#include <linux/ramfs.h>
#include <linux/log2.h>
#include <linux/idr.h>
+#include <linux/fs_struct.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include "pnode.h"
int err;
err = mnt_alloc_id(mnt);
- if (err) {
- kmem_cache_free(mnt_cache, mnt);
- return NULL;
+ if (err)
+ goto out_free_cache;
+
+ if (name) {
+ mnt->mnt_devname = kstrdup(name, GFP_KERNEL);
+ if (!mnt->mnt_devname)
+ goto out_free_id;
}
atomic_set(&mnt->mnt_count, 1);
INIT_LIST_HEAD(&mnt->mnt_share);
INIT_LIST_HEAD(&mnt->mnt_slave_list);
INIT_LIST_HEAD(&mnt->mnt_slave);
- atomic_set(&mnt->__mnt_writers, 0);
- if (name) {
- int size = strlen(name) + 1;
- char *newname = kmalloc(size, GFP_KERNEL);
- if (newname) {
- memcpy(newname, name, size);
- mnt->mnt_devname = newname;
- }
- }
+#ifdef CONFIG_SMP
+ mnt->mnt_writers = alloc_percpu(int);
+ if (!mnt->mnt_writers)
+ goto out_free_devname;
+#else
+ mnt->mnt_writers = 0;
+#endif
}
return mnt;
+
+#ifdef CONFIG_SMP
+out_free_devname:
+ kfree(mnt->mnt_devname);
+#endif
+out_free_id:
+ mnt_free_id(mnt);
+out_free_cache:
+ kmem_cache_free(mnt_cache, mnt);
+ return NULL;
}
/*
}
EXPORT_SYMBOL_GPL(__mnt_is_readonly);
-struct mnt_writer {
- /*
- * If holding multiple instances of this lock, they
- * must be ordered by cpu number.
- */
- spinlock_t lock;
- struct lock_class_key lock_class; /* compiles out with !lockdep */
- unsigned long count;
- struct vfsmount *mnt;
-} ____cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(struct mnt_writer, mnt_writers);
+static inline void inc_mnt_writers(struct vfsmount *mnt)
+{
+#ifdef CONFIG_SMP
+ (*per_cpu_ptr(mnt->mnt_writers, smp_processor_id()))++;
+#else
+ mnt->mnt_writers++;
+#endif
+}
-static int __init init_mnt_writers(void)
+static inline void dec_mnt_writers(struct vfsmount *mnt)
{
- int cpu;
- for_each_possible_cpu(cpu) {
- struct mnt_writer *writer = &per_cpu(mnt_writers, cpu);
- spin_lock_init(&writer->lock);
- lockdep_set_class(&writer->lock, &writer->lock_class);
- writer->count = 0;
- }
- return 0;
+#ifdef CONFIG_SMP
+ (*per_cpu_ptr(mnt->mnt_writers, smp_processor_id()))--;
+#else
+ mnt->mnt_writers--;
+#endif
}
-fs_initcall(init_mnt_writers);
-static void unlock_mnt_writers(void)
+static unsigned int count_mnt_writers(struct vfsmount *mnt)
{
+#ifdef CONFIG_SMP
+ unsigned int count = 0;
int cpu;
- struct mnt_writer *cpu_writer;
for_each_possible_cpu(cpu) {
- cpu_writer = &per_cpu(mnt_writers, cpu);
- spin_unlock(&cpu_writer->lock);
+ count += *per_cpu_ptr(mnt->mnt_writers, cpu);
}
-}
-static inline void __clear_mnt_count(struct mnt_writer *cpu_writer)
-{
- if (!cpu_writer->mnt)
- return;
- /*
- * This is in case anyone ever leaves an invalid,
- * old ->mnt and a count of 0.
- */
- if (!cpu_writer->count)
- return;
- atomic_add(cpu_writer->count, &cpu_writer->mnt->__mnt_writers);
- cpu_writer->count = 0;
-}
- /*
- * must hold cpu_writer->lock
- */
-static inline void use_cpu_writer_for_mount(struct mnt_writer *cpu_writer,
- struct vfsmount *mnt)
-{
- if (cpu_writer->mnt == mnt)
- return;
- __clear_mnt_count(cpu_writer);
- cpu_writer->mnt = mnt;
+ return count;
+#else
+ return mnt->mnt_writers;
+#endif
}
/*
int mnt_want_write(struct vfsmount *mnt)
{
int ret = 0;
- struct mnt_writer *cpu_writer;
- cpu_writer = &get_cpu_var(mnt_writers);
- spin_lock(&cpu_writer->lock);
+ preempt_disable();
+ inc_mnt_writers(mnt);
+ /*
+ * The store to inc_mnt_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 (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(mnt)) {
+ dec_mnt_writers(mnt);
ret = -EROFS;
goto out;
}
- use_cpu_writer_for_mount(cpu_writer, mnt);
- cpu_writer->count++;
out:
- spin_unlock(&cpu_writer->lock);
- put_cpu_var(mnt_writers);
+ preempt_enable();
return ret;
}
EXPORT_SYMBOL_GPL(mnt_want_write);
-static void lock_mnt_writers(void)
-{
- int cpu;
- struct mnt_writer *cpu_writer;
-
- for_each_possible_cpu(cpu) {
- cpu_writer = &per_cpu(mnt_writers, cpu);
- spin_lock(&cpu_writer->lock);
- __clear_mnt_count(cpu_writer);
- cpu_writer->mnt = NULL;
- }
+/**
+ * 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();
+ inc_mnt_writers(mnt);
+ preempt_enable();
+ return 0;
}
+EXPORT_SYMBOL_GPL(mnt_clone_write);
-/*
- * These per-cpu write counts are not guaranteed to have
- * matched increments and decrements on any given cpu.
