Merge tag 'fsnotify_hsm_for_v6.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull fsnotify pre-content notification support from Jan Kara:
 "This introduces a new fsnotify event (FS_PRE_ACCESS) that gets
  generated before a file contents is accessed.

  The event is synchronous so if there is listener for this event, the
  kernel waits for reply. On success the execution continues as usual,
  on failure we propagate the error to userspace. This allows userspace
  to fill in file content on demand from slow storage. The context in
  which the events are generated has been picked so that we don't hold
  any locks and thus there's no risk of a deadlock for the userspace
  handler.

  The new pre-content event is available only for users with global
  CAP_SYS_ADMIN capability (similarly to other parts of fanotify
  functionality) and it is an administrator responsibility to make sure
  the userspace event handler doesn't do stupid stuff that can DoS the
  system.

  Based on your feedback from the last submission, fsnotify code has
  been improved and now file->f_mode encodes whether pre-content event
  needs to be generated for the file so the fast path when nobody wants
  pre-content event for the file just grows the additional file->f_mode
  check. As a bonus this also removes the checks whether the old
  FS_ACCESS event needs to be generated from the fast path. Also the
  place where the event is generated during page fault has been moved so
  now filemap_fault() generates the event if and only if there is no
  uptodate folio in the page cache.

  Also we have dropped FS_PRE_MODIFY event as current real-world users
  of the pre-content functionality don't really use it so let's start
  with the minimal useful feature set"

* tag 'fsnotify_hsm_for_v6.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs: (21 commits)
  fanotify: Fix crash in fanotify_init(2)
  fs: don't block write during exec on pre-content watched files
  fs: enable pre-content events on supported file systems
  ext4: add pre-content fsnotify hook for DAX faults
  btrfs: disable defrag on pre-content watched files
  xfs: add pre-content fsnotify hook for DAX faults
  fsnotify: generate pre-content permission event on page fault
  mm: don't allow huge faults for files with pre content watches
  fanotify: disable readahead if we have pre-content watches
  fanotify: allow to set errno in FAN_DENY permission response
  fanotify: report file range info with pre-content events
  fanotify: introduce FAN_PRE_ACCESS permission event
  fsnotify: generate pre-content permission event on truncate
  fsnotify: pass optional file access range in pre-content event
  fsnotify: introduce pre-content permission events
  fanotify: reserve event bit of deprecated FAN_DIR_MODIFY
  fanotify: rename a misnamed constant
  fanotify: don't skip extra event info if no info_mode is set
  fsnotify: check if file is actually being watched for pre-content events on open
  fsnotify: opt-in for permission events at file open time
  ...

5 files changed, 190 insertions, 32 deletions

diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index 89ff45bd6f01..78f660ebc318 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -89,6 +89,16 @@
 #define FANOTIFY_DIRENT_EVENTS	(FAN_MOVE | FAN_CREATE | FAN_DELETE | \
 				 FAN_RENAME)
 
+/* Content events can be used to inspect file content */
+#define FANOTIFY_CONTENT_PERM_EVENTS (FAN_OPEN_PERM | FAN_OPEN_EXEC_PERM | \
+				      FAN_ACCESS_PERM)
+/* Pre-content events can be used to fill file content */
+#define FANOTIFY_PRE_CONTENT_EVENTS  (FAN_PRE_ACCESS)
+
+/* Events that require a permission response from user */
+#define FANOTIFY_PERM_EVENTS	(FANOTIFY_CONTENT_PERM_EVENTS | \
+				 FANOTIFY_PRE_CONTENT_EVENTS)
+
 /* Events that can be reported with event->fd */
 #define FANOTIFY_FD_EVENTS (FANOTIFY_PATH_EVENTS | FANOTIFY_PERM_EVENTS)
 
@@ -104,10 +114,6 @@
 				 FANOTIFY_INODE_EVENTS | \
 				 FANOTIFY_ERROR_EVENTS)
 
