linux/fs/namespace.c

3215 lines
78 KiB
C
Raw Normal View History

/*
* linux/fs/namespace.c
*
* (C) Copyright Al Viro 2000, 2001
* Released under GPL v2.
*
* Based on code from fs/super.c, copyright Linus Torvalds and others.
* Heavily rewritten.
*/
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/capability.h>
#include <linux/mnt_namespace.h>
#include <linux/user_namespace.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/idr.h>
#include <linux/init.h> /* init_rootfs */
#include <linux/fs_struct.h> /* get_fs_root et.al. */
#include <linux/fsnotify.h> /* fsnotify_vfsmount_delete */
#include <linux/uaccess.h>
#include <linux/proc_ns.h>
#include <linux/magic.h>
#include <linux/bootmem.h>
#include <linux/task_work.h>
#include "pnode.h"
#include "internal.h"
static unsigned int m_hash_mask __read_mostly;
static unsigned int m_hash_shift __read_mostly;
static unsigned int mp_hash_mask __read_mostly;
static unsigned int mp_hash_shift __read_mostly;
static __initdata unsigned long mhash_entries;
static int __init set_mhash_entries(char *str)
{
if (!str)
return 0;
mhash_entries = simple_strtoul(str, &str, 0);
return 1;
}
__setup("mhash_entries=", set_mhash_entries);
static __initdata unsigned long mphash_entries;
static int __init set_mphash_entries(char *str)
{
if (!str)
return 0;
mphash_entries = simple_strtoul(str, &str, 0);
return 1;
}
__setup("mphash_entries=", set_mphash_entries);
static u64 event;
static DEFINE_IDA(mnt_id_ida);
static DEFINE_IDA(mnt_group_ida);
static DEFINE_SPINLOCK(mnt_id_lock);
static int mnt_id_start = 0;
static int mnt_group_start = 1;
static struct hlist_head *mount_hashtable __read_mostly;
static struct hlist_head *mountpoint_hashtable __read_mostly;
static struct kmem_cache *mnt_cache __read_mostly;
static DECLARE_RWSEM(namespace_sem);
/* /sys/fs */
struct kobject *fs_kobj;
EXPORT_SYMBOL_GPL(fs_kobj);
/*
* vfsmount lock may be taken for read to prevent changes to the
* vfsmount hash, ie. during mountpoint lookups or walking back
* up the tree.
*
* It should be taken for write in all cases where the vfsmount
* tree or hash is modified or when a vfsmount structure is modified.
*/
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
__cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock);
static inline struct hlist_head *m_hash(struct vfsmount *mnt, struct dentry *dentry)
{
unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES);
tmp += ((unsigned long)dentry / L1_CACHE_BYTES);
tmp = tmp + (tmp >> m_hash_shift);
return &mount_hashtable[tmp & m_hash_mask];
}
static inline struct hlist_head *mp_hash(struct dentry *dentry)
{
unsigned long tmp = ((unsigned long)dentry / L1_CACHE_BYTES);
tmp = tmp + (tmp >> mp_hash_shift);
return &mountpoint_hashtable[tmp & mp_hash_mask];
}
/*
* allocation is serialized by namespace_sem, but we need the spinlock to
* serialize with freeing.
*/
static int mnt_alloc_id(struct mount *mnt)
{
int res;
retry:
ida_pre_get(&mnt_id_ida, GFP_KERNEL);
spin_lock(&mnt_id_lock);
res = ida_get_new_above(&mnt_id_ida, mnt_id_start, &mnt->mnt_id);
if (!res)
mnt_id_start = mnt->mnt_id + 1;
spin_unlock(&mnt_id_lock);
if (res == -EAGAIN)
goto retry;
return res;
}
static void mnt_free_id(struct mount *mnt)
{
int id = mnt->mnt_id;
spin_lock(&mnt_id_lock);
ida_remove(&mnt_id_ida, id);
if (mnt_id_start > id)
mnt_id_start = id;
spin_unlock(&mnt_id_lock);
}
/*
* Allocate a new peer group ID
*
* mnt_group_ida is protected by namespace_sem
*/
static int mnt_alloc_group_id(struct mount *mnt)
{
int res;
if (!ida_pre_get(&mnt_group_ida, GFP_KERNEL))
return -ENOMEM;
res = ida_get_new_above(&mnt_group_ida,
mnt_group_start,
&mnt->mnt_group_id);
if (!res)
mnt_group_start = mnt->mnt_group_id + 1;
return res;
}
/*
* Release a peer group ID
*/
void mnt_release_group_id(struct mount *mnt)
{
int id = mnt->mnt_group_id;
ida_remove(&mnt_group_ida, id);
if (mnt_group_start > id)
mnt_group_start = id;
mnt->mnt_group_id = 0;
}
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>
2011-01-07 06:50:11 +00:00
/*
* vfsmount lock must be held for read
*/
static inline void mnt_add_count(struct mount *mnt, int n)
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>
2011-01-07 06:50:11 +00:00
{
#ifdef CONFIG_SMP
this_cpu_add(mnt->mnt_pcp->mnt_count, n);
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>
2011-01-07 06:50:11 +00:00
#else
preempt_disable();
mnt->mnt_count += n;
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>
2011-01-07 06:50:11 +00:00
preempt_enable();
#endif
}
/*
* vfsmount lock must be held for write
*/
unsigned int mnt_get_count(struct mount *mnt)
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>
2011-01-07 06:50:11 +00:00
{
#ifdef CONFIG_SMP
unsigned int count = 0;
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>
2011-01-07 06:50:11 +00:00
int cpu;
for_each_possible_cpu(cpu) {
count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_count;
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>
2011-01-07 06:50:11 +00:00
}
return count;
#else
return mnt->mnt_count;
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>
2011-01-07 06:50:11 +00:00
#endif
}
static void drop_mountpoint(struct fs_pin *p)
{
struct mount *m = container_of(p, struct mount, mnt_umount);
dput(m->mnt_ex_mountpoint);
pin_remove(p);
mntput(&m->mnt);
}
static struct mount *alloc_vfsmnt(const char *name)
{
struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
if (mnt) {
int err;
err = mnt_alloc_id(mnt);
if (err)
goto out_free_cache;
if (name) {
mnt->mnt_devname = kstrdup_const(name, GFP_KERNEL);
if (!mnt->mnt_devname)
goto out_free_id;
}
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>
2011-01-07 06:50:11 +00:00
#ifdef CONFIG_SMP
mnt->mnt_pcp = alloc_percpu(struct mnt_pcp);
if (!mnt->mnt_pcp)
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>
2011-01-07 06:50:11 +00:00
goto out_free_devname;
this_cpu_add(mnt->mnt_pcp->mnt_count, 1);
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>
2011-01-07 06:50:11 +00:00
#else
mnt->mnt_count = 1;
mnt->mnt_writers = 0;
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>
2011-01-07 06:50:11 +00:00
#endif
INIT_HLIST_NODE(&mnt->mnt_hash);
INIT_LIST_HEAD(&mnt->mnt_child);
INIT_LIST_HEAD(&mnt->mnt_mounts);
INIT_LIST_HEAD(&mnt->mnt_list);
INIT_LIST_HEAD(&mnt->mnt_expire);
INIT_LIST_HEAD(&mnt->mnt_share);
INIT_LIST_HEAD(&mnt->mnt_slave_list);
INIT_LIST_HEAD(&mnt->mnt_slave);
INIT_HLIST_NODE(&mnt->mnt_mp_list);
#ifdef CONFIG_FSNOTIFY
INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
#endif
init_fs_pin(&mnt->mnt_umount, drop_mountpoint);
}
return mnt;
#ifdef CONFIG_SMP
out_free_devname:
kfree_const(mnt->mnt_devname);
#endif
out_free_id:
mnt_free_id(mnt);
out_free_cache:
kmem_cache_free(mnt_cache, mnt);
return NULL;
}
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
/*
* Most r/o checks on a fs are for operations that take
* discrete amounts of time, like a write() or unlink().
* We must keep track of when those operations start
* (for permission checks) and when they end, so that
* we can determine when writes are able to occur to
* a filesystem.
*/
/*
* __mnt_is_readonly: check whether a mount is read-only
* @mnt: the mount to check for its write status
*
* This shouldn't be used directly ouside of the VFS.
* It does not guarantee that the filesystem will stay
* r/w, just that it is right *now*. This can not and
* should not be used in place of IS_RDONLY(inode).
* mnt_want/drop_write() will _keep_ the filesystem
* r/w.
*/
int __mnt_is_readonly(struct vfsmount *mnt)
{
if (mnt->mnt_flags & MNT_READONLY)
return 1;
if (mnt->mnt_sb->s_flags & MS_RDONLY)
return 1;
return 0;
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
}
EXPORT_SYMBOL_GPL(__mnt_is_readonly);
static inline void mnt_inc_writers(struct mount *mnt)
{
#ifdef CONFIG_SMP
this_cpu_inc(mnt->mnt_pcp->mnt_writers);
#else
mnt->mnt_writers++;
#endif
}
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
static inline void mnt_dec_writers(struct mount *mnt)
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
{
#ifdef CONFIG_SMP
this_cpu_dec(mnt->mnt_pcp->mnt_writers);
#else
mnt->mnt_writers--;
#endif
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
}
static unsigned int mnt_get_writers(struct mount *mnt)
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
{
#ifdef CONFIG_SMP
unsigned int count = 0;
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
int cpu;
for_each_possible_cpu(cpu) {
count += per_cpu_ptr(mnt->mnt_pcp, cpu)->mnt_writers;
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
}
return count;
#else
return mnt->mnt_writers;
#endif
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
}
static int mnt_is_readonly(struct vfsmount *mnt)
{
if (mnt->mnt_sb->s_readonly_remount)
return 1;
/* Order wrt setting s_flags/s_readonly_remount in do_remount() */
smp_rmb();
return __mnt_is_readonly(mnt);
}
/*
* Most r/o & frozen checks on a fs are for operations that take discrete
* amounts of time, like a write() or unlink(). We must keep track of when
* those operations start (for permission checks) and when they end, so that we
* can determine when writes are able to occur to a filesystem.
*/
/**
* __mnt_want_write - get write access to a mount without freeze protection
* @m: the mount on which to take a write
*
* This tells the low-level filesystem that a write is about to be performed to
* it, and makes sure that writes are allowed (mnt it read-write) before
* returning success. This operation does not protect against filesystem being
* frozen. When the write operation is finished, __mnt_drop_write() must be
* called. This is effectively a refcount.
*/
int __mnt_want_write(struct vfsmount *m)
{
struct mount *mnt = real_mount(m);
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
int ret = 0;
preempt_disable();
mnt_inc_writers(mnt);
/*
* The store to mnt_inc_writers must be visible before we pass
* MNT_WRITE_HOLD loop below, so that the slowpath can see our
* incremented count after it has set MNT_WRITE_HOLD.
*/
smp_mb();
while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD)
cpu_relax();
/*
* After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will
* be set to match its requirements. So we must not load that until
* MNT_WRITE_HOLD is cleared.
*/
smp_rmb();
if (mnt_is_readonly(m)) {
mnt_dec_writers(mnt);
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
ret = -EROFS;
}
preempt_enable();
return ret;
}
/**
* mnt_want_write - get write access to a mount
* @m: the mount on which to take a write
*
* This tells the low-level filesystem that a write is about to be performed to
* it, and makes sure that writes are allowed (mount is read-write, filesystem
* is not frozen) before returning success. When the write operation is
* finished, mnt_drop_write() must be called. This is effectively a refcount.
*/
int mnt_want_write(struct vfsmount *m)
{
int ret;
sb_start_write(m->mnt_sb);
ret = __mnt_want_write(m);
if (ret)
sb_end_write(m->mnt_sb);
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
return ret;
}
EXPORT_SYMBOL_GPL(mnt_want_write);
/**
* mnt_clone_write - get write access to a mount
* @mnt: the mount on which to take a write
*
* This is effectively like mnt_want_write, except
* it must only be used to take an extra write reference
* on a mountpoint that we already know has a write reference
* on it. This allows some optimisation.
*
* After finished, mnt_drop_write must be called as usual to
* drop the reference.
*/
int mnt_clone_write(struct vfsmount *mnt)
{
/* superblock may be r/o */
if (__mnt_is_readonly(mnt))
return -EROFS;
preempt_disable();
mnt_inc_writers(real_mount(mnt));
preempt_enable();
return 0;
}
EXPORT_SYMBOL_GPL(mnt_clone_write);
/**
* __mnt_want_write_file - get write access to a file's mount
* @file: the file who's mount on which to take a write
*
* This is like __mnt_want_write, but it takes a file and can
* do some optimisations if the file is open for write already
*/
int __mnt_want_write_file(struct file *file)
{
if (!(file->f_mode & FMODE_WRITER))
return __mnt_want_write(file->f_path.mnt);
else
return mnt_clone_write(file->f_path.mnt);
}
/**
* mnt_want_write_file - get write access to a file's mount
* @file: the file who's mount on which to take a write
*
* This is like mnt_want_write, but it takes a file and can
* do some optimisations if the file is open for write already
*/
int mnt_want_write_file(struct file *file)
{
int ret;
sb_start_write(file->f_path.mnt->mnt_sb);
ret = __mnt_want_write_file(file);
if (ret)
sb_end_write(file->f_path.mnt->mnt_sb);
return ret;
}
EXPORT_SYMBOL_GPL(mnt_want_write_file);
/**
* __mnt_drop_write - give up write access to a mount
* @mnt: the mount on which to give up write access
*
* Tells the low-level filesystem that we are done
* performing writes to it. Must be matched with
* __mnt_want_write() call above.
*/
void __mnt_drop_write(struct vfsmount *mnt)
{
preempt_disable();
mnt_dec_writers(real_mount(mnt));
preempt_enable();
}
/**
* mnt_drop_write - give up write access to a mount
* @mnt: the mount on which to give up write access
*
* Tells the low-level filesystem that we are done performing writes to it and
* also allows filesystem to be frozen again. Must be matched with
* mnt_want_write() call above.
*/
void mnt_drop_write(struct vfsmount *mnt)
{
__mnt_drop_write(mnt);
sb_end_write(mnt->mnt_sb);
}
EXPORT_SYMBOL_GPL(mnt_drop_write);
void __mnt_drop_write_file(struct file *file)
{
__mnt_drop_write(file->f_path.mnt);
}
void mnt_drop_write_file(struct file *file)
{
mnt_drop_write(file->f_path.mnt);
}
EXPORT_SYMBOL(mnt_drop_write_file);
static int mnt_make_readonly(struct mount *mnt)
{
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
int ret = 0;
lock_mount_hash();
mnt->mnt.mnt_flags |= MNT_WRITE_HOLD;
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
/*
* After storing MNT_WRITE_HOLD, we'll read the counters. This store
* should be visible before we do.
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
*/
smp_mb();
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
/*
* With writers on hold, if this value is zero, then there are
* definitely no active writers (although held writers may subsequently
* increment the count, they'll have to wait, and decrement it after
* seeing MNT_READONLY).
*
* It is OK to have counter incremented on one CPU and decremented on
* another: the sum will add up correctly. The danger would be when we
* sum up each counter, if we read a counter before it is incremented,
* but then read another CPU's count which it has been subsequently
* decremented from -- we would see more decrements than we should.
* MNT_WRITE_HOLD protects against this scenario, because
* mnt_want_write first increments count, then smp_mb, then spins on
* MNT_WRITE_HOLD, so it can't be decremented by another CPU while
* we're counting up here.
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
*/
if (mnt_get_writers(mnt) > 0)
ret = -EBUSY;
else
mnt->mnt.mnt_flags |= MNT_READONLY;
/*
* MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers
* that become unheld will see MNT_READONLY.
