Merge tag 'fsnotify_for_v5.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull fsnotify updates from Jan Kara:
 "Support for reporting filesystem errors through fanotify so that
  system health monitoring daemons can watch for these and act instead
  of scraping system logs"

* tag 'fsnotify_for_v5.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs: (34 commits)
  samples: remove duplicate include in fs-monitor.c
  samples: Fix warning in fsnotify sample
  docs: Fix formatting of literal sections in fanotify docs
  samples: Make fs-monitor depend on libc and headers
  docs: Document the FAN_FS_ERROR event
  samples: Add fs error monitoring example
  ext4: Send notifications on error
  fanotify: Allow users to request FAN_FS_ERROR events
  fanotify: Emit generic error info for error event
  fanotify: Report fid info for file related file system errors
  fanotify: WARN_ON against too large file handles
  fanotify: Add helpers to decide whether to report FID/DFID
  fanotify: Wrap object_fh inline space in a creator macro
  fanotify: Support merging of error events
  fanotify: Support enqueueing of error events
  fanotify: Pre-allocate pool of error events
  fanotify: Reserve UAPI bits for FAN_FS_ERROR
  fsnotify: Support FS_ERROR event type
  fanotify: Require fid_mode for any non-fd event
  fanotify: Encode empty file handle when no inode is provided
  ...

3 files changed, 137 insertions, 26 deletions

diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index eec3b7c40811..616af2ea20f3 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -84,13 +84,20 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */
  */
 #define FANOTIFY_DIRENT_EVENTS	(FAN_MOVE | FAN_CREATE | FAN_DELETE)
 
+/* Events that can be reported with event->fd */
+#define FANOTIFY_FD_EVENTS (FANOTIFY_PATH_EVENTS | FANOTIFY_PERM_EVENTS)
+
 /* Events that can only be reported with data type FSNOTIFY_EVENT_INODE */
 #define FANOTIFY_INODE_EVENTS	(FANOTIFY_DIRENT_EVENTS | \
 				 FAN_ATTRIB | FAN_MOVE_SELF | FAN_DELETE_SELF)
 
+/* Events that can only be reported with data type FSNOTIFY_EVENT_ERROR */
+#define FANOTIFY_ERROR_EVENTS	(FAN_FS_ERROR)
+
 /* Events that user can request to be notified on */
 #define FANOTIFY_EVENTS		(FANOTIFY_PATH_EVENTS | \
-				 FANOTIFY_INODE_EVENTS)
+				 FANOTIFY_INODE_EVENTS | \
+				 FANOTIFY_ERROR_EVENTS)
 
 /* Events that require a permission response from user */
 #define FANOTIFY_PERM_EVENTS	(FAN_OPEN_PERM | FAN_ACCESS_PERM | \
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 12d3a7d308ab..787545e87eeb 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -26,20 +26,20 @@
  * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only
  * the child is interested and not the parent.
  */
-static inline void fsnotify_name(struct inode *dir, __u32 mask,
-				 struct inode *child,
-				 const struct qstr *name, u32 cookie)
+static inline int fsnotify_name(__u32 mask, const void *data, int data_type,
+				struct inode *dir, const struct qstr *name,
+				u32 cookie)
 {
 	if (atomic_long_read(&dir->i_sb->s_fsnotify_connectors) == 0)
-		return;
+		return 0;
 
-	fsnotify(mask, child, FSNOTIFY_EVENT_INODE, dir, name, NULL, cookie);
+	return fsnotify(mask, data, data_type, dir, name, NULL, cookie);
 }
 
 static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry,
 				   __u32 mask)
 {
-	fsnotify_name(dir, mask, d_inode(dentry), &dentry->d_name, 0);
+	fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0);
 }
 
 static inline void fsnotify_inode(struct inode *inode, __u32 mask)
@@ -86,7 +86,7 @@ notify_child:
  */
 static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask)
 {
-	fsnotify_parent(dentry, mask, d_inode(dentry), FSNOTIFY_EVENT_INODE);
+	fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY);
 }
 
 static inline int fsnotify_file(struct file *file, __u32 mask)
@@ -154,8 +154,10 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 		new_dir_mask |= FS_ISDIR;
 	}
 
-	fsnotify_name(old_dir, old_dir_mask, source, old_name, fs_cookie);
-	fsnotify_name(new_dir, new_dir_mask, source, new_name, fs_cookie);
+	fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE,
+		      old_dir, old_name, fs_cookie);
+	fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE,
+		      new_dir, new_name, fs_cookie);
 
 	if (target)
 		fsnotify_link_count(target);
@@ -190,16 +192,22 @@ static inline void fsnotify_inoderemove(struct inode *inode)
 
 /*
  * fsnotify_create - 'name' was linked in
+ *
+ * Caller must make sure that dentry->d_name is stable.
+ * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate
+ * ->d_inode later
  */
-static inline void fsnotify_create(struct inode *inode, struct dentry *dentry)
+static inline void fsnotify_create(struct inode *dir, struct dentry *dentry)
 {
-	audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE);
+	audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE);
 
-	fsnotify_dirent(inode, dentry, FS_CREATE);
+	fsnotify_dirent(dir, dentry, FS_CREATE);
 }
 
 /*
  * fsnotify_link - new hardlink in 'inode' directory
+ *
+ * Caller must make sure that new_dentry->d_name is stable.
  * Note: We have to pass also the linked inode ptr as some filesystems leave
  *   new_dentry->d_inode NULL and instantiate inode pointer later
  */
@@ -209,7 +217,8 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode,
 	fsnotify_link_count(inode);
 	audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE);
 
-	fsnotify_name(dir, FS_CREATE, inode, &new_dentry->d_name, 0);
+	fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE,
+		      dir, &new_dentry->d_name, 0);
 }
 
 /*
@@ -227,12 +236,16 @@ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry)
 
 /*
  * fsnotify_mkdir - directory 'name' was created
+ *
+ * Caller must make sure that dentry->d_name is stable.
+ * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate
+ * ->d_inode later
  */
-static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
+static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry)
 {
-	audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE);
+	audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE);
 
-	fsnotify_dirent(inode, dentry, FS_CREATE | FS_ISDIR);
+	fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR);
 }
 
 /*
@@ -326,4 +339,17 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 		fsnotify_dentry(dentry, mask);
 }
 
+static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode,
+				    int error)
+{
+	struct fs_error_report report = {
+		.error = error,
+		.inode = inode,
+		.sb = sb,
+	};
+
+	return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR,
+			NULL, NULL, NULL, 0);
+}
+
 #endif	/* _LINUX_FS_NOTIFY_H */
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 1ce66748a2d2..51ef2b079bfa 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -19,6 +19,7 @@
 #include <linux/atomic.h>
 #include <linux/user_namespace.h>
 #include <linux/refcount.h>
+#include <linux/mempool.h>
 
 /*
  * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily
@@ -42,6 +43,12 @@
 
 #define FS_UNMOUNT		0x00002000	/* inode on umount fs */
 #define FS_Q_OVERFLOW		0x00004000	/* Event queued overflowed */
+#define FS_ERROR		0x00008000	/* Filesystem Error (fanotify) */
+
+/*
+ * FS_IN_IGNORED overloads FS_ERROR.  It is only used internally by inotify
+ * which does not support FS_ERROR.
+ */
 #define FS_IN_IGNORED		0x00008000	/* last inotify event here */
 
 #define FS_OPEN_PERM		0x00010000	/* open event in an permission hook */
@@ -95,7 +102,8 @@
 #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \
 			     FS_EVENTS_POSS_ON_CHILD | \
 			     FS_DELETE_SELF | FS_MOVE_SELF | FS_DN_RENAME | \
-			     FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED)
+			     FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \
+			     FS_ERROR)
 
 /* Extra flags that may be reported with event or control handling of events */
 #define ALL_FSNOTIFY_FLAGS  (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \
@@ -136,6 +144,7 @@ struct mem_cgroup;
  * @dir:	optional directory associated with event -
  *		if @file_name is not NULL, this is the directory that
  *		@file_name is relative to.
+ *		Either @inode or @dir must be non-NULL.
  * @file_name:	optional file name associated with event
  * @cookie:	inotify rename cookie
  *
@@ -155,7 +164,7 @@ struct fsnotify_ops {
 			    const struct qstr *file_name, u32 cookie);
 	void (*free_group_priv)(struct fsnotify_group *group);
 	void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group);
-	void (*free_event)(struct fsnotify_event *event);
+	void (*free_event)(struct fsnotify_group *group, struct fsnotify_event *event);
 	/* called on final put+free to free memory */
 	void (*free_mark)(struct fsnotify_mark *mark);
 };
@@ -238,6 +247,7 @@ struct fsnotify_group {
 			int flags;           /* flags from fanotify_init() */
 			int f_flags; /* event_f_flags from fanotify_init() */
 			struct ucounts *ucounts;
+			mempool_t error_events_pool;
 		} fanotify_data;
 #endif /* CONFIG_FANOTIFY */
 	};
@@ -248,6 +258,14 @@ enum fsnotify_data_type {
 	FSNOTIFY_EVENT_NONE,
 	FSNOTIFY_EVENT_PATH,
 	FSNOTIFY_EVENT_INODE,
+	FSNOTIFY_EVENT_DENTRY,
+	FSNOTIFY_EVENT_ERROR,
+};
+
+struct fs_error_report {
+	int error;
+	struct inode *inode;
+	struct super_block *sb;
 };
 
 static inline struct inode *fsnotify_data_inode(const void *data, int data_type)
@@ -255,8 +273,25 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type)
 	switch (data_type) {
 	case FSNOTIFY_EVENT_INODE:
 		return (struct inode *)data;
+	case FSNOTIFY_EVENT_DENTRY:
+		return d_inode(data);
 	case FSNOTIFY_EVENT_PATH:
 		return d_inode(((const struct path *)data)->dentry);
+	case FSNOTIFY_EVENT_ERROR:
+		return ((struct fs_error_report *)data)->inode;
+	default:
+		return NULL;
+	}
+}
+
+static inline struct dentry *fsnotify_data_dentry(const void *data, int data_type)
+{
+	switch (data_type) {
+	case FSNOTIFY_EVENT_DENTRY:
+		/* Non const is needed for dget() */
+		return (struct dentry *)data;
+	case FSNOTIFY_EVENT_PATH:
+		return ((const struct path *)data)->dentry;
 	default:
 		return NULL;
 	}
@@ -273,6 +308,35 @@ static inline const struct path *fsnotify_data_path(const void *data,
 	}
 }
 
+static inline struct super_block *fsnotify_data_sb(const void *data,
+						   int data_type)
+{
+	switch (data_type) {
+	case FSNOTIFY_EVENT_INODE:
+		return ((struct inode *)data)->i_sb;
+	case FSNOTIFY_EVENT_DENTRY:
+		return ((struct dentry *)data)->d_sb;
+	case FSNOTIFY_EVENT_PATH:
+		return ((const struct path *)data)->dentry->d_sb;
+	case FSNOTIFY_EVENT_ERROR:
+		return ((struct fs_error_report *) data)->sb;
+	default:
+		return NULL;
+	}
+}
+
+static inline struct fs_error_report *fsnotify_data_error_report(
+							const void *data,
+							int data_type)
+{
+	switch (data_type) {
+	case FSNOTIFY_EVENT_ERROR:
+		return (struct fs_error_report *) data;
+	default:
+		return NULL;
+	}
+}
+
 enum fsnotify_obj_type {
 	FSNOTIFY_OBJ_TYPE_INODE,
 	FSNOTIFY_OBJ_TYPE_PARENT,
@@ -482,16 +546,30 @@ extern int fsnotify_fasync(int fd, struct file *file, int on);
 extern void fsnotify_destroy_event(struct fsnotify_group *group,
 				   struct fsnotify_event *event);
 /* attach the event to the group notification queue */
-extern int fsnotify_add_event(struct fsnotify_group *group,
-			      struct fsnotify_event *event,
-			      int (*merge)(struct fsnotify_group *,
-					   struct fsnotify_event *),
-			      void (*insert)(struct fsnotify_group *,
-					     struct fsnotify_event *));
+extern int fsnotify_insert_event(struct fsnotify_group *group,
+				 struct fsnotify_event *event,
+				 int (*merge)(struct fsnotify_group *,
+					      struct fsnotify_event *),
+				 void (*insert)(struct fsnotify_group *,
+						struct fsnotify_event *));
+
+static inline int fsnotify_add_event(struct fsnotify_group *group,
+				     struct fsnotify_event *event,
+				     int (*merge)(struct fsnotify_group *,
+						  struct fsnotify_event *))
+{
+	return fsnotify_insert_event(group, event, merge, NULL);
+}
+
 /* Queue overflow event to a notification group */
 static inline void fsnotify_queue_overflow(struct fsnotify_group *group)
 {
-	fsnotify_add_event(group, group->overflow_event, NULL, NULL);
+	fsnotify_add_event(group, group->overflow_event, NULL);
+}
+
+static inline bool fsnotify_is_overflow_event(u32 mask)
+{
+	return mask & FS_Q_OVERFLOW;
 }
 
 static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group)