-/* Events that require a permission response from user */
-#define FANOTIFY_PERM_EVENTS	(FAN_OPEN_PERM | FAN_ACCESS_PERM | \
-				 FAN_OPEN_EXEC_PERM)
-
 /* Extra flags that may be reported with event or control handling of events */
 #define FANOTIFY_EVENT_FLAGS	(FAN_EVENT_ON_CHILD | FAN_ONDIR)
 
@@ -126,7 +132,9 @@
 /* These masks check for invalid bits in permission responses. */
 #define FANOTIFY_RESPONSE_ACCESS (FAN_ALLOW | FAN_DENY)
 #define FANOTIFY_RESPONSE_FLAGS (FAN_AUDIT | FAN_INFO)
-#define FANOTIFY_RESPONSE_VALID_MASK (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS)
+#define FANOTIFY_RESPONSE_VALID_MASK \
+	(FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS | \
+	 (FAN_ERRNO_MASK << FAN_ERRNO_SHIFT))
 
 /* Do not use these old uapi constants internally */
 #undef FAN_ALL_CLASS_BITS
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a4af70367f8a..534e652bd05f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -173,13 +173,20 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 
 #define	FMODE_NOREUSE		((__force fmode_t)(1 << 23))
 
-/* FMODE_* bit 24 */
-
 /* File is embedded in backing_file object */
-#define FMODE_BACKING		((__force fmode_t)(1 << 25))
+#define FMODE_BACKING		((__force fmode_t)(1 << 24))
+
+/*
+ * Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be
+ * generated (see below)
+ */
+#define FMODE_NONOTIFY		((__force fmode_t)(1 << 25))
 
-/* File was opened by fanotify and shouldn't generate fanotify events */
-#define FMODE_NONOTIFY		((__force fmode_t)(1 << 26))
+/*
+ * Together with FMODE_NONOTIFY defines which fsnotify events shouldn't be
+ * generated (see below)
+ */
+#define FMODE_NONOTIFY_PERM	((__force fmode_t)(1 << 26))
 
 /* File is capable of returning -EAGAIN if I/O will block */
 #define FMODE_NOWAIT		((__force fmode_t)(1 << 27))
@@ -191,6 +198,32 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_NOACCOUNT		((__force fmode_t)(1 << 29))
 
 /*
+ * The two FMODE_NONOTIFY* define which fsnotify events should not be generated
+ * for a file. These are the possible values of (f->f_mode &
+ * FMODE_FSNOTIFY_MASK) and their meaning:
+ *
+ * FMODE_NONOTIFY - suppress all (incl. non-permission) events.
+ * FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events.
+ * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only pre-content events.
+ */
+#define FMODE_FSNOTIFY_MASK \
+	(FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)
+
+#define FMODE_FSNOTIFY_NONE(mode) \
+	((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY)
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+#define FMODE_FSNOTIFY_PERM(mode) \
+	((mode & FMODE_FSNOTIFY_MASK) == 0 || \
+	 (mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM))
+#define FMODE_FSNOTIFY_HSM(mode) \
+	((mode & FMODE_FSNOTIFY_MASK) == 0)
+#else
+#define FMODE_FSNOTIFY_PERM(mode)	0
+#define FMODE_FSNOTIFY_HSM(mode)	0
+#endif
+
+
+/*
  * Attribute flags.  These should be or-ed together to figure out what
  * has been changed!
  */
@@ -1246,6 +1279,7 @@ extern int send_sigurg(struct file *file);
 #define SB_I_RETIRED	0x00000800	/* superblock shouldn't be reused */
 #define SB_I_NOUMASK	0x00001000	/* VFS does not apply umask */
 #define SB_I_NOIDMAP	0x00002000	/* No idmapped mounts on this superblock */
+#define SB_I_ALLOW_HSM	0x00004000	/* Allow HSM events on this superblock */
 