- * A file open()ed for write on one cpu and close()d on
- * another cpu will imbalance this count. Make sure it
- * does not get too far out of whack.
+/**
+ * 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
*/
-static void handle_write_count_underflow(struct vfsmount *mnt)
+int mnt_want_write_file(struct file *file)
{
- if (atomic_read(&mnt->__mnt_writers) >=
- MNT_WRITER_UNDERFLOW_LIMIT)
- return;
- /*
- * It isn't necessary to hold all of the locks
- * at the same time, but doing it this way makes
- * us share a lot more code.
- */
- lock_mnt_writers();
- /*
- * vfsmount_lock is for mnt_flags.
- */
- spin_lock(&vfsmount_lock);
- /*
- * If coalescing the per-cpu writer counts did not
- * get us back to a positive writer count, we have
- * a bug.
- */
- if ((atomic_read(&mnt->__mnt_writers) < 0) &&
- !(mnt->mnt_flags & MNT_IMBALANCED_WRITE_COUNT)) {
- printk(KERN_DEBUG "leak detected on mount(%p) writers "
- "count: %d\n",
- mnt, atomic_read(&mnt->__mnt_writers));
- WARN_ON(1);
- /* use the flag to keep the dmesg spam down */
- mnt->mnt_flags |= MNT_IMBALANCED_WRITE_COUNT;
- }
- spin_unlock(&vfsmount_lock);
- unlock_mnt_writers();
+ if (!(file->f_mode & FMODE_WRITE))
+ return mnt_want_write(file->f_path.mnt);
+ else
+ return mnt_clone_write(file->f_path.mnt);
}
+EXPORT_SYMBOL_GPL(mnt_want_write_file);
/**
* mnt_drop_write - give up write access to a mount
*/
void mnt_drop_write(struct vfsmount *mnt)
{
- int must_check_underflow = 0;
- struct mnt_writer *cpu_writer;
-
- cpu_writer = &get_cpu_var(mnt_writers);
- spin_lock(&cpu_writer->lock);
-
- use_cpu_writer_for_mount(cpu_writer, mnt);
- if (cpu_writer->count > 0) {
- cpu_writer->count--;
- } else {
- must_check_underflow = 1;
- atomic_dec(&mnt->__mnt_writers);
- }
-
- spin_unlock(&cpu_writer->lock);
- /*
- * Logically, we could call this each time,
- * but the __mnt_writers cacheline tends to
- * be cold, and makes this expensive.
- */
- if (must_check_underflow)
- handle_write_count_underflow(mnt);
- /*
- * This could be done right after the spinlock
- * is taken because the spinlock keeps us on
- * the cpu, and disables preemption. However,
- * putting it here bounds the amount that
- * __mnt_writers can underflow. Without it,
- * we could theoretically wrap __mnt_writers.
- */
- put_cpu_var(mnt_writers);
+ preempt_disable();
+ dec_mnt_writers(mnt);
+ preempt_enable();
}
EXPORT_SYMBOL_GPL(mnt_drop_write);
{
int ret = 0;
- lock_mnt_writers();
+ spin_lock(&vfsmount_lock);
+ mnt->mnt_flags |= MNT_WRITE_HOLD;
/*
- * With all the locks held, this value is stable
+ * After storing MNT_WRITE_HOLD, we'll read the counters. This store
+ * should be visible before we do.
*/
- if (atomic_read(&mnt->__mnt_writers) > 0) {
- ret = -EBUSY;
- goto out;
- }
+ smp_mb();
+
/*
- * nobody can do a successful mnt_want_write() with all
- * of the counts in MNT_DENIED_WRITE and the locks held.
+ * 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.
*/
- spin_lock(&vfsmount_lock);
- if (!ret)
+ if (count_mnt_writers(mnt) > 0)
+ ret = -EBUSY;
+ else
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_flags &= ~MNT_WRITE_HOLD;
spin_unlock(&vfsmount_lock);
-out:
- unlock_mnt_writers();
return ret;
}
spin_unlock(&vfsmount_lock);
}
-int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb)
+void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb)
{
mnt->mnt_sb = sb;
mnt->mnt_root = dget(sb->s_root);
- return 0;
}
EXPORT_SYMBOL(simple_set_mnt);
{
kfree(mnt->mnt_devname);
mnt_free_id(mnt);
+#ifdef CONFIG_SMP
+ free_percpu(mnt->mnt_writers);
+#endif
kmem_cache_free(mnt_cache, mnt);
}
* lookup_mnt increments the ref count before returning
* the vfsmount struct.
*/
-struct vfsmount *lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
+struct vfsmount *lookup_mnt(struct path *path)
{
struct vfsmount *child_mnt;
spin_lock(&vfsmount_lock);
- if ((child_mnt = __lookup_mnt(mnt, dentry, 1)))
+ if ((child_mnt = __lookup_mnt(path->mnt, path->dentry, 1)))
mntget(child_mnt);
spin_unlock(&vfsmount_lock);
return child_mnt;
static inline void __mntput(struct vfsmount *mnt)
{
- int cpu;
struct super_block *sb = mnt->mnt_sb;
/*
- * We don't have to hold all of the locks at the
- * same time here because we know that we're the
- * last reference to mnt and that no new writers
- * can come in.
- */
- for_each_possible_cpu(cpu) {
- struct mnt_writer *cpu_writer = &per_cpu(mnt_writers, cpu);
- if (cpu_writer->mnt != mnt)
- continue;
- spin_lock(&cpu_writer->lock);
- atomic_add(cpu_writer->count, &mnt->__mnt_writers);
- cpu_writer->count = 0;
- /*
- * Might as well do this so that no one
- * ever sees the pointer and expects
- * it to be valid.
- */
- cpu_writer->mnt = NULL;
- spin_unlock(&cpu_writer->lock);
- }
- /*
* 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.
*/
- WARN_ON(atomic_read(&mnt->__mnt_writers));
+ /*
+ * atomic_dec_and_lock() used to deal with ->mnt_count decrements
+ * provides barriers, so count_mnt_writers() below is safe. AV
+ */
+ WARN_ON(count_mnt_writers(mnt));
dput(mnt->mnt_root);
free_vfsmnt(mnt);
deactivate_super(sb);
*/
int generic_show_options(struct seq_file *m, struct vfsmount *mnt)
{
- const char *options = mnt->mnt_sb->s_options;
+ const char *options;
+
+ rcu_read_lock();
+ options = rcu_dereference(mnt->mnt_sb->s_options);
if (options != NULL && options[0]) {
seq_putc(m, ',');
mangle(m, options);
}
+ rcu_read_unlock();
return 0;
}
*/
void save_mount_options(struct super_block *sb, char *options)
{
- kfree(sb->s_options);
- sb->s_options = kstrdup(options, GFP_KERNEL);
+ 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 */
static void *m_start(struct seq_file *m, loff_t *pos)
const char *str;
};
-static void show_sb_opts(struct seq_file *m, struct super_block *sb)
+static int show_sb_opts(struct seq_file *m, struct super_block *sb)
{
static const struct proc_fs_info fs_info[] = {
{ MS_SYNCHRONOUS, ",sync" },
if (sb->s_flags & fs_infop->flag)
seq_puts(m, fs_infop->str);
}
+
+ return security_sb_show_options(m, sb);
}
static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt)
{ MNT_NOATIME, ",noatime" },
{ MNT_NODIRATIME, ",nodiratime" },
{ MNT_RELATIME, ",relatime" },
+ { MNT_STRICTATIME, ",strictatime" },
{ 0, NULL }
};
const struct proc_fs_info *fs_infop;
seq_putc(m, ' ');
show_type(m, mnt->mnt_sb);
seq_puts(m, __mnt_is_readonly(mnt) ? " ro" : " rw");
- show_sb_opts(m, mnt->mnt_sb);
+ err = show_sb_opts(m, mnt->mnt_sb);
+ if (err)
+ goto out;
show_mnt_opts(m, mnt);
if (mnt->mnt_sb->s_op->show_options)
err = mnt->mnt_sb->s_op->show_options(m, mnt);
seq_puts(m, " 0 0\n");
+out:
return err;
}
seq_putc(m, ' ');
mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw");
- show_sb_opts(m, sb);
+ err = show_sb_opts(m, sb);
+ if (err)
+ goto out;
if (sb->s_op->show_options)
err = sb->s_op->show_options(m, mnt);
seq_putc(m, '\n');
+out:
return err;
}
*/
if (flags & MNT_FORCE && sb->s_op->umount_begin) {
- lock_kernel();
sb->s_op->umount_begin(sb);
- unlock_kernel();
}
/*
* we just try to remount it readonly.
