fs: scale mntget/mntput

The problem that this patch aims to fix is vfsmount refcounting scalability.
We need to take a reference on the vfsmount for every successful path lookup,
which often go to the same mount point.

The fundamental difficulty is that a "simple" reference count can never be made
scalable, because any time a reference is dropped, we must check whether that
was the last reference. To do that requires communication with all other CPUs
that may have taken a reference count.

We can make refcounts more scalable in a couple of ways, involving keeping
distributed counters, and checking for the global-zero condition less
frequently.

- check the global sum once every interval (this will delay zero detection
  for some interval, so it's probably a showstopper for vfsmounts).

- keep a local count and only taking the global sum when local reaches 0 (this
  is difficult for vfsmounts, because we can't hold preempt off for the life of
  a reference, so a counter would need to be per-thread or tied strongly to a
  particular CPU which requires more locking).

- keep a local difference of increments and decrements, which allows us to sum
  the total difference and hence find the refcount when summing all CPUs. Then,
  keep a single integer "long" refcount for slow and long lasting references,
  and only take the global sum of local counters when the long refcount is 0.

This last scheme is what I implemented here. Attached mounts and process root
and working directory references are "long" references, and everything else is
a short reference.

This allows scalable vfsmount references during path walking over mounted
subtrees and unattached (lazy umounted) mounts with processes still running
in them.

This results in one fewer atomic op in the fastpath: mntget is now just a
per-CPU inc, rather than an atomic inc; and mntput just requires a spinlock
and non-atomic decrement in the common case. However code is otherwise bigger
and heavier, so single threaded performance is basically a wash.

Signed-off-by: Nick Piggin <npiggin@kernel.dk>

2 files changed, 19 insertions, 36 deletions

diff --git a/include/linux/mount.h b/include/linux/mount.h
index 5e7a59408dd4..1869ea24a739 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -13,6 +13,7 @@
 #include <linux/list.h>
 #include <linux/nodemask.h>
 #include <linux/spinlock.h>
+#include <linux/seqlock.h>
 #include <asm/atomic.h>
 
 struct super_block;
@@ -46,12 +47,24 @@ struct mnt_namespace;
 
 #define MNT_INTERNAL	0x4000
 
+struct mnt_pcp {
+	int mnt_count;
+	int mnt_writers;
+};
+
 struct vfsmount {
 	struct list_head mnt_hash;
 	struct vfsmount *mnt_parent;	/* fs we are mounted on */
 	struct dentry *mnt_mountpoint;	/* dentry of mountpoint */
 	struct dentry *mnt_root;	/* root of the mounted tree */
 	struct super_block *mnt_sb;	/* pointer to superblock */
+#ifdef CONFIG_SMP
+	struct mnt_pcp __percpu *mnt_pcp;
+	atomic_t mnt_longrefs;
+#else
+	int mnt_count;
+	int mnt_writers;
+#endif
 	struct list_head mnt_mounts;	/* list of children, anchored here */
 	struct list_head mnt_child;	/* and going through their mnt_child */
 	int mnt_flags;
@@ -70,57 +83,25 @@ struct vfsmount {
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	int mnt_id;			/* mount identifier */
 	int mnt_group_id;		/* peer group identifier */
-	/*
-	 * We put mnt_count & mnt_expiry_mark at the end of struct vfsmount
-	 * to let these frequently modified fields in a separate cache line
-	 * (so that reads of mnt_flags wont ping-pong on SMP machines)
-	 */
-	atomic_t mnt_count;
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	int mnt_pinned;
 	int mnt_ghosts;
-#ifdef CONFIG_SMP
-	int __percpu *mnt_writers;
-#else
-	int mnt_writers;
-#endif
 };
 
-static inline int *get_mnt_writers_ptr(struct vfsmount *mnt)
-{
-#ifdef CONFIG_SMP
-	return mnt->mnt_writers;
-#else
-	return &mnt->mnt_writers;
-#endif
-}
-
-static inline struct vfsmount *mntget(struct vfsmount *mnt)
-{
-	if (mnt)
-		atomic_inc(&mnt->mnt_count);
-	return mnt;
-}
-
 struct file; /* forward dec */
 
 extern int mnt_want_write(struct vfsmount *mnt);
 extern int mnt_want_write_file(struct file *file);
 extern int mnt_clone_write(struct vfsmount *mnt);
 extern void mnt_drop_write(struct vfsmount *mnt);
-extern void mntput_no_expire(struct vfsmount *mnt);
+extern void mntput(struct vfsmount *mnt);
+extern struct vfsmount *mntget(struct vfsmount *mnt);
+extern void mntput_long(struct vfsmount *mnt);
+extern struct vfsmount *mntget_long(struct vfsmount *mnt);
 extern void mnt_pin(struct vfsmount *mnt);
 extern void mnt_unpin(struct vfsmount *mnt);
 extern int __mnt_is_readonly(struct vfsmount *mnt);
 
-static inline void mntput(struct vfsmount *mnt)
-{
-	if (mnt) {
-		mnt->mnt_expiry_mark = 0;
-		mntput_no_expire(mnt);
-	}
-}
-
 extern struct vfsmount *do_kern_mount(const char *fstype, int flags,
 				      const char *name, void *data);
 
diff --git a/include/linux/path.h b/include/linux/path.h
index edc98dec6266..a581e8c06533 100644
--- a/include/linux/path.h
+++ b/include/linux/path.h
@@ -10,7 +10,9 @@ struct path {
 };
 
 extern void path_get(struct path *);
+extern void path_get_long(struct path *);
 extern void path_put(struct path *);
+extern void path_put_long(struct path *);
 
 static inline int path_equal(const struct path *path1, const struct path *path2)
 {