Merge tag 'fsnotify_for_v5.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs

Pull fsnotify updates from Jan Kara:
 "This implements the fanotify FAN_DIR_MODIFY event.

  This event reports the name in a directory under which a change
  happened and together with the directory filehandle and fstatat()
  allows reliable and efficient implementation of directory
  synchronization"

* tag 'fsnotify_for_v5.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
  fanotify: Fix the checks in fanotify_fsid_equal
  fanotify: report name info for FAN_DIR_MODIFY event
  fanotify: record name info for FAN_DIR_MODIFY event
  fanotify: Drop fanotify_event_has_fid()
  fanotify: prepare to report both parent and child fid's
  fanotify: send FAN_DIR_MODIFY event flavor with dir inode and name
  fanotify: divorce fanotify_path_event and fanotify_fid_event
  fanotify: Store fanotify handles differently
  fanotify: Simplify create_fd()
  fanotify: fix merging marks masks with FAN_ONDIR
  fanotify: merge duplicate events on parent and child
  fsnotify: replace inode pointer with an object id
  fsnotify: simplify arguments passing to fsnotify_parent()
  fsnotify: use helpers to access data by data_type
  fsnotify: funnel all dirent events through fsnotify_name()
  fsnotify: factor helpers fsnotify_dentry() and fsnotify_file()
  fsnotify: tidy up FS_ and FAN_ constants

fs/notify/fanotify/fanotify.c

@@ -17,6 +17,59 @@
 
 #include "fanotify.h"
 
+static bool fanotify_path_equal(struct path *p1, struct path *p2)
+{
+	return p1->mnt == p2->mnt && p1->dentry == p2->dentry;
+}
+
+static inline bool fanotify_fsid_equal(__kernel_fsid_t *fsid1,
+				       __kernel_fsid_t *fsid2)
+{
+	return fsid1->val[0] == fsid2->val[0] && fsid1->val[1] == fsid2->val[1];
+}
+
+static bool fanotify_fh_equal(struct fanotify_fh *fh1,
+			      struct fanotify_fh *fh2)
+{
+	if (fh1->type != fh2->type || fh1->len != fh2->len)
+		return false;
+
+	/* Do not merge events if we failed to encode fh */
+	if (fh1->type == FILEID_INVALID)
+		return false;
+
+	return !fh1->len ||
+		!memcmp(fanotify_fh_buf(fh1), fanotify_fh_buf(fh2), fh1->len);
+}
+
+static bool fanotify_fid_event_equal(struct fanotify_fid_event *ffe1,
+				     struct fanotify_fid_event *ffe2)
+{
+	/* Do not merge fid events without object fh */
+	if (!ffe1->object_fh.len)
+		return false;
+
+	return fanotify_fsid_equal(&ffe1->fsid, &ffe2->fsid) &&
+		fanotify_fh_equal(&ffe1->object_fh, &ffe2->object_fh);
+}
+
+static bool fanotify_name_event_equal(struct fanotify_name_event *fne1,
+				      struct fanotify_name_event *fne2)
+{
+	/*
+	 * Do not merge name events without dir fh.
+	 * FAN_DIR_MODIFY does not encode object fh, so it may be empty.
+	 */
+	if (!fne1->dir_fh.len)
+		return false;
+
+	if (fne1->name_len != fne2->name_len ||
+	    !fanotify_fh_equal(&fne1->dir_fh, &fne2->dir_fh))
+		return false;
+
+	return !memcmp(fne1->name, fne2->name, fne1->name_len);
+}
+
 static bool should_merge(struct fsnotify_event *old_fsn,
 			 struct fsnotify_event *new_fsn)
 {
@@ -26,14 +79,15 @@ static bool should_merge(struct fsnotify_event *old_fsn,
 	old = FANOTIFY_E(old_fsn);
 	new = FANOTIFY_E(new_fsn);
 
-	if (old_fsn->inode != new_fsn->inode || old->pid != new->pid ||
-	    old->fh_type != new->fh_type || old->fh_len != new->fh_len)
+	if (old_fsn->objectid != new_fsn->objectid ||
+	    old->type != new->type || old->pid != new->pid)
 		return false;
 
-	if (fanotify_event_has_path(old)) {
-		return old->path.mnt == new->path.mnt &&
-			old->path.dentry == new->path.dentry;
-	} else if (fanotify_event_has_fid(old)) {
+	switch (old->type) {
+	case FANOTIFY_EVENT_TYPE_PATH:
+		return fanotify_path_equal(fanotify_event_path(old),
+					   fanotify_event_path(new));
+	case FANOTIFY_EVENT_TYPE_FID:
 		/*
 		 * We want to merge many dirent events in the same dir (i.e.
 		 * creates/unlinks/renames), but we do not want to merge dirent
@@ -42,11 +96,18 @@ static bool should_merge(struct fsnotify_event *old_fsn,
 		 * mask FAN_CREATE|FAN_DELETE|FAN_ONDIR if it describes mkdir+
 		 * unlink pair or rmdir+create pair of events.
 		 */
-		return (old->mask & FS_ISDIR) == (new->mask & FS_ISDIR) &&
-			fanotify_fid_equal(&old->fid, &new->fid, old->fh_len);
+		if ((old->mask & FS_ISDIR) != (new->mask & FS_ISDIR))
+			return false;
+
+		return fanotify_fid_event_equal(FANOTIFY_FE(old),
+						FANOTIFY_FE(new));
+	case FANOTIFY_EVENT_TYPE_FID_NAME:
+		return fanotify_name_event_equal(FANOTIFY_NE(old),
+						 FANOTIFY_NE(new));
+	default:
+		WARN_ON_ONCE(1);
 	}
 
-	/* Do not merge events if we failed to encode fid */
 	return false;
 }
 
@@ -151,7 +212,7 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 {
 	__u32 marks_mask = 0, marks_ignored_mask = 0;
 	__u32 test_mask, user_mask = FANOTIFY_OUTGOING_EVENTS;
-	const struct path *path = data;
+	const struct path *path = fsnotify_data_path(data, data_type);
 	struct fsnotify_mark *mark;
 	int type;
 
@@ -160,7 +221,7 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 
 	if (!FAN_GROUP_FLAG(group, FAN_REPORT_FID)) {
 		/* Do we have path to open a file descriptor? */
-		if (data_type != FSNOTIFY_EVENT_PATH)
+		if (!path)
 			return 0;
 		/* Path type events are only relevant for files and dirs */
 		if (!d_is_reg(path->dentry) && !d_can_lookup(path->dentry))
@@ -171,6 +232,13 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 		if (!fsnotify_iter_should_report_type(iter_info, type))
 			continue;
 		mark = iter_info->marks[type];
+		/*
+		 * If the event is on dir and this mark doesn't care about
+		 * events on dir, don't send it!
+		 */
+		if (event_mask & FS_ISDIR && !(mark->mask & FS_ISDIR))
+			continue;
+
 		/*
 		 * If the event is for a child and this mark doesn't care about
 		 * events on a child, don't send it!
@@ -187,9 +255,9 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 	test_mask = event_mask & marks_mask & ~marks_ignored_mask;
 
 	/*
-	 * dirent modification events (create/delete/move) do not carry the
-	 * child entry name/inode information. Instead, we report FAN_ONDIR
-	 * for mkdir/rmdir so user can differentiate them from creat/unlink.
+	 * For dirent modification events (create/delete/move) that do not carry
+	 * the child entry name information, we report FAN_ONDIR for mkdir/rmdir
+	 * so user can differentiate them from creat/unlink.
 	 *
 	 * For backward compatibility and consistency, do not report FAN_ONDIR
 	 * to user in legacy fanotify mode (reporting fd) and report FAN_ONDIR
@@ -203,22 +271,20 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 		user_mask &= ~FAN_ONDIR;
 	}
 
-	if (event_mask & FS_ISDIR &&
-	    !(marks_mask & FS_ISDIR & ~marks_ignored_mask))
-		return 0;
-
 	return test_mask & user_mask;
 }
 
-static int fanotify_encode_fid(struct fanotify_event *event,
-			       struct inode *inode, gfp_t gfp,
-			       __kernel_fsid_t *fsid)
+static void fanotify_encode_fh(struct fanotify_fh *fh, struct inode *inode,
+			       gfp_t gfp)
 {
-	struct fanotify_fid *fid = &event->fid;
-	int dwords, bytes = 0;
-	int err, type;
+	int dwords, type, bytes = 0;
+	char *ext_buf = NULL;
+	void *buf = fh->buf;
+	int err;
+
+	if (!inode)
+		goto out;
 
