From 570487d3faf2a1d8a220e6ee10f472163123d7da Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 15 May 2017 14:42:07 -0500
Subject: mnt: In umount propagation reparent in a separate pass

It was observed that in some pathlogical cases that the current code
does not unmount everything it should.  After investigation it
was determined that the issue is that mnt_change_mntpoint can
can change which mounts are available to be unmounted during mount
propagation which is wrong.

The trivial reproducer is:
$ cat ./pathological.sh

mount -t tmpfs test-base /mnt
cd /mnt
mkdir 1 2 1/1
mount --bind 1 1
mount --make-shared 1
mount --bind 1 2
mount --bind 1/1 1/1
mount --bind 1/1 1/1
echo
grep test-base /proc/self/mountinfo
umount 1/1
echo
grep test-base /proc/self/mountinfo

$ unshare -Urm ./pathological.sh

The expected output looks like:
46 31 0:25 / /mnt rw,relatime - tmpfs test-base rw,uid=1000,gid=1000
47 46 0:25 /1 /mnt/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
48 46 0:25 /1 /mnt/2 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
49 54 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
50 53 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
51 49 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
54 47 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
53 48 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
52 50 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000

46 31 0:25 / /mnt rw,relatime - tmpfs test-base rw,uid=1000,gid=1000
47 46 0:25 /1 /mnt/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
48 46 0:25 /1 /mnt/2 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000

The output without the fix looks like:
46 31 0:25 / /mnt rw,relatime - tmpfs test-base rw,uid=1000,gid=1000
47 46 0:25 /1 /mnt/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
48 46 0:25 /1 /mnt/2 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
49 54 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
50 53 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
51 49 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
54 47 0:25 /1/1 /mnt/1/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
53 48 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
52 50 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000

46 31 0:25 / /mnt rw,relatime - tmpfs test-base rw,uid=1000,gid=1000
47 46 0:25 /1 /mnt/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
48 46 0:25 /1 /mnt/2 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000
52 48 0:25 /1/1 /mnt/2/1 rw,relatime shared:1 - tmpfs test-base rw,uid=1000,gid=1000

That last mount in the output was in the propgation tree to be unmounted but
was missed because the mnt_change_mountpoint changed it's parent before the walk
through the mount propagation tree observed it.

Cc: stable@vger.kernel.org
Fixes: 1064f874abc0 ("mnt: Tuck mounts under others instead of creating shadow/side mounts.")
Acked-by: Andrei Vagin <avagin@virtuozzo.com>
Reviewed-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/mount.h     |  1 +
 fs/namespace.c |  1 +
 fs/pnode.c     | 35 ++++++++++++++++++++++++++++++-----
 3 files changed, 32 insertions(+), 5 deletions(-)

diff --git a/fs/mount.h b/fs/mount.h
index bf1fda6eed8f..ede5a1d5cf99 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -58,6 +58,7 @@ struct mount {
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	struct mountpoint *mnt_mp;	/* where is it mounted */
 	struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
+	struct list_head mnt_reparent;	/* reparent list entry */
 #ifdef CONFIG_FSNOTIFY
 	struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
diff --git a/fs/namespace.c b/fs/namespace.c
index 8bd3e4d448b9..51e49866e1fe 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -236,6 +236,7 @@ static struct mount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
 		INIT_HLIST_NODE(&mnt->mnt_mp_list);
+		INIT_LIST_HEAD(&mnt->mnt_reparent);
 		init_fs_pin(&mnt->mnt_umount, drop_mountpoint);
 	}
 	return mnt;
diff --git a/fs/pnode.c b/fs/pnode.c
index 5bc7896d122a..52aca0a118ff 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -439,7 +439,7 @@ static void mark_umount_candidates(struct mount *mnt)
  * NOTE: unmounting 'mnt' naturally propagates to all other mounts its
  * parent propagates to.
  */
-static void __propagate_umount(struct mount *mnt)
+static void __propagate_umount(struct mount *mnt, struct list_head *to_reparent)
 {
 	struct mount *parent = mnt->mnt_parent;
 	struct mount *m;
@@ -464,17 +464,38 @@ static void __propagate_umount(struct mount *mnt)
 		 */
 		topper = find_topper(child);
 		if (topper)
-			mnt_change_mountpoint(child->mnt_parent, child->mnt_mp,
-					      topper);
+			list_add_tail(&topper->mnt_reparent, to_reparent);
 
-		if (list_empty(&child->mnt_mounts)) {
+		if (topper || list_empty(&child->mnt_mounts)) {
 			list_del_init(&child->mnt_child);
+			list_del_init(&child->mnt_reparent);
 			child->mnt.mnt_flags |= MNT_UMOUNT;
 			list_move_tail(&child->mnt_list, &mnt->mnt_list);
 		}
 	}
 }
 
+static void reparent_mounts(struct list_head *to_reparent)
+{
+	while (!list_empty(to_reparent)) {
+		struct mount *mnt, *parent;
+		struct mountpoint *mp;
+
+		mnt = list_first_entry(to_reparent, struct mount, mnt_reparent);
+		list_del_init(&mnt->mnt_reparent);
+
+		/* Where should this mount be reparented to? */
+		mp = mnt->mnt_mp;
+		parent = mnt->mnt_parent;
+		while (parent->mnt.mnt_flags & MNT_UMOUNT) {
+			mp = parent->mnt_mp;
+			parent = parent->mnt_parent;
+		}
+
+		mnt_change_mountpoint(parent, mp, mnt);
+	}
+}
+
 /*
  * collect all mounts that receive propagation from the mount in @list,
  * and return these additional mounts in the same list.
@@ -485,11 +506,15 @@ static void __propagate_umount(struct mount *mnt)
 int propagate_umount(struct list_head *list)
 {
 	struct mount *mnt;
+	LIST_HEAD(to_reparent);
 
 	list_for_each_entry_reverse(mnt, list, mnt_list)
 		mark_umount_candidates(mnt);
 
 	list_for_each_entry(mnt, list, mnt_list)
-		__propagate_umount(mnt);
+		__propagate_umount(mnt, &to_reparent);
+
+	reparent_mounts(&to_reparent);
+
 	return 0;
 }
-- 
cgit v1.2.3


From 99b19d16471e9c3faa85cad38abc9cbbe04c6d55 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 24 Oct 2016 16:16:13 -0500
Subject: mnt: In propgate_umount handle visiting mounts in any order

While investigating some poor umount performance I realized that in
the case of overlapping mount trees where some of the mounts are locked
the code has been failing to unmount all of the mounts it should
have been unmounting.

This failure to unmount all of the necessary
mounts can be reproduced with:

$ cat locked_mounts_test.sh

mount -t tmpfs test-base /mnt
mount --make-shared /mnt
mkdir -p /mnt/b

mount -t tmpfs test1 /mnt/b
mount --make-shared /mnt/b
mkdir -p /mnt/b/10

mount -t tmpfs test2 /mnt/b/10
mount --make-shared /mnt/b/10
mkdir -p /mnt/b/10/20

mount --rbind /mnt/b /mnt/b/10/20

unshare -Urm --propagation unchaged /bin/sh -c 'sleep 5; if [ $(grep test /proc/self/mountinfo | wc -l) -eq 1 ] ; then echo SUCCESS ; else echo FAILURE ; fi'
sleep 1
umount -l /mnt/b
wait %%

$ unshare -Urm ./locked_mounts_test.sh

This failure is corrected by removing the prepass that marks mounts
that may be umounted.

A first pass is added that umounts mounts if possible and if not sets
mount mark if they could be unmounted if they weren't locked and adds
them to a list to umount possibilities.  This first pass reconsiders
the mounts parent if it is on the list of umount possibilities, ensuring
that information of umoutability will pass from child to mount parent.

A second pass then walks through all mounts that are umounted and processes
their children unmounting them or marking them for reparenting.

A last pass cleans up the state on the mounts that could not be umounted
and if applicable reparents them to their first parent that remained
mounted.

While a bit longer than the old code this code is much more robust
as it allows information to flow up from the leaves and down
from the trunk making the order in which mounts are encountered
in the umount propgation tree irrelevant.

Cc: stable@vger.kernel.org
Fixes: 0c56fe31420c ("mnt: Don't propagate unmounts to locked mounts")
Reviewed-by: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/mount.h     |   2 +-
 fs/namespace.c |   2 +-
 fs/pnode.c     | 144 ++++++++++++++++++++++++++++++++++-----------------------
 3 files changed, 88 insertions(+), 60 deletions(-)

diff --git a/fs/mount.h b/fs/mount.h
index ede5a1d5cf99..de45d9e76748 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -58,7 +58,7 @@ struct mount {
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	struct mountpoint *mnt_mp;	/* where is it mounted */
 	struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
-	struct list_head mnt_reparent;	/* reparent list entry */
+	struct list_head mnt_umounting; /* list entry for umount propagation */
 #ifdef CONFIG_FSNOTIFY
 	struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
diff --git a/fs/namespace.c b/fs/namespace.c
index 51e49866e1fe..5e3dcbeb1de5 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -236,7 +236,7 @@ static struct mount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
 		INIT_HLIST_NODE(&mnt->mnt_mp_list);
-		INIT_LIST_HEAD(&mnt->mnt_reparent);
+		INIT_LIST_HEAD(&mnt->mnt_umounting);
 		init_fs_pin(&mnt->mnt_umount, drop_mountpoint);
 	}
 	return mnt;
diff --git a/fs/pnode.c b/fs/pnode.c
index 52aca0a118ff..fbaca7df2eb0 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -413,86 +413,95 @@ void propagate_mount_unlock(struct mount *mnt)
 	}
 }
 
-/*
- * Mark all mounts that the MNT_LOCKED logic will allow to be unmounted.
- */
-static void mark_umount_candidates(struct mount *mnt)
+static void umount_one(struct mount *mnt, struct list_head *to_umount)
 {
-	struct mount *parent = mnt->mnt_parent;
-	struct mount *m;
-
-	BUG_ON(parent == mnt);
-
-	for (m = propagation_next(parent, parent); m;
-			m = propagation_next(m, parent)) {
-		struct mount *child = __lookup_mnt(&m->mnt,
-						mnt->mnt_mountpoint);
-		if (!child || (child->mnt.mnt_flags & MNT_UMOUNT))
-			continue;
-		if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) {
-			SET_MNT_MARK(child);
-		}
-	}
+	CLEAR_MNT_MARK(mnt);
+	mnt->mnt.mnt_flags |= MNT_UMOUNT;
+	list_del_init(&mnt->mnt_child);
+	list_del_init(&mnt->mnt_umounting);
+	list_move_tail(&mnt->mnt_list, to_umount);
 }
 
 /*
  * NOTE: unmounting 'mnt' naturally propagates to all other mounts its
  * parent propagates to.
  */
-static void __propagate_umount(struct mount *mnt, struct list_head *to_reparent)
+static bool __propagate_umount(struct mount *mnt,
+			       struct list_head *to_umount,
+			       struct list_head *to_restore)
 {
-	struct mount *parent = mnt->mnt_parent;
-	struct mount *m;
+	bool progress = false;
+	struct mount *child;
 
-	BUG_ON(parent == mnt);
+	/*
+	 * The state of the parent won't change if this mount is
+	 * already unmounted or marked as without children.
+	 */
+	if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED))
+		goto out;
 
-	for (m = propagation_next(parent, parent); m;
-			m = propagation_next(m, parent)) {
-		struct mount *topper;
-		struct mount *child = __lookup_mnt(&m->mnt,
-						mnt->mnt_mountpoint);
-		/*
-		 * umount the child only if the child has no children
-		 * and the child is marked safe to unmount.
-		 */
-		if (!child || !IS_MNT_MARKED(child))
+	/* Verify topper is the only grandchild that has not been
+	 * speculatively unmounted.
+	 */
+	list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
+		if (child->mnt_mountpoint == mnt->mnt.mnt_root)
 			continue;
-		CLEAR_MNT_MARK(child);
+		if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child))
+			continue;
+		/* Found a mounted child */
+		goto children;
+	}
 
-		/* If there is exactly one mount covering all of child
-		 * replace child with that mount.
-		 */
-		topper = find_topper(child);
-		if (topper)
-			list_add_tail(&topper->mnt_reparent, to_reparent);
+	/* Mark mounts that can be unmounted if not locked */
+	SET_MNT_MARK(mnt);
+	progress = true;
 
-		if (topper || list_empty(&child->mnt_mounts)) {
-			list_del_init(&child->mnt_child);
-			list_del_init(&child->mnt_reparent);
-			child->mnt.mnt_flags |= MNT_UMOUNT;
-			list_move_tail(&child->mnt_list, &mnt->mnt_list);
+	/* If a mount is without children and not locked umount it. */
+	if (!IS_MNT_LOCKED(mnt)) {
+		umount_one(mnt, to_umount);
+	} else {
+children:
+		list_move_tail(&mnt->mnt_umounting, to_restore);
+	}
+out:
+	return progress;
+}
+
+static void umount_list(struct list_head *to_umount,
+			struct list_head *to_restore)
+{
+	struct mount *mnt, *child, *tmp;
+	list_for_each_entry(mnt, to_umount, mnt_list) {
+		list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) {
+			/* topper? */
+			if (child->mnt_mountpoint == mnt->mnt.mnt_root)
+				list_move_tail(&child->mnt_umounting, to_restore);
+			else
+				umount_one(child, to_umount);
 		}
 	}
 }
 
-static void reparent_mounts(struct list_head *to_reparent)
+static void restore_mounts(struct list_head *to_restore)
 {
-	while (!list_empty(to_reparent)) {
+	/* Restore mounts to a clean working state */
+	while (!list_empty(to_restore)) {
 		struct mount *mnt, *parent;
 		struct mountpoint *mp;
 
-		mnt = list_first_entry(to_reparent, struct mount, mnt_reparent);
-		list_del_init(&mnt->mnt_reparent);
+		mnt = list_first_entry(to_restore, struct mount, mnt_umounting);
+		CLEAR_MNT_MARK(mnt);
+		list_del_init(&mnt->mnt_umounting);
 
-		/* Where should this mount be reparented to? */
+		/* Should this mount be reparented? */
 		mp = mnt->mnt_mp;
 		parent = mnt->mnt_parent;
 		while (parent->mnt.mnt_flags & MNT_UMOUNT) {
 			mp = parent->mnt_mp;
 			parent = parent->mnt_parent;
 		}
-
-		mnt_change_mountpoint(parent, mp, mnt);
+		if (parent != mnt->mnt_parent)
+			mnt_change_mountpoint(parent, mp, mnt);
 	}
 }
 
@@ -506,15 +515,34 @@ static void reparent_mounts(struct list_head *to_reparent)
 int propagate_umount(struct list_head *list)
 {
 	struct mount *mnt;
-	LIST_HEAD(to_reparent);
+	LIST_HEAD(to_restore);
+	LIST_HEAD(to_umount);
 
-	list_for_each_entry_reverse(mnt, list, mnt_list)
-		mark_umount_candidates(mnt);
+	list_for_each_entry(mnt, list, mnt_list) {
+		struct mount *parent = mnt->mnt_parent;
+		struct mount *m;
 
