summaryrefslogtreecommitdiff
path: root/fs/namespace.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/namespace.c')
-rw-r--r--fs/namespace.c157
1 files changed, 69 insertions, 88 deletions
diff --git a/fs/namespace.c b/fs/namespace.c
index 4272349650b1..c58674a20cad 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1336,26 +1336,12 @@ static void delayed_mntput(struct work_struct *unused)
}
static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput);
-static void mntput_no_expire(struct mount *mnt)
+static void noinline mntput_no_expire_slowpath(struct mount *mnt)
{
LIST_HEAD(list);
int count;
- rcu_read_lock();
- if (likely(READ_ONCE(mnt->mnt_ns))) {
- /*
- * Since we don't do lock_mount_hash() here,
- * ->mnt_ns can change under us. However, if it's
- * non-NULL, then there's a reference that won't
- * be dropped until after an RCU delay done after
- * turning ->mnt_ns NULL. So if we observe it
- * non-NULL under rcu_read_lock(), the reference
- * we are dropping is not the final one.
- */
- mnt_add_count(mnt, -1);
- rcu_read_unlock();
- return;
- }
+ VFS_BUG_ON(mnt->mnt_ns);
lock_mount_hash();
/*
* make sure that if __legitimize_mnt() has not seen us grab
@@ -1406,6 +1392,26 @@ static void mntput_no_expire(struct mount *mnt)
cleanup_mnt(mnt);
}
+static void mntput_no_expire(struct mount *mnt)
+{
+ rcu_read_lock();
+ if (likely(READ_ONCE(mnt->mnt_ns))) {
+ /*
+ * Since we don't do lock_mount_hash() here,
+ * ->mnt_ns can change under us. However, if it's
+ * non-NULL, then there's a reference that won't
+ * be dropped until after an RCU delay done after
+ * turning ->mnt_ns NULL. So if we observe it
+ * non-NULL under rcu_read_lock(), the reference
+ * we are dropping is not the final one.
+ */
+ mnt_add_count(mnt, -1);
+ rcu_read_unlock();
+ return;
+ }
+ mntput_no_expire_slowpath(mnt);
+}
+
void mntput(struct vfsmount *mnt)
{
if (mnt) {
@@ -3094,19 +3100,7 @@ static struct file *vfs_open_tree(int dfd, const char __user *filename, unsigned
SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, flags)
{
- int fd;
- struct file *file __free(fput) = NULL;
-
- file = vfs_open_tree(dfd, filename, flags);
- if (IS_ERR(file))
- return PTR_ERR(file);
-
- fd = get_unused_fd_flags(flags & O_CLOEXEC);
- if (fd < 0)
- return fd;
-
- fd_install(fd, no_free_ptr(file));
- return fd;
+ return FD_ADD(flags, vfs_open_tree(dfd, filename, flags));
}
/*
@@ -4084,8 +4078,9 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a
dec_mnt_namespaces(ucounts);
return ERR_PTR(ret);
}
- if (!anon)
- ns_tree_gen_id(&new_ns->ns);
+ ns_tree_gen_id(new_ns);
+
+ new_ns->is_anon = anon;
refcount_set(&new_ns->passive, 1);
new_ns->mounts = RB_ROOT;
init_waitqueue_head(&new_ns->poll);
@@ -4274,10 +4269,10 @@ static unsigned int attr_flags_to_mnt_flags(u64 attr_flags)
SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
unsigned int, attr_flags)
{
+ struct path new_path __free(path_put) = {};
struct mnt_namespace *ns;
struct fs_context *fc;
- struct file *file;
- struct path newmount;
+ struct vfsmount *new_mnt;
struct mount *mnt;
unsigned int mnt_flags = 0;
long ret;
@@ -4315,35 +4310,36 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
fc = fd_file(f)->private_data;
- ret = mutex_lock_interruptible(&fc->uapi_mutex);
- if (ret < 0)
+ ACQUIRE(mutex_intr, uapi_mutex)(&fc->uapi_mutex);
+ ret = ACQUIRE_ERR(mutex_intr, &uapi_mutex);
+ if (ret)
return ret;
/* There must be a valid superblock or we can't mount it */
ret = -EINVAL;
if (!fc->root)
- goto err_unlock;
+ return ret;
ret = -EPERM;
if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) {
errorfcp(fc, "VFS", "Mount too revealing");
- goto err_unlock;
+ return ret;
}
ret = -EBUSY;
if (fc->phase != FS_CONTEXT_AWAITING_MOUNT)
- goto err_unlock;
+ return ret;
if (fc->sb_flags & SB_MANDLOCK)
warn_mandlock();
- newmount.mnt = vfs_create_mount(fc);
- if (IS_ERR(newmount.mnt)) {
- ret = PTR_ERR(newmount.mnt);
- goto err_unlock;
- }
- newmount.dentry = dget(fc->root);
- newmount.mnt->mnt_flags = mnt_flags;
+ new_mnt = vfs_create_mount(fc);
+ if (IS_ERR(new_mnt))
+ return PTR_ERR(new_mnt);
+ new_mnt->mnt_flags = mnt_flags;
+
+ new_path.dentry = dget(fc->root);
+ new_path.mnt = new_mnt;
/* We've done the mount bit - now move the file context into more or
* less the same state as if we'd done an fspick(). We don't want to
@@ -4353,38 +4349,27 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
vfs_clean_context(fc);
ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true);
- if (IS_ERR(ns)) {
- ret = PTR_ERR(ns);
- goto err_path;
- }
- mnt = real_mount(newmount.mnt);
+ if (IS_ERR(ns))
+ return PTR_ERR(ns);
+ mnt = real_mount(new_path.mnt);
ns->root = mnt;
ns->nr_mounts = 1;
mnt_add_to_ns(ns, mnt);
- mntget(newmount.mnt);
+ mntget(new_path.mnt);
- /* Attach to an apparent O_PATH fd with a note that we need to unmount
- * it, not just simply put it.
- */
- file = dentry_open(&newmount, O_PATH, fc->cred);
- if (IS_ERR(file)) {
- dissolve_on_fput(newmount.mnt);
- ret = PTR_ERR(file);
- goto err_path;
+ FD_PREPARE(fdf, (flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0,
+ dentry_open(&new_path, O_PATH, fc->cred));
+ if (fdf.err) {
+ dissolve_on_fput(new_path.mnt);
+ return fdf.err;
}
- file->f_mode |= FMODE_NEED_UNMOUNT;
-
- ret = get_unused_fd_flags((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0);
- if (ret >= 0)
- fd_install(ret, file);
- else
- fput(file);
-err_path:
- path_put(&newmount);
-err_unlock:
- mutex_unlock(&fc->uapi_mutex);
- return ret;
+ /*
+ * Attach to an apparent O_PATH fd with a note that we
+ * need to unmount it, not just simply put it.
+ */
+ fd_prepare_file(fdf)->f_mode |= FMODE_NEED_UNMOUNT;
+ return fd_publish(fdf);
}
static inline int vfs_move_mount(const struct path *from_path,
@@ -5026,19 +5011,17 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename,
unsigned, flags, struct mount_attr __user *, uattr,
size_t, usize)
{
- struct file __free(fput) *file = NULL;
- int fd;
-
if (!uattr && usize)
return -EINVAL;
- file = vfs_open_tree(dfd, filename, flags);
- if (IS_ERR(file))
- return PTR_ERR(file);
+ FD_PREPARE(fdf, flags, vfs_open_tree(dfd, filename, flags));
+ if (fdf.err)
+ return fdf.err;
if (uattr) {
- int ret;
struct mount_kattr kattr = {};
+ struct file *file = fd_prepare_file(fdf);
+ int ret;
if (flags & OPEN_TREE_CLONE)
kattr.kflags = MOUNT_KATTR_IDMAP_REPLACE;
@@ -5054,12 +5037,7 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename,
return ret;
}
- fd = get_unused_fd_flags(flags & O_CLOEXEC);
- if (fd < 0)
- return fd;
-
- fd_install(fd, no_free_ptr(file));
- return fd;
+ return fd_publish(fdf);
}
int show_path(struct seq_file *m, struct dentry *root)
@@ -5141,6 +5119,12 @@ static u64 mnt_to_propagation_flags(struct mount *m)
return propagation;
}
+u64 vfsmount_to_propagation_flags(struct vfsmount *mnt)
+{
+ return mnt_to_propagation_flags(real_mount(mnt));
+}
+EXPORT_SYMBOL_GPL(vfsmount_to_propagation_flags);
+
static void statmount_sb_basic(struct kstatmount *s)
{
struct super_block *sb = s->mnt->mnt_sb;
@@ -5976,11 +5960,8 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
}
struct mnt_namespace init_mnt_ns = {
- .ns.inum = ns_init_inum(&init_mnt_ns),
- .ns.ops = &mntns_operations,
+ .ns = NS_COMMON_INIT(init_mnt_ns),
.user_ns = &init_user_ns,
- .ns.__ns_ref = REFCOUNT_INIT(1),
- .ns.ns_type = ns_common_type(&init_mnt_ns),
.passive = REFCOUNT_INIT(1),
.mounts = RB_ROOT,
.poll = __WAIT_QUEUE_HEAD_INITIALIZER(init_mnt_ns.poll),
generated by cgit v1.2.3 (git 2.39.0) at 2025-12-03 13:00:40 +0300