*/
down_write(&sb->s_umount);
- if (!(sb->s_flags & MS_RDONLY)) {
- lock_kernel();
+ if (!(sb->s_flags & MS_RDONLY))
retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
- unlock_kernel();
- }
up_write(&sb->s_umount);
return retval;
}
* unixes. Our API is identical to OSF/1 to avoid making a mess of AMD
*/
-asmlinkage long sys_umount(char __user * name, int flags)
+SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
{
- struct nameidata nd;
+ struct path path;
int retval;
- retval = __user_walk(name, LOOKUP_FOLLOW, &nd);
+ retval = user_path(name, &path);
if (retval)
goto out;
retval = -EINVAL;
- if (nd.path.dentry != nd.path.mnt->mnt_root)
+ if (path.dentry != path.mnt->mnt_root)
goto dput_and_out;
- if (!check_mnt(nd.path.mnt))
+ if (!check_mnt(path.mnt))
goto dput_and_out;
retval = -EPERM;
if (!capable(CAP_SYS_ADMIN))
goto dput_and_out;
- retval = do_umount(nd.path.mnt, flags);
+ retval = do_umount(path.mnt, flags);
dput_and_out:
/* we mustn't call path_put() as that would clear mnt_expiry_mark */
- dput(nd.path.dentry);
- mntput_no_expire(nd.path.mnt);
+ dput(path.dentry);
+ mntput_no_expire(path.mnt);
out:
return retval;
}
/*
* The 2.0 compatible umount. No flags.
*/
-asmlinkage long sys_oldumount(char __user * name)
+SYSCALL_DEFINE1(oldumount, char __user *, name)
{
return sys_umount(name, 0);
}
#endif
-static int mount_is_safe(struct nameidata *nd)
+static int mount_is_safe(struct path *path)
{
if (capable(CAP_SYS_ADMIN))
return 0;
return -EPERM;
#ifdef notyet
- if (S_ISLNK(nd->path.dentry->d_inode->i_mode))
+ if (S_ISLNK(path->dentry->d_inode->i_mode))
return -EPERM;
- if (nd->path.dentry->d_inode->i_mode & S_ISVTX) {
- if (current->uid != nd->path.dentry->d_inode->i_uid)
+ if (path->dentry->d_inode->i_mode & S_ISVTX) {
+ if (current_uid() != path->dentry->d_inode->i_uid)
return -EPERM;
}
- if (vfs_permission(nd, MAY_WRITE))
+ if (inode_permission(path->dentry->d_inode, MAY_WRITE))
return -EPERM;
return 0;
#endif
return NULL;
}
-struct vfsmount *collect_mounts(struct vfsmount *mnt, struct dentry *dentry)
+struct vfsmount *collect_mounts(struct path *path)
{
struct vfsmount *tree;
down_write(&namespace_sem);
- tree = copy_tree(mnt, dentry, CL_COPY_ALL | CL_PRIVATE);
+ tree = copy_tree(path->mnt, path->dentry, CL_COPY_ALL | CL_PRIVATE);
up_write(&namespace_sem);
return tree;
}
if (parent_path) {
detach_mnt(source_mnt, parent_path);
attach_mnt(source_mnt, path);
- touch_mnt_namespace(current->nsproxy->mnt_ns);
+ touch_mnt_namespace(parent_path->mnt->mnt_ns);
} else {
mnt_set_mountpoint(dest_mnt, dest_dentry, source_mnt);
commit_tree(source_mnt);
goto out_unlock;
err = -ENOENT;
- if (IS_ROOT(path->dentry) || !d_unhashed(path->dentry))
+ if (!d_unlinked(path->dentry))
err = attach_recursive_mnt(mnt, path, NULL);
out_unlock:
mutex_unlock(&path->dentry->d_inode->i_mutex);
/*
* recursively change the type of the mountpoint.
- * noinline this do_mount helper to save do_mount stack space.
*/
-static noinline int do_change_type(struct nameidata *nd, int flag)
+static int do_change_type(struct path *path, int flag)
{
- struct vfsmount *m, *mnt = nd->path.mnt;
+ struct vfsmount *m, *mnt = path->mnt;
int recurse = flag & MS_REC;
int type = flag & ~MS_REC;
int err = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (nd->path.dentry != nd->path.mnt->mnt_root)
+ if (path->dentry != path->mnt->mnt_root)
return -EINVAL;
down_write(&namespace_sem);
/*
* do loopback mount.
- * noinline this do_mount helper to save do_mount stack space.
*/
-static noinline int do_loopback(struct nameidata *nd, char *old_name,
+static int do_loopback(struct path *path, char *old_name,
int recurse)
{
- struct nameidata old_nd;
+ struct path old_path;
struct vfsmount *mnt = NULL;
- int err = mount_is_safe(nd);
+ int err = mount_is_safe(path);
if (err)
return err;
if (!old_name || !*old_name)
return -EINVAL;
- err = path_lookup(old_name, LOOKUP_FOLLOW, &old_nd);
+ err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
if (err)
return err;
down_write(&namespace_sem);
err = -EINVAL;
- if (IS_MNT_UNBINDABLE(old_nd.path.mnt))
+ if (IS_MNT_UNBINDABLE(old_path.mnt))
goto out;
- if (!check_mnt(nd->path.mnt) || !check_mnt(old_nd.path.mnt))
+ if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
goto out;
err = -ENOMEM;
if (recurse)
- mnt = copy_tree(old_nd.path.mnt, old_nd.path.dentry, 0);
+ mnt = copy_tree(old_path.mnt, old_path.dentry, 0);
else
- mnt = clone_mnt(old_nd.path.mnt, old_nd.path.dentry, 0);
+ mnt = clone_mnt(old_path.mnt, old_path.dentry, 0);
if (!mnt)
goto out;
- err = graft_tree(mnt, &nd->path);
+ err = graft_tree(mnt, path);
if (err) {
LIST_HEAD(umount_list);
spin_lock(&vfsmount_lock);
out:
up_write(&namespace_sem);
- path_put(&old_nd.path);
+ path_put(&old_path);
return err;
}
* 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.
- * noinline this do_mount helper to save do_mount stack space.
*/
-static noinline int do_remount(struct nameidata *nd, int flags, int mnt_flags,
+static int do_remount(struct path *path, int flags, int mnt_flags,
void *data)
{
int err;
- struct super_block *sb = nd->path.mnt->mnt_sb;
+ struct super_block *sb = path->mnt->mnt_sb;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!check_mnt(nd->path.mnt))
+ if (!check_mnt(path->mnt))
return -EINVAL;
- if (nd->path.dentry != nd->path.mnt->mnt_root)
+ if (path->dentry != path->mnt->mnt_root)
return -EINVAL;
down_write(&sb->s_umount);
if (flags & MS_BIND)
- err = change_mount_flags(nd->path.mnt, flags);
+ err = change_mount_flags(path->mnt, flags);
else
err = do_remount_sb(sb, flags, data, 0);
if (!err)
- nd->path.mnt->mnt_flags = mnt_flags;
+ path->mnt->mnt_flags = mnt_flags;
up_write(&sb->s_umount);
- if (!err)
- security_sb_post_remount(nd->path.mnt, flags, data);
+ if (!err) {
+ security_sb_post_remount(path->mnt, flags, data);
+
+ spin_lock(&vfsmount_lock);
+ touch_mnt_namespace(path->mnt->mnt_ns);
+ spin_unlock(&vfsmount_lock);
+ }
return err;
}
return 0;
}
-/*
- * noinline this do_mount helper to save do_mount stack space.
- */
-static noinline int do_move_mount(struct nameidata *nd, char *old_name)
+static int do_move_mount(struct path *path, char *old_name)
{
- struct nameidata old_nd;
- struct path parent_path;
+ struct path old_path, parent_path;
struct vfsmount *p;
int err = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!old_name || !*old_name)
return -EINVAL;
- err = path_lookup(old_name, LOOKUP_FOLLOW, &old_nd);
+ err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
if (err)
return err;
down_write(&namespace_sem);
- while (d_mountpoint(nd->path.dentry) &&
- follow_down(&nd->path.mnt, &nd->path.dentry))
+ while (d_mountpoint(path->dentry) &&
+ follow_down(path))
;
err = -EINVAL;
- if (!check_mnt(nd->path.mnt) || !check_mnt(old_nd.path.mnt))
+ if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
goto out;
err = -ENOENT;
- mutex_lock(&nd->path.dentry->d_inode->i_mutex);
- if (IS_DEADDIR(nd->path.dentry->d_inode))
+ mutex_lock(&path->dentry->d_inode->i_mutex);
+ if (IS_DEADDIR(path->dentry->d_inode))
goto out1;
- if (!IS_ROOT(nd->path.dentry) && d_unhashed(nd->path.dentry))
+ if (d_unlinked(path->dentry))
goto out1;
err = -EINVAL;
- if (old_nd.path.dentry != old_nd.path.mnt->mnt_root)
+ if (old_path.dentry != old_path.mnt->mnt_root)
goto out1;
- if (old_nd.path.mnt == old_nd.path.mnt->mnt_parent)
+ if (old_path.mnt == old_path.mnt->mnt_parent)
goto out1;
- if (S_ISDIR(nd->path.dentry->d_inode->i_mode) !=
- S_ISDIR(old_nd.path.dentry->d_inode->i_mode))
+ if (S_ISDIR(path->dentry->d_inode->i_mode) !=
+ S_ISDIR(old_path.dentry->d_inode->i_mode))
goto out1;
/*
* Don't move a mount residing in a shared parent.
*/
- if (old_nd.path.mnt->mnt_parent &&
- IS_MNT_SHARED(old_nd.path.mnt->mnt_parent))
+ if (old_path.mnt->mnt_parent &&
+ IS_MNT_SHARED(old_path.mnt->mnt_parent))
goto out1;
/*
* Don't move a mount tree containing unbindable mounts to a destination
* mount which is shared.
*/
- if (IS_MNT_SHARED(nd->path.mnt) &&
- tree_contains_unbindable(old_nd.path.mnt))
+ if (IS_MNT_SHARED(path->mnt) &&
+ tree_contains_unbindable(old_path.mnt))
goto out1;
err = -ELOOP;
- for (p = nd->path.mnt; p->mnt_parent != p; p = p->mnt_parent)
- if (p == old_nd.path.mnt)
+ for (p = path->mnt; p->mnt_parent != p; p = p->mnt_parent)
+ if (p == old_path.mnt)
goto out1;
- err = attach_recursive_mnt(old_nd.path.mnt, &nd->path, &parent_path);
+ err = attach_recursive_mnt(old_path.mnt, path, &parent_path);
if (err)
goto out1;
/* if the mount is moved, it should no longer be expire
* automatically */
- list_del_init(&old_nd.path.mnt->mnt_expire);
+ list_del_init(&old_path.mnt->mnt_expire);
out1:
- mutex_unlock(&nd->path.dentry->d_inode->i_mutex);
+ mutex_unlock(&path->dentry->d_inode->i_mutex);
out:
up_write(&namespace_sem);
if (!err)
path_put(&parent_path);
- path_put(&old_nd.path);
+ path_put(&old_path);
return err;
}
/*
* create a new mount for userspace and request it to be added into the
* namespace's tree
- * noinline this do_mount helper to save do_mount stack space.
*/
-static noinline int do_new_mount(struct nameidata *nd, char *type, int flags,
+static int do_new_mount(struct path *path, char *type, int flags,
int mnt_flags, char *name, void *data)
{
struct vfsmount *mnt;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ lock_kernel();
mnt = do_kern_mount(type, flags, name, data);
+ unlock_kernel();
if (IS_ERR(mnt))
return PTR_ERR(mnt);
- return do_add_mount(mnt, nd, mnt_flags, NULL);
+ return do_add_mount(mnt, path, mnt_flags, NULL);
}
/*
* add a mount into a namespace's mount tree
* - provide the option of adding the new mount to an expiration list
*/
-int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd,
+int do_add_mount(struct vfsmount *newmnt, struct path *path,
int mnt_flags, struct list_head *fslist)
{
int err;
down_write(&namespace_sem);
/* Something was mounted here while we slept */
- while (d_mountpoint(nd->path.dentry) &&
- follow_down(&nd->path.mnt, &nd->path.dentry))
+ while (d_mountpoint(path->dentry) &&
+ follow_down(path))
;
err = -EINVAL;
- if (!check_mnt(nd->path.mnt))
+ if (!(mnt_flags & MNT_SHRINKABLE) && !check_mnt(path->mnt))
goto unlock;
/* Refuse the same filesystem on the same mount point */
err = -EBUSY;
- if (nd->path.mnt->mnt_sb == newmnt->mnt_sb &&
- nd->path.mnt->mnt_root == nd->path.dentry)
+ if (path->mnt->mnt_sb == newmnt->mnt_sb &&
+ path->mnt->mnt_root == path->dentry)
goto unlock;
err = -EINVAL;
goto unlock;
newmnt->mnt_flags = mnt_flags;
- if ((err = graft_tree(newmnt, &nd->path)))
+ if ((err = graft_tree(newmnt, path)))
goto unlock;
if (fslist) /* add to the specified expiration list */
while (!list_empty(&graveyard)) {
m = list_first_entry(&graveyard, struct vfsmount,
mnt_expire);
- touch_mnt_namespace(mnt->mnt_ns);
- umount_tree(mnt, 1, umounts);
+ touch_mnt_namespace(m->mnt_ns);
+ umount_tree(m, 1, umounts);
}
}
}
long do_mount(char *dev_name, char *dir_name, char *type_page,
unsigned long flags, void *data_page)
{
- struct nameidata nd;
+ struct path path;
int retval = 0;
int mnt_flags = 0;
if (data_page)
((char *)data_page)[PAGE_SIZE - 1] = 0;
+ /* 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;
mnt_flags |= MNT_NOATIME;
if (flags & MS_NODIRATIME)
mnt_flags |= MNT_NODIRATIME;
- if (flags & MS_RELATIME)
- mnt_flags |= MNT_RELATIME;
+ if (flags & MS_STRICTATIME)
+ mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME);
if (flags & MS_RDONLY)
mnt_flags |= MNT_READONLY;
flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE |
- MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT);
+ MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
+ MS_STRICTATIME);
/* ... and get the mountpoint */
- retval = path_lookup(dir_name, LOOKUP_FOLLOW, &nd);
+ retval = kern_path(dir_name, LOOKUP_FOLLOW, &path);
if (retval)
return retval;
- retval = security_sb_mount(dev_name, &nd.path,
+ retval = security_sb_mount(dev_name, &path,
type_page, flags, data_page);
if (retval)
goto dput_out;
if (flags & MS_REMOUNT)
- retval = do_remount(&nd, flags & ~MS_REMOUNT, mnt_flags,
+ retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags,
data_page);
else if (flags & MS_BIND)
- retval = do_loopback(&nd, dev_name, flags & MS_REC);
+ retval = do_loopback(&path, dev_name, flags & MS_REC);
else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
- retval = do_change_type(&nd, flags);
+ retval = do_change_type(&path, flags);
else if (flags & MS_MOVE)
- retval = do_move_mount(&nd, dev_name);
+ retval = do_move_mount(&path, dev_name);
else
- retval = do_new_mount(&nd, type_page, flags, mnt_flags,
+ retval = do_new_mount(&path, type_page, flags, mnt_flags,
dev_name, data_page);
dput_out:
- path_put(&nd.path);
+ path_put(&path);
return retval;
}
struct fs_struct *fs)
{
struct mnt_namespace *new_ns;
- struct vfsmount *rootmnt = NULL, *pwdmnt = NULL, *altrootmnt = NULL;
+ struct vfsmount *rootmnt = NULL, *pwdmnt = NULL;
struct vfsmount *p, *q;
new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
if (!new_ns->root) {
up_write(&namespace_sem);
kfree(new_ns);
- return ERR_PTR(-ENOMEM);;
+ return ERR_PTR(-ENOMEM);
}
spin_lock(&vfsmount_lock);
list_add_tail(&new_ns->list, &new_ns->root->mnt_list);
pwdmnt = p;
fs->pwd.mnt = mntget(q);
}
- if (p == fs->altroot.mnt) {
- altrootmnt = p;
- fs->altroot.mnt = mntget(q);
- }
}
p = next_mnt(p, mnt_ns->root);
q = next_mnt(q, new_ns->root);
mntput(rootmnt);
if (pwdmnt)
mntput(pwdmnt);
- if (altrootmnt)
- mntput(altrootmnt);
return new_ns;
}
return new_ns;
}
-asmlinkage long sys_mount(char __user * dev_name, char __user * dir_name,
- char __user * type, unsigned long flags,
- void __user * data)
+SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
+ char __user *, type, unsigned long, flags, void __user *, data)
{
int retval;
unsigned long data_page;
if (retval < 0)
goto out3;
- lock_kernel();
retval = do_mount((char *)dev_page, dir_page, (char *)type_page,
flags, (void *)data_page);
- unlock_kernel();
free_page(data_page);
out3:
}
/*
- * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
- * It can block. Requires the big lock held.
- */
-void set_fs_root(struct fs_struct *fs, struct path *path)
-{
- struct path old_root;
-
- write_lock(&fs->lock);
- old_root = fs->root;
- fs->root = *path;
- path_get(path);
- write_unlock(&fs->lock);
- if (old_root.dentry)
- path_put(&old_root);
-}
-
-/*
- * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values.
- * It can block. Requires the big lock held.
- */
-void set_fs_pwd(struct fs_struct *fs, struct path *path)
-{
- struct path old_pwd;
-
- write_lock(&fs->lock);
- old_pwd = fs->pwd;
- fs->pwd = *path;
- path_get(path);
- write_unlock(&fs->lock);
-
- if (old_pwd.dentry)
- path_put(&old_pwd);
-}
-
-static void chroot_fs_refs(struct path *old_root, struct path *new_root)
-{
- struct task_struct *g, *p;
- struct fs_struct *fs;
-
- read_lock(&tasklist_lock);
- do_each_thread(g, p) {
- task_lock(p);
- fs = p->fs;
- if (fs) {
- atomic_inc(&fs->count);
- task_unlock(p);
- if (fs->root.dentry == old_root->dentry
- && fs->root.mnt == old_root->mnt)
- set_fs_root(fs, new_root);
- if (fs->pwd.dentry == old_root->dentry
- && fs->pwd.mnt == old_root->mnt)
- set_fs_pwd(fs, new_root);
- put_fs_struct(fs);
- } else
- task_unlock(p);
- } while_each_thread(g, p);
- read_unlock(&tasklist_lock);
-}
-
-/*
* 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
* though, so you may need to say mount --bind /nfs/my_root /nfs/my_root
* first.