*/
smp_wmb();
mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD;
unlock_mount_hash();
[PATCH] r/o bind mounts: track numbers of writers to mounts This is the real meat of the entire series. It actually implements the tracking of the number of writers to a mount. However, it causes scalability problems because there can be hundreds of cpus doing open()/close() on files on the same mnt at the same time. Even an atomic_t in the mnt has massive scalaing problems because the cacheline gets so terribly contended. This uses a statically-allocated percpu variable. All want/drop operations are local to a cpu as long that cpu operates on the same mount, and there are no writer count imbalances. Writer count imbalances happen when a write is taken on one cpu, and released on another, like when an open/close pair is performed on two Upon a remount,ro request, all of the data from the percpu variables is collected (expensive, but very rare) and we determine if there are any outstanding writers to the mount. I've written a little benchmark to sit in a loop for a couple of seconds in several cpus in parallel doing open/write/close loops. http://sr71.net/~dave/linux/openbench.c The code in here is a a worst-possible case for this patch. It does opens on a _pair_ of files in two different mounts in parallel. This should cause my code to lose its "operate on the same mount" optimization completely. This worst-case scenario causes a 3% degredation in the benchmark. I could probably get rid of even this 3%, but it would be more complex than what I have here, and I think this is getting into acceptable territory. In practice, I expect writing more than 3 bytes to a file, as well as disk I/O to mask any effects that this has. (To get rid of that 3%, we could have an #defined number of mounts in the percpu variable. So, instead of a CPU getting operate only on percpu data when it accesses only one mount, it could stay on percpu data when it only accesses N or fewer mounts.) [AV] merged fix for __clear_mnt_mount() stepping on freed vfsmount Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@infradead.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2008-02-15 22:37:59 +00:00
return ret;
}
static void __mnt_unmake_readonly(struct mount *mnt)
{
lock_mount_hash();
mnt->mnt.mnt_flags &= ~MNT_READONLY;
unlock_mount_hash();
}
int sb_prepare_remount_readonly(struct super_block *sb)
{
struct mount *mnt;
int err = 0;
/* Racy optimization. Recheck the counter under MNT_WRITE_HOLD */
if (atomic_long_read(&sb->s_remove_count))
return -EBUSY;
lock_mount_hash();
list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) {
if (!(mnt->mnt.mnt_flags & MNT_READONLY)) {
mnt->mnt.mnt_flags |= MNT_WRITE_HOLD;
smp_mb();
if (mnt_get_writers(mnt) > 0) {
err = -EBUSY;
break;
}
}
}
if (!err && atomic_long_read(&sb->s_remove_count))
err = -EBUSY;
if (!err) {
sb->s_readonly_remount = 1;
smp_wmb();
}
list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) {
if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD)
mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD;
}
unlock_mount_hash();
return err;
}
static void free_vfsmnt(struct mount *mnt)
{
kfree_const(mnt->mnt_devname);
#ifdef CONFIG_SMP
free_percpu(mnt->mnt_pcp);
#endif
kmem_cache_free(mnt_cache, mnt);
}
static void delayed_free_vfsmnt(struct rcu_head *head)
{
free_vfsmnt(container_of(head, struct mount, mnt_rcu));
}
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
/* call under rcu_read_lock */
bool legitimize_mnt(struct vfsmount *bastard, unsigned seq)
{
struct mount *mnt;
if (read_seqretry(&mount_lock, seq))
return false;
if (bastard == NULL)
return true;
mnt = real_mount(bastard);
mnt_add_count(mnt, 1);
if (likely(!read_seqretry(&mount_lock, seq)))
return true;
if (bastard->mnt_flags & MNT_SYNC_UMOUNT) {
mnt_add_count(mnt, -1);
return false;
}
rcu_read_unlock();
mntput(bastard);
rcu_read_lock();
return false;
}
/*
* find the first mount at @dentry on vfsmount @mnt.
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
* call under rcu_read_lock()
*/
struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
{
struct hlist_head *head = m_hash(mnt, dentry);
struct mount *p;
hlist_for_each_entry_rcu(p, head, mnt_hash)
if (&p->mnt_parent->mnt == mnt && p->mnt_mountpoint == dentry)
return p;
return NULL;
}
/*
* find the last mount at @dentry on vfsmount @mnt.
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
* mount_lock must be held.
*/
struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
{
struct mount *p, *res;
res = p = __lookup_mnt(mnt, dentry);
if (!p)
goto out;
hlist_for_each_entry_continue(p, mnt_hash) {
if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry)
break;
res = p;
}
out:
return res;
}
/*
* lookup_mnt - Return the first child mount mounted at path
*
* "First" means first mounted chronologically. If you create the
* following mounts:
*
* mount /dev/sda1 /mnt
* mount /dev/sda2 /mnt
* mount /dev/sda3 /mnt
*
* Then lookup_mnt() on the base /mnt dentry in the root mount will
* return successively the root dentry and vfsmount of /dev/sda1, then
* /dev/sda2, then /dev/sda3, then NULL.
*
* lookup_mnt takes a reference to the found vfsmount.
*/
struct vfsmount *lookup_mnt(struct path *path)
{
struct mount *child_mnt;
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
struct vfsmount *m;
unsigned seq;
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
rcu_read_lock();
do {
seq = read_seqbegin(&mount_lock);
child_mnt = __lookup_mnt(path->mnt, path->dentry);
m = child_mnt ? &child_mnt->mnt : NULL;
} while (!legitimize_mnt(m, seq));
rcu_read_unlock();
return m;
}
2013-10-05 02:15:13 +00:00
/*
* __is_local_mountpoint - Test to see if dentry is a mountpoint in the
* current mount namespace.
*
* The common case is dentries are not mountpoints at all and that
* test is handled inline. For the slow case when we are actually
* dealing with a mountpoint of some kind, walk through all of the
* mounts in the current mount namespace and test to see if the dentry
* is a mountpoint.
*
* The mount_hashtable is not usable in the context because we
* need to identify all mounts that may be in the current mount
* namespace not just a mount that happens to have some specified
* parent mount.
*/
bool __is_local_mountpoint(struct dentry *dentry)
{
struct mnt_namespace *ns = current->nsproxy->mnt_ns;
struct mount *mnt;
bool is_covered = false;
if (!d_mountpoint(dentry))
goto out;
down_read(&namespace_sem);
list_for_each_entry(mnt, &ns->list, mnt_list) {
is_covered = (mnt->mnt_mountpoint == dentry);
if (is_covered)
break;
}
up_read(&namespace_sem);
out:
return is_covered;
}
static struct mountpoint *lookup_mountpoint(struct dentry *dentry)
{
struct hlist_head *chain = mp_hash(dentry);
struct mountpoint *mp;
hlist_for_each_entry(mp, chain, m_hash) {
if (mp->m_dentry == dentry) {
/* might be worth a WARN_ON() */
if (d_unlinked(dentry))
return ERR_PTR(-ENOENT);
mp->m_count++;
return mp;
}
}
return NULL;
}
static struct mountpoint *new_mountpoint(struct dentry *dentry)
{
struct hlist_head *chain = mp_hash(dentry);
struct mountpoint *mp;
int ret;
mp = kmalloc(sizeof(struct mountpoint), GFP_KERNEL);
if (!mp)
return ERR_PTR(-ENOMEM);
ret = d_set_mounted(dentry);
if (ret) {
kfree(mp);
return ERR_PTR(ret);
}
mp->m_dentry = dentry;
mp->m_count = 1;
hlist_add_head(&mp->m_hash, chain);
INIT_HLIST_HEAD(&mp->m_list);
return mp;
}
static void put_mountpoint(struct mountpoint *mp)
{
if (!--mp->m_count) {
struct dentry *dentry = mp->m_dentry;
BUG_ON(!hlist_empty(&mp->m_list));
spin_lock(&dentry->d_lock);
dentry->d_flags &= ~DCACHE_MOUNTED;
spin_unlock(&dentry->d_lock);
hlist_del(&mp->m_hash);
kfree(mp);
}
}
static inline int check_mnt(struct mount *mnt)
{
return mnt->mnt_ns == current->nsproxy->mnt_ns;
}
/*
* vfsmount lock must be held for write
*/
static void touch_mnt_namespace(struct mnt_namespace *ns)
{
if (ns) {
ns->event = ++event;
wake_up_interruptible(&ns->poll);
}
}
/*
* vfsmount lock must be held for write
*/
static void __touch_mnt_namespace(struct mnt_namespace *ns)
{
if (ns && ns->event != event) {
ns->event = event;
wake_up_interruptible(&ns->poll);
}
}
/*
* vfsmount lock must be held for write
*/
static void detach_mnt(struct mount *mnt, struct path *old_path)
{
old_path->dentry = mnt->mnt_mountpoint;
old_path->mnt = &mnt->mnt_parent->mnt;
mnt->mnt_parent = mnt;
mnt->mnt_mountpoint = mnt->mnt.mnt_root;
list_del_init(&mnt->mnt_child);
hlist_del_init_rcu(&mnt->mnt_hash);
hlist_del_init(&mnt->mnt_mp_list);
put_mountpoint(mnt->mnt_mp);
mnt->mnt_mp = NULL;
}
/*
* vfsmount lock must be held for write
*/
void mnt_set_mountpoint(struct mount *mnt,
struct mountpoint *mp,
struct mount *child_mnt)
{
mp->m_count++;
mnt_add_count(mnt, 1); /* essentially, that's mntget */
child_mnt->mnt_mountpoint = dget(mp->m_dentry);
child_mnt->mnt_parent = mnt;
child_mnt->mnt_mp = mp;
hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list);
}
/*
* vfsmount lock must be held for write
*/
static void attach_mnt(struct mount *mnt,
struct mount *parent,
struct mountpoint *mp)
{
mnt_set_mountpoint(parent, mp, mnt);
hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry));
list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
}
static void attach_shadowed(struct mount *mnt,
struct mount *parent,
struct mount *shadows)
{
if (shadows) {
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs Pull vfs updates from Al Viro: "Stuff in here: - acct.c fixes and general rework of mnt_pin mechanism. That allows to go for delayed-mntput stuff, which will permit mntput() on deep stack without worrying about stack overflows - fs shutdown will happen on shallow stack. IOW, we can do Eric's umount-on-rmdir series without introducing tons of stack overflows on new mntput() call chains it introduces. - Bruce's d_splice_alias() patches - more Miklos' rename() stuff. - a couple of regression fixes (stable fodder, in the end of branch) and a fix for API idiocy in iov_iter.c. There definitely will be another pile, maybe even two. I'd like to get Eric's series in this time, but even if we miss it, it'll go right in the beginning of for-next in the next cycle - the tricky part of prereqs is in this pile" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (40 commits) fix copy_tree() regression __generic_file_write_iter(): fix handling of sync error after DIO switch iov_iter_get_pages() to passing maximal number of pages fs: mark __d_obtain_alias static dcache: d_splice_alias should detect loops exportfs: update Exporting documentation dcache: d_find_alias needn't recheck IS_ROOT && DCACHE_DISCONNECTED dcache: remove unused d_find_alias parameter dcache: d_obtain_alias callers don't all want DISCONNECTED dcache: d_splice_alias should ignore DCACHE_DISCONNECTED dcache: d_splice_alias mustn't create directory aliases dcache: close d_move race in d_splice_alias dcache: move d_splice_alias namei: trivial fix to vfs_rename_dir comment VFS: allow ->d_manage() to declare -EISDIR in rcu_walk mode. cifs: support RENAME_NOREPLACE hostfs: support rename flags shmem: support RENAME_EXCHANGE shmem: support RENAME_NOREPLACE btrfs: add RENAME_NOREPLACE ...
2014-08-11 18:44:11 +00:00
hlist_add_behind_rcu(&mnt->mnt_hash, &shadows->mnt_hash);
list_add(&mnt->mnt_child, &shadows->mnt_child);
} else {
hlist_add_head_rcu(&mnt->mnt_hash,
m_hash(&parent->mnt, mnt->mnt_mountpoint));
list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
}
}
/*
* vfsmount lock must be held for write
*/
static void commit_tree(struct mount *mnt, struct mount *shadows)
{
struct mount *parent = mnt->mnt_parent;
struct mount *m;
LIST_HEAD(head);
struct mnt_namespace *n = parent->mnt_ns;
BUG_ON(parent == mnt);
list_add_tail(&head, &mnt->mnt_list);
list_for_each_entry(m, &head, mnt_list)
m->mnt_ns = n;
list_splice(&head, n->list.prev);
attach_shadowed(mnt, parent, shadows);
touch_mnt_namespace(n);
}
static struct mount *next_mnt(struct mount *p, struct mount *root)
{
struct list_head *next = p->mnt_mounts.next;
if (next == &p->mnt_mounts) {
while (1) {
if (p == root)
return NULL;
next = p->mnt_child.next;
if (next != &p->mnt_parent->mnt_mounts)
break;
p = p->mnt_parent;
}
}
return list_entry(next, struct mount, mnt_child);
}
static struct mount *skip_mnt_tree(struct mount *p)
{
struct list_head *prev = p->mnt_mounts.prev;
while (prev != &p->mnt_mounts) {
p = list_entry(prev, struct mount, mnt_child);
prev = p->mnt_mounts.prev;
}
return p;
}
struct vfsmount *
vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data)
{
struct mount *mnt;
struct dentry *root;
if (!type)
return ERR_PTR(-ENODEV);
mnt = alloc_vfsmnt(name);
if (!mnt)
return ERR_PTR(-ENOMEM);
if (flags & MS_KERNMOUNT)
mnt->mnt.mnt_flags = MNT_INTERNAL;
root = mount_fs(type, flags, name, data);
if (IS_ERR(root)) {
mnt_free_id(mnt);
free_vfsmnt(mnt);
return ERR_CAST(root);
}
mnt->mnt.mnt_root = root;
mnt->mnt.mnt_sb = root->d_sb;
mnt->mnt_mountpoint = mnt->mnt.mnt_root;
mnt->mnt_parent = mnt;
lock_mount_hash();
list_add_tail(&mnt->mnt_instance, &root->d_sb->s_mounts);
unlock_mount_hash();
return &mnt->mnt;
}
EXPORT_SYMBOL_GPL(vfs_kern_mount);
static struct mount *clone_mnt(struct mount *old, struct dentry *root,
int flag)
{
struct super_block *sb = old->mnt.mnt_sb;
struct mount *mnt;
int err;
mnt = alloc_vfsmnt(old->mnt_devname);
if (!mnt)
return ERR_PTR(-ENOMEM);
if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE))
mnt->mnt_group_id = 0; /* not a peer of original */
else
mnt->mnt_group_id = old->mnt_group_id;
if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) {
err = mnt_alloc_group_id(mnt);
if (err)
goto out_free;
}
smarter propagate_mnt() The current mainline has copies propagated to *all* nodes, then tears down the copies we made for nodes that do not contain counterparts of the desired mountpoint. That sets the right propagation graph for the copies (at teardown time we move the slaves of removed node to a surviving peer or directly to master), but we end up paying a fairly steep price in useless allocations. It's fairly easy to create a situation where N calls of mount(2) create exactly N bindings, with O(N^2) vfsmounts allocated and freed in process. Fortunately, it is possible to avoid those allocations/freeings. The trick is to create copies in the right order and find which one would've eventually become a master with the current algorithm. It turns out to be possible in O(nodes getting propagation) time and with no extra allocations at all. One part is that we need to make sure that eventual master will be created before its slaves, so we need to walk the propagation tree in a different order - by peer groups. And iterate through the peers before dealing with the next group. Another thing is finding the (earlier) copy that will be a master of one we are about to create; to do that we are (temporary) marking the masters of mountpoints we are attaching the copies to. Either we are in a peer of the last mountpoint we'd dealt with, or we have the following situation: we are attaching to mountpoint M, the last copy S_0 had been attached to M_0 and there are sequences S_0...S_n, M_0...M_n such that S_{i+1} is a master of S_{i}, S_{i} mounted on M{i} and we need to create a slave of the first S_{k} such that M is getting propagation from M_{k}. It means that the master of M_{k} will be among the sequence of masters of M. On the other hand, the nearest marked node in that sequence will either be the master of M_{k} or the master of M_{k-1} (the latter - in the case if M_{k-1} is a slave of something M gets propagation from, but in a wrong peer group). So we go through the sequence of masters of M until we find a marked one (P). Let N be the one before it. Then we go through the sequence of masters of S_0 until we find one (say, S) mounted on a node D that has P as master and check if D is a peer of N. If it is, S will be the master of new copy, if not - the master of S will be. That's it for the hard part; the rest is fairly simple. Iterator is in next_group(), handling of one prospective mountpoint is propagate_one(). It seems to survive all tests and gives a noticably better performance than the current mainline for setups that are seriously using shared subtrees. Cc: stable@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-02-27 14:35:45 +00:00
mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~(MNT_WRITE_HOLD|MNT_MARKED);
/* Don't allow unprivileged users to change mount flags */
mnt: Correct permission checks in do_remount While invesgiating the issue where in "mount --bind -oremount,ro ..." would result in later "mount --bind -oremount,rw" succeeding even if the mount started off locked I realized that there are several additional mount flags that should be locked and are not. In particular MNT_NOSUID, MNT_NODEV, MNT_NOEXEC, and the atime flags in addition to MNT_READONLY should all be locked. These flags are all per superblock, can all be changed with MS_BIND, and should not be changable if set by a more privileged user. The following additions to the current logic are added in this patch. - nosuid may not be clearable by a less privileged user. - nodev may not be clearable by a less privielged user. - noexec may not be clearable by a less privileged user. - atime flags may not be changeable by a less privileged user. The logic with atime is that always setting atime on access is a global policy and backup software and auditing software could break if atime bits are not updated (when they are configured to be updated), and serious performance degradation could result (DOS attack) if atime updates happen when they have been explicitly disabled. Therefore an unprivileged user should not be able to mess with the atime bits set by a more privileged user. The additional restrictions are implemented with the addition of MNT_LOCK_NOSUID, MNT_LOCK_NODEV, MNT_LOCK_NOEXEC, and MNT_LOCK_ATIME mnt flags. Taken together these changes and the fixes for MNT_LOCK_READONLY should make it safe for an unprivileged user to create a user namespace and to call "mount --bind -o remount,... ..." without the danger of mount flags being changed maliciously. Cc: stable@vger.kernel.org Acked-by: Serge E. Hallyn <serge.hallyn@ubuntu.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2014-07-29 00:26:07 +00:00
if (flag & CL_UNPRIVILEGED) {
mnt->mnt.mnt_flags |= MNT_LOCK_ATIME;
if (mnt->mnt.mnt_flags & MNT_READONLY)
mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
if (mnt->mnt.mnt_flags & MNT_NODEV)
mnt->mnt.mnt_flags |= MNT_LOCK_NODEV;
if (mnt->mnt.mnt_flags & MNT_NOSUID)
mnt->mnt.mnt_flags |= MNT_LOCK_NOSUID;
if (mnt->mnt.mnt_flags & MNT_NOEXEC)
mnt->mnt.mnt_flags |= MNT_LOCK_NOEXEC;
}
/* Don't allow unprivileged users to reveal what is under a mount */
if ((flag & CL_UNPRIVILEGED) &&
(!(flag & CL_EXPIRE) || list_empty(&old->mnt_expire)))
mnt->mnt.mnt_flags |= MNT_LOCKED;
atomic_inc(&sb->s_active);
mnt->mnt.mnt_sb = sb;
mnt->mnt.mnt_root = dget(root);
mnt->mnt_mountpoint = mnt->mnt.mnt_root;
mnt->mnt_parent = mnt;
lock_mount_hash();
list_add_tail(&mnt->mnt_instance, &sb->s_mounts);
unlock_mount_hash();
if ((flag & CL_SLAVE) ||
((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) {
list_add(&mnt->mnt_slave, &old->mnt_slave_list);
mnt->mnt_master = old;
CLEAR_MNT_SHARED(mnt);
} else if (!(flag & CL_PRIVATE)) {
if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old))
list_add(&mnt->mnt_share, &old->mnt_share);
if (IS_MNT_SLAVE(old))
list_add(&mnt->mnt_slave, &old->mnt_slave);
mnt->mnt_master = old->mnt_master;
}
if (flag & CL_MAKE_SHARED)
set_mnt_shared(mnt);
/* stick the duplicate mount on the same expiry list
* as the original if that was on one */
if (flag & CL_EXPIRE) {
if (!list_empty(&old->mnt_expire))
list_add(&mnt->mnt_expire, &old->mnt_expire);
}
return mnt;
out_free:
mnt_free_id(mnt);
free_vfsmnt(mnt);
return ERR_PTR(err);
}
static void cleanup_mnt(struct mount *mnt)
{
/*
* This probably indicates that somebody messed
* up a mnt_want/drop_write() pair. If this
* happens, the filesystem was probably unable
* to make r/w->r/o transitions.
*/
/*
* The locking used to deal with mnt_count decrement provides barriers,
* so mnt_get_writers() below is safe.
*/
WARN_ON(mnt_get_writers(mnt));
if (unlikely(mnt->mnt_pins.first))
mnt_pin_kill(mnt);
fsnotify_vfsmount_delete(&mnt->mnt);
dput(mnt->mnt.mnt_root);
deactivate_super(mnt->mnt.mnt_sb);
mnt_free_id(mnt);
call_rcu(&mnt->mnt_rcu, delayed_free_vfsmnt);
}
static void __cleanup_mnt(struct rcu_head *head)
{
cleanup_mnt(container_of(head, struct mount, mnt_rcu));
}
static LLIST_HEAD(delayed_mntput_list);
static void delayed_mntput(struct work_struct *unused)
{
struct llist_node *node = llist_del_all(&delayed_mntput_list);
struct llist_node *next;
for (; node; node = next) {
next = llist_next(node);
cleanup_mnt(llist_entry(node, struct mount, mnt_llist));
}
}
static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput);
static void mntput_no_expire(struct mount *mnt)
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>
2011-01-07 06:50:11 +00:00
{
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
rcu_read_lock();
mnt_add_count(mnt, -1);
if (likely(mnt->mnt_ns)) { /* shouldn't be the last one */
rcu_read_unlock();
return;
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>
2011-01-07 06:50:11 +00:00
}
lock_mount_hash();
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>
2011-01-07 06:50:11 +00:00
if (mnt_get_count(mnt)) {
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
rcu_read_unlock();
unlock_mount_hash();
return;
}
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
if (unlikely(mnt->mnt.mnt_flags & MNT_DOOMED)) {
rcu_read_unlock();
unlock_mount_hash();
return;
}
mnt->mnt.mnt_flags |= MNT_DOOMED;
rcu_read_unlock();
list_del(&mnt->mnt_instance);
unlock_mount_hash();
if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) {
struct task_struct *task = current;
if (likely(!(task->flags & PF_KTHREAD))) {
init_task_work(&mnt->mnt_rcu, __cleanup_mnt);
if (!task_work_add(task, &mnt->mnt_rcu, true))
return;
}
if (llist_add(&mnt->mnt_llist, &delayed_mntput_list))
schedule_delayed_work(&delayed_mntput_work, 1);
return;
}
cleanup_mnt(mnt);
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>
2011-01-07 06:50:11 +00:00
}
void mntput(struct vfsmount *mnt)
{
if (mnt) {
struct mount *m = real_mount(mnt);
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>
2011-01-07 06:50:11 +00:00
/* avoid cacheline pingpong, hope gcc doesn't get "smart" */
if (unlikely(m->mnt_expiry_mark))
m->mnt_expiry_mark = 0;
mntput_no_expire(m);
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>
2011-01-07 06:50:11 +00:00
}
}
EXPORT_SYMBOL(mntput);
struct vfsmount *mntget(struct vfsmount *mnt)
{
if (mnt)
mnt_add_count(real_mount(mnt), 1);
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>
2011-01-07 06:50:11 +00:00
return mnt;
}
EXPORT_SYMBOL(mntget);
struct vfsmount *mnt_clone_internal(struct path *path)
[PATCH] saner handling of auto_acct_off() and DQUOT_OFF() in umount The way we currently deal with quota and process accounting that might keep vfsmount busy at umount time is inherently broken; we try to turn them off just in case (not quite correctly, at that) and a) pray umount doesn't fail (otherwise they'll stay turned off) b) pray nobody doesn anything funny just as we turn quota off Moreover, LSM provides hooks for doing the same sort of broken logics. The proper way to deal with that is to introduce the second kind of reference to vfsmount. Semantics: - when the last normal reference is dropped, all special ones are converted to normal ones and if there had been any, cleanup is done. - normal reference can be cloned into a special one - special reference can be converted to normal one; that's a no-op if we'd already passed the point of no return (i.e. mntput() had converted special references to normal and started cleanup). The way it works: e.g. starting process accounting converts the vfsmount reference pinned by the opened file into special one and turns it back to normal when it gets shut down; acct_auto_close() is done when no normal references are left. That way it does *not* obstruct umount(2) and it silently gets turned off when the last normal reference to vfsmount is gone. Which is exactly what we want... The same should be done by LSM module that holds some internal references to vfsmount and wants to shut them down on umount - it should make them special and security_sb_umount_close() will be called exactly when the last normal reference to vfsmount is gone. quota handling is even simpler - we don't use normal file IO anymore, so there's no need to hold vfsmounts at all. DQUOT_OFF() is done from deactivate_super(), where it really belongs. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-07 22:13:39 +00:00
{
struct mount *p;
p = clone_mnt(real_mount(path->mnt), path->dentry, CL_PRIVATE);
if (IS_ERR(p))
return ERR_CAST(p);
p->mnt.mnt_flags |= MNT_INTERNAL;
return &p->mnt;
[PATCH] saner handling of auto_acct_off() and DQUOT_OFF() in umount The way we currently deal with quota and process accounting that might keep vfsmount busy at umount time is inherently broken; we try to turn them off just in case (not quite correctly, at that) and a) pray umount doesn't fail (otherwise they'll stay turned off) b) pray nobody doesn anything funny just as we turn quota off Moreover, LSM provides hooks for doing the same sort of broken logics. The proper way to deal with that is to introduce the second kind of reference to vfsmount. Semantics: - when the last normal reference is dropped, all special ones are converted to normal ones and if there had been any, cleanup is done. - normal reference can be cloned into a special one - special reference can be converted to normal one; that's a no-op if we'd already passed the point of no return (i.e. mntput() had converted special references to normal and started cleanup). The way it works: e.g. starting process accounting converts the vfsmount reference pinned by the opened file into special one and turns it back to normal when it gets shut down; acct_auto_close() is done when no normal references are left. That way it does *not* obstruct umount(2) and it silently gets turned off when the last normal reference to vfsmount is gone. Which is exactly what we want... The same should be done by LSM module that holds some internal references to vfsmount and wants to shut them down on umount - it should make them special and security_sb_umount_close() will be called exactly when the last normal reference to vfsmount is gone. quota handling is even simpler - we don't use normal file IO anymore, so there's no need to hold vfsmounts at all. DQUOT_OFF() is done from deactivate_super(), where it really belongs. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-07 22:13:39 +00:00
}
static inline void mangle(struct seq_file *m, const char *s)
{
seq_escape(m, s, " \t\n\\");
}
/*
* Simple .show_options callback for filesystems which don't want to
* implement more complex mount option showing.
*
* See also save_mount_options().
*/
int generic_show_options(struct seq_file *m, struct dentry *root)
{
const char *options;
rcu_read_lock();
options = rcu_dereference(root->d_sb->s_options);
if (options != NULL && options[0]) {
seq_putc(m, ',');
mangle(m, options);
}
rcu_read_unlock();
return 0;
}
EXPORT_SYMBOL(generic_show_options);
/*
* If filesystem uses generic_show_options(), this function should be
* called from the fill_super() callback.
*
* The .remount_fs callback usually needs to be handled in a special
* way, to make sure, that previous options are not overwritten if the
* remount fails.
*
* Also note, that if the filesystem's .remount_fs function doesn't
* reset all options to their default value, but changes only newly
* given options, then the displayed options will not reflect reality
* any more.
*/
void save_mount_options(struct super_block *sb, char *options)
{
BUG_ON(sb->s_options);
rcu_assign_pointer(sb->s_options, kstrdup(options, GFP_KERNEL));
}
EXPORT_SYMBOL(save_mount_options);
void replace_mount_options(struct super_block *sb, char *options)
{
char *old = sb->s_options;
rcu_assign_pointer(sb->s_options, options);
if (old) {
synchronize_rcu();
kfree(old);
}
}
EXPORT_SYMBOL(replace_mount_options);
#ifdef CONFIG_PROC_FS
/* iterator; we want it to have access to namespace_sem, thus here... */
static void *m_start(struct seq_file *m, loff_t *pos)
{
struct proc_mounts *p = proc_mounts(m);
down_read(&namespace_sem);
if (p->cached_event == p->ns->event) {
void *v = p->cached_mount;
if (*pos == p->cached_index)
return v;
if (*pos == p->cached_index + 1) {
v = seq_list_next(v, &p->ns->list, &p->cached_index);
return p->cached_mount = v;
}
}
p->cached_event = p->ns->event;
p->cached_mount = seq_list_start(&p->ns->list, *pos);
p->cached_index = *pos;
return p->cached_mount;
}
static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
struct proc_mounts *p = proc_mounts(m);
p->cached_mount = seq_list_next(v, &p->ns->list, pos);
p->cached_index = *pos;
return p->cached_mount;
}
static void m_stop(struct seq_file *m, void *v)
{
up_read(&namespace_sem);
}
static int m_show(struct seq_file *m, void *v)
{
struct proc_mounts *p = proc_mounts(m);
struct mount *r = list_entry(v, struct mount, mnt_list);
return p->show(m, &r->mnt);
}
const struct seq_operations mounts_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
.show = m_show,
};
#endif /* CONFIG_PROC_FS */
/**
* may_umount_tree - check if a mount tree is busy
* @mnt: root of mount tree
*
* This is called to check if a tree of mounts has any
* open files, pwds, chroots or sub mounts that are
* busy.
*/
int may_umount_tree(struct vfsmount *m)
{
struct mount *mnt = real_mount(m);
int actual_refs = 0;
int minimum_refs = 0;
struct mount *p;
BUG_ON(!m);
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>
2011-01-07 06:50:11 +00:00
/* write lock needed for mnt_get_count */
lock_mount_hash();
for (p = mnt; p; p = next_mnt(p, mnt)) {
actual_refs += mnt_get_count(p);
minimum_refs += 2;
}
unlock_mount_hash();
if (actual_refs > minimum_refs)
return 0;
return 1;
}
EXPORT_SYMBOL(may_umount_tree);
/**
* may_umount - check if a mount point is busy
* @mnt: root of mount
*
* This is called to check if a mount point has any
* open files, pwds, chroots or sub mounts. If the
* mount has sub mounts this will return busy
* regardless of whether the sub mounts are busy.
*
* Doesn't take quota and stuff into account. IOW, in some cases it will
* give false negatives. The main reason why it's here is that we need
* a non-destructive way to look for easily umountable filesystems.
*/
int may_umount(struct vfsmount *mnt)
{
int ret = 1;
down_read(&namespace_sem);
lock_mount_hash();
if (propagate_mount_busy(real_mount(mnt), 2))
ret = 0;
unlock_mount_hash();
up_read(&namespace_sem);
return ret;
}
EXPORT_SYMBOL(may_umount);
static HLIST_HEAD(unmounted); /* protected by namespace_sem */
static void namespace_unlock(void)
{
struct hlist_head head;
hlist_move_list(&unmounted, &head);
up_write(&namespace_sem);
if (likely(hlist_empty(&head)))
return;
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
synchronize_rcu();
group_pin_kill(&head);
}
static inline void namespace_lock(void)
{
down_write(&namespace_sem);
}
enum umount_tree_flags {
UMOUNT_SYNC = 1,
UMOUNT_PROPAGATE = 2,
};
/*
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
* mount_lock must be held
* namespace_sem must be held for write
*/
static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
{
LIST_HEAD(tmp_list);
struct mount *p;
/* Gather the mounts to umount */
for (p = mnt; p; p = next_mnt(p, mnt)) {
p->mnt.mnt_flags |= MNT_UMOUNT;
list_move(&p->mnt_list, &tmp_list);
}
/* Hide the mounts from lookup_mnt and mnt_mounts */
list_for_each_entry(p, &tmp_list, mnt_list) {
hlist_del_init_rcu(&p->mnt_hash);
list_del_init(&p->mnt_child);
}
/* Add propogated mounts to the tmp_list */
if (how & UMOUNT_PROPAGATE)
propagate_umount(&tmp_list);
while (!list_empty(&tmp_list)) {
p = list_first_entry(&tmp_list, struct mount, mnt_list);
list_del_init(&p->mnt_expire);
list_del_init(&p->mnt_list);
__touch_mnt_namespace(p->mnt_ns);
p->mnt_ns = NULL;
if (how & UMOUNT_SYNC)
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
pin_insert_group(&p->mnt_umount, &p->mnt_parent->mnt, &unmounted);
if (mnt_has_parent(p)) {
hlist_del_init(&p->mnt_mp_list);
put_mountpoint(p->mnt_mp);
mnt_add_count(p->mnt_parent, -1);
/* old mountpoint will be dropped when we can do that */
p->mnt_ex_mountpoint = p->mnt_mountpoint;
p->mnt_mountpoint = p->mnt.mnt_root;
p->mnt_parent = p;
p->mnt_mp = NULL;
}
change_mnt_propagation(p, MS_PRIVATE);
}
}
static void shrink_submounts(struct mount *mnt);
static int do_umount(struct mount *mnt, int flags)
{
struct super_block *sb = mnt->mnt.mnt_sb;
int retval;
retval = security_sb_umount(&mnt->mnt, flags);
if (retval)
return retval;
/*
* Allow userspace to request a mountpoint be expired rather than
* unmounting unconditionally. Unmount only happens if:
* (1) the mark is already set (the mark is cleared by mntput())
* (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount]
*/
if (flags & MNT_EXPIRE) {
if (&mnt->mnt == current->fs->root.mnt ||
flags & (MNT_FORCE | MNT_DETACH))
return -EINVAL;
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>
2011-01-07 06:50:11 +00:00
/*
* probably don't strictly need the lock here if we examined
* all race cases, but it's a slowpath.
*/
lock_mount_hash();
if (mnt_get_count(mnt) != 2) {
unlock_mount_hash();
return -EBUSY;
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>
2011-01-07 06:50:11 +00:00
}
unlock_mount_hash();
if (!xchg(&mnt->mnt_expiry_mark, 1))
return -EAGAIN;
}
/*
* If we may have to abort operations to get out of this
* mount, and they will themselves hold resources we must
* allow the fs to do things. In the Unix tradition of
* 'Gee thats tricky lets do it in userspace' the umount_begin
* might fail to complete on the first run through as other tasks
* must return, and the like. Thats for the mount program to worry
* about for the moment.
*/
if (flags & MNT_FORCE && sb->s_op->umount_begin) {
sb->s_op->umount_begin(sb);
}
/*
* No sense to grab the lock for this test, but test itself looks
* somewhat bogus. Suggestions for better replacement?
* Ho-hum... In principle, we might treat that as umount + switch
* to rootfs. GC would eventually take care of the old vfsmount.
* Actually it makes sense, especially if rootfs would contain a
* /reboot - static binary that would close all descriptors and
* call reboot(9). Then init(8) could umount root and exec /reboot.
*/
if (&mnt->mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) {
/*
* Special case for "unmounting" root ...
* we just try to remount it readonly.
*/
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
down_write(&sb->s_umount);
if (!(sb->s_flags & MS_RDONLY))
retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
up_write(&sb->s_umount);
return retval;
}
namespace_lock();
lock_mount_hash();
event++;
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
if (flags & MNT_DETACH) {
if (!list_empty(&mnt->mnt_list))
umount_tree(mnt, UMOUNT_PROPAGATE);
retval = 0;
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
} else {
shrink_submounts(mnt);
retval = -EBUSY;
if (!propagate_mount_busy(mnt, 2)) {
if (!list_empty(&mnt->mnt_list))
umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
retval = 0;
}
}
unlock_mount_hash();
namespace_unlock();
return retval;
}
/*
* __detach_mounts - lazily unmount all mounts on the specified dentry
*
* During unlink, rmdir, and d_drop it is possible to loose the path
* to an existing mountpoint, and wind up leaking the mount.
* detach_mounts allows lazily unmounting those mounts instead of
* leaking them.
*
* The caller may hold dentry->d_inode->i_mutex.
*/
void __detach_mounts(struct dentry *dentry)
{
struct mountpoint *mp;
struct mount *mnt;
namespace_lock();
mp = lookup_mountpoint(dentry);
if (!mp)
goto out_unlock;
lock_mount_hash();
while (!hlist_empty(&mp->m_list)) {
mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
umount_tree(mnt, 0);
}
unlock_mount_hash();
put_mountpoint(mp);
out_unlock:
namespace_unlock();
}
/*
* Is the caller allowed to modify his namespace?
*/
static inline bool may_mount(void)
{
return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN);
}
/*
* Now umount can handle mount points as well as block devices.
* This is important for filesystems which use unnamed block devices.
*
* We now support a flag for forced unmount like the other 'big iron'
* unixes. Our API is identical to OSF/1 to avoid making a mess of AMD
*/
SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
{
struct path path;
struct mount *mnt;
int retval;
int lookup_flags = 0;
if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW))
return -EINVAL;
if (!may_mount())
return -EPERM;
if (!(flags & UMOUNT_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
retval = user_path_mountpoint_at(AT_FDCWD, name, lookup_flags, &path);
if (retval)
goto out;
mnt = real_mount(path.mnt);
retval = -EINVAL;
if (path.dentry != path.mnt->mnt_root)
goto dput_and_out;
if (!check_mnt(mnt))
goto dput_and_out;
if (mnt->mnt.mnt_flags & MNT_LOCKED)
goto dput_and_out;
retval = -EPERM;
if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN))
goto dput_and_out;
retval = do_umount(mnt, flags);
dput_and_out:
/* we mustn't call path_put() as that would clear mnt_expiry_mark */
dput(path.dentry);
mntput_no_expire(mnt);
out:
return retval;
}
#ifdef __ARCH_WANT_SYS_OLDUMOUNT
/*
* The 2.0 compatible umount. No flags.
*/
SYSCALL_DEFINE1(oldumount, char __user *, name)
{
return sys_umount(name, 0);
}
#endif
static bool is_mnt_ns_file(struct dentry *dentry)
{
/* Is this a proxy for a mount namespace? */
return dentry->d_op == &ns_dentry_operations &&
dentry->d_fsdata == &mntns_operations;
}
struct mnt_namespace *to_mnt_ns(struct ns_common *ns)
{
return container_of(ns, struct mnt_namespace, ns);
}
static bool mnt_ns_loop(struct dentry *dentry)
{
/* Could bind mounting the mount namespace inode cause a
* mount namespace loop?
*/
struct mnt_namespace *mnt_ns;
if (!is_mnt_ns_file(dentry))
return false;
mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode));
return current->nsproxy->mnt_ns->seq >= mnt_ns->seq;
}
struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
int flag)
{
struct mount *res, *p, *q, *r, *parent;
if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(mnt))
return ERR_PTR(-EINVAL);
if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(dentry))
return ERR_PTR(-EINVAL);
res = q = clone_mnt(mnt, dentry, flag);
if (IS_ERR(q))
return q;
q->mnt_mountpoint = mnt->mnt_mountpoint;
p = mnt;
list_for_each_entry(r, &mnt->mnt_mounts, mnt_child) {
struct mount *s;
if (!is_subdir(r->mnt_mountpoint, dentry))
continue;
for (s = r; s; s = next_mnt(s, r)) {
struct mount *t = NULL;
if (!(flag & CL_COPY_UNBINDABLE) &&
IS_MNT_UNBINDABLE(s)) {
s = skip_mnt_tree(s);
continue;
}
if (!(flag & CL_COPY_MNT_NS_FILE) &&
is_mnt_ns_file(s->mnt.mnt_root)) {
s = skip_mnt_tree(s);
continue;
}
while (p != s->mnt_parent) {
p = p->mnt_parent;
q = q->mnt_parent;
}
p = s;
parent = q;
q = clone_mnt(p, p->mnt.mnt_root, flag);
if (IS_ERR(q))
goto out;
lock_mount_hash();
list_add_tail(&q->mnt_list, &res->mnt_list);
mnt_set_mountpoint(parent, p->mnt_mp, q);
if (!list_empty(&parent->mnt_mounts)) {
t = list_last_entry(&parent->mnt_mounts,
struct mount, mnt_child);
if (t->mnt_mp != p->mnt_mp)
t = NULL;
}
attach_shadowed(q, parent, t);
unlock_mount_hash();
}
}
return res;
out:
if (res) {
lock_mount_hash();
umount_tree(res, UMOUNT_SYNC);
unlock_mount_hash();
}
return q;
}
/* Caller should check returned pointer for errors */
struct vfsmount *collect_mounts(struct path *path)
{
struct mount *tree;
namespace_lock();
tree = copy_tree(real_mount(path->mnt), path->dentry,
CL_COPY_ALL | CL_PRIVATE);
namespace_unlock();
if (IS_ERR(tree))
return ERR_CAST(tree);
return &tree->mnt;
}
void drop_collected_mounts(struct vfsmount *mnt)
{
namespace_lock();
lock_mount_hash();
umount_tree(real_mount(mnt), UMOUNT_SYNC);
unlock_mount_hash();
namespace_unlock();
}
/**
* clone_private_mount - create a private clone of a path
*
* This creates a new vfsmount, which will be the clone of @path. The new will
* not be attached anywhere in the namespace and will be private (i.e. changes
* to the originating mount won't be propagated into this).
*
* Release with mntput().
*/
struct vfsmount *clone_private_mount(struct path *path)
{
struct mount *old_mnt = real_mount(path->mnt);
struct mount *new_mnt;
if (IS_MNT_UNBINDABLE(old_mnt))
return ERR_PTR(-EINVAL);
down_read(&namespace_sem);
new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE);
up_read(&namespace_sem);
if (IS_ERR(new_mnt))
return ERR_CAST(new_mnt);
return &new_mnt->mnt;
}
EXPORT_SYMBOL_GPL(clone_private_mount);
int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
struct vfsmount *root)
{
struct mount *mnt;
int res = f(root, arg);
if (res)
return res;
list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) {
res = f(&mnt->mnt, arg);
if (res)
return res;
}
return 0;
}
static void cleanup_group_ids(struct mount *mnt, struct mount *end)
{
struct mount *p;
for (p = mnt; p != end; p = next_mnt(p, mnt)) {
if (p->mnt_group_id && !IS_MNT_SHARED(p))
mnt_release_group_id(p);
}
}
static int invent_group_ids(struct mount *mnt, bool recurse)
{
struct mount *p;
for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) {
if (!p->mnt_group_id && !IS_MNT_SHARED(p)) {
int err = mnt_alloc_group_id(p);
if (err) {
cleanup_group_ids(mnt, p);
return err;
}
}
}
return 0;
}
/*
* @source_mnt : mount tree to be attached
* @nd : place the mount tree @source_mnt is attached
* @parent_nd : if non-null, detach the source_mnt from its parent and
* store the parent mount and mountpoint dentry.
* (done when source_mnt is moved)
*
* NOTE: in the table below explains the semantics when a source mount
* of a given type is attached to a destination mount of a given type.
* ---------------------------------------------------------------------------
* | BIND MOUNT OPERATION |
* |**************************************************************************
* | source-->| shared | private | slave | unbindable |
* | dest | | | | |
* | | | | | | |
* | v | | | | |
* |**************************************************************************
* | shared | shared (++) | shared (+) | shared(+++)| invalid |
* | | | | | |
* |non-shared| shared (+) | private | slave (*) | invalid |
* ***************************************************************************
* A bind operation clones the source mount and mounts the clone on the
* destination mount.
*
* (++) the cloned mount is propagated to all the mounts in the propagation
* tree of the destination mount and the cloned mount is added to
* the peer group of the source mount.
* (+) the cloned mount is created under the destination mount and is marked
* as shared. The cloned mount is added to the peer group of the source
* mount.
* (+++) the mount is propagated to all the mounts in the propagation tree
* of the destination mount and the cloned mount is made slave
* of the same master as that of the source mount. The cloned mount
* is marked as 'shared and slave'.
* (*) the cloned mount is made a slave of the same master as that of the
* source mount.
*
* ---------------------------------------------------------------------------
* | MOVE MOUNT OPERATION |
* |**************************************************************************
* | source-->| shared | private | slave | unbindable |
* | dest | | | | |
* | | | | | | |
* | v | | | | |
* |**************************************************************************
* | shared | shared (+) | shared (+) | shared(+++) | invalid |
* | | | | | |
* |non-shared| shared (+*) | private | slave (*) | unbindable |
* ***************************************************************************
*
* (+) the mount is moved to the destination. And is then propagated to
* all the mounts in the propagation tree of the destination mount.
* (+*) the mount is moved to the destination.
* (+++) the mount is moved to the destination and is then propagated to
* all the mounts belonging to the destination mount's propagation tree.
* the mount is marked as 'shared and slave'.
* (*) the mount continues to be a slave at the new location.
*
* if the source mount is a tree, the operations explained above is
* applied to each mount in the tree.
* Must be called without spinlocks held, since this function can sleep
* in allocations.
*/
static int attach_recursive_mnt(struct mount *source_mnt,
struct mount *dest_mnt,
struct mountpoint *dest_mp,
struct path *parent_path)
{
HLIST_HEAD(tree_list);
struct mount *child, *p;
struct hlist_node *n;
int err;
if (IS_MNT_SHARED(dest_mnt)) {
err = invent_group_ids(source_mnt, true);
if (err)
goto out;
err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list);
smarter propagate_mnt() The current mainline has copies propagated to *all* nodes, then tears down the copies we made for nodes that do not contain counterparts of the desired mountpoint. That sets the right propagation graph for the copies (at teardown time we move the slaves of removed node to a surviving peer or directly to master), but we end up paying a fairly steep price in useless allocations. It's fairly easy to create a situation where N calls of mount(2) create exactly N bindings, with O(N^2) vfsmounts allocated and freed in process. Fortunately, it is possible to avoid those allocations/freeings. The trick is to create copies in the right order and find which one would've eventually become a master with the current algorithm. It turns out to be possible in O(nodes getting propagation) time and with no extra allocations at all. One part is that we need to make sure that eventual master will be created before its slaves, so we need to walk the propagation tree in a different order - by peer groups. And iterate through the peers before dealing with the next group. Another thing is finding the (earlier) copy that will be a master of one we are about to create; to do that we are (temporary) marking the masters of mountpoints we are attaching the copies to. Either we are in a peer of the last mountpoint we'd dealt with, or we have the following situation: we are attaching to mountpoint M, the last copy S_0 had been attached to M_0 and there are sequences S_0...S_n, M_0...M_n such that S_{i+1} is a master of S_{i}, S_{i} mounted on M{i} and we need to create a slave of the first S_{k} such that M is getting propagation from M_{k}. It means that the master of M_{k} will be among the sequence of masters of M. On the other hand, the nearest marked node in that sequence will either be the master of M_{k} or the master of M_{k-1} (the latter - in the case if M_{k-1} is a slave of something M gets propagation from, but in a wrong peer group). So we go through the sequence of masters of M until we find a marked one (P). Let N be the one before it. Then we go through the sequence of masters of S_0 until we find one (say, S) mounted on a node D that has P as master and check if D is a peer of N. If it is, S will be the master of new copy, if not - the master of S will be. That's it for the hard part; the rest is fairly simple. Iterator is in next_group(), handling of one prospective mountpoint is propagate_one(). It seems to survive all tests and gives a noticably better performance than the current mainline for setups that are seriously using shared subtrees. Cc: stable@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-02-27 14:35:45 +00:00
lock_mount_hash();
if (err)
goto out_cleanup_ids;
for (p = source_mnt; p; p = next_mnt(p, source_mnt))
set_mnt_shared(p);
} else {
lock_mount_hash();
}
if (parent_path) {
detach_mnt(source_mnt, parent_path);
attach_mnt(source_mnt, dest_mnt, dest_mp);
touch_mnt_namespace(source_mnt->mnt_ns);
} else {
mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
commit_tree(source_mnt, NULL);
}
hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
struct mount *q;
hlist_del_init(&child->mnt_hash);
q = __lookup_mnt_last(&child->mnt_parent->mnt,
child->mnt_mountpoint);
commit_tree(child, q);
}
unlock_mount_hash();
return 0;
out_cleanup_ids:
smarter propagate_mnt() The current mainline has copies propagated to *all* nodes, then tears down the copies we made for nodes that do not contain counterparts of the desired mountpoint. That sets the right propagation graph for the copies (at teardown time we move the slaves of removed node to a surviving peer or directly to master), but we end up paying a fairly steep price in useless allocations. It's fairly easy to create a situation where N calls of mount(2) create exactly N bindings, with O(N^2) vfsmounts allocated and freed in process. Fortunately, it is possible to avoid those allocations/freeings. The trick is to create copies in the right order and find which one would've eventually become a master with the current algorithm. It turns out to be possible in O(nodes getting propagation) time and with no extra allocations at all. One part is that we need to make sure that eventual master will be created before its slaves, so we need to walk the propagation tree in a different order - by peer groups. And iterate through the peers before dealing with the next group. Another thing is finding the (earlier) copy that will be a master of one we are about to create; to do that we are (temporary) marking the masters of mountpoints we are attaching the copies to. Either we are in a peer of the last mountpoint we'd dealt with, or we have the following situation: we are attaching to mountpoint M, the last copy S_0 had been attached to M_0 and there are sequences S_0...S_n, M_0...M_n such that S_{i+1} is a master of S_{i}, S_{i} mounted on M{i} and we need to create a slave of the first S_{k} such that M is getting propagation from M_{k}. It means that the master of M_{k} will be among the sequence of masters of M. On the other hand, the nearest marked node in that sequence will either be the master of M_{k} or the master of M_{k-1} (the latter - in the case if M_{k-1} is a slave of something M gets propagation from, but in a wrong peer group). So we go through the sequence of masters of M until we find a marked one (P). Let N be the one before it. Then we go through the sequence of masters of S_0 until we find one (say, S) mounted on a node D that has P as master and check if D is a peer of N. If it is, S will be the master of new copy, if not - the master of S will be. That's it for the hard part; the rest is fairly simple. Iterator is in next_group(), handling of one prospective mountpoint is propagate_one(). It seems to survive all tests and gives a noticably better performance than the current mainline for setups that are seriously using shared subtrees. Cc: stable@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-02-27 14:35:45 +00:00
while (!hlist_empty(&tree_list)) {
child = hlist_entry(tree_list.first, struct mount, mnt_hash);
umount_tree(child, UMOUNT_SYNC);
smarter propagate_mnt() The current mainline has copies propagated to *all* nodes, then tears down the copies we made for nodes that do not contain counterparts of the desired mountpoint. That sets the right propagation graph for the copies (at teardown time we move the slaves of removed node to a surviving peer or directly to master), but we end up paying a fairly steep price in useless allocations. It's fairly easy to create a situation where N calls of mount(2) create exactly N bindings, with O(N^2) vfsmounts allocated and freed in process. Fortunately, it is possible to avoid those allocations/freeings. The trick is to create copies in the right order and find which one would've eventually become a master with the current algorithm. It turns out to be possible in O(nodes getting propagation) time and with no extra allocations at all. One part is that we need to make sure that eventual master will be created before its slaves, so we need to walk the propagation tree in a different order - by peer groups. And iterate through the peers before dealing with the next group. Another thing is finding the (earlier) copy that will be a master of one we are about to create; to do that we are (temporary) marking the masters of mountpoints we are attaching the copies to. Either we are in a peer of the last mountpoint we'd dealt with, or we have the following situation: we are attaching to mountpoint M, the last copy S_0 had been attached to M_0 and there are sequences S_0...S_n, M_0...M_n such that S_{i+1} is a master of S_{i}, S_{i} mounted on M{i} and we need to create a slave of the first S_{k} such that M is getting propagation from M_{k}. It means that the master of M_{k} will be among the sequence of masters of M. On the other hand, the nearest marked node in that sequence will either be the master of M_{k} or the master of M_{k-1} (the latter - in the case if M_{k-1} is a slave of something M gets propagation from, but in a wrong peer group). So we go through the sequence of masters of M until we find a marked one (P). Let N be the one before it. Then we go through the sequence of masters of S_0 until we find one (say, S) mounted on a node D that has P as master and check if D is a peer of N. If it is, S will be the master of new copy, if not - the master of S will be. That's it for the hard part; the rest is fairly simple. Iterator is in next_group(), handling of one prospective mountpoint is propagate_one(). It seems to survive all tests and gives a noticably better performance than the current mainline for setups that are seriously using shared subtrees. Cc: stable@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-02-27 14:35:45 +00:00
}
unlock_mount_hash();
cleanup_group_ids(source_mnt, NULL);
out:
return err;
}
static struct mountpoint *lock_mount(struct path *path)
{
struct vfsmount *mnt;
struct dentry *dentry = path->dentry;
retry:
mutex_lock(&dentry->d_inode->i_mutex);
if (unlikely(cant_mount(dentry))) {
mutex_unlock(&dentry->d_inode->i_mutex);
return ERR_PTR(-ENOENT);
}
namespace_lock();
mnt = lookup_mnt(path);
if (likely(!mnt)) {
struct mountpoint *mp = lookup_mountpoint(dentry);
if (!mp)
mp = new_mountpoint(dentry);
if (IS_ERR(mp)) {
namespace_unlock();
mutex_unlock(&dentry->d_inode->i_mutex);
return mp;
}
return mp;
}
namespace_unlock();
mutex_unlock(&path->dentry->d_inode->i_mutex);
path_put(path);
path->mnt = mnt;
dentry = path->dentry = dget(mnt->mnt_root);
goto retry;
}
static void unlock_mount(struct mountpoint *where)
{
struct dentry *dentry = where->m_dentry;
put_mountpoint(where);
namespace_unlock();
mutex_unlock(&dentry->d_inode->i_mutex);
}
static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
{
if (mnt->mnt.mnt_sb->s_flags & MS_NOUSER)
return -EINVAL;
VFS: (Scripted) Convert S_ISLNK/DIR/REG(dentry->d_inode) to d_is_*(dentry) Convert the following where appropriate: (1) S_ISLNK(dentry->d_inode) to d_is_symlink(dentry). (2) S_ISREG(dentry->d_inode) to d_is_reg(dentry). (3) S_ISDIR(dentry->d_inode) to d_is_dir(dentry). This is actually more complicated than it appears as some calls should be converted to d_can_lookup() instead. The difference is whether the directory in question is a real dir with a ->lookup op or whether it's a fake dir with a ->d_automount op. In some circumstances, we can subsume checks for dentry->d_inode not being NULL into this, provided we the code isn't in a filesystem that expects d_inode to be NULL if the dirent really *is* negative (ie. if we're going to use d_inode() rather than d_backing_inode() to get the inode pointer). Note that the dentry type field may be set to something other than DCACHE_MISS_TYPE when d_inode is NULL in the case of unionmount, where the VFS manages the fall-through from a negative dentry to a lower layer. In such a case, the dentry type of the negative union dentry is set to the same as the type of the lower dentry. However, if you know d_inode is not NULL at the call site, then you can use the d_is_xxx() functions even in a filesystem. There is one further complication: a 0,0 chardev dentry may be labelled DCACHE_WHITEOUT_TYPE rather than DCACHE_SPECIAL_TYPE. Strictly, this was intended for special directory entry types that don't have attached inodes. The following perl+coccinelle script was used: use strict; my @callers; open($fd, 'git grep -l \'S_IS[A-Z].*->d_inode\' |') || die "Can't grep for S_ISDIR and co. callers"; @callers = <$fd>; close($fd); unless (@callers) { print "No matches\n"; exit(0); } my @cocci = ( '@@', 'expression E;', '@@', '', '- S_ISLNK(E->d_inode->i_mode)', '+ d_is_symlink(E)', '', '@@', 'expression E;', '@@', '', '- S_ISDIR(E->d_inode->i_mode)', '+ d_is_dir(E)', '', '@@', 'expression E;', '@@', '', '- S_ISREG(E->d_inode->i_mode)', '+ d_is_reg(E)' ); my $coccifile = "tmp.sp.cocci"; open($fd, ">$coccifile") || die $coccifile; print($fd "$_\n") || die $coccifile foreach (@cocci); close($fd); foreach my $file (@callers) { chomp $file; print "Processing ", $file, "\n"; system("spatch", "--sp-file", $coccifile, $file, "--in-place", "--no-show-diff") == 0 || die "spatch failed"; } [AV: overlayfs parts skipped] Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-01-29 12:02:35 +00:00
if (d_is_dir(mp->m_dentry) !=
d_is_dir(mnt->mnt.mnt_root))
return -ENOTDIR;
return attach_recursive_mnt(mnt, p, mp, NULL);
}
/*
* Sanity check the flags to change_mnt_propagation.
*/
static int flags_to_propagation_type(int flags)
{
fs/namespace.c: bound mount propagation fix This issue was discovered by users of busybox. And the bug is actual for busybox users, I don't know how it affects others. Apparently, mount is called with and without MS_SILENT, and this affects mount() behaviour. But MS_SILENT is only supposed to affect kernel logging verbosity. The following script was run in an empty test directory: mkdir -p mount.dir mount.shared1 mount.shared2 touch mount.dir/a mount.dir/b mount -vv --bind mount.shared1 mount.shared1 mount -vv --make-rshared mount.shared1 mount -vv --bind mount.shared2 mount.shared2 mount -vv --make-rshared mount.shared2 mount -vv --bind mount.shared2 mount.shared1 mount -vv --bind mount.dir mount.shared2 ls -R mount.dir mount.shared1 mount.shared2 umount mount.dir mount.shared1 mount.shared2 2>/dev/null umount mount.dir mount.shared1 mount.shared2 2>/dev/null umount mount.dir mount.shared1 mount.shared2 2>/dev/null rm -f mount.dir/a mount.dir/b mount.dir/c rmdir mount.dir mount.shared1 mount.shared2 mount -vv was used to show the mount() call arguments and result. Output shows that flag argument has 0x00008000 = MS_SILENT bit: mount: mount('mount.shared1','mount.shared1','(null)',0x00009000,'(null)'):0 mount: mount('','mount.shared1','',0x0010c000,''):0 mount: mount('mount.shared2','mount.shared2','(null)',0x00009000,'(null)'):0 mount: mount('','mount.shared2','',0x0010c000,''):0 mount: mount('mount.shared2','mount.shared1','(null)',0x00009000,'(null)'):0 mount: mount('mount.dir','mount.shared2','(null)',0x00009000,'(null)'):0 mount.dir: a b mount.shared1: mount.shared2: a b After adding --loud option to remove MS_SILENT bit from just one mount cmd: mkdir -p mount.dir mount.shared1 mount.shared2 touch mount.dir/a mount.dir/b mount -vv --bind mount.shared1 mount.shared1 2>&1 mount -vv --make-rshared mount.shared1 2>&1 mount -vv --bind mount.shared2 mount.shared2 2>&1 mount -vv --loud --make-rshared mount.shared2 2>&1 # <-HERE mount -vv --bind mount.shared2 mount.shared1 2>&1 mount -vv --bind mount.dir mount.shared2 2>&1 ls -R mount.dir mount.shared1 mount.shared2 2>&1 umount mount.dir mount.shared1 mount.shared2 2>/dev/null umount mount.dir mount.shared1 mount.shared2 2>/dev/null umount mount.dir mount.shared1 mount.shared2 2>/dev/null rm -f mount.dir/a mount.dir/b mount.dir/c rmdir mount.dir mount.shared1 mount.shared2 The result is different now - look closely at mount.shared1 directory listing. Now it does show files 'a' and 'b': mount: mount('mount.shared1','mount.shared1','(null)',0x00009000,'(null)'):0 mount: mount('','mount.shared1','',0x0010c000,''):0 mount: mount('mount.shared2','mount.shared2','(null)',0x00009000,'(null)'):0 mount: mount('','mount.shared2','',0x00104000,''):0 mount: mount('mount.shared2','mount.shared1','(null)',0x00009000,'(null)'):0 mount: mount('mount.dir','mount.shared2','(null)',0x00009000,'(null)'):0 mount.dir: a b mount.shared1: a b mount.shared2: a b The analysis shows that MS_SILENT flag which is ON by default in any busybox-> mount operations cames to flags_to_propagation_type function and causes the error return while is_power_of_2 checking because the function expects only one bit set. This doesn't allow to do busybox->mount with any --make-[r]shared, --make-[r]private etc options. Moreover, the recently added flags_to_propagation_type() function doesn't allow us to do such operations as --make-[r]private --make-[r]shared etc. when MS_SILENT is on. The idea or clearing the MS_SILENT flag came from to Denys Vlasenko. Signed-off-by: Roman Borisov <ext-roman.borisov@nokia.com> Reported-by: Denys Vlasenko <vda.linux@googlemail.com> Cc: Chuck Ebbert <cebbert@redhat.com> Cc: Alexander Shishkin <virtuoso@slind.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-05-25 23:26:48 +00:00
int type = flags & ~(MS_REC | MS_SILENT);
/* Fail if any non-propagation flags are set */
if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
return 0;
/* Only one propagation flag should be set */
if (!is_power_of_2(type))
return 0;
return type;
}
/*
* recursively change the type of the mountpoint.
*/
static int do_change_type(struct path *path, int flag)
{
struct mount *m;
struct mount *mnt = real_mount(path->mnt);
int recurse = flag & MS_REC;
int type;
int err = 0;
if (path->dentry != path->mnt->mnt_root)
return -EINVAL;
type = flags_to_propagation_type(flag);
if (!type)
return -EINVAL;
namespace_lock();
if (type == MS_SHARED) {
err = invent_group_ids(mnt, recurse);
if (err)
goto out_unlock;
}
lock_mount_hash();
for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL))
change_mnt_propagation(m, type);
unlock_mount_hash();
out_unlock:
namespace_unlock();
return err;
}
static bool has_locked_children(struct mount *mnt, struct dentry *dentry)
{
struct mount *child;
list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
if (!is_subdir(child->mnt_mountpoint, dentry))
continue;
if (child->mnt.mnt_flags & MNT_LOCKED)
return true;
}
return false;
}
/*
* do loopback mount.
*/
static int do_loopback(struct path *path, const char *old_name,
int recurse)
{
struct path old_path;
struct mount *mnt = NULL, *old, *parent;
struct mountpoint *mp;
int err;
if (!old_name || !*old_name)
return -EINVAL;
err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path);
if (err)
return err;
err = -EINVAL;
if (mnt_ns_loop(old_path.dentry))
goto out;
mp = lock_mount(path);
err = PTR_ERR(mp);
if (IS_ERR(mp))
goto out;
old = real_mount(old_path.mnt);
parent = real_mount(path->mnt);
err = -EINVAL;
if (IS_MNT_UNBINDABLE(old))
goto out2;
if (!check_mnt(parent))
goto out2;
if (!check_mnt(old) && old_path.dentry->d_op != &ns_dentry_operations)
goto out2;
if (!recurse && has_locked_children(old, old_path.dentry))
goto out2;
if (recurse)
mnt = copy_tree(old, old_path.dentry, CL_COPY_MNT_NS_FILE);
else
mnt = clone_mnt(old, old_path.dentry, 0);
if (IS_ERR(mnt)) {
err = PTR_ERR(mnt);
goto out2;
}
mnt->mnt.mnt_flags &= ~MNT_LOCKED;
err = graft_tree(mnt, parent, mp);
if (err) {
lock_mount_hash();
umount_tree(mnt, UMOUNT_SYNC);
unlock_mount_hash();
}
out2:
unlock_mount(mp);
out:
path_put(&old_path);
return err;
}
static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
{
int error = 0;
int readonly_request = 0;
if (ms_flags & MS_RDONLY)
readonly_request = 1;
if (readonly_request == __mnt_is_readonly(mnt))
return 0;
if (readonly_request)
error = mnt_make_readonly(real_mount(mnt));
else
__mnt_unmake_readonly(real_mount(mnt));
return error;
}
/*
* change filesystem flags. dir should be a physical root of filesystem.
* If you've mounted a non-root directory somewhere and want to do remount
* on it - tough luck.
*/
static int do_remount(struct path *path, int flags, int mnt_flags,
void *data)
{
int err;
struct super_block *sb = path->mnt->mnt_sb;
struct mount *mnt = real_mount(path->mnt);
if (!check_mnt(mnt))
return -EINVAL;
if (path->dentry != path->mnt->mnt_root)
return -EINVAL;
/* Don't allow changing of locked mnt flags.
*
* No locks need to be held here while testing the various
* MNT_LOCK flags because those flags can never be cleared
* once they are set.
*/
if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) &&
!(mnt_flags & MNT_READONLY)) {
return -EPERM;
}
mnt: Correct permission checks in do_remount While invesgiating the issue where in "mount --bind -oremount,ro ..." would result in later "mount --bind -oremount,rw" succeeding even if the mount started off locked I realized that there are several additional mount flags that should be locked and are not. In particular MNT_NOSUID, MNT_NODEV, MNT_NOEXEC, and the atime flags in addition to MNT_READONLY should all be locked. These flags are all per superblock, can all be changed with MS_BIND, and should not be changable if set by a more privileged user. The following additions to the current logic are added in this patch. - nosuid may not be clearable by a less privileged user. - nodev may not be clearable by a less privielged user. - noexec may not be clearable by a less privileged user. - atime flags may not be changeable by a less privileged user. The logic with atime is that always setting atime on access is a global policy and backup software and auditing software could break if atime bits are not updated (when they are configured to be updated), and serious performance degradation could result (DOS attack) if atime updates happen when they have been explicitly disabled. Therefore an unprivileged user should not be able to mess with the atime bits set by a more privileged user. The additional restrictions are implemented with the addition of MNT_LOCK_NOSUID, MNT_LOCK_NODEV, MNT_LOCK_NOEXEC, and MNT_LOCK_ATIME mnt flags. Taken together these changes and the fixes for MNT_LOCK_READONLY should make it safe for an unprivileged user to create a user namespace and to call "mount --bind -o remount,... ..." without the danger of mount flags being changed maliciously. Cc: stable@vger.kernel.org Acked-by: Serge E. Hallyn <serge.hallyn@ubuntu.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2014-07-29 00:26:07 +00:00
if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
!(mnt_flags & MNT_NODEV)) {
/* Was the nodev implicitly added in mount? */
if ((mnt->mnt_ns->user_ns != &init_user_ns) &&
!(sb->s_type->fs_flags & FS_USERNS_DEV_MOUNT)) {
mnt_flags |= MNT_NODEV;
} else {
return -EPERM;
}
mnt: Correct permission checks in do_remount While invesgiating the issue where in "mount --bind -oremount,ro ..." would result in later "mount --bind -oremount,rw" succeeding even if the mount started off locked I realized that there are several additional mount flags that should be locked and are not. In particular MNT_NOSUID, MNT_NODEV, MNT_NOEXEC, and the atime flags in addition to MNT_READONLY should all be locked. These flags are all per superblock, can all be changed with MS_BIND, and should not be changable if set by a more privileged user. The following additions to the current logic are added in this patch. - nosuid may not be clearable by a less privileged user. - nodev may not be clearable by a less privielged user. - noexec may not be clearable by a less privileged user. - atime flags may not be changeable by a less privileged user. The logic with atime is that always setting atime on access is a global policy and backup software and auditing software could break if atime bits are not updated (when they are configured to be updated), and serious performance degradation could result (DOS attack) if atime updates happen when they have been explicitly disabled. Therefore an unprivileged user should not be able to mess with the atime bits set by a more privileged user. The additional restrictions are implemented with the addition of MNT_LOCK_NOSUID, MNT_LOCK_NODEV, MNT_LOCK_NOEXEC, and MNT_LOCK_ATIME mnt flags. Taken together these changes and the fixes for MNT_LOCK_READONLY should make it safe for an unprivileged user to create a user namespace and to call "mount --bind -o remount,... ..." without the danger of mount flags being changed maliciously. Cc: stable@vger.kernel.org Acked-by: Serge E. Hallyn <serge.hallyn@ubuntu.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2014-07-29 00:26:07 +00:00
}
if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) &&
!(mnt_flags & MNT_NOSUID)) {
return -EPERM;
}
if ((mnt->mnt.mnt_flags & MNT_LOCK_NOEXEC) &&
!(mnt_flags & MNT_NOEXEC)) {
return -EPERM;
}
if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) &&
((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) {
return -EPERM;
}
err = security_sb_remount(sb, data);
if (err)
return err;
down_write(&sb->s_umount);
if (flags & MS_BIND)
err = change_mount_flags(path->mnt, flags);
else if (!capable(CAP_SYS_ADMIN))
err = -EPERM;
else
err = do_remount_sb(sb, flags, data, 0);
if (!err) {
lock_mount_hash();
mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
mnt->mnt.mnt_flags = mnt_flags;
touch_mnt_namespace(mnt->mnt_ns);
unlock_mount_hash();
}
up_write(&sb->s_umount);
return err;
}
static inline int tree_contains_unbindable(struct mount *mnt)
{
struct mount *p;
for (p = mnt; p; p = next_mnt(p, mnt)) {
if (IS_MNT_UNBINDABLE(p))
return 1;
}
return 0;
}
static int do_move_mount(struct path *path, const char *old_name)
{
struct path old_path, parent_path;
struct mount *p;
struct mount *old;
struct mountpoint *mp;
int err;
if (!old_name || !*old_name)
return -EINVAL;
err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
if (err)
return err;
mp = lock_mount(path);
err = PTR_ERR(mp);
if (IS_ERR(mp))
Add a dentry op to allow processes to be held during pathwalk transit Add a dentry op (d_manage) to permit a filesystem to hold a process and make it sleep when it tries to transit away from one of that filesystem's directories during a pathwalk. The operation is keyed off a new dentry flag (DCACHE_MANAGE_TRANSIT). The filesystem is allowed to be selective about which processes it holds and which it permits to continue on or prohibits from transiting from each flagged directory. This will allow autofs to hold up client processes whilst letting its userspace daemon through to maintain the directory or the stuff behind it or mounted upon it. The ->d_manage() dentry operation: int (*d_manage)(struct path *path, bool mounting_here); takes a pointer to the directory about to be transited away from and a flag indicating whether the transit is undertaken by do_add_mount() or do_move_mount() skipping through a pile of filesystems mounted on a mountpoint. It should return 0 if successful and to let the process continue on its way; -EISDIR to prohibit the caller from skipping to overmounted filesystems or automounting, and to use this directory; or some other error code to return to the user. ->d_manage() is called with namespace_sem writelocked if mounting_here is true and no other locks held, so it may sleep. However, if mounting_here is true, it may not initiate or wait for a mount or unmount upon the parameter directory, even if the act is actually performed by userspace. Within fs/namei.c, follow_managed() is extended to check with d_manage() first on each managed directory, before transiting away from it or attempting to automount upon it. follow_down() is renamed follow_down_one() and should only be used where the filesystem deliberately intends to avoid management steps (e.g. autofs). A new follow_down() is added that incorporates the loop done by all other callers of follow_down() (do_add/move_mount(), autofs and NFSD; whilst AFS, NFS and CIFS do use it, their use is removed by converting them to use d_automount()). The new follow_down() calls d_manage() as appropriate. It also takes an extra parameter to indicate if it is being called from mount code (with namespace_sem writelocked) which it passes to d_manage(). follow_down() ignores automount points so that it can be used to mount on them. __follow_mount_rcu() is made to abort rcu-walk mode if it hits a directory with DCACHE_MANAGE_TRANSIT set on the basis that we're probably going to have to sleep. It would be possible to enter d_manage() in rcu-walk mode too, and have that determine whether to abort or not itself. That would allow the autofs daemon to continue on in rcu-walk mode. Note that DCACHE_MANAGE_TRANSIT on a directory should be cleared when it isn't required as every tranist from that directory will cause d_manage() to be invoked. It can always be set again when necessary. ========================== WHAT THIS MEANS FOR AUTOFS ========================== Autofs currently uses the lookup() inode op and the d_revalidate() dentry op to trigger the automounting of indirect mounts, and both of these can be called with i_mutex held. autofs knows that the i_mutex will be held by the caller in lookup(), and so can drop it before invoking the daemon - but this isn't so for d_revalidate(), since the lock is only held on _some_ of the code paths that call it. This means that autofs can't risk dropping i_mutex from its d_revalidate() function before it calls the daemon. The bug could manifest itself as, for example, a process that's trying to validate an automount dentry that gets made to wait because that dentry is expired and needs cleaning up: mkdir S ffffffff8014e05a 0 32580 24956 Call Trace: [<ffffffff885371fd>] :autofs4:autofs4_wait+0x674/0x897 [<ffffffff80127f7d>] avc_has_perm+0x46/0x58 [<ffffffff8009fdcf>] autoremove_wake_function+0x0/0x2e [<ffffffff88537be6>] :autofs4:autofs4_expire_wait+0x41/0x6b [<ffffffff88535cfc>] :autofs4:autofs4_revalidate+0x91/0x149 [<ffffffff80036d96>] __lookup_hash+0xa0/0x12f [<ffffffff80057a2f>] lookup_create+0x46/0x80 [<ffffffff800e6e31>] sys_mkdirat+0x56/0xe4 versus the automount daemon which wants to remove that dentry, but can't because the normal process is holding the i_mutex lock: automount D ffffffff8014e05a 0 32581 1 32561 Call Trace: [<ffffffff80063c3f>] __mutex_lock_slowpath+0x60/0x9b [<ffffffff8000ccf1>] do_path_lookup+0x2ca/0x2f1 [<ffffffff80063c89>] .text.lock.mutex+0xf/0x14 [<ffffffff800e6d55>] do_rmdir+0x77/0xde [<ffffffff8005d229>] tracesys+0x71/0xe0 [<ffffffff8005d28d>] tracesys+0xd5/0xe0 which means that the system is deadlocked. This patch allows autofs to hold up normal processes whilst the daemon goes ahead and does things to the dentry tree behind the automouter point without risking a deadlock as almost no locks are held in d_manage() and none in d_automount(). Signed-off-by: David Howells <dhowells@redhat.com> Was-Acked-by: Ian Kent <raven@themaw.net> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-01-14 18:45:26 +00:00
goto out;
old = real_mount(old_path.mnt);
p = real_mount(path->mnt);
err = -EINVAL;
if (!check_mnt(p) || !check_mnt(old))
goto out1;
if (old->mnt.mnt_flags & MNT_LOCKED)
goto out1;
err = -EINVAL;
if (old_path.dentry != old_path.mnt->mnt_root)
goto out1;
if (!mnt_has_parent(old))
goto out1;
VFS: (Scripted) Convert S_ISLNK/DIR/REG(dentry->d_inode) to d_is_*(dentry) Convert the following where appropriate: (1) S_ISLNK(dentry->d_inode) to d_is_symlink(dentry). (2) S_ISREG(dentry->d_inode) to d_is_reg(dentry). (3) S_ISDIR(dentry->d_inode) to d_is_dir(dentry). This is actually more complicated than it appears as some calls should be converted to d_can_lookup() instead. The difference is whether the directory in question is a real dir with a ->lookup op or whether it's a fake dir with a ->d_automount op. In some circumstances, we can subsume checks for dentry->d_inode not being NULL into this, provided we the code isn't in a filesystem that expects d_inode to be NULL if the dirent really *is* negative (ie. if we're going to use d_inode() rather than d_backing_inode() to get the inode pointer). Note that the dentry type field may be set to something other than DCACHE_MISS_TYPE when d_inode is NULL in the case of unionmount, where the VFS manages the fall-through from a negative dentry to a lower layer. In such a case, the dentry type of the negative union dentry is set to the same as the type of the lower dentry. However, if you know d_inode is not NULL at the call site, then you can use the d_is_xxx() functions even in a filesystem. There is one further complication: a 0,0 chardev dentry may be labelled DCACHE_WHITEOUT_TYPE rather than DCACHE_SPECIAL_TYPE. Strictly, this was intended for special directory entry types that don't have attached inodes. The following perl+coccinelle script was used: use strict; my @callers; open($fd, 'git grep -l \'S_IS[A-Z].*->d_inode\' |') || die "Can't grep for S_ISDIR and co. callers"; @callers = <$fd>; close($fd); unless (@callers) { print "No matches\n"; exit(0); } my @cocci = ( '@@', 'expression E;', '@@', '', '- S_ISLNK(E->d_inode->i_mode)', '+ d_is_symlink(E)', '', '@@', 'expression E;', '@@', '', '- S_ISDIR(E->d_inode->i_mode)', '+ d_is_dir(E)', '', '@@', 'expression E;', '@@', '', '- S_ISREG(E->d_inode->i_mode)', '+ d_is_reg(E)' ); my $coccifile = "tmp.sp.cocci"; open($fd, ">$coccifile") || die $coccifile; print($fd "$_\n") || die $coccifile foreach (@cocci); close($fd); foreach my $file (@callers) { chomp $file; print "Processing ", $file, "\n"; system("spatch", "--sp-file", $coccifile, $file, "--in-place", "--no-show-diff") == 0 || die "spatch failed"; } [AV: overlayfs parts skipped] Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-01-29 12:02:35 +00:00
if (d_is_dir(path->dentry) !=
d_is_dir(old_path.dentry))
goto out1;
/*
* Don't move a mount residing in a shared parent.
*/
if (IS_MNT_SHARED(old->mnt_parent))
goto out1;
/*
* Don't move a mount tree containing unbindable mounts to a destination
* mount which is shared.
*/
if (IS_MNT_SHARED(p) && tree_contains_unbindable(old))
goto out1;
err = -ELOOP;
for (; mnt_has_parent(p); p = p->mnt_parent)
if (p == old)
goto out1;
err = attach_recursive_mnt(old, real_mount(path->mnt), mp, &parent_path);
if (err)
goto out1;
/* if the mount is moved, it should no longer be expire
* automatically */
list_del_init(&old->mnt_expire);
out1:
unlock_mount(mp);
out:
if (!err)
path_put(&parent_path);
path_put(&old_path);
return err;
}
static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
{
int err;
const char *subtype = strchr(fstype, '.');
if (subtype) {
subtype++;
err = -EINVAL;
if (!subtype[0])
goto err;
} else
subtype = "";
mnt->mnt_sb->s_subtype = kstrdup(subtype, GFP_KERNEL);
err = -ENOMEM;
if (!mnt->mnt_sb->s_subtype)
goto err;
return mnt;
err:
mntput(mnt);
return ERR_PTR(err);
}
/*
* add a mount into a namespace's mount tree
*/
static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
{
struct mountpoint *mp;
struct mount *parent;
int err;
smarter propagate_mnt() The current mainline has copies propagated to *all* nodes, then tears down the copies we made for nodes that do not contain counterparts of the desired mountpoint. That sets the right propagation graph for the copies (at teardown time we move the slaves of removed node to a surviving peer or directly to master), but we end up paying a fairly steep price in useless allocations. It's fairly easy to create a situation where N calls of mount(2) create exactly N bindings, with O(N^2) vfsmounts allocated and freed in process. Fortunately, it is possible to avoid those allocations/freeings. The trick is to create copies in the right order and find which one would've eventually become a master with the current algorithm. It turns out to be possible in O(nodes getting propagation) time and with no extra allocations at all. One part is that we need to make sure that eventual master will be created before its slaves, so we need to walk the propagation tree in a different order - by peer groups. And iterate through the peers before dealing with the next group. Another thing is finding the (earlier) copy that will be a master of one we are about to create; to do that we are (temporary) marking the masters of mountpoints we are attaching the copies to. Either we are in a peer of the last mountpoint we'd dealt with, or we have the following situation: we are attaching to mountpoint M, the last copy S_0 had been attached to M_0 and there are sequences S_0...S_n, M_0...M_n such that S_{i+1} is a master of S_{i}, S_{i} mounted on M{i} and we need to create a slave of the first S_{k} such that M is getting propagation from M_{k}. It means that the master of M_{k} will be among the sequence of masters of M. On the other hand, the nearest marked node in that sequence will either be the master of M_{k} or the master of M_{k-1} (the latter - in the case if M_{k-1} is a slave of something M gets propagation from, but in a wrong peer group). So we go through the sequence of masters of M until we find a marked one (P). Let N be the one before it. Then we go through the sequence of masters of S_0 until we find one (say, S) mounted on a node D that has P as master and check if D is a peer of N. If it is, S will be the master of new copy, if not - the master of S will be. That's it for the hard part; the rest is fairly simple. Iterator is in next_group(), handling of one prospective mountpoint is propagate_one(). It seems to survive all tests and gives a noticably better performance than the current mainline for setups that are seriously using shared subtrees. Cc: stable@vger.kernel.org Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-02-27 14:35:45 +00:00
mnt_flags &= ~MNT_INTERNAL_FLAGS;
mp = lock_mount(path);
if (IS_ERR(mp))
return PTR_ERR(mp);
parent = real_mount(path->mnt);
err = -EINVAL;
if (unlikely(!check_mnt(parent))) {
/* that's acceptable only for automounts done in private ns */
if (!(mnt_flags & MNT_SHRINKABLE))
goto unlock;
/* ... and for those we'd better have mountpoint still alive */
if (!parent->mnt_ns)
goto unlock;
}
/* Refuse the same filesystem on the same mount point */
err = -EBUSY;
if (path->mnt->mnt_sb == newmnt->mnt.mnt_sb &&
path->mnt->mnt_root == path->dentry)
goto unlock;
err = -EINVAL;
VFS: (Scripted) Convert S_ISLNK/DIR/REG(dentry->d_inode) to d_is_*(dentry) Convert the following where appropriate: (1) S_ISLNK(dentry->d_inode) to d_is_symlink(dentry). (2) S_ISREG(dentry->d_inode) to d_is_reg(dentry). (3) S_ISDIR(dentry->d_inode) to d_is_dir(dentry). This is actually more complicated than it appears as some calls should be converted to d_can_lookup() instead. The difference is whether the directory in question is a real dir with a ->lookup op or whether it's a fake dir with a ->d_automount op. In some circumstances, we can subsume checks for dentry->d_inode not being NULL into this, provided we the code isn't in a filesystem that expects d_inode to be NULL if the dirent really *is* negative (ie. if we're going to use d_inode() rather than d_backing_inode() to get the inode pointer). Note that the dentry type field may be set to something other than DCACHE_MISS_TYPE when d_inode is NULL in the case of unionmount, where the VFS manages the fall-through from a negative dentry to a lower layer. In such a case, the dentry type of the negative union dentry is set to the same as the type of the lower dentry. However, if you know d_inode is not NULL at the call site, then you can use the d_is_xxx() functions even in a filesystem. There is one further complication: a 0,0 chardev dentry may be labelled DCACHE_WHITEOUT_TYPE rather than DCACHE_SPECIAL_TYPE. Strictly, this was intended for special directory entry types that don't have attached inodes. The following perl+coccinelle script was used: use strict; my @callers; open($fd, 'git grep -l \'S_IS[A-Z].*->d_inode\' |') || die "Can't grep for S_ISDIR and co. callers"; @callers = <$fd>; close($fd); unless (@callers) { print "No matches\n"; exit(0); } my @cocci = ( '@@', 'expression E;', '@@', '', '- S_ISLNK(E->d_inode->i_mode)', '+ d_is_symlink(E)', '', '@@', 'expression E;', '@@', '', '- S_ISDIR(E->d_inode->i_mode)', '+ d_is_dir(E)', '', '@@', 'expression E;', '@@', '', '- S_ISREG(E->d_inode->i_mode)', '+ d_is_reg(E)' ); my $coccifile = "tmp.sp.cocci"; open($fd, ">$coccifile") || die $coccifile; print($fd "$_\n") || die $coccifile foreach (@cocci); close($fd); foreach my $file (@callers) { chomp $file; print "Processing ", $file, "\n"; system("spatch", "--sp-file", $coccifile, $file, "--in-place", "--no-show-diff") == 0 || die "spatch failed"; } [AV: overlayfs parts skipped] Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-01-29 12:02:35 +00:00
if (d_is_symlink(newmnt->mnt.mnt_root))
goto unlock;
newmnt->mnt.mnt_flags = mnt_flags;
err = graft_tree(newmnt, parent, mp);
unlock:
unlock_mount(mp);
return err;
}
/*
* create a new mount for userspace and request it to be added into the
* namespace's tree
*/
static int do_new_mount(struct path *path, const char *fstype, int flags,
int mnt_flags, const char *name, void *data)
{
struct file_system_type *type;
struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
struct vfsmount *mnt;
int err;
if (!fstype)
return -EINVAL;
type = get_fs_type(fstype);
if (!type)
return -ENODEV;
if (user_ns != &init_user_ns) {
if (!(type->fs_flags & FS_USERNS_MOUNT)) {
put_filesystem(type);
return -EPERM;
}
/* Only in special cases allow devices from mounts
* created outside the initial user namespace.
*/
if (!(type->fs_flags & FS_USERNS_DEV_MOUNT)) {
flags |= MS_NODEV;
mnt: Correct permission checks in do_remount While invesgiating the issue where in "mount --bind -oremount,ro ..." would result in later "mount --bind -oremount,rw" succeeding even if the mount started off locked I realized that there are several additional mount flags that should be locked and are not. In particular MNT_NOSUID, MNT_NODEV, MNT_NOEXEC, and the atime flags in addition to MNT_READONLY should all be locked. These flags are all per superblock, can all be changed with MS_BIND, and should not be changable if set by a more privileged user. The following additions to the current logic are added in this patch. - nosuid may not be clearable by a less privileged user. - nodev may not be clearable by a less privielged user. - noexec may not be clearable by a less privileged user. - atime flags may not be changeable by a less privileged user. The logic with atime is that always setting atime on access is a global policy and backup software and auditing software could break if atime bits are not updated (when they are configured to be updated), and serious performance degradation could result (DOS attack) if atime updates happen when they have been explicitly disabled. Therefore an unprivileged user should not be able to mess with the atime bits set by a more privileged user. The additional restrictions are implemented with the addition of MNT_LOCK_NOSUID, MNT_LOCK_NODEV, MNT_LOCK_NOEXEC, and MNT_LOCK_ATIME mnt flags. Taken together these changes and the fixes for MNT_LOCK_READONLY should make it safe for an unprivileged user to create a user namespace and to call "mount --bind -o remount,... ..." without the danger of mount flags being changed maliciously. Cc: stable@vger.kernel.org Acked-by: Serge E. Hallyn <serge.hallyn@ubuntu.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2014-07-29 00:26:07 +00:00
mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
}
}
mnt = vfs_kern_mount(type, flags, name, data);
if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
!mnt->mnt_sb->s_subtype)
mnt = fs_set_subtype(mnt, fstype);
put_filesystem(type);
if (IS_ERR(mnt))
return PTR_ERR(mnt);
err = do_add_mount(real_mount(mnt), path, mnt_flags);
if (err)
mntput(mnt);
return err;
}
int finish_automount(struct vfsmount *m, struct path *path)
{
struct mount *mnt = real_mount(m);
int err;
/* The new mount record should have at least 2 refs to prevent it being
* expired before we get a chance to add it
*/
BUG_ON(mnt_get_count(mnt) < 2);
if (m->mnt_sb == path->mnt->mnt_sb &&
m->mnt_root == path->dentry) {
err = -ELOOP;
goto fail;
}
err = do_add_mount(mnt, path, path->mnt->mnt_flags | MNT_SHRINKABLE);
if (!err)
return 0;
fail:
/* remove m from any expiration list it may be on */
if (!list_empty(&mnt->mnt_expire)) {
namespace_lock();
list_del_init(&mnt->mnt_expire);
namespace_unlock();
}
mntput(m);
mntput(m);
return err;
}
/**
* mnt_set_expiry - Put a mount on an expiration list
* @mnt: The mount to list.
* @expiry_list: The list to add the mount to.
*/
void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list)
{
namespace_lock();
list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list);
namespace_unlock();
}
EXPORT_SYMBOL(mnt_set_expiry);
/*
* process a list of expirable mountpoints with the intent of discarding any
* mountpoints that aren't in use and haven't been touched since last we came
* here
*/
void mark_mounts_for_expiry(struct list_head *mounts)
{
struct mount *mnt, *next;
LIST_HEAD(graveyard);
if (list_empty(mounts))
return;
namespace_lock();
lock_mount_hash();
/* extract from the expiration list every vfsmount that matches the
* following criteria:
* - only referenced by its parent vfsmount
* - still marked for expiry (marked on the last call here; marks are
* cleared by mntput())
*/
list_for_each_entry_safe(mnt, next, mounts, mnt_expire) {
if (!xchg(&mnt->mnt_expiry_mark, 1) ||
propagate_mount_busy(mnt, 1))
continue;
list_move(&mnt->mnt_expire, &graveyard);
}
while (!list_empty(&graveyard)) {
mnt = list_first_entry(&graveyard, struct mount, mnt_expire);
touch_mnt_namespace(mnt->mnt_ns);
umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
}
unlock_mount_hash();
namespace_unlock();
}
EXPORT_SYMBOL_GPL(mark_mounts_for_expiry);
/*
* Ripoff of 'select_parent()'
*
* search the list of submounts for a given mountpoint, and move any
* shrinkable submounts to the 'graveyard' list.
*/
static int select_submounts(struct mount *parent, struct list_head *graveyard)
{
struct mount *this_parent = parent;
struct list_head *next;
int found = 0;
repeat:
next = this_parent->mnt_mounts.next;
resume:
while (next != &this_parent->mnt_mounts) {
struct list_head *tmp = next;
struct mount *mnt = list_entry(tmp, struct mount, mnt_child);
next = tmp->next;
if (!(mnt->mnt.mnt_flags & MNT_SHRINKABLE))
continue;
/*
* Descend a level if the d_mounts list is non-empty.
*/
if (!list_empty(&mnt->mnt_mounts)) {
this_parent = mnt;
goto repeat;
}
if (!propagate_mount_busy(mnt, 1)) {
list_move_tail(&mnt->mnt_expire, graveyard);
found++;
}
}
/*
* All done at this level ... ascend and resume the search
*/
if (this_parent != parent) {
next = this_parent->mnt_child.next;
this_parent = this_parent->mnt_parent;
goto resume;
}
return found;
}
/*
* process a list of expirable mountpoints with the intent of discarding any
* submounts of a specific parent mountpoint
*
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
* mount_lock must be held for write
*/
static void shrink_submounts(struct mount *mnt)
{
LIST_HEAD(graveyard);
struct mount *m;
/* extract submounts of 'mountpoint' from the expiration list */
while (select_submounts(mnt, &graveyard)) {
while (!list_empty(&graveyard)) {
m = list_first_entry(&graveyard, struct mount,
mnt_expire);
touch_mnt_namespace(m->mnt_ns);
umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC);
}
}
}
/*
* Some copy_from_user() implementations do not return the exact number of
* bytes remaining to copy on a fault. But copy_mount_options() requires that.
* Note that this function differs from copy_from_user() in that it will oops
* on bad values of `to', rather than returning a short copy.
*/
static long exact_copy_from_user(void *to, const void __user * from,
unsigned long n)
{
char *t = to;
const char __user *f = from;
char c;
if (!access_ok(VERIFY_READ, from, n))
return n;
while (n) {
if (__get_user(c, f)) {
memset(t, 0, n);
break;
}
*t++ = c;
f++;
n--;
}
return n;
}
int copy_mount_options(const void __user * data, unsigned long *where)
{
int i;
unsigned long page;
unsigned long size;
*where = 0;
if (!data)
return 0;
if (!(page = __get_free_page(GFP_KERNEL)))
return -ENOMEM;
/* We only care that *some* data at the address the user
* gave us is valid. Just in case, we'll zero
* the remainder of the page.
*/
/* copy_from_user cannot cross TASK_SIZE ! */
size = TASK_SIZE - (unsigned long)data;
if (size > PAGE_SIZE)
size = PAGE_SIZE;
i = size - exact_copy_from_user((void *)page, data, size);
if (!i) {
free_page(page);
return -EFAULT;
}
if (i != PAGE_SIZE)
memset((char *)page + i, 0, PAGE_SIZE - i);
*where = page;
return 0;
}
char *copy_mount_string(const void __user *data)
{
return data ? strndup_user(data, PAGE_SIZE) : NULL;
}
/*
* Flags is a 32-bit value that allows up to 31 non-fs dependent flags to
* be given to the mount() call (ie: read-only, no-dev, no-suid etc).
*
* data is a (void *) that can point to any structure up to
* PAGE_SIZE-1 bytes, which can contain arbitrary fs-dependent
* information (or be NULL).
*
* Pre-0.97 versions of mount() didn't have a flags word.
* When the flags word was introduced its top half was required
* to have the magic value 0xC0ED, and this remained so until 2.4.0-test9.
* Therefore, if this magic number is present, it carries no information
* and must be discarded.
*/
long do_mount(const char *dev_name, const char __user *dir_name,
const char *type_page, unsigned long flags, void *data_page)
{
struct path path;
int retval = 0;
int mnt_flags = 0;
/* Discard magic */
if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
flags &= ~MS_MGC_MSK;
/* Basic sanity checks */
if (data_page)
((char *)data_page)[PAGE_SIZE - 1] = 0;
/* ... and get the mountpoint */
retval = user_path(dir_name, &path);
if (retval)
return retval;
retval = security_sb_mount(dev_name, &path,
type_page, flags, data_page);
if (!retval && !may_mount())
retval = -EPERM;
if (retval)
goto dput_out;
/* Default to relatime unless overriden */
if (!(flags & MS_NOATIME))
mnt_flags |= MNT_RELATIME;
/* Separate the per-mountpoint flags */
if (flags & MS_NOSUID)
mnt_flags |= MNT_NOSUID;
if (flags & MS_NODEV)
mnt_flags |= MNT_NODEV;
if (flags & MS_NOEXEC)
mnt_flags |= MNT_NOEXEC;
if (flags & MS_NOATIME)
mnt_flags |= MNT_NOATIME;
if (flags & MS_NODIRATIME)
mnt_flags |= MNT_NODIRATIME;
if (flags & MS_STRICTATIME)
mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME);
if (flags & MS_RDONLY)
mnt_flags |= MNT_READONLY;
/* The default atime for remount is preservation */
if ((flags & MS_REMOUNT) &&
((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME |
MS_STRICTATIME)) == 0)) {
mnt_flags &= ~MNT_ATIME_MASK;
mnt_flags |= path.mnt->mnt_flags & MNT_ATIME_MASK;
}
flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
MS_STRICTATIME);
if (flags & MS_REMOUNT)
retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags,
data_page);
else if (flags & MS_BIND)
retval = do_loopback(&path, dev_name, flags & MS_REC);
else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
retval = do_change_type(&path, flags);
else if (flags & MS_MOVE)
retval = do_move_mount(&path, dev_name);
else
retval = do_new_mount(&path, type_page, flags, mnt_flags,
dev_name, data_page);
dput_out:
path_put(&path);
return retval;
}
static void free_mnt_ns(struct mnt_namespace *ns)
{
ns_free_inum(&ns->ns);
put_user_ns(ns->user_ns);
kfree(ns);
}
/*
* Assign a sequence number so we can detect when we attempt to bind
* mount a reference to an older mount namespace into the current
* mount namespace, preventing reference counting loops. A 64bit
* number incrementing at 10Ghz will take 12,427 years to wrap which
* is effectively never, so we can ignore the possibility.
*/
static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1);
static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
{
struct mnt_namespace *new_ns;
int ret;
new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
if (!new_ns)
return ERR_PTR(-ENOMEM);
ret = ns_alloc_inum(&new_ns->ns);
if (ret) {
kfree(new_ns);
return ERR_PTR(ret);
}
new_ns->ns.ops = &mntns_operations;
new_ns->seq = atomic64_add_return(1, &mnt_ns_seq);
atomic_set(&new_ns->count, 1);
new_ns->root = NULL;
INIT_LIST_HEAD(&new_ns->list);
init_waitqueue_head(&new_ns->poll);
new_ns->event = 0;
new_ns->user_ns = get_user_ns(user_ns);
return new_ns;
}
struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
struct user_namespace *user_ns, struct fs_struct *new_fs)
{
struct mnt_namespace *new_ns;
struct vfsmount *rootmnt = NULL, *pwdmnt = NULL;
struct mount *p, *q;
struct mount *old;
struct mount *new;
int copy_flags;
BUG_ON(!ns);
if (likely(!(flags & CLONE_NEWNS))) {
get_mnt_ns(ns);
return ns;
}
old = ns->root;
new_ns = alloc_mnt_ns(user_ns);
if (IS_ERR(new_ns))
return new_ns;
namespace_lock();
/* First pass: copy the tree topology */
copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE;
if (user_ns != ns->user_ns)
copy_flags |= CL_SHARED_TO_SLAVE | CL_UNPRIVILEGED;
new = copy_tree(old, old->mnt.mnt_root, copy_flags);
if (IS_ERR(new)) {
namespace_unlock();
free_mnt_ns(new_ns);
return ERR_CAST(new);
}
new_ns->root = new;
list_add_tail(&new_ns->list, &new->mnt_list);
/*
* Second pass: switch the tsk->fs->* elements and mark new vfsmounts
* as belonging to new namespace. We have already acquired a private
* fs_struct, so tsk->fs->lock is not needed.
*/
p = old;
q = new;
while (p) {
q->mnt_ns = new_ns;
if (new_fs) {
if (&p->mnt == new_fs->root.mnt) {
new_fs->root.mnt = mntget(&q->mnt);
rootmnt = &p->mnt;
}
if (&p->mnt == new_fs->pwd.mnt) {
new_fs->pwd.mnt = mntget(&q->mnt);
pwdmnt = &p->mnt;
}
}
p = next_mnt(p, old);
q = next_mnt(q, new);
if (!q)
break;
while (p->mnt.mnt_root != q->mnt.mnt_root)
p = next_mnt(p, old);
}
namespace_unlock();
if (rootmnt)
mntput(rootmnt);
if (pwdmnt)
mntput(pwdmnt);
return new_ns;
}
/**
* create_mnt_ns - creates a private namespace and adds a root filesystem
* @mnt: pointer to the new root filesystem mountpoint
*/
static struct mnt_namespace *create_mnt_ns(struct vfsmount *m)
{
struct mnt_namespace *new_ns = alloc_mnt_ns(&init_user_ns);
if (!IS_ERR(new_ns)) {
struct mount *mnt = real_mount(m);
mnt->mnt_ns = new_ns;
new_ns->root = mnt;
list_add(&mnt->mnt_list, &new_ns->list);
} else {
mntput(m);
}
return new_ns;
}
struct dentry *mount_subtree(struct vfsmount *mnt, const char *name)
{
struct mnt_namespace *ns;
struct super_block *s;
struct path path;
int err;
ns = create_mnt_ns(mnt);
if (IS_ERR(ns))
return ERR_CAST(ns);
err = vfs_path_lookup(mnt->mnt_root, mnt,
name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
put_mnt_ns(ns);
if (err)
return ERR_PTR(err);
/* trade a vfsmount reference for active sb one */
s = path.mnt->mnt_sb;
atomic_inc(&s->s_active);
mntput(path.mnt);
/* lock the sucker */
down_write(&s->s_umount);
/* ... and return the root of (sub)tree on it */
return path.dentry;
}
EXPORT_SYMBOL(mount_subtree);
SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
char __user *, type, unsigned long, flags, void __user *, data)
{
int ret;
char *kernel_type;
char *kernel_dev;
unsigned long data_page;
kernel_type = copy_mount_string(type);
ret = PTR_ERR(kernel_type);
if (IS_ERR(kernel_type))
goto out_type;
kernel_dev = copy_mount_string(dev_name);
ret = PTR_ERR(kernel_dev);
if (IS_ERR(kernel_dev))
goto out_dev;
ret = copy_mount_options(data, &data_page);
if (ret < 0)
goto out_data;
ret = do_mount(kernel_dev, dir_name, kernel_type, flags,
(void *) data_page);
free_page(data_page);
out_data:
kfree(kernel_dev);
out_dev:
kfree(kernel_type);
out_type:
return ret;
}
/*
* Return true if path is reachable from root
*
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
* namespace_sem or mount_lock is held
*/
bool is_path_reachable(struct mount *mnt, struct dentry *dentry,
const struct path *root)
{
while (&mnt->mnt != root->mnt && mnt_has_parent(mnt)) {
dentry = mnt->mnt_mountpoint;
mnt = mnt->mnt_parent;
}
return &mnt->mnt == root->mnt && is_subdir(dentry, root->dentry);
}
int path_is_under(struct path *path1, struct path *path2)
{
int res;
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
read_seqlock_excl(&mount_lock);
res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2);
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
read_sequnlock_excl(&mount_lock);
return res;
}
EXPORT_SYMBOL(path_is_under);
/*
* pivot_root Semantics:
* Moves the root file system of the current process to the directory put_old,
* makes new_root as the new root file system of the current process, and sets
* root/cwd of all processes which had them on the current root to new_root.
*
* Restrictions:
* The new_root and put_old must be directories, and must not be on the
* same file system as the current process root. The put_old must be
* underneath new_root, i.e. adding a non-zero number of /.. to the string
* pointed to by put_old must yield the same directory as new_root. No other
* file system may be mounted on put_old. After all, new_root is a mountpoint.
*
* Also, the current root cannot be on the 'rootfs' (initial ramfs) filesystem.
* See Documentation/filesystems/ramfs-rootfs-initramfs.txt for alternatives
* in this situation.
*
* Notes:
* - we don't move root/cwd if they are not at the root (reason: if something
* cared enough to change them, it's probably wrong to force them elsewhere)
* - it's okay to pick a root that isn't the root of a file system, e.g.
* /nfs/my_root where /nfs is the mount point. It must be a mountpoint,
* though, so you may need to say mount --bind /nfs/my_root /nfs/my_root
* first.
*/
SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
const char __user *, put_old)
{
struct path new, old, parent_path, root_parent, root;
struct mount *new_mnt, *root_mnt, *old_mnt;
struct mountpoint *old_mp, *root_mp;
int error;
if (!may_mount())
return -EPERM;
error = user_path_dir(new_root, &new);
if (error)
goto out0;
error = user_path_dir(put_old, &old);
if (error)
goto out1;
error = security_sb_pivotroot(&old, &new);
if (error)
goto out2;
get_fs_root(current->fs, &root);
old_mp = lock_mount(&old);
error = PTR_ERR(old_mp);
if (IS_ERR(old_mp))
goto out3;
error = -EINVAL;
new_mnt = real_mount(new.mnt);
root_mnt = real_mount(root.mnt);
old_mnt = real_mount(old.mnt);
if (IS_MNT_SHARED(old_mnt) ||
IS_MNT_SHARED(new_mnt->mnt_parent) ||
IS_MNT_SHARED(root_mnt->mnt_parent))
goto out4;
if (!check_mnt(root_mnt) || !check_mnt(new_mnt))
goto out4;
if (new_mnt->mnt.mnt_flags & MNT_LOCKED)
goto out4;
error = -ENOENT;
if (d_unlinked(new.dentry))
goto out4;
error = -EBUSY;
if (new_mnt == root_mnt || old_mnt == root_mnt)
goto out4; /* loop, on the same file system */
error = -EINVAL;
if (root.mnt->mnt_root != root.dentry)
goto out4; /* not a mountpoint */
if (!mnt_has_parent(root_mnt))
goto out4; /* not attached */
root_mp = root_mnt->mnt_mp;
if (new.mnt->mnt_root != new.dentry)
goto out4; /* not a mountpoint */
if (!mnt_has_parent(new_mnt))
goto out4; /* not attached */
/* make sure we can reach put_old from new_root */
if (!is_path_reachable(old_mnt, old.dentry, &new))
goto out4;
/* make certain new is below the root */
if (!is_path_reachable(new_mnt, new.dentry, &root))
goto out4;
root_mp->m_count++; /* pin it so it won't go away */
lock_mount_hash();
detach_mnt(new_mnt, &parent_path);
detach_mnt(root_mnt, &root_parent);
if (root_mnt->mnt.mnt_flags & MNT_LOCKED) {
new_mnt->mnt.mnt_flags |= MNT_LOCKED;
root_mnt->mnt.mnt_flags &= ~MNT_LOCKED;
}
/* mount old root on put_old */
attach_mnt(root_mnt, old_mnt, old_mp);
/* mount new_root on / */
attach_mnt(new_mnt, real_mount(root_parent.mnt), root_mp);
touch_mnt_namespace(current->nsproxy->mnt_ns);
/* A moved mount should not expire automatically */
list_del_init(&new_mnt->mnt_expire);
unlock_mount_hash();
chroot_fs_refs(&root, &new);
put_mountpoint(root_mp);
error = 0;
out4:
unlock_mount(old_mp);
if (!error) {
path_put(&root_parent);
path_put(&parent_path);
}
out3:
path_put(&root);
out2:
path_put(&old);
out1:
path_put(&new);
out0:
return error;
}
static void __init init_mount_tree(void)
{
struct vfsmount *mnt;
struct mnt_namespace *ns;
struct path root;
struct file_system_type *type;
type = get_fs_type("rootfs");
if (!type)
panic("Can't find rootfs type");
mnt = vfs_kern_mount(type, 0, "rootfs", NULL);
put_filesystem(type);
if (IS_ERR(mnt))
panic("Can't create rootfs");
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>
2011-01-07 06:50:11 +00:00
ns = create_mnt_ns(mnt);
if (IS_ERR(ns))
panic("Can't allocate initial namespace");
init_task.nsproxy->mnt_ns = ns;
get_mnt_ns(ns);
root.mnt = mnt;
root.dentry = mnt->mnt_root;
umount: Do not allow unmounting rootfs. Andrew Vagin <avagin@parallels.com> writes: > #define _GNU_SOURCE > #include <sys/types.h> > #include <sys/stat.h> > #include <fcntl.h> > #include <sched.h> > #include <unistd.h> > #include <sys/mount.h> > > int main(int argc, char **argv) > { > int fd; > > fd = open("/proc/self/ns/mnt", O_RDONLY); > if (fd < 0) > return 1; > while (1) { > if (umount2("/", MNT_DETACH) || > setns(fd, CLONE_NEWNS)) > break; > } > > return 0; > } > > root@ubuntu:/home/avagin# gcc -Wall nsenter.c -o nsenter > root@ubuntu:/home/avagin# strace ./nsenter > execve("./nsenter", ["./nsenter"], [/* 22 vars */]) = 0 > ... > open("/proc/self/ns/mnt", O_RDONLY) = 3 > umount("/", MNT_DETACH) = 0 > setns(3, 131072) = 0 > umount("/", MNT_DETACH > causes: > [ 260.548301] ------------[ cut here ]------------ > [ 260.550941] kernel BUG at /build/buildd/linux-3.13.0/fs/pnode.c:372! > [ 260.552068] invalid opcode: 0000 [#1] SMP > [ 260.552068] Modules linked in: xt_CHECKSUM iptable_mangle xt_tcpudp xt_addrtype xt_conntrack ipt_MASQUERADE iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack bridge stp llc dm_thin_pool dm_persistent_data dm_bufio dm_bio_prison iptable_filter ip_tables x_tables crct10dif_pclmul crc32_pclmul ghash_clmulni_intel binfmt_misc nfsd auth_rpcgss nfs_acl aesni_intel nfs lockd aes_x86_64 sunrpc fscache lrw gf128mul glue_helper ablk_helper cryptd serio_raw ppdev parport_pc lp parport btrfs xor raid6_pq libcrc32c psmouse floppy > [ 260.552068] CPU: 0 PID: 1723 Comm: nsenter Not tainted 3.13.0-30-generic #55-Ubuntu > [ 260.552068] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 > [ 260.552068] task: ffff8800376097f0 ti: ffff880074824000 task.ti: ffff880074824000 > [ 260.552068] RIP: 0010:[<ffffffff811e9483>] [<ffffffff811e9483>] propagate_umount+0x123/0x130 > [ 260.552068] RSP: 0018:ffff880074825e98 EFLAGS: 00010246 > [ 260.552068] RAX: ffff88007c741140 RBX: 0000000000000002 RCX: ffff88007c741190 > [ 260.552068] RDX: ffff88007c741190 RSI: ffff880074825ec0 RDI: ffff880074825ec0 > [ 260.552068] RBP: ffff880074825eb0 R08: 00000000000172e0 R09: ffff88007fc172e0 > [ 260.552068] R10: ffffffff811cc642 R11: ffffea0001d59000 R12: ffff88007c741140 > [ 260.552068] R13: ffff88007c741140 R14: ffff88007c741140 R15: 0000000000000000 > [ 260.552068] FS: 00007fd5c7e41740(0000) GS:ffff88007fc00000(0000) knlGS:0000000000000000 > [ 260.552068] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > [ 260.552068] CR2: 00007fd5c7968050 CR3: 0000000070124000 CR4: 00000000000406f0 > [ 260.552068] Stack: > [ 260.552068] 0000000000000002 0000000000000002 ffff88007c631000 ffff880074825ed8 > [ 260.552068] ffffffff811dcfac ffff88007c741140 0000000000000002 ffff88007c741160 > [ 260.552068] ffff880074825f38 ffffffff811dd12b ffffffff811cc642 0000000075640000 > [ 260.552068] Call Trace: > [ 260.552068] [<ffffffff811dcfac>] umount_tree+0x20c/0x260 > [ 260.552068] [<ffffffff811dd12b>] do_umount+0x12b/0x300 > [ 260.552068] [<ffffffff811cc642>] ? final_putname+0x22/0x50 > [ 260.552068] [<ffffffff811cc849>] ? putname+0x29/0x40 > [ 260.552068] [<ffffffff811dd88c>] SyS_umount+0xdc/0x100 > [ 260.552068] [<ffffffff8172aeff>] tracesys+0xe1/0xe6 > [ 260.552068] Code: 89 50 08 48 8b 50 08 48 89 02 49 89 45 08 e9 72 ff ff ff 0f 1f 44 00 00 4c 89 e6 4c 89 e7 e8 f5 f6 ff ff 48 89 c3 e9 39 ff ff ff <0f> 0b 66 2e 0f 1f 84 00 00 00 00 00 90 66 66 66 66 90 55 b8 01 > [ 260.552068] RIP [<ffffffff811e9483>] propagate_umount+0x123/0x130 > [ 260.552068] RSP <ffff880074825e98> > [ 260.611451] ---[ end trace 11c33d85f1d4c652 ]-- Which in practice is totally uninteresting. Only the global root user can do it, and it is just a stupid thing to do. However that is no excuse to allow a silly way to oops the kernel. We can avoid this silly problem by setting MNT_LOCKED on the rootfs mount point and thus avoid needing any special cases in the unmount code. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2014-10-07 19:19:53 +00:00
mnt->mnt_flags |= MNT_LOCKED;
set_fs_pwd(current->fs, &root);
set_fs_root(current->fs, &root);
}
void __init mnt_init(void)
{
unsigned u;
int err;
mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount),
0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
mount_hashtable = alloc_large_system_hash("Mount-cache",
sizeof(struct hlist_head),
mhash_entries, 19,
0,
&m_hash_shift, &m_hash_mask, 0, 0);
mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache",
sizeof(struct hlist_head),
mphash_entries, 19,
0,
&mp_hash_shift, &mp_hash_mask, 0, 0);
if (!mount_hashtable || !mountpoint_hashtable)
panic("Failed to allocate mount hash table\n");
for (u = 0; u <= m_hash_mask; u++)
INIT_HLIST_HEAD(&mount_hashtable[u]);
for (u = 0; u <= mp_hash_mask; u++)
INIT_HLIST_HEAD(&mountpoint_hashtable[u]);
kernfs_init();
err = sysfs_init();
if (err)
printk(KERN_WARNING "%s: sysfs_init error: %d\n",
__func__, err);
fs_kobj = kobject_create_and_add("fs", NULL);
if (!fs_kobj)
printk(KERN_WARNING "%s: kobj create error\n", __func__);
init_rootfs();
init_mount_tree();
}
void put_mnt_ns(struct mnt_namespace *ns)
{
if (!atomic_dec_and_test(&ns->count))
return;
drop_collected_mounts(&ns->root->mnt);
free_mnt_ns(ns);
}
struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
{
struct vfsmount *mnt;
mnt = vfs_kern_mount(type, MS_KERNMOUNT, type->name, data);
if (!IS_ERR(mnt)) {
/*
* it is a longterm mount, don't release mnt until
* we unmount before file sys is unregistered
*/
real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL;
}
return mnt;
}
EXPORT_SYMBOL_GPL(kern_mount_data);
void kern_unmount(struct vfsmount *mnt)
{
/* release long term mount so mount point can be released */
if (!IS_ERR_OR_NULL(mnt)) {
real_mount(mnt)->mnt_ns = NULL;
RCU'd vfsmounts * RCU-delayed freeing of vfsmounts * vfsmount_lock replaced with a seqlock (mount_lock) * sequence number from mount_lock is stored in nameidata->m_seq and used when we exit RCU mode * new vfsmount flag - MNT_SYNC_UMOUNT. Set by umount_tree() when its caller knows that vfsmount will have no surviving references. * synchronize_rcu() done between unlocking namespace_sem in namespace_unlock() and doing pending mntput(). * new helper: legitimize_mnt(mnt, seq). Checks the mount_lock sequence number against seq, then grabs reference to mnt. Then it rechecks mount_lock again to close the race and either returns success or drops the reference it has acquired. The subtle point is that in case of MNT_SYNC_UMOUNT we can simply decrement the refcount and sod off - aforementioned synchronize_rcu() makes sure that final mntput() won't come until we leave RCU mode. We need that, since we don't want to end up with some lazy pathwalk racing with umount() and stealing the final mntput() from it - caller of umount() may expect it to return only once the fs is shut down and we don't want to break that. In other cases (i.e. with MNT_SYNC_UMOUNT absent) we have to do full-blown mntput() in case of mount_lock sequence number mismatch happening just as we'd grabbed the reference, but in those cases we won't be stealing the final mntput() from anything that would care. * mntput_no_expire() doesn't lock anything on the fast path now. Incidentally, SMP and UP cases are handled the same way - no ifdefs there. * normal pathname resolution does *not* do any writes to mount_lock. It does, of course, bump the refcounts of vfsmount and dentry in the very end, but that's it. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2013-09-30 02:06:07 +00:00
synchronize_rcu(); /* yecchhh... */
mntput(mnt);
}
}
EXPORT_SYMBOL(kern_unmount);
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 13:43:34 +00:00
bool our_mnt(struct vfsmount *mnt)
{
return check_mnt(real_mount(mnt));
fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API __d_path() API is asking for trouble and in case of apparmor d_namespace_path() getting just that. The root cause is that when __d_path() misses the root it had been told to look for, it stores the location of the most remote ancestor in *root. Without grabbing references. Sure, at the moment of call it had been pinned down by what we have in *path. And if we raced with umount -l, we could have very well stopped at vfsmount/dentry that got freed as soon as prepend_path() dropped vfsmount_lock. It is safe to compare these pointers with pre-existing (and known to be still alive) vfsmount and dentry, as long as all we are asking is "is it the same address?". Dereferencing is not safe and apparmor ended up stepping into that. d_namespace_path() really wants to examine the place where we stopped, even if it's not connected to our namespace. As the result, it looked at ->d_sb->s_magic of a dentry that might've been already freed by that point. All other callers had been careful enough to avoid that, but it's really a bad interface - it invites that kind of trouble. The fix is fairly straightforward, even though it's bigger than I'd like: * prepend_path() root argument becomes const. * __d_path() is never called with NULL/NULL root. It was a kludge to start with. Instead, we have an explicit function - d_absolute_root(). Same as __d_path(), except that it doesn't get root passed and stops where it stops. apparmor and tomoyo are using it. * __d_path() returns NULL on path outside of root. The main caller is show_mountinfo() and that's precisely what we pass root for - to skip those outside chroot jail. Those who don't want that can (and do) use d_path(). * __d_path() root argument becomes const. Everyone agrees, I hope. * apparmor does *NOT* try to use __d_path() or any of its variants when it sees that path->mnt is an internal vfsmount. In that case it's definitely not mounted anywhere and dentry_path() is exactly what we want there. Handling of sysctl()-triggered weirdness is moved to that place. * if apparmor is asked to do pathname relative to chroot jail and __d_path() tells it we it's not in that jail, the sucker just calls d_absolute_path() instead. That's the other remaining caller of __d_path(), BTW. * seq_path_root() does _NOT_ return -ENAMETOOLONG (it's stupid anyway - the normal seq_file logics will take care of growing the buffer and redoing the call of ->show() just fine). However, if it gets path not reachable from root, it returns SEQ_SKIP. The only caller adjusted (i.e. stopped ignoring the return value as it used to do). Reviewed-by: John Johansen <john.johansen@canonical.com> ACKed-by: John Johansen <john.johansen@canonical.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Cc: stable@vger.kernel.org
2011-12-05 13:43:34 +00:00
}
bool current_chrooted(void)
{
/* Does the current process have a non-standard root */
struct path ns_root;
struct path fs_root;
bool chrooted;
/* Find the namespace root */
ns_root.mnt = &current->nsproxy->mnt_ns->root->mnt;
ns_root.dentry = ns_root.mnt->mnt_root;
path_get(&ns_root);
while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root))
;
get_fs_root(current->fs, &fs_root);
chrooted = !path_equal(&fs_root, &ns_root);
path_put(&fs_root);
path_put(&ns_root);
return chrooted;
}
bool fs_fully_visible(struct file_system_type *type)
{
struct mnt_namespace *ns = current->nsproxy->mnt_ns;
struct mount *mnt;
bool visible = false;
if (unlikely(!ns))
return false;
down_read(&namespace_sem);
list_for_each_entry(mnt, &ns->list, mnt_list) {
struct mount *child;
if (mnt->mnt.mnt_sb->s_type != type)
continue;
/* This mount is not fully visible if there are any child mounts
* that cover anything except for empty directories.
*/
list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
struct inode *inode = child->mnt_mountpoint->d_inode;
if (!S_ISDIR(inode->i_mode))
goto next;
if (inode->i_nlink > 2)
goto next;
}
visible = true;
goto found;
next: ;
}
found:
up_read(&namespace_sem);
return visible;
}
static struct ns_common *mntns_get(struct task_struct *task)
{
struct ns_common *ns = NULL;
struct nsproxy *nsproxy;
task_lock(task);
nsproxy = task->nsproxy;
if (nsproxy) {
ns = &nsproxy->mnt_ns->ns;
get_mnt_ns(to_mnt_ns(ns));
}
task_unlock(task);
return ns;
}
static void mntns_put(struct ns_common *ns)
{
put_mnt_ns(to_mnt_ns(ns));
}
static int mntns_install(struct nsproxy *nsproxy, struct ns_common *ns)
{
struct fs_struct *fs = current->fs;
struct mnt_namespace *mnt_ns = to_mnt_ns(ns);
struct path root;
if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) ||
!ns_capable(current_user_ns(), CAP_SYS_CHROOT) ||
!ns_capable(current_user_ns(), CAP_SYS_ADMIN))
return -EPERM;
if (fs->users != 1)
return -EINVAL;
get_mnt_ns(mnt_ns);
put_mnt_ns(nsproxy->mnt_ns);
nsproxy->mnt_ns = mnt_ns;
/* Find the root */
root.mnt = &mnt_ns->root->mnt;
root.dentry = mnt_ns->root->mnt.mnt_root;
path_get(&root);
while(d_mountpoint(root.dentry) && follow_down_one(&root))
;
/* Update the pwd and root */
set_fs_pwd(fs, &root);
set_fs_root(fs, &root);
path_put(&root);
return 0;
}
const struct proc_ns_operations mntns_operations = {
.name = "mnt",
.type = CLONE_NEWNS,
.get = mntns_get,
.put = mntns_put,
.install = mntns_install,
};