-	fid->ext_fh = NULL;
 	dwords = 0;
 	err = -ENOENT;
 	type = exportfs_encode_inode_fh(inode, NULL, &dwords, NULL);
@@ -229,31 +295,33 @@ static int fanotify_encode_fid(struct fanotify_event *event,
 	if (bytes > FANOTIFY_INLINE_FH_LEN) {
 		/* Treat failure to allocate fh as failure to allocate event */
 		err = -ENOMEM;
-		fid->ext_fh = kmalloc(bytes, gfp);
-		if (!fid->ext_fh)
+		ext_buf = kmalloc(bytes, gfp);
+		if (!ext_buf)
 			goto out_err;
+
+		*fanotify_fh_ext_buf_ptr(fh) = ext_buf;
+		buf = ext_buf;
 	}
 
-	type = exportfs_encode_inode_fh(inode, fanotify_fid_fh(fid, bytes),
-					&dwords, NULL);
+	type = exportfs_encode_inode_fh(inode, buf, &dwords, NULL);
 	err = -EINVAL;
 	if (!type || type == FILEID_INVALID || bytes != dwords << 2)
 		goto out_err;
 
-	fid->fsid = *fsid;
-	event->fh_len = bytes;
+	fh->type = type;
+	fh->len = bytes;
 
-	return type;
+	return;
 
 out_err:
-	pr_warn_ratelimited("fanotify: failed to encode fid (fsid=%x.%x, "
-			    "type=%d, bytes=%d, err=%i)\n",
-			    fsid->val[0], fsid->val[1], type, bytes, err);
-	kfree(fid->ext_fh);
-	fid->ext_fh = NULL;
-	event->fh_len = 0;
-
-	return FILEID_INVALID;
+	pr_warn_ratelimited("fanotify: failed to encode fid (type=%d, len=%d, err=%i)\n",
+			    type, bytes, err);
+	kfree(ext_buf);
+	*fanotify_fh_ext_buf_ptr(fh) = NULL;
+out:
+	/* Report the event without a file identifier on encode error */
+	fh->type = FILEID_INVALID;
+	fh->len = 0;
 }
 
 /*
@@ -269,21 +337,22 @@ static struct inode *fanotify_fid_inode(struct inode *to_tell, u32 event_mask,
 {
 	if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS)
 		return to_tell;
-	else if (data_type == FSNOTIFY_EVENT_INODE)
-		return (struct inode *)data;
-	else if (data_type == FSNOTIFY_EVENT_PATH)
-		return d_inode(((struct path *)data)->dentry);
-	return NULL;
+
+	return (struct inode *)fsnotify_data_inode(data, data_type);
 }
 
 struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 					    struct inode *inode, u32 mask,
 					    const void *data, int data_type,
+					    const struct qstr *file_name,
 					    __kernel_fsid_t *fsid)
 {
 	struct fanotify_event *event = NULL;
+	struct fanotify_fid_event *ffe = NULL;
+	struct fanotify_name_event *fne = NULL;
 	gfp_t gfp = GFP_KERNEL_ACCOUNT;
 	struct inode *id = fanotify_fid_inode(inode, mask, data, data_type);
+	const struct path *path = fsnotify_data_path(data, data_type);
 
 	/*
 	 * For queues with unlimited length lost events are not expected and
@@ -305,33 +374,81 @@ struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 		pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp);
 		if (!pevent)
 			goto out;
+
 		event = &pevent->fae;
+		event->type = FANOTIFY_EVENT_TYPE_PATH_PERM;
 		pevent->response = 0;
 		pevent->state = FAN_EVENT_INIT;
 		goto init;
 	}
-	event = kmem_cache_alloc(fanotify_event_cachep, gfp);
-	if (!event)
-		goto out;
-init: __maybe_unused
-	fsnotify_init_event(&event->fse, inode);
+
+	/*
+	 * For FAN_DIR_MODIFY event, we report the fid of the directory and
+	 * the name of the modified entry.
+	 * Allocate an fanotify_name_event struct and copy the name.
+	 */
+	if (mask & FAN_DIR_MODIFY && !(WARN_ON_ONCE(!file_name))) {
+		fne = kmalloc(sizeof(*fne) + file_name->len + 1, gfp);
+		if (!fne)
+			goto out;
+
+		event = &fne->fae;
+		event->type = FANOTIFY_EVENT_TYPE_FID_NAME;
+		fne->name_len = file_name->len;
+		strcpy(fne->name, file_name->name);
+		goto init;
+	}
+
+	if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) {
+		ffe = kmem_cache_alloc(fanotify_fid_event_cachep, gfp);
+		if (!ffe)
+			goto out;
+
+		event = &ffe->fae;
+		event->type = FANOTIFY_EVENT_TYPE_FID;
+	} else {
+		struct fanotify_path_event *pevent;
+
+		pevent = kmem_cache_alloc(fanotify_path_event_cachep, gfp);
+		if (!pevent)
+			goto out;
+
+		event = &pevent->fae;
+		event->type = FANOTIFY_EVENT_TYPE_PATH;
+	}
+
+init:
+	/*
+	 * Use the victim inode instead of the watching inode as the id for
+	 * event queue, so event reported on parent is merged with event
+	 * reported on child when both directory and child watches exist.
+	 */
+	fsnotify_init_event(&event->fse, (unsigned long)id);
 	event->mask = mask;
 	if (FAN_GROUP_FLAG(group, FAN_REPORT_TID))
 		event->pid = get_pid(task_pid(current));
 	else
 		event->pid = get_pid(task_tgid(current));
-	event->fh_len = 0;
-	if (id && FAN_GROUP_FLAG(group, FAN_REPORT_FID)) {
-		/* Report the event without a file identifier on encode error */
-		event->fh_type = fanotify_encode_fid(event, id, gfp, fsid);
-	} else if (data_type == FSNOTIFY_EVENT_PATH) {
-		event->fh_type = FILEID_ROOT;
-		event->path = *((struct path *)data);
-		path_get(&event->path);
-	} else {
-		event->fh_type = FILEID_INVALID;
-		event->path.mnt = NULL;
-		event->path.dentry = NULL;
+
+	if (fsid && fanotify_event_fsid(event))
+		*fanotify_event_fsid(event) = *fsid;
+
+	if (fanotify_event_object_fh(event))
+		fanotify_encode_fh(fanotify_event_object_fh(event), id, gfp);
+
+	if (fanotify_event_dir_fh(event))
+		fanotify_encode_fh(fanotify_event_dir_fh(event), id, gfp);
+
+	if (fanotify_event_has_path(event)) {
+		struct path *p = fanotify_event_path(event);
+
+		if (path) {
+			*p = *path;
+			path_get(path);
+		} else {
+			p->mnt = NULL;
+			p->dentry = NULL;
+		}
 	}
 out:
 	memalloc_unuse_memcg();
@@ -392,6 +509,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 	BUILD_BUG_ON(FAN_MOVED_FROM != FS_MOVED_FROM);
 	BUILD_BUG_ON(FAN_CREATE != FS_CREATE);
 	BUILD_BUG_ON(FAN_DELETE != FS_DELETE);
+	BUILD_BUG_ON(FAN_DIR_MODIFY != FS_DIR_MODIFY);
 	BUILD_BUG_ON(FAN_DELETE_SELF != FS_DELETE_SELF);
 	BUILD_BUG_ON(FAN_MOVE_SELF != FS_MOVE_SELF);
 	BUILD_BUG_ON(FAN_EVENT_ON_CHILD != FS_EVENT_ON_CHILD);
@@ -402,7 +520,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 	BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC);
 	BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM);
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 20);
 
 	mask = fanotify_group_event_mask(group, iter_info, mask, data,
 					 data_type);
@@ -429,7 +547,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 	}
 
 	event = fanotify_alloc_event(group, inode, mask, data, data_type,
-				     &fsid);
+				     file_name, &fsid);
 	ret = -ENOMEM;
 	if (unlikely(!event)) {
 		/*
@@ -451,7 +569,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 
 		ret = 0;
 	} else if (fanotify_is_perm_event(mask)) {
-		ret = fanotify_get_response(group, FANOTIFY_PE(fsn_event),
+		ret = fanotify_get_response(group, FANOTIFY_PERM(event),
 					    iter_info);
 	}
 finish:
@@ -470,22 +588,58 @@ static void fanotify_free_group_priv(struct fsnotify_group *group)
 	free_uid(user);
 }
 
+static void fanotify_free_path_event(struct fanotify_event *event)
+{
+	path_put(fanotify_event_path(event));
+	kmem_cache_free(fanotify_path_event_cachep, FANOTIFY_PE(event));
+}
+
+static void fanotify_free_perm_event(struct fanotify_event *event)
+{
+	path_put(fanotify_event_path(event));
+	kmem_cache_free(fanotify_perm_event_cachep, FANOTIFY_PERM(event));
+}
+
+static void fanotify_free_fid_event(struct fanotify_event *event)
+{
+	struct fanotify_fid_event *ffe = FANOTIFY_FE(event);
+
+	if (fanotify_fh_has_ext_buf(&ffe->object_fh))
+		kfree(fanotify_fh_ext_buf(&ffe->object_fh));
+	kmem_cache_free(fanotify_fid_event_cachep, ffe);
+}
+
+static void fanotify_free_name_event(struct fanotify_event *event)
+{
+	struct fanotify_name_event *fne = FANOTIFY_NE(event);
+
+	if (fanotify_fh_has_ext_buf(&fne->dir_fh))
+		kfree(fanotify_fh_ext_buf(&fne->dir_fh));
+	kfree(fne);
+}
+
 static void fanotify_free_event(struct fsnotify_event *fsn_event)
 {
 	struct fanotify_event *event;
 
 	event = FANOTIFY_E(fsn_event);
-	if (fanotify_event_has_path(event))
-		path_put(&event->path);
-	else if (fanotify_event_has_ext_fh(event))
-		kfree(event->fid.ext_fh);
 	put_pid(event->pid);
-	if (fanotify_is_perm_event(event->mask)) {
-		kmem_cache_free(fanotify_perm_event_cachep,
-				FANOTIFY_PE(fsn_event));
-		return;
+	switch (event->type) {
+	case FANOTIFY_EVENT_TYPE_PATH:
+		fanotify_free_path_event(event);
+		break;
+	case FANOTIFY_EVENT_TYPE_PATH_PERM:
+		fanotify_free_perm_event(event);
+		break;
+	case FANOTIFY_EVENT_TYPE_FID:
+		fanotify_free_fid_event(event);
+		break;
+	case FANOTIFY_EVENT_TYPE_FID_NAME:
+		fanotify_free_name_event(event);
+		break;
+	default:
+		WARN_ON_ONCE(1);
 	}
-	kmem_cache_free(fanotify_event_cachep, event);
 }
 
 static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)

fs/notify/fanotify/fanotify.h

@@ -5,7 +5,8 @@
 #include <linux/exportfs.h>
 
 extern struct kmem_cache *fanotify_mark_cache;
-extern struct kmem_cache *fanotify_event_cachep;
+extern struct kmem_cache *fanotify_fid_event_cachep;
+extern struct kmem_cache *fanotify_path_event_cachep;
 extern struct kmem_cache *fanotify_perm_event_cachep;
 
 /* Possible states of the permission event */
@@ -18,94 +19,140 @@ enum {
 
 /*
  * 3 dwords are sufficient for most local fs (64bit ino, 32bit generation).
- * For 32bit arch, fid increases the size of fanotify_event by 12 bytes and
- * fh_* fields increase the size of fanotify_event by another 4 bytes.
- * For 64bit arch, fid increases the size of fanotify_fid by 8 bytes and
- * fh_* fields are packed in a hole after mask.
+ * fh buf should be dword aligned. On 64bit arch, the ext_buf pointer is
+ * stored in either the first or last 2 dwords.
  */
-#if BITS_PER_LONG == 32
 #define FANOTIFY_INLINE_FH_LEN	(3 << 2)
-#else
-#define FANOTIFY_INLINE_FH_LEN	(4 << 2)
-#endif
 
-struct fanotify_fid {
-	__kernel_fsid_t fsid;
-	union {
-		unsigned char fh[FANOTIFY_INLINE_FH_LEN];
-		unsigned char *ext_fh;
-	};
-};
+struct fanotify_fh {
+	unsigned char buf[FANOTIFY_INLINE_FH_LEN];
+	u8 type;
+	u8 len;
+} __aligned(4);
+
+static inline bool fanotify_fh_has_ext_buf(struct fanotify_fh *fh)
+{
+	return fh->len > FANOTIFY_INLINE_FH_LEN;
+}
+
+static inline char **fanotify_fh_ext_buf_ptr(struct fanotify_fh *fh)
+{
+	BUILD_BUG_ON(__alignof__(char *) - 4 + sizeof(char *) >
+		     FANOTIFY_INLINE_FH_LEN);
+	return (char **)ALIGN((unsigned long)(fh->buf), __alignof__(char *));
+}
 
-static inline void *fanotify_fid_fh(struct fanotify_fid *fid,
-				    unsigned int fh_len)
+static inline void *fanotify_fh_ext_buf(struct fanotify_fh *fh)
 {
-	return fh_len <= FANOTIFY_INLINE_FH_LEN ? fid->fh : fid->ext_fh;
+	return *fanotify_fh_ext_buf_ptr(fh);
 }
 
-static inline bool fanotify_fid_equal(struct fanotify_fid *fid1,
-				      struct fanotify_fid *fid2,
-				      unsigned int fh_len)
+static inline void *fanotify_fh_buf(struct fanotify_fh *fh)
 {
-	return fid1->fsid.val[0] == fid2->fsid.val[0] &&
-		fid1->fsid.val[1] == fid2->fsid.val[1] &&
-		!memcmp(fanotify_fid_fh(fid1, fh_len),
-			fanotify_fid_fh(fid2, fh_len), fh_len);
+	return fanotify_fh_has_ext_buf(fh) ? fanotify_fh_ext_buf(fh) : fh->buf;
 }
 
 /*
- * Structure for normal fanotify events. It gets allocated in
+ * Common structure for fanotify events. Concrete structs are allocated in
  * fanotify_handle_event() and freed when the information is retrieved by
- * userspace
+ * userspace. The type of event determines how it was allocated, how it will
+ * be freed and which concrete struct it may be cast to.
  */
+enum fanotify_event_type {
+	FANOTIFY_EVENT_TYPE_FID, /* fixed length */
+	FANOTIFY_EVENT_TYPE_FID_NAME, /* variable length */
+	FANOTIFY_EVENT_TYPE_PATH,
+	FANOTIFY_EVENT_TYPE_PATH_PERM,
+};
+
 struct fanotify_event {
 	struct fsnotify_event fse;
 	u32 mask;
-	/*
-	 * Those fields are outside fanotify_fid to pack fanotify_event nicely
-	 * on 64bit arch and to use fh_type as an indication of whether path
-	 * or fid are used in the union:
-	 * FILEID_ROOT (0) for path, > 0 for fid, FILEID_INVALID for neither.
-	 */
-	u8 fh_type;
-	u8 fh_len;
-	u16 pad;
-	union {
-		/*
-		 * We hold ref to this path so it may be dereferenced at any
-		 * point during this object's lifetime
-		 */
-		struct path path;
-		/*
-		 * With FAN_REPORT_FID, we do not hold any reference on the
-		 * victim object. Instead we store its NFS file handle and its
-		 * filesystem's fsid as a unique identifier.
-		 */
-		struct fanotify_fid fid;
-	};
+	enum fanotify_event_type type;
 	struct pid *pid;
 };
 
-static inline bool fanotify_event_has_path(struct fanotify_event *event)
+struct fanotify_fid_event {
+	struct fanotify_event fae;
+	__kernel_fsid_t fsid;
+	struct fanotify_fh object_fh;
+};
+
+static inline struct fanotify_fid_event *
+FANOTIFY_FE(struct fanotify_event *event)
 {
-	return event->fh_type == FILEID_ROOT;
+	return container_of(event, struct fanotify_fid_event, fae);
 }
 
-static inline bool fanotify_event_has_fid(struct fanotify_event *event)
+struct fanotify_name_event {
+	struct fanotify_event fae;
+	__kernel_fsid_t fsid;
+	struct fanotify_fh dir_fh;
+	u8 name_len;
+	char name[0];
+};
+
+static inline struct fanotify_name_event *
+FANOTIFY_NE(struct fanotify_event *event)
 {
-	return event->fh_type != FILEID_ROOT &&
-		event->fh_type != FILEID_INVALID;
+	return container_of(event, struct fanotify_name_event, fae);
 }
 
-static inline bool fanotify_event_has_ext_fh(struct fanotify_event *event)
+static inline __kernel_fsid_t *fanotify_event_fsid(struct fanotify_event *event)
 {
-	return fanotify_event_has_fid(event) &&
-		event->fh_len > FANOTIFY_INLINE_FH_LEN;
+	if (event->type == FANOTIFY_EVENT_TYPE_FID)
+		return &FANOTIFY_FE(event)->fsid;
+	else if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
+		return &FANOTIFY_NE(event)->fsid;
+	else
+		return NULL;
 }
 
-static inline void *fanotify_event_fh(struct fanotify_event *event)
+static inline struct fanotify_fh *fanotify_event_object_fh(
+						struct fanotify_event *event)
 {
-	return fanotify_fid_fh(&event->fid, event->fh_len);
+	if (event->type == FANOTIFY_EVENT_TYPE_FID)
+		return &FANOTIFY_FE(event)->object_fh;
+	else
+		return NULL;
+}
+
+static inline struct fanotify_fh *fanotify_event_dir_fh(
+						struct fanotify_event *event)
+{
+	if (event->type == FANOTIFY_EVENT_TYPE_FID_NAME)
+		return &FANOTIFY_NE(event)->dir_fh;
+	else
+		return NULL;
+}
+
+static inline int fanotify_event_object_fh_len(struct fanotify_event *event)
+{
+	struct fanotify_fh *fh = fanotify_event_object_fh(event);
+
+	return fh ? fh->len : 0;
+}
+
+static inline bool fanotify_event_has_name(struct fanotify_event *event)
+{
+	return event->type == FANOTIFY_EVENT_TYPE_FID_NAME;
+}
+
+static inline int fanotify_event_name_len(struct fanotify_event *event)
+{
+	return fanotify_event_has_name(event) ?
+		FANOTIFY_NE(event)->name_len : 0;
+}
+
+struct fanotify_path_event {
+	struct fanotify_event fae;
+	struct path path;
+};
+
+static inline struct fanotify_path_event *
+FANOTIFY_PE(struct fanotify_event *event)
+{
+	return container_of(event, struct fanotify_path_event, fae);
 }
 
 /*
@@ -117,15 +164,16 @@ static inline void *fanotify_event_fh(struct fanotify_event *event)
  */
 struct fanotify_perm_event {
 	struct fanotify_event fae;
+	struct path path;
 	unsigned short response;	/* userspace answer to the event */
 	unsigned short state;		/* state of the event */
 	int fd;		/* fd we passed to userspace for this event */
 };
 
 static inline struct fanotify_perm_event *
-FANOTIFY_PE(struct fsnotify_event *fse)
+FANOTIFY_PERM(struct fanotify_event *event)
 {
-	return container_of(fse, struct fanotify_perm_event, fae.fse);
+	return container_of(event, struct fanotify_perm_event, fae);
 }
 
 static inline bool fanotify_is_perm_event(u32 mask)
@@ -139,7 +187,24 @@ static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse)
 	return container_of(fse, struct fanotify_event, fse);
 }
 
+static inline bool fanotify_event_has_path(struct fanotify_event *event)
+{
+	return event->type == FANOTIFY_EVENT_TYPE_PATH ||
+		event->type == FANOTIFY_EVENT_TYPE_PATH_PERM;
+}
+
+static inline struct path *fanotify_event_path(struct fanotify_event *event)
+{
+	if (event->type == FANOTIFY_EVENT_TYPE_PATH)
+		return &FANOTIFY_PE(event)->path;
+	else if (event->type == FANOTIFY_EVENT_TYPE_PATH_PERM)
+		return &FANOTIFY_PERM(event)->path;
+	else
+		return NULL;
+}
+
 struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
 					    struct inode *inode, u32 mask,
 					    const void *data, int data_type,
+					    const struct qstr *file_name,
 					    __kernel_fsid_t *fsid);

fs/notify/fanotify/fanotify_user.c

@@ -46,32 +46,53 @@
 extern const struct fsnotify_ops fanotify_fsnotify_ops;
 
 struct kmem_cache *fanotify_mark_cache __read_mostly;
-struct kmem_cache *fanotify_event_cachep __read_mostly;
+struct kmem_cache *fanotify_fid_event_cachep __read_mostly;
+struct kmem_cache *fanotify_path_event_cachep __read_mostly;
 struct kmem_cache *fanotify_perm_event_cachep __read_mostly;
 
 #define FANOTIFY_EVENT_ALIGN 4
+#define FANOTIFY_INFO_HDR_LEN \
+	(sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle))
+
+static int fanotify_fid_info_len(int fh_len, int name_len)
+{
+	int info_len = fh_len;
+
+	if (name_len)
+		info_len += name_len + 1;
+
+	return roundup(FANOTIFY_INFO_HDR_LEN + info_len, FANOTIFY_EVENT_ALIGN);
+}
 
 static int fanotify_event_info_len(struct fanotify_event *event)
 {
-	if (!fanotify_event_has_fid(event))
-		return 0;
+	int info_len = 0;
+	int fh_len = fanotify_event_object_fh_len(event);
+
+	if (fh_len)
+		info_len += fanotify_fid_info_len(fh_len, 0);
 
-	return roundup(sizeof(struct fanotify_event_info_fid) +
-		       sizeof(struct file_handle) + event->fh_len,
-		       FANOTIFY_EVENT_ALIGN);
+	if (fanotify_event_name_len(event)) {
+		struct fanotify_name_event *fne = FANOTIFY_NE(event);
+
+		info_len += fanotify_fid_info_len(fne->dir_fh.len,
+						  fne->name_len);
+	}
+
+	return info_len;
 }
 
 /*
- * Get an fsnotify notification event if one exists and is small
+ * Get an fanotify notification event if one exists and is small
  * enough to fit in "count". Return an error pointer if the count
  * is not large enough. When permission event is dequeued, its state is
  * updated accordingly.
  */
-static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
+static struct fanotify_event *get_one_event(struct fsnotify_group *group,
 					    size_t count)
 {
 	size_t event_size = FAN_EVENT_METADATA_LEN;
-	struct fsnotify_event *fsn_event = NULL;
+	struct fanotify_event *event = NULL;
 
 	pr_debug("%s: group=%p count=%zd\n", __func__, group, count);
 
@@ -85,26 +106,23 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
 	}
 
 	if (event_size > count) {
-		fsn_event = ERR_PTR(-EINVAL);
+		event = ERR_PTR(-EINVAL);
 		goto out;
 	}
-	fsn_event = fsnotify_remove_first_event(group);
-	if (fanotify_is_perm_event(FANOTIFY_E(fsn_event)->mask))
-		FANOTIFY_PE(fsn_event)->state = FAN_EVENT_REPORTED;
+	event = FANOTIFY_E(fsnotify_remove_first_event(group));
+	if (fanotify_is_perm_event(event->mask))
+		FANOTIFY_PERM(event)->state = FAN_EVENT_REPORTED;
 out:
 	spin_unlock(&group->notification_lock);
-	return fsn_event;
+	return event;
 }
 
-static int create_fd(struct fsnotify_group *group,
-		     struct fanotify_event *event,
+static int create_fd(struct fsnotify_group *group, struct path *path,
 		     struct file **file)
 {
 	int client_fd;
 	struct file *new_file;
 
-	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
-
 	client_fd = get_unused_fd_flags(group->fanotify_data.f_flags);
 	if (client_fd < 0)
 		return client_fd;
@@ -113,14 +131,9 @@ static int create_fd(struct fsnotify_group *group,
 	 * we need a new file handle for the userspace program so it can read even if it was
 	 * originally opened O_WRONLY.
 	 */
-	/* it's possible this event was an overflow event.  in that case dentry and mnt
-	 * are NULL;  That's fine, just don't call dentry open */
-	if (event->path.dentry && event->path.mnt)
-		new_file = dentry_open(&event->path,
-				       group->fanotify_data.f_flags | FMODE_NONOTIFY,
-				       current_cred());
-	else
-		new_file = ERR_PTR(-EOVERFLOW);
+	new_file = dentry_open(path,
+			       group->fanotify_data.f_flags | FMODE_NONOTIFY,
+			       current_cred());
 	if (IS_ERR(new_file)) {
 		/*
 		 * we still send an event even if we can't open the file.  this
@@ -204,83 +217,111 @@ static int process_access_response(struct fsnotify_group *group,
 	return -ENOENT;
 }
 
-static int copy_fid_to_user(struct fanotify_event *event, char __user *buf)
+static int copy_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh,
+			     const char *name, size_t name_len,
+			     char __user *buf, size_t count)
 {
 	struct fanotify_event_info_fid info = { };
 	struct file_handle handle = { };
-	unsigned char bounce[FANOTIFY_INLINE_FH_LEN], *fh;
-	size_t fh_len = event->fh_len;
-	size_t len = fanotify_event_info_len(event);
+	unsigned char bounce[FANOTIFY_INLINE_FH_LEN], *fh_buf;
+	size_t fh_len = fh ? fh->len : 0;
+	size_t info_len = fanotify_fid_info_len(fh_len, name_len);
+	size_t len = info_len;
+
+	pr_debug("%s: fh_len=%zu name_len=%zu, info_len=%zu, count=%zu\n",
+		 __func__, fh_len, name_len, info_len, count);
 
-	if (!len)
+	if (!fh_len || (name && !name_len))
 		return 0;
 
-	if (WARN_ON_ONCE(len < sizeof(info) + sizeof(handle) + fh_len))
+	if (WARN_ON_ONCE(len < sizeof(info) || len > count))
 		return -EFAULT;
 
-	/* Copy event info fid header followed by vaiable sized file handle */
-	info.hdr.info_type = FAN_EVENT_INFO_TYPE_FID;
+	/*
+	 * Copy event info fid header followed by variable sized file handle
+	 * and optionally followed by variable sized filename.
+	 */
+	info.hdr.info_type = name_len ? FAN_EVENT_INFO_TYPE_DFID_NAME :
+					FAN_EVENT_INFO_TYPE_FID;
 	info.hdr.len = len;
-	info.fsid = event->fid.fsid;
+	info.fsid = *fsid;
 	if (copy_to_user(buf, &info, sizeof(info)))
 		return -EFAULT;
 
 	buf += sizeof(info);
 	len -= sizeof(info);
-	handle.handle_type = event->fh_type;
+	if (WARN_ON_ONCE(len < sizeof(handle)))
+		return -EFAULT;
+
+	handle.handle_type = fh->type;
 	handle.handle_bytes = fh_len;
 	if (copy_to_user(buf, &handle, sizeof(handle)))
 		return -EFAULT;
 
 	buf += sizeof(handle);
 	len -= sizeof(handle);
+	if (WARN_ON_ONCE(len < fh_len))
+		return -EFAULT;
+
 	/*
-	 * For an inline fh, copy through stack to exclude the copy from
-	 * usercopy hardening protections.
+	 * For an inline fh and inline file name, copy through stack to exclude
+	 * the copy from usercopy hardening protections.
 	 */
-	fh = fanotify_event_fh(event);
+	fh_buf = fanotify_fh_buf(fh);
 	if (fh_len <= FANOTIFY_INLINE_FH_LEN) {
-		memcpy(bounce, fh, fh_len);
-		fh = bounce;
+		memcpy(bounce, fh_buf, fh_len);
+		fh_buf = bounce;
 	}
-	if (copy_to_user(buf, fh, fh_len))
+	if (copy_to_user(buf, fh_buf, fh_len))
 		return -EFAULT;
 
-	/* Pad with 0's */
 	buf += fh_len;
 	len -= fh_len;
+
+	if (name_len) {
+		/* Copy the filename with terminating null */
+		name_len++;
+		if (WARN_ON_ONCE(len < name_len))
+			return -EFAULT;
+
+		if (copy_to_user(buf, name, name_len))
+			return -EFAULT;
+
+		buf += name_len;
+		len -= name_len;
+	}
+
+	/* Pad with 0's */
 	WARN_ON_ONCE(len < 0 || len >= FANOTIFY_EVENT_ALIGN);
 	if (len > 0 && clear_user(buf, len))
 		return -EFAULT;
 
-	return 0;
+	return info_len;
 }
 
 static ssize_t copy_event_to_user(struct fsnotify_group *group,
-				  struct fsnotify_event *fsn_event,
+				  struct fanotify_event *event,
 				  char __user *buf, size_t count)
 {
 	struct fanotify_event_metadata metadata;
-	struct fanotify_event *event;
+	struct path *path = fanotify_event_path(event);
 	struct file *f = NULL;
 	int ret, fd = FAN_NOFD;
 
-	pr_debug("%s: group=%p event=%p\n", __func__, group, fsn_event);
+	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	event = container_of(fsn_event, struct fanotify_event, fse);
-	metadata.event_len = FAN_EVENT_METADATA_LEN;
+	metadata.event_len = FAN_EVENT_METADATA_LEN +
+					fanotify_event_info_len(event);
 	metadata.metadata_len = FAN_EVENT_METADATA_LEN;
 	metadata.vers = FANOTIFY_METADATA_VERSION;
 	metadata.reserved = 0;
 	metadata.mask = event->mask & FANOTIFY_OUTGOING_EVENTS;
 	metadata.pid = pid_vnr(event->pid);
 
-	if (fanotify_event_has_path(event)) {
-		fd = create_fd(group, event, &f);
+	if (path && path->mnt && path->dentry) {
+		fd = create_fd(group, path, &f);
 		if (fd < 0)
 			return fd;
-	} else if (fanotify_event_has_fid(event)) {
-		metadata.event_len += fanotify_event_info_len(event);
 	}
 	metadata.fd = fd;
 
@@ -295,15 +336,39 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	if (copy_to_user(buf, &metadata, FAN_EVENT_METADATA_LEN))
 		goto out_close_fd;
 
+	buf += FAN_EVENT_METADATA_LEN;
+	count -= FAN_EVENT_METADATA_LEN;
+
 	if (fanotify_is_perm_event(event->mask))
-		FANOTIFY_PE(fsn_event)->fd = fd;
+		FANOTIFY_PERM(event)->fd = fd;
 
-	if (fanotify_event_has_path(event)) {
+	if (f)
 		fd_install(fd, f);
-	} else if (fanotify_event_has_fid(event)) {
-		ret = copy_fid_to_user(event, buf + FAN_EVENT_METADATA_LEN);
+
+	/* Event info records order is: dir fid + name, child fid */
+	if (fanotify_event_name_len(event)) {
+		struct fanotify_name_event *fne = FANOTIFY_NE(event);
+
+		ret = copy_info_to_user(fanotify_event_fsid(event),
+					fanotify_event_dir_fh(event),
+					fne->name, fne->name_len,
+					buf, count);
+		if (ret < 0)
+			return ret;
+
+		buf += ret;
+		count -= ret;
+	}
+
+	if (fanotify_event_object_fh_len(event)) {
+		ret = copy_info_to_user(fanotify_event_fsid(event),
+					fanotify_event_object_fh(event),
+					NULL, 0, buf, count);
 		if (ret < 0)
 			return ret;
+
+		buf += ret;
+		count -= ret;
 	}
 
 	return metadata.event_len;
@@ -335,7 +400,7 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
 			     size_t count, loff_t *pos)
 {
 	struct fsnotify_group *group;
-	struct fsnotify_event *kevent;
+	struct fanotify_event *event;
 	char __user *start;
 	int ret;
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
@@ -347,13 +412,13 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
 
 	add_wait_queue(&group->notification_waitq, &wait);
 	while (1) {
-		kevent = get_one_event(group, count);
-		if (IS_ERR(kevent)) {
-			ret = PTR_ERR(kevent);
+		event = get_one_event(group, count);
+		if (IS_ERR(event)) {
+			ret = PTR_ERR(event);
 			break;
 		}
 
-		if (!kevent) {
+		if (!event) {
 			ret = -EAGAIN;
 			if (file->f_flags & O_NONBLOCK)
 				break;
@@ -369,7 +434,7 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
 			continue;
 		}
 
-		ret = copy_event_to_user(group, kevent, buf, count);
+		ret = copy_event_to_user(group, event, buf, count);
 		if (unlikely(ret == -EOPENSTALE)) {
 			/*
 			 * We cannot report events with stale fd so drop it.
@@ -384,17 +449,17 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
 		 * Permission events get queued to wait for response.  Other
 		 * events can be destroyed now.
 		 */
-		if (!fanotify_is_perm_event(FANOTIFY_E(kevent)->mask)) {
-			fsnotify_destroy_event(group, kevent);
+		if (!fanotify_is_perm_event(event->mask)) {
+			fsnotify_destroy_event(group, &event->fse);
 		} else {
 			if (ret <= 0) {
 				spin_lock(&group->notification_lock);
 				finish_permission_event(group,
-					FANOTIFY_PE(kevent), FAN_DENY);
+					FANOTIFY_PERM(event), FAN_DENY);
 				wake_up(&group->fanotify_data.access_waitq);
 			} else {
 				spin_lock(&group->notification_lock);
-				list_add_tail(&kevent->list,
+				list_add_tail(&event->fse.list,
 					&group->fanotify_data.access_list);
 				spin_unlock(&group->notification_lock);
 			}
@@ -440,8 +505,6 @@ static ssize_t fanotify_write(struct file *file, const char __user *buf, size_t
 static int fanotify_release(struct inode *ignored, struct file *file)
 {
 	struct fsnotify_group *group = file->private_data;
-	struct fanotify_perm_event *event;
-	struct fsnotify_event *fsn_event;
 
 	/*
 	 * Stop new events from arriving in the notification queue. since
@@ -456,6 +519,8 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 	 */
 	spin_lock(&group->notification_lock);
 	while (!list_empty(&group->fanotify_data.access_list)) {
+		struct fanotify_perm_event *event;
+
 		event = list_first_entry(&group->fanotify_data.access_list,
 				struct fanotify_perm_event, fae.fse.list);
 		list_del_init(&event->fae.fse.list);
@@ -469,12 +534,14 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 	 * response is consumed and fanotify_get_response() returns.
 	 */
 	while (!fsnotify_notify_queue_is_empty(group)) {
-		fsn_event = fsnotify_remove_first_event(group);
-		if (!(FANOTIFY_E(fsn_event)->mask & FANOTIFY_PERM_EVENTS)) {
+		struct fanotify_event *event;
+
+		event = FANOTIFY_E(fsnotify_remove_first_event(group));
+		if (!(event->mask & FANOTIFY_PERM_EVENTS)) {
 			spin_unlock(&group->notification_lock);
-			fsnotify_destroy_event(group, fsn_event);
+			fsnotify_destroy_event(group, &event->fse);
 		} else {
-			finish_permission_event(group, FANOTIFY_PE(fsn_event),
+			finish_permission_event(group, FANOTIFY_PERM(event),
 						FAN_ALLOW);
 		}
 		spin_lock(&group->notification_lock);
@@ -824,7 +891,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	group->memcg = get_mem_cgroup_from_mm(current->mm);
 
 	oevent = fanotify_alloc_event(group, NULL, FS_Q_OVERFLOW, NULL,
-				      FSNOTIFY_EVENT_NONE, NULL);
+				      FSNOTIFY_EVENT_NONE, NULL, NULL);
 	if (unlikely(!oevent)) {
 		fd = -ENOMEM;
 		goto out_destroy_group;
@@ -1139,7 +1206,10 @@ static int __init fanotify_user_setup(void)
 
 	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
 					 SLAB_PANIC|SLAB_ACCOUNT);
-	fanotify_event_cachep = KMEM_CACHE(fanotify_event, SLAB_PANIC);
+	fanotify_fid_event_cachep = KMEM_CACHE(fanotify_fid_event,
+					       SLAB_PANIC);
+	fanotify_path_event_cachep = KMEM_CACHE(fanotify_path_event,
+						SLAB_PANIC);
 	if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) {
 		fanotify_perm_event_cachep =
 			KMEM_CACHE(fanotify_perm_event, SLAB_PANIC);

fs/notify/fsnotify.c

@@ -143,15 +143,13 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
 }
 
 /* Notify this dentry's parent about a child's events. */
-int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask)
+int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
+		    int data_type)
 {
 	struct dentry *parent;
 	struct inode *p_inode;
 	int ret = 0;
 
-	if (!dentry)
-		dentry = path->dentry;
-
 	if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED))
 		return 0;
 
@@ -168,12 +166,7 @@ int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask
 		mask |= FS_EVENT_ON_CHILD;
 
 		take_dentry_name_snapshot(&name, dentry);
-		if (path)
-			ret = fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH,
-				       &name.name, 0);
-		else
-			ret = fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE,
-				       &name.name, 0);
+		ret = fsnotify(p_inode, mask, data, data_type, &name.name, 0);
 		release_dentry_name_snapshot(&name);
 	}
 
@@ -181,7 +174,7 @@ int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(__fsnotify_parent);
+EXPORT_SYMBOL_GPL(fsnotify_parent);
 
 static int send_to_group(struct inode *to_tell,
 			 __u32 mask, const void *data,
@@ -318,6 +311,7 @@ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info)
 int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
 	     const struct qstr *file_name, u32 cookie)
 {
+	const struct path *path = fsnotify_data_path(data, data_is);
 	struct fsnotify_iter_info iter_info = {};
 	struct super_block *sb = to_tell->i_sb;
 	struct mount *mnt = NULL;
@@ -325,8 +319,8 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
 	int ret = 0;
 	__u32 test_mask = (mask & ALL_FSNOTIFY_EVENTS);
 
-	if (data_is == FSNOTIFY_EVENT_PATH) {
-		mnt = real_mount(((const struct path *)data)->mnt);
+	if (path) {
+		mnt = real_mount(path->mnt);
 		mnt_or_sb_mask |= mnt->mnt_fsnotify_mask;
 	}
 	/* An event "on child" is not intended for a mount/sb mark */
@@ -389,7 +383,7 @@ static __init int fsnotify_init(void)
 {
 	int ret;
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 25);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 26);
 
 	ret = init_srcu_struct(&fsnotify_mark_srcu);
 	if (ret)

fs/notify/inotify/inotify_fsnotify.c

@@ -39,7 +39,7 @@ static bool event_compare(struct fsnotify_event *old_fsn,
 	if (old->mask & FS_IN_IGNORED)
 		return false;
 	if ((old->mask == new->mask) &&
-	    (old_fsn->inode == new_fsn->inode) &&
+	    (old_fsn->objectid == new_fsn->objectid) &&
 	    (old->name_len == new->name_len) &&
 	    (!old->name_len || !strcmp(old->name, new->name)))
 		return true;
@@ -61,6 +61,7 @@ int inotify_handle_event(struct fsnotify_group *group,
 			 const struct qstr *file_name, u32 cookie,
 			 struct fsnotify_iter_info *iter_info)
 {
+	const struct path *path = fsnotify_data_path(data, data_type);
 	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
 	struct inotify_inode_mark *i_mark;
 	struct inotify_event_info *event;
@@ -73,12 +74,9 @@ int inotify_handle_event(struct fsnotify_group *group,
 		return 0;
 
 	if ((inode_mark->mask & FS_EXCL_UNLINK) &&
-	    (data_type == FSNOTIFY_EVENT_PATH)) {
-		const struct path *path = data;
+	    path && d_unlinked(path->dentry))
+		return 0;
 
-		if (d_unlinked(path->dentry))
-			return 0;
-	}
 	if (file_name) {
 		len = file_name->len;
 		alloc_len += len + 1;
@@ -118,7 +116,7 @@ int inotify_handle_event(struct fsnotify_group *group,
 		mask &= ~IN_ISDIR;
 
 	fsn_event = &event->fse;
-	fsnotify_init_event(fsn_event, inode);
+	fsnotify_init_event(fsn_event, (unsigned long)inode);
 	event->mask = mask;
 	event->wd = i_mark->wd;
 	event->sync_cookie = cookie;

fs/notify/inotify/inotify_user.c

@@ -635,7 +635,7 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 		return ERR_PTR(-ENOMEM);
 	}
 	group->overflow_event = &oevent->fse;
-	fsnotify_init_event(group->overflow_event, NULL);
+	fsnotify_init_event(group->overflow_event, 0);
 	oevent->mask = FS_Q_OVERFLOW;
 	oevent->wd = -1;
 	oevent->sync_cookie = 0;

include/linux/fanotify.h

@@ -47,7 +47,8 @@
  * Directory entry modification events - reported only to directory
  * where entry is modified and not to a watching parent.
  */
-#define FANOTIFY_DIRENT_EVENTS	(FAN_MOVE | FAN_CREATE | FAN_DELETE)
+#define FANOTIFY_DIRENT_EVENTS	(FAN_MOVE | FAN_CREATE | FAN_DELETE | \
+				 FAN_DIR_MODIFY)
 
 /* Events that can only be reported with data type FSNOTIFY_EVENT_INODE */
 #define FANOTIFY_INODE_EVENTS	(FANOTIFY_DIRENT_EVENTS | \

include/linux/fsnotify.h

@@ -18,39 +18,63 @@
 #include <linux/bug.h>
 
 /*
- * Notify this @dir inode about a change in the directory entry @dentry.
+ * Notify this @dir inode about a change in a child directory entry.
+ * The directory entry may have turned positive or negative or its inode may
+ * have changed (i.e. renamed over).
  *
  * Unlike fsnotify_parent(), the event will be reported regardless of the
  * FS_EVENT_ON_CHILD mask on the parent inode.
  */
-static inline int fsnotify_dirent(struct inode *dir, struct dentry *dentry,
-				  __u32 mask)
+static inline void fsnotify_name(struct inode *dir, __u32 mask,
+				 struct inode *child,
+				 const struct qstr *name, u32 cookie)
 {
-	return fsnotify(dir, mask, d_inode(dentry), FSNOTIFY_EVENT_INODE,
-			&dentry->d_name, 0);
+	fsnotify(dir, mask, child, FSNOTIFY_EVENT_INODE, name, cookie);
+	/*
+	 * Send another flavor of the event without child inode data and
+	 * without the specific event type (e.g. FS_CREATE|FS_IS_DIR).
+	 * The name is relative to the dir inode the event is reported to.
+	 */
+	fsnotify(dir, FS_DIR_MODIFY, dir, FSNOTIFY_EVENT_INODE, name, 0);
 }
 