*/
-asmlinkage long sys_pivot_root(const char __user * new_root,
- const char __user * put_old)
+SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
+ const char __user *, put_old)
{
struct vfsmount *tmp;
- struct nameidata new_nd, old_nd;
- struct path parent_path, root_parent, root;
+ struct path new, old, parent_path, root_parent, root;
int error;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- error = __user_walk(new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY,
- &new_nd);
+ error = user_path_dir(new_root, &new);
if (error)
goto out0;
error = -EINVAL;
- if (!check_mnt(new_nd.path.mnt))
+ if (!check_mnt(new.mnt))
goto out1;
- error = __user_walk(put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old_nd);
+ error = user_path_dir(put_old, &old);
if (error)
goto out1;
- error = security_sb_pivotroot(&old_nd.path, &new_nd.path);
+ error = security_sb_pivotroot(&old, &new);
if (error) {
- path_put(&old_nd.path);
+ path_put(&old);
goto out1;
}
path_get(¤t->fs->root);
read_unlock(¤t->fs->lock);
down_write(&namespace_sem);
- mutex_lock(&old_nd.path.dentry->d_inode->i_mutex);
+ mutex_lock(&old.dentry->d_inode->i_mutex);
error = -EINVAL;
- if (IS_MNT_SHARED(old_nd.path.mnt) ||
- IS_MNT_SHARED(new_nd.path.mnt->mnt_parent) ||
+ if (IS_MNT_SHARED(old.mnt) ||
+ IS_MNT_SHARED(new.mnt->mnt_parent) ||
IS_MNT_SHARED(root.mnt->mnt_parent))
goto out2;
if (!check_mnt(root.mnt))
goto out2;
error = -ENOENT;
- if (IS_DEADDIR(new_nd.path.dentry->d_inode))
+ if (IS_DEADDIR(new.dentry->d_inode))
goto out2;
- if (d_unhashed(new_nd.path.dentry) && !IS_ROOT(new_nd.path.dentry))
+ if (d_unlinked(new.dentry))
goto out2;
- if (d_unhashed(old_nd.path.dentry) && !IS_ROOT(old_nd.path.dentry))
+ if (d_unlinked(old.dentry))
goto out2;
error = -EBUSY;
- if (new_nd.path.mnt == root.mnt ||
- old_nd.path.mnt == root.mnt)
+ if (new.mnt == root.mnt ||
+ old.mnt == root.mnt)
goto out2; /* loop, on the same file system */
error = -EINVAL;
if (root.mnt->mnt_root != root.dentry)
goto out2; /* not a mountpoint */
if (root.mnt->mnt_parent == root.mnt)
goto out2; /* not attached */
- if (new_nd.path.mnt->mnt_root != new_nd.path.dentry)
+ if (new.mnt->mnt_root != new.dentry)
goto out2; /* not a mountpoint */
- if (new_nd.path.mnt->mnt_parent == new_nd.path.mnt)
+ if (new.mnt->mnt_parent == new.mnt)
goto out2; /* not attached */
/* make sure we can reach put_old from new_root */
- tmp = old_nd.path.mnt;
+ tmp = old.mnt;
spin_lock(&vfsmount_lock);
- if (tmp != new_nd.path.mnt) {
+ if (tmp != new.mnt) {
for (;;) {
if (tmp->mnt_parent == tmp)
goto out3; /* already mounted on put_old */
- if (tmp->mnt_parent == new_nd.path.mnt)
+ if (tmp->mnt_parent == new.mnt)
break;
tmp = tmp->mnt_parent;
}
- if (!is_subdir(tmp->mnt_mountpoint, new_nd.path.dentry))
+ if (!is_subdir(tmp->mnt_mountpoint, new.dentry))
goto out3;
- } else if (!is_subdir(old_nd.path.dentry, new_nd.path.dentry))
+ } else if (!is_subdir(old.dentry, new.dentry))
goto out3;
- detach_mnt(new_nd.path.mnt, &parent_path);
+ detach_mnt(new.mnt, &parent_path);
detach_mnt(root.mnt, &root_parent);
/* mount old root on put_old */
- attach_mnt(root.mnt, &old_nd.path);
+ attach_mnt(root.mnt, &old);
/* mount new_root on / */
- attach_mnt(new_nd.path.mnt, &root_parent);
+ attach_mnt(new.mnt, &root_parent);
touch_mnt_namespace(current->nsproxy->mnt_ns);
spin_unlock(&vfsmount_lock);
- chroot_fs_refs(&root, &new_nd.path);
- security_sb_post_pivotroot(&root, &new_nd.path);
+ chroot_fs_refs(&root, &new);
+ security_sb_post_pivotroot(&root, &new);
error = 0;
path_put(&root_parent);
path_put(&parent_path);
out2:
- mutex_unlock(&old_nd.path.dentry->d_inode->i_mutex);
+ mutex_unlock(&old.dentry->d_inode->i_mutex);
up_write(&namespace_sem);
path_put(&root);
- path_put(&old_nd.path);
+ path_put(&old);
out1:
- path_put(&new_nd.path);
+ path_put(&new);
out0:
return error;
out3: