dcache: convert dentry_stat.nr_unused to per-cpu counters

Before we split up the dcache_lru_lock, the unused dentry counter needs to
be made independent of the global dcache_lru_lock.  Convert it to per-cpu
counters to do this.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Glauber Costa <glommer@openvz.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Cc: Arve Hjønnevåg <arve@android.com>
Cc: Carlos Maiolino <cmaiolino@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Rientjes <rientjes@google.com>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: J. Bruce Fields <bfields@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Kent Overstreet <koverstreet@google.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
diff --git a/fs/dcache.c b/fs/dcache.c
index 6ef1c2e..0316124 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -147,8 +147,22 @@
 };
 
 static DEFINE_PER_CPU(long, nr_dentry);
+static DEFINE_PER_CPU(long, nr_dentry_unused);
 
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
+
+/*
+ * Here we resort to our own counters instead of using generic per-cpu counters
+ * for consistency with what the vfs inode code does. We are expected to harvest
+ * better code and performance by having our own specialized counters.
+ *
+ * Please note that the loop is done over all possible CPUs, not over all online
+ * CPUs. The reason for this is that we don't want to play games with CPUs going
+ * on and off. If one of them goes off, we will just keep their counters.
+ *
+ * glommer: See cffbc8a for details, and if you ever intend to change this,
+ * please update all vfs counters to match.
+ */
 static long get_nr_dentry(void)
 {
 	int i;
@@ -158,10 +172,20 @@
 	return sum < 0 ? 0 : sum;
 }
 
+static long get_nr_dentry_unused(void)
+{
+	int i;
+	long sum = 0;
+	for_each_possible_cpu(i)
+		sum += per_cpu(nr_dentry_unused, i);
+	return sum < 0 ? 0 : sum;
+}
+
 int proc_nr_dentry(ctl_table *table, int write, void __user *buffer,
 		   size_t *lenp, loff_t *ppos)
 {
 	dentry_stat.nr_dentry = get_nr_dentry();
+	dentry_stat.nr_unused = get_nr_dentry_unused();
 	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 #endif
@@ -342,7 +366,7 @@
 		dentry->d_flags |= DCACHE_LRU_LIST;
 		list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
 		dentry->d_sb->s_nr_dentry_unused++;
-		dentry_stat.nr_unused++;
+		this_cpu_inc(nr_dentry_unused);
 		spin_unlock(&dcache_lru_lock);
 	}
 }
@@ -352,7 +376,7 @@
 	list_del_init(&dentry->d_lru);
 	dentry->d_flags &= ~(DCACHE_SHRINK_LIST | DCACHE_LRU_LIST);
 	dentry->d_sb->s_nr_dentry_unused--;
-	dentry_stat.nr_unused--;
+	this_cpu_dec(nr_dentry_unused);
 }
 
 /*
@@ -374,7 +398,7 @@
 		dentry->d_flags |= DCACHE_LRU_LIST;
 		list_add_tail(&dentry->d_lru, list);
 		dentry->d_sb->s_nr_dentry_unused++;
-		dentry_stat.nr_unused++;
+		this_cpu_inc(nr_dentry_unused);
 	} else {
 		list_move_tail(&dentry->d_lru, list);
 	}