vmscan: split LRU lists into anon & file sets

Split the LRU lists in two, one set for pages that are backed by real file
systems ("file") and one for pages that are backed by memory and swap
("anon").  The latter includes tmpfs.

The advantage of doing this is that the VM will not have to scan over lots
of anonymous pages (which we generally do not want to swap out), just to
find the page cache pages that it should evict.

This patch has the infrastructure and a basic policy to balance how much
we scan the anon lists and how much we scan the file lists.  The big
policy changes are in separate patches.

[lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset]
[kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru]
[kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page]
[hugh@veritas.com: memcg swapbacked pages active]
[hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED]
[akpm@linux-foundation.org: fix /proc/vmstat units]
[nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration]
[kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo]
[kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()]
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 52 insertions, 39 deletions

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index c4a8a0605125..62d8bd8f14c0 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1791,7 +1791,7 @@ static void cifs_copy_cache_pages(struct address_space *mapping,
                 SetPageUptodate(page);
                 unlock_page(page);
                 if (!pagevec_add(plru_pvec, page))
-                        __pagevec_lru_add(plru_pvec);
+                        __pagevec_lru_add_file(plru_pvec);
                 data += PAGE_CACHE_SIZE;
         }
         return;
@@ -1925,7 +1925,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
                 bytes_read = 0;
         }
 
-        pagevec_lru_add(&lru_pvec);
+        pagevec_lru_add_file(&lru_pvec);
 
 /* need to free smb_read_data buf before exit */
         if (smb_read_data) {
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 2ab70d46ecbc..efdba2e802d7 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1517,7 +1517,7 @@ static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *sym
         if (!add_to_page_cache(page, dentry->d_inode->i_mapping, 0,
                                                         GFP_KERNEL)) {
                 pagevec_add(&lru_pvec, page);
-                pagevec_lru_add(&lru_pvec);
+                pagevec_lru_add_file(&lru_pvec);
                 SetPageUptodate(page);
                 unlock_page(page);
         } else
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index d020866d4232..3140a4429af1 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -439,7 +439,7 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping,
                         pages[nr] = *cached_page;
                         page_cache_get(*cached_page);
                         if (unlikely(!pagevec_add(lru_pvec, *cached_page)))
-                                __pagevec_lru_add(lru_pvec);
+                                __pagevec_lru_add_file(lru_pvec);
                         *cached_page = NULL;
                 }
                 index++;
@@ -2084,7 +2084,7 @@ err_out:
                                                 OSYNC_METADATA|OSYNC_DATA);
                 }
         }
-        pagevec_lru_add(&lru_pvec);
+        pagevec_lru_add_file(&lru_pvec);
         ntfs_debug("Done.  Returning %s (written 0x%lx, status %li).",
                         written ? "written" : "status", (unsigned long)written,
                         (long)status);
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 59ea42e1ef03..b8edb2860557 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -136,6 +136,8 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
         unsigned long allowed;
         struct vmalloc_info vmi;
         long cached;
+        unsigned long pages[NR_LRU_LISTS];
+        int lru;
 
 /*
  * display in kilobytes.
@@ -154,51 +156,62 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 
         get_vmalloc_info(&vmi);
 