 /* Possible states of 'frozen' field */
 enum {
@@ -2767,6 +2801,8 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt,
 }
 struct file *dentry_open(const struct path *path, int flags,
 			 const struct cred *creds);
+struct file *dentry_open_nonotify(const struct path *path, int flags,
+				  const struct cred *cred);
 struct file *dentry_create(const struct path *path, int flags, umode_t mode,
 			   const struct cred *cred);
 struct path *backing_file_user_path(struct file *f);
@@ -3075,6 +3111,28 @@ static inline void allow_write_access(struct file *file)
 	if (file)
 		atomic_inc(&file_inode(file)->i_writecount);
 }
+
+/*
+ * Do not prevent write to executable file when watched by pre-content events.
+ *
+ * Note that FMODE_FSNOTIFY_HSM mode is set depending on pre-content watches at
+ * the time of file open and remains constant for entire lifetime of the file,
+ * so if pre-content watches are added post execution or removed before the end
+ * of the execution, it will not cause i_writecount reference leak.
+ */
+static inline int exe_file_deny_write_access(struct file *exe_file)
+{
+	if (unlikely(FMODE_FSNOTIFY_HSM(exe_file->f_mode)))
+		return 0;
+	return deny_write_access(exe_file);
+}
+static inline void exe_file_allow_write_access(struct file *exe_file)
+{
+	if (unlikely(!exe_file || FMODE_FSNOTIFY_HSM(exe_file->f_mode)))
+		return;
+	allow_write_access(exe_file);
+}
+
 static inline bool inode_is_open_for_write(const struct inode *inode)
 {
 	return atomic_read(&inode->i_writecount) > 0;
@@ -3730,11 +3788,9 @@ struct ctl_table;
 int __init list_bdev_fs_names(char *buf, size_t size);
 
 #define __FMODE_EXEC		((__force int) FMODE_EXEC)
-#define __FMODE_NONOTIFY	((__force int) FMODE_NONOTIFY)
 
 #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
-#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
-					    (flag & __FMODE_NONOTIFY)))
+#define OPEN_FMODE(flag) ((__force fmode_t)((flag + 1) & O_ACCMODE))
 
 static inline bool is_sxid(umode_t mode)
 {
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 278620e063ab..1a9ef8f6784d 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -108,38 +108,35 @@ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask)
 	fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY);
 }
 
-static inline int fsnotify_file(struct file *file, __u32 mask)
+static inline int fsnotify_path(const struct path *path, __u32 mask)
 {
-	const struct path *path;
+	return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
+}
 
+static inline int fsnotify_file(struct file *file, __u32 mask)
+{
 	/*
 	 * FMODE_NONOTIFY are fds generated by fanotify itself which should not
 	 * generate new events. We also don't want to generate events for
 	 * FMODE_PATH fds (involves open & close events) as they are just
 	 * handle creation / destruction events and not "real" file events.
 	 */
-	if (file->f_mode & (FMODE_NONOTIFY | FMODE_PATH))
+	if (FMODE_FSNOTIFY_NONE(file->f_mode))
 		return 0;
 
-	path = &file->f_path;
-	/* Permission events require group prio >= FSNOTIFY_PRIO_CONTENT */
-	if (mask & ALL_FSNOTIFY_PERM_EVENTS &&
-	    !fsnotify_sb_has_priority_watchers(path->dentry->d_sb,
-					       FSNOTIFY_PRIO_CONTENT))
-		return 0;
-
-	return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
+	return fsnotify_path(&file->f_path, mask);
 }
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+
+void file_set_fsnotify_mode(struct file *file);
+
 /*
  * fsnotify_file_area_perm - permission hook before access to file range
  */
 static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
 					  const loff_t *ppos, size_t count)
 {
-	__u32 fsnotify_mask = FS_ACCESS_PERM;
-
 	/*
 	 * filesystem may be modified in the context of permission events
 	 * (e.g. by HSM filling a file on access), so sb freeze protection
@@ -147,14 +144,49 @@ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
 	 */
 	lockdep_assert_once(file_write_not_started(file));
 
