
 Swap:                  0 kB
+SwapPss:               0 kB
 KernelPageSize:        4 kB
 MMUPageSize:           4 kB
 Locked:              374 kB
@@ -433,16 +434,23 @@ the first of these lines shows the same information as is displayed for the
 mapping in /proc/PID/maps.  The remaining lines show the size of the mapping
 (size), the amount of the mapping that is currently resident in RAM (RSS), the
 process' proportional share of this mapping (PSS), the number of clean and
-dirty private pages in the mapping.  Note that even a page which is part of a
-MAP_SHARED mapping, but has only a single pte mapped, i.e.  is currently used
-by only one process, is accounted as private and not as shared.  "Referenced"
-indicates the amount of memory currently marked as referenced or accessed.
+dirty private pages in the mapping.
+
+The "proportional set size" (PSS) of a process is the count of pages it has
+in memory, where each page is divided by the number of processes sharing it.
+So if a process has 1000 pages all to itself, and 1000 shared with one other
+process, its PSS will be 1500.
+Note that even a page which is part of a MAP_SHARED mapping, but has only
+a single pte mapped, i.e.  is currently used by only one process, is accounted
+as private and not as shared.
+"Referenced" indicates the amount of memory currently marked as referenced or
+accessed.
 "Anonymous" shows the amount of memory that does not belong to any file.  Even
 a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
 and a page is modified, the file page is replaced by a private anonymous copy.
 "Swap" shows how much would-be-anonymous memory is also used, but out on
 swap.
-
+"SwapPss" shows proportional swap share of this mapping.
 "VmFlags" field deserves a separate description. This member represents the kernel
 flags associated with the particular virtual memory area in two letter encoded
 manner. The codes are the following:

fs/proc/task_mmu.c

@@ -446,6 +446,7 @@ struct mem_size_stats {
 	unsigned long anonymous_thp;
 	unsigned long swap;
 	u64 pss;
+	u64 swap_pss;
 };
 
 static void smaps_account(struct mem_size_stats *mss, struct page *page,
@@ -492,9 +493,20 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 	} else if (is_swap_pte(*pte)) {
 		swp_entry_t swpent = pte_to_swp_entry(*pte);
 
-		if (!non_swap_entry(swpent))
+		if (!non_swap_entry(swpent)) {
+			int mapcount;
+
 			mss->swap += PAGE_SIZE;
-		else if (is_migration_entry(swpent))
+			mapcount = swp_swapcount(swpent);
+			if (mapcount >= 2) {
+				u64 pss_delta = (u64)PAGE_SIZE << PSS_SHIFT;
+
+				do_div(pss_delta, mapcount);
+				mss->swap_pss += pss_delta;
+			} else {
+				mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT;
+			}
+		} else if (is_migration_entry(swpent))
 			page = migration_entry_to_page(swpent);
 	}
 
@@ -640,6 +652,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   "Anonymous:      %8lu kB\n"
 		   "AnonHugePages:  %8lu kB\n"
 		   "Swap:           %8lu kB\n"
+		   "SwapPss:        %8lu kB\n"
 		   "KernelPageSize: %8lu kB\n"
 		   "MMUPageSize:    %8lu kB\n"
 		   "Locked:         %8lu kB\n",
@@ -654,6 +667,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   mss.anonymous >> 10,
 		   mss.anonymous_thp >> 10,
 		   mss.swap >> 10,
+		   (unsigned long)(mss.swap_pss >> (10 + PSS_SHIFT)),
 		   vma_kernel_pagesize(vma) >> 10,
 		   vma_mmu_pagesize(vma) >> 10,
 		   (vma->vm_flags & VM_LOCKED) ?

include/linux/swap.h

@@ -431,6 +431,7 @@ extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct page *, struct block_device **);
 extern sector_t swapdev_block(int, pgoff_t);
 extern int page_swapcount(struct page *);
+extern int swp_swapcount(swp_entry_t entry);
 extern struct swap_info_struct *page_swap_info(struct page *);
 extern int reuse_swap_page(struct page *);
 extern int try_to_free_swap(struct page *);
@@ -522,6 +523,11 @@ static inline int page_swapcount(struct page *page)
 	return 0;
 }
 
+static inline int swp_swapcount(swp_entry_t entry)
+{
+	return 0;
+}
+
 #define reuse_swap_page(page)	(page_mapcount(page) == 1)
 
 static inline int try_to_free_swap(struct page *page)

mm/swapfile.c

@@ -874,6 +874,48 @@ int page_swapcount(struct page *page)
 	return count;
 }
 
+/*
+ * How many references to @entry are currently swapped out?
+ * This considers COUNT_CONTINUED so it returns exact answer.
+ */
+int swp_swapcount(swp_entry_t entry)
+{
+	int count, tmp_count, n;
+	struct swap_info_struct *p;
+	struct page *page;
+	pgoff_t offset;
+	unsigned char *map;
+
+	p = swap_info_get(entry);
+	if (!p)
+		return 0;
+
+	count = swap_count(p->swap_map[swp_offset(entry)]);
+	if (!(count & COUNT_CONTINUED))
+		goto out;
+
+	count &= ~COUNT_CONTINUED;
+	n = SWAP_MAP_MAX + 1;
+
+	offset = swp_offset(entry);
+	page = vmalloc_to_page(p->swap_map + offset);
+	offset &= ~PAGE_MASK;
+	VM_BUG_ON(page_private(page) != SWP_CONTINUED);
+
+	do {
+		page = list_entry(page->lru.next, struct page, lru);
+		map = kmap_atomic(page);
+		tmp_count = map[offset];
+		kunmap_atomic(map);
+
+		count += (tmp_count & ~COUNT_CONTINUED) * n;
+		n *= (SWAP_CONT_MAX + 1);
+	} while (tmp_count & COUNT_CONTINUED);
+out:
+	spin_unlock(&p->lock);
+	return count;
+}
+
 /*
  * We can write to an anon page without COW if there are no other references
  * to it.  And as a side-effect, free up its swap: because the old content