3.16.41-rc1 review patch. If anyone has any objections, please let me know.
------------------
From: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
commit d29216842a85c7970c536108e093963f02714498 upstream.
CAI Qian <caiqian@xxxxxxxxxx> pointed out that the semantics
of shared subtrees make it possible to create an exponentially
increasing number of mounts in a mount namespace.
mkdir /tmp/1 /tmp/2
mount --make-rshared /
for i in $(seq 1 20) ; do mount --bind /tmp/1 /tmp/2 ; done
Will create create 2^20 or 1048576 mounts, which is a practical problem
as some people have managed to hit this by accident.
As such CVE-2016-6213 was assigned.
Ian Kent <raven@xxxxxxxxxx> described the situation for autofs users
as follows:
> The number of mounts for direct mount maps is usually not very large because of
> the way they are implemented, large direct mount maps can have performance
> problems. There can be anywhere from a few (likely case a few hundred) to less
> than 10000, plus mounts that have been triggered and not yet expired.
>
> Indirect mounts have one autofs mount at the root plus the number of mounts that
> have been triggered and not yet expired.
>
> The number of autofs indirect map entries can range from a few to the common
> case of several thousand and in rare cases up to between 30000 and 50000. I've
> not heard of people with maps larger than 50000 entries.
>
> The larger the number of map entries the greater the possibility for a large
> number of active mounts so it's not hard to expect cases of a 1000 or somewhat
> more active mounts.
So I am setting the default number of mounts allowed per mount
namespace at 100,000. This is more than enough for any use case I
know of, but small enough to quickly stop an exponential increase
in mounts. Which should be perfect to catch misconfigurations and
malfunctioning programs.
For anyone who needs a higher limit this can be changed by writing
to the new /proc/sys/fs/mount-max sysctl.
Tested-by: CAI Qian <caiqian@xxxxxxxxxx>
Signed-off-by: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
[bwh: Backported to 3.16:
- Use ACCESS_ONCE() instead of READ_ONCE()
- Adjust context]
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
Documentation/sysctl/fs.txt | 7 +++++++
fs/mount.h | 2 ++
fs/namespace.c | 49 ++++++++++++++++++++++++++++++++++++++++++++-
fs/pnode.c | 2 +-
fs/pnode.h | 1 +
include/linux/mount.h | 2 ++
kernel/sysctl.c | 9 +++++++++
7 files changed, 70 insertions(+), 2 deletions(-)
--- a/Documentation/sysctl/fs.txt
+++ b/Documentation/sysctl/fs.txt
@@ -265,6 +265,13 @@ aio-nr can grow to.
==============================================================
+mount-max:
+
+This denotes the maximum number of mounts that may exist
+in a mount namespace.
+
+==============================================================
+
2. /proc/sys/fs/binfmt_misc
----------------------------------------------------------
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -11,6 +11,8 @@ struct mnt_namespace {
u64 seq; /* Sequence number to prevent loops */
wait_queue_head_t poll;
u64 event;
+ unsigned int mounts; /* # of mounts in the namespace */
+ unsigned int pending_mounts;
};
struct mnt_pcp {
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -27,6 +27,9 @@
#include "pnode.h"
#include "internal.h"
+/* Maximum number of mounts in a mount namespace */
+unsigned int sysctl_mount_max __read_mostly = 100000;
+
static unsigned int m_hash_mask __read_mostly;
static unsigned int m_hash_shift __read_mostly;
static unsigned int mp_hash_mask __read_mostly;
@@ -811,6 +814,9 @@ static void commit_tree(struct mount *mn
list_splice(&head, n->list.prev);
+ n->mounts += n->pending_mounts;
+ n->pending_mounts = 0;
+
attach_shadowed(mnt, parent, shadows);
touch_mnt_namespace(n);
}
@@ -1284,9 +1290,14 @@ static void umount_tree(struct mount *mn
propagate_umount(&tmp_list);
hlist_for_each_entry(p, &tmp_list, mnt_hash) {
+ struct mnt_namespace *ns;
list_del_init(&p->mnt_expire);
list_del_init(&p->mnt_list);
- __touch_mnt_namespace(p->mnt_ns);
+ ns = p->mnt_ns;
+ if (ns) {
+ ns->mounts--;
+ __touch_mnt_namespace(ns);
+ }
p->mnt_ns = NULL;
if (how & UMOUNT_SYNC)
p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
@@ -1641,6 +1652,28 @@ static int invent_group_ids(struct mount
return 0;
}
+int count_mounts(struct mnt_namespace *ns, struct mount *mnt)
+{
+ unsigned int max = ACCESS_ONCE(sysctl_mount_max);
+ unsigned int mounts = 0, old, pending, sum;
+ struct mount *p;
+
+ for (p = mnt; p; p = next_mnt(p, mnt))
+ mounts++;
+
+ old = ns->mounts;
+ pending = ns->pending_mounts;
+ sum = old + pending;
+ if ((old > sum) ||
+ (pending > sum) ||
+ (max < sum) ||
+ (mounts > (max - sum)))
+ return -ENOSPC;
+
+ ns->pending_mounts = pending + mounts;
+ return 0;
+}
+
/*
* @source_mnt : mount tree to be attached
* @nd : place the mount tree @source_mnt is attached
@@ -1710,10 +1743,18 @@ static int attach_recursive_mnt(struct m
struct path *parent_path)
{
HLIST_HEAD(tree_list);
+ struct mnt_namespace *ns = dest_mnt->mnt_ns;
struct mount *child, *p;
struct hlist_node *n;
int err;
+ /* Is there space to add these mounts to the mount namespace? */
+ if (!parent_path) {
+ err = count_mounts(ns, source_mnt);
+ if (err)
+ goto out;
+ }
+
if (IS_MNT_SHARED(dest_mnt)) {
err = invent_group_ids(source_mnt, true);
if (err)
@@ -1750,11 +1791,13 @@ static int attach_recursive_mnt(struct m
out_cleanup_ids:
while (!hlist_empty(&tree_list)) {
child = hlist_entry(tree_list.first, struct mount, mnt_hash);
+ child->mnt_parent->mnt_ns->pending_mounts = 0;
umount_tree(child, UMOUNT_SYNC);
}
unlock_mount_hash();
cleanup_group_ids(source_mnt, NULL);
out:
+ ns->pending_mounts = 0;
return err;
}
@@ -2586,6 +2629,8 @@ static struct mnt_namespace *alloc_mnt_n
init_waitqueue_head(&new_ns->poll);
new_ns->event = 0;
new_ns->user_ns = get_user_ns(user_ns);
+ new_ns->mounts = 0;
+ new_ns->pending_mounts = 0;
return new_ns;
}
@@ -2635,6 +2680,7 @@ struct mnt_namespace *copy_mnt_ns(unsign
q = new;
while (p) {
q->mnt_ns = new_ns;
+ new_ns->mounts++;
if (new_fs) {
if (&p->mnt == new_fs->root.mnt) {
new_fs->root.mnt = mntget(&q->mnt);
@@ -2673,6 +2719,7 @@ static struct mnt_namespace *create_mnt_
struct mount *mnt = real_mount(m);
mnt->mnt_ns = new_ns;
new_ns->root = mnt;
+ new_ns->mounts++;
list_add(&mnt->mnt_list, &new_ns->list);
} else {
mntput(m);
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -258,7 +258,7 @@ static int propagate_one(struct mount *m
read_sequnlock_excl(&mount_lock);
}
hlist_add_head(&child->mnt_hash, list);
- return 0;
+ return count_mounts(m->mnt_ns, child);
}
/*
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -50,4 +50,5 @@ void mnt_set_mountpoint(struct mount *,
struct mount *copy_tree(struct mount *, struct dentry *, int);
bool is_path_reachable(struct mount *, struct dentry *,
const struct path *root);
+int count_mounts(struct mnt_namespace *ns, struct mount *mnt);
#endif /* _LINUX_PNODE_H */
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -91,4 +91,6 @@ extern void mark_mounts_for_expiry(struc
extern dev_t name_to_dev_t(char *name);
+extern unsigned int sysctl_mount_max;
+
#endif /* _LINUX_MOUNT_H */
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -63,6 +63,7 @@
#include <linux/binfmts.h>
#include <linux/sched/sysctl.h>
#include <linux/kexec.h>
+#include <linux/mount.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
@@ -1685,6 +1686,14 @@ static struct ctl_table fs_table[] = {
.mode = 0644,
.proc_handler = proc_doulongvec_minmax,
},
+ {
+ .procname = "mount-max",
+ .data = &sysctl_mount_max,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
+ },
{ }
};