+	if (!(perm_mask & (MAY_READ | MAY_WRITE | MAY_ACCESS)))
+		return 0;
+
+	if (likely(!FMODE_FSNOTIFY_PERM(file->f_mode)))
+		return 0;
+
+	/*
+	 * read()/write() and other types of access generate pre-content events.
+	 */
+	if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) {
+		int ret = fsnotify_pre_content(&file->f_path, ppos, count);
+
+		if (ret)
+			return ret;
+	}
+
 	if (!(perm_mask & MAY_READ))
 		return 0;
 
-	return fsnotify_file(file, fsnotify_mask);
+	/*
+	 * read() also generates the legacy FS_ACCESS_PERM event, so content
+	 * scanners can inspect the content filled by pre-content event.
+	 */
+	return fsnotify_path(&file->f_path, FS_ACCESS_PERM);
+}
+
+/*
+ * fsnotify_truncate_perm - permission hook before file truncate
+ */
+static inline int fsnotify_truncate_perm(const struct path *path, loff_t length)
+{
+	struct inode *inode = d_inode(path->dentry);
+
+	if (!(inode->i_sb->s_iflags & SB_I_ALLOW_HSM) ||
+	    !fsnotify_sb_has_priority_watchers(inode->i_sb,
+					       FSNOTIFY_PRIO_PRE_CONTENT))
+		return 0;
+
+	return fsnotify_pre_content(path, &length, 0);
 }
 
 /*
- * fsnotify_file_perm - permission hook before file access
+ * fsnotify_file_perm - permission hook before file access (unknown range)
  */
 static inline int fsnotify_file_perm(struct file *file, int perm_mask)
 {
@@ -168,22 +200,34 @@ static inline int fsnotify_open_perm(struct file *file)
 {
 	int ret;
 
+	if (likely(!FMODE_FSNOTIFY_PERM(file->f_mode)))
+		return 0;
+
 	if (file->f_flags & __FMODE_EXEC) {
-		ret = fsnotify_file(file, FS_OPEN_EXEC_PERM);
+		ret = fsnotify_path(&file->f_path, FS_OPEN_EXEC_PERM);
 		if (ret)
 			return ret;
 	}
 
-	return fsnotify_file(file, FS_OPEN_PERM);
+	return fsnotify_path(&file->f_path, FS_OPEN_PERM);
 }
 
 #else
+static inline void file_set_fsnotify_mode(struct file *file)
+{
+}
+
 static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
 					  const loff_t *ppos, size_t count)
 {
 	return 0;
 }
 
+static inline int fsnotify_truncate_perm(const struct path *path, loff_t length)
+{
+	return 0;
+}
+
 static inline int fsnotify_file_perm(struct file *file, int perm_mask)
 {
 	return 0;
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 3ecf7768e577..0d24a21a8e60 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -55,6 +55,9 @@
 #define FS_OPEN_PERM		0x00010000	/* open event in an permission hook */
 #define FS_ACCESS_PERM		0x00020000	/* access event in a permissions hook */
 #define FS_OPEN_EXEC_PERM	0x00040000	/* open/exec event in a permission hook */
+/* #define FS_DIR_MODIFY	0x00080000 */	/* Deprecated (reserved) */
+
+#define FS_PRE_ACCESS		0x00100000	/* Pre-content access hook */
 
 /*
  * Set on inode mark that cares about things that happen to its children.
@@ -77,8 +80,14 @@
  */
 #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME)
 
-#define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \
-				  FS_OPEN_EXEC_PERM)
+/* Content events can be used to inspect file content */
+#define FSNOTIFY_CONTENT_PERM_EVENTS (FS_OPEN_PERM | FS_OPEN_EXEC_PERM | \
+				      FS_ACCESS_PERM)
+/* Pre-content events can be used to fill file content */
+#define FSNOTIFY_PRE_CONTENT_EVENTS  (FS_PRE_ACCESS)
+
+#define ALL_FSNOTIFY_PERM_EVENTS (FSNOTIFY_CONTENT_PERM_EVENTS | \
+				  FSNOTIFY_PRE_CONTENT_EVENTS)
 
 /*
  * This is a list of all events that may get sent to a parent that is watching
@@ -285,6 +294,7 @@ static inline void fsnotify_group_assert_locked(struct fsnotify_group *group)
 /* When calling fsnotify tell it if the data is a path or inode */
 enum fsnotify_data_type {
 	FSNOTIFY_EVENT_NONE,
+	FSNOTIFY_EVENT_FILE_RANGE,
 	FSNOTIFY_EVENT_PATH,
 	FSNOTIFY_EVENT_INODE,
 	FSNOTIFY_EVENT_DENTRY,
@@ -297,6 +307,17 @@ struct fs_error_report {
 	struct super_block *sb;
 };
 
+struct file_range {
+	const struct path *path;
+	loff_t pos;
+	size_t count;
+};
+
+static inline const struct path *file_range_path(const struct file_range *range)
+{
+	return range->path;
+}
+
 static inline struct inode *fsnotify_data_inode(const void *data, int data_type)
 {
 	switch (data_type) {
@@ -306,6 +327,8 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type)
 		return d_inode(data);
 	case FSNOTIFY_EVENT_PATH:
 		return d_inode(((const struct path *)data)->dentry);
+	case FSNOTIFY_EVENT_FILE_RANGE:
+		return d_inode(file_range_path(data)->dentry);
 	case FSNOTIFY_EVENT_ERROR:
 		return ((struct fs_error_report *)data)->inode;
 	default:
@@ -321,6 +344,8 @@ static inline struct dentry *fsnotify_data_dentry(const void *data, int data_typ
 		return (struct dentry *)data;
 	case FSNOTIFY_EVENT_PATH:
 		return ((const struct path *)data)->dentry;
+	case FSNOTIFY_EVENT_FILE_RANGE:
+		return file_range_path(data)->dentry;
 	default:
 		return NULL;
 	}
@@ -332,6 +357,8 @@ static inline const struct path *fsnotify_data_path(const void *data,
 	switch (data_type) {
 	case FSNOTIFY_EVENT_PATH:
 		return data;
+	case FSNOTIFY_EVENT_FILE_RANGE:
+		return file_range_path(data);
 	default:
 		return NULL;
 	}
@@ -347,6 +374,8 @@ static inline struct super_block *fsnotify_data_sb(const void *data,
 		return ((struct dentry *)data)->d_sb;
 	case FSNOTIFY_EVENT_PATH:
 		return ((const struct path *)data)->dentry->d_sb;
+	case FSNOTIFY_EVENT_FILE_RANGE:
+		return file_range_path(data)->dentry->d_sb;
 	case FSNOTIFY_EVENT_ERROR:
 		return ((struct fs_error_report *) data)->sb;
 	default:
@@ -366,6 +395,18 @@ static inline struct fs_error_report *fsnotify_data_error_report(
 	}
 }
 
+static inline const struct file_range *fsnotify_data_file_range(
+							const void *data,
+							int data_type)
+{
+	switch (data_type) {
+	case FSNOTIFY_EVENT_FILE_RANGE:
+		return (struct file_range *)data;
+	default:
+		return NULL;
+	}
+}
+
 /*
  * Index to merged marks iterator array that correlates to a type of watch.
  * The type of watched object can be deduced from the iterator type, but not
@@ -854,9 +895,17 @@ static inline void fsnotify_init_event(struct fsnotify_event *event)
 {
 	INIT_LIST_HEAD(&event->list);
 }
+int fsnotify_pre_content(const struct path *path, const loff_t *ppos,
+			 size_t count);
 
 #else
 
+static inline int fsnotify_pre_content(const struct path *path,
+				       const loff_t *ppos, size_t count)
+{
+	return 0;
+}
+
 static inline int fsnotify(__u32 mask, const void *data, int data_type,
 			   struct inode *dir, const struct qstr *name,
 			   struct inode *inode, u32 cookie)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f02925447e59..21428d897d76 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3431,6 +3431,7 @@ extern vm_fault_t filemap_fault(struct vm_fault *vmf);
 extern vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		pgoff_t start_pgoff, pgoff_t end_pgoff);
 extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf);
+extern vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf);
 
 extern unsigned long stack_guard_gap;
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */