Merge branch 'vfs.all' of https://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs.git

14 files changed, 80 insertions, 11 deletions

diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index 4f1084937315..7713fd60c985 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -100,8 +100,10 @@ struct wb_completion {
  * refcounted with the number of inodes attached to it, and pins the memcg
  * and the corresponding blkcg.  As the corresponding blkcg for a memcg may
  * change as blkcg is disabled and enabled higher up in the hierarchy, a wb
- * is tested for blkcg after lookup and removed from index on mismatch so
- * that a new wb for the combination can be created.
+ * is tested for blkcg after lookup and killed on mismatch so that a new wb
+ * for the combination can be created.  A killed wb stays in the index until
+ * it is released or a new wb takes over its slot, so that foreign flushes
+ * can still reach it.
  *
  * Each bdi_writeback that is not embedded into the backing_dev_info must hold
  * a reference to the parent backing_dev_info.  See cgwb_create() for details.
@@ -160,6 +162,7 @@ struct bdi_writeback {
 					 * to this wb */
 	struct llist_head switch_wbs_ctxs;	/* queued contexts for
 						 * writeback switching */
+	struct work_struct replaced_work;	/* see switch_replaced_cgwb() */
 
 	union {
 		struct work_struct release_work;
@@ -196,7 +199,7 @@ struct backing_dev_info {
 	struct bdi_writeback wb;  /* the root writeback info for this bdi */
 	struct list_head wb_list; /* list of all wbs */
 #ifdef CONFIG_CGROUP_WRITEBACK
-	struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
+	struct radix_tree_root cgwb_tree; /* radix tree of cgroup wbs, incl. killed */
 	struct mutex cgwb_release_mutex;  /* protect shutdown of wb structs */
 	struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */
 #endif
@@ -230,6 +233,17 @@ static inline bool wb_tryget(struct bdi_writeback *wb)
 }
 
 /**
+ * wb_tryget_live - try to increment a wb's refcount if it hasn't been killed
+ * @wb: bdi_writeback to get
+ */
+static inline bool wb_tryget_live(struct bdi_writeback *wb)
+{
+	if (wb != &wb->bdi->wb)
+		return percpu_ref_tryget_live(&wb->refcnt);
+	return true;
+}
+
+/**
  * wb_get - increment a wb's refcount
  * @wb: bdi_writeback to get
  */
@@ -271,7 +285,8 @@ static inline void wb_put(struct bdi_writeback *wb)
  * wb_dying - is a wb dying?
  * @wb: bdi_writeback of interest
  *
- * Returns whether @wb is unlinked and being drained.
+ * Returns whether @wb has been killed and is being drained.  A dying wb may
+ * still be in bdi->cgwb_tree, see cgwb_kill().
  */
 static inline bool wb_dying(struct bdi_writeback *wb)
 {
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index c2284466e7aa..84057fa92f24 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -151,6 +151,7 @@ static inline void bdi_wb_stat_mod(struct inode *inode, enum wb_stat_item item,
 
 struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi,
 				    struct cgroup_subsys_state *memcg_css);
+void cgwb_kick_replaced(struct bdi_writeback *wb);
 struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi,
 				    struct cgroup_subsys_state *memcg_css,
 				    gfp_t gfp);
@@ -222,7 +223,7 @@ wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp)
 
 	rcu_read_lock();
 	wb = wb_find_current(bdi);
-	if (wb && unlikely(!wb_tryget(wb)))
+	if (wb && unlikely(!wb_tryget_live(wb)))
 		wb = NULL;
 	rcu_read_unlock();
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 0cc09b975d8f..64287a032120 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -58,6 +58,7 @@ struct block_device {
 	struct address_space	*bd_mapping;	/* page cache */
 
 	atomic_t		bd_openers;
+	unsigned int		bd_fs_users; /* Protected by bd_mapping->host->i_rwsem. */
 	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
 	void *			bd_claiming;
 	void *			bd_holder;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 215753171cef..2d92b2b57079 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1709,6 +1709,7 @@ bool disk_live(struct gendisk *disk);
 unsigned int block_size(struct block_device *bdev);
 
 #ifdef CONFIG_BLOCK
+void kill_bdev(struct block_device *bdev);
 void invalidate_bdev(struct block_device *bdev);
 int sync_blockdev(struct block_device *bdev);
 int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend);
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 49c26af37349..7fb1663a5fc6 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -171,6 +171,26 @@ extern int cred_fscmp(const struct cred *, const struct cred *);
 extern void __init cred_init(void);
 extern int set_cred_ucounts(struct cred *);
 
