Merge tag 'pull-mount' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs mount updates from Al Viro:

 - mount hash conflicts rudiments are gone now - we do not allow
     multiple mounts with the same parent/mountpoint to be hashed at the
     same time.

 - 'struct mount' changes:
      - mnt_umounting is gone
      - mnt_slave_list/mnt_slave is an hlist now
      - overmounts are kept track of by explicit pointer in mount
      - a bunch of flags moved out of mnt_flags to a new field, with
        only namespace_sem for protection
      - mnt_expiry is protected by mount_lock now (instead of
        namespace_sem)
      - MNT_LOCKED is used only for mounts that need to remain attached
        to their parents to prevent mountpoint exposure - no more
        overloading it for absolute roots
      - all mnt_list uses are transient now - it's used only to
        represent temporary sets during umount_tree()

 - mount refcounting change: children no longer pin parents for any
   mounts, whether they'd passed through umount_tree() or not

 - 'struct mountpoint' changes:
      - refcount is no more; what matters is ->m_list emptiness
      - instead of temporary bumping the refcount, we insert a new
        object (pinned_mountpoint) into ->m_list
      - new calling conventions for lock_mount() and friends

 - do_move_mount()/attach_recursive_mnt() seriously cleaned up

 - globals in fs/pnode.c are gone

 - propagate_mnt(), change_mnt_propagation() and propagate_umount()
   cleaned up (in the last case - pretty much completely rewritten).

 - freeing of emptied mnt_namespace is done in namespace_unlock(). For
   one thing, there are subtle ordering requirements there; for another
   it simplifies cleanups.

 - assorted cleanups

 - restore the machinery for long-term mounts from accumulated bitrot.

   This is going to get a followup come next cycle, when the change of
   vfs_fs_parse_string() calling conventions goes into -next

* tag 'pull-mount' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (48 commits)
  statmount_mnt_basic(): simplify the logics for group id
  invent_group_ids(): zero ->mnt_group_id always implies !IS_MNT_SHARED()
  get rid of CL_SHARE_TO_SLAVE
  take freeing of emptied mnt_namespace to namespace_unlock()
  copy_tree(): don't link the mounts via mnt_list
  change_mnt_propagation(): move ->mnt_master assignment into MS_SLAVE case
  mnt_slave_list/mnt_slave: turn into hlist_head/hlist_node
  turn do_make_slave() into transfer_propagation()
  do_make_slave(): choose new master sanely
  change_mnt_propagation(): do_make_slave() is a no-op unless IS_MNT_SHARED()
  change_mnt_propagation() cleanups, step 1
  propagate_mnt(): fix comment and convert to kernel-doc, while we are at it
  propagate_mnt(): get rid of last_dest
  fs/pnode.c: get rid of globals
  propagate_one(): fold into the sole caller
  propagate_one(): separate the "what should be the master for this copy" part
  propagate_one(): separate the "do we need secondary here?" logics
  propagate_mnt(): handle all peer groups in the same loop
  propagate_one(): get rid of dest_master
  mount: separate the flags accessed only under namespace_sem
  ...

Author: torvalds

Documentation/filesystems/propagate_umount.txt

@@ -5,16 +5,23 @@
 
 #include <linux/fs.h>
 #include <linux/mount.h>
+#include <linux/fs_context.h>
 
 #include "i915_drv.h"
 #include "i915_gemfs.h"
 #include "i915_utils.h"
 
+static int add_param(struct fs_context *fc, const char *key, const char *val)
+{
+	return vfs_parse_fs_string(fc, key, val, strlen(val));
+}
+
 void i915_gemfs_init(struct drm_i915_private *i915)
 {
-	char huge_opt[] = "huge=within_size"; /* r/w */
 	struct file_system_type *type;
+	struct fs_context *fc;
 	struct vfsmount *gemfs;
+	int ret;
 
 	/*
 	 * By creating our own shmemfs mountpoint, we can pass in
@@ -38,8 +45,16 @@ void i915_gemfs_init(struct drm_i915_private *i915)
 	if (!type)
 		goto err;
 
-	gemfs = vfs_kern_mount(type, SB_KERNMOUNT, type->name, huge_opt);
-	if (IS_ERR(gemfs))
+	fc = fs_context_for_mount(type, SB_KERNMOUNT);
+	if (IS_ERR(fc))
+		goto err;
+	ret = add_param(fc, "source", "tmpfs");
+	if (!ret)
+		ret = add_param(fc, "huge", "within_size");
+	if (!ret)
+		gemfs = fc_mount_longterm(fc);
+	put_fs_context(fc);
+	if (ret)
 		goto err;
 
 	i915->mm.gemfs = gemfs;

drivers/gpu/drm/i915/gem/i915_gemfs.c

@@ -3,14 +3,21 @@
 
 #include <linux/fs.h>
 #include <linux/mount.h>
+#include <linux/fs_context.h>
 
 #include "v3d_drv.h"
 
+static int add_param(struct fs_context *fc, const char *key, const char *val)
+{
+	return vfs_parse_fs_string(fc, key, val, strlen(val));
+}
+
 void v3d_gemfs_init(struct v3d_dev *v3d)
 {
-	char huge_opt[] = "huge=within_size";
 	struct file_system_type *type;
+	struct fs_context *fc;
 	struct vfsmount *gemfs;
+	int ret;
 
 	/*
 	 * By creating our own shmemfs mountpoint, we can pass in
@@ -28,8 +35,16 @@ void v3d_gemfs_init(struct v3d_dev *v3d)
 	if (!type)
 		goto err;
 
-	gemfs = vfs_kern_mount(type, SB_KERNMOUNT, type->name, huge_opt);
-	if (IS_ERR(gemfs))
+	fc = fs_context_for_mount(type, SB_KERNMOUNT);
+	if (IS_ERR(fc))
+		goto err;
+	ret = add_param(fc, "source", "tmpfs");
+	if (!ret)
+		ret = add_param(fc, "huge", "within_size");
+	if (!ret)
+		gemfs = fc_mount_longterm(fc);
+	put_fs_context(fc);
+	if (ret)
 		goto err;
 
 	v3d->gemfs = gemfs;

drivers/gpu/drm/v3d/v3d_gemfs.c

@@ -1588,7 +1588,7 @@ static struct vfsmount *__init mount_one_hugetlbfs(struct hstate *h)
 	} else {
 		struct hugetlbfs_fs_context *ctx = fc->fs_private;
 		ctx->hstate = h;
-		mnt = fc_mount(fc);
+		mnt = fc_mount_longterm(fc);
 		put_fs_context(fc);
 	}
 	if (IS_ERR(mnt))

fs/hugetlbfs/inode.c

@@ -44,7 +44,6 @@ struct mountpoint {
 	struct hlist_node m_hash;
 	struct dentry *m_dentry;
 	struct hlist_head m_list;
-	int m_count;
 };
 
 struct mount {
@@ -70,38 +69,55 @@ struct mount {
 	struct list_head mnt_list;
 	struct list_head mnt_expire;	/* link in fs-specific expiry list */
 	struct list_head mnt_share;	/* circular list of shared mounts */
-	struct list_head mnt_slave_list;/* list of slave mounts */
-	struct list_head mnt_slave;	/* slave list entry */
+	struct hlist_head mnt_slave_list;/* list of slave mounts */
+	struct hlist_node mnt_slave;	/* slave list entry */
 	struct mount *mnt_master;	/* slave is on master->mnt_slave_list */
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	struct mountpoint *mnt_mp;	/* where is it mounted */
 	union {
 		struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
 		struct hlist_node mnt_umount;
 	};
-	struct list_head mnt_umounting; /* list entry for umount propagation */
 #ifdef CONFIG_FSNOTIFY
 	struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
 	struct list_head to_notify;	/* need to queue notification */
 	struct mnt_namespace *prev_ns;	/* previous namespace (NULL if none) */
 #endif
+	int mnt_t_flags;		/* namespace_sem-protected flags */
 	int mnt_id;			/* mount identifier, reused */
 	u64 mnt_id_unique;		/* mount ID unique until reboot */
 	int mnt_group_id;		/* peer group identifier */
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	struct hlist_head mnt_pins;
 	struct hlist_head mnt_stuck_children;
+	struct mount *overmount;	/* mounted on ->mnt_root */
 } __randomize_layout;
 
+enum {
+	T_SHARED		= 1, /* mount is shared */
+	T_UNBINDABLE		= 2, /* mount is unbindable */
+	T_MARKED		= 4, /* internal mark for propagate_... */
+	T_UMOUNT_CANDIDATE	= 8, /* for propagate_umount */
+
+	/*
+	 * T_SHARED_MASK is the set of flags that should be cleared when a
+	 * mount becomes shared.  Currently, this is only the flag that says a
+	 * mount cannot be bind mounted, since this is how we create a mount
+	 * that shares events with another mount.  If you add a new T_*
+	 * flag, consider how it interacts with shared mounts.
+	 */
+	T_SHARED_MASK	= T_UNBINDABLE,
+};
+
 #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */
 
 static inline struct mount *real_mount(struct vfsmount *mnt)
 {
 	return container_of(mnt, struct mount, mnt);
 }
 
-static inline int mnt_has_parent(struct mount *mnt)
+static inline int mnt_has_parent(const struct mount *mnt)
 {
 	return mnt != mnt->mnt_parent;
 }
@@ -146,8 +162,8 @@ struct proc_mounts {
 
 extern const struct seq_operations mounts_op;
 
-extern bool __is_local_mountpoint(struct dentry *dentry);
-static inline bool is_local_mountpoint(struct dentry *dentry)
+extern bool __is_local_mountpoint(const struct dentry *dentry);
+static inline bool is_local_mountpoint(const struct dentry *dentry)
 {
 	if (!d_mountpoint(dentry))
 		return false;
@@ -160,6 +176,13 @@ static inline bool is_anon_ns(struct mnt_namespace *ns)
 	return ns->seq == 0;
 }
 
+static inline bool anon_ns_root(const struct mount *m)
+{
+	struct mnt_namespace *ns = READ_ONCE(m->mnt_ns);
+
+	return !IS_ERR_OR_NULL(ns) && is_anon_ns(ns) && m == ns->root;
+}
+
 static inline bool mnt_ns_attached(const struct mount *mnt)
 {
 	return !RB_EMPTY_NODE(&mnt->mnt_node);
@@ -170,7 +193,7 @@ static inline bool mnt_ns_empty(const struct mnt_namespace *ns)
 	return RB_EMPTY_ROOT(&ns->mounts);
 }
 
-static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list)
+static inline void move_from_ns(struct mount *mnt)
 {
 	struct mnt_namespace *ns = mnt->mnt_ns;
 	WARN_ON(!mnt_ns_attached(mnt));
@@ -180,7 +203,6 @@ static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list)
 		ns->mnt_first_node = rb_next(&mnt->mnt_node);
 	rb_erase(&mnt->mnt_node, &ns->mounts);
 	RB_CLEAR_NODE(&mnt->mnt_node);
-	list_add_tail(&mnt->mnt_list, dt_list);
 }
 
 bool has_locked_children(struct mount *mnt, struct dentry *dentry);