-/* Notify this dentry's parent about a child's events. */
-static inline int fsnotify_parent(const struct path *path,
-				  struct dentry *dentry, __u32 mask)
+static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry,
+				   __u32 mask)
 {
-	if (!dentry)
-		dentry = path->dentry;
-
-	return __fsnotify_parent(path, dentry, mask);
+	fsnotify_name(dir, mask, d_inode(dentry), &dentry->d_name, 0);
 }
 
 /*
- * Simple wrapper to consolidate calls fsnotify_parent()/fsnotify() when
- * an event is on a path.
+ * Simple wrappers to consolidate calls fsnotify_parent()/fsnotify() when
+ * an event is on a file/dentry.
  */
-static inline int fsnotify_path(struct inode *inode, const struct path *path,
-				__u32 mask)
+static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask)
+{
+	struct inode *inode = d_inode(dentry);
+
+	if (S_ISDIR(inode->i_mode))
+		mask |= FS_ISDIR;
+
+	fsnotify_parent(dentry, mask, inode, FSNOTIFY_EVENT_INODE);
+	fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+}
+
+static inline int fsnotify_file(struct file *file, __u32 mask)
 {
-	int ret = fsnotify_parent(path, NULL, mask);
+	const struct path *path = &file->f_path;
+	struct inode *inode = file_inode(file);
+	int ret;
+
+	if (file->f_mode & FMODE_NONOTIFY)
+		return 0;
+
+	if (S_ISDIR(inode->i_mode))
+		mask |= FS_ISDIR;
 
+	ret = fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
 	if (ret)
 		return ret;
+
 	return fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0);
 }
 
@@ -58,19 +82,16 @@ static inline int fsnotify_path(struct inode *inode, const struct path *path,
 static inline int fsnotify_perm(struct file *file, int mask)
 {
 	int ret;
-	const struct path *path = &file->f_path;
-	struct inode *inode = file_inode(file);
 	__u32 fsnotify_mask = 0;
 
-	if (file->f_mode & FMODE_NONOTIFY)
-		return 0;
 	if (!(mask & (MAY_READ | MAY_OPEN)))
 		return 0;
+
 	if (mask & MAY_OPEN) {
 		fsnotify_mask = FS_OPEN_PERM;
 
 		if (file->f_flags & __FMODE_EXEC) {
-			ret = fsnotify_path(inode, path, FS_OPEN_EXEC_PERM);
+			ret = fsnotify_file(file, FS_OPEN_EXEC_PERM);
 
 			if (ret)
 				return ret;
@@ -79,10 +100,7 @@ static inline int fsnotify_perm(struct file *file, int mask)
 		fsnotify_mask = FS_ACCESS_PERM;
 	}
 
-	if (S_ISDIR(inode->i_mode))
-		fsnotify_mask |= FS_ISDIR;
-
-	return fsnotify_path(inode, path, fsnotify_mask);
+	return fsnotify_file(file, fsnotify_mask);
 }
 
 /*
@@ -122,10 +140,8 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
 		mask |= FS_ISDIR;
 	}
 
-	fsnotify(old_dir, old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_name,
-		 fs_cookie);
-	fsnotify(new_dir, new_dir_mask, source, FSNOTIFY_EVENT_INODE, new_name,
-		 fs_cookie);
+	fsnotify_name(old_dir, old_dir_mask, source, old_name, fs_cookie);
+	fsnotify_name(new_dir, new_dir_mask, source, new_name, fs_cookie);
 
 	if (target)
 		fsnotify_link_count(target);
@@ -180,12 +196,13 @@ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry)
  * Note: We have to pass also the linked inode ptr as some filesystems leave
  *   new_dentry->d_inode NULL and instantiate inode pointer later
  */
-static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry)
+static inline void fsnotify_link(struct inode *dir, struct inode *inode,
+				 struct dentry *new_dentry)
 {
 	fsnotify_link_count(inode);
 	audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE);
 
-	fsnotify(dir, FS_CREATE, inode, FSNOTIFY_EVENT_INODE, &new_dentry->d_name, 0);
+	fsnotify_name(dir, FS_CREATE, inode, &new_dentry->d_name, 0);
 }
 
 /*
@@ -229,15 +246,7 @@ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry)
  */
 static inline void fsnotify_access(struct file *file)
 {
-	const struct path *path = &file->f_path;
-	struct inode *inode = file_inode(file);
-	__u32 mask = FS_ACCESS;
-
-	if (S_ISDIR(inode->i_mode))
-		mask |= FS_ISDIR;
-
-	if (!(file->f_mode & FMODE_NONOTIFY))
-		fsnotify_path(inode, path, mask);
+	fsnotify_file(file, FS_ACCESS);
 }
 
 /*
@@ -245,15 +254,7 @@ static inline void fsnotify_access(struct file *file)
  */
 static inline void fsnotify_modify(struct file *file)
 {
-	const struct path *path = &file->f_path;
-	struct inode *inode = file_inode(file);
-	__u32 mask = FS_MODIFY;
-
-	if (S_ISDIR(inode->i_mode))
-		mask |= FS_ISDIR;
-
-	if (!(file->f_mode & FMODE_NONOTIFY))
-		fsnotify_path(inode, path, mask);
+	fsnotify_file(file, FS_MODIFY);
 }
 
 /*
@@ -261,16 +262,12 @@ static inline void fsnotify_modify(struct file *file)
  */
 static inline void fsnotify_open(struct file *file)
 {
-	const struct path *path = &file->f_path;
-	struct inode *inode = file_inode(file);
 	__u32 mask = FS_OPEN;
 
-	if (S_ISDIR(inode->i_mode))
-		mask |= FS_ISDIR;
 	if (file->f_flags & __FMODE_EXEC)
 		mask |= FS_OPEN_EXEC;
 
-	fsnotify_path(inode, path, mask);
+	fsnotify_file(file, mask);
 }
 
 /*
@@ -278,16 +275,10 @@ static inline void fsnotify_open(struct file *file)
  */
 static inline void fsnotify_close(struct file *file)
 {
-	const struct path *path = &file->f_path;
-	struct inode *inode = file_inode(file);
-	fmode_t mode = file->f_mode;
-	__u32 mask = (mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE;
+	__u32 mask = (file->f_mode & FMODE_WRITE) ? FS_CLOSE_WRITE :
+						    FS_CLOSE_NOWRITE;
 
-	if (S_ISDIR(inode->i_mode))
-		mask |= FS_ISDIR;
-
-	if (!(file->f_mode & FMODE_NONOTIFY))
-		fsnotify_path(inode, path, mask);
+	fsnotify_file(file, mask);
 }
 
 /*
@@ -295,14 +286,7 @@ static inline void fsnotify_close(struct file *file)
  */
 static inline void fsnotify_xattr(struct dentry *dentry)
 {
-	struct inode *inode = dentry->d_inode;
-	__u32 mask = FS_ATTRIB;
-
-	if (S_ISDIR(inode->i_mode))
-		mask |= FS_ISDIR;
-
-	fsnotify_parent(NULL, dentry, mask);
-	fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+	fsnotify_dentry(dentry, FS_ATTRIB);
 }
 
 /*
@@ -311,7 +295,6 @@ static inline void fsnotify_xattr(struct dentry *dentry)
  */
 static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 {
-	struct inode *inode = dentry->d_inode;
 	__u32 mask = 0;
 
 	if (ia_valid & ATTR_UID)
@@ -332,13 +315,8 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 	if (ia_valid & ATTR_MODE)
 		mask |= FS_ATTRIB;
 
-	if (mask) {
-		if (S_ISDIR(inode->i_mode))
-			mask |= FS_ISDIR;
-
-		fsnotify_parent(NULL, dentry, mask);
-		fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
-	}
+	if (mask)
+		fsnotify_dentry(dentry, mask);
 }
 
 #endif	/* _LINUX_FS_NOTIFY_H */

include/linux/fsnotify_backend.h

@@ -47,18 +47,18 @@
 #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	/* Directory entry was modified */
 
 #define FS_EXCL_UNLINK		0x04000000	/* do not send events if object is unlinked */
-#define FS_ISDIR		0x40000000	/* event occurred against dir */
-#define FS_IN_ONESHOT		0x80000000	/* only send event once */
-
-#define FS_DN_RENAME		0x10000000	/* file renamed */
-#define FS_DN_MULTISHOT		0x20000000	/* dnotify multishot */
-
 /* This inode cares about things that happen to its children.  Always set for
  * dnotify and inotify. */
 #define FS_EVENT_ON_CHILD	0x08000000
 
+#define FS_DN_RENAME		0x10000000	/* file renamed */
+#define FS_DN_MULTISHOT		0x20000000	/* dnotify multishot */
+#define FS_ISDIR		0x40000000	/* event occurred against dir */
+#define FS_IN_ONESHOT		0x80000000	/* only send event once */
+
 #define FS_MOVE			(FS_MOVED_FROM | FS_MOVED_TO)
 
 /*
@@ -67,7 +67,8 @@
  * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event
  * when a directory entry inside a child subdir changes.
  */
-#define ALL_FSNOTIFY_DIRENT_EVENTS	(FS_CREATE | FS_DELETE | FS_MOVE)
+#define ALL_FSNOTIFY_DIRENT_EVENTS	(FS_CREATE | FS_DELETE | FS_MOVE | \
+					 FS_DIR_MODIFY)
 
 #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \
 				  FS_OPEN_EXEC_PERM)
@@ -133,8 +134,7 @@ struct fsnotify_ops {
  */
 struct fsnotify_event {
 	struct list_head list;
-	/* inode may ONLY be dereferenced during handle_event(). */
-	struct inode *inode;	/* either the inode the event happened to or its parent */
+	unsigned long objectid;	/* identifier for queue merges */
 };
 
 /*
@@ -213,10 +213,36 @@ struct fsnotify_group {
 	};
 };
 
-/* when calling fsnotify tell it if the data is a path or inode */
-#define FSNOTIFY_EVENT_NONE	0
-#define FSNOTIFY_EVENT_PATH	1
-#define FSNOTIFY_EVENT_INODE	2
+/* When calling fsnotify tell it if the data is a path or inode */
+enum fsnotify_data_type {
+	FSNOTIFY_EVENT_NONE,
+	FSNOTIFY_EVENT_PATH,
+	FSNOTIFY_EVENT_INODE,
+};
+
+static inline const struct inode *fsnotify_data_inode(const void *data,
+						      int data_type)
+{
+	switch (data_type) {
+	case FSNOTIFY_EVENT_INODE:
+		return data;
+	case FSNOTIFY_EVENT_PATH:
+		return d_inode(((const struct path *)data)->dentry);
+	default:
+		return NULL;
+	}
+}
+
+static inline const struct path *fsnotify_data_path(const void *data,
+						    int data_type)
+{
+	switch (data_type) {
+	case FSNOTIFY_EVENT_PATH:
+		return data;
+	default:
+		return NULL;
+	}
+}
 
 enum fsnotify_obj_type {
 	FSNOTIFY_OBJ_TYPE_INODE,
@@ -351,9 +377,10 @@ struct fsnotify_mark {
 /* called from the vfs helpers */
 
 /* main fsnotify call to send events */
-extern int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
-		    const struct qstr *name, u32 cookie);
-extern int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask);
+extern int fsnotify(struct inode *to_tell, __u32 mask, const void *data,
+		    int data_type, const struct qstr *name, u32 cookie);
+extern int fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
+			   int data_type);
 extern void __fsnotify_inode_delete(struct inode *inode);
 extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt);
 extern void fsnotify_sb_delete(struct super_block *sb);
@@ -500,21 +527,22 @@ extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info);
 extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info);
 
 static inline void fsnotify_init_event(struct fsnotify_event *event,
-				       struct inode *inode)
+				       unsigned long objectid)
 {
 	INIT_LIST_HEAD(&event->list);
-	event->inode = inode;
+	event->objectid = objectid;
 }
 
 #else
 
-static inline int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
-			   const struct qstr *name, u32 cookie)
+static inline int fsnotify(struct inode *to_tell, __u32 mask, const void *data,
+			   int data_type, const struct qstr *name, u32 cookie)
 {
 	return 0;
 }
 
-static inline int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask)
+static inline int fsnotify_parent(struct dentry *dentry, __u32 mask,
+				  const void *data, int data_type)
 {
 	return 0;
 }

include/uapi/linux/fanotify.h

@@ -24,10 +24,11 @@
 #define FAN_OPEN_PERM		0x00010000	/* File open in perm check */
 #define FAN_ACCESS_PERM		0x00020000	/* File accessed in perm check */
 #define FAN_OPEN_EXEC_PERM	0x00040000	/* File open/exec in perm check */
+#define FAN_DIR_MODIFY		0x00080000	/* Directory entry was modified */
 
-#define FAN_ONDIR		0x40000000	/* event occurred against dir */
+#define FAN_EVENT_ON_CHILD	0x08000000	/* Interested in child events */
 
-#define FAN_EVENT_ON_CHILD	0x08000000	/* interested in child events */
+#define FAN_ONDIR		0x40000000	/* Event occurred against dir */
 
 /* helper events */
 #define FAN_CLOSE		(FAN_CLOSE_WRITE | FAN_CLOSE_NOWRITE) /* close */
@@ -116,6 +117,7 @@ struct fanotify_event_metadata {
 };
 
 #define FAN_EVENT_INFO_TYPE_FID		1
+#define FAN_EVENT_INFO_TYPE_DFID_NAME	2
 
 /* Variable length info record following event metadata */
 struct fanotify_event_info_header {
@@ -124,7 +126,12 @@ struct fanotify_event_info_header {
 	__u16 len;
 };
 
-/* Unique file identifier info record */
+/*
+ * Unique file identifier info record. This is used both for
+ * FAN_EVENT_INFO_TYPE_FID records and for FAN_EVENT_INFO_TYPE_DFID_NAME
+ * records. For FAN_EVENT_INFO_TYPE_DFID_NAME there is additionally a null
+ * terminated name immediately after the file handle.
+ */
 struct fanotify_event_info_fid {
 	struct fanotify_event_info_header hdr;
 	__kernel_fsid_t fsid;

kernel/audit_fsnotify.c

@@ -160,23 +160,14 @@ static int audit_mark_handle_event(struct fsnotify_group *group,
 {
 	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
 	struct audit_fsnotify_mark *audit_mark;
-	const struct inode *inode = NULL;
+	const struct inode *inode = fsnotify_data_inode(data, data_type);
 
 	audit_mark = container_of(inode_mark, struct audit_fsnotify_mark, mark);
 
 	BUG_ON(group != audit_fsnotify_group);
 
-	switch (data_type) {
-	case (FSNOTIFY_EVENT_PATH):
-		inode = ((const struct path *)data)->dentry->d_inode;
-		break;
-	case (FSNOTIFY_EVENT_INODE):
-		inode = (const struct inode *)data;
-		break;
-	default:
-		BUG();
+	if (WARN_ON(!inode))
 		return 0;
-	}
 
 	if (mask & (FS_CREATE|FS_MOVED_TO|FS_DELETE|FS_MOVED_FROM)) {
 		if (audit_compare_dname_path(dname, audit_mark->path, AUDIT_NAME_FULL))

kernel/audit_watch.c

@@ -471,25 +471,13 @@ static int audit_watch_handle_event(struct fsnotify_group *group,
 				    struct fsnotify_iter_info *iter_info)
 {
 	struct fsnotify_mark *inode_mark = fsnotify_iter_inode_mark(iter_info);
-	const struct inode *inode;
+	const struct inode *inode = fsnotify_data_inode(data, data_type);
 	struct audit_parent *parent;
 
 	parent = container_of(inode_mark, struct audit_parent, mark);
 
 	BUG_ON(group != audit_watch_group);
-
-	switch (data_type) {
-	case (FSNOTIFY_EVENT_PATH):
-		inode = d_backing_inode(((const struct path *)data)->dentry);
-		break;
-	case (FSNOTIFY_EVENT_INODE):
-		inode = (const struct inode *)data;
-		break;
-	default:
-		BUG();
-		inode = NULL;
-		break;
-	}
+	WARN_ON(!inode);
 
 	if (mask & (FS_CREATE|FS_MOVED_TO) && inode)
 		audit_update_watch(parent, dname, inode->i_sb->s_dev, inode->i_ino, 0);