-	list_for_each_entry(mnt, list, mnt_list)
-		__propagate_umount(mnt, &to_reparent);
+		for (m = propagation_next(parent, parent); m;
+		     m = propagation_next(m, parent)) {
+			struct mount *child = __lookup_mnt(&m->mnt,
+							   mnt->mnt_mountpoint);
+			if (!child)
+				continue;
+
+			/* Check the child and parents while progress is made */
+			while (__propagate_umount(child,
+						  &to_umount, &to_restore)) {
+				/* Is the parent a umount candidate? */
+				child = child->mnt_parent;
+				if (list_empty(&child->mnt_umounting))
+					break;
+			}
+		}
+	}
 
-	reparent_mounts(&to_reparent);
+	umount_list(&to_umount, &to_restore);
+	restore_mounts(&to_restore);
+	list_splice_tail(&to_umount, list);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 296990deb389c7da21c78030376ba244dc1badf5 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 24 Oct 2016 17:25:19 -0500
Subject: mnt: Make propagate_umount less slow for overlapping mount
 propagation trees

Andrei Vagin pointed out that time to executue propagate_umount can go
non-linear (and take a ludicrious amount of time) when the mount
propogation trees of the mounts to be unmunted by a lazy unmount
overlap.

Make the walk of the mount propagation trees nearly linear by
remembering which mounts have already been visited, allowing
subsequent walks to detect when walking a mount propgation tree or a
subtree of a mount propgation tree would be duplicate work and to skip
them entirely.

Walk the list of mounts whose propgatation trees need to be traversed
from the mount highest in the mount tree to mounts lower in the mount
tree so that odds are higher that the code will walk the largest trees
first, allowing later tree walks to be skipped entirely.

Add cleanup_umount_visitation to remover the code's memory of which
mounts have been visited.

Add the functions last_slave and skip_propagation_subtree to allow
skipping appropriate parts of the mount propagation tree without
needing to change the logic of the rest of the code.

A script to generate overlapping mount propagation trees:

$ cat runs.h
set -e
mount -t tmpfs zdtm /mnt
mkdir -p /mnt/1 /mnt/2
mount -t tmpfs zdtm /mnt/1
mount --make-shared /mnt/1
mkdir /mnt/1/1

iteration=10
if [ -n "$1" ] ; then
	iteration=$1
fi

for i in $(seq $iteration); do
	mount --bind /mnt/1/1 /mnt/1/1
done

mount --rbind /mnt/1 /mnt/2

TIMEFORMAT='%Rs'
nr=$(( ( 2 ** ( $iteration + 1 ) ) + 1 ))
echo -n "umount -l /mnt/1 -> $nr        "
time umount -l /mnt/1

nr=$(cat /proc/self/mountinfo | grep zdtm | wc -l )
time umount -l /mnt/2

$ for i in $(seq 9 19); do echo $i; unshare -Urm bash ./run.sh $i; done

Here are the performance numbers with and without the patch:

     mhash |  8192   |  8192  | 1048576 | 1048576
    mounts | before  | after  |  before | after
    ------------------------------------------------
      1025 |  0.040s | 0.016s |  0.038s | 0.019s
      2049 |  0.094s | 0.017s |  0.080s | 0.018s
      4097 |  0.243s | 0.019s |  0.206s | 0.023s
      8193 |  1.202s | 0.028s |  1.562s | 0.032s
     16385 |  9.635s | 0.036s |  9.952s | 0.041s
     32769 | 60.928s | 0.063s | 44.321s | 0.064s
     65537 |         | 0.097s |         | 0.097s
    131073 |         | 0.233s |         | 0.176s
    262145 |         | 0.653s |         | 0.344s
    524289 |         | 2.305s |         | 0.735s
   1048577 |         | 7.107s |         | 2.603s

Andrei Vagin reports fixing the performance problem is part of the
work to fix CVE-2016-6213.

Cc: stable@vger.kernel.org
Fixes: a05964f3917c ("[PATCH] shared mounts handling: umount")
Reported-by: Andrei Vagin <avagin@openvz.org>
Reviewed-by: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/pnode.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 62 insertions(+), 1 deletion(-)

diff --git a/fs/pnode.c b/fs/pnode.c
index fbaca7df2eb0..53d411a371ce 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -24,6 +24,11 @@ static inline struct mount *first_slave(struct mount *p)
 	return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave);
 }
 
+static inline struct mount *last_slave(struct mount *p)
+{
+	return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave);
+}
+
 static inline struct mount *next_slave(struct mount *p)
 {
 	return list_entry(p->mnt_slave.next, struct mount, mnt_slave);
@@ -162,6 +167,19 @@ static struct mount *propagation_next(struct mount *m,
 	}
 }
 
+static struct mount *skip_propagation_subtree(struct mount *m,
+						struct mount *origin)
+{
+	/*
+	 * Advance m such that propagation_next will not return
+	 * the slaves of m.
+	 */
+	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
+		m = last_slave(m);
+
+	return m;
+}
+
 static struct mount *next_group(struct mount *m, struct mount *origin)
 {
 	while (1) {
@@ -505,6 +523,15 @@ static void restore_mounts(struct list_head *to_restore)
 	}
 }
 
+static void cleanup_umount_visitations(struct list_head *visited)
+{
+	while (!list_empty(visited)) {
+		struct mount *mnt =
+			list_first_entry(visited, struct mount, mnt_umounting);
+		list_del_init(&mnt->mnt_umounting);
+	}
+}
+
 /*
  * collect all mounts that receive propagation from the mount in @list,
  * and return these additional mounts in the same list.
@@ -517,11 +544,23 @@ int propagate_umount(struct list_head *list)
 	struct mount *mnt;
 	LIST_HEAD(to_restore);
 	LIST_HEAD(to_umount);
+	LIST_HEAD(visited);
 
-	list_for_each_entry(mnt, list, mnt_list) {
+	/* Find candidates for unmounting */
+	list_for_each_entry_reverse(mnt, list, mnt_list) {
 		struct mount *parent = mnt->mnt_parent;
 		struct mount *m;
 
+		/*
+		 * If this mount has already been visited it is known that it's
+		 * entire peer group and all of their slaves in the propagation
+		 * tree for the mountpoint has already been visited and there is
+		 * no need to visit them again.
+		 */
+		if (!list_empty(&mnt->mnt_umounting))
+			continue;
+
+		list_add_tail(&mnt->mnt_umounting, &visited);
 		for (m = propagation_next(parent, parent); m;
 		     m = propagation_next(m, parent)) {
 			struct mount *child = __lookup_mnt(&m->mnt,
@@ -529,6 +568,27 @@ int propagate_umount(struct list_head *list)
 			if (!child)
 				continue;
 
+			if (!list_empty(&child->mnt_umounting)) {
+				/*
+				 * If the child has already been visited it is
+				 * know that it's entire peer group and all of
+				 * their slaves in the propgation tree for the
+				 * mountpoint has already been visited and there
+				 * is no need to visit this subtree again.
+				 */
+				m = skip_propagation_subtree(m, parent);
+				continue;
+			} else if (child->mnt.mnt_flags & MNT_UMOUNT) {
+				/*
+				 * We have come accross an partially unmounted
+				 * mount in list that has not been visited yet.
+				 * Remember it has been visited and continue
+				 * about our merry way.
+				 */
+				list_add_tail(&child->mnt_umounting, &visited);
+				continue;
+			}
+
 			/* Check the child and parents while progress is made */
 			while (__propagate_umount(child,
 						  &to_umount, &to_restore)) {
@@ -542,6 +602,7 @@ int propagate_umount(struct list_head *list)
 
 	umount_list(&to_umount, &to_restore);
 	restore_mounts(&to_restore);
+	cleanup_umount_visitations(&visited);
 	list_splice_tail(&to_umount, list);
 
 	return 0;
-- 
cgit v1.2.3