+/**
+ * enum cred_ids - which of its ids a subject acts with
+ * @CRED_IDS_REAL:      uid and gid
+ * @CRED_IDS_EFFECTIVE: euid and egid
+ * @CRED_IDS_FS:        fsuid and fsgid
+ */
+enum cred_ids {
+	CRED_IDS_REAL,
+	CRED_IDS_EFFECTIVE,
+	CRED_IDS_FS,
+};
+
+bool cred_ids_allow_signal(const struct cred *subj, const struct cred *obj);
+bool cred_ids_allow_sigio(const struct cred *subj, const struct cred *obj);
+bool cred_ids_allow_sched(const struct cred *subj, const struct cred *obj);
+bool cred_ids_allow_ioprio(const struct cred *subj, const struct cred *obj);
+bool cred_ids_allow_move(const struct cred *subj, const struct cred *obj);
+bool cred_ids_allow_control(const struct cred *subj, enum cred_ids which,
+			    const struct cred *obj);
+
 static inline bool cap_ambient_invariant_ok(const struct cred *cred)
 {
 	return cap_issubset(cred->cap_ambient,
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index 6ad6b9e7a226..204e16bbe263 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -30,6 +30,12 @@
  */
 #define __O_REGULAR		(1 << 30)
 
+#define O_MKDIR_MASK	(O_CREAT | O_DIRECTORY)
+static inline bool O_IS_MKDIR(unsigned int flags)
+{
+	return (flags & O_MKDIR_MASK) == O_MKDIR_MASK;
+}
+
 /* List of all valid flags for the how->resolve argument: */
 #define VALID_RESOLVE_FLAGS \
 	(RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \
diff --git a/include/linux/file_ref.h b/include/linux/file_ref.h
index 31551e4cb8f3..e5fc45714fe2 100644
--- a/include/linux/file_ref.h
+++ b/include/linux/file_ref.h
@@ -69,7 +69,11 @@ bool __file_ref_put(file_ref_t *ref, unsigned long cnt);
  *
  * Similar to atomic_inc_not_zero() but saturates at FILE_REF_MAXREF.
  *
- * Provides full memory ordering.
+ * Provides acquire memory ordering: loads after a successful get are
+ * ordered after the increment. That is what the pointer recheck of the
+ * fget-rcu pattern needs, the load of the pointer the reference is
+ * taken through is ordered before the increment by its address
+ * dependency.
  *
  * Return: False if the attempt to acquire a reference failed. This happens
  *         when the last reference has been put already. True if a reference
@@ -78,7 +82,7 @@ bool __file_ref_put(file_ref_t *ref, unsigned long cnt);
 static __always_inline __must_check bool file_ref_get(file_ref_t *ref)
 {
 	/*
-	 * Unconditionally increase the reference count with full
+	 * Unconditionally increase the reference count with acquire
 	 * ordering. The saturation and dead zones provide enough
 	 * tolerance for this.
 	 *
@@ -105,7 +109,7 @@ static __always_inline __must_check bool file_ref_get(file_ref_t *ref)
 	 * FILE_REF_ONEREF. It would need 2305843009213693952/2^61
 	 * file_ref_get()s to resurrect such a dead file.
 	 */
-	return !atomic_long_add_negative(1, &ref->refcnt);
+	return !atomic_long_add_negative_acquire(1, &ref->refcnt);
 }
 
 /**
@@ -129,6 +133,17 @@ static __always_inline void file_ref_inc(file_ref_t *ref)
  * are done before, and provides an acquire ordering on success such
  * that free() must come after.
  *
+ * The decrement is fully ordered though and it has to stay that way.
+ * When the last reference goes synchronously, in __fput_sync() and on
+ * the fallback path of fput_close_sync(), the full barrier is what
+ * orders the caller's earlier stores, in close(2) the cleared slot in
+ * the descriptor table, before the slab handoff that lets another CPU
+ * reallocate the file. A lookup that increments the recycled counter
+ * then sees the cleared slot and fails its recheck. The deferred
+ * fput() has the cmpxchg() of task_work_add() for that, the
+ * synchronous paths have nothing else. So this is not a candidate for
+ * atomic_long_dec_return_release().
+ *
  * Return: True if this was the last reference with no future references
  *         possible. This signals the caller that it can safely release
  *         the object which is protected by the reference counter.
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5b3a100aba77..58d25fc23ec4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1186,10 +1186,10 @@ static inline unsigned imajor(const struct inode *inode)
 