+        for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
+                pages[lru] = global_page_state(NR_LRU_BASE + lru);
+
         /*
          * Tagged format, for easy grepping and expansion.
          */
         len = sprintf(page,
-                "MemTotal:     %8lu kB\n"
-                "MemFree:      %8lu kB\n"
-                "Buffers:      %8lu kB\n"
-                "Cached:       %8lu kB\n"
-                "SwapCached:   %8lu kB\n"
-                "Active:       %8lu kB\n"
-                "Inactive:     %8lu kB\n"
+                "MemTotal:       %8lu kB\n"
+                "MemFree:        %8lu kB\n"
+                "Buffers:        %8lu kB\n"
+                "Cached:         %8lu kB\n"
+                "SwapCached:     %8lu kB\n"
+                "Active:         %8lu kB\n"
+                "Inactive:       %8lu kB\n"
+                "Active(anon):   %8lu kB\n"
+                "Inactive(anon): %8lu kB\n"
+                "Active(file):   %8lu kB\n"
+                "Inactive(file): %8lu kB\n"
 #ifdef CONFIG_HIGHMEM
-                "HighTotal:    %8lu kB\n"
-                "HighFree:     %8lu kB\n"
-                "LowTotal:     %8lu kB\n"
-                "LowFree:      %8lu kB\n"
+                "HighTotal:      %8lu kB\n"
+                "HighFree:       %8lu kB\n"
+                "LowTotal:       %8lu kB\n"
+                "LowFree:        %8lu kB\n"
 #endif
-                "SwapTotal:    %8lu kB\n"
-                "SwapFree:     %8lu kB\n"
-                "Dirty:        %8lu kB\n"
-                "Writeback:    %8lu kB\n"
-                "AnonPages:    %8lu kB\n"
-                "Mapped:       %8lu kB\n"
-                "Slab:         %8lu kB\n"
-                "SReclaimable: %8lu kB\n"
-                "SUnreclaim:   %8lu kB\n"
-                "PageTables:   %8lu kB\n"
+                "SwapTotal:      %8lu kB\n"
+                "SwapFree:       %8lu kB\n"
+                "Dirty:          %8lu kB\n"
+                "Writeback:      %8lu kB\n"
+                "AnonPages:      %8lu kB\n"
+                "Mapped:         %8lu kB\n"
+                "Slab:           %8lu kB\n"
+                "SReclaimable:   %8lu kB\n"
+                "SUnreclaim:     %8lu kB\n"
+                "PageTables:     %8lu kB\n"
 #ifdef CONFIG_QUICKLIST
-                "Quicklists:   %8lu kB\n"
+                "Quicklists:     %8lu kB\n"
 #endif
-                "NFS_Unstable: %8lu kB\n"
-                "Bounce:       %8lu kB\n"
-                "WritebackTmp: %8lu kB\n"
-                "CommitLimit:  %8lu kB\n"
-                "Committed_AS: %8lu kB\n"
-                "VmallocTotal: %8lu kB\n"
-                "VmallocUsed:  %8lu kB\n"
-                "VmallocChunk: %8lu kB\n",
+                "NFS_Unstable:   %8lu kB\n"
+                "Bounce:         %8lu kB\n"
+                "WritebackTmp:   %8lu kB\n"
+                "CommitLimit:    %8lu kB\n"
+                "Committed_AS:   %8lu kB\n"
+                "VmallocTotal:   %8lu kB\n"
+                "VmallocUsed:    %8lu kB\n"
+                "VmallocChunk:   %8lu kB\n",
                 K(i.totalram),
                 K(i.freeram),
                 K(i.bufferram),
                 K(cached),
                 K(total_swapcache_pages),
-                K(global_page_state(NR_ACTIVE)),
-                K(global_page_state(NR_INACTIVE)),
+                K(pages[LRU_ACTIVE_ANON]   + pages[LRU_ACTIVE_FILE]),
+                K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]),
+                K(pages[LRU_ACTIVE_ANON]),
+                K(pages[LRU_INACTIVE_ANON]),
+                K(pages[LRU_ACTIVE_FILE]),
+                K(pages[LRU_INACTIVE_FILE]),
 #ifdef CONFIG_HIGHMEM
                 K(i.totalhigh),
                 K(i.freehigh),
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index 5145cb9125af..76acdbc34611 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -112,12 +112,12 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
                         goto add_error;
 
                 if (!pagevec_add(&lru_pvec, page))
-                        __pagevec_lru_add(&lru_pvec);
+                        __pagevec_lru_add_file(&lru_pvec);
 
                 unlock_page(page);
         }
 
-        pagevec_lru_add(&lru_pvec);
+        pagevec_lru_add_file(&lru_pvec);
         return 0;
 
  fsize_exceeded: