Replace the MNT_VNODE_FOREACH interface with MNT_VNODE_FOREACH_ALL.

The primary changes are that the user of the interface no longer
needs to manage the mount-mutex locking and that the vnode that
is returned has its mutex locked (thus avoiding the need to check
to see if its is DOOMED or other possible end of life senarios).

To minimize compatibility issues for third-party developers, the
old MNT_VNODE_FOREACH interface will remain available so that this
change can be MFC'ed to 9. Following the MFC to 9, MNT_VNODE_FOREACH
will be removed in head.

The reason for this update is to prepare for the addition of the
MNT_VNODE_FOREACH_ACTIVE interface that will loop over just the
active vnodes associated with a mount point (typically less than
1% of the vnodes associated with the mount point).

Reviewed by: kib
Tested by:   Peter Holm
MFC after:   2 weeks

3 files changed, 102 insertions, 32 deletions

diff --git a/sys/kern/vfs_default.c b/sys/kern/vfs_default.c
index 25278c8..4e62765 100644
--- a/sys/kern/vfs_default.c
+++ b/sys/kern/vfs_default.c
@@ -1114,18 +1114,15 @@ vfs_stdsync(mp, waitfor)
 	/*
 	 * Force stale buffer cache information to be flushed.
 	 */
-	MNT_ILOCK(mp);
 loop:
-	MNT_VNODE_FOREACH(vp, mp, mvp) {
-		/* bv_cnt is an acceptable race here. */
-		if (vp->v_bufobj.bo_dirty.bv_cnt == 0)
+	MNT_VNODE_FOREACH_ALL(vp, mp, mvp) {
+		if (vp->v_bufobj.bo_dirty.bv_cnt == 0) {
+			VI_UNLOCK(vp);
 			continue;
-		VI_LOCK(vp);
-		MNT_IUNLOCK(mp);
+		}
 		if ((error = vget(vp, lockreq, td)) != 0) {
-			MNT_ILOCK(mp);
 			if (error == ENOENT) {
-				MNT_VNODE_FOREACH_ABORT_ILOCKED(mp, mvp);
+				MNT_VNODE_FOREACH_ALL_ABORT(mp, mvp);
 				goto loop;
 			}
 			continue;
@@ -1134,9 +1131,7 @@ loop:
 		if (error)
 			allerror = error;
 		vput(vp);
-		MNT_ILOCK(mp);
 	}
-	MNT_IUNLOCK(mp);
 	return (allerror);
 }
 
diff --git a/sys/kern/vfs_mount.c b/sys/kern/vfs_mount.c
index 657fa92..6a5dfb0 100644
--- a/sys/kern/vfs_mount.c
+++ b/sys/kern/vfs_mount.c
@@ -81,7 +81,6 @@ SYSCTL_INT(_vfs, OID_AUTO, usermount, CTLFLAG_RW, &usermount, 0,
     "Unprivileged users may mount and unmount file systems");
 
 MALLOC_DEFINE(M_MOUNT, "mount", "vfs mount structure");
-static MALLOC_DEFINE(M_VNODE_MARKER, "vnodemarker", "vnode marker");
 static uma_zone_t mount_zone;
 
 /* List of mounted filesystems. */
@@ -1720,10 +1719,14 @@ vfs_copyopt(opts, name, dest, len)
 }
 
 /*
- * This is a helper function for filesystems to traverse their
- * vnodes.  See MNT_VNODE_FOREACH() in sys/mount.h
+ * These are helper functions for filesystems to traverse all
+ * their vnodes.  See MNT_VNODE_FOREACH() in sys/mount.h.
+ *
+ * This interface has been deprecated in favor of MNT_VNODE_FOREACH_ALL.
  */
 
+MALLOC_DECLARE(M_VNODE_MARKER);
+
 struct vnode *
 __mnt_vnode_next(struct vnode **mvp, struct mount *mp)
 {
@@ -1812,7 +1815,6 @@ __mnt_vnode_markerfree(struct vnode **mvp, struct mount *mp)
 	MNT_REL(mp);
 }
 