 struct fown_struct {
 	struct file *file;	/* backpointer for security modules */
-	rwlock_t lock;          /* protects pid, uid, euid fields */
+	rwlock_t lock;          /* protects pid, cred fields */
 	struct pid *pid;	/* pid or -pgrp where SIGIO should be sent */
 	enum pid_type pid_type;	/* Kind of process group SIGIO should be sent to */
-	kuid_t uid, euid;	/* uid/euid of process setting the owner */
+	const struct cred *cred; /* of the process setting the owner */
 	int signum;		/* posix.1b rt signal to be delivered on IO */
 };
 
diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h
index 6ce105fe8359..8176133bcdb3 100644
--- a/include/linux/fs/super_types.h
+++ b/include/linux/fs/super_types.h
@@ -359,5 +359,6 @@ struct super_block {
 #define SB_I_NOIDMAP	0x00002000	/* No idmapped mounts on this superblock */
 #define SB_I_ALLOW_HSM	0x00004000	/* Allow HSM events on this superblock */
 #define SB_I_NO_DATA_INTEGRITY	0x00008000 /* fs cannot guarantee data persistence on sync */
+#define SB_I_NO_ATOMIC_MKDIR	0x00010000 /* no O_CREAT|O_DIRECTORY on this fs */
 
 #endif /* _LINUX_FS_SUPER_TYPES_H */
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index 97eef8d3863d..fb725707754d 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -42,6 +42,9 @@ static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd)
 	read_sequnlock_excl(&fs->seq);
 }
 
+int get_task_root(struct task_struct *task, struct path *root);
+int get_task_pwd(struct task_struct *task, struct path *pwd);
+
 struct fs_struct *switch_fs_struct(struct fs_struct *new_fs);
 
 extern bool current_chrooted(void);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6af3b7008f1a..9971a6f7e607 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4402,6 +4402,7 @@ extern int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
 extern int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
 extern struct file *get_mm_exe_file(struct mm_struct *mm);
 extern struct file *get_task_exe_file(struct task_struct *task);
+int get_task_exe_path(struct task_struct *task, struct path *exe_path);
 
 extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages);
 
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 57860e321cf5..e1ef34b5b09d 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -74,7 +74,6 @@ extern void mnt_drop_write(struct vfsmount *mnt);
 extern void mnt_drop_write_file(struct file *file);
 extern void mntput(struct vfsmount *mnt);
 extern struct vfsmount *mntget(struct vfsmount *mnt);
-extern void mnt_make_shortterm(struct vfsmount *mnt);
 extern struct vfsmount *mnt_clone_internal(const struct path *path);
 extern bool __mnt_is_readonly(const struct vfsmount *mnt);
 extern bool mnt_may_suid(struct vfsmount *mnt);
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 47d7deaeed8f..903fc811efd4 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -29,6 +29,7 @@ enum {
 	PROC_ENTRY_proc_compat_ioctl	= 1U << 2,
 	PROC_ENTRY_proc_lseek		= 1U << 3,
 
+	PROC_ENTRY_CANT_MOUNT		= 1U << 6,
 	PROC_ENTRY_FORCE_LOOKUP		= 1U << 7,
 };
 
@@ -87,6 +88,8 @@ extern void proc_flush_pid(struct pid *);
 
 extern struct proc_dir_entry *proc_symlink(const char *,
 		struct proc_dir_entry *, const char *);
+struct proc_dir_entry *proc_self_symlink(const char *, struct proc_dir_entry *,
+					 const char *);
 struct proc_dir_entry *_proc_mkdir(const char *, umode_t, struct proc_dir_entry *, void *, bool);
 extern struct proc_dir_entry *proc_mkdir(const char *, struct proc_dir_entry *);
 extern struct proc_dir_entry *proc_mkdir_data(const char *, umode_t,
@@ -179,6 +182,8 @@ static inline void proc_flush_pid(struct pid *pid)
 
 static inline struct proc_dir_entry *proc_symlink(const char *name,
 		struct proc_dir_entry *parent,const char *dest) { return NULL;}
+static inline struct proc_dir_entry *proc_self_symlink(const char *name,
+		struct proc_dir_entry *parent, const char *dest) { return NULL; }
 static inline struct proc_dir_entry *proc_mkdir(const char *name,
 	struct proc_dir_entry *parent) {return NULL;}
 static inline struct proc_dir_entry *proc_create_mount_point(const char *name) { return NULL; }
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index b749a9a5a5ee..88e4b5049698 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -209,6 +209,7 @@ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id,
 			   enum wb_reason reason, struct wb_completion *done);
 void cgroup_writeback_umount(struct super_block *sb);
 bool cleanup_offline_cgwb(struct bdi_writeback *wb);
+bool switch_replaced_cgwb(struct bdi_writeback *wb);
 
 /**
  * inode_attach_wb - associate an inode with its wb