-
 int
 __vfs_statfs(struct mount *mp, struct statfs *sbp)
 {
diff --git a/sys/kern/vfs_subr.c b/sys/kern/vfs_subr.c
index 051f8f7..14f8528 100644
--- a/sys/kern/vfs_subr.c
+++ b/sys/kern/vfs_subr.c
@@ -2467,17 +2467,13 @@ vflush(struct mount *mp, int rootrefs, int flags, struct thread *td)
 		}
 		vput(rootvp);
 	}
-	MNT_ILOCK(mp);
 loop:
-	MNT_VNODE_FOREACH(vp, mp, mvp) {
-		VI_LOCK(vp);
+	MNT_VNODE_FOREACH_ALL(vp, mp, mvp) {
 		vholdl(vp);
-		MNT_IUNLOCK(mp);
 		error = vn_lock(vp, LK_INTERLOCK | LK_EXCLUSIVE);
 		if (error) {
 			vdrop(vp);
-			MNT_ILOCK(mp);
-			MNT_VNODE_FOREACH_ABORT_ILOCKED(mp, mvp);
+			MNT_VNODE_FOREACH_ALL_ABORT(mp, mvp);
 			goto loop;
 		}
 		/*
@@ -2486,7 +2482,6 @@ loop:
 		if ((flags & SKIPSYSTEM) && (vp->v_vflag & VV_SYSTEM)) {
 			VOP_UNLOCK(vp, 0);
 			vdrop(vp);
-			MNT_ILOCK(mp);
 			continue;
 		}
 		/*
@@ -2504,7 +2499,7 @@ loop:
 			if (error != 0) {
 				VOP_UNLOCK(vp, 0);
 				vdrop(vp);
-				MNT_VNODE_FOREACH_ABORT(mp, mvp);
+				MNT_VNODE_FOREACH_ALL_ABORT(mp, mvp);
 				return (error);
 			}
 			error = VOP_GETATTR(vp, &vattr, td->td_ucred);
@@ -2515,7 +2510,6 @@ loop:
 			    (vp->v_writecount == 0 || vp->v_type != VREG)) {
 				VOP_UNLOCK(vp, 0);
 				vdropl(vp);
-				MNT_ILOCK(mp);
 				continue;
 			}
 		} else
@@ -2540,9 +2534,7 @@ loop:
 		}
 		VOP_UNLOCK(vp, 0);
 		vdropl(vp);
-		MNT_ILOCK(mp);
 	}
-	MNT_IUNLOCK(mp);
 	if (rootrefs > 0 && (flags & FORCECLOSE) == 0) {
 		/*
 		 * If just the root vnode is busy, and if its refcount
@@ -3279,19 +3271,15 @@ vfs_msync(struct mount *mp, int flags)
 	struct vm_object *obj;
 
 	CTR2(KTR_VFS, "%s: mp %p", __func__, mp);
-	MNT_ILOCK(mp);
-	MNT_VNODE_FOREACH(vp, mp, mvp) {
-		VI_LOCK(vp);
+	MNT_VNODE_FOREACH_ALL(vp, mp, mvp) {
 		obj = vp->v_object;
 		if (obj != NULL && (obj->flags & OBJ_MIGHTBEDIRTY) != 0 &&
 		    (flags == MNT_WAIT || VOP_ISLOCKED(vp) == 0)) {
-			MNT_IUNLOCK(mp);
 			if (!vget(vp,
 			    LK_EXCLUSIVE | LK_RETRY | LK_INTERLOCK,
 			    curthread)) {
 				if (vp->v_vflag & VV_NOSYNC) {	/* unlinked */
 					vput(vp);
-					MNT_ILOCK(mp);
 					continue;
 				}
 
@@ -3305,11 +3293,9 @@ vfs_msync(struct mount *mp, int flags)
 				}
 				vput(vp);
 			}
-			MNT_ILOCK(mp);
 		} else
 			VI_UNLOCK(vp);
 	}
-	MNT_IUNLOCK(mp);
 }
 
 /*
@@ -4504,3 +4490,90 @@ vfs_unixify_accmode(accmode_t *accmode)
 
 	return (0);
 }
+
+/*
+ * These are helper functions for filesystems to traverse all
+ * their vnodes.  See MNT_VNODE_FOREACH_ALL() in sys/mount.h.
+ *
+ * This interface replaces MNT_VNODE_FOREACH.
+ */
+
+MALLOC_DEFINE(M_VNODE_MARKER, "vnodemarker", "vnode marker");
+
+struct vnode *
+__mnt_vnode_next_all(struct vnode **mvp, struct mount *mp)
+{
+	struct vnode *vp;
+
+	if (should_yield())
+		kern_yield(PRI_UNCHANGED);
+	MNT_ILOCK(mp);
+	KASSERT((*mvp)->v_mount == mp, ("marker vnode mount list mismatch"));
+	vp = TAILQ_NEXT(*mvp, v_nmntvnodes);
+	while (vp != NULL && (vp->v_type == VMARKER ||
+	    (vp->v_iflag & VI_DOOMED) != 0))
+		vp = TAILQ_NEXT(vp, v_nmntvnodes);
+
+	/* Check if we are done */
+	if (vp == NULL) {
+		__mnt_vnode_markerfree_all(mvp, mp);
+		/* MNT_IUNLOCK(mp); -- done in above function */
+		mtx_assert(MNT_MTX(mp), MA_NOTOWNED);
+		return (NULL);
+	}
+	TAILQ_REMOVE(&mp->mnt_nvnodelist, *mvp, v_nmntvnodes);
+	TAILQ_INSERT_AFTER(&mp->mnt_nvnodelist, vp, *mvp, v_nmntvnodes);
+	VI_LOCK(vp);
+	MNT_IUNLOCK(mp);
+	return (vp);
+}
+
+struct vnode *
+__mnt_vnode_first_all(struct vnode **mvp, struct mount *mp)
+{
+	struct vnode *vp;
+
+	*mvp = malloc(sizeof(struct vnode), M_VNODE_MARKER, M_WAITOK | M_ZERO);
+	MNT_ILOCK(mp);
+	MNT_REF(mp);
+	(*mvp)->v_type = VMARKER;
+
+	vp = TAILQ_FIRST(&mp->mnt_nvnodelist);
+	while (vp != NULL && (vp->v_type == VMARKER ||
+	    (vp->v_iflag & VI_DOOMED) != 0))
+		vp = TAILQ_NEXT(vp, v_nmntvnodes);
+
+	/* Check if we are done */
+	if (vp == NULL) {
+		*mvp = NULL;
+		MNT_REL(mp);
+		MNT_IUNLOCK(mp);
+		free(*mvp, M_VNODE_MARKER);
+		return (NULL);
+	}
+	(*mvp)->v_mount = mp;
+	TAILQ_INSERT_AFTER(&mp->mnt_nvnodelist, vp, *mvp, v_nmntvnodes);
+	VI_LOCK(vp);
+	MNT_IUNLOCK(mp);
+	return (vp);
+}
+
+
+void
+__mnt_vnode_markerfree_all(struct vnode **mvp, struct mount *mp)
+{
+
+	if (*mvp == NULL) {
+		MNT_IUNLOCK(mp);
+		return;
+	}
+
+	mtx_assert(MNT_MTX(mp), MA_OWNED);
+
+	KASSERT((*mvp)->v_mount == mp, ("marker vnode mount list mismatch"));
+	TAILQ_REMOVE(&mp->mnt_nvnodelist, *mvp, v_nmntvnodes);
+	MNT_REL(mp);
+	MNT_IUNLOCK(mp);
+	free(*mvp, M_VNODE_MARKER);
+	*mvp = NULL;
+}